<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Robohub</title>
	<atom:link href="https://robohub.org/feed/" rel="self" type="application/rss+xml" />
	<link>https://robohub.org</link>
	<description>Connecting the robotics community to the world</description>
	<lastBuildDate>Mon, 16 Nov 2026 11:03:40 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.4</generator>
	<item>
		<title>Robot swarms trained by trial and error in simulation keep working on real robots</title>
		<link>https://robohub.org/robot-swarms-trained-by-trial-and-error-in-simulation-keep-working-on-real-robots/</link>
		
		<dc:creator><![CDATA[IRIDIA]]></dc:creator>
		<pubDate>Tue, 17 Nov 2026 11:00:30 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[swarm]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=224055</guid>

					<description><![CDATA[Reinforcement learning lets robots learn behaviors on their own, through trial and error, usually inside a computer simulation. Moving what they learn onto physical robots is another matter. Simulated and real robots never behave quite the same way, a mismatch known as the “reality gap,” and reinforcement learning has long been particularly sensitive to it. [&#8230;]]]></description>
										<content:encoded><![CDATA[<img fetchpriority="high" decoding="async" class="alignnone wp-image-224059" src="https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-425x283.jpg" alt="" width="923" height="615" srcset="https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-6-2048x1365.jpg 2048w" sizes="(max-width: 923px) 100vw, 923px" />
<p>Reinforcement learning lets robots learn behaviors on their own, through trial and error, usually inside a computer simulation. Moving what they learn onto physical robots is another matter. Simulated and real robots never behave quite the same way, a mismatch known as the “reality gap,” and reinforcement learning has long been particularly sensitive to it. Researchers at IRIDIA, the artificial intelligence laboratory of the Université libre de Bruxelles (ULB), have shown how to get around it for robot swarms: swarms trained with their method in simulation keep performing reliably once they are moved onto real robots.</p>
<p>Teaching a swarm of robots to search for survivors after an earthquake, or to explore a hostile site, entirely inside a computer before risking a real machine sounds like the sensible way to do it. The catch is the reality gap. Friction, sensor noise and mechanical imprecision rarely behave the way they do in a simulation, and skills learned there tend to fall apart when a robot meets the real world.</p>
<p>Ilyes Gharbi, Mauro Birattari and colleagues at IRIDIA (Brussels School of Engineering, ULB) report their results in <a href="https://www.science.org/doi/10.1126/scirobotics.adw4624" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Science Robotics</a>.</p>
<p>Reinforcement learning has become one of the most powerful tools in robotics for producing complex behaviors automatically, and it is behind some of the most striking recent advances in legged locomotion and robotic manipulation. Swarm robotics followed a different path. Its own tradition of modular design methods assembles robot behaviors from predefined building blocks. These methods transfer reliably to real robots, but they rely on slow, costly search procedures. The two lines of research had rarely been compared on solid experimental ground.</p>
<p>The researchers’ idea was to give the robots less freedom in exchange for more reliability. Instead of letting the learning algorithm set each wheel’s speed directly, they had it choose, moment by moment, among a handful of tried-and-tested behaviors: moving toward a light, aggregating with peers, exploring. This restriction keeps the robots from learning to exploit quirks of the simulator that don’t exist in reality. What is left to learn is the part that matters: when to switch from one behavior to another so that the group works together.</p>
<p>“For years we have argued that the reality gap is, at its core, a problem of overfitting: a design method that is too flexible learns the simulator rather than the task,” says Mauro Birattari, who led the research. “Reinforcement learning is very good at finding whatever works in simulation, including tricks that only work there. By limiting what the robots can learn, we leave the algorithm only the decisions that still make sense on a real robot.”</p>
<img decoding="async" class="alignnone wp-image-224073" src="https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-425x283.jpg" alt="" width="930" height="619" srcset="https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/11/swarmACB-5-2048x1365.jpg 2048w" sizes="(max-width: 930px) 100vw, 930px" />
<p>The team tested the approach on a swarm of 20 e-puck robots across five different collective missions, with 250 experiments on the physical robots in total. Swarms trained this way transferred to reality reliably. They substantially outperformed a state-of-the-art method in which the algorithm controls the robots’ motors directly, and which struggled once it left the simulator. The researchers also found that simpler, more constrained policies transferred better than larger, more flexible ones. That goes against a widespread intuition in artificial intelligence, that bigger and more flexible models are generally better.</p>
<p>“What excites me is that this makes reinforcement learning a practical tool for swarm robotics,” says Ilyes Gharbi, first author of the study. “Designing collective behaviors by hand takes experts a lot of time. With this approach, a swarm can be trained in simulation for a new mission and deployed on real robots with confidence that it will behave as expected. The next step is to test it on larger swarms, other robot platforms and less controlled environments.”</p>
<p>The study brings together two research traditions that had developed largely separately: the efficiency of reinforcement learning and the reliability of swarm robotics ’modular methods. Both will be needed before groups of autonomous robots can be trusted with tasks such as search and rescue, environmental monitoring, or exploring places too dangerous for people.</p>
<p>This research was partially supported by the Belgian Fonds de la Recherche Scientifique—FNRS through the PDR project “Reinforcement Learning for Robot Swarms.”</p>
<p><strong>Publication</strong><br />
I. Gharbi, M. Kegeleirs, G. Legarda Herranz, J. Szpirer, K. Hasselmann, M. Birattari, “<a href="https://www.science.org/doi/10.1126/scirobotics.adw4624" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Structural bias enables reliable sim-to-real transfer in reinforcement learning for robot swarms</a>,” <em>Science Robotics</em> (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Watch the IROS 2026 plenary and keynote talks</title>
		<link>https://robohub.org/watch-the-iros-2026-plenary-and-keynote-talks/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Mon, 16 Nov 2026 11:03:40 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=224106</guid>

					<description><![CDATA[The 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) was held in Pittsburgh from 27 September to 1 October. The event brought together researchers and industry professionals with expertise spanning many different aspects of robotics. IEEE have made the keynote and plenary panel recordings available to watch. You can also catch the opening [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426.jpg" alt="" width="900" height="600" class="size-full wp-image-221223" srcset="https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426.jpg 900w, https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" />
<p>The <a href="https://2026.ieee-iros.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</a> was held in Pittsburgh from 27 September to 1 October. The event brought together researchers and industry professionals with expertise spanning many different aspects of robotics. </p>
<p>IEEE have made the keynote and plenary panel recordings <a href="https://ieeetv.ieee.org/event/iros-2026" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">available to watch</a>. You can also catch the opening and awards ceremonies, and the town hall meeting. </p>
<p>Watch IEEE.tv <a href="https://ieeetv.ieee.org/event/iros-2026" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><strong>here</strong></a>. </p>
<p>Available to watch are the following:</p>
<ul>
<li>Plenary panels</li>
<ul>
<li><em>Start-ups and entrepreneurship</em></li>
<li><em>Space</em></li>
<li><em>Should robots be generalists or specialists?</em></li>
</ul>
<li>Keynote talks</li>
<ul>
<li><strong>Elena De Momi</strong> &#8211; <em>Open questions on the road to autonomous surgery</em></li>
<li><strong>Naomi Fitter</strong> &#8211; <em>Socially-informed context awareness for robots in human-populated settings</em></li>
<li><strong>Greg Chirikjian</strong> &#8211; <em>From hyper-redundancy to robot imagination and affordance learning</em></li>
<li><strong>Al Rizzi</strong> &#8211; <em>Developing advanced robot capability at the RAI Institute</em></li>
<li><strong>Gaurav Bansal</strong> &#8211; <em>Building autonomy for the real world</em></li>
<li><strong>Genta Suzuki</strong> &#8211; <em>Fujitsu Kozuchi Physical OS: a research strategy for scalable physical AI</em></li>
<li><strong>Yigit Menguc</strong> &#8211; <em>Soft robotics, tensegrity, and the people who love them</em></li>
<li><strong>Robin Murphy</strong> &#8211; <em>Rethinking disaster robotics: the open questions that matter now</em></li>
<li><strong>Jen Jen Chung</strong> &#8211; <em>All data are equal, but some data are more equal than others</em></li>
<li><strong>Tim Bretl</strong> &#8211; <em>How you can be part of a revolution in composite manufacturing</em></li>
<li><strong>Lael Odhner</strong> &#8211; <em>Big bets in manipulation systems: where is the frontier today?</em></li>
<li><strong>Gina Olson</strong> &#8211; <em>Complexity in soft and bio-inspired robots</em></li>
<li><strong>David Held</strong> &#8211; <em>Robots that learn after deployment: designing policies for fast adaptation</em></li>
<li><strong>Brittany Duncan</strong> &#8211; <em>Patterns from the field: how contextual lessons can inform robot design</em></li>
<li><strong>Ankur Mehta</strong> &#8211; <em>Robotics problems that robotics can’t solve</em></li>
</ul>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 170 &#8211; Robots in the real world, with Daniela Shchegelskaya</title>
		<link>https://robohub.org/robot-talk-episode-170-robots-in-the-real-world-with-daniela-shchegelskaya/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 13 Nov 2026 13:22:49 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=224093</guid>

					<description><![CDATA[Claire chatted to Daniela Shchegelskaya from the University of Twente about getting robots to operate reliably in safety-critical environments. Daniela Shchegelskaya is an electronics and robotics engineer specialising in autonomous systems, control engineering, and Al-driven robotics for industrial and safety-critical environments. She works on deploying real-world autonomous robots beyond lab conditions, focusing on reliability, connectivity, [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-224094" src="https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-425x425.jpg" alt="" width="425" height="425" srcset="https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-425x425.jpg 425w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-290x290.jpg 290w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-768x768.jpg 768w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-24x24.jpg 24w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-48x48.jpg 48w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-96x96.jpg 96w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-150x150.jpg 150w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya-300x300.jpg 300w, https://robohub.org/wp-content/uploads/2026/11/170_Daniela-Shchegelskaya.jpg 1000w" sizes="(max-width: 425px) 100vw, 425px" />
<p>Claire chatted to Daniela Shchegelskaya from the University of Twente about getting robots to operate reliably in safety-critical environments.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43740094/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>
<p>Daniela Shchegelskaya is an electronics and robotics engineer specialising in autonomous systems, control engineering, and Al-driven robotics for industrial and safety-critical environments. She works on deploying real-world autonomous robots beyond lab conditions, focusing on reliability, connectivity, and system-level design. At Elimpus, she works on the integration of Boston Dynamics’ Spot for inspections in live power substations, including autonomous navigation, network connectivity, remote diagnostics, data collection and system-level reliability.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>AI100 report released: embodied AI highlighted as grand challenge</title>
		<link>https://robohub.org/ai100-report-released-embodied-ai-highlighted-as-grand-challenge/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Wed, 11 Nov 2026 13:48:55 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=224068</guid>

					<description><![CDATA[The One Hundred Year Study on Artificial Intelligence (AI100) is a longitudinal study that assesses AI’s development and societal impact. Reports are released once every five years, with the 2026 edition the third in the series. The title of this year&#8217;s report is &#8220;AI Goes Mainstream: The Scaling Era and the Rise of Generative AI&#8221;. [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" src="https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-1024x375.jpg" alt="" width="1024" height="375" class="alignnone size-large wp-image-224070" srcset="https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-1024x375.jpg 1024w, https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-425x156.jpg 425w, https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-768x282.jpg 768w, https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-1536x563.jpg 1536w, https://robohub.org/wp-content/uploads/2026/11/AI100Report_2026_WebGraphic_3000x1100_1-2048x751.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" />
<p>The <a href="https://ai100.stanford.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">One Hundred Year Study on Artificial Intelligence (AI100)</a> is a longitudinal study that assesses AI’s development and societal impact. Reports are released once every five years, with the <a href="https://ai100.stanford.edu/reports/2026-report" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2026 edition</a> the third in the series. The title of this year&#8217;s report is <em>&#8220;AI Goes Mainstream: The Scaling Era and the Rise of Generative AI&#8221;</em>. The panel behind the project is an <a href="https://ai100.stanford.edu/standingcommittee" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">international committee</a> of experts tasked with examining AI’s evolution across technical, ethical, economic, and societal domains. They respond to 12 standing questions about AI’s advances, opportunities, dangers, and societal effects, and compare developments since 2021 with the previous panel’s assessments.</p>
<p>The 2026 AI100 Study Panel report examines the scaling of data and computing resources behind generative AI, advances in scientific discovery, investment in AI infrastructure, the concentration of frontier AI development, cybersecurity and military applications, the trustworthiness of digital media, emerging risks, public participation, and international governance. </p>
<p>One of the standing questions concerns open grand challenges in the field, with the experts highlighting six as particularly inspiring and scientifically important. Most relevant to the robotics community is the problem of <em>physical AI and embodied intelligence</em>. In the five years since the <a href="https://ai100.stanford.edu/gathering-strength-gathering-storms-one-hundred-year-study-artificial-intelligence-ai100-2021-study" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">last AI100 report</a> (published in 2021), we&#8217;ve witnessed integration of natural language processing (NLP) into robotic systems, the use of vision-language-action models for training and control, and advances in simulation technology which have allowed models trained in virtual settings to be deployed on physical hardware. </p>
<p>The 2026 AI100 report notes that China is the leader in industrial robot development, deploying more robots than the rest of the world combined. China also produces about 80% of the world’s humanoid robots. Although this sector currently accounts for just 2% of the market, it is growing rapidly. </p>
<p>Despite the progress of recent years, there remains a huge gap between the demonstration of capabilities and deployment. Many of the success stories have been in highly constrained environments (such as warehouses), or with very specific products (for example, floor cleaners). The key challenge remains the sheer complexity of the real world. Some of the scientific problems to overcome include long-horizon planning under uncertainty, achieving dexterous manipulation of diverse objects, and establishing formal performance guarantees. </p>
<p>Whilst there are some practitioners who believe that the current statistical learning paradigms are sufficient for attacking these open problems, many others feel that fundamentally new ideas will be required to bring robot deployment into genuine real-world scenarios. It will be interesting to observe how this plays out over the next five years. </p>
<p>You can read the report in full <a href="https://ai100.stanford.edu/reports/2026-report" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>AIhub coffee corner: Are humanoids the future of embodied AI?</title>
		<link>https://robohub.org/aihub-coffee-corner-are-humanoids-the-future-of-embodied-ai/</link>
		
		<dc:creator><![CDATA[AIhub]]></dc:creator>
		<pubDate>Mon, 09 Nov 2026 14:21:13 +0000</pubDate>
				<category><![CDATA[opinions]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=21655</guid>

					<description><![CDATA[The AIhub coffee corner captures the musings of AI experts over a short conversation. This month we ask whether humanoids are the future of robotics. How has the technology evolved recently, and what can we expect in the years to come? Joining the conversation this time are: Joydeep Biswas (University of Texas at Austin), Sanmay […]]]></description>
										<content:encoded><![CDATA[<img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2020/02/AIhub-coffee-corner-1.jpg" alt="AIhub coffee corner" width="847" height="612" class="alignnone size-full wp-image-1184" srcset="https://aihub.org/wp-content/uploads/2020/02/AIhub-coffee-corner-1.jpg 847w, https://aihub.org/wp-content/uploads/2020/02/AIhub-coffee-corner-1-300x217.jpg 300w, https://aihub.org/wp-content/uploads/2020/02/AIhub-coffee-corner-1-768x555.jpg 768w" sizes="(max-width: 847px) 100vw, 847px" />
<p>The AIhub coffee corner captures the musings of AI experts over a short conversation. This month we ask whether humanoids are the future of robotics. How has the technology evolved recently, and what can we expect in the years to come? Joining the conversation this time are: Joydeep Biswas (University of Texas at Austin), Sanmay Das (Virginia Tech), Rina Dechter (University of California, Irvine), Ioannis Erripis (AIhub), Sabine Hauert (University of Bristol), Ella Scallan (AIhub), and Marija Slavkovik (University of Bergen).</p>
<p><strong>Lucy Smith:</strong> There have been huge advancements in humanoid robots over the past couple of years. Today’s topic is particularly timely, as <a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a> recently took place. I thought it would be interesting to start with an overview of recent developments at RoboCup.</p>
<p><strong>Joydeep Biswas:</strong> This all started snowballing a couple of years ago, and we suddenly started to see this huge inflection on the capabilities. New humanoid robots were showing up at RoboCup that didn’t fall down as much. Suddenly we were able to deploy robots without humans following them around. I want to highlight that this is not just one key technical innovation, it required the confluence of a wide number of things: much better hardware, significant advances in algorithms, and advances in how we train and learn. Once upon a time, humanoid robots required classical control. However, most modern humanoid robots are using learned controllers for walking. So the rise of doing sim-to-real, like training these models in simulation and transferring them to the real world, are new algorithmic innovations. </p>
<p>This year we had 55 humanoid robot soccer teams at the international competition, which is a lot for an international competition. We had a <a href="https://youtu.be/XuEdf0fMAME?si=7ywZsn1zPY1XHnZb" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">demo game of 11 vs 11 humanoid robots</a>. Every year we have the RoboCup trustees play against the robots to see where we&#8217;re at. It used to be trivial. I won&#8217;t say it was hard this year, but I will say it&#8217;s getting less easy for the trustees as the years go by. </p>
<p>RoboCup has recognized that we are at the inflection point, and at the trustees level we’ve been thinking about how to restructure our competitions to focus on these big advances coming up. We&#8217;ve simplified our soccer leagues significantly &#8211; in 2028, there will only be humanoid league soccer. Once upon a time, we couldn&#8217;t have a fully integrated humanoid robot capable of doing everything. Even though it&#8217;s not perfect today, we have the ability to integrate control, perception etc. We feel that from the scientific perspective, it is worth exploring having everything integrated into one robot form. </p>
<p><strong>Sabine Hauert:</strong> I started out excited about robotics because of RoboCup. I was in Manuela Veloso&#8217;s team doing the aibo (robot dogs) league. And that got me excited about robots working together. And then from there, they went on to the Nao robots and then to the humanoids. I guess this is a way to shake things up and to get it to the next level.</p>
<p>Generally, I think the humanoid shift has been fascinating. And looking at <a href="https://2026.ieee-icra.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ICRA</a> and <a href="https://2026.ieee-iros.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IROS</a>, just the sheer shift in what&#8217;s on that exhibit floor over the years is really quite drastic. It used to be all drones and then it was all robot dogs and now it&#8217;s all hands and humanoids. There are also some of the more industrial robots that have been there for a while. But that shift is very striking because you walk around and there&#8217;s just so many of them. And at the <a href="https://www.youtube.com/shorts/Pc48Ox0j81A" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robot parade</a> you just see all these humanoid form factors and it&#8217;s very exciting from the hardware perspective. In addition there have been beautiful advances in the control to make that hardware and shape form work. I&#8217;m very excited for other robots, actually, not necessarily humanoids, because some of that technology can be transferred. </p>
<p>I don&#8217;t know that we need humanoids for everything. I&#8217;m still very much in the category of people that think we need task-specific robots so that we can build them for the things that they&#8217;re meant to do. Maybe we get a general form factor not through having a human form, but by having lots of different robots with different form factors that work together, giving you the same capabilities as a human, but through multiplication rather than putting everything in one agent. But humanoids are part of the ecosystem, and I think they&#8217;re boosting the field, and so there&#8217;s a lot to gain from that.</p>
<p><strong>Ella Scallan:</strong> Are humanoids the most effective shape to get tasks done? </p>
<p><strong>Joydeep:</strong> No! The argument has been that everyday environments are designed for the human factor. So if you could have a working robot which has a humanoid factor, they could be a drop-in replacement and be able to use the tools and the environments which humans can. There is one big presupposition there: that we have functioning humanoid robots. As of today, that is absolutely not the case. In fact, if you want to have something work well today, there are very few cases where you could argue that the humanoid robot is the best solution. I think being a researcher in this area, it&#8217;s great to actually think a little bit about how we get to that eventual goal. Humanoids are rarely the correct solution for an application. Simple tasks, which are what we would call kinematic planning (for example, they are position-based &#8211; you want to pick up a block and put it somewhere else), are better with a wheeled robot, because the base is stable, and much easier with simpler planners, which have fewer degrees of freedom. You add a humanoid, suddenly the complexity increases. Now you&#8217;re not just worrying about position, you&#8217;re worrying about position and forces and velocities and accelerations which has much higher dimensions for planning. And it&#8217;s just not very easy to do. There are many more reasons too, that&#8217;s just one example.</p>
<p><strong>Marija Slavkovik:</strong> Can I give a historical anecdote here in response to that? A humanoid shape is not necessarily the best thing. Douglas Bader was a pilot in the Royal Air Force in the Second World War. He was considered to be a better pilot because he didn&#8217;t have legs, which he lost in an accident. And because he didn&#8217;t have legs, he was able to better handle high acceleration. There are some pretty horrible examples of children being used because their smaller bodies were better suited to the task, like kid jockeys on camels, children in mines, or in weaving. Of course, these are all examples of people, but their bodies are not what you think about when you say humanoid robot. </p>
<p><strong>Sanmay Das:</strong> I mean, it&#8217;s an interesting set of questions. I was wandering around one of these big conventions recently, and it was all about AI and robotics and very government tech/dev tech-focused. But one of the things they had that people were really interested in was this robot barista. You could ask it to make a coffee and it was going around doing things with the arms, but it wasn&#8217;t producing particularly good coffee from what I could tell. And I was thinking I have a semi-automatic espresso machine that I press a button on that does a really good job of making good coffee. I don&#8217;t see why we need this extremely complicated thing. But at the same time, people like it, right? How much of this is that people are more comfortable engaging with robots in this form? I think that one of the main things that we need to be careful about is anthropomorphization. I think for robotics, especially as they become more and more capable, this is really going to become a question. People will anthropomorphize these humanoid robots in ways that they will not your Roombas and your robot dogs and so on, and do we want that? And I think that that&#8217;s going to be an interesting question to think about.</p>
<p><strong>Ella:</strong> Even creating humanoid robots is an act of anthropromorphization.They aren’t the most effective shape for the task, so we’re sacrificing some function for form. </p>
<p><strong>Marija:</strong> Speaking of what we want, I&#8217;ve seen videos of  robots that roll into a bathroom and clean it. They use the same brush for the toilet and the sink, but that&#8217;s a separate problem. My question is: how realistic are these? Because they&#8217;re just promotional videos: <em>“invest now, and in one year, these are going to be real”</em>. I even see some folding laundry, which is the holy grail, right? Robotics wise, are we there yet?</p>
<p><strong>Joydeep:</strong> I think you bring up an excellent point, which is truth in advertising. We are definitely seeing a lot of new capabilities that we didn&#8217;t have before, but we have to be honest about what they are and are not capable of. For many actors, it is in their best interests to promote the best of their platforms and hide the worst just because of the financial incentives. If you think a little bit about what went into setting up the demo, how many takes did it actually take you to do it? How over engineered was it for that very specific scenario? It worked with a particular brush,  what if I gave it a slightly different brush? What if the light was turned off and it was on? And I can tell you the answer here is that none of these solutions are really robust. They&#8217;re definitely not general purpose. The best advancements are definitely over-optimized to very specific scenarios. Also the ways in which they&#8217;re being trained are just not scalable for doing the wider broad set of things that we want to do. So I think as a community, we need to demand and require truth in advertising. And the downside of this huge influx of companies in the space is that the incentives for scientific advancement are not necessarily well aligned with the advancement of companies today.</p>
<p><strong>Sabine:</strong> I think there&#8217;s a sense that people think it&#8217;s been done because they&#8217;ve seen it in a video, when a lot of it is either remote controlled or very fine-tuned for the scenarios that they&#8217;ve been designed for, as Joydeep mentions. There isn&#8217;t a “get your humanoid out-of-the-box and have it doing something useful in an environment it&#8217;s never seen before” because the data&#8217;s not there, it&#8217;s not been trained there.</p>
<p><strong>Joydeep:</strong> Yes. Even for a wheeled robot, we don&#8217;t have that capability.</p>
<p><strong>Rina Dechter:</strong> Thinking about one use case, robotics for social interaction with humans, for example if you wanted healthcare assistance or similar, psychologically it might give a better impression if you were assisted by a humanoid than a box. It may make a difference to people. But in other cases I agree, the best form for the robot depends on the tasks.</p>
<p><strong>Joydeep:</strong> I 100% agree. I think also it&#8217;s the challenge of the latest capabilities of our current research algorithms, because behind the capabilities that we&#8217;re seeing today are things like reinforcement learning and learning from demonstration. This is great for non-human interactive stuff like manipulating objects, but it doesn&#8217;t really scale well to human interaction. You can&#8217;t collect a very large number of demonstrations of a robot interacting with a person because there&#8217;s no one person. Everybody is different. And you can&#8217;t simulate a human realistically either. So the capabilities that we are using to bring these advances are just not very good for the human interaction capability that we need for the important problems.</p>
<p><strong>Sabine:</strong> At the Bristol Robotics Laboratory we have the assistive living research facility and there are all these robots that are beautiful for human-robot interaction. So probably there&#8217;s a nice space for the humanoid form in those caring settings as long as they&#8217;re not deceiving in the way that we worry about from an ethical perspective. You also expect more from your humanoid in terms of its capabilities somehow because of its human shape. So somehow the cartoony ones that weren&#8217;t that capable were maybe better for those settings, also safer. I&#8217;ve seen so many videos of these humanoids toppling over in crowds. </p>
<p><strong>Rina:</strong> What I found really impressive was when robots started to talk using LLMs. It really was amazing. And this is because it&#8217;s more going towards the human. It has moved from just writing text to generating it and voicing it. I think it’s easier to be influenced and believe something that’s a human-like object. </p>
<p><strong>Marija:</strong> I wonder how much of this humanoid obsession comes from science fiction&#8217;s original picturing of humanoid robots? That sets the shape of the robot and the term robot. So everything is already pre-biased to be in that shape. It makes for a better story. Whereas if it is some kind of a box that does something, you have to do a lot of explaining as to what the robot is and what it does. I remember watching the Roomba clean the floor for the first time, and it was a very annoying experience  because it&#8217;s not doing the things the way you would have done them. </p>
<p><strong>Sabine:</strong> Also, because AI has had such advances with LLMs, I think people just see humanoids as the next obvious thing that will definitely happen. This is now seen as the normal form factor for a more general form of intelligence. And so there&#8217;s this obviousness to it. In some discussions, people have really been pushing me for an answer on when humanoids are going to work the way we expect. And I don’t know. RoboCup has an answer for that, right, because they have an aim to get them playing at human level against the trustees.</p>
<p><strong>Joydeep:</strong> Well, I won&#8217;t say Robocup has an answer. Robocup has a challenge to defeat the human world champions by 2050. That&#8217;s more an open conjecture. You raised an important point that not everybody in the general public is aware of. There&#8217;s an equivocation of the capabilities needed. People see the capabilities of chatbots and you think that a robot picking up a laptop is trivial. But that&#8217;s because they&#8217;re equivocating what is hard as a human to what is hard for a robot, but it&#8217;s absolutely not true. In fact, doing the so-called very high-level planning in some sense can be easier for a robot than interacting with the embodied world. This is Moravec&#8217;s paradox. Lots of roboticists have spoken about this, but I think there&#8217;s a gap in the public perception of what is easy versus hard and the disconnect between what is easy and hard for a human versus what&#8217;s easy and hard for a robot.</p>
<p><strong>Sabine:</strong> And there&#8217;s also just the data. We had buckets of data for language that we don&#8217;t have in the physical world.</p>
<p><strong>Joydeep:</strong> We don&#8217;t have the internet of physical interactions.</p>
<p><strong>Marija:</strong> Well, we now have people being paid to do manual movements that are supposed to be somehow used for training afterwards.</p>
<p><strong>Joydeep:</strong> Yeah, so there&#8217;s a huge effort right now across so many companies spending so many millions to billions of dollars on what&#8217;s called teleoperation. And that is a human controlling a robot to do a task because that data can be used to train a robot. And yes, it is true, it is useful data, but there&#8217;s a divide even in the robotics community. There are some people who believe this is all you need &#8211; you just need to scale up. There are other people, like me, who don&#8217;t buy the argument that more teleoperation data is going to get us to general purpose robots. And I think the reason for that is rather simple. It&#8217;s that the complexity of the tasks that we want to do has combinatorial explosion. And we&#8217;re never going to have that level of demonstrations. And the other thing here is that we&#8217;ve seen this craze before with self-driving cars. If you think back, in 2014, maybe a little bit earlier, a common narrative among self-driving companies was that we just needed to go out and build HD maps of our environment and that&#8217;s all we needed. Like driving would be solved. Guess what? It didn&#8217;t turn out to be the case. This current craze about collecting data and mimicking humans feels very similar to that era. That&#8217;s not to say it wasn&#8217;t useful. But I don&#8217;t think that alone is going to solve the problem.</p>
<p><strong>Marija:</strong> I agree with you as a non-expert in this, because humans do things the way humans do them, and machines do them the way machines do them. Birds fly, airplanes fly, but not in the same way. Again, with my non-able body examples, people without legs don&#8217;t “walk” like people with legs, right?</p>
<p><strong>Sabine:</strong> One reason the humanoid form might make a lot of sense in robotics from the data perspective is human video. There&#8217;s loads of human video. And I&#8217;m guessing the reason for that is they collect the data from the humans rather than have them teleoperate a robotic system. And then things need to have a similar physical frame for those videos of humans then to translate to the capabilities of the robots. We recently did tests with VLMs [vision-language models] and it was harder to use that data that&#8217;s already available in these trained models because data is human-centric, and our robots are not in humanoid form. </p>
<p><strong>Joydeep:</strong> I think what you said is absolutely true. We have a ton of videos on YouTube of humans doing tasks. The mismatch of course is the data; the way that data was collected was using very different sensors than what robots would have. So there is a mismatch there beyond the mismatch of the embodiment. But many of us agree that that data is useful.</p>
<p><strong>Ella:</strong> If the solution to get general purpose robots isn&#8217;t more data, do we need to wait for better AI and better learning methods?  </p>
<p><strong>Joydeep:</strong> All the time. I mean, there&#8217;s one thing that&#8217;s clear. I think many of us believe that experience from interaction is crucial. You don&#8217;t learn just by mimicking what someone else did. You learn by getting some initial understanding based on seeing what other people did, but then trying it out and gaining intuition. And this is true for learning algorithms as well. If the expert shows you how to do a thing, and if you can do exactly what the expert did, you&#8217;ll be good. But invariably what happens is that if you try to do exactly what the expert did, you make one mistake and suddenly you&#8217;re in a state which you did not have in the expert demonstration. Now what do you do? You don&#8217;t have any training data for that, right? So this is why experience is useful and important.</p>
<p><strong>Rina:</strong> From a causality perspective, the language we use is that there is observational data and interventional data. Causality cannot be gleaned just from observation, you have to interact in order to see what&#8217;s going on.</p>
<p><strong>Joydeep:</strong> Yeah. I think interaction is the best way to exploit some of the behaviors that Marija was talking about, like getting behaviors optimized to the form and functionality that you have.</p>
<p><strong>Sabine:</strong> I do worry though about this idea that now we need better robots or better AI to complete useful tasks. We were so close to getting our robots that were simple working really well, with enough computation on board, good sensing, that they were useful in lots of different ways. And now somehow we&#8217;ve moved the goalposts towards robots that are maybe not as green, not as easy to verify and test etc because they&#8217;re in a more complex form factor. And so I worry that we&#8217;re going to keep moving the goalposts instead of benefiting from all the stuff that already works in the robotics field and trying to get that out into applications. And the fundraising kind of shows that: the humanoids are raising and it&#8217;s harder to raise if you&#8217;re not in this next wave of humanoids or physical AI. We need to make sure it doesn&#8217;t end up being the only way forward.</p>
<p><strong>Joydeep:</strong> In a talk I give I have a slide about this. I talk about the open challenges for robots and say that you need the following to have a successful mobile robot: a sufficiently detailed map of the world, an accurate predefined notion of action costs, a well-defined task objective, a curated list of entities of interest, no surprises, and enough onboard sensing and compute. This is a very large caveat list, but in settings such as manufacturing and logistics, these can all be achieved. But the moment you take any of these caveats out, suddenly you&#8217;re in the research landscape. And that&#8217;s kind of where we&#8217;re at.</p>
<p><strong>Sabine:</strong> The other thing I heard is that people are calling everything humanoids, so the word has taken over. It&#8217;s got a lot of excitement, it&#8217;s helping to raise funds. And then you&#8217;ll have a wheeled humanoid, or a humanoid with six arms, for example. And there will all be forms of humanoids. So it&#8217;ll go full circle back to the different form factors.</p>
<p><strong>Marija:</strong> If you think about it, a computer playing chess does little for solving general AI tasks.  But it acted as a catalyst to attract attention, funding and resources so that they can be used to actually develop deep learning and so on. So maybe it works out in the end. You create this magic for people to believe in and invest in, and something else comes out of it. Although I&#8217;m not going to say I&#8217;m advocating this, it&#8217;s definitely borderline fraud sometimes, these videos of depicted abilities. It&#8217;s just easier to sell, right?</p>
<p>That was the trick, Sabine, that whenever somebody asks you when we are going to see useful or capable humanoids, you can ask them what they mean by useful or capable. Because then you turn around the question. People understand that we already have very many useful and capable things.</p>
<p><strong>Sabine:</strong> Yeah, so they were asking when the breakthrough was going to be. I say the breakthrough is when we see all those robots that work in everyday environments, not necessarily humanoid, and all the things we&#8217;re pushing research-wise out in the world. And I think that&#8217;s the breakthrough.</p>
<p><strong>Joydeep:</strong> I think even before ChatGPT was released December 2022, and folks who were playing with these large language models, GPT 2, 3, etc, we were seeing capabilities which were very hard to do beforehand. What really made it break through in the public consciousness was having a public-facing website &#8211; that was an inflection point. I doubt that for the robotic space we&#8217;re going to see a similar inflection point where suddenly we&#8217;re able to see generational new capabilities. I think we&#8217;re probably going to see slow adoption of robots in limited capabilities and specific scenarios, increasingly more and more and more. It&#8217;s just going to be a very slow adoption. We&#8217;re not going to suddenly have a robot capable of doing it all. </p>
<p><strong>Marija:</strong> If any of you see a robot that folds laundry or irons laundry, wake me up in the middle of the night. To me, that&#8217;s the breakthrough point. If I see one of them, I don&#8217;t care how much it costs.</p>
<p><strong>Joydeep:</strong> Well, again, the question is, under what conditions? If you are okay with a few hours to fold your laundry and specific kinds of laundry.</p>
<p><strong>Marija:</strong> It can take as much time as it wants, let&#8217;s make it one week maximum. But no caveats. You have to take it out of the dryer and fold it in a neat stack, unspecified laundry. I mean, think about it. Would you care how long it takes as long as it&#8217;s done? How long does it take me, the lazy human to do it? Three days it&#8217;s going to live in the dryer until I get to it.</p>
<p><strong>Joydeep:</strong> Yeah, so the challenges here are robustness. So you said it should not matter what the laundry is, and you want a certain degree of accuracy. You don&#8217;t want that every fifth attempt, it makes a catastrophic failure, and then you have to go rescue the robot. Now, not only do you have to do your laundry on your own, you also have to rescue the robot. I think as humans we have very high expectations for autonomy, which we don&#8217;t explicitly mention, which is fine, but I think that&#8217;s the challenge. In research papers, we say that an 80% success rate is phenomenal. No, 80% success rate as a product is awful. It&#8217;s a failure. Or even 99%, it&#8217;s still not good enough.</p>
<p><strong>Ioannis Erripis:</strong> I have two small questions. Firstly, I&#8217;ve seen recently at least three companies that are advertising household humanoid robots. What do you think about those?</p>
<p><strong>Sabine:</strong> The remote controlled ones.</p>
<p><strong>Joydeep:</strong> Yeah, there&#8217;s certainly not anything which can do all household tasks autonomously. They&#8217;re actually using you for data collection. </p>
<p><strong>Sabine:</strong> There&#8217;s a company in San Francisco that will pay you to do your household cleaning, because they collect data from your house.</p>
<p><strong>Ioannis:</strong> My second question is more maybe superficial. What do you think about the design of most of the humanoid robots? And let me rephrase this a bit more specifically. One of my favourite robots was maybe Honda&#8217;s ASIMO, which looked like an astronaut toy. If you see behind the glass, it is smiling and has a very cute face. It&#8217;s a robot that you would easily give as a gift to your child, for example. But almost all humanoid robots are very menacing. They almost look like a villain from a movie. And actually, at the same time, they aspire to be adopted by consumers. What do you think about this? To me, it looks like a very unorthodox approach.</p>
<p><strong>Joydeep:</strong> I think you&#8217;re absolutely right, but there are companies which are trying to build humanoid robots which are human approachable. Fauna Robotics is one of them. They are very much leaning into exactly what you&#8217;re saying.</p>
<p><strong>Ioannis:</strong> I guess that&#8217;s an exception.</p>
<p><strong>Joydeep:</strong> I agree it&#8217;s an exception, and I think partly that is because the capabilities that we&#8217;re really missing today are these fine-grained motor skills. People are trying to think about whether we can just build a form and understand how we can solve these fine-grained motor skills, and then we&#8217;ll talk about the interaction. But you&#8217;re absolutely right that we should think about them jointly.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 169 &#8211; Robot sensing inspired by nature, with Dexter Shepherd</title>
		<link>https://robohub.org/robot-talk-episode-169-robot-sensing-inspired-by-nature-with-dexter-shepherd/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 06 Nov 2026 13:39:37 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223990</guid>

					<description><![CDATA[Claire chatted to Dexter Shepherd from the University of Sussex about using artificial intelligence to help robots understand and adapt to their environment. Dexter Shepherd is a Postdoctoral Researcher at the University of Sussex, exploring machine learning for bio-inspired tactile sensing and robotic locomotion. His work combines embedded AI systems, spatial-temporal models, and reinforcement learning [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-223992" src="https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd-425x319.jpg" alt="" width="850" height="638" srcset="https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd-425x319.jpg 425w, https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd-1024x768.jpg 1024w, https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd-768x576.jpg 768w, https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd-1536x1152.jpg 1536w, https://robohub.org/wp-content/uploads/2026/11/Dexter-Shepherd.jpg 2000w" sizes="(max-width: 850px) 100vw, 850px" />
<p>Claire chatted to Dexter Shepherd from the University of Sussex about using artificial intelligence to help robots understand and adapt to their environment.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43658209/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>
<p><a href="https://shepai.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Dexter Shepherd</a> is a Postdoctoral Researcher at the University of Sussex, exploring machine learning for bio-inspired tactile sensing and robotic locomotion. His work combines embedded AI systems, spatial-temporal models, and reinforcement learning to enable robots to classify textures, orient themselves, and adapt their movements. Beyond his research, Dexter leads and coordinates AI training initiatives in Africa with making electronics and applying AI on embedded devices.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robots in society, business and culture: October 2026</title>
		<link>https://robohub.org/robots-in-society-business-and-culture-october-2026/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 04 Nov 2026 11:51:57 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223976</guid>

					<description><![CDATA[The biohybrid robot pushes off from the ground as soon as it is stimulated by an electrical impulse. Credit: Nature Communications (2026). By Emmet Cole In our monthly series, we showcase a selection of robotics stories from society, business, research and culture, as we track the field’s ongoing journey from specialized industrial machines to an [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg.webp" alt="" width="604" height="300" class="alignnone size-full wp-image-223977" srcset="https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg.webp 604w, https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg-425x211.webp 425w" sizes="(max-width: 604px) 100vw, 604px" /><em>The biohybrid robot pushes off from the ground as soon as it is stimulated by an electrical impulse. Credit: <a href="https://www.nature.com/articles/s41467-026-77655-1" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Nature Communications</a> (2026).</em></p>
<p><strong>By Emmet Cole</strong></p>
<p><em>In our monthly series, we showcase a selection of robotics stories from society, business, research and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon.</em></p>
<hr>
<h4>People perceive robots approaching from behind as faster</h4>
<p>A Toyohashi University of Technology team tested <a href="https://doi.org/10.1109/LRA.2026.3732839" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">whether a robot’s approach direction changes how fast it seems to move</a>. Across five experiments using a real mobile robot and virtual reality, 92% of participants showed the same bias: at the same physical speed, a robot approaching from behind seemed faster than one approaching from the front.</p>
<p>In the first experiment, participants learned two reference speeds—0.5 and 1.0 metres per second—then judged a robot approaching at speeds between those values. Follow-up experiments suggested the effect wasn’t explained by the robot’s appearance or motor noise. The researchers link it instead to visual factors involved in turning to look at something coming from behind.</p>
<p>The researchers say further work is needed to see how the bias affects comfort, perceived safety, and people’s actual avoidance behaviour.</p>
<h4>Monocular drone racer</h4>
<p>Engineers at <a href="https://www.tudelft.nl/en/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Delft University of Technology</a> have developed <a href="https://www.science.org/doi/10.1126/scirobotics.aee9250" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">an AI system</a> that enables a racing drone to navigate demanding courses at extreme speed using only a single camera, while outperforming human drone champions in the process. The team’s <a href="https://www.tudelft.nl/en/2026/tu-delft/the-science-behind-worlds-fastest-autonomous-racing-drone" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MonoRace</a> autonomous drone system generalizes to a competition environment without any external motion tracking system, using only a monocular rolling-shutter camera and an inertial measurement unit.</p>
<div class="keep-aspect"><iframe title="MonoRace: Robust monocular AI for champion-level drone racing" width="500" height="281" src="https://www.youtube-nocookie.com/embed/E0R_ugLAKL8?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Researchers at ETH Zurich <a href="https://ethz.ch/en/news-and-events/eth-news/news/2026/10/one-small-leap-for-a-muscle-one-giant-step-for-robotics.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">designed lab-grown mouse muscle tissue</a> and its soft hydrogel scaffold together, using computer simulations to find arrangements that turn muscle contractions into larger movements. The resulting bioactuators, each about 1.5 centimetres long, powered small prototypes that could jump, swim, walk and grasp. The team reports up to 11 times more range of motion than earlier systems using a comparable amount of muscle tissue.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg.webp" alt="" width="604" height="300" class="alignnone size-full wp-image-223977" srcset="https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg.webp 604w, https://robohub.org/wp-content/uploads/2026/11/Picture1.jpg-425x211.webp 425w" sizes="(max-width: 604px) 100vw, 604px" /><em>The biohybrid robot pushes off from the ground as soon as it is stimulated by an electrical impulse. Credit: <a href="https://www.nature.com/articles/s41467-026-77655-1" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Nature Communications</a> (2026).</em></p>
<p>Meanwhile, another team at ETH Zurich <a href="https://leggedrobotics.github.io/rubik-skills/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">demonstrated</a> a quadruped robot that can <a href="https://arxiv.org/pdf/2610.24610" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">autonomously solve a giant Rubik’s Cube</a> using its feet. One foot pins the cube while the other turns its layers; the robot also flips and repositions the cube while keeping its balance. In tests, it completed three autonomous solves of a 4.6-kilogram cube, each taking about 30 steps and eight to nine minutes.</p>
<p>The ability to coordinate perception, balance and repeated precise contact to manipulate a free-standing object could improve design of robots that need to handle objects without hands or in situations where their legs are their only available tools.</p>
<div class="keep-aspect"><iframe title="Solving a Giant Rubik&amp;apos;s Cube with a Quadruped Robot" width="500" height="281" src="https://www.youtube-nocookie.com/embed/ZTboM3JACMc?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<h4>RobCo hits a billion</h4>
<p>German industrial robot startup <a href="https://www.reuters.com/legal/transactional/german-robot-startup-robco-hits-1-billion-valuation-ceo-moves-us-2026-10-05/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RobCo hit a USD1 billion valuation</a> in October following the sale of USD40 million of shares. The company plans to launch Alfie, a two-armed, self-learning robot ⁠designed ​to handle industrial tasks in March 2027.</p>
<p>Meanwhile, GXO Logistics, Inc. and Agility Robotics, announced <a href="https://www.agilityrobotics.com/content/gxo-and-agility-robotics-expand-partnership-to-accelerate-deployment-of-humanoids-in-u-s-operations" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">an expansion of their partnership</a> to advance humanoid automation in logistics with deployments of Agility’s Digit humanoid robot to GXO sites in North Carolina and Tennessee. (<a href="https://www.ieee-ras.org/commercializing-robotics-damion-shelton-agility-robotics-and-carnegie-mellon-university/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">We spoke with Damion Shelton recently</a> as part of our commercialization series)</p>
<p><a href="https://idw-online.de/de/news879575" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">TUM RoboGym</a>, an advanced training and research center for embodied artificial intelligence, opened in October. The result of a collaboration between the Munich Institute of Robotics and Machine Intelligence (TUM MIRMI) at the Technical University of Munich (TUM) and NEURA Robotics, TUM RoboGym will initially see around 100 humanoid and service robots learn specific skills and processes in 48 training cells.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/11/Picture2.png.webp" alt="" width="604" height="400" class="alignnone size-full wp-image-223978" srcset="https://robohub.org/wp-content/uploads/2026/11/Picture2.png.webp 604w, https://robohub.org/wp-content/uploads/2026/11/Picture2.png-425x281.webp 425w" sizes="(max-width: 604px) 100vw, 604px" /><em>Credit: Andreas Heddergott / TUM</em></p>
<p>Elsewhere, Teradyne Robotics –the company behind Universal Robots and  Mobile Industrial Robots- <a href="https://www.universal-robots.com/news-and-media/news-center/teradyne-robotics-and-sereact-partner-to-scale-physical-ai-solutions-for-retail-and-logistics" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">announced a partnership</a> with physical AI company Sereact, to accelerate industrial AI solutions in retail, logistics and manufacturing. Sereact’s physical AI platform Cortex is trained in NVIDIA Isaac Sim using NVIDIA Cosmos open world models. It is then post-trained with reinforcement learning and benchmarked on Teradyne Robotics hardware before deployment.</p>
<h4>Kwon Byungjun’s <em>I Embrace You</em></h4>
<p>At Seoul’s <a href="https://sema.seoul.go.kr/en/whatson/exhibition/detail?exNo=1540505" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Buk-Seoul Museum of Art</a>, the artist Kwon Byungjun uses wobbling humanoid robots and sound to explore how we respond to people who feel like strangers. The exhibition draws on the arrival of Yemeni refugees on Jeju Island in 2017 as imperfect robots struggle to move, yet keep reaching out, opening their arms to offer visitors a hug. Their performances combine movement and sounds from lullabies, nature and AI, asking how different beings might find ways to live alongside each other.</p>
<p>The exhibition runs until 16 May 2027.</p>
<div class="keep-aspect"><iframe title="Seoul Museum of Art | 어린이⁺ 전시 《권병준: 내 마음속에 너는》 작가 인터뷰" width="500" height="281" src="https://www.youtube-nocookie.com/embed/e6AHEyFUCb4?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Muscle coordination can be mimicked by electric motors – it could lead to improved robots</title>
		<link>https://robohub.org/muscle-coordination-can-be-mimicked-by-electric-motors-it-could-lead-to-improved-robots/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Mon, 02 Nov 2026 13:55:16 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">http://robohub.org/?guid=5131d9f9b75385cd04ef532b18664da5</guid>

					<description><![CDATA[Coordination appears to emerge spontaneously from muscle fibres.]]></description>
										<content:encoded><![CDATA[<img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-10-01-at-17.55.32-1024x608.jpeg" alt="" width="1024" height="608" class="alignnone size-large wp-image-221566" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-10-01-at-17.55.32-1024x608.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-10-01-at-17.55.32-425x253.jpeg 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-10-01-at-17.55.32-768x456.jpeg 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-10-01-at-17.55.32.jpeg 1296w" sizes="(max-width: 1024px) 100vw, 1024px" />
<p><strong>By <a href="https://theconversation.com/profiles/hermes-bloomfield-gadelha-706231" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Hermes Bloomfield-Gadêlha</a>, <em><a href="https://theconversation.com/institutions/university-of-bristol-1211" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Bristol</a></em></strong></p>
<p>People often take their muscles for granted. They pick up a bag, tighten a grip, climb a hill, hold a cup of coffee and the body quietly adjusts force, speed and position without the person ever thinking about it.</p>
<p>Muscle turns <a href="https://www.britannica.com/science/skeletal-muscle" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">chemical energy into movement</a>. It is able to produce force smoothly and reliably, even though it is built from huge numbers of tiny molecular components. When the load changes, <a href="https://theconversation.com/topics/muscles-3083" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">muscles</a> don’t simply wobble or fail. They adapt.</p>
<p>But the way that muscle works on a molecular level isn’t a settled issue. With colleagues, our team at the University of Bristol built a physical model using ordinary electric motors to try and simulate how muscles may perform its tasks. </p>
<p>The results, published in <a href="https://royalsocietypublishing.org/rsif/article/23/236/20250438/480965/A-discontinuously-coupled-network-of-phase" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">the Royal Society journal Interface</a>, show that the coordination we see in real muscle may simply emerge as a property of their setup. It’s not something you have to programme and police continuously. The findings could even help improve the way that robots function.</p>
<p>If we were to zoom inside a muscle, we would find bundles of smaller and smaller structures. The <a href="https://www.britannica.com/science/sarcomere" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sarcomere</a> is the key force producing unit. It is made of protein filaments, called <a href="https://www.britannica.com/science/actin" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">actin</a>, and molecular motors called <a href="https://www.britannica.com/science/myosin" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">myosin</a>. Together, they form the <a href="https://www.britannica.com/science/actomyosin" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">actomyosin</a> system. </p>
<p>Tiny myosin motors repeatedly grab, pull and release actin cables, helping muscle fibres contract. When you hold a cup of tea, thousands of these motors have to work together to produce a steady force. But there are unanswered questions about this system.</p>
<p><figure class="align-center ">
            <img decoding="async" alt="" src="https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=217&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=217&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=217&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=273&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=273&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/745239/original/file-20260630-71-d6gzel.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=273&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"><em>Illustration showing the smallest functional unit of muscle: the sarcomere.</em><br />
          </figure>
</p>
<p>We first devised a mathematical model of muscle. Real muscle motors (myosin) run on a complex chemical cycle, but we didn’t try to reproduce that chemistry. Instead, we represented each force producing unit as something much simpler: a cycling “rotor” (or motor) that can contribute only when it is mechanically engaged to a physical “backbone”. When it is disengaged, it effectively drops out, and becomes isolated from the rest.</p>
<p>To test whether we could translate these ideas to a real physical system, we built a tabletop device: a line of simple electric motors interacting through a shared mechanical backbone. They pulled against a thick fluid, creating resistance similar to the viscous load experienced by biological motors inside muscle.</p>
<p><figure class="align-center ">
            <img decoding="async" alt="" src="https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=474&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=474&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=474&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=596&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=596&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/745231/original/file-20260630-57-arz7yr.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=596&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"><em>An illustration of the artificial muscle unit used in <a href="https://doi.org/10.1098/rsif.2025.0438" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">the study</a>.</em></figure>
</p>
<p>Our physical model produces force when supplied with current. We wanted to see whether, when many driving units were embedded in the right kind of mechanical setting, could the setting organise into coordinated muscle-like behaviour?</p>
<p>In both the mathematical model and the device, the motors don’t stay connected all the time. Instead, each motor briefly makes contact with a shared moving backbone, pushes on it, then lets go. As the backbone moves, it carries the mechanical effects of one motor to the next, allowing them to coordinate without ever communicating directly.</p>
<p>When they are not connected, each motor acts on its own. That single design choice makes the whole network of motors reorganise itself over time – much like biological motors do inside muscle, where motors attach and detach as part of their biochemical cycles. </p>
<p>In practical terms, the scaffold where the rotors live is doing a lot of the coordinating work, but it is hidden. It mediates how units can “feel” one another strongly enough for collective patterns to form. </p>
<div class="keep-aspect"><iframe title="How simple motors can mimic real muscles" width="500" height="281" src="https://www.youtube-nocookie.com/embed/OpHmxYp0Rg0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Even in this stripped-down system, several muscle-like forms of behaviour spontaneously appear. As resistance increases, the motors collectively develop a load-speed relationship. Load refers to the mechanical tension and physical stress placed on the system.</p>
<p>More units end up contributing effectively as the load rises. Their participation increases under increasing loads. We also found that under certain conditions, motion can become jerky. For example, periods of coordinated pulling were interrupted by sudden slips. This echoes patterns seen in real actomyosin experiments. </p>
<p>Instead of everything working in unison, the system can self-organise into travelling waves of coordination, where the pattern moves along the array.</p>
<p>In a loose way, this “scales up” the core idea behind a sarcomere: many force units embedded in a shared structure that transmits forces from one unit to the next, allowing coordination to emerge spontaneously.</p>
<h2>Coordinating without a conductor</h2>
<p>Muscle isn’t the only place where nature has solved the problem of coordinating many tiny motors. Microscopic flagella are tail-like appendages seen on the cells of some <a href="https://www.britannica.com/science/eukaryote" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">eukaryotes</a> – the group of organisms that includes animals and plants. </p>
<p>Examples of these flagella include the tail on human <a href="https://www.britannica.com/science/sperm" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sperm</a>. Cilia are microscopic, hair-like structures on many eukaryotic cells. Both flagella and cilia are powered by large numbers of molecular motors distributed along a long, slender scaffold. </p>
<div class="keep-aspect"><iframe title="Virtual human sperm swimming in high viscosity fluid" width="500" height="281" src="https://www.youtube-nocookie.com/embed/5lwAcXZ47fM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<em>Bending waves caused by motor contraction in sperm swimming.</em></p>
<p>Their internal core – the <a href="https://www.nature.com/articles/s41467-023-40338-2" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">axoneme</a> – is a beautifully organised structure that transmits forces along its length and turns local motor activity into bending waves. Those waves are essential: in sperm they underpin motility and fertility,  and in cilia they help move fluids in the airways and other tissues, with clear links to health and disease. </p>
<p>In that sense, flagella are “muscle-like” systems in disguise. You again have drivers (motors that generate force) embedded in a coupling structure (a mechanical scaffold that transmits force and feedback). And the geometry determines how local activity adds up to a coherent, travelling wave.</p>
<p>If the structure and layout are doing some of the organising work, it speaks to a question that has long intrigued scientists: how evolution builds systems made up of a large number of individual motors that nevertheless coordinate themselves, remain reliable and adapt to changing conditions without a central control system? </p>
<h2>Uses in robotics</h2>
<p>Our results matter beyond biology. In robotics, getting many actuators (the “muscles” of a robot, which convert an energy source like electricity into motion) to cooperate is challenging and expensive. You add sensors, feedback loops, control algorithms, sometimes even mechanical ratchets or complex gearing to keep everything stable under loads. It works, but it can be fragile and prone to errors. </p>
<div class="keep-aspect"><iframe title="Watch: Boston Dynamic&amp;apos;s Atlas robot fail compilation" width="500" height="281" src="https://www.youtube-nocookie.com/embed/aX7KypGlitg?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<em>A compilation of task failures by Boston Dynamics’ Atlas robot (The Independent).</em></p>
<p>Our physical model of muscle, where coordination emerges as a property of the setup, suggests that simpler actuators for robotics are possible. This is exactly the kind of fundamental design that researchers have been chasing for <a href="https://www.nature.com/collections/wpsbvwhdyh" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">soft robots</a> (which use flexible materials) and artificial muscles for robotics.</p>
<p>Muscle may be an example of coordination without a conductor. Thousands of molecular motors working together, not because each one is individually controlled, but because the soft structure around them helps guide their collective behaviour. </p>
<p>Our findings suggest that robotics could begin to harness the same principle. In future, this could help bring robotics closer to biology, opening the way to more organic machines, whose bodies help shape how they move and adapt.<!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding="async" src="https://counter.theconversation.com/content/278728/count.gif?distributor=republish-lightbox-basic" alt="The Conversation" width="1" height="1" style="border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important" referrerpolicy="no-referrer-when-downgrade" /><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https://theconversation.com/republishing-guidelines --></p>
<p><span><a href="https://theconversation.com/profiles/hermes-bloomfield-gadelha-706231" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Hermes Bloomfield-Gadêlha</a>, Mathematician, <em><a href="https://theconversation.com/institutions/university-of-bristol-1211" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Bristol</a></em></span></p>
<p>This article is republished from <a href="https://theconversation.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Conversation</a> under a Creative Commons license. Read the <a href="https://theconversation.com/muscle-coordination-can-be-mimicked-by-electric-motors-it-could-lead-to-improved-robots-278728" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">original article</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 168 &#8211; Advancing robotics with novel electronics, with Zlatka Stoeva</title>
		<link>https://robohub.org/robot-talk-episode-168-advancing-robotics-with-novel-electronics-with-zlatka-stoeva/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 30 Oct 2026 13:33:53 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223896</guid>

					<description><![CDATA[Claire chatted to Zlatka Stoeva from DZP Technologies about flexible, stretchable and soft printed electronics for dexterous robots. Zlatka Stoeva is a founder and managing director of DZP Technologies, a Cambridge-based company specialising in advanced materials and novel forms of electronics. Zlatka’s background is in materials chemistry, and she developed the innovative electronic materials which [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-223897" src="https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva-425x239.jpg" alt="" width="425" height="239" srcset="https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva-1024x576.jpg 1024w, https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva-768x432.jpg 768w, https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva-1536x864.jpg 1536w, https://robohub.org/wp-content/uploads/2026/10/Zlatka-Stoeva.jpg 1920w" sizes="(max-width: 425px) 100vw, 425px" />
<p>Claire chatted to Zlatka Stoeva from DZP Technologies about flexible, stretchable and soft printed electronics for dexterous robots.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43447264/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>
<p>Zlatka Stoeva is a founder and managing director of <a href="https://www.dzptechnologies.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">DZP Technologies</a>, a Cambridge-based company specialising in advanced materials and novel forms of electronics. Zlatka’s background is in materials chemistry, and she developed the innovative electronic materials which set the foundation for the company current portfolio of flexible, stretchable and soft electronics. DZP Technologies ventured into robotics during an ARIA-funded project, focused on printed electronics components for the dexterous robot.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Competing in RoboCup@Home and winning the 2026 best paper award: an interview with Raphael Memmesheimer</title>
		<link>https://robohub.org/competing-in-robocuphome-and-winning-the-2026-best-paper-award-an-interview-with-raphael-memmesheimer/</link>
		
		<dc:creator><![CDATA[AIhub]]></dc:creator>
		<pubDate>Wed, 28 Oct 2026 09:07:21 +0000</pubDate>
				<category><![CDATA[opinions]]></category>
		<category><![CDATA[household]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=21589</guid>

					<description><![CDATA[Team NimbRo’s robot in action during the RoboCup@Home competition at RoboCup 2026. Raphael leads the team. Raphael Memmesheimer has been successfully competing in the RoboCup@Home league winning the RoboCup@Home competition five times. He and his colleagues won the best paper award at RoboCup 2026 for their work “Efficient Image Annotation via Semi-Supervised Object Segmentation with […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-scaled.jpg" alt="" width="2560" height="2135" class="alignnone size-full wp-image-21599" srcset="https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-300x250.jpg 300w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-1024x854.jpg 1024w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-768x640.jpg 768w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-1536x1281.jpg 1536w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Grasping_2-2048x1708.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /><em>Team NimbRo&#8217;s robot in action during the RoboCup@Home competition at RoboCup 2026. Raphael leads the team.</em></p>
<p>Raphael Memmesheimer has been successfully competing in the RoboCup@Home league winning the RoboCup@Home competition five times. He and his colleagues won the best paper award at RoboCup 2026 for their work <a href="https://arxiv.org/abs/2604.22992" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation”</a>. We caught up with Raphael to find out more about this research, his history with RoboCup, and the challenges of the @Home competition.</p>
<h4>Could you start by telling us how you got involved with RoboCup@Home?</h4>
<p>I&#8217;ve actually been involved in the @Home league since I was a student, and my first time going to a World Cup for @Home was in 2013. That competition motivated me to do a PhD and infected me in a way that meant I basically aligned my academic career to it. I always return to robot competitions because this is one of the rare places where you can benchmark robots in a real environment and have a real competition. Commonly in research you tune your approaches on data sets and show that they perform in a one-shot video. In robot competitions, you basically have to roll out your robot, it enters the arena, and then it operates autonomously on its own. It is always interesting to see how new developments make the robots perform better.  </p>
<h4>You and your co-authors won the best paper award at the RoboCup symposium this year. Congratulations! Could you give us a quick introduction to the paper?</h4>
<p>The motivation for this work is that we only have two preparation days at the RoboCup competitions. So we arrive there, we have to assemble our robots, and the robots need to get used to the new environment [a model apartment] that we haven&#8217;t seen before. Also, the robots don&#8217;t have a clue about anything in this apartment. And within the two preparation days, the robots need to learn the objects they are interacting with. For example, they have to recognise what a spoon is, or a specific drink. </p>
<p>Our paper basically supports us in very efficiently generating this data such that the robots can more quickly learn models for the objects that are involved in this competition. And the interesting thing is it&#8217;s not just a few objects that we can distinguish between; there can be up to 50 different objects that we haven&#8217;t seen before. Our approach basically optimizes the process so that we can quickly get a good vision model for the robot. We are aware of open-vocabulary approaches but found them to have issues distinguishing between objects of a category like drinks.</p>
<img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-scaled.jpg" alt="" width="2560" height="1826" class="alignnone size-full wp-image-21594" srcset="https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-300x214.jpg 300w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-1024x730.jpg 1024w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-768x548.jpg 768w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-1536x1096.jpg 1536w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Best_Paper_Award-2048x1461.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" />
<h4>Is it possible to do some pre-training to anticipate objects that might be used in the competition?</h4>
<p>Partially that&#8217;s possible, but most objects cannot really be anticipated. We know that there are drinks, there are snacks, that there are cutlery items in the apartment. But what cannot be anticipated is the details because objects come from different areas in the world. The organisers will usually go to a shopping mall and just get local groceries there. Those objects are then distributed in the apartment. Part of the object set comes from the publicly available <a href="https://www.ycbbenchmarks.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">YCB Dataset</a>, for those we can gather data beforehand, and of course pre-training with large general object sets.</p>
<h4>Could you talk about your methodology?</h4>
<p>We use a multi-stage approach. Firstly, we segment, such that we learn what an object actually is on a segmentation level. We look at all the objects that robots saw in the past editions of these competitions, and we train one model that just says, <em>“oh, there is something which might be an object”</em>. And then we get reference images of the actual objects and we semi-supervised or semi-automatically label those objects. The idea is that we combine identifying something as an object with a reference of what could actually be there. That allows us to simplify the labeling approach. Around 60% of the data is automatically labeled based on our approach. That would take a lot of hours by human annotation.</p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/labelled-images.jpeg" alt="" width="1486" height="392" class="alignnone size-full wp-image-21597" srcset="https://aihub.org/wp-content/uploads/2026/10/labelled-images.jpeg 1486w, https://aihub.org/wp-content/uploads/2026/10/labelled-images-300x79.jpeg 300w, https://aihub.org/wp-content/uploads/2026/10/labelled-images-1024x270.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/10/labelled-images-768x203.jpeg 768w" sizes="(max-width: 1486px) 100vw, 1486px" /><em>Labeled example images from different competition venues. Figure from <a href="https://arxiv.org/abs/2604.22992" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation”</a>.</em></p>
<h4>Have you been able to use the method already in RoboCup competitions?</h4>
<p>Yes, we used it in Brazil for RoboCup 2025 and at RoboCup GermanOpen for the local RoboCup competitions. The method is continuously evolving. Now that we have this very good vision model, it means that we save a lot of time during the two preparation days and we can concentrate more on testing and achieving the actual tasks instead of just focusing on the vision element. One side note: nowadays there are promptable object detection or segmentation methods, but we found that they don&#8217;t scale yet to the number of classes that are involved in this competition. They work fine with 5 to 10 different classes, but we had issues distinguishing all 50 classes just by prompting them. </p>
<p>In this year’s World Cup (in Korea) we used an evolved approach where we used videos to generate even more data. </p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-scaled.jpg" alt="" width="2560" height="2407" class="alignnone size-full wp-image-21600" srcset="https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-300x282.jpg 300w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-1024x963.jpg 1024w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-768x722.jpg 768w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-1536x1444.jpg 1536w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-2048x1925.jpg 2048w, https://aihub.org/wp-content/uploads/2026/10/2026_07_04_RoboCup_Home_NimbRo_Picking_Laundry-24x24.jpg 24w" sizes="(max-width: 2560px) 100vw, 2560px" /><em>Team NimbRo&#8217;s robot picking laundry from the washing machine.</em></p>
<h4>How did your team get on in the competition this time? </h4>
<p>It went well. We had issues, as always during competitions, but we ended up in 3rd place. There was a new “Doing Laundry” task introduced this year. The robot had to carry a laundry basket from a washing machine to a folding table and open the washing machine. It had to detect the washing machine door, then find the specific point to grasp the handle to open the machine door. Then it had to pull out t-shirts and fold them.</p>
<p>Our robot performed the best in this task. It was able to open the washing machine and start folding the laundry. And this was possible because we used these semi-automatic labeling approaches. </p>
<div class="keep-aspect"><iframe title="[2026] RoboCup@Home NimbRo Doing Laundry Challenge" width="500" height="281" src="https://www.youtube-nocookie.com/embed/wZRlQrzK4Cw?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<h4>What were the other tasks that teams needed to carry out?</h4>
<p>The first big hurdle at the competition is to make the robot pass the initial inspection. Robots must satisfy certain safety and interactive capabilities and if they fail they are not allowed to take part in the competition. </p>
<p>In the competition itself there are five main tasks. </p>
<p>One is human-robot interaction. The robots have to open the door for party guests and greet them. Here, the robot has to go to the door, find the handle, align the end-effector to the handle, open the door, let the human enter, speak with the guest while holding eye-contact, guide them to the living room, find them a free seat, and introduce this guest to any other guests. This process continues on repeat as long as there are new guests arriving. </p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-scaled.jpg" alt="" width="2499" height="2560" class="alignnone size-full wp-image-21601" srcset="https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-scaled.jpg 2499w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-293x300.jpg 293w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-1000x1024.jpg 1000w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-768x787.jpg 768w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-1500x1536.jpg 1500w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-1999x2048.jpg 1999w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-24x24.jpg 24w, https://aihub.org/wp-content/uploads/2026/10/2026_07_03_RoboCup_Home_NimbRo_Opening_Door-48x48.jpg 48w" sizes="(max-width: 2499px) 100vw, 2499px" /><em>Team NimbRo&#8217;s robot opening the door.</em></p>
<p>Another task is a pick and place task, and this time we had to clear a table after breakfast. So the robot had to bring the cutlery to the dishwasher, put a dishwasher tablet into the dishwasher, close the dishwasher, and then prepare the table ready for the next meal. That&#8217;s a very manipulation intensive task. </p>
<p>There is also a general-purpose service robot task. This task is undefined because the robot has to deal with a random natural language command that can incorporate all elements of the apartment. For example it might be asked to go and fetch a particular drink or snack and hand it to someone. In the past there were people from the audience called into the arena and asked to give a command. It&#8217;s interesting to see how good these robots are at interacting with a new person and not someone they are used to receiving commands from. </p>
<p>Another interesting task is the restaurant task. Here, the robots are not in the known environment that we trained them in for two days, instead they are taken to an unknown restaurant location. The robot is placed there and needs to serve naturally. Only the menu is known to the teams in advance. The robots need to scan the restaurant to autonomously operate and find waving customers. The order is then given by voice, and usually these restaurant environments are very noisy. This is a very interesting task for the audience because it&#8217;s in the wild and people gather around it to watch it. </p>
<p>Then, of course, there’s the new laundry task that I described above. To add to what I said before, this is a very hard task because the robot cannot see into the washing machine. So it has to feel if it has a T-shirt in its hand and take the t-shirt out of the machine. Then the robot has to go to a table and start folding other t-shirts. </p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-scaled.jpg" alt="" width="2560" height="1624" class="alignnone size-full wp-image-21602" srcset="https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-300x190.jpg 300w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-1024x650.jpg 1024w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-768x487.jpg 768w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-1536x974.jpg 1536w, https://aihub.org/wp-content/uploads/2026/10/2026_07_05_RoboCup_Home_Team_NimbRo-2048x1299.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /><em>Team NimbRo</em></p>
<h4>Interesting. I was at RoboCup in Eindhoven and I found the @Home competition fascinating.</h4>
<p>We actually won the competition that year! </p>
<p>The league was more divided then, with three different leagues: two standard platforms and an open platform league. It was the open platform league that we won.</p>
<p>Now, all of those leagues have been merged. This year there were 24 teams from all over the world participating in just one league, which is amazing. It also drives competition a lot.</p>
<h4>How much of an improvement have you seen over the years that you&#8217;ve been doing RoboCup@Home?</h4>
<p>There are always phases of improvement, as I would describe them. I started pre-deep learning, and there were no vision robust models for seeing objects in unknown environments. What was working well was mapping and navigation. When I started in the league, the robots were already talking, but often, instead of talking to a human like they were supposed to, they might talk to a potted plant or a coat hanger because they had a shape similar to a human. This is no longer the case &#8211; nowadays we perceive humans quite well. We can also recognize speech quite well. Task planning is still a challenge, but it has improved. Then there are things that appear and push the boundaries, such as large language models, open vocabulary approaches and, most recently, agentic systems. But every now and then there&#8217;s stagnation because teams are just overwhelmed by the wide amount of different challenges that this competition throws at you. Basically your robot has to do everything. It needs to navigate in an apartment, it needs to be able to interact with humans, it has to manipulate items, and it has to do task planning. And all of those are very intensive research areas that are challenging in themselves. In addition the implementations must be very robust, as there are only a few trials.</p>
<h4>How are you and the team planning to improve the robot for the next competition?</h4>
<p>We are working on improving manipulation capabilities so that the robot can more quickly pick various objects. We are also continuously testing our robots&#8217; performance to make our robots more human-like, and using two arms for manipulation is something we want to improve. </p>
<h4>About Raphael</h4>
<table border="0" width="100%" cellspacing="0" cellpadding="10">
<tbody>
<tr>
<td align="left" valign="top" width="150">
<img decoding="async" src="https://aihub.org/wp-content/uploads/2026/10/Raphael.jpeg" alt="" width="792" height="1030" class="alignnone size-full wp-image-21590" srcset="https://aihub.org/wp-content/uploads/2026/10/Raphael.jpeg 792w, https://aihub.org/wp-content/uploads/2026/10/Raphael-231x300.jpeg 231w, https://aihub.org/wp-content/uploads/2026/10/Raphael-787x1024.jpeg 787w, https://aihub.org/wp-content/uploads/2026/10/Raphael-768x999.jpeg 768w" sizes="(max-width: 792px) 100vw, 792px" />
</td>
<td align="left" valign="top">
<p>Raphael Memmesheimer’s long-term research goal is to develop autonomous service robots that assist people in everyday environments: robots that perceive, understand, and learn from human behavior using multi-modal sensory information and that prove themselves outside the lab. He is currently a postdoctoral researcher with the Autonomous Intelligent Systems (AIS) group at the University of Bonn, where he re-established and leads the domestic service robot team NimbRo@Home. He is also a founding member of the Center for Robotics at the University of Bonn.</p>
<p>Raphael Memmesheimer has extensive experience in benchmark robotics competitions, having led teams at two universities to multiple international titles. Notably, he has won the RoboCup@Home World Championship five times (including three consecutive titles), along with multiple victories at the RoboCup German Open and top placements in the European Robotics League and the World Robot Summit.</p>
</td>
</tr>
</tbody>
</table>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robots in society, business and culture: September 2026</title>
		<link>https://robohub.org/robots-in-society-business-and-culture-september-2026/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Mon, 26 Oct 2026 10:17:34 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223866</guid>

					<description><![CDATA[A walking robotic hand, from Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand, Amirhossein Kazemipour, Hehui Zheng, Robert Katzschmann. By Emmet Cole In our monthly series, we showcase a selection of robotics stories from society, business, research and culture, as we track the field’s ongoing journey from specialized industrial machines to [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/10/robot_hand-1024x797.jpeg" alt="" width="1024" height="797" class="alignnone size-large wp-image-223870" srcset="https://robohub.org/wp-content/uploads/2026/10/robot_hand-1024x797.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/10/robot_hand-425x331.jpeg 425w, https://robohub.org/wp-content/uploads/2026/10/robot_hand-768x597.jpeg 768w, https://robohub.org/wp-content/uploads/2026/10/robot_hand.jpeg 1054w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>A walking robotic hand, from <a href="https://arxiv.org/abs/2609.17172" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand</a>, Amirhossein Kazemipour, Hehui Zheng, Robert Katzschmann.</em></p>
<p><strong>By Emmet Cole</strong></p>
<p><em>In our monthly series, we showcase a selection of robotics stories from society, business, research and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon.</em></p>
<hr>
<h4>Five million and counting</h4>
<p>More than five million industrial robots are now operating in factories worldwide, according to the International Federation of Robotics’ newly released <a href="https://ifr.org/ifr-press-releases/news/five-million-robots-now-operate-in-factories-globally" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">World Robotics 2026 report</a>.</p>
<p>Factories installed more than 600,000 industrial robots during 2025, an increase of 11% on the previous year. The global operational stock grew by 9%.</p>
<p>China continued to pull away from the rest of the world. Its factories installed 354,000 robots, accounting for 59% of the global total. Chinese manufacturers supplied 55% of their domestic market.</p>
<p>The United States overtook Japan to become the world’s second-largest market, with almost 38,500 installations. India installed nearly 10,500 robots, an increase of 15%. Europe moved in the opposite direction: installations fell by 8% in Germany, 11% in Italy, 8% in France and 15% in Spain.</p>
<p>IFR forecasts that worldwide installations will reach 655,000 units in 2026 and 806,000 in 2029.</p>
<div class="keep-aspect"><iframe title="FACTS about INDUSTRIAL ROBOTS  - World Robotics 2026 Report" width="500" height="281" src="https://www.youtube-nocookie.com/embed/LxJzrm5mDH4?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Separately, Toyota told investors that modernizing factories operated by the company, its group businesses and major suppliers could require around <a href="https://www.reuters.com/business/autos-transportation/toyota-estimates-factory-automation-could-cost-64-billion-per-year-2028-2026-09-18/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">400,000 robots</a>. The estimate includes replacement machines, new industrial robots, automated logistics systems and possible future humanoid deployments. Toyota said the programme could cost ¥1 trillion, or approximately $6.4 billion, annually from 2028, although it has not made a firm spending commitment.</p>
<p>Elsewhere, Universal Robots used the IMTS trade show in Chicago to launch <a href="https://www.universal-robots.com/news-and-media/news-center/universal-robots-unveils-gen-7-new-platform-industrial-automation-physical-ai/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Gen 7</a>, a redesigned cobot platform built around greater computing power, tool-flange connectivity, sensor integration and support for AI-assisted applications.</p>
<h4>The hands behind the robots</h4>
<p>In Rajasthan, India, women are being paid to record household activities from cameras worn on their heads, according to an investigation by <a href="https://www.decodeinternet.in/labour/the-women-training-humanoid-robots-from-their-kitchens-in-rajasthan-32178" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Decode</a>. Their footage captures everyday tasks such as cooking, cleaning and folding clothes from the worker’s point of view.</p>
<p>The recordings can be divided into individual actions and used to teach robots how people manipulate objects in real homes. This kind of data is especially valuable because household environments contain clutter, variation and improvised behaviour that are difficult to reproduce in a robotics laboratory.</p>
<p>Decode estimates that between 20,000 and 30,000 people may be doing this work in India, although that figure is an extrapolation rather than an official count. The article also stops short of establishing which robot companies ultimately receive the featured workers’ recordings.</p>
<h4>Lethal autonomous robots</h4>
<p>International efforts to regulate autonomous weapons reached a significant point in September. Three years of discussions by the United Nations Group of Governmental Experts ended with growing support for formal negotiations on new international rules.</p>
<p><a href="https://www.hrw.org/news/2026/09/07/un-talks-on-killer-robots-ends-with-calls-for-negotiations-growing" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Human Rights Watch</a> says 76 states now support negotiations on legally binding measures governing autonomous weapons systems. However, the group’s final report was weakened during negotiations. References to ethical concerns and to the design and development of the weapons were among the passages removed or reduced following objections from states including Russia and the United States.</p>
<p>The issue will now move to the Convention on Certain Conventional Weapons Review Conference in November, where states may decide whether to establish a negotiating mandate.</p>
<p>The <a href="https://www.stopkillerrobots.org/news/nothing-less-than-negotiations/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Stop Killer Robots campaign</a> argues that further discussion is no longer enough and that states should begin negotiating prohibitions and regulations.</p>
<p>Computer scientist Stuart Russell also entered the debate in a short <a href="https://news.berkeley.edu/2026/09/03/watch-uc-berkeley-professor-calls-for-a-halt-to-ai-weapons/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">UC Berkeley video</a>. Russell called for a ban on small autonomous anti-personnel weapons, warning that machines capable of selecting and attacking people could become cheap, scalable weapons of mass destruction.</p>
<div class="keep-aspect"><iframe title="Autonomous weapons explained in 101 seconds | 101 in 101: AI Weapons" width="500" height="281" src="https://www.youtube-nocookie.com/embed/FN82b_T_74c?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>His intervention is more specific than a call to prohibit every military application of AI. It focuses on systems that can independently identify human targets and apply lethal force at scale.</p>
<h4>Does the robot play fair?</h4>
<p>A study published in the <em>International Journal of Human–Computer Interaction</em> examined whether perceptions of fairness can reduce conflict between people and security robots.</p>
<p>Xin Ye and Lionel Robert considered two forms of fairness. <a href="https://www.tandfonline.com/doi/full/10.1080/10447318.2026.2723654" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Distributive fairness</a> concerns whether the robot’s decision or its consequences appear fair. Informational fairness concerns whether the robot provides an adequate explanation for that decision.</p>
<p>The researchers found that both can help reduce conflict and improve acceptance. The broader implication is that security robots may need to justify their actions as well as perform their assigned tasks effectively.</p>
<p>The results come from controlled human–robot interaction research, so they should not be treated as evidence from robots exercising authority in operational policing environments. Nevertheless, the study raises a question that will become more pressing as autonomous systems move into security roles: what does it mean for a machine’s exercise of authority to be regarded as legitimate?</p>
<h4>Give us a hand</h4>
<p>Finally, researchers at ETH Zurich have taught an anthropomorphic robotic hand to <a href="https://arxiv.org/abs/2609.17172" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">walk on its fingertips</a>.</p>
<p>The self-contained hand uses reinforcement-learning policies to crawl, steer and recover after falling. It can also support its own weight while pressing successive keyboard commands, and it can push an object towards targets using overhead visual feedback.</p>
<div class="keep-aspect"><iframe title="This Robotic Hand Walks on Its Fingertips" width="500" height="281" src="https://www.youtube-nocookie.com/embed/93BLyBPAfYs?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The work is currently an eight-page arXiv preprint, and separate policies are used for different tasks. Even so, it offers an inventive demonstration of a robot repurposing the same hardware for movement, balance and manipulation.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 167 &#8211; Automating construction, with Jan Petrš</title>
		<link>https://robohub.org/robot-talk-episode-167-automating-construction-with-jan-petrs/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 23 Oct 2026 11:43:25 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223861</guid>

					<description><![CDATA[Claire chatted to Jan Petrš from École Polytechnique Fédérale de Lausanne (EPFL) and Déploya Robotics about novel robot designs for construction and architecture. Jan Petrš is a roboticist, architect, and entrepreneur working at the intersection of robotics and construction. He is currently the co-founder of Déploya Robotics, an EPFL spin-off developing deployable robotic systems for [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-223863" src="https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-403x425.jpg" alt="" width="403" height="425" srcset="https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-403x425.jpg 403w, https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-972x1024.jpg 972w, https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-768x809.jpg 768w, https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-1458x1536.jpg 1458w, https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-1944x2048.jpg 1944w, https://robohub.org/wp-content/uploads/2026/10/Jan-Petrs_preferred-24x24.jpg 24w" sizes="(max-width: 403px) 100vw, 403px" />
<p>Claire chatted to Jan Petrš from École Polytechnique Fédérale de Lausanne (EPFL) and Déploya Robotics about novel robot designs for construction and architecture.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43406219/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>
<p>Jan Petrš is a roboticist, architect, and entrepreneur working at the intersection of robotics and construction. He is currently the co-founder of <a href="https://deploya.ch/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Déploya Robotics</a>, an EPFL spin-off developing deployable robotic systems for automated façade installation. Previously, he was a Postdoctoral Researcher at EPFL’s Laboratory of Intelligent Systems, where he focused on tensegrity robotics. His PhD research at the Czech Technical University focused on developing a robotic system combining reconfigurable and soft robotics for architectural and construction applications.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>ACM SIGAI Autonomous Agents Award 2027 open for nominations</title>
		<link>https://robohub.org/acm-sigai-autonomous-agents-award-2027-open-for-nominations/</link>
		
		<dc:creator><![CDATA[ACM SIGAI]]></dc:creator>
		<pubDate>Tue, 20 Oct 2026 10:37:56 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=21562</guid>

					<description><![CDATA[Nominations are solicited for the 2027 ACM SIGAI Autonomous Agents Research Award. This award is made for excellence in research in the area of autonomous agents. It is intended to recognize researchers in autonomous agents whose current work is an important influence on the field. The award is an official ACM award, funded by an […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" class="alignnone size-full wp-image-9893" src="https://aihub.org/wp-content/uploads/2022/07/acmsigai-logo.png" alt="ACM SIGAI logo" width="906" height="509" srcset="https://aihub.org/wp-content/uploads/2022/07/acmsigai-logo.png 906w, https://aihub.org/wp-content/uploads/2022/07/acmsigai-logo-300x169.png 300w, https://aihub.org/wp-content/uploads/2022/07/acmsigai-logo-768x431.png 768w" sizes="(max-width: 906px) 100vw, 906px" /><br />
Nominations are solicited for the 2027 <a href="https://sigai.acm.org/main/autonomous-agents-research-award/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ACM SIGAI Autonomous Agents Research Award</a>. This award is made for excellence in research in the area of autonomous agents. It is intended to recognize researchers in autonomous agents whose current work is an important influence on the field. The award is an official ACM award, funded by an endowment created by ACM SIGAI from the proceeds of previous Autonomous Agents conferences. The recipient of the award will receive a monetary prize and a certificate, and will be invited to present a plenary talk at the AAMAS 2027 conference.</p>
<h4>How to nominate</h4>
<p>Anyone can make a nomination. Nominations should be made by filling out this <a href="https://forms.gle/NGC1tC2nqUWpanMB6" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">google form</a>, and should consist of a short (&lt; 1 page) statement that emphasizes not only the research contributions that the individual has made that merit the award but also how the individual’s current work is an important influence on the field.</p>
<p>Note: a candidate can only be considered for the award if they are explicitly nominated. If you believe that someone deserves the award, then nominate them &#8211; don&#8217;t assume that somebody else will!</p>
<p>Nomination link is <a href="https://forms.gle/NGC1tC2nqUWpanMB6" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<h4>Important Dates</h4>
<p>5 December 2026 &#8211; Deadline for nominations<br />
1 February 2027 &#8211; Announcement of winner<br />
3-7 May 2027 &#8211; AAMAS-2027 conference in Hanoi, Vietnam</p>
<p>For any questions please contact <a href="mailto:svenk@uci.edu">Sven Koenig</a> (Award Chair) or <a href="mailto:louise.dennis@manchester.ac.uk">Louise Dennis</a> (SIGAI Vice Chair).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Powered by muscle cells, a paper-thin robot swims through watery maze</title>
		<link>https://robohub.org/powered-by-muscle-cells-a-paper-thin-robot-swims-through-watery-maze/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Mon, 19 Oct 2026 07:07:59 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://news.mit.edu/2026/powered-by-muscle-cells-paper-thin-robot-swims-through-watery-maze-0929</guid>

					<description><![CDATA[MIT engineers’ new aquabot offers a way to design small, efficient “biohybrid” robots.]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-01-press_0.jpg" alt="" width="900" height="599" class="alignnone size-full wp-image-221537" srcset="https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-01-press_0.jpg 900w, https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-01-press_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-01-press_0-768x511.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /><em>MIT engineers developed a soft robot that can flap through water in response to flashes of light. Photo credit: Melanie Gonick, MIT</em>.</p>
<p><strong>By Jennifer Chu</strong></p>
<p>Swimming can take a lot of muscle. But as MIT engineers have found, even a single layer of muscle cells can power through water if designed right.&nbsp;</p>
<p>In a paper appearing today in the journal <em>Advanced Functional Materials</em>, the team presents a design for a thin, muscle-powered swimming robot. The “skeleton” of the aquabot is made from a film of gel that is about the length and width of a stick of gum. The two halves of the gel form the “fins” of the bot. Each fin is covered with a layer of live muscle cells that is much thinner than a single strand of hair. The cells are genetically engineered to twitch in response to light.&nbsp;</p>
<p>When the researchers shine light on one fin, the muscles on its surface twitch in response, causing the whole fin to flap with enough force to pull the robot through water. By flashing light on one fin or the other, at various intervals, they can control the swimming robot’s direction and speed.&nbsp;</p>
<p>The engineers showed that the paper-thin bot could swim and swivel through a simple watery maze. At its fastest, the robot can swim a distance of about four times its body length in one minute. That’s a snail’s pace compared to Olympic swimmers, who can cover up to 65 body lengths per minute. But the bot could hold its own against more leisurely swimmers like the cow shark, which explores the ocean at about the same rate.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-02-press.jpg" alt="" width="900" height="600" class="alignnone size-full wp-image-221536" srcset="https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-02-press.jpg 900w, https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-02-press-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/MIT-RoboMuscle-02-press-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /><em>In their new work, the team Raman Lab aimed to maximize muscle movements to produce more force — enough, say, to power a swimming robot. Pictured is Maheera Bawa, a graduate student at Raman Lab. Photo credit: Melanie Gonick, MIT.</em></p>
<p>“It takes a lot of force to move through water versus air,” says study author Ritu Raman, associate professor of mechanical engineering at MIT. “The robot’s quite strong, given its size.”</p>
<p><center></p>
<p><iframe width="322" height="576" src="https://www.youtube-nocookie.com/embed/omkiYBBrGZs" title="(ᴡᴀʀɴɪɴɢ: ғʟᴀsʜɪɴɢ ʟɪɢʜᴛs) How to make robot powered by skeletal muscle" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen=""></iframe></p>
<p></center></p>
<p>The new robot is the first example of a very thin, two-dimensional, muscle-powered robot capable of locomotion.&nbsp;</p>
<p>“Currently, biohybrid robots from our group and others’ are built from bulky, 3D chunks of lab-grown skeletal muscle that require millions of cells to fabricate,” says Raman, who notes that thinner, less bulky designs such as the team’s new bot could be cheaper to build and could move more efficiently. “We believe that biohybrid robots powered by living muscle could one day perform delicate jobs like exploring environments too fragile or unpredictable for conventional hardware, because living tissue is soft, responsive to its surroundings, and can heal itself.”</p>
<p>The study’s MIT co-authors are first author Maheera Bawa, Arielle Berman, Laura Schwendeman, Ferdows Afghah, and Seanbiron Johnson.</p>
<p><strong>Maximizing movement</strong></p>
<p>Last year, Raman’s group developed an&nbsp;<a href="https://news.mit.edu/2025/artificial-muscle-flexes-multiple-directions-offering-path-soft-wiggly-robots-0317" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">iris-inspired disk of artificial muscle tissue</a>. They stamped a disk of gel with a pattern of concentric and radial grooves, and deposited live muscle cells onto the gel’s surface. The cells formed a thin layer that grew along the grooves, and when stimulated with light, the cells moved in patterns that stretched and squeezed the disk, similar to how a human iris dilates and constricts the eye’s pupil.&nbsp;</p>
<p>That work was the first to demonstrate that muscle cells could be grown in a very thin layer, and in complex patterns that when stimulated could move in multiple, controllable directions.&nbsp;</p>
<p>“People hadn’t seen this muscle architecture engineered from scratch before,” Raman says. “And the cells were moving in multiple directions. But they only moved about 100 microns. From a robotics perspective, their movements were tiny.”&nbsp;</p>
<p>In their new work, the team aimed to maximize muscle movements to produce more force — enough, say, to power a swimming robot. The key, they found, was to optimize the skeleton on which the cells grow.&nbsp;</p>
<p>In their previous iris-inspired design, they grew muscle cells on fibrin, which is a type of ultrasoft gel that the team realized can quickly shrivel in response to the forces generated by the muscles. To better support cells and maximize their force, the researchers focused on tuning the underlying gel by changing three properties: the gel’s composition, its stiffness, and the size and shape of the grooves that are stamped into it.&nbsp;</p>
<p>“For engineering any type of tissue, it’s known that these are knobs you can tune,” Raman says. “And we wanted to optimize all these parameters to support live muscle cells.”</p>
<p><strong>Tuning a skeleton</strong></p>
<p>To find an optimal “skeleton” on which to grow muscle cells, the team experimented with multiple formulations of gel, of different stiffnesses, and stamped with grooves of different geometries. For instance, one groove type resembled a skinny square trough, where another was more of a long curved valley. They found that when they deposited muscles onto each type of grooved gel, cells settled into alignment in grooves that were more square than curved. More aligned cells tend to fuse into fibers that then form a stronger, more coordinated muscle tissue. Square grooves, they found, were the way to go.&nbsp;</p>
<p>Instead of using fibrin, they tried&nbsp;gelatin methacrylate (GelMA), a material that is often used in tissue engineering. They made different recipes of GelMA to create skeletons of different stiffnesses and observed how muscle cells grew when deposited on the gel’s surface. They found that cells grew in better alignment, and produced the most force, on stiffer gels.&nbsp;</p>
<p>The team also varied the gel thickness and found that a half-millimeter-thin film of GelMa offered good support for a single layer of muscle cells. The film was light enough that the cells were able to stick to the gel when they contracted, rather than peeling away.&nbsp;</p>
<p>Finally, the team “exercised” the muscles, using a training routine of flashing lights to strengthen the muscles.&nbsp;</p>
<p>With the pumped-up cells and the optimized gel, the team designed a thin, two-finned robot, comprising the gel, stamped on both sides with square-bottomed grooves and lined with muscle cells. The cells fused into fibers, eventually forming a strong, aligned muscle tissue.&nbsp;</p>
<p>“You can think of the robot as having two independent muscles,” Raman says. “If we shine a light on just one, only that muscle moves. If shining on both, they both flap.”</p>
<p>The researchers submerged the robot in a large petri dish of water and manually maneuvered a light source over the bot. The robot followed the light, flapping its fins in response to navigate through a maze that the team placed in the dish.</p>
<p>The current design is relatively basic as far as its form. The researchers intended first to show that the bot could produce enough force to swim.</p>
<p>“Our next goal is to optimize the body design to enable faster swimming,” Raman says. “But even at slow swim speeds, one could imagine a muscle-powered swimmer being used for purposes like environmental monitoring in aquatic environments.”</p>
<p>This research was supported, in part, by the Office of Naval Research.&nbsp;</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 166 &#8211; Evolving robot bodies and brains, with Rika Antonova</title>
		<link>https://robohub.org/robot-talk-episode-166-evolving-robot-bodies-and-brains-with-rika-antonova/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 16 Oct 2026 11:36:47 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223134</guid>

					<description><![CDATA[Claire chatted to Rika Antonova from the University of Cambridge about using artificial intelligence to develop complimentary robot hardware and algorithms. Rika Antonova is an Associate Professor at the University of Cambridge. Her research interests include co-design, automated algorithm discovery, data-efficient reinforcement learning, exploration, active learning, and​ robotics. After completing a research Master’s degree at [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-223136" src="https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-425x354.jpg" alt="" width="425" height="354" srcset="https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-425x354.jpg 425w, https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-1024x854.jpg 1024w, https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-768x641.jpg 768w, https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-1536x1281.jpg 1536w, https://robohub.org/wp-content/uploads/2026/10/Rika-Antonova-2048x1708.jpg 2048w" sizes="(max-width: 425px) 100vw, 425px" />
<p>Claire chatted to Rika Antonova from the University of Cambridge about using artificial intelligence to develop complimentary robot hardware and algorithms.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43233098/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>

<p class="wp-block-paragraph"><a href="https://camral.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Rika Antonova</a> is an Associate Professor at the University of Cambridge. Her research interests include co-design, automated algorithm discovery, data-efficient reinforcement learning, exploration, active learning, and​ robotics. After completing a research Master’s degree at the Robotics Institute at Carnegie Mellon University and a PhD at KTH Royal Institute of Technology, Rika undertook a Computing Innovation Fellowship at Stanford University. Before that, she was a senior software engineer at Google.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Neurosymbolic planning using natural language communication for cooperative autonomous vehicles</title>
		<link>https://robohub.org/neurosymbolic-planning-using-natural-language-communication-for-cooperative-autonomous-vehicles/</link>
		
		<dc:creator><![CDATA[Neel P. Bhatt]]></dc:creator>
		<pubDate>Wed, 14 Oct 2026 09:14:30 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=21287</guid>

					<description><![CDATA[Imagine you are driving toward an intersection. A truck parked on the corner blocks your view of a car speeding toward the intersection from the right. You can’t see it, but the car next to you can. What if that neighboring vehicle could simply tell your car, “Vehicle merging from the right, about 15 meters […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/09/birds-eye.jpeg" alt="" width="1380" height="630" class="alignnone size-full wp-image-21375" srcset="https://aihub.org/wp-content/uploads/2026/09/birds-eye.jpeg 1380w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-300x137.jpeg 300w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-1024x467.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-768x351.jpeg 768w" sizes="(max-width: 1380px) 100vw, 1380px" /></p>
<p>Imagine you are driving toward an intersection. A truck parked on the corner blocks your view of a car speeding toward the intersection from the right. You can’t see it, but the car next to you can. What if that neighboring vehicle could simply tell your car,</p>
<p><em>“Vehicle merging from the right, about 15 meters away, moving quickly.”</em></p>
<p>Your car now knows something its own sensors could never observe.</p>
<p>This simple idea of cars helping each other by describing what they see in natural language motivates <a href="https://arxiv.org/abs/2510.12992" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><strong>UNCAP</strong></a>, our new framework for cooperative autonomous driving. But there’s an important twist: not every neighboring vehicle is worth listening to, and not every message deserves the same level of trust.</p>
<p>UNCAP teaches autonomous vehicles both <strong>who to talk to</strong> as well as <strong>how much to trust what they hear</strong>.</p>
<h4>Why should cars talk with language instead of sharing sensor data?</h4>
<p>Researchers have since long envisioned fleets of autonomous vehicles cooperating to make driving safer. Blind corners, occlusions, and hidden pedestrians will become much less dangerous if nearby cars can share what they observe.</p>
<p>The traditional approach is straightforward: cars can exchange raw sensor data such as camera images, LiDAR point clouds, or radar measurements. However, this quickly becomes impractical to be implemented at scale for a variety of reasons. Raw sensor streams consume enormous bandwidth, require significant computation to process stream data, and assume that every vehicle has comparable sensing hardware. In reality, with the rise of autonomous driving, the roads are instead observing a mixture of manufacturers, sensor configurations, and heterogenous software stacks. Natural language offers an intriguing alternative to sensor data sharing. Instead of transmitting megabytes of images, a vehicle might simply say, <em>“pedestrian crossing behind bus”</em> or <em>“motorcycle approaching from the left, fast-moving”</em>. These messages are tiny, hardware-agnostic, and immediately understandable by modern vision-language models across the spectrum.</p>
<p>But language introduces a new problem. At a busy intersection, a vehicle might have ten or twenty neighbors. Should it listen to all of them? And if two vehicles disagree, whose description should it believe? UNCAP answers all these questions!</p>
<h4>How UNCAP works</h4>
<p>An appeal of UNCAP is that it works <strong>entirely in a zero-shot manner</strong>. Instead of training a new model (which is resource intensive), UNCAP has a “Bring-your-own-model” strategy. It builds on existing vision-language models and adds a communication strategy that allows vehicles to cooperate intelligently. The UNCAP framework includes four stages.</p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/09/uncap.jpeg" alt="" width="1380" height="792" class="alignnone size-full wp-image-21374" srcset="https://aihub.org/wp-content/uploads/2026/09/uncap.jpeg 1380w, https://aihub.org/wp-content/uploads/2026/09/uncap-300x172.jpeg 300w, https://aihub.org/wp-content/uploads/2026/09/uncap-1024x588.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/09/uncap-768x441.jpeg 768w" sizes="(max-width: 1380px) 100vw, 1380px" /><em>UNCAP helps each vehicle decide which neighbors matter. Those messages describe nearby vehicles, motion, and confidence, which UNCAP combines before making a driving decision.</em></p>
<h4>1. Discover nearby vehicles</h4>
<p>Each vehicle periodically broadcasts a tiny “heartbeat” of information containing only its position and direction of travel. This heartbeat consists of only a few bytes of data. The aim is to provide just enough context for nearby vehicles to understand who is around them.</p>
<h4>2. Decide who matters</h4>
<p>On the road, most nearby vehicles are irrelevant. A car traveling away from the intersection provides little useful information, whereas a vehicle approaching the same intersection may offer exactly the observations we need. UNCAP reasons about which neighbors are both close enough and likely to affect the vehicle’s future path. This is crucial as it dramatically reduces the bandwidth of unnecessary communication as well as the computation required by downstream stages. It enables UNCAP to scale to handle large teams.</p>
<h4>3. Exchange observations and reason about trust</h4>
<p>Relevant vehicles then describe what they see using natural language, accompanied by calibrated confidence estimates. Calibration is desirable as it produces reliable uncertainty estimates. UNCAP uses <strong>conformal prediction</strong>, which is a lightweight calibration method that ensures confidence values reflect the actual reliability of the information being received. Every vehicle then reasons about whether an incoming message actually reduces its uncertainty about the scenario. To answer this, UNCAP measures the <strong>mutual information</strong> contributed by each incoming observation. Mutual information ensures that the vehicle can give greater weightage to messages that make the scene clearer, while uninformative or potentially misleading observations are discounted. Rather than blindly treating every neighbor homogenously, each vehicle builds an uncertainty-aware understanding of the environment.</p>
<h4>4. Make a driving decision</h4>
<p>Finally, the scene description generated by reasoning about all incoming messages is passed to an off-the-shelf vision-language model, which produces a driving decision such as merge, wait, or yield, along with a corresponding confidence score.</p>
<h4>What did this research teach us?</h4>
<p>We evaluated UNCAP in the popular CARLA driving simulator using the OPV2V benchmark, which is a widely used benchmark by autonomous driving researchers. OPV2V includes highway merging, urban intersections, and other scenarios where vehicles frequently experience occlusions.</p>
<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/09/birds-eye.jpeg" alt="" width="1380" height="630" class="alignnone size-full wp-image-21375" srcset="https://aihub.org/wp-content/uploads/2026/09/birds-eye.jpeg 1380w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-300x137.jpeg 300w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-1024x467.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/09/birds-eye-768x351.jpeg 768w" sizes="(max-width: 1380px) 100vw, 1380px" /><em>These bird&#8217;s-eye-view (BEV) examples compare driving with and without UNCAP. With selected helper messages, vehicles behave more proactively in merging and intersection scenes.</em></p>
<p>Compared with non-communicating vehicles, and compared with prior language-based approaches that blindly broadcast every observation to every other car, UNCAP consistently improved both efficiency and safety. Over various scenarios, our experiments yielded key qualitative gains of UNCAP over traditional cooperation schemes include:</p>
<ul>
<li>63% less communication bandwidth</li>
<li>31% higher driving score</li>
<li>61% lower decision uncertainty</li>
<li>4× larger safety margins during near-miss events</li>
</ul>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/09/fig3.jpeg" alt="" width="1212" height="864" class="alignnone size-full wp-image-21376" srcset="https://aihub.org/wp-content/uploads/2026/09/fig3.jpeg 1212w, https://aihub.org/wp-content/uploads/2026/09/fig3-300x214.jpeg 300w, https://aihub.org/wp-content/uploads/2026/09/fig3-1024x730.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/09/fig3-768x547.jpeg 768w" sizes="(max-width: 1212px) 100vw, 1212px" /><em>UNCAP avoids broadcasting every observation to every nearby vehicle. It sharply reduces bandwidth while preserving the information needed for a driving decision.</em></p>
<p>Perhaps the most surprising result was that <strong>sharing raw images actually performed worse than sharing language</strong>.</p>
<p>Modern vision-language models appear to struggle when jointly reasoning over multiple camera feeds captured from different viewpoints. Translating those observations into concise natural-language descriptions first seems to act as a form of structured reasoning, distilling the essential information before it reaches the decision-making model.</p>
<p>Equally encouraging, the improvements were consistent across several underlying vision-language models, including GPT-4o, GPT-4.1, GPT-4o-mini, and GPT-5. This suggests that the benefits stem from the communication strategy itself rather than from any particular model.</p>
<h4>Looking ahead</h4>
<p>UNCAP is an early step toward autonomous vehicles that cooperate more like human drivers.</p>
<p>Today’s implementation has important limitations. Our experiments are limited to simulation, so real-world constraints such as noisy sensing, unreliable wireless communication, network delays and packet losses remain to be explored. Finally, because querying today’s vision-language models takes roughly a second, decisions are made at key moments rather than continuously.</p>
<p>That being said, the broader message extends well beyond autonomous driving.</p>
<p>As AI systems increasingly operate in teams, whether fleets of robots, drones, or software agents, the challenge is no longer simply making each agent smarter. The critical need of the hour is to ensure that each agent in the team learns how to communicate efficiently, decide which information to trust, and build a shared understanding of the world.</p>
<p>In a nutshell, UNCAP suggests that natural language, paired with principled reasoning about uncertainty, can provide a surprisingly effective foundation for that future.</p>
<h4>Read the paper in full</h4>
<p><a href="https://arxiv.org/abs/2510.12992" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles</a>, <em>Neel P. Bhatt, Po-han Li, Kushagra Gupta, Rohan Siva, Daniel Milan, Alexander T. Hogue, Sandeep P. Chinchali, David Fridovich-Keil, Zhangyang Wang, Ufuk Topcu</em>.</p>
<hr>
<p>This work was nominated for the AAMAS 2026 best paper award.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Humanoid robots can sprint and box – but the real test is doing the laundry</title>
		<link>https://robohub.org/humanoid-robots-can-sprint-and-box-but-the-real-test-is-doing-the-laundry/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Mon, 12 Oct 2026 07:51:21 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221548</guid>

					<description><![CDATA[By Wai-keung Fung, Cardiff Metropolitan University At the recent World Humanoid Robot Games 2026 in Beijing, robots sprinted, boxed, played football and tackled tasks inspired by factories, restaurants and emergency situations. The robot Tiangong Ultra even completed the 100 metres in 8.64 seconds, quicker than Usain Bolt’s 9.58-second world record. But if we really want [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221551" srcset="https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/10/sophiamartin-clothes-pins-8281931-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By <a href="https://theconversation.com/profiles/wai-keung-fung-2713865" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Wai-keung Fung</a>, <em><a href="https://theconversation.com/institutions/cardiff-metropolitan-university-1585" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff Metropolitan University</a></em></strong></p>
<p>At the recent World Humanoid Robot Games 2026 in Beijing, robots sprinted, boxed, played football and tackled tasks inspired by factories, restaurants and emergency situations. The robot Tiangong Ultra even completed the 100 metres in 8.64 seconds, quicker than Usain Bolt’s 9.58-second world record.</p>
<p>But if we really want to know whether humanoid <a href="https://theconversation.com/topics/robots-6403" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robots</a> are ready for everyday life, a far less glamorous challenge may tell us more: doing the laundry. Can a robot take a crumpled T-shirt from a laundry basket, work out which way round it is, <a href="https://www.figure.ai/news/helix-learns-to-fold-laundry" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">fold it neatly</a> and recover when the sleeve slips from its hand?</p>
<p>No robot system can yet reliably handle the whole laundry process, from carrying a basket to the washing machine and sorting clothes for different programmes to taking them out, hanging them to dry, folding and ironing them. Even folding remains a challenge: robots need to cope with clothes of different shapes, sizes, materials and levels of creasing.</p>
<p><a href="https://theconversation.com/robots-can-run-faster-than-elite-human-sprinters-but-are-they-really-athletes-290559" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Running fast</a> is difficult, of course. A humanoid has to coordinate many joints, keep its balance and generate powerful movements without falling over. The task itself, however, is fairly clear. The robot knows where to go, the track is predictable and the finish line does not suddenly change shape.</p>
<div class="keep-aspect"><iframe title="Biggest fails from the 2026 World Humanoid Robot Games in China" width="500" height="281" src="https://www.youtube-nocookie.com/embed/XgnBN8BLc-o?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Laundry is a very different problem. A shirt may be inside out. One sleeve may be hidden underneath another garment. A pair of trousers may be twisted around a towel. Fabric is also soft and constantly changing shape. Pick up one corner of a T-shirt and the rest of it moves. </p>
<p>Humans deal with this without giving it much thought. We shake a shirt out, notice where the sleeves are, feel when the fabric slips and adjust our grip almost automatically. For a robot, every one of those little actions is a problem to solve. This is why an everyday chore can reveal more about robot intelligence than a spectacular athletic feat.</p>
<p>A useful household robot cannot simply replay the same movement again and again. It has to notice when reality is different from what it expected and adapt. That’s important to consider because humanoid robots are increasingly discussed as future helpers in homes and care settings, as well as factories and warehouses. </p>
<p>A factory production line can often be arranged so that parts arrive in predictable positions. A family home is not like that: clothes, toys and furniture move around constantly, while people, children and pets make the environment even less predictable.</p>
<h2>Why one robot cannot simply copy another</h2>
<p>There is another difficulty. Once one robot learns how to fold a shirt, it might seem obvious that we should simply transfer that skill to every other robot. Unfortunately, physical skills do not work like an app that can be installed on any machine.</p>
<p>Imagine a specialist laundry robot with rigid arms, overhead cameras and grippers designed specifically for fabric. A humanoid may have cameras in its head, five-fingered hands and different joints and balance constraints. The same movement could therefore produce a very different result. </p>
<p>A fixed robot arm can reach forward without worrying about falling over. A humanoid may have to move its hips, legs and feet just to keep itself stable while reaching across a table.</p>
<div class="keep-aspect"><iframe title="Autonomous Laundry Folding by Torobo2" width="500" height="281" src="https://www.youtube-nocookie.com/embed/4U52YaO8g3A?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Sensors are important too. One robot may have sensitive touch sensors in its fingers. Another may rely mainly on cameras. </p>
<p>Some knowledge can still transfer. One robot can teach another something about what a shirt looks like, where its shoulders are likely to be, what a good fold looks like or how to recognise when a sleeve is trapped underneath. The receiving robot still has to work out how to carry out those ideas with its own hands, joints, cameras and body.</p>
<p>Research projects such as <a href="https://robotics-transformer-x.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Open X-Embodiment</a> are exploring exactly this problem by pooling experience from many different robots. The project has brought together more than one million real robot trajectories from 22 different robot types. The hope is that robots can learn useful patterns from one another rather than starting from zero every time. </p>
<h2>What should count as progress?</h2>
<p>The Humanoid Robot Games are valuable because they make robotics visible and show how quickly the technology is moving. </p>
<p>We should simply be careful about what those demonstrations prove. For robots intended to live and work alongside us, better questions might be: can the robot deal with an unfamiliar object? Can it notice that it has made a mistake and recover without human intervention? How long can it keep working before someone has to step in?</p>
<p>These measures are unlikely to produce viral videos. They are, however, much closer to the abilities that will determine whether humanoid robots become genuinely useful.</p>
<p>A robot that can run 100 metres faster than the human world record time is impressive. A robot that can take a messy basket of laundry, sort it, fold it and recognise when things have gone wrong may tell us far more about whether general purpose robot intelligence has really arrived.</p>
<p>The most important race for humanoid robots may not be against the clock. It may be against the laundry pile.<!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding="async" src="https://counter.theconversation.com/content/290684/count.gif?distributor=republish-lightbox-basic" alt="The Conversation" width="1" height="1" style="border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important" referrerpolicy="no-referrer-when-downgrade" /><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https://theconversation.com/republishing-guidelines --></p>
<p><span><a href="https://theconversation.com/profiles/wai-keung-fung-2713865" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Wai-keung Fung</a>, Senior Lecturer in Electronics Robotics &#038; Control Engineering, <em><a href="https://theconversation.com/institutions/cardiff-metropolitan-university-1585" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff Metropolitan University</a></em></span></p>
<p>This article is republished from <a href="https://theconversation.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Conversation</a> under a Creative Commons license. Read the <a href="https://theconversation.com/humanoid-robots-can-sprint-and-box-but-the-real-test-is-doing-the-laundry-290684" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">original article</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 165 &#8211; Robots behind the research, with Kushant Patel</title>
		<link>https://robohub.org/robot-talk-episode-165-robots-behind-the-research-with-kushant-patel/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 09 Oct 2026 11:52:18 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=223071</guid>

					<description><![CDATA[Claire chatted to Kushant Patel from Brookhaven National Laboratory about robots that work in scientific facilities, such as particle accelerators. Kushant Patel builds software that helps robots and instruments perceive, map, and move through the physical world. After completing a Master’s in Mechatronics Engineering at the University of Waterloo, he spent two years at the University [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-223073" src="https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel-319x425.jpg" alt="" width="319" height="425" srcset="https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel-319x425.jpg 319w, https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel-768x1024.jpg 768w, https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel-1152x1536.jpg 1152w, https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel-1536x2048.jpg 1536w, https://robohub.org/wp-content/uploads/2026/10/Kushant-Patel.jpg 1920w" sizes="(max-width: 319px) 100vw, 319px" />
<p>Claire chatted to Kushant Patel from Brookhaven National Laboratory about robots that work in scientific facilities, such as particle accelerators.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/43224733/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>

<p class="wp-block-paragraph"><a href="https://kushantp58.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Kushant Patel</a> builds software that helps robots and instruments perceive, map, and move through the physical world. After completing a Master’s in Mechatronics Engineering at the University of Waterloo, he spent two years at the University of California, Berkeley teaching quadruped robots to map and inspect nuclear material, and a year at the University of California, Davis building closed-loop brain-computer interfaces. At Brookhaven National Laboratory, he is developing control systems for advanced synchrotron beamlines.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>What three days building a robot taught me</title>
		<link>https://robohub.org/what-three-days-building-a-robot-taught-me/</link>
		
		<dc:creator><![CDATA[Devashish Tambade]]></dc:creator>
		<pubDate>Wed, 07 Oct 2026 07:12:39 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221363</guid>

					<description><![CDATA[Last month, I went to York to build a robot. I came back with a robot, a tiny trophy-shaped sense of achievement, and somehow a few new friends. From 25th-27th August, I joined the UK RAS STEPS MicroMaze Robot Hackathon at the Institute for Safe Autonomy, University of York. The brief sounded simple: build a [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/York_DevInYork-1024x576.jpeg" alt="" width="1024" height="576" class="alignnone size-large wp-image-221365" srcset="https://robohub.org/wp-content/uploads/2026/09/York_DevInYork-1024x576.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/09/York_DevInYork-425x239.jpeg 425w, https://robohub.org/wp-content/uploads/2026/09/York_DevInYork-768x432.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/York_DevInYork.jpeg 1280w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>Last month, I went to York to build a robot. I came back with a robot, a tiny trophy-shaped sense of achievement, and somehow a few new friends.</p>
<p>From 25th-27th August, I joined the UK RAS STEPS MicroMaze Robot Hackathon at the Institute for Safe Autonomy, University of York.</p>
<p>The brief sounded simple: build a small autonomous robot, then make it survive increasingly difficult mazes. Simple&#8230; right? Until you actually have to build one.</p>
<p>Over three days, Emily, Joolz and I went from a box of parts and a laser-cut chassis to a robot that could actually make its way through a maze. There were sensors, motors, Raspberry Pi Pico W, MicroPython, plenty of debugging and, of course, the occasional, “Why is it doing THAT?”</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/York-Timelapse.gif" alt="" width="852" height="480" class="alignnone size-full wp-image-221360" /> </p>
<p>But to be honest, looking back, the technical part wasn&#8217;t even my favourite bit. Somewhere between building, debugging, failed runs and laughing at our own mistakes, the three of us went from a team that had just met to people I now genuinely consider friends.</p>
<p>And on the final day, Michael Smith, Eugen Guritanu, Emily, Joolz and I spent the day wandering around York, eating, talking and generally making the most of being there. It&#8217;s funny how quickly that happens at these events. You arrive knowing very few people. A few days later, you&#8217;re discussing robots, arguing about how to fix things, sharing stories and making plans to meet again.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/York_Friends-1024x768.jpeg" alt="" width="1024" height="768" class="alignnone size-large wp-image-221367" srcset="https://robohub.org/wp-content/uploads/2026/09/York_Friends-1024x768.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/09/York_Friends-425x319.jpeg 425w, https://robohub.org/wp-content/uploads/2026/09/York_Friends-768x576.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/York_Friends-1536x1152.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/09/York_Friends.jpeg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>We also got to spend some time at the Institute for Safe Autonomy, which was a brilliant setting for the hackathon. There&#8217;s something quite fitting about asking a room full of technical people to make a tiny autonomous robot behave itself.</p>
<p>A huge thank you to (always witty &#8216;n&#8217; playful) Rob Woolley for organising the hackathon, and to the Institute for Safe Autonomy, University of York and the wider UK RAS STEPS team for creating these opportunities for Research Technical Professionals.</p>
<p>And finally Emily, Joolz, Michael and Eugen, I&#8217;m very glad a robotics hackathon turned into a York friendship trip :-)</p>
<p>For now, I&#8217;ll leave you with a few tiny robots, some good York memories, and another reminder that sometimes the best things you build at these events aren&#8217;t always the things you planned to build.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/York_Robots-1024x768.jpeg" alt="" width="1024" height="768" class="alignnone size-large wp-image-221368" srcset="https://robohub.org/wp-content/uploads/2026/09/York_Robots-1024x768.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/09/York_Robots-425x319.jpeg 425w, https://robohub.org/wp-content/uploads/2026/09/York_Robots-768x576.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/York_Robots-1536x1152.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/09/York_Robots.jpeg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Research could guide the future design of social robots</title>
		<link>https://robohub.org/research-could-guide-the-future-design-of-social-robots/</link>
		
		<dc:creator><![CDATA[the University of Glasgow]]></dc:creator>
		<pubDate>Mon, 05 Oct 2026 10:00:33 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221459</guid>

					<description><![CDATA[By the University of Glasgow Giving robot companions animal-like or anime-style faces and voices could maximise their emotional appeal to users, according to new research which could help guide the growing field of social robotics. Social robots can provide companionship and comfort to their owners by mimicking human or petlike behaviours. Although the robots are [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone  wp-image-221480" src="https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-425x249.png" alt="" width="645" height="378" srcset="https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-425x249.png 425w, https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-1024x599.png 1024w, https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-768x449.png 768w, https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-1536x898.png 1536w, https://robohub.org/wp-content/uploads/2026/10/Screenshot-2026-09-27-at-10.29.52-1-2048x1198.png 2048w" sizes="(max-width: 645px) 100vw, 645px" /></p>
<p><strong>By the <a href="https://www.gla.ac.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Glasgow</a></strong></p>
<p>Giving robot companions animal-like or anime-style faces and voices could maximise their emotional appeal to users, according to new research which could help guide the growing field of social robotics.</p>
<p>Social robots can provide companionship and comfort to their owners by mimicking human or petlike behaviours. Although the robots are a fast-growing sector of the tech industry, surprisingly little academic research has explored how their designs can be optimised to make the robots as expressive and emotionally engaging as possible.</p>
<p>In a new paper set to be presented at a conference this week, researchers from the University of Glasgow show how they have been working to close that research gap.</p>
<p>With the help of a group of volunteers, they used augmented reality technology to test dozens of different combinations of faces and voices overlaid on the body of an existing social robot called a Qoobo, which has a soft, cushion-like body and a swinging tail.</p>
<div class="keep-aspect"><iframe title="Research could guide the future design of social robots" width="500" height="281" src="https://www.youtube-nocookie.com/embed/4BIbWGGkqPM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Dr Shaun Macdonald and Josh Yip of the University of Glasgow’s School of Computing Science used this rapid prototyping approach to explore how users felt about the virtual robots, and how effectively they were able to ‘read’ the robot’s emotional states to make them feel more like real creatures.</p>
<p>Dr Macdonald said: &#8220;Social robots can provide valuable experiences for a wide range of people. Older people have reported that they can help mitigate feelings of loneliness or social isolation, for example, and people living in spaces where they can’t keep a real pet have kindled some of that sense of companionship with what we call zoomorphic robots, which mimic animals’ appearances and behaviour.</p>
<p>“However, the aesthetic design of zoomorphic social robots so far has largely been the result of educated guesswork, with very little research available on what makes them appealing to users.</p>
<p>“What we’ve done here for the first time here is take a more systematic approach to designing the appearance of a zoomorphic robot by harnessing augmented reality to enable rapid, side-by-side design tests. In the future, these insights could help create a new generation of user-customisable robots which can tailor their appearances to better suit their owners’ preferences.”</p>
<p>The research builds on Dr Macdonald’s previous research in advancing the design of social robots. His work includes the development of a software system called <a href="https://www.gla.ac.uk/news/archiveofnews/2025/august/headline_1204486_en.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Augmenting Zoomorphic Robotics with Affect</a>, or AZRA, which can overlay augmented-reality sounds and animations over the bodies of real-world social robots to prototype new appearances and functionalities.</p>
<p>In this research, the team began by creating a ‘mood board’ of appealing images of animals and robots drawn from real life and from popular culture to help them design a series of prototype faces for virtual robots. They ended up with five prototype faces comprised of animal-like, robot-like, emoji-style, anime-inspired designs, with another comprised simply of eyes.</p>
<p>They chose five distinct vocalisations to enable the prototypes to express themselves to the volunteers: recordings of cat noises, human-like vocal sounds, abstract electronic noises, music and samples of ‘animalese’, the nonsense sounds used by the characters in the popular Nintendo game series Animal Crossing.</p>
<p><img decoding="async" class="alignnone wp-image-221460" src="https://robohub.org/wp-content/uploads/2026/09/Media_1288956_smxx-425x310.png" alt="" width="923" height="673" srcset="https://robohub.org/wp-content/uploads/2026/09/Media_1288956_smxx-425x310.png 425w, https://robohub.org/wp-content/uploads/2026/09/Media_1288956_smxx-768x560.png 768w, https://robohub.org/wp-content/uploads/2026/09/Media_1288956_smxx.png 946w" sizes="(max-width: 923px) 100vw, 923px" /></p>
<p>Then, 24 volunteers were given AR headsets and asked to rank different combinations of faces and voices overlaid on Qoobo for how clearly they expressed an emotion and how much empathy they felt towards the prototype robot, as well as how appropriate the combination of factors felt to them.</p>
<p>The results revealed that combinations of animal-like faces and vocalisations matched Qoobo’s animal-like body were well-liked by the volunteers, who found them more engaging and immersive. While that result might be unsurprising, the team also found that anime-like faces were just as highly-ranked despite not being based on real life.</p>
<p>Josh Yip said: “Anime-like faces are more expressive than animal faces could ever really be, giving the robot abilities to express themselves beyond those of a normal pet but in a way that didn’t feel uncanny. It still felt like it could be a pet-like creature to our study participants.</p>
<p>“We also found that faces consistently outperformed sounds at conveying emotion and creating connections. Interestingly, the study participants found that the human sounds were easier to read emotionally but were liked less than animal sounds, even though they found them harder to clearly identify with specific emotions.”</p>
<p><img decoding="async" class="alignnone wp-image-221462" src="https://robohub.org/wp-content/uploads/2026/09/Media_1288957_smxx-425x310.png" alt="" width="917" height="669" srcset="https://robohub.org/wp-content/uploads/2026/09/Media_1288957_smxx-425x310.png 425w, https://robohub.org/wp-content/uploads/2026/09/Media_1288957_smxx-768x560.png 768w, https://robohub.org/wp-content/uploads/2026/09/Media_1288957_smxx.png 946w" sizes="(max-width: 917px) 100vw, 917px" /></p>
<p>The team were surprised to find that, although the study participants insisted that they felt that being able to correctly read the robot’s emotions was very important to them, the data showed that readability had little influence on the designs they preferred. Along similar lines, ‘animalese’ sounds ranked highly with users despite being unintelligible, with some users feeling it suggested the robot had a greater sense of intelligence than other sounds.</p>
<p>The study’s participants reactions to the prototypes were also affected by whether they owned a real animal pet themselves. Pet owners were more likely to treat the animal-like prototypes as real pets, but to be more likely to treat robot-like faces as machines.</p>
<p>Dr Macdonald added: “Our research suggests that although there is no single face or voice that has universal appeal, the combination of the two can have a big effect on how well users feel that robots are able to communicate emotions.</p>
<p>“We hope our findings will help inform the design of future generations of zoomorphic social robot technology, but they could also extend the lifespan of existing devices by enabling users to overlay new faces, voices and functionality on them using augmented reality.”</p>
<p>The team’s paper, titled ‘<a href="https://programs.sigchi.org/mobilehci/2026/program/content/263592" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Anime, Animal or Animal Crossing? Comparing Aesthetic Styles for Zoomorphic Robot Faces and Sounds using Augmented Reality</a>’, will be presented at the ACM International Conference on Mobile Human-Computer Interaction conference in Swansea, Wales on Thursday 3 September.</p>
<p>The project was supported by funding from the University of Glasgow’s EPSRC Impact Acceleration Account and the Engineering and Physical Sciences Research Council (EPSRC).</p>
<p>This article is republished from the <a href="https://www.gla.ac.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Glasgow</a> under a Creative Commons license. Read the original article <a href="https://www.gla.ac.uk/news/headline_1288953_en.html?utm_medium=email&amp;utm_source=govdelivery" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 164 &#8211; Accelerating robot learning, with Michelle Lu</title>
		<link>https://robohub.org/robot-talk-episode-164-accelerating-robot-learning-with-michelle-lu/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 02 Oct 2026 11:33:00 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221571</guid>

					<description><![CDATA[Claire chatted to Michelle Lu from Vsim Technology about using simulation and artificial intelligence to teach robots new skills. Michelle Lu is co-founder and CEO of Vsim Technology. She was previously a Director of Simulation Technology at NVIDIA, where she and her co-founder created the world’s first end-to-end GPU-accelerated reinforcement learning (RL) framework, Isaac Gym, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone size-medium wp-image-221573" src="https://robohub.org/wp-content/uploads/2026/10/Michelle-Lu-283x425.png" alt="" width="283" height="425" srcset="https://robohub.org/wp-content/uploads/2026/10/Michelle-Lu-283x425.png 283w, https://robohub.org/wp-content/uploads/2026/10/Michelle-Lu.png 640w" sizes="(max-width: 283px) 100vw, 283px" /></p>
<p>Claire chatted to Michelle Lu from Vsim Technology about using simulation and artificial intelligence to teach robots new skills.</p>
<p><iframe src="https://play.libsyn.com/embed/episode/id/43127618/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe></p>
<p>Michelle Lu is co-founder and CEO of <a href="https://v-sim.co.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Vsim Technology</a>. She was previously a Director of Simulation Technology at NVIDIA, where she and her co-founder created the world’s first end-to-end GPU-accelerated reinforcement learning (RL) framework, Isaac Gym, which set the template for how modern GPU-accelerated simulation-based RL is performed in robotics. In 2022, Michelle and her co-founder left NVIDIA to create Vsim, driven to solve the limitations that plague simulation-based robotics AI: efficiency, scalability and the sim-to-real gap.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotics and automation? Informal reflections on familiar terms</title>
		<link>https://robohub.org/robotics-and-automation-informal-reflections-on-familiar-terms/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 30 Sep 2026 08:37:22 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221356</guid>

					<description><![CDATA[By Emmet Cole &#8220;Robotics and automation&#8221; is a pairing heard often around these parts. It puts the &#8220;RA&#8221; in IEEE RAS, after all. The familiar combination shows up in conference titles, funding calls, and program descriptions. But what is actually meant by the two words? Is robotics a subdomain of automation? Does the distinction matter? [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221522" srcset="https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/estateagentnetworking-scrabble-2378253-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By <a href="https://www.linkedin.com/in/emmet-cole-6b71995" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Emmet Cole</a></strong></p>
<p>&#8220;Robotics and automation&#8221; is a pairing heard often around these parts. It puts the &#8220;RA&#8221; in IEEE RAS, after all.</p>
<p>The familiar combination shows up in conference titles, funding calls, and program descriptions. But what is actually meant by the two words? Is robotics a subdomain of automation? Does the distinction matter?</p>
<p>As a recent IEEE RAS Communications Board meeting drew to a close, IEEE experts informally reflected on these questions and their significance for the RAS community and beyond.</p>
<p><em>The excerpts below have been lightly edited for clarity.</em></p>
<hr>
<p><strong><a href="https://www.linkedin.com/in/sabinehauert/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Sabine Hauert:</a></strong> <em>We often use the phrase &#8220;robotics and automation,&#8221; including in the name of IEEE RAS. But what do we actually mean by those two words? Why is there a distinction, and does it accurately capture our fields?</em></p>
<p><strong><a href="https://www.santannapisa.it/en/mariateresa-pedone-0" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Mariateresa Pedone:</a></strong> My feeling is that automation is almost invisible in everyday life. Its role is mainly to make processes repeatable, efficient, scalable and predictable. Robotics becomes relevant when automation needs a physical presence.</p>
<p><strong>Sabine Hauert:</strong> <em>That gives us a useful starting point with automation as the process, and robotics as its physical presence. David, do you see it that way?</em></p>
<p><strong><a href="https://dgarzonramos.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">David Garzon Ramos:</a></strong> My feeling is that automation has focused on supporting other activities. We automate a process because we want to make it more efficient or effective. Robotics, meanwhile, has also developed on its own grounds. We develop robots partly because we want to understand principles of intelligence, control and embodiment. That is how the history of the two fields has played out.</p>
<p><strong>Sabine Hauert:</strong> <em>Would that make robotics a subcategory of automation?</em></p>
<p><strong>David Garzon Ramos:</strong> I don’t think anybody necessarily wants to say that one is broader than the other. We see a similar question now with physical AI: is physical AI broader than robotics? Maybe, maybe not. These descriptions help people identify with a particular community. They can also help to manage expectations about the kind of work being done.</p>
<p><strong><a href="https://www.linkedin.com/in/cpacchierotti/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Claudio Pacchierotti:</a></strong> I would add that not all robots are automated. You can have robots that are fully teleoperated by humans, so there is little or no automation involved. A robot is a machine that physically interacts with the environment, while an automation process does not have to involve a robot. Not all automation involves robots, and not all robots are autonomous.</p>
<p><strong>Sabine Hauert:</strong> <em>That complicates the picture. Automation might not require a robot at all; it could be carried out entirely through software. And a robot could be controlled by a person rather than operating autonomously.</em></p>
<p><strong><a href="https://www.linkedin.com/in/ellen-rumley-b22210104/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Ellen Rumley:</a></strong> The definition of robotics can become hazy too. Imagine a large factory with a computer-controlled conveyor system that interacts with the physical world and sorts packages. Do we consider the whole system a robot if it isn’t an individual unit that moves around or appears somewhat lifelike?</p>
<p><strong>Claudio Pacchierotti:</strong> I introduce this question when I teach robotics to elementary school children. The first activity is simply: &#8220;Is this a robot?&#8221; A washing machine washes your clothes in a very physical way. In one sense, it could be seen as a robot. It is also highly automated. Yet most people would say it is not a robot. Once you start testing the definition against familiar objects, the boundary becomes interesting.</p>
<p><strong>Ellen Rumley:</strong> These questions have practical consequences. I do a lot of comparisons of industrial and service robotics between countries, and the categories are not always consistent. Robot vacuum cleaners, for example, may be counted differently in different countries. China can appear to produce millions more service robots partly because of what is included in the category. Definitions affect the international comparisons and the story the numbers appear to tell.</p>
<p><strong>Sabine Hauert:</strong> <em>So, this is not only a philosophical or linguistic question. What counts as a robot can affect statistics, national comparisons and perceptions of technological strength.</em></p>
<p><strong><a href="https://eds.ucsd.edu/people/faculty/eguchi.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Amy Eguchi:</a></strong> It also affects education. My background is in education, and robotics was an addition to my work. Whenever I return to Japan, I see more everyday appliances with automated functions. A washing machine can dispense its own detergent and softener, remember your preferred settings and complete the process after you press one button. I have also seen products advertised as having an &#8220;AI microwave.&#8221; Is that a robot, or is it simply automation?</p>
<p><strong>Sabine Hauert:</strong> <em>So, the answer may depend partly on what people encounter in everyday life.</em></p>
<p><strong>Amy Eguchi:</strong> Exactly. A definition may seem clear when you read it, but the categories overlap in practice. Children in different countries are familiar with different devices. That changes the examples educators can use and perhaps what children intuitively understand as robotics, automation or AI.</p>
<p><strong>Sabine Hauert:</strong> <em>We are also discussing two English words. Other languages and cultures may not separate the concepts in quite the same way. And once a technology becomes familiar, it can disappear into the category of the appliance. A robot vacuum eventually becomes simply a vacuum.</em></p>
<p><strong>David Garzon Ramos:</strong> The language also changes with research trends. Now that I write proposals, I use terms such as &#8220;physical AI&#8221; and &#8220;embodiment,&#8221; although I still describe myself as a roboticist when I talk to friends. The same has happened with terms such as intelligent systems, AI and machine learning. Concepts become entangled because the language helps attract attention and communicate with particular audiences.</p>
<p><strong>Sabine Hauert:</strong> <em>From a communications perspective, that can be difficult. Every new project seems to require all the relevant words—robotics, automation and now sometimes physical AI. It raises the question of what the differences are, where the fields overlap and why they cannot simply sit under one recognizable term.</em></p>
<p><strong>David Garzon Ramos:</strong> I think it depends on the purpose. If you are speaking to children, &#8220;robot&#8221; may immediately create interest, while &#8220;automation process&#8221; may not. &#8220;Physical AI&#8221; may confuse them again. We need to be flexible and use language in ways that are useful to the audience. If we fix a definition today, the terminology may shift when a new model or research trend appears.</p>
<p><strong>Sabine Hauert:</strong> <em>I think there is a historical element too. Conference names and the names of professional communities preserve something of the way the fields developed. Sometimes a new word takes over, and sometimes another is added. But all these areas are closely linked. We may not have settled the definitions, but we have shown why these overlaps are worth discussing.</em></p>
<hr>
<p>Are you a roboticist who dabbles in automation? Or an automation specialist who occasionally ventures into robotics territory? Is the distinction important and/or meaningful? <a href="mailto:ras@ieee.org">Drop us a line</a> and we may share your insights in a future feature article.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Small, medium or large, a robotic fish maintains its swimming ability</title>
		<link>https://robohub.org/small-medium-or-large-a-robotic-fish-maintains-its-swimming-ability/</link>
		
		<dc:creator><![CDATA[EPFL]]></dc:creator>
		<pubDate>Mon, 28 Sep 2026 11:24:15 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221236</guid>

					<description><![CDATA[The scalable robot ScaFi. 2026 CREATE Lab EPFL. CC BY SA-4.0. Propeller-powered underwater vehicles have long helped scientists explore and monitor aquatic environments. But they&#8217;re limited by their own mechanics: spinning blades can snag on vegetation, stir up sediment, and startle the wildlife they&#8217;re often sent to study, making them poorly suited to shallow creeks, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-1024x575.jpg" alt="" width="1024" height="575" class="alignnone size-large wp-image-221237" srcset="https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-1024x575.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-768x431.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-1536x862.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-1-2048x1150.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The scalable robot ScaFi. 2026 CREATE Lab EPFL. CC BY SA-4.0.</em></p>
<p>Propeller-powered underwater vehicles have long helped scientists explore and monitor aquatic environments. But they&#8217;re limited by their own mechanics: spinning blades can snag on vegetation, stir up sediment, and startle the wildlife they&#8217;re often sent to study, making them poorly suited to shallow creeks, dense weeds, or close encounters with fish.</p>
<p>That&#8217;s one reason roboticists have spent years building machines that swim like fish instead, bending their bodies rather than spinning a propeller. The catch is that most fish-inspired robots are built for one size and one job, so scaling them up or down usually means starting from scratch.</p>
<div class="keep-aspect"><iframe title="Small, medium or large, a robotic fish maintains its swimming ability" width="500" height="281" src="https://www.youtube-nocookie.com/embed/cAoykn3hJ_w?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>A team of engineers at EPFL and New York University (NYU) says it has found a way to solve that problem. <a href="https://engineering.nyu.edu/news/robot-grows-fish-not-machine" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">They&#8217;ve unveiled ScaFi</a> (for Scalable Fish), a robot modeled on fish like cod and mackerel. These fish swim by concentrating most of their body bending toward the tail end, a style that, in nature, spans an unusually wide range of body sizes.</p>
<p>&#8220;Right now, if you want to monitor a creek and then monitor a lake, you basically need two different robots, built and tested from the ground up,&#8221; says <a href="https://engineering.nyu.edu/faculty/nana-obayashi" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Nana Obayashi</a>, first author on the study published in <a href="https://www.nature.com/articles/s44182-026-00105-z" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">npj Robotics</a>. &#8220;The environments we care about don&#8217;t come in one size, so we don&#8217;t think the tools should either.&#8221;</p>
<p>Currently an assistant professor of mechanical and aerospace engineering at the <a href="https://engineering.nyu.edu/research/centers/nyu-center-robotics-and-embodied-intelligence-creo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NYU Center for Robotics and Embodied Intelligence</a>, Obayashi led the project while completing her PhD in the <a href="https://www.epfl.ch/labs/create/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Computational Robot Design &#038; Fabrication Lab</a>, led by Josie Hughes, in EPFL’s School of Engineering.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/79142cbb.jpg" alt="" width="647" height="407" class="alignnone size-full wp-image-221238" srcset="https://robohub.org/wp-content/uploads/2026/09/79142cbb.jpg 647w, https://robohub.org/wp-content/uploads/2026/09/79142cbb-425x267.jpg 425w" sizes="(max-width: 647px) 100vw, 647px" /><em>ScaFi at 0.6, 1.1, and 2.9 meters long. 2026 CREATE Lab EPFL. CC BY SA-4.0.</em></p>
<h4>Studying different environments systematically</h4>
<p>ScaFi has a rigid front section and a flexible tail made of fiberglass rods. A single motor pulls two tendons that cross near the tail&#8217;s end, producing the &#8220;S&#8221;-shaped bend required for fish-like swimming motion.</p>
<p>The diameter of the rods forming the tail are the only part that must change with the size of the robot. They grow proportionally thicker as the robot scales up, to preserve similar tail-bending behavior. The underlying motor mechanism and crossed-tendon system stay the same.</p>
<p>That matters because it could cut the engineering effort needed to build fish-like robots for different environments. It also gives researchers a platform for studying how swimming performance changes with scale, a question that&#8217;s hard to study systematically in animals or custom-made robots alike.</p>
<h4>Into the water!</h4>
<p>The team built three robots — roughly 0.6, 1.1, and 2.9 meters long — and tested how well each swam. In collaboration with EPFL’s <a href="https://www.epfl.ch/labs/unfold/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Unsteady Flow Diagnostics Lab</a>, led by Karen Mulleners, the researchers found that the smallest robot produced swirling water patterns similar to those left by real fish, and across all three sizes, swimming motion lined up closely once adjusted for body size. This suggests that that the scaling approach preserved the fish-like gait even as the robots grew nearly fivefold in length.</p>
<p>They also deployed the robots in the field: the medium-sized one in a Swiss stream, the largest on Lake Geneva, the smallest in creeks only 15–30 centimeters deep. During the stream test, the robot kept swimming even after a GPS dropout.</p>
<p>Energy efficiency proved harder to scale. The two smaller robots performed similarly, but the largest was consistently less efficient and needed a different, more powerful motor. The authors suggest drag and inertia may be to blame, though the exact cause is unresolved, meaning the team scaled the swimming motion itself more cleanly than the energy it takes to produce it.</p>
<p>A similar tradeoff showed up in disturbance tests. The smallest robot was most agile but recovered slowest after being knocked off course, while the larger robots were less nimble but more stable.</p>
<p>The same approach, scaling around one key structural parameter, could apply to other compliant robots, including ones outside water. Whether energetic performance can be scaled as successfully as the swimming motion remains an open question.</p>
<h4>Funding</h4>
<p>This research was partially funded by the European Union&#8217;s Horizon 2020 program under Marie Skłodowska-Curie grant agreement No. 945363.</p>
<h4>Reference</h4>
<p>Obayashi, N., Anastasiadis, A., Gumowski, J. et al. <a href="https://www.nature.com/articles/s44182-026-00105-z" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ScaFi: length-scalable, compliant, parametric robotic fish design for operation in multiple environmental niches</a>. npj Robot (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 163 &#8211; Robots helping people, with Aaron Edsinger</title>
		<link>https://robohub.org/robot-talk-episode-163-robots-helping-people-with-aaron-edsinger/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 25 Sep 2026 11:54:14 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221394</guid>

					<description><![CDATA[Claire chatted to Aaron Edsinger from Hello Robot about their Stretch robots that can help people with mobility issues live more independently. Aaron Edsinger is CEO and Co-Founder of Hello Robot, a robotics company dedicated to developing practical, safe, and accessible robots for people. With a passion for building robots and robot companies, Aaron has [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-medium wp-image-221396" src="https://robohub.org/wp-content/uploads/2026/09/Aaron-Edsinger-385x425.png" alt="" width="385" height="425" srcset="https://robohub.org/wp-content/uploads/2026/09/Aaron-Edsinger-385x425.png 385w, https://robohub.org/wp-content/uploads/2026/09/Aaron-Edsinger-927x1024.png 927w, https://robohub.org/wp-content/uploads/2026/09/Aaron-Edsinger-768x849.png 768w, https://robohub.org/wp-content/uploads/2026/09/Aaron-Edsinger.png 1086w" sizes="(max-width: 385px) 100vw, 385px" />
<p>Claire chatted to Aaron Edsinger from Hello Robot about their Stretch robots that can help people with mobility issues live more independently.</p>
<iframe src="https://play.libsyn.com/embed/episode/id/42966228/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe>

<p class="wp-block-paragraph">Aaron Edsinger is CEO and Co-Founder of <a href="https://hello-robot.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Hello Robot</a>, a robotics company dedicated to developing practical, safe, and accessible robots for people. With a passion for building robots and robot companies, Aaron has founded four companies focused on bringing human collaborative robots to the consumer, manufacturing, healthcare and research markets. As Robotics Director at Google, he led the business, product and technical development of two of Google’s central investments in robotics, and helped to define the overall robotics strategy.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>An open source approach to physical AI from Intrinsic</title>
		<link>https://robohub.org/an-open-source-approach-to-physical-ai-from-intrinsic/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Fri, 25 Sep 2026 08:41:15 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221427</guid>

					<description><![CDATA[Deborah Lupton / Pop Chips / Licenced by CC-BY 4.0 Intrinsic (an AI robotics group at Google) announced that the company is making parts of its platform open source. Intrinsic Core™ is a set of ROS-compatible capabilities for building sophisticated robotic applications. The capabilities included in the open source package are as follow: Intrinsic Control. [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/DeborahLupton-PopChips-1280x678-1-1024x542.jpg" alt="A repeating pattern of a photograph of a silicon chip, recoloured so that it is multi-coloured, in the style of pop art." width="1024" height="542" class="alignnone size-large wp-image-221430" srcset="https://robohub.org/wp-content/uploads/2026/09/DeborahLupton-PopChips-1280x678-1-1024x542.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/DeborahLupton-PopChips-1280x678-1-425x225.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/DeborahLupton-PopChips-1280x678-1-768x407.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/DeborahLupton-PopChips-1280x678-1.jpg 1280w" sizes="(max-width: 1024px) 100vw, 1024px" /><em><a href="https://zenodo.org/records/18929888" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Deborah Lupton</a> / <a href="https://betterimagesofai.org/images?artist=DeborahLupton&#038;title=PopChips" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Pop Chips</a> / <a href="https://creativecommons.org/licenses/by/4.0/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Licenced by CC-BY 4.0</a></em></p>
<p>Intrinsic (an AI robotics group at Google) <a href="https://www.intrinsic.ai/blog/posts/introducing-intrinsic-core" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">announced</a> that the company is making parts of its platform open source. <a href="https://www.intrinsic.ai/intrinsic-core" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Intrinsic Core<img src="https://s.w.org/images/core/emoji/17.0.2/72x72/2122.png" alt="™" class="wp-smiley" style="height: 1em; max-height: 1em;" /></a> is a set of ROS-compatible capabilities for building sophisticated robotic applications. </p>
<p>The capabilities included in the open source package are as follow:</p>
<ul>
<li><strong>Intrinsic Control</strong>. A hardware-agnostic, real-time control framework that delivers sensor-based control. It allows the robot to dynamically adapt its behavior mid-trajectory based on changes in the environment. It is designed to deliver efficient, collision-free paths. The idea is that users can swap out different robot arms, grippers, sensors, and more without needing to rewrite drivers.</li>
<li><strong>Pose estimation</strong>. Provides an accurate six degrees of freedom pose estimation of 3D parts. </li>
<li><strong>Motion planning</strong>. Logic auto-generates efficient paths while avoiding collisions. </li>
<li><strong>Grasp planning</strong>. Designed to enable various grippers to automatically and dynamically adapt to the location and orientation of a part and grasp it with a higher probability of success. </li>
<li><strong>Simulation services</strong>. These aim to provide a straightforward way to test and troubleshoot robotic solutions that update as you build.</li>
<li><strong>Camera calibration</strong>. Automates how a robot’s camera can be calibrated and physically aligned</li>
<li><strong>Intrinsic-ROS drivers</strong>. Pre-configured, ROS-compatible drivers for supported robots, grippers, and 3D cameras.</li>
</ul>
<p>Alongside this package, Intrinsic has also released Open Machine Tending Solution (OMTS). This is a ready-made reference design for a real-world use case. The intention is to give developers a starting point to customize their own solution, without needing to build from scratch.</p>
<p>You can download Intrinsic Core on GitHub <a href="https://github.com/intrinsic-ai/intrinsic-core" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>What&#8217;s coming up at #IROS2026?</title>
		<link>https://robohub.org/whats-coming-up-at-iros2026/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Thu, 24 Sep 2026 09:50:46 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221324</guid>

					<description><![CDATA[The 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026) will be held from 27 September &#8211; 1 October in Pittsburgh, USA. The programme includes plenary and keynote talks, workshops, tutorials, forums, competitions, and a debate. Keynote talks The keynote talks will be held from 28 &#8211; 30 September: Elena De Momi &#8211; [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/IROS2026logo.jpeg" alt="" width="768" height="499" class="alignnone size-full wp-image-221325" srcset="https://robohub.org/wp-content/uploads/2026/09/IROS2026logo.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/IROS2026logo-425x276.jpeg 425w" sizes="(max-width: 768px) 100vw, 768px" /></p>
<p>The <a href="https://2026.ieee-iros.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2026 IEEE/RSJ International Conference on Intelligent Robots and Systems</a> (IROS 2026) will be held from 27 September &#8211; 1 October in Pittsburgh, USA. The programme includes plenary and keynote talks, workshops, tutorials, forums, competitions, and a debate. </p>
<h4>Keynote talks</h4>
<p>The keynote talks will be held from 28 &#8211; 30 September: </p>
<ul>
<li><strong>Elena De Momi</strong> &#8211; <em>Open Questions on the Road to Autonomous Surgery</em></li>
<li><strong>Naomi Fitter</strong> &#8211; <em>Socially-Informed Context Awareness for Robots in Human-Populated Settings</em></li>
<li><strong>Greg Chirikjian</strong> &#8211; <em>From Hyper-Redundancy to Robot Imagination and Affordance Learning</em></li>
<li><strong>Genta Suzuki</strong> &#8211; <em>Fujitsu Kozuchi Physical OS: A Research Strategy for Scalable Physical AI</em></li>
<li><strong>Gaurav Bansal</strong> &#8211; <em>Title to be confirmed</em></li>
<li><strong>Al Rizzi</strong> &#8211; <em>Developing Advanced Robot Capability at the RAI Institute</em></li>
<li><strong>Yekai Sun</strong> &#8211; <em>Tokens of the Physical World: Accelerating Intelligence Emergence via Multimodal Embodied Data</em></li>
<li><strong>He Wang</strong> &#8211; <em>Towards the AlphaGo and ChatGPT Moments of Embodied AI</em></li>
<li><strong>Jen Jen Chung</strong> &#8211; <em>All data are equal, but some data are more equal than others</em></li>
<li><strong>Yigit Menguc</strong> &#8211; <em>Soft Robotics, Tensegrity, and the People Who Love Them</em></li>
<li><strong>Robin Murphy</strong> &#8211; <em>Rethinking Disaster Robotics: The Open Questions That Matter Now</em></li>
<li><strong>Gina Olson</strong> &#8211; <em>Embracing Design Complexity: A Biomimetic Approach to (Soft?) Snake Robots</em></li>
<li><strong>Tim Bretl</strong> &#8211; <em>How you can be part of a revolution in composite manufacturing</em>
<li><strong>Lael Odhner</strong> &#8211; <em>Big bets in manipulation systems: where is the frontier today?</em></li>
<li><strong>David Held</strong> &#8211; <em>Robots That Learn After Deployment: Designing Policies for Fast Adaptation</em></li>
<li><strong>Ankur Mehta</strong> &#8211; <em>Robotics problems that robotics can&#8217;t solve</em></li>
<li><strong>Brittany Duncan</strong> &#8211; <em>Patterns from the Field: how contextual lessons can inform robot design</em></li>
<li><strong>Ralph Hollis</strong> &#8211; <em>Lorentz Levitation Technology for Fine Motion Robotics, Haptic Interaction, and Vibration Isolation</em></li>
<li><strong>Genki Yamauchi</strong> &#8211; <em>From Big Sites to Every Site: Extending Construction Robotics to the Work Done by Hand</em></li>
<li><strong>Nancy Pollard</strong> &#8211; <em>Title to be confirmed</em></li>
</ul>
<h4>Forums</h4>
<p>Community discussion sessions open to all attendees, these forums will be held on Monday 28 and Tuesday 29 September.</p>
<ul>
<li><em>Monday 28 (afternoon):</em> US Government Funding</li>
<li><em>Tuesday 29 (morning):</em> Robotics Education: Experiential Learning</li>
<li><em>Tuesday 29 (afternoon):</em> Is Robotics Underinvesting in Its Own Foundations?</li>
</ul>
<h4>Plenary panels</h4>
<p>Three plenary panels will be held: </p>
<ul>
<li><em>Monday 28:</em> Start-ups and entrepreneurship</li>
<li><em>Tuesday 29:</em> Space</li>
<li><em>Wednesday 30:</em> Should robots be generalists or specialists?</li>
</ul>
<h4>Workshops and tutorials</h4>
<p>There are 44 workshops and tutorials planned for Sunday 27 September, with a further 42 scheduled for Thursday 1 October. You can find out more about these <a href="https://2026.ieee-iros.org/program/workshops-tutorials/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<h4>Introduction to science communication</h4>
<p>Join Sabine Hauert (University of Bristol and Robohub), Ella Scallan (Robohub), and Evan Ackerman (IEEE Spectrum) for a science communication crash course. This will take place at 11:00 on Tuesday 29 September. Find out more <a href="https://2026.ieee-iros.org/program/society-events/#science-communication-crash-course" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<h4>Find out more</h4>
<ul>
<li><a href="https://2026.ieee-iros.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Conference webpage</a></li>
<li><a href="https://2026.ieee-iros.org/program/technical-tours/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Technical tours</a></li>
<li><a href="https://2026.ieee-iros.org/program/competitions/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Competitions</a></li>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotics roadmaps from around the world spotlight of the month: China</title>
		<link>https://robohub.org/robotics-roadmaps-from-around-the-world-spotlight-of-the-month-china/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 23 Sep 2026 08:20:26 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221313</guid>

					<description><![CDATA[China is targeting the next industrial revolution by doubling down on embodied AI and humanoid robotics, building directly on its vast manufacturing infrastructure. By Ellen H. Rumley and Allison Okamura Beyond the Robot Olympics Chinese robots have quickly entered global public consciousness in recent years, appearing as background robo-dancers in pop concerts and as humanoid [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/STB-china.jpeg" alt="" width="1080" height="880" class="alignnone size-full wp-image-221316" srcset="https://robohub.org/wp-content/uploads/2026/09/STB-china.jpeg 540w, https://robohub.org/wp-content/uploads/2026/09/STB-china-425x346.jpeg 425w" sizes="(max-width: 1080px) 100vw, 1080px" /></p>
<p><em>China is targeting the next industrial revolution by doubling down on embodied AI and humanoid robotics, building directly on its vast manufacturing infrastructure.</em></p>
<hr>
<p><strong>By Ellen H. Rumley and Allison Okamura</strong></p>
<h4>Beyond the Robot Olympics</h4>
<p>Chinese robots have quickly entered global public consciousness in recent years, appearing as background robo-dancers in pop concerts and as humanoid marathon and sprint runners outpacing elite athletes (<a href="https://english.news.cn/20251231/0a082888ab384fcaa572ee7a11ae7d9d/c.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">1</a>). Domestically, robots are deployed as traffic guides and restaurant service staff, while swarms of drones entertain audiences in urban light shows or deliver takeout to high-rises (<a href="https://www.theguardian.com/technology/2026/mar/19/inside-chinas-robotics-revolution" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2</a>, <a href="https://www.technologyreview.com/2023/05/23/1073500/drone-food-delivery-shenzhen-meituan/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">3</a>). These public debuts serve to both normalize automation in everyday civilian life (<a href="https://www.mri.co.jp/en/knowledge/article/202502_3.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">4</a>) while projecting international soft power.</p>
<p>Behind the public spectacle lies a bold agenda for global economic dominance. In its geopolitical contest with the United States, Beijing sees robotics as the core engine to project power and dictate the future of global supply chains (<a href="https://chinapower.csis.org/china-industrial-robots/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">5</a>). This ambition is further accelerated by domestic drivers of an aging population and a shrinking industrial workforce, compounded by the legacy of the one-child policy and rapid urbanization. Alongside targeted talent acquisition initiatives like the K-Visa (<a href="https://www.chinadaily.com.cn/a/202509/10/WS68c0d3bfa3108622abc9feaa.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">6</a>, <a href="https://www.cnbc.com/2025/10/01/cnbcs-the-china-connection-newsletter-chinas-k-visa-plans-spark-worries-of-a-talent-flood.html?msockid=062529b9c15461b83c7f3f9fc0866067" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">7</a>), China aims to pioneer a new era of industrial leadership while mitigating a long-term structural gap through a state-orchestrated robotics surge.</p>
<h4>Five-Year Plans (FYPs)</h4>
<p>The Chinese Communist Party leverages its central authority to align state enterprise, private capital, and supply chains towards common strategic objectives, carrying the momentum to implement sweeping technological changes. Since the 1950s, every five years the government has produced large-scale roadmaps detailing major objectives mandated across its various levels of government. Called the Five-Year Plans (FYPs) – these documents provide bold economic development initiatives that are credited for structural reform like the opening of China to foreign trade in the 1980s (<a href="https://link.springer.com/chapter/10.1007/978-981-19-5904-2_3" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">8</a>). The FYPs have been influential in strengthening the nation’s manufacturing base and is now playing a defining role in advancing Chinese robotics.</p>
<h4>FYP13 &#038; FYP14: Made in China</h4>
<p>The 13th FYP (2016-2020) laid the critical foundation of China’s robotics ascent and operationalized Made in China 2025 (MIC2025), a campaign to transition China from a “low-cost global factory floor” into a sovereign high-tech manufacturing leader (<a href="https://www.jhwhitney.com/documents/FG/jhwhitney/newsite/research/647758_Made_in_China_2025_set_the_tempo_of_Chinas_industrial_ambitions___World_Economic_Forum.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">9</a>). While most leading industrial nations historically outsourced production, China, as a historical receiver of outsourced production, took advantage of their vast manufacturing infrastructure to invest early into physical foundries and integrated supply chains that many nations are now spending heavily on to re-shore within their own borders (<a href="https://voxdev.org/topic/macroeconomics-growth/how-china-became-worlds-factory-trade-industrial-policy-and-growth" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">10</a>). Key goals of MIC2025 were to climb up the global value chain across strategic sectors like robotics, using massive government subsidies to offset production costs (<a href="https://cepr.org/voxeu/columns/two-decades-chinese-industrial-subsidies" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">11</a>). While many international critics condemned these subsidies as market distortion and imposed sanctions as a response (<a href="https://archivemacropolo.org/analysis/made-in-china-2025-dropped-media-analysis?rp=m" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">12</a>), paradoxically this intensified Beijing’s efforts towards a sovereign tech sector.</p>
<p>Foreign frictions did ultimately lead Beijing to retire the branding “Made in China 2025”, but its core robotics objectives were carried out through focused sectoral plans in the 14th FYP (2021-2025). The Ministry of Industry and Information Technology (MIIT) even introduced two robot-specific initiatives: the “14th Five Year Plan for the Robotics Industry” (2021), which granted state-support for R&#038;Ds in an effort to replace foreign suppliers of critical robotic components with domestic supplies, as well as the “Robot + Application Action Plan” (2023), which stimulated robotics demand by mandating adoption of domestic robotics across ten key sectors including agriculture, logistics, and health. This dual coordination of supply and demand, along with the push for general industrial leadership, enabled several impressive milestones to be achieved by 2025: China increased domestic market shares in industrial robots from 30% to 57% within a decade (<a href="https://www.therobotreport.com/2014-was-another-record-year-for-robotics/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">13</a>, <a href="https://ifr.org/downloads/papers/Executive_Summary_-_World_Robotics_RD_Programs_V04.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">14</a>), and domestic suppliers for industrial robots became market leaders for the first time (<a href="https://ifr.org/ifr-press-releases/news/top-5-global-robotics-trends-2026" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">15</a>). They reached 295,000 units of industrial robot installations in 2025 alone – 54% of all global installations that year – and entered the top five global manufacturers rankings for industrial robotics. Regional robotics hubs also flourished, including AI R&#038;D clusters in Shanghai, hardware manufacturing bases in the Yangtze River Delta (<a href="https://journals.sagepub.com/doi/10.1177/10245294241261878" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">16</a>) and a growing startup ecosystem in Shenzhen (<a href="https://merics.org/en/report/embodied-ai-chinas-ambitious-path-transform-its-robotics-industry" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">17</a>) – creating a full-stack environment capable of rapidly prototyping fully integrated robotic systems. Local sourcing of many basic hardware components was further made possible by the massive mining and refining infrastructure that China possesses – which processes over 70% of the global production of rare earths like neodymium, which are critical for hardware like electromagnetic motors (<a href="https://www.statista.com/chart/35398/china-dominant-share-in-global-mining-production-of-critical-minerals/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">18</a>).</p>
<h4>Bottlenecks in Precision Hardware &#038; Semiconductors</h4>
<p>The 13th and 14th FYPs propelled China into a position of industrial robotic leadership in production scale, installation quantity, and cost effectiveness. Despite their indisputable achievements, some critical milestones were not met. For one, domestic robotics supply chains did not approach the levels of self-sufficiency expected by 2025. While Chinese robotics command near totality of domestic market shares in lower-stakes industries like textiles, they captured closer to 30% of domestic market shares for higher stakes sectors like automotive industries (<a href="https://chinapower.csis.org/china-industrial-robots/#:~:text=China&#039;s%20degree%20of%20robotics%20self%2Dreliance%20varies%20considerably,of%20robots%20reportedly%20come%20from%20Chinese%20firms." data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">5</a>), and even less so – at 15%  – for high-end machine tools (<a href="https://rhg.com/research/was-made-in-china-2025-successful/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">19</a>). This disparity stems from a historical deficit in high-precision engineering in China. Key components essential for durable industrial-grade robots, such as strain-wave reducers, precision gearboxes, and high-performance servo motors, remain reliant on imports from Japan and Germany (<a href="https://www.uscc.gov/research/made-china-2025-evaluating-chinas-performance#_Toc213921797" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">20</a>), where precision manufacturing traditions are backed by decades of institutional standards and specialized labor (<a href="https://www.sciencedirect.com/science/article/pii/0141635979900771" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">21</a>, <a href="https://onlinelibrary.wiley.com/doi/10.1111/jpim.12766" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">22</a>). The incoming 15th FYP does address this shortcoming, however, and prioritizes China’s advancement of precision hardware in the coming years (<a href="https://thediplomat.com/2026/03/chinas-new-five-year-plan-prioritizes-robotics-the-world-should-pay-attention/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">23</a>).</p>
<p>Concurrently, Beijing fell short of its goal to achieve 70% self-sufficiency in semiconductor manufacturing, missing the mark by an estimated 40% (<a href="https://www.csis.org/analysis/chinas-localization-drive-semiconductors-gains-impetus-allied-chip-export-controls" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">24</a>). This discrepancy highlights a bottleneck for China’s robotics ambitions, which depend on advanced logic chips for model training. The sharp decline in Chinese purchases of U.S. AI chips by late 2025 reflects an accelerated push toward domestic chip sovereignty (<a href="https://www.brookings.edu/articles/ball-games-over-the-us-is-out-of-the-ai-chip-market-in-china/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">25</a>). Against the backdrop of export controls from the U.S. and rising tensions across the Taiwan Strait—the global leader of semiconductor manufacturing (<a href="https://www.nytimes.com/2026/02/24/technology/taiwan-china-chips-silicon-valley-tsmc.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">26</a>) – Beijing’s pursuit of computational autonomy serves to protect itself against supply chain chokepoints that could derail its incoming robotics plans.</p>
<h4>FYP15: Embodied AI with a Human Form</h4>
<p>The 15th Five Year Plan (2026-2030) marks a strategic shift from traditional advanced automation towards ‘embodied intelligence’ – defined as AI that physically interacts with real-world environments. Elevated to one of China’s top priority “future industries”, embodied AI is tasked with driving economic growth while modernizing national defense (<a href="https://ifr.org/ifr-press-releases/news/china-makes-ai-powered-robots-core-of-national-strategy" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">27</a>, <a href="https://jamestown.org/new-military-civil-fusion-body-for-prc-robotics-ecosystem/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">28</a>). Elevating embodied AI from a niche subgoal to a central industry priority carries significant policy weight; central ministries, provincial governments, and state financial institutions are now mandated to tightly coordinate robotics development, reallocating substantial shares of state-backed venture capital and guidance funds to the sector (<a href="https://thediplomat.com/2026/03/chinas-new-five-year-plan-prioritizes-robotics-the-world-should-pay-attention/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">23</a>).</p>
<p>Much like the 13th and 14th FYPs laid the groundwork for industrial automation, the 15th FYP launches a major campaign to accelerate physical AI through the “AI Plus Action Plan” (<a href="https://www.gov.cn/zhengce/content/202508/content_7037861.htm" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">29</a>). Under this initiative, Beijing is pushing for the widespread diffusion of low-cost, high-efficiency AI infrastructure across society – both domestically and across the Global South. AI integration is targeted across science, education, agriculture, green technology, defense, governance, and industrial development. Instead of pushing the frontiers of AI development, this policy prioritizes practical cross-sectoral applications that may already be feasible for domestic AI semiconductor chips – driving the iterative hardware advancements needed for Beijing’s long-term technology sovereignty (<a href="https://www.dw.com/en/china-chips-semiconductor-industry-us-technology-artificial-intelligence/a-76056790" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">30</a>). And as physical embodiment of AI, robots are expected to soon play a pivotal role in these directives (<a href="https://thediplomat.com/2026/03/chinas-new-five-year-plan-prioritizes-robotics-the-world-should-pay-attention/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">23</a>). The real-world interaction of robots could provide vast physical dataset spillovers that further accelerate AI capabilities – a process supported by policies like “sandbox regulations” designating specific urban zones for real-world testing and training (<a href="https://chinafyp.com/BilingualReader?part=2" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">31</a>).</p>
<p>The 15th FYP specifically emphasizes the development of embodied AI in humanoid form factors. State subsidies are flooding the humanoid sector along large investments from tech giants like Huawei and Alibaba (<a href="https://chinabizinsider.com/huawei-backs-gigaai-in-latest-bet-on-chinas-booming-humanoid-robot-sector/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">32</a>, <a href="https://www.cnbc.com/2025/09/08/alibaba-leads-100-million-investment-in-chinese-humanoid-robot-startup.html?msockid=062529b9c15461b83c7f3f9fc0866067" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">33</a>), signaling a push from government and private entities alike towards the mass-deployment of humanoids in a manner reminiscent of the Chinese global domination of the electric vehicle (EV) market (<a href="https://www.sciencedirect.com/science/article/pii/S0928765523000799" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">34</a>, <a href="https://static1.squarespace.com/static/5b48c76fb98a78701dd7f077/t/6a257acaca7dbc0fe9800f28/1780841162023/Lu_Ma_2026_Rise+of+China%27s+EV+Industry.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">35</a>). Owing also to the hardware surplus and supply chain synergies resulting from the EV push (<a href="https://www.nytimes.com/2026/06/11/business/china-robots-humanoid.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">36</a>), China has already managed to scale its domestic humanoid sector to over 150 companies – resulting in 15,000 global installations, equivalent to 85% of global humanoid deployments in 2025 during the country’s first year of mass production (<a href="https://chinabizinsider.com/chinas-humanoid-robot-dominance-what-it-means-for-the-global-economy/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">37</a>, <a href="https://english.ckgsb.edu.cn/knowledge/article/humanoid-robots-in-china-progress-limits-and-reality/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">38</a>). Efforts for mass production were especially prominent at this year’s International Conference on Robotics and Automation (ICRA 2026), where Chinese humanoids and dexterous hand start-ups dominated the exhibit floor. Clearly, Beijing views humanoids as a leapfrog technology that could spearhead the next industrial revolution.</p>
<p>There are ongoing debates within the robotics community as to whether humanoids are the ideal form factor for general-purpose robots. On one hand, redundant joints for appearing human-like could introduce unnecessary mechanical inefficiencies and control complexity. On the other hand, humanoids could be, with enough data, an ideal form factor for interacting with everyday objects and urban spaces designed with people in mind.</p>
<p>Indeed, China’s focus on the humanoid form factor aligns closely with its data aggregation strategy: mapping directly to human workers allows a seamless transfer of human motion data into imitation learning models. In line, by July 2026, 40 humanoid training facilities had opened across major Chinese cities (<a href="https://restofworld.org/2026/china-robots-training-centers-workers/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">39</a>). In these hubs, humanoids from various domestic manufacturers are pooled to train basic skills – such as grasping and transport – in simulated real-world scenarios (<a href="https://www.globaltimes.cn/page/202607/1366926.shtml" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">40</a>). Human operators wearing VR headsets and exoskeletons teleoperate the robots through task execution, capturing raw motion and spatial data. This supervised training is repeated hundreds of times daily, cleaned, labeled, and shared across manufacturers as foundational reference datasets. This shared public infrastructure enables scalable low-cost training useful for AI model developers – underpinning a broader national strategy towards leadership in generalizable physical AI (<a href="https://govwhitepapers.com/whitepapers/chinas-embodied-ai" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">41</a>).</p>
<p>Ultimately, Beijing is placing a large gamble on humanoids. While concentrating national resources has propelled China into the global market lead, it also exposes the sector to severe structural risks. Intense domestic competition can drive down hardware prices, squeeze profit margins and place firms at risk of overcapacity (<a href="https://www.nytimes.com/2025/12/17/business/china-robot-unitree-ubtech.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">42</a>). Because policy-driven supply currently outpaces market demand, only a fraction of today’s 150+ companies are expected to survive the coming years (<a href="https://www.reuters.com/investigations/chinas-humanoid-robots-arent-smart-enough-take-your-job-yet-2026-08-27/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">43</a>, <a href="https://advisor.morganstanley.com/john.howard/documents/field/j/jo/john-howard/The_Humanoid_100_-_Mapping_the_Humanoid_Robot_Value_Chain.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">44</a>). While parallel R&#038;D efforts can spur rapid innovation, the absence of a strong commercial demand risks investments from Beijing amounting to waste, which would further strain local government budgets.</p>
<p>This risk extends to investors as well: when government backing signals long-term viability before demand has caught up, the speculative value of humanoids can inflate beyond justification, creating conditions of volatility we see mostly recently playing out in the market. Unitree Robotics, the leading Chinese humanoid and quadruped manufacturer illustrates this pattern as it went public on the Shanghai Stock Exchange; shares surged as much as 629% intraday and has dropped by nearly 45% in the days following (<a href="https://www.reuters.com/business/finance/china-robot-maker-unitrees-post-listing-slump-sparks-bubble-fears-2026-08-25/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">45</a>).</p>
<p>Ultimately, China’s 15th FYP represents a high-risk, high-reward strategy, leveraging state coordination and massive data scale to brute-force the commercial viability of humanoid robots. Whether Beijing succeeds in leapfrogging the world in embodied AI or stumbles under the weight of market overcapacity will carry high consequences for the international robotics industry and society at large.</p>
<p>Thanks for reading. Next up, we will be taking a road(map)-trip across the European Union and examine Brussels’ contrasting regulatory approaches to robotics.</p>
<hr>
<p>Ellen H. Rumley – Policy Analyst</p>
<p>Allison Okamura – Vice President</p>
<p><em>IEEE RAS Science &#038; Technology Watch Board </em></p>
<hr>
<h4>References</h4>
<ol>
<li>Ye, Ziyin. “Yearender: China’s Humanoid Robots Step from Spectacle toward Scalable Industrial Reality.” Xinhua, 31 Dec. 2025.</li>
<li>Che, Chang. “Inside China’s Robotics Revolution.” The Guardian, 19 Mar. 2026.</li>
<li>Yang, Zeyi. “Food Delivery by Drone Is Just Part of Daily Life in Shenzhen.” MIT Technology Review, 23 May 2023.</li>
<li>“How Different Countries Perceive Robots: An Original Survey.” Mitsubishi Research Institute, Feb. 2025.</li>
<li>Grant-Chapman, Hugh, et al. “Is China leading the Robotics Revolution?” ChinaPower Project, Center for Strategic and International Studies, 12 Feb. 2026.</li>
<li>“Robotics Revolution Driving Industrial Transformation.” China Daily, 10 Sept. 2025.</li>
<li>Bao, Anniek. “China’s K-Visa Plans Spark Worries of a Talent Flood.” CNBC, 1 Oct. 2025.</li>
<li>Yin, Ju and Xu, Jia. “Made in China 2025 and Industrial Upgrade.” SpringerLink, Springer, 2023.</li>
<li>Kuo, Kaiser. “Made in China 2.0: The future of global manufacturing?” World Economic Forum / J.H. Whitney &#038; Co., 26 June 2025.</li>
<li>Amodio, Francesco, et al. “How China Became the World’s Factory: Trade, Industrial Policy, and Growth.” VoxDev, 18 Feb. 2026.</li>
<li>Xiang, Shuhui, et al. “Two Decades of Chinese Industrial Subsidies.” VoxEU, Centre for Economic Policy Research, 7 Jan. 2026.</li>
<li>“Made in China 2025 Dropped: Media Analysis.” MacroPolo, 15 Mar. 2019.</li>
<li>Tobe, Frank. “2014 Was Another Record Year for Robotics.” The Robot Report, 11 Apr. 2014.</li>
<li>Kim, Jenny, et al. “World Robotics R&#038;D Programs.” International Federation of Robotics, 1 Jan. 2025.</li>
<li>“Top 5 Global Robotics Trends 2026.” International Federation of Robotics, 8 Jan. 2026.</li>
<li>Andreoni, Antonio, et al. “China’s Industrial Policy and Robotics Automation.” Global Media and Communication, SAGE Publications, 2 Aug. 2024.</li>
<li>Chang, Wendy, et al. “Embodied AI: China’s Ambitious Path to Transform Its Robotics Industry.” Mercator Institute for China Studies (MERICS), 30 Apr. 2026.</li>
<li>Gaudiaut, Tristan. “China’s Dominant Share in Global Mining Production of Critical Minerals.” Statista, 5 Nov. 2025.</li>
<li>“Was Made in China 2025 Successful?” Rhodium Group, 5 May 2025.</li>
<li>“Made in China 2025: Evaluating China’s Performance.” U.S.-China Economic and Security Review Commission, 14 Nov. 2025.</li>
<li>Tsuwa, Hideo, et al. “Precision Engineering and Industrial Automation Development.” Precision Engineering, ScienceDirect, Jan. 1979.</li>
<li>Lampe, Hannes W., et al. “Product Innovation and Industrial Policy in Emerging Markets.” Journal of Product Innovation Management, Wiley, 27 Nov. 2024.</li>
<li>Cheung, Sunny. “China’s New Five-Year Plan Prioritizes Robotics: The World Should Pay Attention.” The Diplomat, Mar. 2026.</li>
<li>Shivakumar, Sujai, et al. “China’s Localization Drive in Semiconductors Gains Impetus Allied Chip Export Controls.” Center for Strategic and International Studies, 24 Mar. 2026.</li>
<li>MacCarthy, Mark. “Ball Game’s Over: The US Is Out of the AI Chip Market in China.” Brookings Institution, 17 Jun. 2026.</li>
<li>Mickle, Tripp. “Taiwan, China, Chips, and Silicon Valley.” The New York Times, 24 Feb. 2026.</li>
<li>“China Makes AI-Powered Robots Core of National Strategy.” International Federation of Robotics, 5 May 2026.</li>
<li>Cheung, Sunny. “New Military-Civil Fusion Body for PRC Robotics Ecosystem.” China Brief, Jamestown Foundation, 18 Dec. 2025.</li>
<li>“State Council Policy Briefing on Technological Advancement and Industry Guidelines.” The State Council of the People’s Republic of China, 21 Aug. 2025.</li>
<li>Martin, Nik. “China Chips and Semiconductor Industry: US Technology Constraints and Artificial Intelligence.” Deutsche Welle, 20 Apr. 2026.</li>
<li>“China’s 15th Five Year Plan Explorer.” China FYP.</li>
<li>“Huawei Backs GigaAI in Latest Bet on China’s Booming Humanoid Robot Sector.” China Biz Insider, 28 Nov. 2025.</li>
<li>Cheng, Evelyn. “Alibaba Leads $100 Million Investment in Chinese Humanoid Robot Startup.” CNBC, 8 Sept. 2025.</li>
<li>Zhang, Tong, et al. “Empirical Analysis of Technological Innovation and Robotics Integration.” Journal of Asian Economics, ScienceDirect.</li>
<li>Lu, Fengming and Ma, Xiao. “Rise of China’s EV Industry.” The China Journal, No. 96, Jul. 2026.</li>
<li>Tobin, Meaghan and Keith Bradsher, Keith. “Why It’s Nearly Impossible to Build a Robot Without China.” The New York Times, 11 Jun. 2026.</li>
<li>Ye, Alice. “China’s Humanoid Robot Dominance: What It Means for the Global Economy.” China Biz Insider, 20 May 2026.</li>
<li>Tao, Ni. “Humanoid Robots in China: Progress, Limits, and Reality.” Cheung Kong Graduate School of Business, 23 Jan. 2026.</li>
<li>Zhou, Viola and Lo, Kinling. “Inside China’s Robot Training Centers for Workers.” Rest of World, 7 Jan. 2026.</li>
<li>Yiyi, Zhang. “China Ramps Up Embodied AI and Next-Gen Robotics Ecosystem.” Global Times, 27 Jul. 2026.</li>
<li>Hannas, William C., et al. China’s Embodied AI Development and Strategic Roadmaps. GovWhitePapers, 1 Dec. 2025.</li>
<li>Tobin, Meaghan and Wu, Xinyun. “Unitree and UBTech Lead China’s Robotics Expansion.” The New York Times, 17 Dec. 2025.</li>
<li>Chen, Laurie, et al. “China’s Humanoid Robots Aren’t Smart Enough to Take Your Job Yet.” Reuters, 27 Aug. 2026.</li>
<li>Jonas, Adam et al. “The Humanoid 100: Mapping the Humanoid Robot Value Chain.” Morgan Stanley Research, 6 Feb. 2025.</li>
<li>“China Robot Maker Unitree’s Post-Listing Slump Sparks Bubble Fears.” Reuters, 24 Aug. 2026.</li>
</ol>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Mars rovers give scientists a ground-level view of the red planet – peek inside their NASA control room</title>
		<link>https://robohub.org/mars-rovers-give-scientists-a-ground-level-view-of-the-red-planet-peek-inside-their-nasa-control-room/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Mon, 21 Sep 2026 09:38:58 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">http://robohub.org/?guid=3a0db0729d8686bde9c4a63421137abe</guid>

					<description><![CDATA[Each day in the control room of the Curiosity rover is jam-packed with important scientific decisions, as a NASA project scientist describes.]]></description>
										<content:encoded><![CDATA[<p><figure><img decoding="async" src="https://images.theconversation.com/files/752877/original/file-20260807-50-uvk49f.jpg?ixlib=rb-4.1.1&amp;rect=181%2C0%2C2636%2C1757&amp;q=45&amp;auto=format&amp;w=1050&amp;h=700&amp;fit=crop" /><figcaption><span class="caption"><em>NASA’s Curiosity Mars rover used two cameras to create this selfie in front of Mont Mercou, a tall rock outcrop.</span> <span class="attribution"><a class="source" href="https://science.nasa.gov/resource/curiositys-selfie-at-mont-mercou/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NASA/JPL-Caltech/MSSS</a></span></em></figcaption></figure>
</p>
<p><strong>By Ashwin R. Vasavada</strong></p>
<p>Lights blink on as I enter the <a href="https://www.jpl.nasa.gov/roc/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Rover Operations Center</a> at NASA’s <a href="https://www.jpl.nasa.gov/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Jet Propulsion Laboratory</a> in Pasadena, California, at 7:30 a.m. I’m the first to arrive, even though I already feel late. </p>
<p>Sometime during the night on Earth, the <a href="https://science.nasa.gov/mission/msl-curiosity/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Curiosity rover</a> finished its day exploring on Mars and beamed its latest collection of images and measurements to a Mars orbiter zooming by overhead. The orbiter relayed the data to Earth, where it now waits on servers here and at partner institutions around the globe.</p>
<p>Once our rover operations shift kicks off at 8:15 a.m., a few dozen engineers and scientists will have just three hours to check the health of the rover, analyze the new science data and agree on the next set of rover activities. Then we’ll spend another four hours turning those plans into rover commands for tomorrow, making sure they are safe and fit within the rover’s available time and energy. Not long after that, the Sun will rise on Mars, and Curiosity will look toward Earth, expecting its next instructions.</p>
<p>As <a href="https://scholar.google.com/citations?user=lw4-KZoAAAAJ&amp;hl=en" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Curiosity’s project scientist</a>, it’s my job to ensure that what emerges from this rush is a set of measurements that advance the mission’s science objectives and keep it on track to achieve what our team promised NASA and, ultimately, the public. It’s a seemingly overwhelming task given everything that must happen in the next seven hours. But after repeating it over a thousand times since Curiosity landed in 2012, our team has gotten pretty good at it. </p>
<div class="keep-aspect"><iframe title="Curiosity Mars Rover Snaps 1.8 Billion-Pixel Panorama (narrated video)" width="500" height="281" src="https://www.youtube-nocookie.com/embed/X2UaFuJsqxk?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<em>NASA Curiosity project scientist Ashwin Vasavada guides this tour of the rover’s view of the Martian surface.</em></p>
<h2>Reading the rocks</h2>
<p><a href="https://science.nasa.gov/mission/msl-curiosity/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NASA created Curiosity</a> to search for evidence of ancient habitable environments, such as those with liquid water and the chemicals, nutrients and energy sources required for life. The investigation called for a long-lived, mobile spacecraft that would allow scientists on Earth to virtually explore a local area on Mars, select and acquire rock samples, and analyze them in onboard laboratories. </p>
<p>JPL responded with the car-size, drill-equipped <a href="https://www.youtube.com/watch?v=liypQHa_dr8%22" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Curiosity rover</a>. NASA added a suite of scientific instruments and a science team from the United States and around the world.</p>
<p>NASA sent Curiosity to Mars’ <a href="https://science.nasa.gov/photojournal/destination-gale-crater-in-august-2012/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Gale Crater</a> to climb Aeolis Mons, a mountain whose 3 miles (5 kilometers) of sedimentary rock layers hold a record of environmental conditions from about 3.5 billion years ago. The evidence suggests that back then a thicker, ancient atmosphere <a href="https://science.nasa.gov/mars/facts/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sheltered flowing streams and sparkling lakes</a>. </p>
<p>Curiosity has climbed through a vertical half-mile (1 kilometer) of rock layers so far, finding clay-rich, mudstone layers that give way at higher elevations to younger sandstones full of salty minerals. Our team determined that lakes persisted for <a href="https://doi.org/10.1007/s11214-022-00882-7" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">millions of years</a> before the climate became arid and sand dunes overtook the lakes, although groundwater occasionally breached the surface to produce streams that wove among the dunes.</p>
<p>Samples Curiosity drilled from the lake sediments contain <a href="https://www.nasa.gov/missions/mars-science-laboratory/curiosity-rover/nasas-curiosity-finds-organic-molecules-never-seen-before-on-mars/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">small organic – meaning carbon-based – molecules</a>, the <a href="https://theconversation.com/ancient-mars-may-have-had-a-carbon-cycle-a-new-study-suggests-the-red-planet-may-have-once-been-warmer-wetter-and-more-favorable-for-life-255207" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">raw materials for potential life</a>. The association of wet environments, organic molecules and a mix of chemicals similar to those that microbes harness for energy on Earth allowed our team to conclude that conditions in Gale were once <a href="http://doi.org/10.1126/science.1242777" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">capable of supporting life</a>. Determining conclusively <a href="https://theconversation.com/scientists-detected-a-potential-biosignature-on-mars-an-astrobiologist-explains-what-these-traces-of-life-are-and-how-researchers-figure-out-their-source-265157" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">whether life actually took hold</a> will require bringing such rocks back to laboratories on Earth.</p>
<h2>Preparing a plan</h2>
<p>As my colleagues arrive in the building and online, I’m lost in the latest images. Curiosity is well into the higher and drier strata of Aeolis Mons, yet the rocks have salts, scours and <a href="https://www.nasa.gov/missions/mars-science-laboratory/curiosity-rover/nasas-curiosity-rover-sees-martian-spiderwebs-up-close/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">other signs of ancient water</a>. These images suggest that perhaps even Mars’ dry period provided habitats for life.</p>
<p>During our previous shift, I asked the engineers who plan the rover’s route to take it into an area that appears exceptionally smooth and flat on images taken from orbit. After years of <a href="https://science.nasa.gov/resource/mars-report-curiosity-rovers-most-challenging-climb-yet/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">rough offroad driving</a>, they were excited to open up the throttle and let the rover drive 120 feet (37 meters) across this Martian “parking lot” – a pretty long distance for Curiosity.</p>
<p><figure class="align-center zoomable">
            <a aria-label="Zoomable image" href="https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=1000&amp;fit=clip" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" alt="A photo of the Martian surface with polygon-shaped rock formations on the surface." src="https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=389&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=389&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=389&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=488&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=488&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/753964/original/file-20260813-50-erzsg1.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=488&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"></a><em>Polygon fractures with honeycomblike textures, discovered by NASA’s Curiosity Mars rover. <a href="https://www.nasa.gov/missions/mars-science-laboratory/curiosity-rover/nasas-curiosity-mars-rover-discovers-field-of-honeycomb-textures/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NASA/JPL-Caltech/MSSS</a></em></figure>
</p>
<p>What I’m looking at now is taking my breath away. Instead of smooth slabs, every surface around the rover is <a href="https://www.nasa.gov/missions/mars-science-laboratory/curiosity-rover/nasas-curiosity-mars-rover-discovers-field-of-honeycomb-textures/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">textured by small polygons</a>, each a few inches across, as if someone covered Mars in honeycomb wallpaper. Our geologists suspect that the polygons outline fractures that formed through drying, like cracks in mud do, or through thermal cycles, or compression.</p>
<p>My computer screen shows the area in front of Curiosity covered by dots, each one representing a candidate target for the rover to observe with its cameras, its laser spectrometer, or the sensors on its arm. There are way too many dots, which is not a bad problem to have. A science team member trained to moderate the day’s discussion begins to narrow the list. Distinguished faculty, postdocs and students from around the world take turns advocating for their target.</p>
<p>The debate centers on what set of images and chemical measurements will best help distinguish how the polygons formed. I’m the tiebreaker if our team can’t quickly reach consensus, but that’s rarely needed. It’s Friday, so the three days of activities we plan for the rover today will take place over the weekend, and the results will arrive for our next shift on Monday. Curiosity works weekends.</p>
<h2>Engineering the uplink</h2>
<p>Later on, I walk into the adjacent room where a robotics engineer visualizes in 3D how Curiosity’s five-jointed arm will reach the winning rock targets. I sit down next to another engineer who is simulating the rover’s next drive. We agree that the terrain ahead is rough: no more parking lot, all curbs. We discuss how she might steer the rover around the rock obstacles to reach the next science waypoint.</p>
<p>By noon, the science team’s role in operations is done, but my colleagues linger online to discuss the latest data in more detail. Meanwhile, the rover and instrument operators begin converting the day’s scientific requests into hundreds of commands that must be sent to <a href="https://www.nasa.gov/communicating-with-missions/dsn/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NASA’s Deep Space Network</a> in a few hours. There’s still a lot to do, but the team is in the homestretch for the day. </p>
<p>On Mars, the horizon is starting to brighten. Before too long, Curiosity will be expecting to hear from us.</p>
<p><img decoding="async" src="https://counter.theconversation.com/content/289022/count.gif" alt="The Conversation" width="1" height="1" /></p>
<p class="fine-print"><em><span>This research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract (80NM0018D0004) with the National Aeronautics and Space Administration.</span></em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Reimagining robotics for sustainability</title>
		<link>https://robohub.org/reimagining-robotics-for-sustainability/</link>
		
		<dc:creator><![CDATA[EPFL]]></dc:creator>
		<pubDate>Fri, 18 Sep 2026 08:59:50 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221188</guid>

					<description><![CDATA[By Celia Luterbacher Imagine a robot designed to install solar panels with much greater speed and precision than a human. The robot is made from expensive materials and powered by a heavy battery that must be recharged every few hours. If the costs of building and operating the robot outweigh the benefits of the clean [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/2216x1244-1024x575.jpg" alt="" width="1024" height="575" class="alignnone size-large wp-image-221189" srcset="https://robohub.org/wp-content/uploads/2026/09/2216x1244-1024x575.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-768x432.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-1536x863.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/2216x1244-2048x1151.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By Celia Luterbacher</strong></p>
<p>Imagine a robot designed to install solar panels with much greater speed and precision than a human. The robot is made from expensive materials and powered by a heavy battery that must be recharged every few hours. If the costs of building and operating the robot outweigh the benefits of the clean energy it helps produce, can it really be considered sustainable?</p>
<p>In a 2025 <a href="https://www.science.org/doi/10.1126/science.adx2444" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">article</a> published in <em>Science</em>, Aude Billard, head of the <a href="https://www.epfl.ch/labs/lasa/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Learning Algorithms and Systems Lab</a> in EPFL&#8217;s School of Engineering and Academic director of the Robotics Center, gives precisely this example to illustrate the tension between robotic performance and sustainability. Roboticists, she argues, can no longer ignore the fact that robots use energy-intensive power systems and electronic components made from finite resources.</p>
<p>At the same time, robots have the potential to contribute to addressing some of society’s most pressing sustainability challenges, for example through environmental and biodiversity monitoring, precision agriculture, and the maintenance of critical infrastructure like bridges, buildings, and power grids.</p>
<blockquote><p>&#8220;Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges.&#8221;</p>
<p>&#8211; Mirko Kovač, Laboratory of Sustainability Robotics</p></blockquote>
<h4>Beyond sustainable robotics</h4>
<p>Current research at the intersection of robotics and sustainability follows two main paths: developing robots that enable a more sustainable use of resources, and developing robots that are themselves more sustainable due to improved energy efficiency, biodegradability, or recyclability.</p>
<p>Mirko Kovač heads the joint <a href="https://www.epfl.ch/labs/lsr/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Laboratory of Sustainability Robotics</a> at Empa and EPFL&#8217;s School of Architecture, Civil and Environmental Engineering. In a <a href="https://www.nature.com/articles/s42256-026-01260-6" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">cover article</a> recently published in <em>Nature Machine Intelligence</em>, Kovač and his co-authors propose a manifesto that calls on academia, industry, and governments to extend and integrate these approaches within a broader framework that evaluates robots according to their overall contribution to sustainability goals. The manifesto defines a new discipline called Sustainability Robotics (not to be confused with sustainable robotics).</p>
<p>“Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges,” Kovač says.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/80bf00dd-1024x894.jpg" alt="" width="1024" height="894" class="alignnone size-large wp-image-221190" srcset="https://robohub.org/wp-content/uploads/2026/09/80bf00dd-1024x894.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/80bf00dd-425x371.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/80bf00dd-768x671.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/80bf00dd.jpg 1415w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The three core principles of Sustainability Robotics. 2026 LSR/EPFL &#8211; CC BY SA 4.0</em></p>
<h4>Minimally invasive, accessible…</h4>
<p>In their article, the researchers argue that robots should no longer be evaluated solely based on technical performance. Instead, their environmental, social, and economic impacts should become part of the equation. To guide this transition, they propose three core principles: robotic systems should be <a href="https://www.empa.ch/web/s604/sustainability-robotics-nature-machine-intelligence" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">minimally invasive, universally accessible, and symbiotic</a>, creating value for people as well as economies and ecosystems.</p>
<p>Rather than viewing sustainability challenges like climate change, biodiversity loss, and resource scarcity as constraints on innovation, the authors argue that they can become opportunities to develop entirely new engineering solutions. Indeed, several EPFL laboratories are already exploring what Sustainability Robotics might look like in practice.</p>
<p>For example, the eel-inspired <a href="https://actu.epfl.ch/news/pinpointing-sources-of-water-pollution-with-a-robo/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Envirobot</a>, from Auke Ijspeert&#8217;s <a href="https://www.epfl.ch/labs/biorob/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Biorobotics Lab</a>, supports environmental research by targeting the autonomous monitoring of water quality. The project reflects the lab&#8217;s broader efforts to draw inspiration from animals to develop robots capable of operating in complex natural environments while improving our understanding of biological locomotion.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221191" srcset="https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/2e40e5ca-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The eel-inspired Envirobot from the Biorobotics Lab supports environmental research by targeting the autonomous monitoring of water quality. 2017 Alain Herzog / EPFL &#8211; CC BY SA 4.0</em>.</p>
<p>Engineers in the <a href="https://www.epfl.ch/labs/lis/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Laboratory of Intelligent Systems</a>, led by Dario Floreano, have developed <a href="https://actu.epfl.ch/news/eco-friendly-aquatic-robot-is-made-from-fish-foo-2/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">an aquatic robot made from fish food</a>. Likewise designed for environmental monitoring, the device can be equipped with biodegradable sensors for collecting data like pH, temperature, and the presence of pollutants. At the end of its life, it can also feed aquatic organisms rather than becoming electronic waste.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221192" srcset="https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/2c1a8b9b-2048x1366.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>This edible robot from the Laboratory for Intelligent Systems is an alternative to electronic environmental monitoring devices. EPFL &#8211; CC-BY-SA 4.0</em>.</p>
<h4>…and symbiotic</h4>
<p>Sustainability Robotics’ concept of symbiosis also raises questions about how robots can create value across multiple domains. One example is the <a href="https://www.robofood.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboFood</a> initiative, coordinated by Floreano, which explores edible robots and roboticized food systems. Although food and robots are usually considered to be two separate worlds, Floreano argues that merging them could have advantages for healthcare, food production, and environmental sustainability.</p>
<p>“Edible robots could be used to deliver food to endangered areas, to deliver medicines in innovative ways to people who have difficulty swallowing or to animals, or even to monitor food and its freshness using sensors that can be eaten,” he says. “They could also help limit electronic and food waste.”</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221193" srcset="https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/09/a5ee20d7-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Edible robotic teddy bears, created by the LIS at EPFL &#8211; 2025 EPFL/Jamani Caillet &#8211; CC-BY-SA 4.0</em>.</p>
<p>Another example comes from the built environment. In the <a href="https://www.crclcrclcrcl.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Lab for Creative Computation</a>, Stefana Parascho <a href="https://link.springer.com/article/10.1007/s41693-026-00201-4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">investigates</a> how robotic workflows, which typically require uniform components and predefined plans, can be adapted to use irregular and reclaimed construction materials. Such approaches could help reduce waste while allowing architects to work with available materials instead of relying exclusively on standardized products. They could also inspire fabrication processes characterized by <a href="https://www.epfl.ch/campus/art-culture/museum-exhibitions/archizoom/do-robots-dream-of-construction-sites-2/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">more adaptive and collaborative human-robot interactions</a>.</p>
<p>In addition to materials and applications, research in the <a href="https://www.epfl.ch/labs/create/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Computational Design and Fabrication (CREATE)</a> Lab, led by Josie Hughes, shows how sustainability can be embedded directly into robot design from the beginning. One way to do this is through simplified, energy-efficient approaches to robotic control, as demonstrated by the <a href="https://actu.epfl.ch/news/robotic-dog-runs-almost-entirely-on-its-own/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">quadruped robot PAWS</a>. Once set in motion, the canine-inspired robot can run by itself using compliant materials and synergistic joints, without activating any motors. The project demonstrates how nature can inspire robust locomotion through mechanical design, rather than increasingly complex control systems.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/3a9f1cf2-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221194" srcset="https://robohub.org/wp-content/uploads/2026/09/3a9f1cf2-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/3a9f1cf2-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/3a9f1cf2-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/3a9f1cf2-1536x1025.jpg 1536w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Once set in motion, the CREATE Lab&#8217;s canine-inspired PAWS robot can run by itself using compliant materials and synergistic joints, without activating any motors. 2023 Alain Herzog/EPFL CC BY SA -4.0</em>.</p>
<h4>A new measure of performance</h4>
<p>Ultimately, Billard and Kovač both call for a broader definition of robotic success that accounts for social, economic, and environmental value alongside technical performance. Of course, this won&#8217;t be easy; robots designed with sustainability objectives in mind will still require energy and materials to build and operate, and their use will still carry inherent risks. However, as Kovač puts it: “the challenge is not to eliminate these trade-offs, but to make them visible, and account for them when evaluating a robot&#8217;s overall impact.”</p>
<p>Many of the projects already emerging from EPFL labs draw inspiration from biological systems that have been refining solutions to the trade-offs between locomotion, dexterity, efficiency, and adaptability for millions of years. In doing so, they suggest a vision of robotics that comes full circle: using lessons learned from nature to better understand and protect it.</p>
<p>In that sense, sustainability may become one of the most important performance metrics for the next generation of robots.</p>
<h4>References</h4>
<ul>
<li>Aude G. Billard. <a href="https://www.science.org/doi/10.1126/science.adx2444" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Designing and using robots for environmental sustainability</a>. Science 388, eadx2444 (2025).</li>
<li>Song, S., Mazzolai, B. &#038; Kovač, M. <a href="https://www.nature.com/articles/s42256-026-01260-6" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A manifesto for Sustainability Robotics</a>. Nature Machine Intelligence (2026).</li>
<li><a href="https://www.empa.ch/web/s604/sustainability-robotics-nature-machine-intelligence" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Empa press release</a></li>
<li><a href="https://infoscience.epfl.ch/entities/publication/ed68b8ed-c572-46f0-aacb-d147a17e43cc/conferencedetails" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Envirobot: A bio-inspired environmental monitoring platform</a>. IEEE/OES Conference on Autonomous Underwater Vehicles (AUV), Tokyo, Japan (2016), pp. 1-6.</li>
<li><a href="https://www.robofood.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboFood</a></li>
<li>Skevaki, E., Duong, E., Yang, HB. et al. <a href="https://link.springer.com/article/10.1007/s41693-026-00201-4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Crafting structural timber trusses from irregular offcuts via human–robot interaction</a>. Construction Robotics 10, 20 (2026).</li>
<li>Stefana Parascho. <a href="https://www.annualreviews.org/content/journals/10.1146/annurev-control-080122-090049" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Construction Robotics: From Automation to Collaboration</a>. Annual Review of Control, Robotics, and Autonomous Systems 6:183-204. 2023.</li>
<li>Stella, F., Achkar, M.M., Della Santina, C. et al. <a href="https://www.nature.com/articles/s42256-025-00988-x" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity</a>. Nature Machine Intelligence 7, 386–399 (2025).</li>
<li>Zhang, S., Kwak, B., Zhu, R. et al. <a href="https://www.nature.com/articles/s41467-025-59559-8" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Edible aquatic robots with Marangoni propulsion</a>. Nature Communications 16, 4238 (2025).</li>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Watch the ICRA keynote and plenary talks</title>
		<link>https://robohub.org/watch-the-icra-keynote-and-plenary-talks/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Wed, 16 Sep 2026 08:47:13 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221222</guid>

					<description><![CDATA[The 2026 IEEE International Conference on Robotics &#038; Automation (ICRA) was held in Vienna from the 1 &#8211; 5 June. The event brought together researchers and industry professionals with expertise spanning many different aspects of robotics. IEEE have made the keynote and plenary talk recordings available to watch. You can also catch the panel discussions [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426.jpg" alt="" width="900" height="600" class="size-full wp-image-221223" srcset="https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426.jpg 900w, https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/bigstock-Movie-Old-Film-Reel-On-Dark-Ba-244927426-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /></p>
<p>The <a href="https://2026.ieee-icra.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2026 IEEE International Conference on Robotics &#038; Automation (ICRA)</a> was held in Vienna from the 1 &#8211; 5 June. The event brought together researchers and industry professionals with expertise spanning many different aspects of robotics. </p>
<p>IEEE have made the keynote and plenary talk recordings <a href="https://ieeetv.ieee.org/event/icra-2026" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">available to watch</a>. You can also catch the panel discussions and keynote tutorials. </p>
<p>Watch <a href="https://ieeetv.ieee.org/event/icra-2026" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><strong>here</strong></a>. </p>
<p>Available to watch are the following:</p>
<ul>
<li>Plenary talks</li>
<ul>
<li><em>Ken Goldberg</em> &#8211; A Tale of Two Cultures:  Can Agentic Coding Close the Gap?</li>
<li><em>Barbara Mazzolai</em> &#8211; Natural Revolution: Biological Principles for Frugal and Sustainable Robotics</li>
<li><em>Roland Siegwart</em> &#8211; Aerial Robots – From Omnidirectional Flight to Physical Interaction at Height</li>
</ul>
<li>Keynote sessions</li>
<ul>
<li>Autonomous Vehicles &#038; Navigation</li>
<li>Medical &#038; Healthcare Robotics</li>
<li>Robot Perception &#038; Spatial AI</li>
<li>Manipulation, Humanoids, Embodied Design</li>
<li>Robot Learning, Planning &#038; Foundation Models</li>
<li>Human-Robot Interaction</li>
</ul>
<li>Industry keynote sessions</li>
<li>Awards</li>
<li>Keynote tutorials</li>
<li>Panels</li>
<ul>
<li>Panel 1 – From Humanoid Robotics Research to Startup Creation: The Role of Public Funding</li>
<li>Panel 2 – Advancing Sustainability in Robotics: From Green Design to Real-World Impact</li>
<li>Panel 3 – Building Sustainable and Trustworthy AI for Automation</li>
<li>Panel 4 – Publish or Perish: Surviving the Paper Deluge – Is AI the solution? If not, what is the Solution?</li>
<li>Panel 5 – “Robots for All” in a Fragmented World: Competing Global Visions and Shared Futures from Europe, Asia, and the United States</li>
<li>
Panel 6 – Impact and Financial Return on Humanoid Investment</li>
</ul>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robots in society, business and culture: August 2026</title>
		<link>https://robohub.org/robots-in-society-business-and-culture-august-2026/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Mon, 14 Sep 2026 09:01:21 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221228</guid>

					<description><![CDATA[Credit: Baumis Robots (Karlsruhe Institute of Technology). By Emmet Cole In our new monthly series, we showcase a selection of robotics stories from society, business, research, and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon. Reshoring reimagined? In early August, The Information published an article [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46-1024x596.jpeg" alt="" width="1024" height="596" class="alignnone size-large wp-image-221232" srcset="https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46-1024x596.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46-425x247.jpeg 425w, https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46-768x447.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46-1536x894.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/09/Screenshot-2026-09-09-at-14.49.46.jpeg 1738w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Credit: <a href="https://www.youtube.com/@baumisrobots9583" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Baumis Robots</a> (Karlsruhe Institute of Technology).</em></p>
<p><strong>By Emmet Cole</strong></p>
<p><em>In our new monthly series, we showcase a selection of robotics stories from society, business, research, and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon.</em></p>
<hr>
<h4>Reshoring reimagined?</h4>
<p>In early August, <a href="https://www.theinformation.com/articles/u-s-robotics-startups-stuffing-parts-china-luggage" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Information</a> published an article that claimed U.S.-based founders, investors and startups, are travelling to an electronics market in Shenzhen to buy servomotors, sensors, controllers and gimbals.  The report also claimed that Unitree and Zhiyuan robots are being bought intact, then stripped down into parts and carried back to the USA in suitcases.</p>
<p>By late August, in a separate development, reports emerged that a US Department of Energy lab is investigating whether Chinese LiDAR sensors pose a security risk, if widely used on vehicles in the United States. According to <a href="https://techcrunch.com/2026/08/21/us-government-lab-is-probing-chinese-lidar-for-security-vulnerabilities/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">TechCrunch</a>, the research is being funded by one or more companies in the electric and autonomous vehicle industries.</p>
<p>Together, the stories highlight the ongoing tension between US security concerns and its robotics industry’s continuing dependence on Chinese hardware.</p>
<h4>Motorless shape shifters</h4>
<p>Don’t cancel any Shenzhen travel plans just yet, but engineers at Princeton have unveiled a motorless, <a href="https://www.pnas.org/doi/10.1073/pnas.2530458123" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">origami-inspired robot</a> that can roll, crawl, and change shape through a combination of magnetic control and multistable geometry.</p>
<div class="keep-aspect"><iframe title="Robot Clip" src="https://player.vimeo.com/video/1215917548?dnt=1&amp;app_id=122963" width="500" height="281" frameborder="0" allow="autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share" referrerpolicy="strict-origin-when-cross-origin"></iframe></div>
<p></p>
<p>Project lead Glaucio Paulino told <a href="https://engineering.princeton.edu/news/2026/08/06/new-system-makes-building-robots-snap" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Princeton Engineering</a>:</p>
<p><em>Geometry is the real actuator here. Instead of relying on complicated mechanisms, we use mathematical principles to encode multiple stable configurations directly into the structure. That opens a new pathway for designing lightweight, adaptable systems.</em></p>
<h4>Managing expectations</h4>
<p><a href="https://www.bbc.com/news/articles/czxq0wgkkdjo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Robot deployments can fail</a> for <a href="https://breakingdefense.com/2025/06/army-considering-terminating-general-dynamics-oversight-of-new-155mm-production-lines/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">many reasons</a>, making expectation management a key part of successful robotics projects. This might mean explaining that although collaborative robots can sometimes be deployed without fencing, that is not appropriate for every application, and a risk assessment is still required.</p>
<p>It might mean explaining that although robot-assisted radical prostatectomy typically reduces blood loss and shortens hospital stays compared with open surgery, longer-term outcomes depend heavily on the patient, the cancer and the surgeon.</p>
<p>In the humanoid space, where expectations are often formed by spectacle and driven by anthropomorphism and millions of years of evolution, the effects can be particularly acute.</p>
<p>A <a href="https://drexel.edu/news/archive/2026/August/Ayaz-expressive-robot-mistakes" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Drexel-led study</a> involving 50 adult men that measured brain activity, hormones, self-reported attitudes and behaviour in order to assess trust in human-humanoid interaction, found that participants formed stronger initial connections with an expressive Pepper robot than with a stationary version that gave no nonverbal cues.</p>
<p>But when the expressive robot made errors, the participants’ brains responded as they would to a person breaking a social norm, rather than a machine making a technical error.</p>
<p>Counterintuitively:</p>
<p><em>[…] levels of “the bonding hormone,” oxytocin, which is typically present in higher amounts among friends, relatives and romantic partners, actually rose in participants as the engaging robot made mistakes. This led [researchers] to believe that the hormone functions as a warning signal, rather than a sign of connection, in human-robot interactions.</em></p>
<p>Read the full <em>Science Robotics</em> paper <a href="https://www.science.org/doi/10.1126/scirobotics.aec1762" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<h4>Beyond automotive</h4>
<p>For decades, the automotive sector has been the leading segment for robotics adoption. That’s still the case, but as the latest <a href="https://www.automate.org/robotics/news/robot-orders-increase-in-q2-as-automation-demand-broadens-across-industries" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">North American Q2 figures</a> from the Association for Advancing Automation (A3) show, automotive OEM’s share is continuing to slide as robots diversify across other industry segments.</p>
<p>Notably, North American companies ordered 8,940 robots valued at US$622 million in the second quarter of 2026, a 4.3% increase in units ordered and a 21.3% increase in revenue, according to A3’s numbers.</p>
<h4>Recycling robots</h4>
<p><a href="https://spectrum.ieee.org/recycling-robot" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE Spectrum</a> profiled an automated recycling system developed by researchers at Germany’s <a href="https://www.wbk.kit.edu/english/index.php" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Karlsruhe Institute of Technology</a>. The system uses CAD data, physical observations and a predictive algorithm to predict defects in products and adapt its disassembly strategy while protecting valuable components.</p>
<div class="keep-aspect"><iframe title="From CAD to POMDP: Probabilistic Planning for Robotic Disassembly of End-of-Life Products" width="500" height="281" src="https://www.youtube-nocookie.com/embed/0sEtcPTLFSQ?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<h4>All eyes on China</h4>
<p>As August came to a close, the eyes of the robotics world (and the general public) turned to Beijing, China as the city played host to both the World Robot Conference (WRC) and the World Humanoid Robot Games.</p>
<p>The <a href="https://www.worldrobotconference.com/en" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">WRC</a>, primarily a showcase of Chinese products, brought together ~300 companies exhibiting more than 2,000 products. These included robots for parcel sorting, manufacturing, surgery and domestic work.</p>
<div class="keep-aspect"><iframe title="LIVE: World Robot Conference in Beijing" width="500" height="281" src="https://www.youtube-nocookie.com/embed/r39i7_LTPOA?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Unitree supplied much of the spectacle with its remarkably fast “Superman” humanoid and an <a href="https://www.reuters.com/world/asia-pacific/chinese-humanoid-robot-maker-unitree-set-jump-over-600-shanghai-debut-2026-08-19/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">extraordinary stock-market debut</a>. Its shares closed 460% above the IPO price, although by August 28 they had <a href="https://www.reuters.com/commentary/breakingviews/chinas-robots-fail-early-market-test-2026-08-28" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">fallen almost 30%</a> -another lesson in managing expectations. CEO Wang Xingxing also predicted that robotics is approaching a <a href="https://www.reuters.com/world/asia-pacific/robots-poised-chatgpt-moment-unitree-ceo-says-2026-08-20/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“ChatGPT moment”</a>.</p>
<div class="keep-aspect"><iframe title="Unitree New Robot Preview: “Superman” Breaking the Limits of Humanity" width="500" height="281" src="https://www.youtube-nocookie.com/embed/O7OkiZfIlS4?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The World Humanoid Robot Games brought the theme of spectacle versus reality to another level. Robots kick-boxed, played table tennis, performed gymnastic routines, and played football. There were moments of hilarity…</p>
<div class="keep-aspect"><iframe title="Funny moments from Beijing’s World Humanoid Robot Games 2026" width="500" height="281" src="https://www.youtube-nocookie.com/embed/pnz79EmT-V8?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>…and some genuinely impressive technology demonstrations.</p>
<p>After watching <a href="https://www.youtube.com/watch?v=C8hm-H9rmVE" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">several hours of livestreams</a> from the games across several days, and looking at the print media coverage, I began to wonder whether events like these help people manage expectations around robots much.</p>
<p>The media focus on spectacle doesn’t help. Yes, a humanoid ran at Usain Bolt-like speeds and then into a wall. Yes, the kickboxing humanoids had an endearing <a href="https://en.wikipedia.org/wiki/Mr._Magoo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Mr. Magoo</a>-like quality. Technology demonstration aside, there isn’t much call for either in industrial applications.</p>
<p>Blink and you’d miss it -and much of the media coverage did- but the games also hosted multiple competitions centred around industrial manufacturing, logistics, household services and emergency response.</p>
<p>In the industrial “assembly and material supply” contest, for example, robots had to move containers onto shelves, identify and sort differently packaged components, and insert intake and exhaust valves into the correct openings in an engine cylinder head.</p>
<p>Other contests tested packaging and warehouse intake, while eight dexterous-hand challenges included screw fastening, unpacking boxes, connecting cables and picking up beans with tweezers. Some competitions required autonomous robots and others tested teleoperation capabilities.</p>
<div class="keep-aspect"><iframe title="Gold Medals at the 2026 World Humanoid Robot Games: Real-time Teleoperation with MANUS Metagloves" width="500" height="281" src="https://www.youtube-nocookie.com/embed/OPwHAMCD9y0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>These slower, less spectacular competitions tested the precision, perception and adaptability humanoids will need before they can perform useful work in factories and warehouses.</p>
<p>All that said, everybody needs a humanoid riding a giant quadruped.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Building and programming autonomous robots at the York Micromaze Hackathon</title>
		<link>https://robohub.org/building-and-programming-autonomous-robots-at-the-york-micromaze-hackathon/</link>
		
		<dc:creator><![CDATA[Folasayo Ogundipe]]></dc:creator>
		<pubDate>Fri, 11 Sep 2026 13:07:25 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221180</guid>

					<description><![CDATA[From 25–27 August, UK RAS STEPS members came together at the University of York’s Institute for Safe Autonomy for a three-day Micromaze Robot Hackathon. Working in teams, participants were challenged to design, build and program autonomous robots capable of navigating a series of increasingly complex mazes. Each team used a custom Raspberry Pi Pico W [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/WhatsApp-Image-2026-08-27-at-4.48.18-PM-1024x576.jpeg" alt="" width="1024" height="576" class="alignnone size-large wp-image-221181" srcset="https://robohub.org/wp-content/uploads/2026/09/WhatsApp-Image-2026-08-27-at-4.48.18-PM-1024x576.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/09/WhatsApp-Image-2026-08-27-at-4.48.18-PM-425x239.jpeg 425w, https://robohub.org/wp-content/uploads/2026/09/WhatsApp-Image-2026-08-27-at-4.48.18-PM-768x432.jpeg 768w, https://robohub.org/wp-content/uploads/2026/09/WhatsApp-Image-2026-08-27-at-4.48.18-PM.jpeg 1080w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>From 25–27 August, UK RAS STEPS members came together at the University of York’s Institute for Safe Autonomy for a three-day Micromaze Robot Hackathon.</p>
<p>Working in teams, participants were challenged to design, build and program autonomous robots capable of navigating a series of increasingly complex mazes. Each team used a custom Raspberry Pi Pico W robotics platform, designed a laser-cut chassis, integrated motors and sensors, and developed its control software in MicroPython.</p>
<p>Participants had access to ultrasonic, infrared and time-of-flight sensors, alongside laser-cutting and 3D-printing facilities. The final challenge considered maze performance, collision avoidance, robot design, code quality, wireless control and any innovative features developed by the teams.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/DSC09599-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221182" srcset="https://robohub.org/wp-content/uploads/2026/09/DSC09599-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/DSC09599-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/DSC09599-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/DSC09599.jpg 1080w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>The programme also included a tour of the Institute for Safe Autonomy, collaborative development sessions, final presentations and robot demonstrations.</p>
<p>Beyond the technical challenge, the Hackathon helped test an activity that could be developed into future continuing professional development for people new to robotics or an outreach programme for children and students.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/DSC09572-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221183" srcset="https://robohub.org/wp-content/uploads/2026/09/DSC09572-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/09/DSC09572-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/09/DSC09572-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/09/DSC09572.jpg 1080w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>Thank you to Rob Woolley, the University of York team and everyone who participated and contributed to the event.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotics roadmaps from around the world spotlight of the month: United States of America</title>
		<link>https://robohub.org/robotics-roadmaps-from-around-the-world-spotlight-of-the-month-united-states-of-america/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 09 Sep 2026 11:25:43 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[IEEE RAS]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221158</guid>

					<description><![CDATA[US robotics researchers and industry are looking for a cohesive national robotics strategy that will maintain basic research and innovation while improving domestic production and adoption of robots. By Ellen H. Rumley and Allison Okamura A leader in tech innovation Robots are a crowd-pleasing example of American innovation and global technological leadership. The latest press [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/09/STB-Article-3.png.webp" alt="" width="900" height="511" class="alignnone size-full wp-image-221159" srcset="https://robohub.org/wp-content/uploads/2026/09/STB-Article-3.png.webp 600w, https://robohub.org/wp-content/uploads/2026/09/STB-Article-3.png-425x242.webp 425w" sizes="(max-width: 900px) 100vw, 900px" /><em>US robotics researchers and industry are looking for a cohesive national robotics strategy that will maintain basic research and innovation while improving domestic production and adoption of robots.</em></p>
<p><strong>By Ellen H. Rumley and Allison Okamura</strong></p>
<h4>A leader in tech innovation</h4>
<p>Robots are a crowd-pleasing example of American innovation and global technological leadership. The latest press release of Boston Dynamics’ <em>Atlas</em> executing the ‘Ghost Rabona’ soccer kick highlights the increasingly natural movements of humanoids (<a href="https://www.youtube.com/watch?v=V1Lxp-Q6Y9g" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">1</a>). At the other end of the spectrum, academic researchers are redefining the limits of miniaturization and building robots at the micrometer scale (<a href="https://www.engineering.upenn.edu/stories/penn-and-umich-create-worlds-smallest-programmable-autonomous-robots/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2</a>). Private and government funding propel foundational research forward, leading to breakthroughs in both hardware and software across U.S. labs and corporations (<a href="https://www.nsf.gov/science-matters/7-cool-nsf-funded-robots-are-advancing-science-helping#:~:text=Directly%20administering%20drugs%20to%20specific,organs%20that%20have%20rough%20terrain." data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">3</a>, <a href="https://www.forbes.com/lists/ai50/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">4</a>). Such progress reaffirms the U.S. as an intellectual and innovative powerhouse, a reputation that carries large geopolitical weight.</p>
<p>But retaining a lead solely in the R&#038;D phase yields diminishing returns if the U.S. fails to manufacture robotic hardware at scale within its own borders. Critics fear this dynamic prevents the U.S. from reaping the economic benefits of the very technology it pioneers (<a href="https://itif.org/publications/2025/07/18/time-to-act-policies-to-strengthen-us-robotics-industry/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">5</a>, <a href="https://www.automate.org/a3/advocacy-principles" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">6</a>). Ramping up domestic production will require a heavily coordinated effort between government, industry, and academics – a pivot from traditional U.S. technology strategy.</p>
<h4>Free market and military capital</h4>
<p>Historically, the U.S. has maintained a laissez-faire approach to technological innovation, allowing corporate and private investors driven by the free market to shape the course of advancement. This innovation-first strategy is largely credited with fueling the growth of global tech giants and the rise of Silicon Valley, which altogether represents roughly 12% of the national GDP (<a href="https://www.cta.tech/press-releases/tech-sector-supports-18-million-us-jobs-represents-12-of-gdp-says-cta" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">7</a>). America’s leadership in artificial intelligence can be largely attributed to this free-market engine, which prioritizes high projected profit margins and rapid scalability of software (<a href="https://www.brookings.edu/articles/hardware-and-software-a-new-perspective-on-the-past-and-future-of-economic-growth/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">8</a>).</p>
<p>When it comes to U.S. robotics hardware, the Department of Defense/War (DoD/DoW) has stepped in as one of the primary catalysts for innovation and investment. The Pentagon’s fiscal year 2026 budget requested an unprecedented $13.4 billion for developing autonomous systems; a major increase from years prior. The DoD/DoW is requesting an additional $53.6 billion for autonomous systems and drones for 2027 (<a href="https://defensescoop.com/2026/04/21/dod-plans-largest-ever-investment-drones-anti-drone-weapons/#:~:text=Specifically%2C%20he%20noted%20that%20the,like%20the%20collaborative%20combat%20aircraft.”" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">9</a>). Private capital has quickly mirrored federal priorities; in the first quarter of 2026 alone, defense technology venture capital investments reached a record $19.8 billion. This surge is tightly bound to contemporary geopolitical conflicts, such as the hybrid warfare seen in Ukraine, where the U.S. plays a key role in funding drone production and in recent times deploying humanoids (<a href="https://www.nytimes.com/2025/01/17/us/politics/ukraine-drones-biden-support.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">10</a>, <a href="https://www.cnbc.com/2026/05/30/humanoid-robots-ukraine-war-foundation-military-ai.html?msockid=062529b9c15461b83c7f3f9fc0866067" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">11</a>). The significant role that autonomous systems have played in conflict zones like the Strait of Hormuz has also signaled the high dependency of strategic military operations on robotics (<a href="https://www.reuters.com/business/aerospace-defense/iran-could-disrupt-strait-hormuz-with-drones-months-2026-03-04/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">12</a>).</p>
<h4>A bottleneck for domestic manufacturing</h4>
<p>While investment in robotic innovation does provide certain economic benefits, it does not support U.S. competitiveness in critical industries – specifically in physical manufacturing. Hardware inherently requires higher, long-term capital expenditures and yields lower short-term financial returns compared to software. Consequently, there could be less incentive to compete against other global manufacturing leaders. Furthermore, while the DoD funds early-stage R&#038;D and specialized military platforms, its mandate stops short of supporting commercial scaling efforts necessary to implement technologies for broader civilian and industrial applications.</p>
<p>As a result, while the U.S. is the third-largest consumer of industrial robotics in the world (with industrial adoption surging by 11% just last year in sectors like logistics, packaging and automotive) (<a href="https://ifr.org/ifr-press-releases/news/us-robot-industry-returns-to-double-digit-growth#:~:text=Preliminary%20results%20published%20by%20International,and%20other%20non%2Dmanufacturing%20sectors." data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">13</a>), it lacks the infrastructure to build what it consumes. While a few prominent U.S. companies do manufacture application-specific robots (some examples being Intuitive Surgical, Amazon Robotics, and Agility), the U.S. mostly relies on foreign imports for baseline industrial robot installations (<a href="https://www.mckinsey.com/mgi/our-research/ramping-up-manufacturing-in-america" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">14</a>). Contrast this with Japan, which relies on foreign imports for a mere 2% of its domestic installations (<a href="https://ifr.org/ifr-press-releases/news/japan-is-worlds-number-one-robot-maker" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">15</a>).</p>
<p>The systemic under-development in domestic robotic manufacturing leaves the U.S. vulnerable to hardware dependencies and supply chain disruptions. While industrial leaders like Japan and Germany are reliable trade partners, the U.S. government increasingly views hardware dependencies as a national security vulnerability. In recent years, robots have been reclassified as a critical dual-use technology, considered central to 21st century technological sovereignty (<a href="https://setr.stanford.edu/sites/default/files/2026-02/SETR2026_web-260219.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">16</a>). This reality makes robotics manufacturing a target for foreign adversaries, since foreign supply chains introduce operational chokepoints.</p>
<p>Currently, the U.S. government responds to these vulnerabilities through aggressive export controls and protective procurement policies, which are designed to slow down adversary agendas by blocking their access to the U.S. IP and markets. As one example, in 2021 the President issued the <em>NSPM-33</em> (a national security memorandum directed to executive agencies) mandating federally funded research institutions to establish strict internal compliance frameworks (<a href="https://www.iarpa.gov/images/pdfs/010422-NSPM-33-Implementation-Guidance.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">17</a>). While designed to allow the continued recruitment of international talent, it enforces rigid vetting protocols on researchers potentially associated with Malign Foreign Talent Recruitment Programs (MFTRP) or of dual national affiliation (<a href="https://bidenwhitehouse.archives.gov/wp-content/uploads/2024/02/OSTP-Foreign-Talent-Recruitment-Program-Guidelines.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">18</a>). As another example, in early 2026 lawmakers proposed the bipartisan <em>American Security Robotics Act</em>, a bill designed to ban the federal procurement and operation of unmanned ground vehicles and humanoids manufactured by foreign adversaries, specifically targeting China (<a href="https://www.govinfo.gov/content/pkg/BILLS-119hr8189ih/pdf/BILLS-119hr8189ih.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">19</a>).</p>
<h4>Getting by without a government-led national robotics strategy</h4>
<p>Rising concerns over robotics supply chain vulnerabilities strongly echo the semiconductor anxieties that originally led to the CHIPS and Science Act of 2022, which marked a historical pivot for the U.S. towards an active state-supported industrial policy (<a href="https://www.csis.org/analysis/innovation-lightbulb-tracking-chips-act-incentives" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">20</a>). Today, there is a similar pressure mounting for the federal government to coordinate a sovereign robotics pipeline via a unified national roadmap.</p>
<p>The challenge facing the U.S. does not seem to be a lack of federal funding, but rather how the funding is distributed across multiple agencies with different mandates (<a href="https://www.csis.org/blogs/strategic-technologies-blog/why-united-states-needs-robots-rebuild#:~:text=The%20National%20Robotics%20Initiative%2C%20once,company%20mass%2Dproducing%20industrial%20robots." data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">21</a>). The National Science Foundation funds basic academic research; Department of Energy runs national research laboratories and funds external research programs developing robotics relating to energy infrastructure; National Institute of Health supports and conducts medical robotics research; NASA funds and develops robotics for space applications; the ARM Institute supports domestic manufacturing initiatives while satisfying dual-use funding criteria through the DoD/DoW; and DARPA funds robotic innovations relevant to national security. (The latter organizes the well-known <em>DARPA Grand Challenges</em>, robotics competitions for fueling research bridging fundamental science and military applications.) Because federal investments from these programs and agencies are confined to isolated, mission-specific niches, the U.S. remains one of the few leading industrial nations without a centralized robotics strategy.</p>
<p>This structural fragmentation may soon change as political attention shifts towards treating robotics as a critical sector (<a href="https://www.politico.com/news/2025/12/03/trump-administration-ai-robotics-00674204" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">22</a>). In 2025, four state representatives re-launched the bipartisan <em>Congressional Robotics Caucus</em> as a platform for members of Congress to stay informed over the diverse issues surrounding robotics policy (<a href="https://mcgovern.house.gov/news/documentsingle.aspx?DocumentID=400154" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">23</a>). In June 2026, legislators formally introduced the bipartisan <em>National Commission on Robotics Act</em>, which calls for an independent commission of 18 robotics experts tasked with providing evidence-based policy to accelerate domestic development (<a href="https://www.congress.gov/bill/119th-congress/house-bill/7334" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">24</a>). This legislative momentum is reinforced by a series of recent Executive Orders (mandates from the US President) demanding a high-level federal coordination including the <em>Unleashing American Drone Dominance</em> Order (<a href="https://www.war.gov/News/News-Stories/Article/Article/4520698/drone-dominance-program-receives-first-order-gauntlet-ii-gets-underway/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">25</a>), the <em>Golden Dome for America</em> Order (<a href="https://www.cbo.gov/system/files/2026-05/62379-golden-dome.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">26</a>), and the <em>Launching the Genesis Mission</em> Order (<a href="https://www.energy.gov/articles/energy-department-advances-investments-ai-science" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">27</a>).</p>
<h4>Robotics strategies from non-government actors</h4>
<p>In the absence of a centralized federal initiative, stakeholders in industry, NGOs, and academia are self-organizing and publishing their own robotics frameworks recommendations for the United States.</p>
<p>In 2025, A3 (Association for Advancing Automation) released their <em>Vision for a U.S. National Robotics and Automation Strategy</em> (<a href="https://www.automate.org/a3/advocacy-principles" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">28</a>), which argues that the future of U.S. leadership in artificial intelligence is inextricably linked with its global robotics leadership. A3 provides actionable policy items, such as the formation of a governmental robotics office for coordinating federal robotics initiatives, the establishment new standards for nascent robotic hardware and software, and the introduction of tax incentives for rapid robotics adoption and creation of worker training programs.</p>
<p>Complementing these industry goals, in 2025 the nonpartisan thinktank, Special Competitive Studies Project (SCSP), has released their <em>Memos to the President – National Robotics Strategy</em> (<a href="https://www.scsp.ai/wp-content/uploads/2025/02/Robotics-Memo.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">29</a>). This document couples the call for mass industrial robotics adoption with recommendations for more aggressive trade restrictions on Chinese technologies. Following this publication, SCSP launched its <em>National Security Commission on Robotics for Advanced Manufacturing</em> for implementing this comprehensive strategy; members include industry and academic players including GM, Boston Dynamics, Nvidia, AMD, the University of Michigan and MIT’s Industrial Performance Center (<a href="https://en.sedaily.com/news/2026/03/24/boston-dynamics-joins-us-robotics-strategy-think-tank" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">30</a>).</p>
<p>Academics have similarly spearheaded their own national strategies. Once every four years, academics led by Professor Henrik Christensen (UC San Diego) publish a roadmap for U.S. robotics (<a href="https://hichristensen.com/pdf/roadmap-2024.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">31</a>). Past editions directly catalyzed the creation of the National Robotics Initiative (NRI), a multi-agency federal program running from 2012 to 2022 that supported foundational research on robotics, specifically promoting collaborative robots for working alongside humans. (Christensen also recently published <em>Global Robotics Technology Roadmap 2025–2035</em>, an independent positions paper synthesizing government and industry strategies across Europe, Asia, and the United States (<a href="https://hichristensen.com/pdf/global_robotics_roadmap_2025.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">32</a>).)</p>
<p>All three stakeholders share a common motivation for a national robotics strategy: the nation’s population and workforce are declining; There is a surplus of jobs fulfilling the 3 Ds (dull, dirty, dangerous); Robotics should become a national priority once more. In addition to funding and incentives, authors also discuss the need to consider the impact of technology on the workforce –  a topic of large structural tension, with fear of robots displacing jobs and particularly outcompeting blue-collar and immigrant workers (<a href="https://www.nytimes.com/2026/02/09/opinion/immigration-farming-trump-robots-labor.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">33</a>, <a href="https://www.pewresearch.org/short-reads/2026/03/12/key-findings-about-how-americans-view-artificial-intelligence/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">34</a>). Christensen et al. delve deeper into the psychology of the workforce, and recommend a framework which balances technological growth with worker empowerment. They propose that prioritizing human-centered collaborative robots and wearable devices could shift the robotics narrative from a source of widening economic disparity towards heightening workplace satisfaction and production efficiency. However, recent mass layoffs amidst installations of collaborative robots reveal the complexity of this balancing act (<a href="https://www.yahoo.com/news/politics/articles/unions-furious-gm-replaces-1-123041510.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">35</a>).</p>
<p>The U.S. is in the midst of a major shift regarding how it shapes robotics advancement. Because a formal federal strategy does not yet exist, private and academic stakeholders are proactively drafting the blueprints themselves. Consolidating these ideas into a unified national policy will have far-reaching consequences for national security, geopolitical influence, labor markets, and manufacturing sovereignty. The world watches carefully as this shift unfolds.</p>
<p>Thanks for reading. For our next article we will be delving into China’s national robotic strategies – stay tuned.</p>
<hr>
<p>Ellen H. Rumley – Policy Analyst</p>
<p>Allison Okamura – Vice President</p>
<p><em>IEEE RAS Science &#038; Technology Watch Board </em></p>
<hr>
<h4>References</h4>
<ol>
<li>Boston Dynamics and Hyundai. School of Football | The Ghost Rabona | Boston Dynamics x Hyundai. YouTube, 2026.</li>
<li>University of Pennsylvania School of Engineering and Applied Science. “Penn and UMich Create World’s Smallest Programmable Autonomous Robots.” Penn Engineering Today, 2024.</li>
<li>“7 Cool NSF-Funded Robots That Are Advancing Science and Helping Society.” S. National Science Foundation, 7 Apr. 2021.</li>
<li>“AI 50 List: Top Artificial Intelligence Companies.” Forbes, 2026.</li>
<li>Atkinson, Robert D. A Time to Act: Policies to Strengthen the US Robotics Industry. Information Technology and Innovation Foundation (ITIF), 2025.</li>
<li>Association for Advancing Automation (A3). Policy Recommendations and Advocacy Principles for the U.S. Automate.org, 2025.</li>
<li>Consumer Technology Association. “Tech Sector Supports 18 Million US Jobs, Represents 12% of GDP, Says CTA.” CTA Press Releases, 2026.</li>
<li>Brookings Institution. Hardware and Software: A New Perspective on the Past and Future of Economic Growth. Brookings, 2024.</li>
<li>United States Department of Defense. Comptroller Budget Materials: Fiscal Year 2026. 2025.</li>
<li>Marrow, Michael. “DoD Plans Largest-Ever Investment in Drones, Anti-Drone Weapons.” DefenseScoop, 21 Apr. 2026.</li>
<li>Smith, Matt. “Humanoid Robots and Military AI Take the Field in Ukraine War.” CNBC, 30 May 2026.</li>
<li>Reuters Defense Bureau. “Iran Could Disrupt Strait of Hormuz with Drones Within Months.” Reuters, 4 Mar. 2026.</li>
<li>International Federation of Robotics. “US Robot Industry Returns to Double-Digit Growth.” IFR Press Releases, 2026.</li>
<li>McKinsey Global Institute. Ramping Up Manufacturing in America? McKinsey &#038; Company, 2026.</li>
<li>International Federation of Robotics. “Japan Is World’s Number One Robot Maker.” IFR Press Releases, 2022.</li>
<li>Stanford University. Stanford Emerging Technologies Review 2026. 19 Feb. 2026.</li>
<li>National Science and Technology Council. Guidance for Implementation of National Security Presidential Memorandum 33 (NSPM-33). Jan. 2022.</li>
<li>White House Office of Science and Technology Policy. Guidelines for Foreign Talent Recruitment Programs. Feb. 2024.</li>
<li>United States, Congress, House. American Security Robotics Act. 119th Congress, H.R. 8189. Government Publishing Office, 2026.</li>
<li>Center for Strategic and International Studies. Innovation Lightbulb: Tracking CHIPS Act Incentives. CSIS, 2025.</li>
<li>Center for Strategic and International Studies. “Why the United States Needs Robots to Rebuild.” CSIS Strategic Technologies Blog, 2025.</li>
<li>Politico Pro Staff. “White House and Congressional Frameworks Shift Toward AI and Robotics.” Politico, 3 Dec. 2025.</li>
<li>United States, Congress, House of Representatives. “McGovern, Latta, Stevens, Obernolte Announce Re-Launch of Congressional Robotics Caucus.” Office of Congressman Jim McGovern, May 2025.</li>
<li>United States, Congress, House. National Commission on Robotics Act. 119th Congress, June 2026, H.R. 7334.</li>
<li>S. Army News Service. “Drone Dominance Program Receives First Order; Gauntlet II Gets Underway.” Defense Department News, 2026.</li>
<li>Congressional Budget Office. Cost Estimate and Analysis of the Golden Dome Air Defense Framework. May 2026.</li>
<li>S. Department of Energy. “Energy Department Advances Investments in AI and Robotics for Scientific Discovery.” DOE News, 2025.</li>
<li>Association for Advancing Automation. “A3 Policy Recommendations and Advocacy Principles for the U.S.” April 2024.</li>
<li>Special Competitive Studies Project. Memos to the President: National Robot Strategy. SCSP, 2025.</li>
<li>“Boston Dynamics Joins U.S. Robot Strategy Think Tank Led by Ex-Google CEO.” Seoul Economic Daily, March 2026.</li>
<li>Christensen, Henrik, et al. Robotics for a Better Tomorrow: 2024 US National Robotics Roadmap. UC San Diego / Academic Coalition, 2024.</li>
<li>Christensen, Henrik. Global Robotics Technology Roadmap 2025–2035. Independent Position Paper, 2025.</li>
<li>Appelbaum, Binyamin. “What Replaces Deported Immigrant Workers? Not Americans.” The New York Times, Feb. 2026.</li>
<li>Pew Research Center. “Key Findings About How Americans View Artificial Intelligence and Automated Systems.” Pew Short Reads, 12 Mar. 2026.</li>
<li>“Unions Furious as GM Replaces 1,000 Factory Zero Workers with 50 Robots.” Yahoo News, June 2026.</li>
</ol>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Could robots help tackle loneliness? BBC’s Ann Droid raises questions about the future of care</title>
		<link>https://robohub.org/could-robots-help-tackle-loneliness-bbcs-ann-droid-raises-questions-about-the-future-of-care/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Mon, 07 Sep 2026 09:33:36 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221105</guid>

					<description><![CDATA[By Maria Jose Galvez Trigo, Cardiff University and Paul Willis, Cardiff University New BBC sitcom Ann Droid imagines a near future in which robots provide care and companionship to older people at home. The series centres on Sue, a recent widow played by Sue Johnston, her hapless son Michael and Linda, an assistive care robot [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-1024x740.jpg" alt="" width="1024" height="740" class="alignnone size-large wp-image-221108" srcset="https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-1024x740.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-425x307.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-768x555.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-1536x1110.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/antranias-human-511848-2048x1479.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By <a href="https://theconversation.com/profiles/maria-jose-galvez-trigo-2751723" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Maria Jose Galvez Trigo</a>, <em><a href="https://theconversation.com/institutions/cardiff-university-1257" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff University</a></em> and <a href="https://theconversation.com/profiles/paul-willis-2751692" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Paul Willis</a>, <em><a href="https://theconversation.com/institutions/cardiff-university-1257" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff University</a></em></strong></p>
<p>New BBC sitcom Ann Droid imagines a near future in which robots provide care and companionship to older people at home.</p>
<p>The series centres on Sue, a recent widow played by Sue Johnston, her hapless son Michael and Linda, an assistive care <a href="https://theconversation.com/topics/robots-6403" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robot</a> played by Diane Morgan. Linda is designed to provide daily support and companionship, with predictably comic results.</p>
<p>As researchers in <a href="https://ijpds.org/index.php/ijpds/article/view/3393" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">social care</a>, ageing and human-centred <a href="https://ieeexplore.ieee.org/document/10974051" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robotics</a>, we obviously watched <a href="https://www.bbc.co.uk/programmes/m002xhy2" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Ann Droid</a> with a keen eye. Beneath the jokes are questions that researchers are already tackling. </p>
<p>Could robots help address loneliness among older people? Can a machine provide companionship without replacing human connection? While the series exaggerates what robots can currently do, some of the technology it depicts is already being tested.</p>
<div class="keep-aspect"><iframe title="Introducing new Diane Morgan comedy, Ann Droid - BBC" width="500" height="281" src="https://www.youtube-nocookie.com/embed/hqAlc6F6WAo?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<em>The BBC’s Ann Droid sitcom.</em></p>
<p>A social enterprise in south-west England has been piloting <a href="https://comfortcompanions.co.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Comfort Companions</a> in partnership with Age UK South Gloucestershire. AI-generated personas offer conversation and guidance to older people living alone and at risk of loneliness. </p>
<p>It runs <a href="https://www.somersetlive.co.uk/news/somerset-news/family-tech-venture-launches-service-10455052" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">alongside</a> Age UK’s volunteer programme, with befrienders helping older people learn how to use the app. The AI companions are intended to supplement the waiting list for human befrienders rather than replacing them. </p>
<p>Physical robots are being tested too. West Berkshire Council has been running a <a href="https://www.bbc.co.uk/news/articles/cly19413xpyo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">trial</a> using robotic pets in its care homes. </p>
<p>Neither scheme offers robots who look like Linda. Current systems tend to be AI avatars on a screen or robotic cats or dogs, or speakers that provide a voice in the room. They do much less than Linda too. They can’t help someone up after a fall, wash them or get them dressed. </p>
<p>What technology does currently do best is monitoring and prompting. Systems that can detect a fall and alert another person are far more mature, while technology can also encourage someone to contact friends, make a phone call, or get out of the house. </p>
<h2>Can a machine make you less lonely?</h2>
<p>It’s worth considering this distinction because <a href="https://www.campaigntoendloneliness.org/facts-and-statistics/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">loneliness</a> is not simply the same as being alone. It’s a <a href="https://peplau.psych.ucla.edu/wp-content/uploads/sites/141/2017/07/Perlman-Peplau-98.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">personal feeling</a> that our relationships are insufficient, accompanied by a desire for more or better social contact.</p>
<p>A robot companion, therefore, is unlikely to solve loneliness simply by being present. What matters is the quality of the interaction and whether technology can help someone maintain relationships with the people who matter to them.</p>
<p>This is one of the more interesting ideas in Ann Droid. Linda can sometimes strengthen Sue’s existing relationships rather than replace them, encouraging her to meet friends and plan activities outside the home. That’s potentially a more useful way to think about companion technology. The goal need not be to create an artificial friend who substitutes for a human one, but to help people remain connected to others.</p>
<p>The barriers are still substantial. Battery life is a limitation. Most humanoid robots manage between 90 minutes and five hours per charge when new. This is why an overnight camping trip featured in the sitcom is a fair test on the fantasy. </p>
<p>Robots are much better at some tasks than others. A machine may be able to play chess, for example, but <a href="https://arxiv.org/abs/1910.00127" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">picking up</a> an unfamiliar household object in the real world remains surprisingly difficult.</p>
<p>The social barriers are even harder. Robots struggle with the social subtleties that people take for granted. Systems that learn by copying human behaviour can reproduce an action without understanding its intention. They also cannot reliably interpret facial expressions.</p>
<p>A <a href="https://www.sciencedirect.com/science/article/pii/S0957417426016222" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">review</a> of systems designed to detect emotion from faces found that they performed worst when interpreting older faces, with anger and neutral expressions among the least reliably identified. This is important in care because recognising how someone is feeling can be crucial.</p>
<h2>Would we trust a robot carer?</h2>
<p>Ann Droid also plays on a more instinctive discomfort: should we trust a machine that’s designed to look after us? The sitcom playfully touches on public worries about interacting with robotic companions, including people’s distrust and worries about potential harms. For example, in one episode two robots enjoy a joke together about killing their human companions. </p>
<p><a href="https://www.sciencedirect.com/science/article/pii/S1041610226000347" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Research</a> suggests that older people can see value in companion robots. But acceptance depends partly on whether people feel they remain in control. And appearance is a factor too. </p>
<p>In 1970, the roboticist Masahiro Mori <a href="https://spectrum.ieee.org/the-uncanny-valley" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">proposed</a> the idea of the “uncanny valley”. As machines become more human-like, we initially respond more positively to them. But when they look almost human without quite getting there, that warmth can turn into discomfort. </p>
<div class="keep-aspect"><iframe title="Dinner with the robot-in-law went badly wrong - BBC" width="500" height="281" src="https://www.youtube-nocookie.com/embed/EdWS4uUpnL8?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<em>Ann Droid &#8211;  dinner with the robot-in-law.</em></p>
<p>Robots have some obvious advantages. They don’t get bored, tired or impatient. They can handle dangerous tasks and they’re available at 3am. But they can’t provide something fundamental to care: a relationship in which both people choose to be there.</p>
<p>That’s the bond that no machine can supply. Robots may have a useful role in social care, but they’re worth having only when people want them, alongside human care and companionship. Otherwise, we risk finding an expensive technological answer to a much harder question: why do some older people have so little human contact in the first place?<!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding="async" src="https://counter.theconversation.com/content/289430/count.gif?distributor=republish-lightbox-basic" alt="The Conversation" width="1" height="1" style="border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important" referrerpolicy="no-referrer-when-downgrade" /><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https://theconversation.com/republishing-guidelines --></p>
<p><span><a href="https://theconversation.com/profiles/maria-jose-galvez-trigo-2751723" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Maria Jose Galvez Trigo</a>, Senior Lecturer (Associate Professor) in Human-Centred Robotics and AI, <em><a href="https://theconversation.com/institutions/cardiff-university-1257" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff University</a></em> and <a href="https://theconversation.com/profiles/paul-willis-2751692" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Paul Willis</a>, Professor of Social Care, <em><a href="https://theconversation.com/institutions/cardiff-university-1257" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Cardiff University</a></em></span></p>
<p>This article is republished from <a href="https://theconversation.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Conversation</a> under a Creative Commons license. Read the <a href="https://theconversation.com/could-robots-help-tackle-loneliness-bbcs-ann-droid-raises-questions-about-the-future-of-care-289430" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">original article</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Exploring the Moon will require rovers that can think for themselves – an upcoming NASA mission will test whether they can</title>
		<link>https://robohub.org/exploring-the-moon-will-require-rovers-that-can-think-for-themselves-an-upcoming-nasa-mission-will-test-whether-they-can/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Fri, 04 Sep 2026 09:32:44 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221011</guid>

					<description><![CDATA[By Wanjiku Chebet Kanjumba, University of Florida NASA is planning to send three small rovers to the Moon with a single instruction: Work out among yourselves how to explore a patch of ground. The Cooperative Autonomous Distributed Robotic Exploration mission, or CADRE, will land on the side of the Moon facing Earth as part of [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-1024x890.jpg" alt="" width="1024" height="890" class="alignnone size-large wp-image-221014" srcset="https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-1024x890.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-425x369.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-768x667.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-1536x1335.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/pexels-full-moon-1869760-2048x1779.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By <a href="https://theconversation.com/profiles/wanjiku-chebet-kanjumba-2685452" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Wanjiku Chebet Kanjumba</a>, <em><a href="https://theconversation.com/institutions/university-of-florida-1392" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Florida</a></em></strong></p>
<p>NASA is planning to send three small rovers to the Moon with a single instruction: Work out among yourselves how to explore a patch of ground.</p>
<p>The Cooperative Autonomous Distributed Robotic Exploration mission, or CADRE, <a href="https://www.jpl.nasa.gov/missions/cadre/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">will land</a> on the side of the Moon facing Earth as part of NASA’s <a href="https://www.nasa.gov/missions/moon-base/nasa-provides-updates-on-moon-base-cargo-landers-tech-demonstrations/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IM-3 launch</a>, planned for late 2026. These rovers will spend roughly two weeks mapping the terrain as a self-guided team. No joystick will control them, and no human will approve each turn.</p>
<p><figure class="align-center zoomable">
            <a aria-label="Zoomable image" href="https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=1000&amp;fit=clip" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" alt="Three small robotic rovers drive across a sterile warehouse floor." src="https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=338&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=338&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=338&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=424&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=424&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/753170/original/file-20260810-60-1boygh.jpeg?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=424&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"></a><em>Engineers test whether the CADRE rovers can drive and coordinate on their own at NASA’s Jet Propulsion Laboratory in Pasadena, Calif. <a href="https://www.jpl.nasa.gov/images/pia26164-nasas-cadre-rovers-take-first-autonomous-drive/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">NASA/JPL-Caltech</a>.</em><br />
          </figure>
</p>
<p>The rovers will elect a leader among themselves, assign their own tasks and redraw their plans as a group when one of them runs low on charge. If it succeeds, CADRE will be the first time NASA has operated multiple rovers beyond Earth as a single autonomous system.</p>
<p>That achievement will matter well beyond this mission, because NASA is scoping out future missions <a href="https://theconversation.com/scientists-suspect-theres-ice-hiding-on-the-moon-and-a-host-of-missions-from-the-us-and-beyond-are-searching-for-it-216060" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">to the lunar South Pole</a>, where water in the form of <a href="https://theconversation.com/how-can-there-be-ice-on-the-moon-225979" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ice sits locked in craters</a> that haven’t seen sunlight in billions of years. If researchers can chemically split that ice apart and turn it into propellant and breathable air, it could become the feedstock for a <a href="https://www.csis.org/analysis/cracking-code-lunar-economy" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">lunar economy</a> built around fuel depots and life support made on the Moon.</p>
<p>Right now, the only demand for that ice comes from government contracts. And an operation that must be babysat from 239,000 miles (384,000 kilometers) away will not easily scale into a market. So, while a full-blown lunar economy is still far off, CADRE is testing whether robots can work unsupervised long enough, and in enough numbers, to keep a lunar operation running month after month.</p>
<p>I’m an aerospace engineering Ph.D. candidate <a href="https://doi.org/10.2514/6.2026-1921" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">researching guidance, navigation and control</a> for spacecraft in-orbit servicing and active debris removal. I work on the same problem these rovers face: how a machine decides what to do next when it cannot call home for instructions.</p>
<h2>Why Earth cannot drive</h2>
<p>At the Moon’s South Pole, the terrain itself can cause communication disruptions. Commands reach a rover by way of relay satellites, and crater rims can block the line of sight to those relays. A rover that ventures down into a shadowed crater may lose contact for its entire trip.</p>
<p>Spotty communication doesn’t just make trying to drive annoying. It can cost the rover power it cannot recover.</p>
<p>A polar rover runs on a <a href="https://ntrs.nasa.gov/citations/20120010094" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">finite illumination budget</a>. Solar panels charge the battery only while the Sun is up, and on the Moon sunrise is not a daily event. Night <a href="https://www.iflscience.com/how-long-is-a-lunar-day-and-night-72768" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">lasts about two Earth weeks</a>, and at the poles, only a few ridges stay lit for long stretches. So for every minute a rover spends idle, awaiting new instructions, it is spending stored energy it cannot replace until the Sun comes back.</p>
<figure class="align-center zoomable">
            <a aria-label="Zoomable image" href="https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=1000&amp;fit=clip" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" alt="Two graphs sharing one time axis that spans a single surface trip. The top graph, stored energy, rises while the rover recharges in sunlight at the start, then falls in a straight line at a constant rate for the rest of the trip. The bottom graph, tasks completed, has two step lines: the autonomous team's keeps stepping up through the shaded communication blackouts, while the ground-commanded team's stays flat through each one, so the gap between the two widens." src="https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=491&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=491&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=491&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=617&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=617&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/753619/original/file-20260812-50-iumkqp.png?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=617&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"></a><em>In the top image, a rover’s stored energy climbs while it charges in sunlight, then falls at the same rate whether it is working or waiting idly. In the bottom image, the gray bands are communication blackouts. A team waiting on commands from Earth stops until the link returns, while an autonomous team keeps assigning itself work, and the gap that opens between the two lines is work recovered from what would otherwise be dead time. Credit: Wanjiku Chebet Kanjumba.</em><br />
          </figure>
<h2>Why the pole is the hard case</h2>
<p>The lunar poles also come with unique challenges. Sunlight can swing from direct glare to absolute shadow as a rover drives down from a sunlit crater rim to the shadowed floor below, so a camera that worked at the top could go blind at the bottom.</p>
<p>The Moon also doesn’t have GPS satellites like Earth does, so rovers can’t know exactly where they are. They need to build their own maps from what their cameras and sensors see.</p>
<p>Temperatures inside permanently shadowed regions <a href="https://doi.org/10.1038/s41550-020-1198-9" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">drop below minus 274 degrees Fahrenheit</a> (minus 170 degrees Celsius). And the Moon’s dust is more dangerous than it sounds. An electric charge lifts it off the ground, and billions of years of tiny meteorite strikes have left <a href="https://science.nasa.gov/biological-physical/what-is-lunar-regolith/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">every grain sharp and jagged</a>.</p>
<p>That dust grinds at the wheel bearings and works past the seals. Keeping it out of the rover’s moving parts is still an <a href="https://doi.org/10.1016/j.asr.2026.01.006" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">unsolved problem</a>. The dust can also film over the camera lenses that navigation depends on, leaving a rover unable to see where it is going or move safely.</p>
<h2>Why one rover is not enough</h2>
<p>Sending a single rover to check out a crater on the Moon is a risky mission. If it gets stuck, the campaign ends. If its instruments fail, no second machine can take the measurements. Multirobot teams <a href="https://doi.org/10.3389/frobt.2023.1149080" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">distribute that risk</a> and split up the jobs. One rover might carry the sensors and another the drill, while a lander positioned on a sunlit ridge acts as the power and communications hub.</p>
<p>Under a communications blackout, a rover team that waits for its commands from Earth has to stop. An autonomous team reassigns tasks among itself, selecting the next objective that it can reach and complete with the amount of power it has left. Dead time becomes work time.</p>
<p>In ground testing at NASA’s Jet Propulsion Laboratory, the CADRE rovers achieved this coordination. Faced with unexpected obstacles, they replanned paths as a group, and when one rover’s battery ran low, the whole team paused so <a href="https://www.jpl.nasa.gov/missions/cadre/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">they could continue together</a>.</p>
<figure class="align-center zoomable">
            <a aria-label="Zoomable image" href="https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=1000&amp;fit=clip" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" alt="A diagram showing how different rovers and a lander communicate and work together on the lunar surface" src="https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;fit=clip" srcset="https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=600&amp;h=367&amp;fit=crop&amp;dpr=1 600w, https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=600&amp;h=367&amp;fit=crop&amp;dpr=2 1200w, https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=600&amp;h=367&amp;fit=crop&amp;dpr=3 1800w, https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=45&amp;auto=format&amp;w=754&amp;h=462&amp;fit=crop&amp;dpr=1 754w, https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=30&amp;auto=format&amp;w=754&amp;h=462&amp;fit=crop&amp;dpr=2 1508w, https://images.theconversation.com/files/753611/original/file-20260812-50-e1qt4h.jpg?ixlib=rb-4.1.1&amp;q=15&amp;auto=format&amp;w=754&amp;h=462&amp;fit=crop&amp;dpr=3 2262w" sizes="(min-width: 1466px) 754px, (max-width: 599px) 100vw, (min-width: 600px) 600px, 237px"></a><em>A prospecting team splits the work. A lander on the sunlit rim supplies power and relays communications, while a rover and a drill work the permanently shadowed crater floor below, where water ice may be trapped and no sunlight reaches. Once they drop past the rim’s radio horizon, they are out of contact and have to divide the tasks and manage their own power. Credit: Wanjiku Chebet Kanjumba.</em><br />
          </figure>
<h2>What remains uncertain</h2>
<p>A campaign at the lunar South Pole would need to run for months, and no robot team has yet worked that hard, for that long, that far from help. Engineers are <a href="https://www.nasa.gov/lunar-surface-technology/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">developing ways</a> for rovers to navigate without satellite positioning and to make decisions onboard, but that software still has to be tested on the surface.</p>
<p>Meanwhile, as of mid-August 2026, <a href="https://www.planetary.org/space-missions/change-7" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">China’s Chang&#8217;e-7</a> mission is waiting at Wenchang, the launch site on Hainan Island in China, with liftoff expected by the end of the year. Its lander, rover and hopping probe are meant to work at the pole as a team, with the probe built to leap into permanently shadowed craters. If the U.S. wants to keep pace, it will need its own robots that coordinate without supervision.</p>
<p>Finally, there is no agreed way for a rover built by one company to hand a task to a tool built by another, or to decide which one works the crater floor first. As autonomous rover teams improve, the groups building them will have to work out those rules.</p>
<p>CADRE will tell scientists whether three small rovers can reason together on the Moon. The harder question is whether a dozen different machines from different builders can do the same thing, reliably, for years.<!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding="async" src="https://counter.theconversation.com/content/289200/count.gif?distributor=republish-lightbox-basic" alt="The Conversation" width="1" height="1" style="border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important" referrerpolicy="no-referrer-when-downgrade" /><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https://theconversation.com/republishing-guidelines --></p>
<p><span><a href="https://theconversation.com/profiles/wanjiku-chebet-kanjumba-2685452" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Wanjiku Chebet Kanjumba</a>, Ph.D. Candidate in Aerospace Engineering, <em><a href="https://theconversation.com/institutions/university-of-florida-1392" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">University of Florida</a></em></span></p>
<p>This article is republished from <a href="https://theconversation.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Conversation</a> under a Creative Commons license. Read the <a href="https://theconversation.com/exploring-the-moon-will-require-rovers-that-can-think-for-themselves-an-upcoming-nasa-mission-will-test-whether-they-can-289200" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">original article</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Surviving the paper deluge: Notes from an ICRA panel on publishing, LLMs, and the future of peer review</title>
		<link>https://robohub.org/surviving-the-paper-deluge-notes-from-an-icra-panel-on-publishing-llms-and-the-future-of-peer-review/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 02 Sep 2026 07:58:49 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221100</guid>

					<description><![CDATA[A recent ICRA panel titled “Surviving the Paper Deluge” brought together leading robotics researchers who have grappled with the overwhelming number of robotics papers being published today. The discussion ranged from hard numbers on publication growth, through the promises and risks of large language models (LLMs), to radical proposals for reshaping peer review as we [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/bigstock-Stack-Of-Paperwork-And-Documen-283334074.jpg" alt="" width="900" height="600" class="size-full wp-image-221101" srcset="https://robohub.org/wp-content/uploads/2026/08/bigstock-Stack-Of-Paperwork-And-Documen-283334074.jpg 900w, https://robohub.org/wp-content/uploads/2026/08/bigstock-Stack-Of-Paperwork-And-Documen-283334074-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/bigstock-Stack-Of-Paperwork-And-Documen-283334074-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /> </p>
<p>A recent ICRA panel titled “Surviving the Paper Deluge” brought together leading robotics researchers who have <a href="https://www.ieee-ras.org/surviving-the-paper-deluge-a-one-year-study-in-learning-from-demonstration/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">grappled with the overwhelming number of robotics papers being published today</a>.</p>
<p>The discussion ranged from hard numbers on publication growth, through the promises and risks of large language models (LLMs), to radical proposals for reshaping peer review as we know it.</p>
<p>Panel chair <a href="https://ieeexplore.ieee.org/author/37273980800" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Aude Billard</a> pointed to rapid growth across major IEEE Robotics and Automation Society venues, with a roughly exponential curve beginning around 2017. An estimate for 2025 suggests around 70,000 papers containing the word “robotics.”</p>
<p>Billard noted that while in some fields, extreme specialization may be an acceptable survival strategy, robotics is inherently different. A robot is an integration of perception, control, manipulation, learning, hardware, interaction, safety, and deployment. If researchers can only stay current within narrow silos, the field risks losing one of its core strengths: the ability to connect ideas across domains.</p>
<p><a href="https://eps.leeds.ac.uk/computing/staff/16237/dr-kunpeng-yao" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Kunpeng Yao</a> presented a case study funded by <a href="https://www.ieee-ras.org/about-ras/governance/science-and-technology-watch-board/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE RAS Science and Technology Watch Board</a>. The team tried to do something that borders on heroic in today’s publishing environment; that is, reading an entire subfield carefully over a single year.</p>
<p>Focusing on papers related to learning from demonstration, the team searched IEEE Xplore for relevant 2024 papers, screened the results manually, and identified 347 relevant papers. Of those, only 69, or about 20 percent, were judged to have made notable contributions.</p>
<p>According to the criteria used, ‘notable’ papers tended to offer new formulations, mechanisms, or theoretical guarantees; serious comparisons against strong state of the art; clear gains in robustness, transfer, or failure recovery; new teaching or data collection modalities; and convincing real-robot validation. Papers were less compelling when they simply relabelled existing approaches or failed to demonstrate their claims.</p>
<p>Yao summarized one lesson neatly: notability should be judged against the state of the art, not against “the newest vocabulary.”</p>
<p>That distinction is of particular importance in a field where new labels can travel quickly and a paper may sound fresh without actually moving the frontier. Conversely, useful work is sometimes hidden in less fashionable venues or written by less visible groups.</p>
<h4>Degrees of hallucination</h4>
<p>One question is whether large language models can help with literature review. <a href="https://ieeexplore.ieee.org/author/38252346300" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Nadia Figueroa</a> explained that LLMs can improve the mechanics of literature review. That is, they can help with search, retrieval, clustering, tables, summaries, and rough conceptual maps. Work that once took weeks or months can now sometimes be done in hours. For a new PhD student entering a field, that is a genuine reduction in the barrier to entry.</p>
<p>But Figueroa also identified hallucination as a major issue. First-order hallucination involves fake or incorrect references. More subtle is second-order hallucination, where the reference is real but the model misstates what the paper actually did. Also dangerous is third-order hallucination, where the LLM invents plausible but false commonalities across papers.</p>
<p>“The danger currently is not fake citations,” observed Figueroa. “It’s fake understanding.”</p>
<p>An LLM-based literature review can contain real papers and still misrepresent the field. It can be fluent, structured, and wrong. If researchers outsource not just the mechanics of reading but the cognitive act of comparison, judgment, and doubt, the field may produce more text while developing less understanding.</p>
<h4>Salami and sandcastles</h4>
<p>Meanwhile, <a href="https://ieeexplore.ieee.org/author/37274057100" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Greg Dudek</a> described the familiar problem of “salami slicing,” where a larger body of work is divided into “the thinnest possible slices” and spread across workshops, conferences, and journals.</p>
<p>For Dudek, the system rewards this behaviour. Students need papers to graduate. Early-career researchers need papers for jobs. Committees often face too much material to read deeply, so titles, venues, counts, and indices become tempting shortcuts.</p>
<p>But the result is costly for readers. Multiple papers repeat the same background, divide one contribution into fragments, and make it harder to reconstruct the full story.</p>
<p>His preferred remedy is simple in principle but difficult in practice: publish fewer, more integrated papers.</p>
<p>Dudek is under no illusion about how hard this will be. “There is no fix,” he said, if by fix we mean a return to a quieter world. Incremental reforms may help, but the flood is still rising. He compared small procedural fixes to building better walls around a sandcastle while “there’s a tsunami coming from the back of the room.”</p>
<h4>Re-designing peer review?</h4>
<p><a href="https://ieeexplore.ieee.org/author/613201789123653" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Renaud Detry</a> argued that the growth in publications partly reflects the growing presence of applied systems work in academic venues. That is not necessarily bad. Robotics advances through real systems, data, benchmarks, platforms, and the last-mile effort needed to make ideas work outside idealized settings.</p>
<p>The problem is that the same evaluation machinery often judges very different contribution types. A new algorithm, a carefully engineered system, a benchmark, a dataset, and an industrially relevant validation study should not all have to pretend to be the same kind of paper. Robotics may need clearer tracks for fundamental science, applications, infrastructure, benchmarks, and technical correctness.</p>
<h4>Visibility is not value</h4>
<p><a href="https://ieeexplore.ieee.org/author/37068725100" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Dongheui Lee</a> addressed another vital part of the new publication ecosystem: arXiv, open-source releases, project pages, videos, blogs, and social media. These tools can broaden access, improve reproducibility, and help readers decide what to examine closely. But they also distort attention. Visibility can reflect institutional prestige, networks, speed, and self-promotion as much as scientific value.</p>
<p>Lee’s suggestion was pragmatic: keep expert peer review as a quality filter but use its signals better. Editorial boards and media teams could do more to promote strong papers that receive excellent reviews but do not come from famous labs.</p>
<h4>Beyond the gatekeeper model</h4>
<p>The most radical question came from <a href="https://ieeexplore.ieee.org/author/37274050800" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Shigeki Sugano</a>, who asked “What if we were to abandon peer review altogether?” In Sugano’s model, legitimate robotics and AI manuscripts would be uploaded first to an open archive, along with videos, code, and data.</p>
<p>Community evaluation, under verified identities, would happen in public. Journals and conferences would then certify high-value work rather than deciding what gets to exist.</p>
<p>“The question is not whether peer review is valuable,” he argued. “The question is whether it must remain the only gate to visibility.”</p>
<p>Not everyone agreed. Popularity bias, gaming, reputation effects, and low-quality papers flooding the system were highlighted by other panelists as possible risks. Still, Sugano’s radical proposal addressed real challenges around the ability of traditional accept-or-reject peer review models to scale to meet the deluge of papers flooding the robotics community’s information space.</p>
<p>No one on the panel pretended there was a clean fix. Instead, it emerged that the paper deluge is a tangle of volume, incentives, tools, evaluation, visibility, and culture.</p>
<p>Nevertheless, several useful principles emerged. LLMs may provide some mechanical support but carry risks of intellectual outsourcing. Read selectively and deeply. Reward quality before publication counts. Recognize different kinds of value in robotics research. Treat visibility as a possible indicator of worth, not as a verdict.</p>
<h4>The open question</h4>
<p>One major question remains: what happens to robotics research if papers continue to be published at the current rate?</p>
<p>There are clear benefits. More papers, more preprints, and more routes into publication can lower barriers to entry, help new researchers find a foothold, and make the field more open to a wider range of voices. Platforms such as arXiv have also made it easier for work to circulate before, or outside of, traditional publication channels.</p>
<p>But the risks are equally clear. Robotics is an integrative field, bringing together perception, control, manipulation, locomotion, hardware, safety, learning, and human-robot interaction. If researchers can only keep up with narrow slices of that landscape, the field may become more siloed. One result could be a growing reliance on off-the-shelf tools, including black-box commercial systems, without a deep understanding of the foundations on which those tools depend.</p>
<p>There is also the problem of memory. At a certain scale, no individual researcher can read far enough back, or broadly enough across adjacent domains. That increases the risk of duplicated work, overlooked insights, and important papers disappearing beneath the next wave of more fashionable topics.</p>
<hr>
<p>This article originally appeared on <a href="https://www.ieee-ras.org/surviving-the-paper-deluge-notes-from-an-icra-panel-on-publishing-llms-and-the-future-of-peer-review/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE RAS</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>When expressive humanoid robots are awkward, people become wary – new brain study</title>
		<link>https://robohub.org/when-expressive-humanoid-robots-are-awkward-people-become-wary-new-brain-study/</link>
		
		<dc:creator><![CDATA[The Conversation]]></dc:creator>
		<pubDate>Mon, 31 Aug 2026 09:18:24 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220994</guid>

					<description><![CDATA[Photo by Alex Knight on Unsplash. By Hasan Ayaz, Drexel University; Ewart J. de Visser, United States Air Force Academy; Frank Krueger, George Mason University, and Yigit Topoglu, United States Air Force Academy People become more suspicious of a humanoid robot that makes errors, especially when the robot is an expressive conversation partner. In our [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-220997" srcset="https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/alex-knight-2EJCSULRwC8-unsplash-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Photo by <a href="https://unsplash.com/@agk42?utm_source=unsplash&#038;utm_medium=referral&#038;utm_content=creditCopyText" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Alex Knight</a> on <a href="https://unsplash.com/photos/white-robot-near-brown-wall-2EJCSULRwC8?utm_source=unsplash&#038;utm_medium=referral&#038;utm_content=creditCopyText" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Unsplash</a></em>.</p>
<p><strong>By <a href="https://theconversation.com/profiles/hasan-ayaz-2745434" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Hasan Ayaz</a>, <em><a href="https://theconversation.com/institutions/drexel-university-1074" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Drexel University</a></em>; <a href="https://theconversation.com/profiles/ewart-j-de-visser-2745463" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Ewart J. de Visser</a>, <em><a href="https://theconversation.com/institutions/united-states-air-force-academy-5707" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">United States Air Force Academy</a></em>; <a href="https://theconversation.com/profiles/frank-krueger-2745454" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Frank Krueger</a>, <em><a href="https://theconversation.com/institutions/george-mason-university-1331" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">George Mason University</a></em>, and <a href="https://theconversation.com/profiles/yigit-topoglu-2745449" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Yigit Topoglu</a>, <em><a href="https://theconversation.com/institutions/united-states-air-force-academy-5707" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">United States Air Force Academy</a></em></strong></p>
<p>People become more suspicious of a humanoid robot that makes errors, especially when the robot is an expressive conversation partner.</p>
<p>In our <a href="https://doi.org/10.1126/scirobotics.aec1762" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">new study</a> published in the journal Science Robotics, we had 50 people hold conversations and make joint decisions with the commercial <a href="https://humanoidindex.org/robots/pepper" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">humanoid robot Pepper</a>, which is designed to be expressive and recognize emotions. Sometimes we had the robot give sound advice. Sometimes we had it make conversational mistakes, interrupting people or pushing illogical suggestions.</p>
<p>For some participants, the robot was animated, using gestures, eye contact and nods. For others, it stayed motionless.</p>
<p>We measured four things: brain activity, levels of the hormone oxytocin, self-reported trust and our observations of the robot’s influence on participants’ decisions.</p>
<p>We found that when people interacted with an expressive robot that violated interaction norms, their <a href="https://www.health.harvard.edu/mind-and-mood/oxytocin-the-love-hormone" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">oxytocin</a> levels increased. Oxytocin is popularly known as the “love hormone” for its role in social bonding, so the straightforward prediction is that it declines when a partner disappoints you.</p>
<p>Instead, the higher a person’s oxytocin during an expressive robot’s errors, the less they trusted the robot and the less often they took its advice. It turns out that the hormone was tracking with suspicion, not affection.</p>
<p>Errors damaged trust and diminished influence whether or not the robot was expressive. What expressiveness in the robot changed in participants was how their brains handled the moment.</p>
<p>Reading someone’s brain during a real conversation is hard because the conventional method requires lying motionless inside an MRI scanner. Instead, we used <a href="https://med.stanford.edu/cibsr/GettingReady/about-nirs.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">functional near-infrared spectroscopy</a>, a portable sensor worn on the forehead that tracks oxygen levels in the brain while people move and talk normally.</p>
<p>The two brain regions we closely watched were the dorsolateral prefrontal cortex and the medial prefrontal cortex. The <a href="https://www.simplypsychology.org/dorsolateral-prefrontal-cortex.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">dorsolateral prefrontal cortex</a> monitors uncertainty and flags when expectations or norms get broken. The <a href="https://www.simplypsychology.org/dorsomedial-prefrontal-cortex.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">medial prefrontal cortex</a> supports “<a href="https://dictionary.apa.org/mentalization" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">mentalizing</a>,” the everyday work of inferring what another party intends.</p>
<p>When an animated robot erred, people seemed caught off guard and had to work harder to make sense of an awkward social situation. Activity rose in the two brain regions, and the two started working together more closely. That closer teamwork predicted the rise in oxytocin levels, which itself predicted falling trust and less influence on participants’ behavior. In contrast, this coordinated brain activity was absent in participants who interacted with expressionless robots.</p>
<h2>Why it matters</h2>
<p>Robots are <a href="https://www.washingtonpost.com/technology/2025/09/05/humanoid-robots-ai-agility-chatgpt/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">moving into homes, hospitals and workplaces</a>, where trust in robots determines whether people use them at all. A common design assumption has been that lifelike, socially expressive robots earn more trust, which protects a robot’s “reputation” even when it makes mistakes.</p>
<p>However, research is beginning to show that <a href="https://doi.org/10.1109/RO-MAN57019.2023.10309321" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">that assumption is faulty</a>. Our work shows that expressive cues appear to shift how people perceive a mistake out of the category of technical malfunction and into the category of social violation, like those that happen between people. </p>
<p>A motionless robot’s error looks mechanical, while the same error from an animated robot engages the machinery you use to judge people.</p>
<h2>What other research is being done</h2>
<p>Researchers increasingly treat trust as a <a href="https://doi.org/10.1007/978-3-319-22261-5_7" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">multilevel phenomenon</a> – spanning individuals, relationships, networks of people and societies – rather than a single attitude.</p>
<p>Much research on oxytocin involves humans interacting with humans, where the hormone is tied to bonding, though a growing body of work shows that those effects <a href="https://doi.org/10.1016/j.neubiorev.2026.106566" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">depend on the context, uncertainty and perceived threat</a>.</p>
<p>Others are using wearable brain imaging systems to study social cognition <a href="https://doi.org/10.1038/s41583-023-00692-y" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">in natural encounters</a> between people, which isn’t possible when subjects are in scanners like MRI machines.</p>
<h2>What’s next</h2>
<p>The participants in this study were all young men, and we used one robot design. A key next step is testing whether the same oxytocin-linked vigilance appears in women, mixed groups, other cultures and other robot designs. Our brain sensor also reached only the front of the brain, leaving deeper regions involved in social processing unmeasured.</p>
<p>We also want to examine whether robots can repair trust after a mistake by acknowledging the error, apologizing or signaling good intent, the way that people do after awkward or uncomfortable interactions.</p>
<p><em>The <a href="https://theconversation.com/us/topics/research-brief-83231" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Research Brief</a> is a short take about interesting academic work.</em><!-- Below is The Conversation's page counter tag. Please DO NOT REMOVE. --><img decoding="async" src="https://counter.theconversation.com/content/288696/count.gif?distributor=republish-lightbox-basic" alt="The Conversation" width="1" height="1" style="border: none !important; box-shadow: none !important; margin: 0 !important; max-height: 1px !important; max-width: 1px !important; min-height: 1px !important; min-width: 1px !important; opacity: 0 !important; outline: none !important; padding: 0 !important" referrerpolicy="no-referrer-when-downgrade" /><!-- End of code. If you don't see any code above, please get new code from the Advanced tab after you click the republish button. The page counter does not collect any personal data. More info: https://theconversation.com/republishing-guidelines --></p>
<p><span><a href="https://theconversation.com/profiles/hasan-ayaz-2745434" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Hasan Ayaz</a>, Professor of Biomedical Engineering, Science and Health Systems, <em><a href="https://theconversation.com/institutions/drexel-university-1074" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Drexel University</a></em>; <a href="https://theconversation.com/profiles/ewart-j-de-visser-2745463" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Ewart J. de Visser</a>, Technical Director, Warfighter Effectiveness Research Center, <em><a href="https://theconversation.com/institutions/united-states-air-force-academy-5707" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">United States Air Force Academy</a></em>; <a href="https://theconversation.com/profiles/frank-krueger-2745454" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Frank Krueger</a>, Professor of Systems Social Neuroscience, <em><a href="https://theconversation.com/institutions/george-mason-university-1331" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">George Mason University</a></em>, and <a href="https://theconversation.com/profiles/yigit-topoglu-2745449" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Yigit Topoglu</a>, Research Scientist, Warfighter Effectiveness Research Center, <em><a href="https://theconversation.com/institutions/united-states-air-force-academy-5707" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">United States Air Force Academy</a></em></span></p>
<p>This article is republished from <a href="https://theconversation.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Conversation</a> under a Creative Commons license. Read the <a href="https://theconversation.com/when-expressive-humanoid-robots-are-awkward-people-become-wary-new-brain-study-288696" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">original article</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>First 11 vs 11 humanoid soccer game played at RoboCup 2026</title>
		<link>https://robohub.org/first-11-vs-11-humanoid-soccer-game-played-at-robocup-2026/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Fri, 28 Aug 2026 06:25:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=21143</guid>

					<description><![CDATA[Action from the 11 vs 11 humanoid match at RoboCup 2026. Photo credit: RoboCup Federation. RoboCup 2026 saw history made, as two teams of 11 humanoids took to the soccer field, the first time a full complement of robots has competed. The game saw B-Human (Bremen, Germany) take on HTWK Robots (Leipzig, Germany), with both […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/08/11vs11.jpeg" alt="" width="1364" height="898" class="alignnone size-full wp-image-21145" srcset="https://aihub.org/wp-content/uploads/2026/08/11vs11.jpeg 1364w, https://aihub.org/wp-content/uploads/2026/08/11vs11-300x198.jpeg 300w, https://aihub.org/wp-content/uploads/2026/08/11vs11-1024x674.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/08/11vs11-768x506.jpeg 768w" sizes="(max-width: 1364px) 100vw, 1364px" /><em>Action from the 11 vs 11 humanoid match at RoboCup 2026. Photo credit: RoboCup Federation.</em></p>
<p><a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a> saw history made, as two teams of 11 humanoids took to the soccer field, the first time a full complement of robots has competed. The game saw <em>B-Human</em> (Bremen, Germany) take on <em>HTWK Robots</em> (Leipzig, Germany), with both sides using machines designed by Booster Robotics. </p>
<p>You can watch highlights of the match below:</p>
<div class="keep-aspect"><iframe title="While the World Watches Fifa World Cup, Robots Made History in RoboCup 2026" width="500" height="281" src="https://www.youtube-nocookie.com/embed/XuEdf0fMAME?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p><a href="https://aihub.org/2026/03/24/a-history-of-robocup-with-manuela-veloso/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Back in 1997</a>, RoboCup&#8217;s founders set the lofty goal of developing a team of autonomous robots that could beat the human World Cup champions by 2050. There has been significant progress since those early days, and this match saw another step towards that ambition. </p>
<p>“This match shows how far humanoid robotics has come,” said Ubbo Visser, President of the RoboCup Federation. “We have seen increased teamwork and advanced skills over the years already, but the new humanoid hardware paired with the new level of intelligence provided by AI puts humanoid robot soccer on another level.”</p>
<h4>Find out more:</h4>
<ul>
<li><a href="https://www.youtube.com/channel/UCzO59BkINO0uFrwEcNg9yfA" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Team B-Human YouTube channel</a></li>
<li><a href="https://www.youtube.com/channel/UCtF1RHsnDRkqDocerRjvfAQ" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Team HTWK Robots YouTube channel</a></li>
<li><a href="https://robocup.org/news/192" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">While the World Watches Soccer, Robots Made History in Incheon</a> &#8211; RoboCup Federation article about the match</li>
<li><a href="https://aihub.org/2026/08/26/first-11-vs-11-humanoid-soccer-game-played-at-robocup-2026/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup Federation website</a></li>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>How green is your robot? And other awkward questions</title>
		<link>https://robohub.org/how-green-is-your-robot-and-other-awkward-questions/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 26 Aug 2026 07:36:33 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[IEEE RAS]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220716</guid>

					<description><![CDATA[Deborah Lupton / Servers in a Landscape / Licenced by CC-BY 4.0 By Emmet Cole Robots clean rivers and sort waste, monitor ecosystems, and inspect renewable-energy infrastructure. But even the greenest robot has an environmental footprint. If robotics is going to help build a more sustainable world, the robotics community has to answer some potentially [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1-724x1024.png" alt="This image is a collage with a colourful Japanese vintage landscape showing a mountain, hills, flowers and other plants and a small stream. There are 3 large black data servers placed in the bottom half of the image, with a cloud of black smoke emitting from them, partly obscuring the scenery." width="724" height="1024" class="alignnone size-large wp-image-220719" srcset="https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1-724x1024.png 724w, https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1-301x425.png 301w, https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1-768x1086.png 768w, https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1-1086x1536.png 1086w, https://robohub.org/wp-content/uploads/2026/07/DeborahLupton-Serversin-a-Landscape-1280x1810-1.png 1280w" sizes="(max-width: 724px) 100vw, 724px" /><em><a href="https://betterimagesofai.org/whoWeAre" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Deborah Lupton</a> / <a href="https://betterimagesofai.org/images?artist=DeborahLupton&#038;title=ServersinaLandscape" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Servers in a Landscape</a> / <a href="https://creativecommons.org/licenses/by/4.0/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Licenced by CC-BY 4.0</a></em></p>
<p><strong>By Emmet Cole</strong></p>
<p>Robots <a href="https://www.bbc.com/news/articles/cy08y3zglklo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">clean rivers</a> and <a href="https://www.bbc.com/news/articles/cvg0w84q1wyo" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sort waste</a>, <a href="https://spectrum.ieee.org/why-we-need-robot-sloths" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">monitor ecosystems</a>, and <a href="https://ieeexplore.ieee.org/document/10695781" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">inspect renewable-energy infrastructure</a>. But even the greenest robot has an environmental footprint. </p>
<p>If robotics is going to help build a more sustainable world, the robotics community has to answer some potentially awkward questions, starting with this one: <em>How sustainable are robots themselves?</em></p>
<p>Across a full lifecycle, from rare earth mineral extraction and manufacturing to operation and end-of-life, robots have an environmental impact. But the robotics community has, until now, lacked dedicated tools for calculating it. </p>
<p>The <a href="https://roboticsecolabel.com/en" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Robotics Eco-Label</a> project, led by <a href="https://ieeexplore.ieee.org/author/37295389300" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Bram Vanderborght</a> at Belgium’s Vrije Universiteit Brussel, is an attempt to address that gap with a lightweight, web-based Toolkit that provides roboticists with a way to quantify robot sustainability.</p>
<p>Separating a robot’s core technologies into materials, energy sources, sensors, processors, actuators, design, and recyclability, the Robotics Eco-Label Toolkit then evaluates each based on <a href="https://roboticsecolabel.com/en/the-five-sustainability-metrics" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">five metrics</a>: resource conservation, lifecycle extension, carbon footprint, energy efficiency, and circularity. The numbers are combined in a weighted matrix to yield a 0–100 Eco-Score for Robots. The weights used are not currently fixed; that will be one of the targets of further research and collaboration. (For an indicative score on your robot, try the project’s interactive self-assessment tool <a href="https://roboticsecolabel.com/en/form/eco-label-score-calculator" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.) </p>
<p>A low score in one area might point to energy-hungry actuators, limited repairability, hard-to-recycle materials, or a lack of end-of-life planning. A higher score, by contrast, suggests that sustainability has been considered across the system. One of the project’s stated goals is to make environmental trade-offs visible early enough in the development process to shape sustainable robot design choices. </p>
<p>The project also includes educational content and community features so researchers and developers can compare approaches, share case studies, and turn broad sustainability goals into improved design decisions. For companies, Eco-Label could well turn out to be a way to achieve competitive advantage, while it could also help buyers make more informed decisions. </p>
<p>Robotics Eco-Label is just one of the IEEE RAS Sustainability Grant-funded projects showcased at <a href="https://2026.ieee-icra.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ICRA</a> in June. The grants are a key component of IEEE RAS’ broader effort to make <a href="https://www.ieee-ras.org/about-ras/governance/standing-committees/sustainability-and-climate-change/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sustainability</a> a more visible part of robotics research, education, design, and deployment. </p>
<h4>Are you buying more robot than you need?</h4>
<p>Sometimes, sustainable robotics starts with better purchasing decisions. This includes avoiding overspecification; that is, buying robots that are larger or more capable than necessary.  </p>
<p>Matching robots to their intended workload can reduce unused capacity, avoid unnecessary material use, and cut wasted energy over a robot’s life cycle. </p>
<p>That principle underpins the work of an IEEE RAS-funded team, led by <a href="https://ieeexplore.ieee.org/author/3708836608" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Antun Skuric</a>, that has developed an <a href="https://huggingface.co/spaces/sustainable-robotics/robot_chooser" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">open-source platform</a> for assessing the sustainability of collaborative robots.</p>
<p>To use it, you define a required workspace, payload, and trajectory, and the platform identifies the minimum-mass robot that satisfies your application requirements. </p>
<p>The application features interactive tools that enable users to visualize and jog the robot, inspect task-related variables and requirements, view the reachable space, and observe important robot configurations. This enables robot performance to be calculated based on specific task conditions and requirements.</p>
<h4>Can robots really help communities overcome energy poverty?</h4>
<p>Energy poverty and inefficient solar energy utilization are major challenges in Nigeria, where more than 90 million people lack reliable electricity access. </p>
<p>The SolarPeer 360 project, led by <a href="https://www.linkedin.com/in/umar-abdulganiy/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Umar Adetola Abdulganiyy</a>, a student at the Federal University of Technology, Minna, Nigeria, takes on this challenge through a combination of robotic solar tracking, AI-assisted optimization, and peer-to-peer energy distribution. </p>
<p>A timely reminder that robots can help support sustainability goals directly, SolarPeer addresses two connected problems, inefficient small solar installations and the lack of transparent, affordable mechanisms for sharing surplus renewable energy among households and small businesses. </p>
<p>According to the team, SolarPeer 360 is built on a sustainability logic in which “energy captured more efficiently can be shared more fairly, and energy shared more transparently can create local economic value while reducing waste and fossil-fuel dependence.”  </p>
<p>SolarPeer links smart solar capture through tracking, controlled and metered distribution through embedded electronics, and behavior optimization through data, interfaces, and AI guidance. </p>
<p>Early results indicate meaningful gains: The team reported a 60.3 percent gain in average power in one tracked-versus-fixed solar comparison, with measured average power rising from 3.83 W to 6.14 W. Meanwhile, AI-guided energy advisory and optimization contributed to a ~25 percent reduction in energy wastage in the testing environment. </p>
<p>Beyond the lab, the team deployed five community mini-systems and ran a solar training and empowerment workshop that reached more than 500 students.</p>
<h4>Can Caretta work faster?</h4>
<p>Sustainability in robotics is not just a technical challenge. It’s also a cultural and educational challenge for the next generation of engineers, researchers, teachers, and users. </p>
<p>That’s part of the reasoning behind the ‘Caretta’ project, led by <a href="https://ieeexplore.ieee.org/author/696071446314805" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Mustafa Kemal Ambar</a>, which brought robotics and sustainability education to students aged 8 to 16 on the island of Cyprus. </p>
<p>Inspired by the Caretta sea turtle, <a href="https://drive.google.com/file/d/1sv7zNQTq8kiE0temN_v2YWOo0kA-Ii8F/view" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">the project produced a functional robot prototype</a> designed to reduce coastal pollution. Two successful coastal clean-up events were held and more than 30 students were engaged in the project through seminars and hands-on learning.</p>
<p>Treating the beach as both a test site and a classroom, students saw how engineering connects to local environmental problems and community needs. </p>
<p>During a field exercise, one student pointed to plastic debris near the water and observed: “Maybe turtles won’t eat this anymore if Caretta works faster.”</p>
<p>Can the robotics community work faster to build sustainability into its foundations and practices? Early results from IEEE RAS Sustainability Grant projects suggest that work is already underway. </p>
<h4>Want to learn more?</h4>
<p><a href="https://www.ieee-ras.org/ras-university/?ras_page=docs" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RAS University</a> now has a free new class on Sustainable Robotics, you can learn more <a href="https://www.youtube.com/playlist?list=PL9Hnb9qlvGkQeAxrAsRdNaL9JeVukTA-c" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<p>You can also follow activities from the Sustainability and Climate Change Committee, including upcoming grant calls <a href="https://www.ieee-ras.org/about-ras/governance/standing-committees/sustainability-and-climate-change/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>. </p>
<hr>
<p>This article originally appeared on <a href="https://www.ieee-ras.org/category/ras-feature/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE RAS</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>These tiny drones are powered by sound</title>
		<link>https://robohub.org/these-tiny-drones-are-powered-by-sound/</link>
		
		<dc:creator><![CDATA[EPFL]]></dc:creator>
		<pubDate>Mon, 24 Aug 2026 09:53:49 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=221003</guid>

					<description><![CDATA[The MICROBS Lab&#8217;s microfliers. 2026 EPFL/MICROBS &#8211; CC-BY-SA 4.0. By Celia Luterbacher When you blow air across the neck of a bottle, you’re not just producing a pleasant tone: you’re also demonstrating a phenomenon called Helmholtz resonance. This occurs when airflow passing across an opening causes air trapped inside a cavity (like a glass bottle) [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/2216x1244-1024x576.jpg" alt="" width="1024" height="576" class="alignnone size-large wp-image-221004" srcset="https://robohub.org/wp-content/uploads/2026/08/2216x1244-1024x576.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/2216x1244-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/2216x1244-768x432.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/2216x1244-1536x864.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/2216x1244.jpg 1889w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The MICROBS Lab&#8217;s microfliers. 2026 EPFL/MICROBS &#8211; CC-BY-SA 4.0.</em></p>
<p><strong>By Celia Luterbacher</strong></p>
<p>When you blow air across the neck of a bottle, you’re not just producing a pleasant tone: you’re also demonstrating a phenomenon called Helmholtz resonance. This occurs when airflow passing across an opening causes air trapped inside a cavity (like a glass bottle) to oscillate back and forth. At certain frequencies, these oscillations become much stronger, producing the familiar humming sound.</p>
<p>Now, researchers in the MicroBioRobotic Systems (<a href="https://www.epfl.ch/labs/microbs/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MICROBS</a>) Lab in EPFL’s School of Engineering have harnessed the physics behind this phenomenon to build hollow structures that act as miniature, sound-powered machines. The innovation <a href="https://www.science.org/doi/10.1126/sciadv.aef5620" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">has been published</a> in Science Advances.</p>
<p>“Instead of pushing devices around with sound waves, we have created acoustic resonators that are tuned to harness sound at specific frequencies to generate directional thrust and controlled motion,” says lab head Selman Sakar. “Our work shows the feasibility of transforming a simple, cleverly designed mechanical piece into robotic matter.”</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/9304150f-1024x683.jpg" alt="" width="1024" height="683" class="alignnone size-large wp-image-221005" srcset="https://robohub.org/wp-content/uploads/2026/08/9304150f-1024x683.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/9304150f-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/9304150f-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/9304150f-1536x1024.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/9304150f-2048x1365.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The MICROBS Lab&#8217;s sound-powered boat. 2026 EPFL/MICROBS &#8211; CC-BY-SA 4.0.</em></p>
<h4>Miniature boats and microfliers</h4>
<p>While previous approaches have used sound waves to levitate passive objects mid-air, the EPFL team designed devices that convert sound into their own propulsive force. Their innovation lies in the fabrication of hollow round or bell-shaped structures called cavities.</p>
<p>When sound waves excite the air inside these cavities, the oscillating air is forced out as a concentrated jet, while the incoming airflow is more diffuse. This imbalance generates thrust that can propel small vehicles. These sound-powered cavities can be made from a variety of materials, including common 3D-printing plastics, rubber-like polymers, and glass.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/50e00f16-1024x636.jpg" alt="" width="1024" height="636" class="alignnone size-large wp-image-221006" srcset="https://robohub.org/wp-content/uploads/2026/08/50e00f16-1024x636.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/50e00f16-425x264.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/50e00f16-768x477.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/50e00f16-1536x954.jpg 1536w, https://robohub.org/wp-content/uploads/2026/08/50e00f16.jpg 1903w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>The MICROBS Lab&#8217;s microflier. 2026 EPFL/MICROBS &#8211; CC-BY-SA 4.0.</em></p>
<p>At the centimeter scale, the team built miniature boats equipped with up to three cavities, each tuned to a different audible frequency and positioned to push the boat in a particular direction. By changing the frequency of sound waves from a speaker, the researchers could selectively activate different cavities to move the boats, steer them around obstacles, and even program them for autonomous navigation.</p>
<p>Using a 3D nanoprinting technique, the team built &#8216;microfliers&#8217;: ultralight flying vehicles with three microscopic cavities integrated directly into their polymer structures. In contrast to the boats, the microfliers were powered at ultrasonic frequencies inaudible to the human ear. One design weighing just 150 micrograms used its cavities to generate direct upward thrust like a rocket. Another microflier combined the cavities with tiny blades, which spun at speeds of up to 13,000 revolutions per minute, to generate stable, helicopter-like aerodynamic lift.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/baf4aeaf-1024x755.jpg" alt="" width="1024" height="755" class="alignnone size-large wp-image-221007" srcset="https://robohub.org/wp-content/uploads/2026/08/baf4aeaf-1024x755.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/baf4aeaf-425x313.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/baf4aeaf-768x566.jpg 768w, https://robohub.org/wp-content/uploads/2026/08/baf4aeaf.jpg 1081w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>A microflier in flight. 2026 EPFL/MICROBS &#8211; CC-BY-SA 4.0.</em></p>
<h4>Toward sound-responsive robotics</h4>
<p>Because the devices rely on hollow cavities rather than motors, gears, or magnetic components, they can be made extremely small and lightweight using a variety of 3D-printing methods.</p>
<p>“Our concept is compatible with even further miniaturization, enabling advanced designs that push the boundaries of robotics and aeronautics,” says first author and MICROBS Lab PhD student Junsun Hwang.</p>
<p>Sakar adds that in the future, several sound-responsive structures could be built into a single flexible device, with each one reacting to a different sound frequency. “This would allow specific parts of the device to move, bend or vibrate, potentially leading to aerodynamic robotic devices that can change shape in response to sound,” he says.</p>
<h4>Reference</h4>
<p><a href="https://www.science.org/doi/10.1126/sciadv.aef5620" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Acoustic resonators as wireless actuators in air for small-scale robots</a>, <em>Junsun Hwang et al.</em>, Science Advances (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>#AAMAS2026 blue sky award winner: Foundation world models for agents in changing environments</title>
		<link>https://robohub.org/aamas2026-blue-sky-award-winner-foundation-world-models-for-agents-in-changing-environments/</link>
		
		<dc:creator><![CDATA[AIhub]]></dc:creator>
		<pubDate>Fri, 21 Aug 2026 08:23:06 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20949</guid>

					<description><![CDATA[Florent Delgrange won the Best Blue Sky Paper Award at AAMAS 2026 for his work Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments. We caught up with him to find out more about his vision for agent learning. What is the topic of your Blue Sky Ideas paper and […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13.png" alt="" width="1810" height="678" class="alignnone size-full wp-image-20951" srcset="https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13.png 1810w, https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13-300x112.png 300w, https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13-1024x384.png 1024w, https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13-768x288.png 768w, https://aihub.org/wp-content/uploads/2026/08/Screenshot-2026-08-03-at-08.57.13-1536x575.png 1536w" sizes="(max-width: 1810px) 100vw, 1810px" /></p>
<p>Florent Delgrange won the Best Blue Sky Paper Award at AAMAS 2026 for his work <em><a href="https://arxiv.org/abs/2602.23997" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments</a></em>. We caught up with him to find out more about his vision for agent learning. </p>
<h4>What is the topic of your Blue Sky Ideas paper and why is it an interesting area for study?</h4>
<p>My Blue Sky Ideas paper asks a simple but difficult question: how can an autonomous agent keep learning as its world changes without quietly losing the guarantees that made its behavior trustworthy?</p>
<p>Reinforcement learning and formal methods address complementary parts of this problem. Reinforcement learning allows an agent to learn by trial and error and can scale to environments for which we could never write down every rule. However, the agent is usually asked to maximize a reward. A poorly specified reward can be exploited, and a high reward does not by itself tell us that a safety or coordination requirement has been satisfied. Reactive synthesis starts from the other end: given a model of the environment and a logical description of the intended behavior, it can construct a policy that is correct by design. The difficulty is that it normally needs an explicit, fixed model, which is precisely what an agent lacks in an open and changing world.</p>
<p>The paper proposes a research agenda that brings these traditions into one loop. A <em>foundation world model</em> would be learned from experience, but structured so that a verifier can reason about it. As the agent learns a policy, it would update its model, measure the reliability of its abstraction, and check whether the policy still satisfies its specification. The verifier&#8217;s feedback could reject an unsafe update, request data from an uncertain region, or trigger a revision of the model.</p>
<p>This matters because real environments do not politely remain as they were during training. Goals evolve, conditions change, and, in a multi-agent system, every adapting agent changes the environment perceived by the others. Reliability therefore cannot be a certificate obtained once at deployment. It has to be maintained as the agent continues to learn.</p>
<h4>What is your vision for foundation world models?</h4>
<p>To me, <em>foundation</em> refers first to reuse, not simply to size. I do not envision a larger video predictor trained on more trajectories. I envision a persistent and structured model that an agent can carry across tasks, policies, and changing populations of agents.</p>
<p>One way to think about it is as a map that records more than roads. It should also tell the agent which areas have been surveyed, which conclusions depend on those areas, and when a change in the world has made an old route unreliable. A useful foundation world model should do the same for decision-making: predict what may happen, expose the structure needed for reasoning, and quantify when those predictions are trustworthy enough to support a guarantee.</p>
<p>I’d want such a model to have three key properties. First, it should be <em>calibrated:</em> every learned abstraction should come with a measure of its error or coverage, so that the agent knows where formal conclusions remain valid. Second, it should be <em>compositional:</em> verified local dynamics, behaviors, and certificates should be reusable when a new task is assembled. Third, it should be <em>semantically queryable:</em> a formal requirement or high-level instruction should help the agent derive a suitable reward model, task-specific abstraction, or policy prior with little additional experience.</p>
<p>The durable idea is that the world model becomes a common substrate for learning, planning, and verification. It should help an agent act, but also identify the limits of its competence, gather evidence where those limits matter, and explain why a particular behavior can or cannot currently be certified.</p>
<h4>How does this vision differ from current models?</h4>
<p>Most current model-based approaches focus on learning for a particular task, environment, policy, or training distribution. Their main model learning objective is predictive accuracy: reconstruct an observation, forecast the next (latent) state, or generate imagined trajectories for planning. Those are important capabilities, but average predictive metric is not the same as fitness for a particular guarantee.</p>
<p>Consider a model for a scenario involving an agent interacting in a warehouse, where the world model predicts almost every transition correctly but misses a rare, dangerous interaction with a forklift. Its average error may be excellent while that transition is exactly the one that determines whether a collision-avoidance claim is valid. The reverse is also possible: a compact model may ignore colors and textures yet preserve everything needed to reason about routes and collisions. For verification, the relevant question is therefore not only “How accurate is the model?” but “Which conclusions does this accuracy justify, for this policy and this requirement?”</p>
<p>Foundation world models would make that connection an explicit design objective. Their abstractions would carry reliability information tied to the behavior being analyzed, and this information would be revised online as the data distribution changes. Previously verified components could be reused and composed, while specifications expressed in logic or language could guide which representation and policy the agent needs for a new task.</p>
<p>The main difference is therefore a change in role. Current models are primarily prediction tools. The model I envisage is a persistent, analyzable basis for learning, adaptation, and formal reasoning, with language models providing a complementary semantic interface. They could translate high-level instructions into candidate specifications or propose structured model updates, while the world model grounds these proposals in experience and the verifier checks their validity. Foundation world models may benefit from scale through broader task and environment coverage, but scale alone does not provide the structure or certificates required for reliability.</p>
<h4>Could you give an example of how such a model might work?</h4>
<p>Consider a delivery robot in a busy warehouse. Its task could be stated as: “eventually deliver the package while always avoiding collisions.” Instead of manually combining many bonuses and penalties, the system would translate that requirement into a reward model. Learning and verification would then start from the same description of the intended behavior.</p>
<p>As the robot receives observations, it would learn a compact representation of the warehouse and a policy that acts on that representation. A verifier would ask two related questions. Does the policy satisfy the delivery and collision-avoidance requirement in the learned world model? And is the learned abstraction accurate enough, along the routes that matter, for that conclusion to be trusted? A certificate is meaningful only when both answers are supported.</p>
<p>Now suppose a new forklift begins using a shortcut that was rarely visited during training, cluttering the way. Rather than treating an old prediction as a guarantee, the model should lower its confidence in that region. The verifier would detect this, withdraw the affected certificate, reject a risky policy update, direct exploration toward the shortcut, and reinstate a guarantee only after the world model has been recalibrated.</p>
<p>The paper also considers a more ambitious test-time loop. A language model could propose one or more small formal program describing the new dynamics. A model checker would test them, learn to compose with them, and return a counterexample or structural inconsistency when they are wrong. The language model could revise its hypothesis, the robot could collect targeted experience, and the cycle would repeat. In this division of labor, the language model proposes and the formal verifier checks. </p>
<p>We already have pieces of the loop, including formal reward translations, verifiable abstractions, safe policy-improvement methods, and program generation. Building an efficient end-to-end agent that keeps all of these pieces calibrated while it learns remains the research challenge.</p>
<h4>What do you think the impact of such a framework on multi-agent systems could be?</h4>
<p>Multi-agent systems make the problem both more urgent and more difficult. Each learning agent is a moving part of every other agent&#8217;s environment. Even when the physical world is unchanged, the effective dynamics evolve as agents update their policies, join or leave the system, share information, or pursue new objectives.</p>
<p>A foundation world model could retain reusable descriptions of these interaction patterns, while formal specifications state what must hold for the group. A fleet of warehouse robots, for example, may need to avoid collisions and complete deliveries while respecting shared capacity constraints. The model could connect each local policy to the assumptions on which its certificate depends. If one robot changes its route, the system could identify which assumptions and guarantees are affected, collect new data where needed, and revise only the relevant components rather than relearning and re-verifying the entire fleet.</p>
<p>Composition is the main source of potential leverage. Verified local dynamics or coordination behaviors could serve as building blocks for new teams and tasks, and previous agents could provide useful priors for new participants. This could support faster adaptation while making failures easier to diagnose: the system should report which interaction invalidated a certificate and provide a counterexample, rather than only revealing that the joint reward has fallen.</p>
<p>The central obstacle for multi-agent systems is scalability. The joint state space grows very quickly with the number of agents, and local guarantees do not automatically compose into a global one. We will need principled ways to expose dependencies, preserve soundness under composition, and run verification quickly enough to influence learning online. If we can solve those problems, the field could move from learning coordination strategies and checking them afterwards to learning new strategies while continuously tracking which global properties remain guaranteed.</p>
<h4>About Florent</h4>
<table border="0" width="100%" cellspacing="0" cellpadding="10">
<tbody>
<tr>
<td align="left" valign="top" width="150">
<img decoding="async" src="https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center.jpg" alt="" width="270" height="270" class="alignnone size-full wp-image-20953" srcset="https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center.jpg 270w, https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center-150x150.jpg 150w, https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center-24x24.jpg 24w, https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center-48x48.jpg 48w, https://aihub.org/wp-content/uploads/2026/08/avatar_hu4594711ef1297a26ac282190ec80585c_211443_270x270_fill_q75_lanczos_center-96x96.jpg 96w" sizes="(max-width: 270px) 100vw, 270px" />
</td>
<td align="left" valign="top">
<p>Florent Delgrange is a postdoctoral researcher in computer science at the Artificial Intelligence Lab of Vrije Universiteit Brussel (VUB). His research lies at the intersection of reinforcement learning, world models, and formal verification. He develops methods for agents that can learn and adapt while justifying and certifying the behavior they adopt. He completed a joint PhD at VUB and the University of Antwerp in 2024 on the formal verification of deep reinforcement learning policies. His paper <em><a href="https://arxiv.org/abs/2602.23997" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments</a></em> received the Best Blue Sky Paper Award at AAMAS 2026.</p>
</td>
</tr>
</tbody>
</table>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotics roadmaps from around the world spotlight of the month: Japan</title>
		<link>https://robohub.org/robotics-roadmaps-from-around-the-world-spotlight-of-the-month-japan/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 19 Aug 2026 07:39:34 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220912</guid>

					<description><![CDATA[Robots have been a prolific theme in Japanese pop culture and media since the 1950s, which includes global icons like the Transformers, Astro Boy, and Doraemon (1). Perhaps not coincidentally, Japanese citizens have a positive outlook on robotic technologies and their use in the labor sector compared to many other nations (2); much to their [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/ROADMAP-STEPS-1024x882.png" alt="" width="1024" height="882" class="alignnone size-large wp-image-220919" srcset="https://robohub.org/wp-content/uploads/2026/08/ROADMAP-STEPS-1024x882.png 1024w, https://robohub.org/wp-content/uploads/2026/08/ROADMAP-STEPS-425x366.png 425w, https://robohub.org/wp-content/uploads/2026/08/ROADMAP-STEPS-768x662.png 768w, https://robohub.org/wp-content/uploads/2026/08/ROADMAP-STEPS.png 1286w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>Robots have been a prolific theme in Japanese pop culture and media since the 1950s, which includes global icons like the <em>Transformers, Astro Boy</em>, and <em>Doraemon</em> (<a href="https://books.google.de/books?hl=en&#038;lr=&#038;id=qiZhey9aKZgC&#038;oi=fnd&#038;pg=PA7&#038;dq=loving+the+machine+the+art+and+science+of+japanese+robots&#038;ots=XSraPsmPC5&#038;sig=f8s1TeQ6RiGMEtbQcKXRCACbWts&#038;redir_esc=y#v=onepage&#038;q=loving%20the%20machine%20the%20art%20and%20science%20of%20japanese%20robots&#038;f=false" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">1</a>). Perhaps not coincidentally, Japanese citizens have a positive outlook on robotic technologies and their use in the labor sector compared to many other nations (<a href="https://www.mri.co.jp/en/knowledge/article/202502_3.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">2</a>); much to their advantage, as robotics continues to be a vital pillar for ensuring Japan’s economic resilience and future growth. Here, we discuss priorities and long-term agendas as presented in Japan’s national robotics strategies.</p>
<h4>Natural disasters, aging, and economic competition</h4>
<p>The combination of its geographic location, geologically active landmass, and topography renders Japan prone to frequent natural disasters. Although weather control is among Japan’s lofty research goals for the next 25 years (<a href="https://www8.cao.go.jp/cstp/english/moonshot/sub8_en.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">3</a>), geological disturbances remain inevitable. As such, disaster mitigation and response are high priorities that serve as motivation for robotics development in Japan (<a href="https://www8.cao.go.jp/cstp/tougosenryaku/togo2025_honbun_eiyaku.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">4</a>). Intelligent machines are expected to expedite disaster response and search-and-rescue, while minimizing exposure of workers and volunteers to unnecessary hazards – a notable reminder being the 2011 Fukushima Disaster (<a href="https://www.britannica.com/event/Fukushima-accident" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">5</a>).</p>
<p>Aging workforce is a second pressing issue. Japan is currently the oldest demographic nation, defined as of 2007 as a “super-aged” society with nearly a third of citizens aged 65 or older (<a href="https://www8.cao.go.jp/kourei/english/annualreport/2024/pdf/2024.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">6</a>). According to government roadmaps (<a href="https://www8.cao.go.jp/cstp/tougosenryaku/togo2025_honbun_eiyaku.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">4</a>), Japan views robotic development as a crucial tool for preventing a GDP collapse due to the rapid labor shortage, specifically in services like healthcare, elderly assistance, and manual labor. Unlike countries which opt for immigration reform for addressing fluctuation in labor markets, Japan maintains historically tight immigration regulations. A strong preference towards preserving traditional values may influence their massive investments towards shifting to a robotic workforce (<a href="https://japannews.yomiuri.co.jp/politics/politics-government/20251223-300198/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">7</a>).</p>
<p>Japan has a mature robotics industry, claiming the title of the largest manufacturer and exporter of industrial robots for the last half century (<a href="https://www.nasdaq.com/articles/japans-robot-dominance" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">8</a>). 45% of the global supply originated from Japan in 2022, with nearly an 80% export rate to countries such as EU members, the USA, and China (<a href="https://ifr.org/news/japan-is-worlds-number-one-robot-maker/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">9</a>). However, the combination of economic decline and competition from oversea manufacturing present the challenge of maintaining leadership in the global value chain. Leveraging their specialty in robotics hardware design is crucial to maintain a competitive edge in the global economy.</p>
<h4>Society 5.0</h4>
<p>Japan is betting on bold technological solutions for ensuring the prosperity of their future society. To do so, the government proposes a streamlined effort towards technocentric “super-smart cities” (coined <em>Society 5.0</em>) (<a href="https://www8.cao.go.jp/cstp/kihonkeikaku/5basicplan_en.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">10</a>). The directive is set by the <em>Science and Technology Basic Plan</em>, a large-scale roadmap updated every five years (with 2026 marking the transition into the 7th Plan). An additional <em>Integrated Innovation Strategy</em> is used as an annually-updated agile document for integrating urgent priorities into the larger Basic Plan.</p>
<h4>Super cities</h4>
<p>Japan is investing heavily into research on human-robot interactions, so that users are embedded early on into technological design considerations of <em>Society 5.0</em>. Accordingly, in 2020 the Japanese Parliament passed the <em>Super City Amendment</em>, which allows regulatory sandboxes for specific “super cities” (currently Osaka and Tsukuba) to bypass certain laws that otherwise impede the integration of technologies like AI-driven robots into the public space (<a href="https://www.japaneselawtranslation.go.jp/outline/87/905R507.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">11</a>, <a href="https://www.chisou.go.jp/tiiki/kokusentoc/supercity/openlabo/pdf/scewc2025_en.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">12</a>). These large-scale tests are carried out preceding what they hope could become widespread implementation of robotics to mitigate issues such as labor shortage. Following suit, as of late September 2025, the automobile industry Toyota has launched their own version of a Super City, <em>Woven City</em>, which provides a campus for employees to work, live, and even raise a family (<a href="https://global.toyota/en/newsroom/corporate/43347785.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">13</a>).</p>
<h4>Moonshot programs</h4>
<p>Japan also utilizes high-risk, high-impact research roadmaps with 30-year timelines, called <em>Moonshot Programs</em>, to encourage bold technological solutions for the future (<a href="https://www.jst.go.jp/moonshot/en/index.html#program-list" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">14</a>). The authors of these programs are a blend of members from government, industry, and academia. Two of the current ten Moonshot Goals are directly related to robotics.</p>
<p>Goal 1 of the Moonshot Program is to <em>Overcome Limitations of Body, Brain, Space, and Time</em>, a goal largely focused on the creation of <em>Cybernetic Avatars</em> – the fusing of sensations and motions between human users and tele-operated robots. By 2050, they hope to create the technology and infrastructure to implement Cybernetic Avatars into everyday society. Goal 3 of the Moonshot Program is the <em>Co-Evolution of Robots and AI</em>. Sub-goals within Goal 3 include the creation of robots that 1) 90% of citizens will feel comfortable engaging with by 2030, 2) work in remote and dangerous locations by 2050, and 3) autonomously innovate by 2050.</p>
<h4>Humanoids and physical AI</h4>
<p>In December 2025, a strategic update has been made to Goal 3 of the Moonshot Program, which prioritizes the development of general-purpose autonomous humanoid robots which can adapt to human-centric environments (<a href="https://www.jst.go.jp/moonshot/en/application/202510/files/besshi3_goal3_en.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">15</a>). Japan had in fact led humanoid research decades back (<a href="https://www.waseda.jp/top/en/news/88080" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">16</a>), already developing Honda’s famous <em>Asimo</em> in 2000 (<a href="https://global.honda/en/ASIMO/history/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">17</a>) – but despite these early successes, humanoids remained astronomically expensive to manufacture, impractical for real-world applications, and remained publicity tools for promoting other industrial products. These commercialization challenges have largely been overcome with advancements in low-cost and back-drivable actuation components, additive manufacturing, and generalizable AI. As countries like China and the USA have sparked a humanoids build-up race, Japan is playing catch-up to re-assert themselves in this arena, which is rapidly taking center stage in the tech world (<a href="https://www.morganstanley.com/insights/articles/humanoid-robot-market-5-trillion-by-2050" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">18</a>).</p>
<p>To keep up in this humanoids race, it is crucial for Japan to invest heavily in domestic AI. In line with this need, in the same month as the Moonshot Program update, the Japanese Ministry of Economy, Trade and Industry (METI) decided to quadruple its previous investments in AI to $8 billion USD (now the third highest expenditure for AI just after China and the USA), with approximately $2.5 billion USD of this fund allocated specifically for physical AI (robots) (<a href="https://www.japantimes.co.jp/business/2025/12/26/economy/ai-budget-support/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">19</a>).</p>
<p>In March 2026, Japan has also included updates to their Integrated Innovation Strategy (<a href="https://japannews.yomiuri.co.jp/politics/politics-government/20260326-318683/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">20</a>), with plans to install R&#038;D hubs across its 16 sectors for training domestic AI-robots and recruit both local and international talent. Overall, it would seem that Japan is leveraging its expertise in precision hardware to perform large-scale physical training for high-precision AI-driven robots.</p>
<h4>Strategic relations with the USA</h4>
<p>For the better part of the last century, Japan and the USA have been allies and trading partners. Japan’s recent Moonshot Program, along with their National Defense Strategy from 2022, both state the importance of their continued partnership (<a href="https://www.cas.go.jp/jp/siryou/221216anzenhoshou/nss-e.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">21</a>). Notably, the USA is a global leader in AI but lacks a government-backed robotic hardware strategy, which could ensure a symbiotic relationship with Japan’s mature hardware ecosystem (<a href="https://global.fujitsu/en-global/pr/news/2025/10/03-01" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">22</a>).</p>
<p>Supply chain pressures have also incentivized Japan and the USA’s joint collaboration to conduct deep-sea rare-earth mining using advanced robotic systems off the coast of Japan, in line with Goal 3 of the Moonshot Program. The first successful mining test, which involved underwater autonomous vehicles, was conducted in February 2026 (<a href="https://japannews.yomiuri.co.jp/politics/politics-government/20260202-308491/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">23</a>). The use of robotics for underwater monitoring will also surely become critical for monitoring the impact of deep-sea mining to the marine environment, a highly contested topic (<a href="" data-wpel-link="internal">24</a>).</p>
<p>In a historical move amidst mounting geopolitical tensions, Japan has also recently introduced dual-use technologies as a priority for their revised 7th Basic Plan (<a href="https://www8.cao.go.jp/cstp/siryo/haihui084/haihu-084.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">25</a>), which demands the ramp-up of domestic R&#038;D and research on unmanned vehicles and drone technologies (a move strongly endorsed by the USA). This decision comes with the high expenditure commitment of 2% of the national GDP.</p>
<p>Japan has ambitious societal plans for the coming decades, and robotics will play an increasing vital role – from sustaining domestic services, to enabling the physical autonomy of citizens, and revitalizing the economy. Ultimately, Japan’s roadmaps reveal a future where robots are partners for shaping a resilient and human-centric society.</p>
<p>On that note – our next month’s article will feature robotics strategies from the USA. Thanks for reading, and stay tuned.</p>
<hr>
<p><em>This is a continuation of a monthly series on international robotics roadmaps. We welcome questions, comments, and feedback for future editions at ras@ieee.org.</em></p>
<p><strong>Ellen H. Rumley</strong> – <em>Policy Analyst</em></p>
<p><strong>Allison Okamura</strong> – <em>Vice President</em></p>
<p><em>IEEE RAS Science &#038; Technology Watch Board</em></p>
<hr>
<h4>References</h4>
<p>[1] Hornyak, T. N. (2006). Loving the Machine: The Art and Science of Japanese Robots. Tokyo: Kodansha International.</p>
<p>[2] Mitsubishi Research Institute. (2022). How different countries perceive robots: An original survey.</p>
<p>[3] Cabinet Office, Government of Japan. (2021). Moonshot Goal 8: Realization of a society safe from the threat of extreme winds and rains by controlling and modifying the weather by 2050. Bureau of Science, Technology and Innovation.</p>
<p>[4] Cabinet Office, Government of Japan. (2025). Integrated innovation strategy 2025. [5] Encyclopaedia Britannica. (2026, March 9). Fukushima accident.</p>
<p>[6] Cabinet Office, Government of Japan. (2024). Annual report on the state of the formation of a resilient society for an aging population: White paper on the aging society 2024.</p>
<p>[7] Speed, J. Japan aims to take in 1.23M foreign workers under labor migration programs. The Japan Times.</p>
<p>[8] Nasdaq. (2021, October 25). Japan’s robot dominance.</p>
<p>[9] International Federation of Robotics. (2022, March 10). Japan is world’s number one robot maker.</p>
<p>[10] Cabinet Office, Government of Japan. (2016). The 5th Science and Technology Basic Plan (2016–2020).</p>
<p>[11] Cabinet Office, Government of Japan. (2020). Act partially amending the Act on National Strategic Special Zones and the Act on Special Districts for Structural Reform (Act No. 34 of 2020).</p>
<p>[12] Cabinet Office, Government of Japan. (2022). Designation of the Super City type National Strategic Special Zones: Osaka Prefecture/Osaka City and Tsukuba City. Bureau of Regional Revitalization.</p>
<p>[13] Toyota Motor Corporation. (2025, September 25). Toyota Woven City officially launches as a test course for the future of mobility [Press release].</p>
<p>[14] Japan Science and Technology Agency. (n.d.). Moonshot R&#038;D | TOP.</p>
<p>[15] Kuniyoshi, Y. (2025, October 28). Appendix 3: PD’s policy (Moonshot Goal 3). Japan Science and Technology Agency (JST).</p>
<p>[16] Waseda University. (2026, May 8). The robots of Waseda: A 50-year journey in humanoid innovation. Waseda University News.</p>
<p>[17] Honda Motor Co., Ltd. (n.d.). History of robotics development. Honda Global Corporate Website.</p>
<p>[18] Morgan Stanley Research. (2025, May). Humanoids: A $5 trillion market. Morgan Stanley Investment Management.</p>
<p>[19] Nohara, Yoshiaki, and Komaki Ito. “Japan to quadruple spending support for chips and AI in budget.” The Japan Times, 26 Dec. 2025.</p>
<p>[20] The Japan News. (2024, May 20). Japanese govt to set up global hubs for AI robotics research.</p>
<p>[21] Cabinet Secretariat. (2022, December 16). National security strategy of Japan [Provisional translation].</p>
<p>[22] Fujitsu. (2025, October 3). Fujitsu expands strategic collaboration with NVIDIA to deliver full-stack AI infrastructure [Press release].</p>
<p>[23] The Japan News. (2024, August 24). Japan deep-sea drilling ship Chikyu extracts rare earth mud; represents major breakthrough for domestic supply. The Japan News. [24] Lelyveld, M. (2024, September 10). Japan’s deep-sea gamble: A new rare earth frontier in the Pacific. The Diplomat.</p>
<p>[25] Cabinet Office, Government of Japan. (2026, March 27). The 7th science, technology, and innovation basic plan (FY2026–FY2030) [Cabinet Decision].</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Intermittent swimming promotes the energy efficiency of fish-like robot movements</title>
		<link>https://robohub.org/intermittent-swimming-promotes-the-energy-efficiency-of-fish-like-robot-movements/</link>
		
		<dc:creator><![CDATA[Xiangxiao Liu]]></dc:creator>
		<pubDate>Mon, 17 Aug 2026 13:00:27 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220804</guid>

					<description><![CDATA[Image credits: Xiangxiao Liu, Francois A. Longchamp, and Louis GeverBiorobotics Laboratory, EPFL Improving energy performance can effectively extend the time a robot can operate and reduce battery load, enabling lighter, more flexible, and more durable robotic systems. Nature has evolved optimal energy-saving locomotion strategies through billions of years of natural selection, providing unparalleled blueprints for [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone wp-image-220811" src="https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-425x239.png" alt="" width="921" height="518" srcset="https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-425x239.png 425w, https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-1024x576.png 1024w, https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-768x432.png 768w, https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-1536x864.png 1536w, https://robohub.org/wp-content/uploads/2026/07/Photo-4-Intermittent-swimming-article-Credit-Xiangxiao-Liu-Francois-A.-Longchamp-and-Louis-GeverBiorobotics-Laboratory-EPFL-1-2048x1152.png 2048w" sizes="(max-width: 921px) 100vw, 921px" /><br />
Image credits: Xiangxiao Liu, Francois A. Longchamp, and Louis GeverBiorobotics Laboratory, EPFL</p>
<p>Improving energy performance can effectively extend the time a robot can operate and reduce battery load, enabling lighter, more flexible, and more durable robotic systems. Nature has evolved optimal energy-saving locomotion strategies through billions of years of natural selection, providing unparalleled blueprints for robotic optimization. Among diverse modes of aquatic locomotion, intermittent swimming, also called bout-and-glide swimming, is a widespread adaptive behavior in aquatic organisms of a wide range of sizes, including larval zebrafish, red-nose tetra, koi carp, and even whales.</p>
<p>This natural bout-and-glide gait features alternating motion phases: short periods of active body and tail undulation for propulsion, followed by passive gliding with a streamlined, straight body posture. It is widely recognized that this intermittent swimming gait is closely associated with optimizing biological energy, making it of great research value to transplant and explore such natural motion mechanisms into robotic control systems.</p>
<p>In this study, an international joint team comprising researchers from EPFL (Switzerland), Duke University (USA), and Instituto Superior Tecnico (Portugal) developed a <a href="https://doi.org/10.1126/scirobotics.adw7868" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">larval zebrafish-inspired robotic platform (ZBot)</a> to systematically investigate the intrinsic characteristics and performance advantages of bout-and-glide intermittent swimming compared to continuous swimming.</p>
<p>This research focused on four scientific questions:</p>
<p>1. <strong>Which neural control mechanism underlies intermittent swimming locomotion?</strong><br />
To validate the bioinspired energy-saving mechanism of fish intermittent swimming, the team developed a biomimetic robot, ZBot (Figure 1), scaled up 200 times from a larval zebrafish, with a body length of 80 cm and a weight of 2.8 kg. The ZBot replicates the larval zebrafish’s morphological features, segmented body structure, and center-of-mass distribution. Its flexible tail consists of six servomotor-driven segments to simulate natural fish undulation, while the head integrates core devices, including a central controller that serves as its nervous system, high-precision cameras, and real-time power meters. Equipped with expandable sensor interfaces, ZBot supports diverse experimental needs, including visual-motor processing [2] and vestibular system research.</p>
<p><img decoding="async" class="alignnone wp-image-220807" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.28.32-425x208.png" alt="" width="924" height="452" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.28.32-425x208.png 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.28.32-768x376.png 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.28.32.png 878w" sizes="(max-width: 924px) 100vw, 924px" /><br />
<strong>Figure 1.</strong> ZBot and real larval zebrafish.</p>
<p>2. <strong>Can intermittent bout-and-glide swimming achieve higher energy efficiency than continuous tail-beating swimming, and if so, under which conditions?</strong></p>
<p>The team from EPFL and Duke University collaborated to build a neurocomputational model simulating zebrafish neural circuits, centered on Central Pattern Generators (CPGs), bout-gate modules, and ventral spinal projection neurons (vSPNs). The CPGs generate continuous rhythmic oscillation signals to generate basic swimming undulations, with the bout gate acting as a core switching unit: it accumulates input signals via a leaky integrator and triggers CPG-driven tail undulation only when reaching a fixed threshold, forming the natural intermittent “active bout + passive glide” swimming rhythm. The simulated vSPNs further adjust tail deflection angle, enabling flexible maneuver swimming direction..</p>
<p>By adjusting parameters such as tail oscillation frequency, amplitude, and bout gate threshold, ZBot can accurately replicate multiple swimming gaits of larval zebrafish, including slow straight swims, routine turns, and J-turns (Figure 2). The EPFL-Duke team extended the model to construct an end-to-end framework for the larval zebrafish’s visually guided optomotor response, transforming the retinal input into motor output. This framework successfully reproduced the optomotor response in both ZBot and a <a href="https://doi.org/10.1126/scirobotics.adv4408" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">digital twin simulation, simZFish</a>.</p>
<p><img decoding="async" class="alignnone wp-image-220808" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.29.01-425x245.png" alt="" width="923" height="532" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.29.01-425x245.png 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.29.01-1024x590.png 1024w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.29.01-768x442.png 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.29.01.png 1104w" sizes="(max-width: 923px) 100vw, 923px" /><br />
<strong>Figure 2. </strong>Top view of ZBot bout-and-glide swimming in water (1 cP, 64000 ≤ Re ≤160000), moderately viscous liquid (213.9 cP, 37.4 ≤ Re ≤ 448.8, intermediate flow regime), and highly viscous liquids (457.0 cP, 1.0 ≤ Re ≤ 87.5, close to viscous flow regime). Recorded at 5 frames per second.</p>
<p>3. <strong>Are the energy-saving advantages of intermittent swimming constant in viscous fluid regimes, e.g., with low Reynolds number, as seen for tiny larval zebrafish and microbionic swimming robots?</strong></p>
<p>Reynolds number is a dimensionless quantity that quantifies the relative magnitude of inertial forces and viscous forces acting on a fluid flow or a solid object moving through fluid. A lower Reynold number (&lt;1000) indicates the fluid dynamics in viscous regime, where the moving object experiences the viscous force to a high degree. A higher Reynolds number (&gt;1000) indicates the fluid dynamics in inertial-dominated regime, where inertial forces overwhelm viscous forces.</p>
<p>Large creatures, such as whales, swim in turbulent flow regimes with a high Reynolds (Re) number. Small creatures, such as tiny larval zebrafish, swim in an intermediate flow regime that is more strongly influenced by viscous drag. Thus, it is interesting to examine the effects of different flow regimes on dynamic behavior during intermittent swimming gaits. Leveraging the inverse relationship between Reynolds number (Re) and fluid viscosity, the team changed the fluid environments to mimic aquatic organisms of varying sizes by adjusting liquid viscosity (Figure 2 and Video 1). The moderately viscous fluid has a viscosity of 213.9 cP, comparable to fruit topping syrup; the highly viscous liquid has a viscosity of 457.0 cP, comparable to the standard makeup cleansing oil. Increased viscosity significantly shortens ZBot’s traveling distance, with the displacement in highly viscous fluid (473.0 cP, 1.0 &lt; Re &lt; 87.5) only 1/30 of that in normal water (1 CP, 64000 &lt; Re &lt; 16000. Intriguingly, viscosity has minimal impact on turning performance: ZBot’s turning angle per bout is approximately 60 degrees in normal water and remains at 45 degrees in highly viscous fluid.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220804-1" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/07/Video-2.-ZBot-was-tested-in-fluids-of-different-viscosities-by-mixing-water-with-carboxymethyl-cellulose-sodium-salt-1-1.mp4?_=1" /><a href="https://robohub.org/wp-content/uploads/2026/07/Video-2.-ZBot-was-tested-in-fluids-of-different-viscosities-by-mixing-water-with-carboxymethyl-cellulose-sodium-salt-1-1.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/07/Video-2.-ZBot-was-tested-in-fluids-of-different-viscosities-by-mixing-water-with-carboxymethyl-cellulose-sodium-salt-1-1.mp4</a></video></div></p>
<p><strong>Video 1. </strong>ZBot was tested in fluids of different viscosities (by mixing water with carboxymethyl cellulose sodium salt)</p>
<p>4. <strong>What mechanisms lead to the energy efficiency of intermittent swimming?</strong></p>
<p>A well-known hypothesis on the benefits of intermittent swimming is that it improves energy efficiency during swimming. Through experiments, the team confirmed that intermittent swimming reduces energy consumption across all achievable velocities compared to continuous tail-beating swimming, in both high- and low-Reynolds-number regimes. However, due to the limited bout and glide cycle, the maximum velocity when using intermittent swimming is only about 60% of that when using continuous tail-beating swimming.</p>
<p>A popular reason for this energy saving is that intermittent swimming enhances the transfer of energy from kinematic tail movements to the body&#8217;s dynamic displacement in the liquid. This &#8220;fluid dynamics&#8221; hypothesis has several variants, but essentially proposes that the straight-tail posture during gliding phases reduces drag force and thus saves energy. In this study, the team proposed and explored another hypothesis, the “actuator efficiency” hypothesis. Bout-and-glide swimming enhances the transfer of energy from electricity (or chemical energy in fishes) to kinematic tail movements. In other words, intermittent swimming allows the robot (or fish) to use their actuators (or muscles) in more energy-efficient regimes than continuous swimming.</p>
<p>Both robotic servomotors and biological fish muscles follow an inverted U-shaped efficiency curve, achieving optimal energy conversion only under moderate load conditions. At lower swimming velocities, where intermittent swimming occurs, continuous tail-beating causes actuators to operate persistently in underloaded, inefficient states, resulting in wasted energy. In contrast, the bout-glide cycle modulates actuator working conditions: the short bout phase keeps motors within the high-efficiency load range, and the glide phase minimizes the inefficient operation. This cyclic regulation promotes the overall actuator energy conversion efficiency.</p>
<p><strong>Importance of this research</strong></p>
<p>This study takes natural animal movement as its core inspiration, successfully translating evolutionary biological advantages into improvements in robotic engineering performance, with value in both the life sciences and robotic engineering. For biological research, the bioinspired robot platform enables mechanistic decoding of neural-motor-energy correlations, shifting biological observation from correlational observations to causal verification and providing a new tool for vertebrate neural circuit research. For the robotics industry, this research verifies and provides a strategy for robotic control to lower energy consumption.</p>
<p>By learning from natural intermittent locomotion strategies, underwater robots can adopt adaptive gait switching, intermittent bout-and-glide mode for improved energy-saving endurance during low- and medium-speed cruising, and continuous driving mode for high-speed emergency maneuvering.</p>
]]></content:encoded>
					
		
		<enclosure url="https://robohub.org/wp-content/uploads/2026/07/Video-2.-ZBot-was-tested-in-fluids-of-different-viscosities-by-mixing-water-with-carboxymethyl-cellulose-sodium-salt-1-1.mp4" length="9696912" type="video/mp4" />

			</item>
		<item>
		<title>What does it take for a robot to hold a conversation with a room, not just a person?</title>
		<link>https://robohub.org/what-does-it-take-for-a-robot-to-hold-a-conversation-with-a-room-not-just-a-person/</link>
		
		<dc:creator><![CDATA[Umar Farooq]]></dc:creator>
		<pubDate>Fri, 14 Aug 2026 09:04:11 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220884</guid>

					<description><![CDATA[By Umar Farooq That was one of the questions at the heart of my last week (20th-24th July) at the Imperial Robotics Summer School, hosted at Imperial College, London; a week that sharpened my thinking and pushed me to look at robotics problems from angles I don&#8217;t usually get to in my day-to-day work. The [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/Umar-3-1024x683.jpeg" alt="" width="1024" height="683" class="alignnone size-large wp-image-220890" srcset="https://robohub.org/wp-content/uploads/2026/08/Umar-3-1024x683.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/08/Umar-3-425x283.jpeg 425w, https://robohub.org/wp-content/uploads/2026/08/Umar-3-768x512.jpeg 768w, https://robohub.org/wp-content/uploads/2026/08/Umar-3.jpeg 1080w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By Umar Farooq</strong></p>
<p>That was one of the questions at the heart of my last week (20th-24th July) at the Imperial Robotics Summer School, hosted at Imperial College, London; a week that sharpened my thinking and pushed me to look at robotics problems from angles I don&#8217;t usually get to in my day-to-day work.</p>
<p>The summer school brought together emerging researchers, academics, and industry professionals from across the robotics community for an intensive, hands-on programme. I came away having learned a huge amount, from expert-led lectures on robot kinematics, dynamics, sensing and control, and robot learning, through to specialised sessions on aerial robotics, robot intelligence, surgical robot vision, bio-inspired sensing and control, and personal assistive robotics.</p>
<p>One of the standout parts of the week was getting into Imperial&#8217;s robotics labs themselves, seeing research up close across adaptive and intelligent robotics, aerial robotics, robotic surgery, manipulation and touch, and assistive robotics. Alongside researchers from across the UK and beyond, we dug into real-world robotics challenges spanning quadruped locomotion, vision-based robot learning, tactile sensing, and healthcare applications.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/Umar-5-1024x768.jpeg" alt="" width="1024" height="768" class="alignnone size-large wp-image-220891" srcset="https://robohub.org/wp-content/uploads/2026/08/Umar-5-1024x768.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/08/Umar-5-425x319.jpeg 425w, https://robohub.org/wp-content/uploads/2026/08/Umar-5-768x576.jpeg 768w, https://robohub.org/wp-content/uploads/2026/08/Umar-5-1536x1152.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/08/Umar-5-2048x1536.jpeg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>Our group project focused on enabling a robot to interact with several people at once, rather than the typical one-to-one interaction most social robots are designed around. We worked on detecting the active speaker in real time, tracking each person&#8217;s identity through the interaction, and generating natural gaze and head-turn behaviour so the robot felt genuinely attentive to the whole group rather than just one person. Along the way, I got a much clearer picture of the full pipeline from language to motion, how an LLM translates natural intent into structured commands, how those get mapped to high-level robot functions, how inverse kinematics turns that into joint trajectories, and how it all finally reaches the actuators through the robot&#8217;s control stack. It was a great, hands-on introduction to just how hard multi-party human-robot interaction really is. and I came away with a much deeper appreciation for the interdisciplinary side of robotics research.</p>
<p>None of this would have been possible without UK RAS STEPS, who funded my place as one of five RTPs selected to attend. Beyond this summer school, UK RAS STEPS has been really helpful for my development, with different workshops along the way that I&#8217;ve learned a lot from. A special thank you also to Marie Daniels for her support and guidance throughout the application process.</p>
<p>Thanks as well to the wider Imperial College, London team, the lecturers, researchers, and fellow participants, for a week full of great conversations and a real learning environment.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/Umar-6-768x1024.jpeg" alt="" width="768" height="1024" class="alignnone size-large wp-image-220892" srcset="https://robohub.org/wp-content/uploads/2026/08/Umar-6-768x1024.jpeg 768w, https://robohub.org/wp-content/uploads/2026/08/Umar-6-319x425.jpeg 319w, https://robohub.org/wp-content/uploads/2026/08/Umar-6-1152x1536.jpeg 1152w, https://robohub.org/wp-content/uploads/2026/08/Umar-6-1536x2048.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/08/Umar-6-scaled.jpeg 1920w" sizes="(max-width: 768px) 100vw, 768px" /></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotics roadmaps from around the world</title>
		<link>https://robohub.org/robotics-roadmaps-from-around-the-world/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 12 Aug 2026 08:27:10 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220914</guid>

					<description><![CDATA[What’s a robotics roadmap, and why should we care? Machines with pre-defined capabilities will soon be old-school. Future machines are expected to learn and adapt to unpredictability and to interact with the physical world with the ableness of our own bodies. Welcome to Industry 4.0 (1). The reliance of modern societies on robots, from manufacturing [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/STB_Feature1.png" alt="" width="947" height="785" class="alignnone size-full wp-image-220915" srcset="https://robohub.org/wp-content/uploads/2026/08/STB_Feature1.png 947w, https://robohub.org/wp-content/uploads/2026/08/STB_Feature1-425x352.png 425w, https://robohub.org/wp-content/uploads/2026/08/STB_Feature1-768x637.png 768w" sizes="(max-width: 947px) 100vw, 947px" /></p>
<p>What’s a robotics roadmap, and why should we care?</p>
<p>Machines with pre-defined capabilities will soon be old-school. Future machines are expected to learn and adapt to unpredictability and to interact with the physical world with the ableness of our own bodies. Welcome to Industry 4.0 (1).</p>
<p>The reliance of modern societies on robots, from manufacturing to healthcare to agriculture to transportation (2), already suggests the magnitude of impact that recent innovations in robotic hardware could have once transferred from the laboratory to the market. Investment in robotics is a national priority in many countries (3). We are in fact in the midst of a global race to advance robots for physically embodying artificial intelligence, which is expected to have a dominating influence in global labor markets, immigration, military, commerce, and education (4).</p>
<p>Gaining familiarity with relevant stakeholders helps roboticists to understand their role in influencing the trajectory of their innovation. Roboticists can advise policymakers, for example, on the viability of their field and its potential to transform specific sectors. Government support in these areas enables academic institutes and industries to advance their technology, which can also reassure private investors to bet their money on related businesses. Done well, this process will expedite innovation where society needs it most.</p>
<p>We have a responsibility as a robotics community to discuss the collective milestones that we envision for a better society. What do we want robots to do in 10 years? Who should be the end users? And what resources do we need to transfer our technology into the real world? Though it feels removed from our typical day-to-day work as roboticists, grappling with these questions and reaching the right people could have far-reaching impact.</p>
<p>Roadmaps are an effective tool, especially for the interdisciplinary robotics community, to consolidate ideas and define a shared trajectory. They take many forms, depending on the target audience; a federal action plan can serve as a directive for research institutions while incentivizing investors to support an industry, an academic paper drafted by a coalition of robotics experts can serve as a beacon for innovators and ignite a common vision.</p>
<p>Influential robotics roadmaps have been authored by members of academia, industry, and government alike, often involving a combination of these entities to reflect their diverse perspectives and to propose objectives within realistic constraints. Some examples of these roadmaps include: The US National Robotics Roadmap–a bottom-up, academic-led roadmap that incentivizes major government investment towards innovations in collaborative robots (5,6); the industry-led ADRA Strategic Research, Innovation and Deployment Agenda–which successfully championed a ‘Physical AI’ funding track across the EU through the Horizon Europe innovation funding program (7); and Made in China 2025–a major government-driven plan including robotics development goals which helped transition China from low-cost workshops into a global high-tech leader over the course of a decade (8).</p>
<p>While internationally collaborative robotics roadmaps do exist (9), the majority of robotics roadmaps are highly country-specific, each having a set of unique priorities steeped in economics, geopolitics, and cultural values. A streamlined robotics agenda can help one country rise in the global value chain, while for another it may kickstart innovation needed for achieving technological sovereignty, particularly critical in an era where disruptive digital transformation can dictate shifts in global order.</p>
<p>In this monthly bite-size article series, we will untangle some of the latest information on roadmaps from leading robotics countries around the world. Each month will highlight one country and its robotics agenda.</p>
<p>Some topics we will delve into include:</p>
<ul>
<li>the outstanding priorities and strategies of various country’s robotics roadmaps.</li>
<li>the potential target audiences and intended outcomes of their readership.</li>
<li>the influence of geopolitical tensions on roadmap strategies.</li>
</ul>
<p>Thank you for reading this introductory article. Stay tuned for future additions. We would appreciate your opinions and feedback in the meantime, which you can send us at ras@ieee.org.</p>
<hr>
<p>Robotics Roadmap Issue #1</p>
<p>Ellen H. Rumley – Policy Analyst<br />
Allison Okamura – Vice President</p>
<p><em>IEEE RAS Science &#038; Technology Watch Board</em></p>
<hr>
<h4>References</h4>
<p>[1] Saurabh Vaidya, Prashant Ambad, Santosh Bhosle, <a href="https://www.sciencedirect.com/science/article/pii/S2351978918300672?via%3Dihub" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Industry 4.0 – A Glimpse</a>, Procedia Manufacturing, Volume 20, 2018, Pages 233-238, ISSN 2351-9789.<br />
[2] International Federation of Robotics (2025). <a href="https://ifr.org/ifr-press-releases/news/service-robots-see-global-growth-boom" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">World Robotics 2025 – Service Robots</a>.<br />
[3] International Federation of Robotics. (2024). <a href="https://ifr.org/downloads/papers/Executive_Summary_-_World_Robotics_RD_Programs_V04.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Executive summary: World robotics R&#038;D programs (Version 4)</a>.<br />
[4] Special Competitive Studies Project (SCSP). (2025). <a href="https://www.scsp.ai/reports/2025-gaps-analysis/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“Who’s Ahead, Who’s Behind, and Where We Are Headed Next in the U.S.-China Technology Competition?”</a><br />
[5] D. J. Hicks and R. Simmons, <a href="https://doi.org/10.1109/MRA.2019.2912860" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“The National Robotics Initiative: A Five-Year Retrospective,”</a> in IEEE Robotics &#038; Automation Magazine, vol. 26, no. 3, pp. 70-77, Sept. 2019.<br />
[6] Christensen, Henrik, et al. <a href="https://hichristensen.com/pdf/roadmap-2020.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A Roadmap for US Robotics – Robotics for a Better Tomorrow</a>. UC San Diego, Computing Community Consortium and Engineering Research Visioning Alliance, Apr. 2024.<br />
[7] Fredrik Heintz, Nabil Belbachir, and Edward Curry, <a href="https://adr-association.eu/sites/default/files/2024-09/Adra%20Strategic%20Research%20Jul24_v2-2.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“Strategic Research, Innovation, and Deployment Agenda 2025-2027”</a>, February 2024, Brussels, ADRA.<br />
[8] State Council of the People’s Republic of China. (2015). <a href="https://cset.georgetown.edu/wp-content/uploads/t0432_made_in_china_2025_EN.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Made in China 2025</a>. Beijing: State Council.<br />
[9] D. Araiza-Illan et al., <a href="https://doi.org/10.1109/MRA.2025.3620148" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">“A Road Map for Responsible Robotics: Promoting Human Agency and Collaborative Efforts,”</a> in IEEE Robotics &#038; Automation Magazine, vol. 32, no. 4, pp. 12-24, Dec. 2025.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>A ‘5-in-1’ seed-sized surgical robot</title>
		<link>https://robohub.org/a-5-in-1-seed-sized-surgical-robot/</link>
		
		<dc:creator><![CDATA[Nanyang Technological University, Singapore]]></dc:creator>
		<pubDate>Mon, 10 Aug 2026 14:38:45 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220898</guid>

					<description><![CDATA[Scientists from Nanyang Technological University, Singapore (NTU Singapore) have developed a tiny seed-sized robot that can navigate across soft and uneven surfaces to perform five surgical functions wirelessly, paving the way for developing robots to make surgeries and medical treatments more precise. The miniature robot, measuring just 4.4 mm in length and controlled by weak [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/Screenshot-2026-08-06-at-13.20.28-1024x557.png" alt="" width="1024" height="557" class="alignnone size-large wp-image-220899" srcset="https://robohub.org/wp-content/uploads/2026/08/Screenshot-2026-08-06-at-13.20.28-1024x557.png 1024w, https://robohub.org/wp-content/uploads/2026/08/Screenshot-2026-08-06-at-13.20.28-425x231.png 425w, https://robohub.org/wp-content/uploads/2026/08/Screenshot-2026-08-06-at-13.20.28-768x418.png 768w, https://robohub.org/wp-content/uploads/2026/08/Screenshot-2026-08-06-at-13.20.28.png 1026w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>Scientists from Nanyang Technological University, Singapore (NTU Singapore) have developed a tiny seed-sized robot that can navigate across soft and uneven surfaces to perform five surgical functions wirelessly, paving the way for developing robots to make surgeries and medical treatments more precise.</p>
<p>The miniature robot, measuring just 4.4 mm in length and controlled by weak magnetic fields, can move, cut biological tissues, release drugs, grip and store tissue samples, or generate heat remotely at any one time. It takes under a second to switch between these functions.</p>
<p>Led by Associate Professor Lum Guo Zhan from NTU’s School of Mechanical and Aerospace Engineering (MAE), the work was <a href="https://advanced.onlinelibrary.wiley.com/doi/10.1002/adma.202523056" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">recently published</a> in the academic journal <em>Advanced Materials</em>.</p>
<div class="keep-aspect"><iframe title="Meet the new &quot;5-in-1&quot; surgical microrobot" width="500" height="281" src="https://www.youtube-nocookie.com/embed/owKVqJFU94A?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Using magnetic coils in the laboratory to remotely control the robot, the team was able to make the robot deploy different tools and perform different functions, such as activating a tiny blade to cut through tissue, or emitting heat to a targeted area, which could be relevant for approaches being studied that use heat for cancer treatment.</p>
<p>“Most magnetic robots like this can perform only one or two functions. Our latest invention can now do five, and our long-term goal is for doctors to use these mini robots in the body, navigate them to a targeted location, and use them to perform treatments,” said Assoc Prof Lum, who is a pioneer in miniature robots made from soft, flexible materials.</p>
<p>Mini robots are being studied worldwide as a possible way to make minimally invasive surgical and medical procedures safer, less painful and more precise.</p>
<p>Such devices could one day allow doctors to carry out targeted surgeries deep inside the body without large cuts or bulky surgical instruments.</p>
<h4>Overcoming a key robotics challenge</h4>
<p> To fit multiple functions into a robot only a few millimetres long, the NTU team developed a device for controlling movements that is activated by magnetic fields and which can be reprogrammed in under a second.</p>
<p>The robot is made from soft magnetic materials, including PDMS and Ecoflex, which are silicone-based materials commonly used in soft robotics as they are flexible and can be shaped into small structures.</p>
<p>These materials are embedded with magnetic microparticles measuring 5 micrometres each, allowing different parts of the robot to respond to magnetic fields.</p>
<p>At the centre of the device is a magnetic module that can be magnetised, demagnetised and remagnetised in different directions.</p>
<p>Each magnetic orientation activates a different function of the robot, allowing the same mobile robot to perform five different functions, including cutting and grasping tissues.</p>
<p>The researchers also engineered different regions of the robot to ensure that only one part, but not the rest, responds to the same magnetic field. </p>
<p>This means that only one part of the robot reacts to a magnetic field to change its shape to activate a tool or function, while other parts remain still and unchanged in their current forms, addressing a major limitation in miniature magnetic robots.</p>
<p>At small scales, magnetic fields often affect the entire device at once, causing it to behave like a single magnet, with all parts reacting to a magnetic field, thus limiting how precisely it can move or activate different tools.</p>
<p>Most miniature magnetic robots are also limited to five degrees of freedom. They can only move along three axes and rotate in two directions.</p>
<p>The NTU robot adds a sixth movement, rolling, which allows it to spin around its own long axis. This gives the robot finer control over how it can be positioned, which is important for navigating narrow, soft and irregular spaces, such as those inside the body.</p>
<p>Unlike slime-like mini robots, the NTU robot has a solid but flexible body, making it sturdier and easier to retrieve after use.</p>
<h4>Tested on biological tissues</h4>
<p>The NTU team tested the robot’s surgical functions using biological tissue models, including chicken liver, as well as gelatin-based materials that simulate soft tissue.</p>
<p>In laboratory tests, the robot cut through biological tissues, dispensing particles simulating drug particles, gripped and stored tissue samples, and generated localised heat after being induced by magnetic fields.</p>
<p>To produce heat, the researchers exposed the robot to a high-frequency alternating magnetic field. This caused magnetic materials inside the device to generate heat remotely, in an approach relevant to magnetic hyperthermia methods being explored in cancer treatment.</p>
<p>The team also evaluated the biocompatibility of the robot’s materials by exposing them to human skin cells under laboratory conditions.</p>
<p>More than 99 per cent of the cells remained viable after exposure to the robot’s materials, similar to the control group, suggesting that the materials were largely non-toxic under the experimental conditions.</p>
<p>The team – including NTU’s MAE alumnae Dr Chelsea Shan Xian Ng and Yu Xuan Yeoh, and current PhD student Nicholas Yong Wei Foo, who are co-authors of the research – is now exploring how future versions could be combined with imaging technologies, sensing systems and clinically realistic artificial organ models that better mimic the physical behaviour of human tissues.</p>
<p>Assoc Prof Lum is also working with surgeons to understand how mini robotic systems could eventually fit into real clinical workflows.</p>
<p>“For these robots to move closer to practical use, we need to understand not just how they work in the lab, but how they could be guided, monitored and controlled in realistic medical settings,” he added.</p>
<p>Giving independent comments, Dr Yeo Leong Litt, Leonard, Senior Consultant from the Division of Neurology at the National University Hospital, said: “These millimetre-scale magnetically guided robots are truly remarkable in their ability to traverse complicated environments and then perform a variety of tasks such as deliver medication to a location, perform biopsies and administer therapeutic heat remotely. I can envision that they have the potential to replace many aspects of interventional radiological surgery and become a new mode of therapy in medicine.”</p>
<h4>Read the work in full</h4>
<p><a href="https://advanced.onlinelibrary.wiley.com/doi/10.1002/adma.202523056" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Miniature Soft Robot With Magnetically Reprogrammable Surgical Functions</a>, <em>Chelsea Shan Xian Ng, Yu Xuan Yeoh, Nicholas Yong Wei Foo, Keerthana Radhakrishnan, Guo Zhan Lum</em>. </p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>AI agents create virtual playgrounds to help robots get crucial training data</title>
		<link>https://robohub.org/ai-agents-create-virtual-playgrounds-to-help-robots-get-crucial-training-data/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Fri, 07 Aug 2026 07:17:33 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220795</guid>

					<description><![CDATA[A new system developed at MIT uses three agents to piece together the objects, walls, and overall look of a 3D scene. Its realistic recreations of indoor spaces help robots practice skills and try out different ways of doing tasks before they’re powered on. Image: Tim Malieckal/MIT CSAIL using assets from the researchers. By Alex [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.11.36-1024x676.jpeg" alt="" width="1024" height="676" class="alignnone size-large wp-image-220797" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.11.36-1024x676.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.11.36-425x281.jpeg 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.11.36-768x507.jpeg 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.11.36.jpeg 1436w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>A new system developed at MIT uses three agents to piece together the objects, walls, and overall look of a 3D scene. Its realistic recreations of indoor spaces help robots practice skills and try out different ways of doing tasks before they’re powered on. Image: Tim Malieckal/MIT CSAIL using assets from the researchers.</em></p>
<p><strong>By Alex Shipps</strong></p>
<p>Robots walking down the street, surrounded by astounded onlookers, is an increasingly common sight. But these machines aren’t yet the do-it-all assistants you’d want working in a kitchen or factory, and a major bottleneck is data. Much like humans, robots learn best by experience. The challenge is that it’s labor-intensive and time-consuming to physically teach these machines so many actions across different settings. </p>
<p>“One natural idea is to use simulation as a training ground. While there has been significant progress over the last few years in the physics engines that power robotics simulators, one of the remaining challenges has been creating sufficiently rich and diverse simulation content to capture the complexity of the real world,” says Russ Tedrake, the Toyota Professor of Electrical Engineering and Computer Science (EECS), Aeronautics and Astronautics, and Mechanical Engineering at MIT, and a principal investigator at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).</p>
<p>It turns out that AI agents, or semi-autonomous programs that “think” and complete well-defined tasks, could help produce the lifelike virtual settings that robots need. The new “<a href="https://scenesmith.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">SceneSmith</a>” system developed by researchers at MIT CSAIL and Toyota Research Institute uses three agents to piece together the objects, walls, and overall look of a 3D scene. Its recreations of indoor spaces such as restaurants, bedrooms, and hotels are more realistic and detailed than prior systems, helping robots practice skills and try out different ways of doing tasks before they’re powered on. In turn, engineers save time on real-world testing.</p>
<p>The agents have a sense of how everyday places are supposed to look because they each call on a multi-modal system called a vision-language model (VLM), specifically the state-of-the-art VLM <a href="https://openai.com/index/introducing-gpt-5-2/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">GPT-5.2</a>. It’s trained on lots of text and images from the internet to handle more visual prompts. This advanced model gives each agent a sort of spatial knowledge: First, a “designer” agent generates the elements of a scene, then a “critic” advises whether it looks realistic, and finally, an “orchestrator” manages their back-and-forth, deciding when the design is done. Once the three VLMs wrap up their creative collaboration, the scene is ready to load directly into physics simulation software.</p>
<p>“We’ve found that the system can construct 3D scenes the way a human designer would,” says MIT EECS PhD student Nicholas Pfaff, a CSAIL researcher and a lead author on a <a href="https://arxiv.org/abs/2602.09153" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">paper</a> with Tedrake presenting the work. “We made over 1,300 scenes using a leading VLM that has internet-scale priors, and it made insanely creative and diverse arrangements. I hadn’t taught the system to do that in the prompts; it just improvised.”</p>
<h4>Talk to my agent</h4>
<p>Thanks to VLM agents, you can ask SceneSmith to do things like “generate a garage with a car, a workbench, tires stacked in the corner, and a ladder against the wall,” and get a virtual playground rich with objects a robot can tinker with. These rooms are decorated with up to six times more items per scene than prior methods, making them great for helping robots learn skills such as putting a cup in the sink, placing fruit on plates, and moving a soda can from a shelf to a table.</p>
<p>With so many rich virtual environments handy, you can evaluate whether your robot is ready for deployment without so much trial and error in the physical world. The researchers tested out different action plans (also called “policies”) in SceneSmith’s digital worlds, generating 100 unique spaces in the process. A VLM agent evaluated each attempt, and it found the robot’s plans were faulty, with the machine often failing at its chores. Humans agreed with the model’s verdicts over 99 percent of the time, which could help roboticists weed out flawed approaches in simulation before a robot moves in the real world.</p>
<p>But how realistic are these virtual worlds, really? It can be difficult to prove outright, so the researchers approached the question from several angles. The most telling test: they dropped a pretrained robot policy — an AI controller trained largely on real-world data, which had never seen a SceneSmith scene — into the generated environments. In one test, users told the system to “take the apple from the bowl and place it onto the cutting board,” and the simulated robot did exactly that. If the scenes didn’t closely resemble the real settings the policy had learned from, it simply wouldn’t have worked. </p>
<p>The team also teleoperated robots through the virtual spaces, guiding them to open cabinets, put away bottles, and navigate between rooms. Their experiments revealed that the environments hold up under sustained physical interaction, expanding beyond visual inspection.</p>
<h4>Behind the scenes</h4>
<p>The agents that SceneSmith uses each have a well-defined role in the generative process, fleshing out scenes in stages. They essentially create a floor plan and bring it to life. </p>
<p>Let’s say you wanted to create a scene similar to the first floor of a house. The “designer” VLM would start with a general layout, which the “critic” reviews, and then the “orchestrator” signs off. The agents repeat this approach for each step: adding furniture, placing objects on walls and then ceilings, and finally, dropping in objects that robots can manipulate. For example, the VLMs can add cabinets that the robots can open and close — an articulated item, which prior baselines didn’t often have.</p>
<p>At each stage, the second VLM ensures the scene is practical, advising that a bathtub is removed from a living room, for example. The third VLM ensures a high-quality scene is generated, even taking the design process a few turns back if the visuals aren’t up to par. Once the three VLMs wrap up their creative collaboration, the mechanics of the physical world are added via simulation software.</p>
<p>With a sound understanding of how rooms should look, where objects should be placed, and real-world physics, SceneSmith has a noticeable edge over prior methods. Compared to scene-generation baselines such as “<a href="https://arxiv.org/abs/2503.16848" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">HSM</a>” and “<a href="https://arxiv.org/abs/2312.09067" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Holodeck</a>,” SceneSmith made environments with more objects, including a private office, a pottery store, and even a Minecraft-themed gaming room.</p>
<p>SceneSmith was also a favorite among over 200 users. They found the system’s visuals to be more realistic over 90 percent of the time. They also observed that, generally speaking, it followed prompts more closely than other approaches did. In other words, it was the best at generating the virtual playgrounds users actually wanted to see.</p>
<h4>A system of many talents</h4>
<p>Realism, diversity, and richness are all strong suits for SceneSmith, even when it comes to generating individual 3D objects. You can prompt it to create a rolling serving cart, and it’ll make a 2D image that it then turns into a detailed model with physical properties like mass, friction, and inertia.</p>
<p>Such a detailed process does come with a speed trade-off, though. It can take multiple hours to produce a single scene because the agents are creating and closely scrutinizing each object. With more computing power, the system could see dramatic increases in efficiency. CSAIL engineers are also hoping to expand to deformable objects (like sponges), should extensive 3D libraries become available.</p>
<p>“SceneSmith represents a significant advance in this regard by providing an agentic framework for generating simulation-ready indoor environments just from a simple text prompt,” says Jeremy Binagia, an applied scientist at Amazon Robotics who wasn’t involved in the research. “It advances the state of the art in several ways, including pushing the limits of the density of objects in the simulated environment, ensuring that all of the objects are physically accurate (versus just being visually realistic), and creating assets that are not constrained to a fixed library, since they can be generated via text-to-3D.”</p>
<p>Pfaff and Tedrake wrote the paper with Thomas Cohn SM ’24, an MIT PhD student and CSAIL researcher; and Toyota Research Institute roboticists Sergey Zakharov and Rick Cory SM ’08, PhD ’10. Their work was supported, in part, by Amazon, the U.S. Office of Naval Research, the Toyota Research Institute, and the U.S. National Science Foundation.</p>
<p>The team presented <a href="https://arxiv.org/abs/2602.09153" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">their findings</a> as a spotlight at the 2026 International Conference on Machine Learning.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robots in society, business and culture: July 2026</title>
		<link>https://robohub.org/robots-in-society-business-and-culture-july-2026/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Thu, 06 Aug 2026 07:30:38 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220835</guid>

					<description><![CDATA[By Emmet Cole This new monthly series from IEEE RAS showcases a selection of robotics stories from society, business, research, and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon. Technological isolationism or prudence? On July 28, the United States’ Federal Communications Commission blocked new foreign-made [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/RoboCup-action-1024x437.jpeg" alt="" width="1024" height="437" class="alignnone size-large wp-image-220848" srcset="https://robohub.org/wp-content/uploads/2026/08/RoboCup-action-1024x437.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/08/RoboCup-action-425x181.jpeg 425w, https://robohub.org/wp-content/uploads/2026/08/RoboCup-action-768x328.jpeg 768w, https://robohub.org/wp-content/uploads/2026/08/RoboCup-action-1536x656.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/08/RoboCup-action.jpeg 1626w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By Emmet Cole</strong></p>
<p><em>This new monthly series from IEEE RAS showcases a selection of robotics stories from society, business, research, and culture, as we track the field’s ongoing journey from specialized industrial machines to an increasingly visible social phenomenon.</em></p>
<hr>
<h4>Technological isolationism or prudence?</h4>
<p>On July 28, the United States’ Federal Communications Commission blocked <em>new</em> foreign-made “<a href="https://docs.fcc.gov/public/attachments/DA-26-786A1.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">advanced robotic devices</a>” from receiving the equipment authorization needed for sale in the United States, citing <a href="https://www.fcc.gov/sites/default/files/robots-nsd.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">supply-chain vulnerabilities and cybersecurity risks</a>.</p>
<p>The block applies to networked humanoids, quadrupeds, other qualifying mobile robots weighing more than 4.4 lb. In a parallel action, the FCC also restricted foreign-produced connected power inverters.</p>
<p>Existing authorized models are unaffected for now, and exemptions or conditional approvals may be available.</p>
<div class="keep-aspect"><iframe title="FCC chair Carr defends new ban on foreign-made humanoid robots" width="500" height="281" src="https://www.youtube-nocookie.com/embed/kTeCO57t9cs?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Reaction is predictably mixed. <a href="https://www.linkedin.com/in/georgstieler/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Georg Stieler</a>, a global robotics advisor and managing director for Asia at STM, told <a href="https://www.therobotreport.com/industry-reacts-fcc-ban-u-s-imports-new-humanoid-quadruped-robots/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Robot Report</a>:</p>
<p><em>“In the near term, the measure could slow U.S. physical AI innovation by cutting startups and researchers off from future low-cost Chinese platforms before comparable Western alternatives exist. It also opens opportunities for U.S. suppliers and allied manufacturers able to localize production in the U.S. or obtain conditional approval. Yet excluding foreign products is not the same as building a competitive industrial base.”</em></p>
<p>Meanwhile, John Moolenaar, a Michigan Republican who chairs the House ​Select Committee on China, told <a href="https://www.reuters.com/world/trump-administration-ban-new-chinese-robots-inverters-protecting-us-ai-buildout-2026-07-28/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Reuters</a> that the FCC move “protects our country and strengthens our nation’s robotics industry.”</p>
<p>On July 30, Reuters reported that China’s Commerce Ministry threatened to “resolutely retaliate” if the United States maintains the restrictions and urged the United States to immediately withdraw the ban.</p>
<p>Expect this story to run and run over the coming weeks, with many peaks and valleys for various stakeholders.</p>
<p>Speaking of peaks and valleys, Unitree Robotics’ newly launched Super Athlete AS2-W seems to handle them quite well…</p>
<div class="keep-aspect"><iframe title="Unitree Super Athlete AS2-W" width="500" height="281" src="https://www.youtube-nocookie.com/embed/Xha2TJ_1C6Q?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<h4>Ghostly smudges, puffins &#038; growing ivy</h4>
<p><a href="https://news.northwestern.edu/stories/2026/07/new-spinning-drone-hides-in-plain-sight" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Researchers at Northwestern University</a> have developed a drone that almost disappears while in plain view. Dubbed ‘Phantom Twist’, the drone spins up to 25 times per second, which is too fast for the human eye to see clearly. Instead, the drone becomes a “ghostly smudge” that blends into its environment.</p>
<p>The device could be used to monitor wildlife, survey the environment and inspect infrastructure with less visual disruption. Covert surveillance applications may be a little while off though, as the propellors announce the drone’s presence with great gusto.</p>
<div class="keep-aspect"><iframe title="New drone nearly disappears in flight" width="500" height="281" src="https://www.youtube-nocookie.com/embed/1mUgyV3A1O0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Meanwhile, researchers at <a href="https://news.mit.edu/2026/new-flapping-robot-swims-and-flies-like-diving-bird-0709" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT and EPFL</a> unveiled an ingenious 250-gram robot that can fly, dive beneath the water, swim and then launch itself back into the air using the same pair of flexible, flapping wings.</p>
<div class="keep-aspect"><iframe title="Puffin-Inspired Robot that Swims and Flies" width="500" height="281" src="https://www.youtube-nocookie.com/embed/9XJhrKpcBGI?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Inspired by diving birds including puffins and petrels, the <a href="https://aura.mit.edu/research/faav.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Flapping-wing Aerial Aquatic Vehicle</a> cruises through the air at 6.3 metres per second and swims at almost one metre per second. The team envisages future versions flying to remote or hazardous waters to monitor algal blooms, coral reefs, pollutants, fisheries and coastal erosion.</p>
<p>Have you ever been out cycling in the rain and found yourself wishing for a raincoat that could put itself on automatically while you ride? Kim Nam Gyun at South Korea’s KAIST did. And <a href="https://www.reuters.com/world/asia-pacific/south-korea-us-team-unveils-robotic-technology-that-dresses-wearer-2026-07-17/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">in July</a> that thought culminated in the unveiling of a robotic technology, inspired by climbing ivy, that enables a person to suit up without using their ​hands or requiring aid from others.</p>
<div class="keep-aspect"><iframe title="KAIST and Stanford Unveil Robot That Dresses People in 10 Seconds | Asia One News" width="500" height="281" src="https://www.youtube-nocookie.com/embed/C91fqVZvW2Q?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The vine robot, which turns the clothing inside out as it moves up the body, was developed in collaboration with researchers from Stanford University, and could find applications in chip cleanrooms and among ‌emergency services personnel.</p>
<h4>Humanoid, all too humanoid</h4>
<p>Returning to the topic of valleys for a moment, it was uncanny valley time on social media in July following a showcase of the <a href="https://www.aheadform.com/origin-f1" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Origin F1</a> at <a href="https://english.shanghai.gov.cn/en-WAIC2026/index.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">WAIC 2026</a> in Shanghai.</p>
<p>Boasting “natural eye contact,” “subtle expressions,” and “new skins, new souls” [sic] the robot provoked both awe and revulsion, and often at the same time, as is the custom in that strange region of robot design.</p>
<div class="keep-aspect"><iframe title="Origin F1 by AheadForm at WAIC 2026" width="500" height="281" src="https://www.youtube-nocookie.com/embed/m9hgKc6rrHY?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>LG Display provided a contrasting design vision at <a href="https://news.lgdisplay.com/en/2026/07/lg-display-presents-vision-of-lifestyle-transformationat-k-display-2026/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">K-Display 2026</a>, presenting a curved OLED “face” for humanoid robots that communicates through deliberately artificial expressions rather than attempting to pass as human.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/LG-Humanoid.jpg" alt="" width="1024" height="768" class="alignnone size-full wp-image-220836" srcset="https://robohub.org/wp-content/uploads/2026/08/LG-Humanoid.jpg 1024w, https://robohub.org/wp-content/uploads/2026/08/LG-Humanoid-425x319.jpg 425w, https://robohub.org/wp-content/uploads/2026/08/LG-Humanoid-768x576.jpg 768w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>A <a href="https://arxiv.org/abs/2607.13060" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">new Bayesian model of the uncanny valley</a> published in July might provide robot designers with a framework for handling uncanny valley design issues in future.</p>
<p>The team from the University of Tokyo note that existing guidelines, “such as adopting robot-like appearances, avoiding excessive realism, and reducing cross-modal mismatches, remain difficult to use for algorithmic design because they are not expressed as manipulable variables.”</p>
<p>The researchers propose a hierarchical Bayesian generative model that operationalizes these guidelines as mathematical design variables. In effect, the model attempts to turn broad advice such as “avoid excessive realism” into variables that designers can manipulate and test.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/08/July-ROund-up-2.png" alt="" width="604" height="240" class="alignnone size-full wp-image-220837" srcset="https://robohub.org/wp-content/uploads/2026/08/July-ROund-up-2.png 604w, https://robohub.org/wp-content/uploads/2026/08/July-ROund-up-2-425x169.png 425w" sizes="(max-width: 604px) 100vw, 604px" /></p>
<p>Separate from robot design questions and complexities, it is, as a general rule in life and robotics, better to keep your head while all around you are losing theirs. Although that message didn’t seem to get through a humanoid fighting robot at a recent event in China, with <a href="https://www.youtube.com/watch?v=UijhbHvxWrA" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Pythonesque</a> results…</p>
<div class="keep-aspect"><iframe title="Losing a Head Doesn&amp;apos;t Stop This Robot From Battling Another in the Ring" width="500" height="281" src="https://www.youtube-nocookie.com/embed/FEcPelBd9t0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<h4>Historic RoboCup match</h4>
<p>On July 5, at <a href="https://robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a>, two full teams of full-sized humanoid robots played an 11-vs-11 soccer match for the first time, bringing one of robotics’ most ambitious long-term visions closer to reality. The milestone match featured B-Human from Bremen, Germany vs HTWK Robots from Leipzig, Germany.</p>
<div class="keep-aspect"><iframe title="While the World Watches Fifa World Cup, Robots Made History in RoboCup 2026" width="500" height="281" src="https://www.youtube-nocookie.com/embed/XuEdf0fMAME?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>RoboCup’s long-term <a href="https://robocup.org/objective" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">objective</a> is gloriously ambitious:</p>
<p><em>By the middle of the 21st century, a team of fully autonomous humanoid robot soccer players shall win a soccer game, complying with the official rules of FIFA, against the winner of the most recent World Cup.</em></p>
<p>Do you think RoboCup’s objective is attainable? Will robots ever prevail over human <a href="https://en.wikipedia.org/wiki/Tiki-taka" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">tiki-taka</a>? Drop us a line at <a href="mailto:ras@ieee.org">ras@ieee.org</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Simulated zebrafish and a vision-equipped robotic fish reveal how the body shapes brain circuits</title>
		<link>https://robohub.org/simulated-zebrafish-and-a-vision-equipped-robotic-fish-reveal-how-the-body-shapes-brain-circuits/</link>
		
		<dc:creator><![CDATA[Xiangxiao Liu]]></dc:creator>
		<pubDate>Mon, 03 Aug 2026 11:17:56 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220786</guid>

					<description><![CDATA[Image credit: Olivier Porchet, Biorobotics Laboratory, EPFL When a fish holds its position against a current in a river, its brain must figure out how fast to swim and how to steer to offset the water flow. Most fish use vision to register the world sliding past, detect optic flow speed and direction, and their [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone wp-image-220802" src="https://robohub.org/wp-content/uploads/2026/07/Photo-3-simZFish-article-Credit-Olivier-PorchetBiorobotics-Laboratory-EPFL-compressed-1-425x283.jpeg" alt="" width="921" height="613" srcset="https://robohub.org/wp-content/uploads/2026/07/Photo-3-simZFish-article-Credit-Olivier-PorchetBiorobotics-Laboratory-EPFL-compressed-1-425x283.jpeg 425w, https://robohub.org/wp-content/uploads/2026/07/Photo-3-simZFish-article-Credit-Olivier-PorchetBiorobotics-Laboratory-EPFL-compressed-1-1024x683.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/07/Photo-3-simZFish-article-Credit-Olivier-PorchetBiorobotics-Laboratory-EPFL-compressed-1-768x512.jpeg 768w" sizes="(max-width: 921px) 100vw, 921px" /><br />
Image credit: Olivier Porchet, Biorobotics Laboratory, EPFL</p>
<p>When a fish holds its position against a current in a river, its brain must figure out how fast to swim and how to steer to offset the water flow. Most fish use vision to register the world sliding past, detect optic flow speed and direction, and their brains turn these signals into compensatory swimming. Neuroscientists call this stabilizing reflex the optomotor response (OMR), from neural activity imaging. The retina captures signals of optic-flow direction, central pretectal neurons interpret direction, and spinal nerves drive muscle contractions.</p>
<p>The catch is that one cannot easily change the living brain to test how these circuits work. Although advances in imaging now allow detailed recording, and even manipulation, of neurons alongside behavior, rewiring connections to ask what a particular link actually does remains almost impossible in the living, complex animal.</p>
<p>A joint team from <a href="https://www.epfl.ch/en/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">EPFL</a> (Switzerland), <a href="https://www.duke.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Duke University</a> (USA), and the <a href="https://tecnico.ulisboa.pt/pt/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Instituto Superior Técnico</a> (Portugal) took on this challenge by creating a realistic larval zebrafish simulation and a biomimetic robot, <a href="https://doi.org/10.1126/scirobotics.adv4408" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">published in Science Robotics</a>. The team found a way to replicate the body and known neural circuit architectures of live zebrafish, first as a physics-based simulation, then as a free-swimming robot that autonomously navigates upstream using vision and these bio-inspired neural circuits.</p>
<p>The results revealed the minimal set of neural components needed for the OMR and, more interestingly, showed that this balanced neural circuit allows autonomous upstream navigation even in poor visibility. It also highlighted that the fish’s body and eyes are part of the neural computation.</p>
<p><strong>A blueprint from the living fish brain</strong><br />
The starting point was work in the <a href="https://www.neuro.duke.edu/research/faculty-labs/naumann-lab" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Naumann Lab at Duke</a>, where detailed behavioral studies and whole-brain calcium imaging of larval zebrafish exposed to visual stimuli that mimicked riverbed optic flow, paired with circuit modeling, yielded a <a href="https://doi.org/10.1016/j.cell.2016.10.019" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">best-fit wiring diagram of the brain-scale OMR pathways</a>.</p>
<p>Drawing on other insights about neural processing in the vertebrate retina and spinal cord, <a href="https://www.epfl.ch/labs/biorob/people/liu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Dr. Xiangxiao Liu</a> and <a href="https://people.epfl.ch/lucathomas.zunino" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Luca Zunino</a> from the EPFL team used this neural circuit model to develop a neuromechanical simulation, simZFish, that not only recreates the larval fish body, complete with eyes and fins, but also takes this experimentally derived brain blueprint to be the simulation’s brain, opening new paths for neuroscience and brain-inspired robotics.</p>
<p><strong>simZFish: a brain you can take apart</strong><br />
Built in the physics-based Webots simulator, simZFish reproduces a six-day-old larva at 1:1 scale: a tiny 4 mm body, weighing only 0.3 mg with seven segments, driven by six simulated motors, a head with two sideways-facing cameras for eyes, and realistic water fluid dynamics. With just the right head-to-tail weight balance, the simulated simZFish moves just like real larval zebrafish. Its artificial brain replicates the entire neural circuit found in fish, from light-changing pixels to muscle activation.</p>
<p>The pretectum is a visual brain region that contains neurons that receive direct input from the retina, computing motion directions. The artificial retina detects motion and feeds four types of direction-selective ganglion cells, which drive pretectal neurons that integrate and process visual information from both eyes, and downstream hindbrain motor command neurons that set how often the fish swims and which way it turns. Finally, to emulate how the real fish swims in intermittent bouts, a &#8220;bout gate&#8221; releases a burst of tail beats, producing the characteristic burst-and-glide swimming of real larval zebrafish.</p>
<p>Because every part is simulated, researchers can change any aspect of simZFish&#8217;s body or neural connection weights, delete or add neurons, or change the eye’s lens and see the consequences immediately. In contrast, with animal experiments, one can only record correlations of neural activation if the fish happens to execute the behavior in question, but cannot exclude that some other processing was going on or easily change or interact with the internal structure. simZFish turns that black box into an open, well-lit one with identified components, allowing the team to pinpoint the &#8220;minimal essential elements&#8221; for OMR behavior.</p>
<p><img decoding="async" class="alignnone wp-image-220794" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21-425x190.png" alt="" width="935" height="418" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21-425x190.png 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21-1024x457.png 1024w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21-768x343.png 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21-1536x686.png 1536w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.08.21.png 1688w" sizes="(max-width: 935px) 100vw, 935px" /><br />
<strong>Figure 1.</strong> The larval zebrafish-sized simZFish can swim around in simulated water in a virtual Petri dish and be presented with an unlimited number of visual environments. SimZFish has two laterally placed virtual cameras that can ‘see’ the virtual environment (top-left boxes), a sensorimotor controller, and six motors linked in series in the tail, enabling it to capture and respond to visual motion information.</p>
<p><strong>The body is part of the computation</strong><br />
One specific insight from building this bio-inspired system concerned retinal-brain connectivity. With cameras on the sides of simZFish’s head, optic flow generated when fish are dragged in a river produces conflicting swirls across the visual fields, highlighting a version of the classic &#8220;aperture problem&#8221;. Therefore, feeding the motion information from the entire simulated retina into the circuit caused those signals to cancel out, breaking the OMR behavior. When the team restricted input to the lower posterior part of the visual field, the behavior snapped back into place.</p>
<p>Strikingly, that is exactly the region that most strongly drives the OMR in real zebrafish, and it matches the large, lower-posterior receptive fields neuroscientists have recorded in the real fish’s pretectum. The insight is not so much that the simulation &#8220;reveals&#8221; the circuit, but that embodiment, in this case the perspective distortion of the laterally placed eyes, explains why the circuit is wired the way it is: the layout of the body and eyes dictates a configuration that captures the most useful motion information with the fewest connections, an efficient solution evolution appears to have found as well.</p>
<p><strong>Closing the loop: a prediction sends the neuroscientists back to the microscope</strong></p>
<p>The simulation also predicted that the original neural circuit model was incomplete because it could not readily test behavioral responses to new stimuli. However, when each simulated eye was shown motion in the opposite direction, a shearing stimulus the model had never encountered, simZFish1.0 turned far more than expected. When our lead neurobiologist, <a href="https://www.neuro.duke.edu/profile/matt-loring" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Dr. Matthew Loring</a>, showed these visual stimuli to real zebrafish, they barely turned.</p>
<p>That mismatch sent the neuroscientists at Duke back to the microscope. Using volumetric two-photon calcium imaging, they recorded tens of thousands of neurons. They found that certain binocular neurons in the pretectum, specific response types that the circuit model relies on, existed in multiple previously overlooked subtypes. The team updated the too-simplistic simZFish1.0 model using neurons predicted by the simulation, which come in forward- and backward-tuned subtypes, with responses to one eye suppressed when the other eye sees forward motion.</p>
<p>Adding these subtypes and updating the connectivity produced simZFish 2.0, which reproduced the real fish’s behavior far better, including the response to the artificial shearing stimulus. &#8220;simZFish narrows the search, and the animal experiments verify the predictions, and together they complete the puzzle of the neural circuit,&#8221; said EPFL’s <a href="https://www.epfl.ch/labs/biorob/people/ijspeert/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Auke Ijspeert</a>, who directs the Biorobotics Laboratory (BioRob) at EPFL.</p>
<p>The final test came when the team released simZFish into a simulated flowing river, dragging its body with realistic forces, now with a realistic riverbed rather than artificial moving stripes. Strikingly, no matter which direction the simZFish started in, it eventually turned and swam upstream. “It was remarkable to observe that our experimentally derived neural circuits were allowing the simulation to navigate upstream autonomously”, marveled Eva Naumann, Assistant Professor of Neurobiology and Secondary Biomedical Engineering at Duke University.</p>
<p><strong>Into the wild: a robot that keeps up with the current using vision alone</strong><br />
To see whether a neural circuit tuned in a clean simulation could cope with the real world, the team scaled the tiny simZFish design up into <a href="https://www.science.org/doi/10.1126/scirobotics.adw7868" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ZBot</a>, an 80-centimeter, 2.7-kilogram robotic implementation carrying two real cameras, six tail motors, and a Raspberry Pi running the very same neural network, in a water-tight enclosed head.</p>
<p>Dropped into the sometimes-muddy, turbulent Chamberonne river near Lausanne, with plenty of river rocks, dappled light, drifting leaves, ZBot used the OMR circuit to counteract the water flow. With its visually activated OMR circuit, it stayed in the aerial drone camera’s view for much longer, 58 seconds, compared with roughly 37 seconds when its &#8220;eyes&#8221; were switched off and just 20 seconds when it drifted with the motors off (Figure 2, Video 1).</p>
<p><img decoding="async" class="alignnone wp-image-220793" src="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-425x93.png" alt="" width="914" height="200" srcset="https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-425x93.png 425w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-1024x224.png 1024w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-768x168.png 768w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-1536x337.png 1536w, https://robohub.org/wp-content/uploads/2026/07/Screenshot-2026-07-30-at-16.07.36-2048x449.png 2048w" sizes="(max-width: 914px) 100vw, 914px" /><br />
<strong>Figure 2.</strong> ZBot swimming in the Chamberonne River, Canton de Vaud, Switzerland.</p>
<p>It is the first demonstration that a fish could, in principle, fight a current using visual circuits alone. This overturns a long-held assumption that this behavior, rheotaxis, requires the mechanical &#8220;lateral line&#8221; network of sensory organs along the side of the fish body to detect water flow. &#8220;This is the first proof that effective rheotaxis can be achieved using visual neural circuits alone,&#8221; noted Professor Ijspeert.</p>
<p><div style="width: 1280px;" class="wp-video"><video class="wp-video-shortcode" id="video-220786-2" width="1280" height="720" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/07/Video-1.-With-the-OMR-neural-model-embodied-ZBot-maintains-its-position-far-better-than-with-random-bouting-OMR-circuit-blinded-or-passive-drifting-motors-off.-1.mp4?_=2" /><a href="https://robohub.org/wp-content/uploads/2026/07/Video-1.-With-the-OMR-neural-model-embodied-ZBot-maintains-its-position-far-better-than-with-random-bouting-OMR-circuit-blinded-or-passive-drifting-motors-off.-1.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/07/Video-1.-With-the-OMR-neural-model-embodied-ZBot-maintains-its-position-far-better-than-with-random-bouting-OMR-circuit-blinded-or-passive-drifting-motors-off.-1.mp4</a></video></div></p>
<p><strong>Video 1.</strong> With the OMR neural model embodied, ZBot maintains its position far better than with random bouting (OMR circuit blinded) or passive drifting (motors off).</p>
<p><strong>Why it matters for robotics</strong><br />
For robotics, the appeal is building more efficient, more autonomous agents. Most drones employ dedicated downward-facing cameras for position stabilization. By contrast, our method leverages the existing lateral cameras and requires no additional hardware, cutting both hardware and computational costs. Interestingly, this balancing circuit that compares across eyes seemed to handle poor visibility very well, likely also because the burst-and-glide swimming allowed the ZBot to integrate useful sensory information during the glide phase, when visual input was not degraded by self-motion.</p>
<p>The same bio-inspired burst-and-glide control of the ZBot underlies a companion study by the team showing that <a href="https://doi.org/10.1126/scirobotics.adw7868" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">intermittent swimming saves energy</a>, pointing toward lighter, longer-lasting aquatic robots that switch gaits as real fish do. Both the simulator and the robot designs are open-source, so other groups can reuse the models or build and test new circuits.</p>
<p>Yet, as the ZBot is roughly 200 times larger than its biological model and swims in a different fluid regime, it tests the circuit’s logic rather than the larva’s exact mechanics. The realistic simZFish’s visual circuit also holds its position only against a gentle flow, because the model currently cannot dynamically respond to different flow regimes. For the ZBot, about half the river trials were discarded for collisions or signal dropouts, probably because the stripped-down OMR circuit doesn’t allow the ZBot to avoid obstacles.</p>
<p>Even so, the approach the team built offers a powerful template for connecting brains, bodies, and behavior. &#8220;By integrating simulation, robotics, and animal experiments, we get a far more complete view of an animal’s neural model,&#8221; said Naumann, who runs a systems neuroscience lab testing how visual neural circuits interact in live zebrafish. Starting from these tiny baby fish, this iterative simulation-neurobiology-robotics approach is opening new ways to understand animal intelligence and to build efficient, brain-inspired aquatic robots.</p>
<p><strong>Paper and team information</strong><br />
You can access the simZFish open-source platform <a href="https://ponyo.epfl.ch/proj/zebrafish/simzfish" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a> and explore more work on the <a href="https://github.com/Naumann-Lab" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Naumann Lab Github</a>.</p>
<p>EPFL led simZFish development, neuromechanical modeling, and ZBot design and testing. Duke University led the zebrafish behavioral experiments, two-photon calcium imaging, and neural network modeling and data analysis. The Instituto Superior Técnico contributed modeling and theoretical analysis of the visual neuromechanical system.</p>
]]></content:encoded>
					
		
		<enclosure url="https://robohub.org/wp-content/uploads/2026/07/Video-1.-With-the-OMR-neural-model-embodied-ZBot-maintains-its-position-far-better-than-with-random-bouting-OMR-circuit-blinded-or-passive-drifting-motors-off.-1.mp4" length="9753051" type="video/mp4" />

			</item>
		<item>
		<title>Researchers develop modular nanorobot</title>
		<link>https://robohub.org/researchers-develop-modular-nanorobot/</link>
		
		<dc:creator><![CDATA[University of Basel]]></dc:creator>
		<pubDate>Fri, 31 Jul 2026 09:21:31 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220709</guid>

					<description><![CDATA[Illustration of the versatile nanorobot. It is 150 times smaller than the diameter of a human hair. (Illustration: Marina Bräm) By Angelika Jacobs Nanorobots sound like science fiction: tiny machines for medicine, the environment, or industry. In fact, nanorobotics has become a rapidly growing field of research. It is considered a promising approach, for example, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Header_Nanoroboter_1000x500.jpg" alt="" width="1000" height="500" class="alignnone size-full wp-image-220710" srcset="https://robohub.org/wp-content/uploads/2026/07/Header_Nanoroboter_1000x500.jpg 1000w, https://robohub.org/wp-content/uploads/2026/07/Header_Nanoroboter_1000x500-425x213.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/Header_Nanoroboter_1000x500-768x384.jpg 768w" sizes="(max-width: 1000px) 100vw, 1000px" /><em>Illustration of the versatile nanorobot. It is 150 times smaller than the diameter of a human hair. (Illustration: Marina Bräm)</em></p>
<p><strong>By Angelika Jacobs</strong></p>
<p>Nanorobots sound like science fiction: tiny machines for medicine, the environment, or industry. In fact, nanorobotics has become a rapidly growing field of research. It is considered a promising approach, for example, for delivering active substances to specific locations in the body. Unlike their larger-scale counterparts, they are not made of electronics, computer chips, and software, but rather of biomolecules and nanoparticles.</p>
<p>Researchers led by Prof. Dr. Cornelia Palivan from the University of Basel are now reporting on a sophisticated modular nanorobot with greater functional flexibility than many existing systems. “Previous nanorobots are often designed for a specific task only,” says Cornelia Palivan. “Our modular system, on the other hand, can be adapted to different applications.” The technology could be used not only in medicine but also in industry and environmental technology.</p>
<h4>Propulsion module and payload capsule</h4>
<p>The nanorobot, which the team describes in the journal <em>Advanced Functional Materials</em>, resembles a lunar rocket with multiple modules. A magnetic propulsion module moves the nanorobot, while a second module serves as a payload capsule, safely transporting therapeutic agents or enzymes to their target location.</p>
<p>In previous work, Palivan’s team developed nanoscale polymer vesicles that protect encapsulated enzymes. Molecules can enter the vesicle through pores, be processed by the enzymes and then their products are released into the environment. The payload capsule of the nanorobot contains four such enzyme-loaded polymer vesicles, providing the desired functionality. Depending on the design, the vesicles inside the payload capsule can also be selectively opened, for example to release bioactive compounds.</p>
<h4>A DNA-based molecular Velcro system</h4>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/TEM-image-of-nanorobots_500x375-2.jpg" alt="" width="1000" height="750" class="alignnone size-full wp-image-220712" srcset="https://robohub.org/wp-content/uploads/2026/07/TEM-image-of-nanorobots_500x375-2.jpg 500w, https://robohub.org/wp-content/uploads/2026/07/TEM-image-of-nanorobots_500x375-2-425x319.jpg 425w" sizes="(max-width: 1000px) 100vw, 1000px" /><em>One of the nanorobots, imaged with a Transmission Electron Microscope. (Image: Voichita Mihali)</em>.</p>
<p>The two modules are connected by a DNA-based “Velcro fastener”: complementary DNA strands on both modules ensure that the propulsion module and the payload capsule self-assemble in a programable manner and remain stably coupled.</p>
<p>To enable the nanorobot to dock onto specific cells or materials, the payload capsule is also equipped with additional biomolecules that facilitate docking. In the lab, the team tested this using a human cancer cell line known as HeLa cells. They loaded the nanorobots with fluorescent molecules and observed under the microscope that they accumulated on the surface of the cells.</p>
<h4>Targeted attack on cancer cells and other applications</h4>
<p>Equipped with the necessary enzymes, the nanorobots successfully produced an anticancer drug which reduced the viability of the HeLa cells to 16 percent within 72 hours. “The drug can have a concentrated local effect if we use our nanorobot to specifically target it to the cancer cells,” explains Dr. Voichita Mihali, the first author of the study.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Enzymreaktion_Nanoroboter_1000x750.jpg" alt="" width="1000" height="750" class="alignnone size-full wp-image-220711" srcset="https://robohub.org/wp-content/uploads/2026/07/Enzymreaktion_Nanoroboter_1000x750.jpg 1000w, https://robohub.org/wp-content/uploads/2026/07/Enzymreaktion_Nanoroboter_1000x750-425x319.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/Enzymreaktion_Nanoroboter_1000x750-768x576.jpg 768w" sizes="(max-width: 1000px) 100vw, 1000px" /><em>Illustration of the nanorobot sitting on a surface. The enzymes in its payload capsule catalyze reactions, converting molexules from the environment into the desired product.<br />
The nanorobot can attach itself to specific surfaces and carry out enzymatic reactions there. The enzymes (purple) inside the payload capsule convert molecules from the surrounding environment (left, dark gray) into the desired product (right, light gray). (Illustration: Marina Bräm)</em>.</p>
<p>For other applications outside the medical domain, for example catalysis, another feature might prove particularly valuable: Since the propulsion module is magnetic, the nanorobots can be retrieved and reused after their task is completed. The researchers were also able to separate the two modules, refill the payload capsules, and recombine them with the propulsion modules. </p>
<p>The modular nanorobot represents an important step toward a multifunctional tool for a wide range of applications. Although its use in humans remains a long-term goal, the system can be readily adapted for other domains simply by modifying the payload capsule.</p>
<p>The work was conducted within the framework of the National Center of Competence in Research – Molecular Systems Engineering and the Swiss Nanoscience Institute. The University of Basel team collaborated with researchers from Heidelberg University.</p>
<h4>Reference</h4>
<p><a href="https://advanced.onlinelibrary.wiley.com/doi/10.1002/adfm.202600079" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Multiplex Modular Nanorobotic Systems with Catalytic Activity under Magnetic Navigation</a>, <em>Voichita Mihali et al.</em>, Advanced Functional Materials (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Surviving the paper deluge: a one-year study in learning from demonstration</title>
		<link>https://robohub.org/surviving-the-paper-deluge-a-one-year-study-in-learning-from-demonstration/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Wed, 29 Jul 2026 09:16:32 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[IEEE RAS]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220654</guid>

					<description><![CDATA[By Emmet Cole With the explosion of robotics research, staying current in fields like Learning from Demonstration (LfD) is a monumental challenge. Is AI the solution to the “paper deluge,” or is it part of the problem? Read the article preview below to learn more! Download the full paper: Surviving the Paper Deluge. Authors: Aude [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2016/07/bigstock-Stack-Of-Business-Papers-88335854.jpg" alt="" width="900" height="600" class="alignnone size-full wp-image-64317" srcset="https://robohub.org/wp-content/uploads/2016/07/bigstock-Stack-Of-Business-Papers-88335854.jpg 900w, https://robohub.org/wp-content/uploads/2016/07/bigstock-Stack-Of-Business-Papers-88335854-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/07/bigstock-Stack-Of-Business-Papers-88335854-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /></p>
<p><strong>By Emmet Cole</strong></p>
<p>With the explosion of robotics research, staying current in fields like Learning from Demonstration (LfD) is a monumental challenge. Is AI the solution to the “paper deluge,” or is it part of the problem? Read the article preview below to learn more!</p>
<p>Download the full paper: <a href="https://www.ieee-ras.org/wp-content/uploads/2026/05/Surviving-the-Paper-Deluge.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Surviving the Paper Deluge</a>.</p>
<p><strong>Authors: Aude Billard, Renaud Detry, Nadia Figueroa, Maximilian Foriest, Dongheui Lee, Kunpeng Yao</strong><br />
<em>Contributions: The five senior authors (A.B, R.D, N.F, D.L and K.Yao) collectively designed the study, read the papers, conducted the qualitative and quantitative analysis and writing of the paper. M. F. contributed scripts for LLM analysis and participated in LLM-Human comparison.</em></p>
<hr>
<h4>Summary</h4>
<p>Scientists are expected to read newly published papers in their field to stay current and keep their work relevant. However, when faced with the massive number of publications, it may seem an overwhelming task to read all these papers, even if one were to reduce this to only a fraction related to one’s own area of research.  As an example, in 2024 alone, IEEE published no less than 46,968 papers on “robotics” or “automation”, and IEEE publications represent only a fraction of the total research available online</p>
<p>To assess the magnitude of this challenge, as well as to evaluate how much genuine progress is reported in today’s publications, we undertook exactly this effort. For the task to be reasonable, we reduced our search to one particular subarea, learning from demonstration (LfD), that is methods whereby robots are taught by human experts. We monitor progress through both quantitative and qualitative metrics, offering a review on current trends and notable contributions. We also delineate areas of importance, but that seem to receive little attention and offer recommendations for promoting. </p>
<p>Our assessment was primarily based both on a human-eye assessment of all papers. We also explored the use of AI and other computing tools to do this task in our place. While scripts and large language models (LLMs) can be used fairly faithfully to provide general quantitative assessment, they fail when it comes to assessing the true importance of the research. They cannot recognize a paper revisiting a work that already had solutions. They fail to recognize when the abstract or claims of the paper are overstatements over the true contribution reported in the paper. </p>
<p>Our overall assessment led us to conclude that from a deck of more than 300 papers, only about 20% of the papers could be qualified as offering highly notable contributions, while the remainder of the papers offered a variety of incremental improvements over existing methods, or new domains of applications. The notable contributions did not correlate necessarily with a higher number of downloads or citations. Finding these gems is, however, essential to reduce the risk that novel work goes unnoticed and reduce duplication of efforts. We offer a few thoughts on how to best combine direct reading of the literature with automated approaches (scripts and LLMs) to streamline the review process. We close with a few recommendations: a) develop a research engine that restores the natural importance of work done by journal and conference editorial boards to rank papers based on evaluation scores and peer-reviewed status, in place of Google Scholar or IEEEXplore, that place all publications on equal footing, disregarding peer reviewing and the reputation of journals and conferences, b) consider establishing a blind publication model and topic-based social media posting, where authors’ name and institution are downplayed and become accessory to the paper to ensure that focus be on the content of the publication rather than secondary aspects, c) take a holistic approach to use of LLM in support of reviewing literature, using them for what they excel at, namely summarizing a piece of work and collecting precise quantitative information, but bearing in mind that, while today the tools cannot match expert capacity to assess true novelty, should they achieve this one day, this may have repercussion on our own ability to provide said expertise. </p>
<h4>Publications growth</h4>
<p>Over the past decade, the number of submissions to robotics journals has grown steadily on a yearly basis, with an explosive trend in 2023 (26%) and 2024 (31%), likely due to different factors, including growing interest in the public and private sectors and to the availability of AI tools supporting the writing of papers and code. The number of published papers has closely followed this trend, despite all efforts made by editorial boards to contain the growth by decreasing acceptance rates. Conferences have followed the same trend. For instance, ICRA doubled the number of papers it published in ten years, reaching approximately 1,800 in 2024. Simultaneously, the strong pressure exerted by the community to publish rapidly has led to a 50% decrease in the time window between the submission of a paper and its publication. The phenomenon is not particular to IEEE publications, and journals and conferences such as IJRR, RSS and CoRL have followed the same trend.</p>
<p>Clearly, it would be unrealistic to expect any researcher to read all of these publications. One might argue that researchers are typically interested in only a subset of the literature, for instance a specific domain or methodology, and would therefore read only a fraction of all published papers. Yet even this narrower scope may prove unmanageable. To assess how feasible it is for a researcher to stay current within their own area of expertise, we undertook the task of reading a large fraction of all papers published in our domain – learning from demonstration – over the course of a single year (2024).</p>
<hr>
<p>This article originally appeared on <a href="https://www.ieee-ras.org/category/ras-feature/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE RAS</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Soft robotic heart offers new way to study disease and test life-saving devices</title>
		<link>https://robohub.org/soft-robotic-heart-offers-new-way-to-study-disease-and-test-life-saving-devices/</link>
		
		<dc:creator><![CDATA[University of New South Wales]]></dc:creator>
		<pubDate>Tue, 28 Jul 2026 09:18:50 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220699</guid>

					<description><![CDATA[The soft robotic model of the human heart, developed at UNSW. Credit: UNSW/Richard Freeman. UNSW researchers have developed a soft robotic model of the human heart that can mimic disease and provide a realistic environment for testing the next generation of cardiac devices. Researchers at UNSW Sydney have developed a fully synthetic soft robotic heart [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-Soft-Robotic-Heart-SH01-0097-crop.cropimg.width700.cropbasic.jpg" alt="" width="700" height="466" class="alignnone size-full wp-image-220703" srcset="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-Soft-Robotic-Heart-SH01-0097-crop.cropimg.width700.cropbasic.jpg 700w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-Soft-Robotic-Heart-SH01-0097-crop.cropimg.width700.cropbasic-425x283.jpg 425w" sizes="(max-width: 700px) 100vw, 700px" /><em>The soft robotic model of the human heart, developed at UNSW. Credit: UNSW/Richard Freeman.</em></p>
<p>UNSW researchers have developed a soft robotic model of the human heart that can mimic disease and provide a realistic environment for testing the next generation of cardiac devices.</p>
<p>Researchers at UNSW Sydney have developed a fully synthetic soft robotic heart that reproduces the complex movements and internal structures of the human heart, opening the door to better treatments, safer medical devices and more personalised care.</p>
<p>Published in <a href="https://www.nature.com/articles/s41467-026-73791-w" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Nature Communications</a> and <a href="https://advanced.onlinelibrary.wiley.com/doi/abs/10.1002/advs.75382" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Advanced Science</a>, the research introduces a beating model of the left side of the heart that includes artificial valves, papillary muscles and chordae tendineae – structures that are critical to healthy heart function and are frequently affected by disease.</p>
<p>The device is able to accurately reproduce the process in a real heart where cardiac valves leak and blood flows backwards, which increases the risk of heart failure and other life-threatening complications.</p>
<p>In that way, the research team say the new soft robot can eventually help provide a better understanding of heart conditions, reduce reliance on animal testing and provide doctors with patient-specific models to plan treatments before procedures are performed.</p>
<p>Team leader, Scientia Associate Professor <a href="https://research.unsw.edu.au/people/associate-professor-thanh-nho-do" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Thanh Nho Do</a>, from <a href="https://www.unsw.edu.au/engineering/our-schools/biomedical-engineering/our-research/impact/cardiovascular-health/artificial-muscles-to-keep-64-million-hearts-pumping" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">UNSW’s School of Biomedical Engineering</a> and <a href="https://www.medicalrobotics-lab.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">UNSW Medical Robotics Lab</a>, says the work is important because cardiovascular disease remains the world&#8217;s leading cause of death.</p>
<p>“Heart failure with preserved ejection fraction (HFpEF) is a complex heart condition that often occurs alongside other health problems such as high blood pressure, irregular heartbeats, kidney disease, obesity, and diabetes,” Professor Do says.</p>
<p>“Because it affects people in different ways, developing medical devices to improve heart function is challenging.</p>
<p>“The valves in the heart are also crucial for cardiac efficiency, but disease can cause them to become leaky or stiff. This can increase the workload of the heart and contribute to heart failure.</p>
<p>“Our broader goal is to build realistic artificial heart models that can help researchers understand disease and develop safer, more effective devices before they are tested on animals or reach patients.”</p>
<h4>Recreating the beating heart</h4>
<p>The model developed at UNSW is a soft, flexible replica of the left side of the heart. Silicone membranes form the internal chambers, while soft robotic artificial muscles wrapped around the structure reproduce the way the heart naturally contracts and twists.</p>
<p>Unlike conventional laboratory models, the soft robotic heart contains the structures responsible for controlling the mitral valve, which in real life acts like a pair of swinging doors that open and close with each heartbeat to ensure oxygen-rich blood flows to the body while preventing backward leakage.</p>
<p>The inclusion of this specific physiological feature of the heart in the model will allow researchers to reproduce diseases in which the valve does leak and blood starts to flow backwards.</p>
<p>“The model is made from flexible materials and powered by artificial muscles that are arranged to mimic the layered muscle architecture of the human heart,” Dr James Davies, a postdoc in Do’s group, says.</p>
<p>“We found a way to model this muscle fibre architecture using soft robotic artificial muscle fibres. They are powered by hydraulic pressure which we control to make our ventricular muscle model move like the real thing.</p>
<p>“We then wrap this artificial musculature around silicone membranes which model the inner surface of the human left heart, forming our left heart, atrioventricular model. These membranes contain the simulated blood within the left heart allowing simulated pumping of blood in and out of the model.”</p>
<p>The system allows researchers to actively adjust the tension in the artificial papillary muscles that support the mitral valve.</p>
<p>By doing so, the team was able to recreate disease-like conditions including mitral valve prolapse and regurgitation, where blood leaks backwards instead of flowing efficiently through the heart.</p>
<h4>Mimicking human heart disease</h4>
<p>Using ultrasound imaging and measurements of pressure and blood flow, the researchers showed that the artificial heart behaves in ways remarkably similar to a human heart.</p>
<p>Healthy valve function produced normal pressure and flow patterns, while introducing disease caused characteristic changes seen in patients.</p>
<p>“In the first study reproducing the internal valving of the human heart, we were able to generate pressure and flow waveforms similar to that of the real thing,” Professor Do says.</p>
<p>“Critically, we were able to adjust mitral valve function by controlling papillary muscle length.</p>
<p>“We validated this using invasive pressure and flow measurements in and out of the heart, but we were also able to demonstrate compatibility of the model with non-invasive clinical measures of heart function such as ultrasound imaging, or echocardiography.</p>
<p>“Simulated healthy mitral valve function followed physiological expectations in heart pressure and flow, while inducing disease showed increased regurgitation, or backflow, and a decrease in outlet pressure and flow, also consistent with human heart valve disease.”</p>
<p><a href="https://www.unsw.edu.au/staff/nigel-lovell" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Scientia Professor Nigel Lovell</a>, Head of School of Biomedical Engineering &#038; Director of Tyree IHealthE, added: “The ultrasound imaging also resembled human cardiac imaging owing to the biomimetic form and function of our model. We were able to observe human-like valve leaflet motion and visualise blood flow across the valves, including the formation of regurgitant jets leaking out of valves with induced disease.”</p>
<p>The researchers also used the system to test a newly developed soft robotic cardiac catheter inside the beating model.</p>
<p>The catheter was able to navigate within the artificial heart and detect when it came into contact with moving cardiac structures, demonstrating how the platform could accelerate development of future surgical tools.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop-1024x643.jpeg" alt="" width="1024" height="643" class="alignnone size-large wp-image-220704" srcset="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop-1024x643.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop-425x267.jpeg 425w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop-768x482.jpeg 768w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop-1536x964.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0012-crop.jpeg 1920w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Credit: UNSW/Richard Freeman</em>.</p>
<h4>Reducing reliance on animal models</h4>
<p>Because the simulator offers a controllable and repeatable environment, the researchers believe it could help reduce the need for animal studies during the early stages of medical device development.</p>
<p>“We hope to bring into existence a platform to comprehensively model cardiac disease and simulate their various treatments, including cardiac implants and surgical tools,” Professor Do says.</p>
<p>“Particularly in the early stages of cardiac device development, such a platform will offer control over heart function while maintaining anatomical and physiological relevance, reducing our reliance on animal models and its associated costs and ethical concerns.</p>
<p>“Being able to induce a broad range of specific cardiac disease such as HFpEF which remains one of the least well understood and hardest heart failure to treat, we hope to aid in the development of new, purpose-built implants and devices that save and improve lives and reduce the burden of cardiovascular disease on healthcare systems.</p>
<p>“HFpEF disease that makes up 50% of heart failure cases deserves its own mechanical treatment options.”</p>
<p>More importantly, the model successfully reproduced many of the changes seen in HFpEF, including changes in heart function and blood flow.</p>
<p>When researchers simulated one of the earliest signs of HFpEF — a reduced ability of the heart to relax between beats — the model showed that blood flowed into the heart more slowly and less efficiently. This delayed filling increased pressure inside the heart, closely matching what is commonly observed in patients with HFpEF.</p>
<p>The researchers also envision a future in which patient-specific versions of the model could be created using medical imaging data.</p>
<p>These personalised models could help clinicians evaluate different devices and treatment approaches before operating, improving surgical planning and potentially leading to better outcomes.</p>
<p>“With the rise of personalised medicine, we also hope to enable better patient-specific cardiovascular modelling that can aid in surgical planning and inform decisions around implant type, size, and functional parameters,” Professor Do says.</p>
<p>“We are looking forward to validating these concepts and pushing towards clinical adoption in the future.”</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102-1024x612.jpeg" alt="" width="1024" height="612" class="alignnone size-large wp-image-220705" srcset="https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102-1024x612.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102-425x254.jpeg 425w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102-768x459.jpeg 768w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102-1536x918.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/07/2026-06-19-soft-robotic-heart-sh01-0102.jpeg 1920w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Dr James Davies and Scientia Associate Professor Thanh Nho Do in their laboratory. Credit: UNSW/Richard Freeman</em>.</p>
<h4>Future validation</h4>
<p>While the study demonstrates the technology&#8217;s potential, the researchers stress that the current model is still a proof of concept rather than a finished clinical tool.</p>
<p>Several challenges remain, including improving materials, refining the control systems and making the device even more compatible with medical imaging. Future versions will also need to better reproduce certain aspects of heart function and use patient-specific geometries rather than simplified structures.</p>
<p>Most importantly, the platform must be validated against real patient data.</p>
<p>“The most important next step is deeper validation against clinical data,” Professor Do says.</p>
<p>“The current studies demonstrate strong proof-of-concept performance.</p>
<p>“The model can reproduce key pressure, flow, motion, valve, and imaging features that align with human heart behaviour. However, before this platform can be used for clinical decision-making, we need to compare it systematically with patient data across a wide range of heart anatomies and disease severities.”</p>
<p>The team, which also includes <a href="https://www.svhs.org.au/our-services/our-specialists/prof-christopher-hayward" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Professor Christopher Hayward</a>, a heart failure and transplant cardiologist at St Vicent’s Hospital Sydney, as well as <a href="https://www.unsw.edu.au/staff/jelena-rnjak-kovacina" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Professor Jelena Rnjak-Kovacina</a> and <a href="https://www.phan-lab.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Scientia Associate Professor Hoang-Phuong Phan</a> from UNSW, hope that with further development of this technology it can be adopted in clinical settings.</p>
<p>“Rather than viewing the current model as a finished clinical tool, we see it as an enabling platform,” Dr Davies added.</p>
<p>“It demonstrates that soft robotic artificial hearts can reproduce disease mechanics in ways that conventional benchtop models cannot, and it provides a clear pathway toward patient-specific modelling, device testing, and eventually treatment planning.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>A mini robot to simplify dental treatment</title>
		<link>https://robohub.org/a-mini-robot-to-simplify-dental-treatment/</link>
		
		<dc:creator><![CDATA[University of Basel]]></dc:creator>
		<pubDate>Fri, 24 Jul 2026 09:45:56 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220541</guid>

					<description><![CDATA[A miniature robot developed at the University of Basel could help prepare teeth for a crown. Photo: University of Basel, Catherine Weyer. By Angelika Jacobs A routine check-up at the dentist ends with bad news: tooth decay has left a large cavity, and the tooth needs a crown. The treatment requires several follow-up appointments. During [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Header_Dentalroboter_1000x500.jpg" alt="" width="1000" height="500" class="alignnone size-full wp-image-220542" srcset="https://robohub.org/wp-content/uploads/2026/07/Header_Dentalroboter_1000x500.jpg 1000w, https://robohub.org/wp-content/uploads/2026/07/Header_Dentalroboter_1000x500-425x213.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/Header_Dentalroboter_1000x500-768x384.jpg 768w" sizes="(max-width: 1000px) 100vw, 1000px" /><em>A miniature robot developed at the University of Basel could help prepare teeth for a crown. Photo: University of Basel, Catherine Weyer.</em></p>
<p><strong>By Angelika Jacobs</strong></p>
<p>A routine check-up at the dentist ends with bad news: tooth decay has left a large cavity, and the tooth needs a crown. The treatment requires several follow-up appointments. During the first appointment, the dentist removes the decay, fills the cavity and prepares the tooth for the crown. She then takes an impression and fits a temporary crown. The permanent crown is produced based on the impression and can only be placed at a later appointment.</p>
<p>In future, this process could become much faster thanks to a small dental robot developed by researchers at the Department of Biomedical Engineering at the University of Basel. The idea came from researchers at the University of Zurich, who were also involved in the development.</p>
<p>The prototype is about the size of a wine cork, measuring just 43 by 26 by 28 millimeters. Its motors and control system are located outside the robot and connected to it via flexible drive shafts, cables and tubes. “It is designed to be small enough to fit comfortably into an open mouth,” says Dr Yukiko Tomooka, first author of the paper in <em>IEEE Transactions on Medical Robotics and Bionics</em>, in which the research team presents the robot.</p>
<h4>Fewer appointments at the dentist</h4>
<p>The prototype, called “MIR” — short for “Miniature Intraoral Robot” — is designed to prepare teeth precisely according to a digital plan. The idea is that, after a scan during the first appointment, dentists could plan exactly how the robot should remove the tooth material and order the crown straight away, rather than waiting until a second appointment.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Tomooka_Dentalroboter_375x500.jpg" alt="" width="750" height="1000" class="alignnone size-full wp-image-220543" srcset="https://robohub.org/wp-content/uploads/2026/07/Tomooka_Dentalroboter_375x500.jpg 375w, https://robohub.org/wp-content/uploads/2026/07/Tomooka_Dentalroboter_375x500-319x425.jpg 319w" sizes="(max-width: 750px) 100vw, 750px" /><em>Dr Yukiko Tomooka mounting the dental robot on a model patient. Photo: University of Basel, Catherine Weyer.</em></p>
<h4>Remarkably precise dental robot</h4>
<p>The researchers tested their dental robot on tooth models made of synthetic resin and on a ceramic material with a hardness similar to that of tooth enamel. The robot prepares the tooth in two steps: first, it uses a wide drill to reduce the tooth surface, removing material from above. In the second step, a longer, thinner drill works on the sides of the tooth.</p>
<p>What is remarkable is how precisely the dental robot already works, even though it does not yet have any sensors to measure or even correct its position directly. In tests, the positional error was less than 0.2 millimeters, which will be further reduced after sensors are integrated into the system.</p>
<p>In addition to precision, the researchers are also measuring the forces generated during drilling. In the tests, these remained below five newtons, roughly equivalent to the gravitational force of a half-liter bottle of water. The team is also investigating the noise produced by the system in order to better assess its suitability for use in dental practice.</p>
<h4>Sensors and camera to follow</h4>
<p>Further work is still needed before MIR can be used in dental practices. As a next step, the researchers plan to integrate sensors and a camera into the robot so that the system can monitor its position and the progress of the treatment. “Even after a power outage, MIR would know where it is and where it needs to continue based on the sensor data,” explains research group leader Professor Georg Rauter. The aim is to achieve this without making the mini robot any larger.</p>
<p>Rauter’s team regularly works closely with practicing physicians and dentists to develop robots for medical applications. The dental robot was developed as part of an Innosuisse-funded project in collaboration with the Center for Dentistry at the University of Zurich, Basel-based Camlog Biotechnologies GmbH and the University of Bern.</p>
<h4>Read the work in full</h4>
<p><a href="https://ieeexplore.ieee.org/document/11478483" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Miniature Intraoral Robot (MIR) for Minimally Invasive Tooth Preparation</a>, <em>Yukiko Tomooka, Carina Schmidt, Jenni Hjerppe, Marc Balmer, Ronald Jung, Raphael Mohler, Ahmet Yildiz, Murali Karnam, Manuela Eugster, Georg Rauter</em>, IEEE Transactions on Medical Robotics and Bionics (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Pressure-free growing robots for soft medical robotics</title>
		<link>https://robohub.org/pressure-free-growing-robots-for-soft-medical-robotics/</link>
		
		<dc:creator><![CDATA[IEEE Robotics and Automation Society (RAS)]]></dc:creator>
		<pubDate>Thu, 23 Jul 2026 07:53:40 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[IEEE RAS]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220646</guid>

					<description><![CDATA[By Emmet Cole Researchers at the University of Leeds and collaborators from the University of California San Diego won the Best Paper Award at RoboSoft, the leading international conference focused on soft robotics research. Soft robotics is gaining attention in medical applications because compliant machines can interact more safely with delicate objects and complex anatomy. [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/Robosoft_BestPaper_FeatureArticle-1024x354.png" alt="" width="1024" height="354" class="alignnone size-large wp-image-220647" srcset="https://robohub.org/wp-content/uploads/2026/07/Robosoft_BestPaper_FeatureArticle-1024x354.png 1024w, https://robohub.org/wp-content/uploads/2026/07/Robosoft_BestPaper_FeatureArticle-425x147.png 425w, https://robohub.org/wp-content/uploads/2026/07/Robosoft_BestPaper_FeatureArticle-768x266.png 768w, https://robohub.org/wp-content/uploads/2026/07/Robosoft_BestPaper_FeatureArticle.png 1384w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p><strong>By Emmet Cole</strong></p>
<p>Researchers at the University of Leeds and collaborators from the University of California San Diego won the Best Paper Award at <a href="https://www.robosoft2026.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboSoft</a>, the leading international conference focused on soft robotics research. Soft robotics is gaining attention in medical applications because compliant machines can interact more safely with delicate objects and complex anatomy.</p>
<p>The award-winning paper describes a 1.8 mm soft growing robot that can be steered magnetically, sense its own shape in real time, and operate without internal pressure. These advances could help improve patient outcomes following minimally invasive procedures.</p>
<p>We spoke with lead author <a href="https://ieeexplore.ieee.org/author/37089513545" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Benjamin Calmé</a> about the team’s work.</p>
<hr>
<p><strong>Q:</strong> Congratulations to you and your team on winning the award. Before we get into the paper itself, could you tell readers a little about yourself and how you arrived in this field?</p>
<p><strong>Benjamin Calmé:</strong> My path into robotics is a bit unusual. I’m from France and I actually started with a medical degree. Over time I realized I was more interested in research than in day‑to‑day clinical practice. In France, if you want a research and teaching career in medicine, you’re expected to get an equivalent engineering degree as well. That’s what pushed me toward engineering—and from there into robotics.</p>
<p>That led me into robotics labs in Paris and Strasbourg, where I worked on medical robotic platforms for applications such as needle insertion inside MRI scanners and technologies to help runners reduce injury risk. Through those projects I fell in love with robotics.</p>
<p>Staying in medical robotics was a natural extension of my previous work. It’s also why I was hired in Leeds. That is, you need someone who can translate between surgeons and engineers. Surgeons know what they want clinically, engineers know how they want to solve the problem, and those views don’t always match. My role is often to say, “This is what the surgeon actually wants, and this is how we can realistically help.”</p>
<p>I also help when systems move toward pre-clinical testing: designing study protocols, discussing workflows with clinicians, and helping them understand how a new platform behaves compared with conventional tools.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/2Robosoft_BestPaper_FeatureArticle.png" alt="" width="824" height="493" class="alignnone size-full wp-image-220650" srcset="https://robohub.org/wp-content/uploads/2026/07/2Robosoft_BestPaper_FeatureArticle.png 824w, https://robohub.org/wp-content/uploads/2026/07/2Robosoft_BestPaper_FeatureArticle-425x254.png 425w, https://robohub.org/wp-content/uploads/2026/07/2Robosoft_BestPaper_FeatureArticle-768x459.png 768w" sizes="(max-width: 824px) 100vw, 824px" /></p>
<p><strong>Q:</strong> For readers outside soft robotics, what is a “growing robot”?</p>
<p><strong>Benjamin Calmé:</strong> It moves more like a plant than a traditional robot. Instead of pushing or dragging its whole body through the environment, it extends at the tip by bringing material from inside the robot outward. In effect, the robot grows into the space ahead of it.</p>
<p>We often call these ‘vine robots’ because the idea is inspired by climbing plants. The body is soft and compliant, so when it encounters obstacles, it can deform and follow paths of lower resistance.</p>
<p>That can be very useful inside the body, where space is constrained and tissues are delicate. Rather than forcing its way forward, the robot can adapt to the environment.</p>
<p><strong>Q:</strong> What problems does this work address?</p>
<p><strong>Benjamin Calmé:</strong> A central issue is friction. In many procedures, conventional flexible tools still rub against tissue as they are inserted and withdrawn. That can cause irritation or inflammation.</p>
<p>With a growing robot, the body sections already in place move far less because new material advances at the tip. That can significantly reduce friction along the path.</p>
<p>For patients, that can mean less discomfort and fewer side effects. It can also help clinicians attempt procedures in anatomical regions, such as the brain, where the margin for error is very small.</p>
<p><strong>Q:</strong> Your paper highlights pressure-free growth. Why is this important?</p>
<p><strong>Benjamin Calmé:</strong> Safety is one reason, and controllability is another.</p>
<p>Many earlier growing robots relied on internal air pressure. But if you are working in fluid-filled spaces near the spine, or inside blood vessels, introducing air because of a leak is unacceptable. By removing the need for internal pressure, that risk disappears.</p>
<p>There is also a practical control benefit. In some earlier prototypes, we used pressure to grow and magnetic fields to steer. That meant alternating between growth and steering steps rather than doing both together.</p>
<p>Now we can grow and steer simultaneously, which makes the system faster and more usable.</p>
<p><strong>Q:</strong> What is novel about your approach compared with previous systems?</p>
<p><strong>Benjamin Calmé:</strong> One key contribution is combining shape control and shape sensing in a structure that can still be miniaturized. Our current prototype has an outer diameter of just 1.8 mm. Many previous designs place separate actuators or sensors along the robot body. Those solutions can become slow, bulky, or difficult to shrink to catheter scale.</p>
<p>We instead embed magnetic functionality directly into the silicone body by mixing magnetic particles into the material, molding it, and then magnetizing regions in controlled directions.</p>
<p>You can think of that pattern as the robot’s magnetic DNA. When we apply an external magnetic field, the robot bends into predictable shapes. By tracking how those magnetized regions move, we can also estimate the robot’s shape in real time. So, with one integrated structure, we achieve both actuation and sensing.</p>
<p><strong>Q:</strong> How does the real-time shape control system operate?</p>
<p><strong>Benjamin Calmé:</strong> We first manufacture the internal tail section of the robot from silicone containing magnetic particles. That tail later everts and becomes the outer body as the robot grows.</p>
<p>Before that happens, we place the material in a coil and apply a strong magnetic field. By orienting the material carefully during magnetization, we assign different magnetic directions along its length and cross-section.</p>
<p>Once deployed, moving an external magnet around the robot creates specific deformations. Because the magnetic pattern is known, we can also infer shape as the robot moves, with sensing updates up to 500 Hz.</p>
<p>A subtle challenge was preventing unwanted attraction between inner and outer layers, which would increase friction. Designing patterns that gave useful control without causing sticking required significant optimization.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/3Robosoft_BestPaper_FeatureArticle.png" alt="" width="1016" height="380" class="alignnone size-full wp-image-220651" srcset="https://robohub.org/wp-content/uploads/2026/07/3Robosoft_BestPaper_FeatureArticle.png 508w, https://robohub.org/wp-content/uploads/2026/07/3Robosoft_BestPaper_FeatureArticle-425x159.png 425w" sizes="(max-width: 1016px) 100vw, 1016px" /></p>
<p><strong>Q:</strong> The paper also demonstrates retroflexion and biome sampling in an ex vivo stomach model. Why are those meaningful milestones?</p>
<p><strong>Benjamin Calmé:</strong> Retroflexion and biopsy in an ex vivo stomach are important because they show the robot can perform endoscopic maneuvers in a realistic anatomy, not just in bench-top tests. Retroflexion proves it can safely reach difficult angles without the high friction and tissue stress of conventional scopes, and successful sampling shows it can precisely position tools and carry out a core clinical task. Together, they’re a first demonstration that this pressure-free growing robot can do meaningful work in settings that resemble actual medical procedures.</p>
<p><strong>Q:</strong> What were the biggest engineering hurdles?</p>
<p><strong>Benjamin Calmé:</strong> Manufacturing at this scale was a major challenge. Our catheter has an outer diameter of about 1.8 mm, with wall thickness near 100 microns.</p>
<p>That required careful control of injection molding, vacuum processes, particle distribution, and defect prevention. Tiny bubbles or inconsistencies can affect both mechanical performance and magnetic behavior.</p>
<p><strong>Q:</strong> What comes next, and how close is clinical use?</p>
<p><strong>Benjamin Calmé:</strong> We are especially interested in neural and spinal applications, where precise placement of electrodes could help restore function after injury.</p>
<p>We are still early in development. A realistic near-term target is robust pre-clinical performance: safety, biocompatibility, and successful in-vivo demonstrations.</p>
<p>Clinical adoption takes much longer because regulation must be rigorous. That is appropriate when patient safety is involved.</p>
<p><strong>Q:</strong> How would you explain this advance to a non-technical person?</p>
<p><strong>Benjamin Calmé:</strong> I sometimes use the image of brain surgery done with chopsticks. Right now, your surgeon is often working around the most sensitive parts of your body with rigid tools that must be manipulated with extreme care. We’re trying to replace those chopsticks with a softer, more precise, less dangerous tool.</p>
<p>This soft growing robot can be very small and dexterous. It can reduce some types of human error, like tremor, and it doesn’t take much space, so there’s more room for other instruments and better imaging. Surgeons can also see and reach regions that used to be in blind spots.</p>
<p>In the simplest terms, we’re developing a new class of soft, growing robotic tools that can sneak into delicate spaces in the body, minimize damage along the way, and give surgeons more control and information than they have with today’s rigid instruments.</p>
<hr>
<p><em>The paper, <a href="https://ieeexplore.ieee.org/document/11522898" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">&#8220;Pressure-free Magnetic Soft Growing Robot with Real-Time Shape Control and Sensing for Biome Sampling,&#8221;</a> appears in the proceedings of the 2026 IEEE 9th International Conference on Soft Robotics (RoboSoft).</em></p>
<hr>
<p>This article originally appeared on <a href="https://www.ieee-ras.org/category/ras-feature/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">IEEE RAS</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Interactive world simulator for robot policy training and evaluation</title>
		<link>https://robohub.org/interactive-world-simulator-for-robot-policy-training-and-evaluation/</link>
		
		<dc:creator><![CDATA[Yixuan Wang]]></dc:creator>
		<pubDate>Mon, 20 Jul 2026 08:39:44 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20554</guid>

					<description><![CDATA[Imagine you want to teach a robot to push an object on a table. The standard recipe in robot learning is to collect hundreds of expert demonstrations on a real robot, train an imitation learning policy on that data, and then evaluate the policy by running it many times on the same real robot. Both […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" class="alignnone  wp-image-20819" src="https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-300x161.png" alt="" width="922" height="495" srcset="https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-300x161.png 300w, https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-1024x550.png 1024w, https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-768x413.png 768w, https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-1536x825.png 1536w, https://aihub.org/wp-content/uploads/2026/07/Screenshot-2026-07-17-at-17.20.49-2048x1101.png 2048w" sizes="(max-width: 922px) 100vw, 922px" /><br />
Imagine you want to teach a robot to push an object on a table. The standard recipe in robot learning is to collect hundreds of expert demonstrations on a real robot, train an imitation learning policy on that data, and then evaluate the policy by running it many times on the same real robot. Both stages (data collection and evaluation) are slow, expensive, and hard to reproduce: hardware breaks, lighting changes, objects drift out of place, and every new task means more hours in the lab.</p>
<p>A natural question is whether we can replace some of this real-robot work with a simulator. Classical physics-based simulators are powerful, but building one for a new task means manually modeling geometries, contacts, friction, and deformation, and the resulting simulator often still does not match reality closely enough for policies trained inside it to transfer.</p>
<p>In our work, we take a different route. We build an <a href="https://arxiv.org/abs/2603.08546" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Interactive World Simulator</a>: a learned, action-conditioned video prediction model that, given the current image and a sequence of robot actions, predicts the next frames purely in pixel space, with no physics engine inside. You can plug in a teleoperation device and control the robot through this learned world model for more than 10 minutes at 15 FPS on a single RTX 4090, and the predicted video stays stable and physically plausible.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-3" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_1.mp4?_=3" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_1.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_1.mp4</a></video></div></p>
<p>The key idea is that, if the simulator is faithful enough, we could unlock two long-standing bottlenecks in robot learning:</p>
<p>&#8211; Data generation for training becomes cheap, because we can collect demonstrations inside the simulator.<br />
&#8211; Policy evaluation becomes scalable and reproducible, because we can roll many policies through the simulator under identical conditions.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-4" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_2.mp4?_=4" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_2.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_2.mp4</a></video></div></p>
<p><strong>What the world simulator can do</strong><br />
We trained our world simulator on four manipulation tasks that span very different physical regimes: T pushing (rigid-body contact), rope routing (deformable–rigid interaction with a clip), mug grasping (fine-grained gripper dynamics), and pile sweeping (manipulating piles of objects). All four behaviors are learned from interaction data alone, with no physics priors hard-coded.</p>
<p>A few examples of what the model captures:</p>
<p>Rope routing: it correctly distinguishes between the rope actually being inserted into the clip and the rope swinging past it without making contact. Crucially, it does not bias toward either outcome — it follows what the actions imply.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-5" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_5.mp4?_=5" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_5.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_5.mp4</a></video></div></p>
<p>Mug grasping: it captures fine-grained effects such as the mug slipping out of the gripper, or the handle being nudged and rotated.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-6" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_6.mp4?_=6" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_6.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_6.mp4</a></video></div></p>
<p>Pile sweeping: it can generate video for multiple viewpoints consistently</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-7" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_8.mp4?_=7" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_8.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_8.mp4</a></video></div></p>
<p>You can try this directly on our <a href="http://yixuanwang.me/interactive_world_sim/#long-interaction" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">project page</a>: just open a browser and play with it using your keyboard!</p>
<p><strong>How we built the interactive world simulator</strong></p>
<p>At a high level, Interactive World Simulator is trained in two stages. First, we trained an autoencoder that compresses RGB images into compact 2D latent representations and reconstructs them back into images. This lets the model reason in a lower-dimensional space while still producing high-fidelity pixel-level outputs.</p>
<p>Second, we froze this autoencoder and trained an action-conditioned dynamics model in the latent space. Given past visual latents and robot actions, the model predicts the next latent state, which is then decoded back into an image. At inference time, this process is repeated autoregressively: predicted frames become part of the context for predicting future frames. Because prediction happens in latent space and uses consistency models, the simulator can run interactively while remaining stable over long horizons.</p>
<p><strong>How is it different from prior works?</strong></p>
<p>This differs from several existing approaches to robot simulation and world modeling. Classical physics simulators can be powerful, but they often require manually specifying object geometry, contact dynamics, friction, and deformation, and the resulting simulation may still have a large sim-to-real gap. Recent video-generation and world-model methods offer a more data-driven alternative, but many are either not explicitly conditioned on robot actions, too slow for real-time interaction, closed-source, or unstable under long-horizon rollouts.</p>
<p>In contrast, our Interactive World Simulator is action-conditioned, produces physically accurate pixel-level predictions, and supports stable interactions for more than 10 minutes at 15 FPS on a single consumer RTX 4090 GPU. This makes it practical not only as a visual prediction model, but as an interactive engine for collecting policy-training data and evaluating robot policies reproducibly. It has multiple applications.</p>
<p><strong>Application 1: scalable data generation</strong></p>
<p>If our simulator is good enough, can demonstrations collected using this world model actually replace real demonstrations for training imitation learning policies?</p>
<p>To answer this, we collected demonstrations entirely inside our world simulator and then trained imitation learning policies on 0% real-world data and 100% generated data. We deployed the trained policies directly on the real robot. The deployed policies do not just complete the tasks. They remain robust under continuous human perturbations. This demonstrates that the generated data quality is comparable to real data.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-8" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_4.mp4?_=8" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_4.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_4.mp4</a></video></div></p>
<p><strong>Application 2: faithful policy evaluation</strong></p>
<p>Evaluating a robot policy in the real world is hard: you need to reset the scene, rerun the policy many times, and compare across checkpoints under matched conditions. In practice, this is not scalable and reproducible.</p>
<p>In contrast, we could roll out policies in our world model for reproducible evaluation. We evaluated the same four policies (DP, ACT, π0, π0.5) inside the simulator and on the real robot, with the same initial configurations. Each point in our evaluation is a policy checkpoint, scored in both real world and world model. We observe a strong correlation between the two scores, across tasks and across policies. Qualitatively, good policies that succeed in the simulator also succeed on the real robot, and bad policies that fail in the simulator also fail on the real robot.</p>
<p><div style="width: 1920px;" class="wp-video"><video class="wp-video-shortcode" id="video-220616-9" width="1920" height="1080" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/twitter_9.mp4?_=9" /><a href="https://aihub.org/wp-content/uploads/2026/07/twitter_9.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/twitter_9.mp4</a></video></div></p>
<p><strong>Looking forward</strong></p>
<p>Action-conditioned video prediction has long shown great potential for robotics, but existing approaches have been either too slow for interactive use or too brittle under long-horizon inference. By addressing both of these — stability and computational efficiency — the Interactive World Simulator becomes a practical engine for two things at once: training imitation policies on simulator-generated data that perform comparably to those trained on real-world demonstrations, and evaluating policies in a way that closely tracks real-world performance.</p>
<p>Going forward, we will extend the framework to more diverse environments and increasingly complex manipulation tasks, to further unlock the potential of large-scale robotic data. An important direction for future work is to study how the performance of world models scales with increasing amounts of interaction data and computational resources. Understanding these scaling behaviors could guide the design of larger and more capable world models for robotics.</p>
]]></content:encoded>
					
		
		<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_1.mp4" length="5248255" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_2.mp4" length="15191375" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_5.mp4" length="11353209" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_6.mp4" length="4947759" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_8.mp4" length="4932996" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_4.mp4" length="13094173" type="video/mp4" />
<enclosure url="https://aihub.org/wp-content/uploads/2026/07/twitter_9.mp4" length="5947974" type="video/mp4" />

			</item>
		<item>
		<title>Undergrads’ weed-killing robot wins top prize</title>
		<link>https://robohub.org/undergrads-weed-killing-robot-wins-top-prize/</link>
		
		<dc:creator><![CDATA[Cornell University]]></dc:creator>
		<pubDate>Fri, 17 Jul 2026 10:15:46 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220552</guid>

					<description><![CDATA[Andrew James (from left), Neil Morrison, Natalia Kurz and Michael Neiss work on a prototype of their weed-killing robot ahead of The Farm Robotics Challenge, which they won on May 21. By Holly Hartigan A team of Cornell undergraduates beat 95 other teams to take the grand prize at The Farm Robotics Challenge with their [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/0n7a0022-a.jpg" alt="" width="670" height="377" class="alignnone size-full wp-image-220553" srcset="https://robohub.org/wp-content/uploads/2026/07/0n7a0022-a.jpg 670w, https://robohub.org/wp-content/uploads/2026/07/0n7a0022-a-425x239.jpg 425w" sizes="(max-width: 670px) 100vw, 670px" /><em>Andrew James (from left), Neil Morrison, Natalia Kurz and Michael Neiss work on a prototype of their weed-killing robot ahead of The Farm Robotics Challenge, which they won on May 21.</em></p>
<p><strong>By Holly Hartigan</strong></p>
<p>A team of Cornell undergraduates beat 95 other teams to take the grand prize at <a href="https://www.farmroboticschallenge.ai/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">The Farm Robotics Challenge</a> with their invention: an autonomous robot that kills weeds with electricity.</p>
<p>Their robot can travel through a vineyard or orchard without a human operator, zapping weeds with a small amount of electricity, saving labor and energy and preventing crop loss, without the use of herbicides.</p>
<p>Led by Andrew James, an agricultural sciences major in the College of Agriculture and Life Sciences (CALS), the team of agricultural specialists and engineers studied the existing electrical weeding technology, developed their own low-energy system and built a working prototype over the course of four intense months.</p>
<p>Natalia Kurz, a biological engineering major in CALS, said the project required a lot of late nights. “There were fears for us, like, was it just going to be for nothing?”</p>
<p>Now, James and his co-founders are using the $50,000 grand prize to form a company – Rootline Robotics – to continue working on the robot. Agricultural technology firm Reservoir sponsored the award and will host the startup at its incubator in Sonoma, California.</p>
<p>“I’ve always been interested in building a startup within the ag-robotics space,” James said. “So after winning this competition and seeing all the amazing support from so many different industry stakeholders in this really exciting collaboration, it makes a lot of sense to keep going.”</p>
<h4>The problem of weeds</h4>
<p>Weeds are a huge challenge in orchards and vineyards because they steal water and nutrients, especially in the spring, according to Steve Selin, owner of South Hill Cider in Ithaca. </p>
<p>“The weed pressure is very strong, and the grasses grow right up to the trees because we can’t afford to weed whack or mulch them as much as we would like to in order to control them,” he said. “If the trees get really stressed out, they’ll just drop the fruit.”</p>
<p>To control weeds, organic growers typically employ string trimming, mowing and mulching, which are all very labor intensive. Existing electric weeders require an operator, consume a lot of energy and cost $150,000, on average, which is out of reach for most growers, James said. </p>
<p>Selin provided feedback to the students as they developed their robot and said he is excited to try out Rootline’s new technology. </p>
<p>“In May and June, if you could do something to knock the weeds back enough that they’re not going to compete with the trees, then the rest of the year you wouldn’t have to worry about it,” he said. “You can let them come back and have positive impacts, like shading the soil, which would help the soil microbes to have a healthier ecosystem.”</p>
<h4>The interdisciplinary nature of robots</h4>
<p>“Robotics is many different systems in one,” Kurz said. “It is interdisciplinary by definition.”</p>
<p>Next, the Rootline team will work on improving its technology and validating it with growers before bringing it to market, all while Kurz and Neiss finish their degrees.</p>
<p>Neiss said the way the team came together felt a bit like destiny. </p>
<p>“If you have many different minds in one room that gives you the ability to reach solutions that are going to be the most feasible and effective,” he said.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>A flapping robot swims and flies like a diving bird</title>
		<link>https://robohub.org/a-flapping-robot-swims-and-flies-like-a-diving-bird/</link>
		
		<dc:creator><![CDATA[EPFL]]></dc:creator>
		<pubDate>Wed, 15 Jul 2026 10:03:17 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220573</guid>

					<description><![CDATA[Image copyright: Raphael Zufferey. By Jennifer Chu Loons, gulls, puffins, and petrels are some of the 100 species of birds that can both fly and swim. These diving birds can plunge in water to swim after prey, and then leap back into the air to fly away. Now, inspired by these naturally aquatic aviators, engineers [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/3840x2160-1024x576.jpg" alt="" width="1024" height="576" class="alignnone size-large wp-image-220574" srcset="https://robohub.org/wp-content/uploads/2026/07/3840x2160-1024x576.jpg 1024w, https://robohub.org/wp-content/uploads/2026/07/3840x2160-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/3840x2160-768x432.jpg 768w, https://robohub.org/wp-content/uploads/2026/07/3840x2160-1536x864.jpg 1536w, https://robohub.org/wp-content/uploads/2026/07/3840x2160-2048x1152.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Image copyright: Raphael Zufferey</em>.</p>
<p><strong>By Jennifer Chu</strong></p>
<p>Loons, gulls, puffins, and petrels are some of the 100 species of birds that can both fly and swim. These diving birds can plunge in water to swim after prey, and then leap back into the air to fly away. Now, inspired by these naturally aquatic aviators, engineers at EPFL and MIT have designed a robot that can swim underwater, and flap out of the water to continue flying through air, much like diving birds.</p>
<p>The “flapping-wing aerial-aquatic vehicle,” or FAAV, weighs less than 300 grams and is designed to help scientists study the mechanics that enable diving birds to fly through air and water. The robot has a central body, or fuselage, two flexible, flapping wings, and a steerable tail. The wings and tail can be swapped out for different sizes. In experiments carried out in a water tank and a lake, the engineers identified combinations of wing size, flapping frequency, and tail angle that enable the robot to smoothly transition from swimming through water, to breaking through the surface, to flying through the air.</p>
<div class="keep-aspect"><iframe title="Puffin-Inspired Robot that Swims and Flies" width="500" height="281" src="https://www.youtube-nocookie.com/embed/9XJhrKpcBGI?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Their results, published in <a href="https://www.science.org/doi/10.1126/science.aeb6744" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Science</a>, can help scientists understand how diving birds adapt their flight mechanics to move through air and water, which have very different physical properties. The design could also launch a new class of aerial-aquatic drones and vehicles. The researchers envision such winged robots could be deployed to fly to and sample from aquatic regions that would otherwise be too dangerous for traditional ocean vessels to access.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/6048x2571-1024x435.jpg" alt="" width="1024" height="435" class="alignnone size-large wp-image-220575" srcset="https://robohub.org/wp-content/uploads/2026/07/6048x2571-1024x435.jpg 1024w, https://robohub.org/wp-content/uploads/2026/07/6048x2571-425x181.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/6048x2571-768x326.jpg 768w, https://robohub.org/wp-content/uploads/2026/07/6048x2571-1536x653.jpg 1536w, https://robohub.org/wp-content/uploads/2026/07/6048x2571-2048x871.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Image copyright: Raphael Zufferey</em>.</p>
<p>“Our dream vision is for oceanographers, marine biologists and coastal communities to launch this robot from a boat, or from shore, and it would fly close to the area of interest, such as an iceberg, a port facility or over a pod of whales,” says lead author and former EPFL researcher Raphael Zufferey, now an assistant professor of mechanical engineering at MIT. “It would dive into the water to take a measurement or collect a sample, and fly back to deliver the data at a fraction of the cost of traditional methods. Then it could go back out to dive for more.”</p>
<h4>Flight mechanics</h4>
<p>Zufferey began working on the robot as a postdoctoral fellow in the Laboratory of Intelligent Systems (<a href="https://www.epfl.ch/labs/lis/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">LIS</a>) and Biorobotics Lab (<a href="https://www.epfl.ch/labs/biorob/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">BioRob</a>) in EPFL’s School of Engineering, under the supervision of respective lab heads and co-authors Dario Floreano and Auke Ijspeert. He completed the work at MIT, where he now leads the <a href="https://aura.mit.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">AURA Lab</a>, which focuses on engineering bioinspired aerial and aquatic vehicles. The study also includes co-authors from Northwest Indian College (USA).</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/f04eb66b-1024x766.jpg" alt="" width="1024" height="766" class="alignnone size-large wp-image-220576" srcset="https://robohub.org/wp-content/uploads/2026/07/f04eb66b-1024x766.jpg 1024w, https://robohub.org/wp-content/uploads/2026/07/f04eb66b-425x318.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/f04eb66b-768x575.jpg 768w, https://robohub.org/wp-content/uploads/2026/07/f04eb66b-1536x1150.jpg 1536w, https://robohub.org/wp-content/uploads/2026/07/f04eb66b-2048x1533.jpg 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>With bird biomechanics in mind, the team developed a robot with wings made of thin membranes coated with hydrophobic nanoparticles to help wick away water. The body contains a battery and a waterproof electric motor that drives a crankshaft, which in turn pumps the wings up and down at pre-set frequencies. The tail is motorized, enabling it to change its angle to help the robot fly up or dive down.</p>
<p>The researchers performed experiments first in a small water tank at EPFL, and then in Lake Geneva. They found that wing size (80 centimeters) and flexibility are key; the wings need to be flexible enough to minimize flapping amplitude in water, and firm enough to keep the robot aloft in the air. The robot could swim at speeds of almost one meter per second when it flapped with a frequency of around 5 hertz (five flaps per second), and fly at around 6 meters per second when flapping at a similar frequency. These speeds and flapping frequencies are similar to those of actual diving birds. To make the leap from water to air, the robot must be pitched at a relatively steep 70 degrees to keep its wingtips from touching the water’s surface.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/07/6c673685-1024x576.jpg" alt="" width="1024" height="576" class="alignnone size-large wp-image-220577" srcset="https://robohub.org/wp-content/uploads/2026/07/6c673685-1024x576.jpg 1024w, https://robohub.org/wp-content/uploads/2026/07/6c673685-425x239.jpg 425w, https://robohub.org/wp-content/uploads/2026/07/6c673685-768x432.jpg 768w, https://robohub.org/wp-content/uploads/2026/07/6c673685-1536x864.jpg 1536w, https://robohub.org/wp-content/uploads/2026/07/6c673685.jpg 1920w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Image copyright: Raphael Zufferey</em>.</p>
<h4>Like a bird, but without feet</h4>
<p>Interestingly, this combination of wing size, flap frequency, and tail pitch enabled the robot to swim underwater, launch off the surface, and fly without something that many diving birds require: feet. “If you look at birds, most birds need to paddle their feet at the surface to take off. And the question was, do we need the same for robots? And it turns out we don’t,” Zufferey says. “No one’s been able to fly out of the water with wings.”</p>
<p>Going forward, the team is improving the design of the wings to enable them to turn in addition to flapping up and down. They will also test the robot’s performance under turbulent conditions, such as swimming out of choppy waters, and flying through wind. Then, they hope to deploy the vehicle to help answer questions in ocean science.</p>
<h4>Reference</h4>
<p><a href="https://www.science.org/doi/10.1126/science.aeb6744" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Leaping out of the water: Aerial-aquatic locomotion with flapping wings</a>, <em>Raphael Zufferey, Simon L. Jeger, Moritz Hüsser, Fernando Ruiz, Anthony Lapsansky, Auke Ijspeert, Dario Floreano</em>, Science (2026).</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Wristband enables wearers to control a robotic hand with their own movements</title>
		<link>https://robohub.org/wristband-enables-wearers-to-control-a-robotic-hand-with-their-own-movements/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Mon, 13 Jul 2026 08:27:45 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://news.mit.edu/2026/wristband-enables-wearers-control-robotic-hand-with-own-movements-0325</guid>

					<description><![CDATA[By moving their hands and fingers, users can direct a robot to play piano or shoot a basketball, or they can manipulate objects in a virtual environment.]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-01-press_0.jpg" alt="" width="900" height="600" class="alignnone size-full wp-image-220100" srcset="https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-01-press_0.jpg 900w, https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-01-press_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-01-press_0-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /><em>Graduate student Dian Li working with a robotic hand. Credit: Melanie Gonick.</em></p>
<p><strong>By Jennifer Chu</strong></p>
<p>The next time you’re scrolling your phone, take a moment to appreciate the feat: The seemingly mundane act is possible thanks to the coordination of 34 muscles, 27 joints, and over 100 tendons and ligaments in your hand. Indeed, our hands are the most nimble parts of our bodies. Mimicking their many nuanced gestures has been a longstanding challenge in robotics and virtual reality.</p>
<p>Now, MIT engineers have designed an ultrasound wristband that precisely tracks a wearer’s hand movements in real-time. The wristband produces ultrasound images of the wrist’s muscles, tendons, and ligaments as the hand moves, and is paired with an artificial intelligence algorithm that continuously translates the images into the corresponding positions of the five fingers and palm.</p>
<p>The researchers can train the wristband to learn a wearer’s hand motions, which the device can communicate in real-time to a robot or a virtual environment.</p>
<p>In demonstrations, the team has shown that a person wearing the wristband can wirelessly control a robotic hand. As the person gestures or points, the robot does the same. In a sort of wireless marionette interaction, the wearer can manipulate the robot to play a simple tune on the piano and shoot a small basketball into a desktop hoop. With the same wristband, a wearer can also manipulate objects on a computer screen, for instance pinching their fingers together to enlarge and minimize a virtual object.</p>
<div class="keep-aspect"><iframe title="A real-time hand tracker" width="500" height="281" src="https://www.youtube-nocookie.com/embed/F2HaSoladgM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The team is using the wristband to gather hand motion data from many more users with different hand sizes, finger shapes, and gestures. They envision building a large dataset of hand motions that can be plumbed, for instance, to train humanoid robots in dexterity tasks, such as performing certain surgical procedures. The ultrasound band could also be used to grasp, manipulate, and interact with objects in video games, design applications, or other virtual settings.</p>
<p>“We think this work has immediate impact in potentially replacing hand tracking techniques with wearable ultrasound bands in virtual and augmented reality,” says Xuanhe Zhao, the Uncas and Helen Whitaker Professor of Mechanical Engineering at MIT. “It could also provide huge amounts of training data for dexterous humanoid robots.”</p>
<p>Zhao, Gengxi Lu, and their colleagues present the wristband’s new design in a <a href="https://www.nature.com/articles/s41928-026-01594-4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">paper which appeared</a> in <em>Nature Electronics.</em> Their MIT co-authors are former postdocs Xiaoyu Chen, Shucong Li, and Bolei Deng; graduate students SeongHyeon Kim and Dian Li; postdocs Shu Wang and Runze Li; and Anantha Chandrakasan, MIT provost and the Vannevar Bush Professor of Electrical Engineering and Computer Science. Other co-authors are graduate students Yushun Zheng and Junhang Zhang, Baoqiang Liu, Chen Gong, and Professor Qifa Zhou from the University of Southern California.</p>
<p><strong>Seeing strings</strong></p>
<p>There are currently a number of approaches to capturing and mimicking human hand dexterity in robots. Some approaches use cameras to record a person’s hand movements as they manipulate objects or perform tasks. Others involve having a person wear a glove with sensors, which records the person’s hand movements and transmits the data to a receiving robot. But erecting a complex camera system for different applications is impractical and prone to visual obstacles. And sensor-laden gloves could limit a person’s natural hand motions and sensations.</p>
<p>A third approach uses the electrical signals from muscles in the wrist or forearm that scientists then correlate with specific hand movements. Researchers have made significant advances in this approach, however these signals are easily affected by noise in the environment. They are also not sensitive enough to distinguish subtle changes in movements. For instance, they may discern whether a thumb and index finger are pinched together or pulled apart, but not much of the in-between path.</p>
<p>Zhao’s team wondered whether ultrasound imaging might capture more dexterous and continuous hand movements. His group has been developing various forms of ultrasound stickers — miniaturized versions of the transducers used in doctor’s offices that are paired with hydrogel material that can safely stick to skin.</p>
<p>In their new study, the team incorporated the ultrasound sticker design into a wearable wristband to continuously image the muscles and tendons in the wrist.</p>
<p>“The tendons and muscles in your wrist are like strings pulling on puppets, which are your fingers,” Lu says. “So the idea is: Each time you take a picture of the state of the strings, you’ll know the state of the hand.”</p>
<p><strong>Mapping manipulation</strong></p>
<p>The team designed a wristband with an ultrasound sticker that is the size of a smartwatch, and added onboard electronics that are about as small as a cellphone. They attached the wristband to a volunteer’s wrist and confirmed that the device produced clear and continuous images of the wrist as the volunteer moved their fingers in various gestures.</p>
<p>The challenge then was to relate the black and white ultrasound images of the wrist to specific positions of the hand. As it turns out, the fingers and thumb are capable of 22 degrees of freedom, or different ways of extending or angling. The researchers found that they could identify specific regions in their ultrasound images of the wrist that correlate to each of these 22 degrees of freedom. For instance, changes in one region relate to thumb extension, while changes in another region correlate with movements of the index finger.</p>
<p>To establish these connections, a volunteer wearing the wristband would move their hand in various positions while the researchers recorded the gestures with multiple cameras surrounding the volunteer. By matching changes in certain regions of the ultrasound images with hand positions recorded by the cameras, the team could label wrist image regions with the corresponding degree of freedom in the hand. But to do this translation continuously, and in real-time, would be an impossible task for humans.</p>
<p>So, the team turned to artificial intelligence. They used an AI algorithm that can be trained to recognize image patterns and correlate them with specific labels and, in this case, the hand’s various degrees of freedom. The researchers trained the algorithm with ultrasound images that they meticulously labeled, annotating the image regions associated with a specific degree of freedom. They tested the algorithm on a new set of ultrasound images and found it correctly predicted the corresponding hand gestures.</p>
<p>Once the researchers successfully paired the AI algorithm with the wristband, they tested the device on more volunteers. For the new study, eight volunteers with different hand and wrist sizes wore the wristband while they formed various hand gestures and grasps, including making the signs for all 26 letters in American Sign Language. They also held objects such as a tennis ball, a plastic bottle, a pair of scissors, and a pencil. In each case, the wristband precisely tracked and predicted the position of the hand.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-02-press.jpg" alt="" width="900" height="600" class="alignnone size-full wp-image-220101" srcset="https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-02-press.jpg 900w, https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-02-press-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/03/MIT-Hand-Tracker-02-press-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /><em>MIT engineers have designed an ultrasound wristband that precisely tracks a wearer’s hand movements in real time. The wristband produces ultrasound images of the wrist’s muscles, tendons, and ligaments as the hand moves. Credit: Melanie Gonick.</em></p>
<p>To demonstrate potential applications, the team developed a simple computer program that they wirelessly paired with the wristband. As a wearer went through the motions of pinching and grasping, the gestures corresponded to zooming in and out on an object on the computer screen, and virtually moving and manipulating it in a smooth and continuous fashion.</p>
<p>The researchers also tested the wristband as a wireless controller of a simple commercial robotic hand. While wearing the wristband, a volunteer went through the motions of playing a keyboard. The robot in turn mimicked the motions in real-time to play a simple tune on a piano. The same robot was also able to mimic a person’s finger taps to play a desktop basketball game.</p>
<p>Zhao is planning to further miniaturize the wristband’s hardware, as well as train the AI software on many more gestures and movements from volunteers with wider ranging hand sizes and shapes. Ultimately, the team is building toward a wearable hand tracker that can be worn by anyone, to wirelessly manipulate humanoid robots or virtual objects with high dexterity.</p>
<p>“We believe this is the most advanced way to track dexterous hand motion, through wearable imaging of the wrist,” Zhao says. “We think these wearable ultrasound bands can provide&nbsp;intuitive and versatile controls for virtual reality and robotic hands.”</p>
<p>This research was supported, in part, by MIT, the U.S. National Institutes of Health, the U.S. National Science Foundation, the U.S. Department of Defense, and&nbsp;Singapore National Research Foundation through the Singapore-MIT Alliance for Research and Technology.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>#RoboCup2026 social media round-up</title>
		<link>https://robohub.org/robocup2026-social-media-round-up/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Wed, 08 Jul 2026 06:56:38 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<category><![CDATA[RoboCup2026]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20640</guid>

					<description><![CDATA[This year, RoboCup took place in Incheon, South Korea, from 2-6 July. The event saw teams take part in competitions, training sessions, and a symposium. Take a look at what the participants got up to in our round up from social media. The wait is over! 🤖🎉 RoboCup 2026 officially begins today! Join us for […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28.jpeg" alt="" width="1854" height="966" class="alignnone size-full wp-image-20407" srcset="https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28.jpeg 1854w, https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28-300x156.jpeg 300w, https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28-1024x534.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28-768x400.jpeg 768w, https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28-1536x800.jpeg 1536w" sizes="(max-width: 1854px) 100vw, 1854px" /></p>
<p>This year, <a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup</a> took place in Incheon, South Korea, from 2-6 July. The event saw teams take part in competitions, training sessions, and a symposium. Take a look at what the participants got up to in our round up from social media.</p>
<blockquote class="twitter-tweet">
<p lang="en" dir="ltr">The wait is over! <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f916.png" alt="&#x1f916;" class="wp-smiley" style="height: 1em; max-height: 1em;" /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f389.png" alt="&#x1f389;" class="wp-smiley" style="height: 1em; max-height: 1em;" /></p>
<p>RoboCup 2026 officially begins today!</p>
<p>Join us for an exciting first day!</p>
<p><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f4cd.png" alt="&#x1f4cd;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Incheon Convention Center (Songdo Convensia)</p>
<p>For the full schedule, visit:<br /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f517.png" alt="&#x1f517;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> <a href="https://t.co/T5mjdVMhH3" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://t.co/T5mjdVMhH3</a><a href="https://x.com/hashtag/RoboCup2026?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup2026</a> <a href="https://x.com/hashtag/RoboCup?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup</a> <a href="https://x.com/hashtag/Robotics?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Robotics</a> <a href="https://x.com/hashtag/AI?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#AI</a> <a href="https://t.co/wHZkfM69jL" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">pic.twitter.com/wHZkfM69jL</a></p>
<p>&mdash; RoboCup Federation (@robocup_org) <a href="https://x.com/robocup_org/status/2072455369624781311?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">July 1, 2026</a></p>
</blockquote>
<p> <script async src="https://platform.x.com/widgets.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaMeFW6E9cy/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaMeFW6E9cy/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaMeFW6E9cy/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by RoboCup Federation (@robocup.official)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaKsvhnziqu/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaKsvhnziqu/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaKsvhnziqu/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by BerlinUnited (@berlin_united_robocup)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="twitter-tweet">
<p lang="en" dir="ltr">Can&#39;t make it to Incheon? We&#39;ve got you covered! <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f916.png" alt="&#x1f916;" class="wp-smiley" style="height: 1em; max-height: 1em;" /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f3a5.png" alt="&#x1f3a5;" class="wp-smiley" style="height: 1em; max-height: 1em;" /></p>
<p>Starting July 2, follow all the excitement of RoboCup 2026 live from anywhere in the world!</p>
<p><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f4fa.png" alt="&#x1f4fa;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Where to watch:<br /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/25b6.png" alt="&#x25b6;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> YouTube: <a href="https://x.com/Robocup?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">@RoboCup</a><br /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f3ae.png" alt="&#x1f3ae;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Twitch: robocupofficial<a href="https://x.com/hashtag/RoboCup2026?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup2026</a> <a href="https://x.com/hashtag/RoboCup?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup</a> <a href="https://x.com/hashtag/LiveStreaming?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#LiveStreaming</a> <a href="https://x.com/hashtag/Robotics?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Robotics</a> <a href="https://x.com/hashtag/AI?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#AI</a> <a href="https://x.com/hashtag/Incheon?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Incheon</a> <a href="https://t.co/p3wm8mr3CV" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">pic.twitter.com/p3wm8mr3CV</a></p>
<p>&mdash; RoboCup Federation (@robocup_org) <a href="https://x.com/robocup_org/status/2072110374279692634?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">July 1, 2026</a></p>
</blockquote>
<p> <script async src="https://platform.x.com/widgets.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaXeou8gdSG/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaXeou8gdSG/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaXeou8gdSG/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by RoboCupJunior Egypt (@rcjegypt)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="bluesky-embed" data-bluesky-uri="at://did:plc:sw5vvo3a6eozbv6f27kmxyil/app.bsky.feed.post/3mpx7l7xcnk2m" data-bluesky-cid="bafyreib6m2xzzyrh7nfnto3ox45syd4hc42itswjevdxt2fyr7akht4itm" data-bluesky-embed-color-mode="system">
<p lang="en">Little Booster K1, trying to get up after falling mid football game!<br />
#robocup2026</p>
<p><a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil/post/3mpx7l7xcnk2m?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">[image or embed]</a></p>
<p>&mdash; Raghav Arora (<a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">@ra-aurora.bsky.social</a>) <a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil/post/3mpx7l7xcnk2m?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">6 July 2026 at 05:05</a></p>
</blockquote>
<p><script async src="https://embed.bsky.app/static/embed.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaV_gYPkqJO/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaV_gYPkqJO/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaV_gYPkqJO/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by Colegio Leonardo Da Vinci (@davinci_colegio)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaXUn5aGaBg/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaXUn5aGaBg/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaXUn5aGaBg/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by Tech United (@techunitedeindhoven)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="twitter-tweet">
<p lang="en" dir="ltr"><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/26bd.png" alt="&#x26bd;" class="wp-smiley" style="height: 1em; max-height: 1em;" /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f916.png" alt="&#x1f916;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> Big win at <a href="https://x.com/hashtag/RoboCup2026?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup2026</a>! </p>
<p>4 Mini Pi plus teams reached the Top 8, with Hamburg Bit-Bots taking <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f948.png" alt="&#x1f948;" class="wp-smiley" style="height: 1em; max-height: 1em;" />. </p>
<p>Open platforms accelerate robotics. <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f680.png" alt="&#x1f680;" class="wp-smiley" style="height: 1em; max-height: 1em;" /> <a href="https://x.com/hashtag/HumanoidRobots?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#HumanoidRobots</a> <a href="https://x.com/hashtag/Robotics?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Robotics</a> <a href="https://x.com/hashtag/OpenSource?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#OpenSource</a> <a href="https://x.com/hashtag/EmbodiedAI?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#EmbodiedAI</a> <a href="https://x.com/hashtag/ROS2?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#ROS2</a> <a href="https://x.com/hashtag/Automation?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Automation</a> <a href="https://x.com/hashtag/PhysicalAI?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#PhysicalAI</a> <a href="https://t.co/BAZeQGHuNp" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">pic.twitter.com/BAZeQGHuNp</a></p>
<p>&mdash; High Torque Robotics (@HTrobotics) <a href="https://x.com/HTrobotics/status/2073772956095049991?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">July 5, 2026</a></p>
</blockquote>
<p> <script async src="https://platform.x.com/widgets.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaVQqF8BoM1/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaVQqF8BoM1/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaVQqF8BoM1/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by B-Human (@bhumnbhumn)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/reel/DaWu3Vbxq3_/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/reel/DaWu3Vbxq3_/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/reel/DaWu3Vbxq3_/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by Fernanda Bufon Färber (@fernandabufon)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="bluesky-embed" data-bluesky-uri="at://did:plc:sw5vvo3a6eozbv6f27kmxyil/app.bsky.feed.post/3mpx7egq64s2m" data-bluesky-cid="bafyreie7ltkvkxjyra2xid2b67f6ggtomopxfnntdgkyqqdnystkqgwrpm" data-bluesky-embed-color-mode="system">
<p lang="en">Straight from RoboCup 2026, at Incheon, Korea.<br />
We added an external lidar, and a literal backpack to the booster T1 to achieve accurate indoor localisation and navigation.<br />
@texasrobotics.bsky.social #Robocup2026</p>
<p><a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil/post/3mpx7egq64s2m?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">[image or embed]</a></p>
<p>&mdash; Raghav Arora (<a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">@ra-aurora.bsky.social</a>) <a href="https://bsky.app/profile/did:plc:sw5vvo3a6eozbv6f27kmxyil/post/3mpx7egq64s2m?ref_src=embed" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">6 July 2026 at 05:01</a></p>
</blockquote>
<p><script async src="https://embed.bsky.app/static/embed.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaX0oPHg1im/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaX0oPHg1im/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaX0oPHg1im/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by Robot Club Toulon (@robotclubtoulon)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="twitter-tweet">
<p lang="en" dir="ltr">A team from China&#39;s Tsinghua University successfully defended its Humanoid League title at RoboCup 2026 on Sunday in South Korea. <a href="https://x.com/hashtag/RoboCup2026?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup2026</a> <a href="https://x.com/hashtag/HumanoidLeague?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#HumanoidLeague</a> <a href="https://x.com/hashtag/TsinghuaUniversity?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#TsinghuaUniversity</a> <a href="https://x.com/hashtag/robotsoccer?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#robotsoccer</a> <a href="https://t.co/88gKYpxL3J" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">pic.twitter.com/88gKYpxL3J</a></p>
<p>&mdash; China Xinhua News (@XHNews) <a href="https://x.com/XHNews/status/2074088555039830491?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">July 6, 2026</a></p>
</blockquote>
<p> <script async src="https://platform.x.com/widgets.js" charset="utf-8"></script></p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/p/DaZ4WlSCSW3/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/p/DaZ4WlSCSW3/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/p/DaZ4WlSCSW3/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by autonOhm (@autonohm_official)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<blockquote class="twitter-tweet">
<p lang="en" dir="ltr">This is RoboCup 2026! <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f30d.png" alt="&#x1f30d;" class="wp-smiley" style="height: 1em; max-height: 1em;" /><img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f916.png" alt="&#x1f916;" class="wp-smiley" style="height: 1em; max-height: 1em;" /></p>
<p>Nearly 3,000 participants from 40 countries, united by one passion: advancing robotics and artificial intelligence!<br />Thank you to everyone who is part of this incredible journey! <img decoding="async" src="https://s.w.org/images/core/emoji/17.0.2/72x72/1f499.png" alt="&#x1f499;" class="wp-smiley" style="height: 1em; max-height: 1em;" /><a href="https://x.com/hashtag/RoboCup2026?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#RoboCup2026</a> <a href="https://x.com/hashtag/Robotics?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Robotics</a> <a href="https://x.com/hashtag/AI?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#AI</a> <a href="https://x.com/hashtag/Incheon?src=hash&amp;ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">#Incheon</a> <a href="https://t.co/X5enZLypmF" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">pic.twitter.com/X5enZLypmF</a></p>
<p>&mdash; RoboCup Federation (@robocup_org) <a href="https://x.com/robocup_org/status/2073322953496834448?ref_src=twsrc%5Etfw" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">July 4, 2026</a></p>
</blockquote>
<p> <script async src="https://platform.x.com/widgets.js" charset="utf-8"></script></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>#RoboCup2026 – humanoid league knockout stages</title>
		<link>https://robohub.org/robocup2026-humanoid-league-knockout-stages/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Mon, 06 Jul 2026 10:15:49 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<category><![CDATA[RoboCup2026]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20629</guid>

					<description><![CDATA[This weekend saw the finale of the league competitions at RoboCup 2026 in Incheon, South Korea, with the winners in the small, middle, and large humanoid divisions decided. Congratulations to the following teams, who finished in the top three positions in each size class: Small division Invic, Wuhan University, China Hamburg Bit-Bots, Universität Hamburg, Germany […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-scaled.jpg" alt="" width="2560" height="1928" class="alignnone size-full wp-image-20630" srcset="https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-300x226.jpg 300w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-1024x771.jpg 1024w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-768x578.jpg 768w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-1536x1157.jpg 1536w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260704_091501758-2048x1542.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>This weekend saw the finale of the league competitions at <a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a> in Incheon, South Korea, with the winners in the small, middle, and large humanoid divisions decided. Congratulations to the following teams, who finished in the top three positions in each size class:</p>
<h4>Small division</h4>
<ol>
<li><strong>Invic</strong>, Wuhan University, China</li>
<li><strong>Hamburg Bit-Bots</strong>, Universität Hamburg, Germany</li>
<li><strong>GeoHBots</strong>, School of Artificial Intelligence, China University of Geosciences, China</li>
</ol>
<h4>Middle division</h4>
<ol>
<li><strong>B-Human</strong>, Universität Bremen and German Research Center for Artificial Intelligence (DFKI), Germany</li>
<li><strong>HTWK Robots</strong>, Leipzig University of Applied Sciences, Germany</li>
<li><strong>Rhoban</strong>, University of Bordeaux, France</li>
</ol>
<h4>Large division</h4>
<ol>
<li><strong>Tsinghua Hephaestus</strong>, Tsinghua University, China</li>
<li><strong>CAU Mountain&#038;Sea</strong>, China Agricultural University, China</li>
<li><strong>Water</strong>, Beijing Information Science &#038; Technology University, China</li>
</ol>
<p>You can watch the action from one of the semi-finals in the middle division, which saw HTWK take on Rhoban.</p>
<div class="keep-aspect"><iframe title="RoboCup 2026 Semi Final! - HTWK Robots vs. Rhoban (Humanoid Soccer League)" width="500" height="281" src="https://www.youtube-nocookie.com/embed/qlVlp5ircAY?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p>In the final of the middle division, HTWK took on B-Human:</p>
<div class="keep-aspect"><iframe title="RoboCup 2026 Final: HTWK Robots vs B-Human | Live Commentary" width="500" height="281" src="https://www.youtube-nocookie.com/embed/8U5bdhOvHpM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p>In addition to the main competitions, there were five league-wide awards:</p>
<ul>
<li><strong>Best Customized Humanoid Award:</strong> HERoEHS (ALICE 4th version)</li>
<li><strong>Best Humanoid Software Award:</strong> B-Human (Game Controller)</li>
<li><strong>Open Research Challenge:</strong> Ruhrbot Devils (AI Camera Platform for Embedded 2D/3D Game Analysis in RoboCup HSL)</li>
<li><strong>Best Innovation Award:</strong> Bahia Robotics Team</li>
<li><strong>Best Referee Award:</strong> Anastasia Prisacaru (Berlin United)</li>
</ul>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-scaled.jpg" alt="" width="2560" height="1928" class="alignnone size-full wp-image-20632" srcset="https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-300x226.jpg 300w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-1024x771.jpg 1024w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-768x578.jpg 768w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-1536x1157.jpg 1536w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260705_023428603-2048x1542.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>Hear from Team Hephaestus of Tsinghua University, who won the large division:</p>
<div class="keep-aspect"><iframe title="Humanoid robots take to the pitch in South Korea at RoboCup 2026 finals" width="500" height="281" src="https://www.youtube-nocookie.com/embed/cnf0iODmv7o?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p>Although the competitions have drawn to a close, RoboCup 2026 continues today with a symposium, which brings together researchers and practitioners from around the world to present and discuss innovative research in robotics and artificial intelligence. You can find out more <a href="https://2026.robocup.org/symposium/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>#RoboCup2026 – humanoid league day 2</title>
		<link>https://robohub.org/robocup2026-humanoid-league-day-2/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Fri, 03 Jul 2026 18:36:55 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<category><![CDATA[RoboCup2026]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20591</guid>

					<description><![CDATA[The second day’s play at RoboCup 2026 has drawn to a close with another bumper set of matches. Teams have come from far and wide to take part in the humanoid soccer competition this year, with 17 different countries represented. China is the most represented country, boasting 15 teams across the three divisions. Other countries […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-scaled.jpg" alt="" width="2560" height="1928" class="alignnone size-full wp-image-20616" srcset="https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-300x226.jpg 300w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-1024x771.jpg 1024w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-768x578.jpg 768w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-1536x1157.jpg 1536w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_065500354-2048x1542.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>The second day&#8217;s play at <a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a> has drawn to a close with another bumper set of matches. Teams have <a href="https://hsl.robocup.org/qualified-teams/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">come from far and wide</a> to take part in the humanoid soccer competition this year, with 17 different countries represented. China is the most represented country, boasting 15 teams across the three divisions. Other countries taking part are geographically widespread, ranging from Colombia to Malaysia, from Germany to Australia. </p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-scaled.jpg" alt="" width="2560" height="1928" class="alignnone size-full wp-image-20620" srcset="https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-300x226.jpg 300w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-1024x771.jpg 1024w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-768x578.jpg 768w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-1536x1157.jpg 1536w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260703_071112613-2048x1542.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>In advance of the competition, all applying teams provided a video, team description paper, and information about the robots and software that they use. You can see the complete set of these <a href="https://hsl.robocup.org/qualified-teams/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>. As a taster, here is the qualification video from team CAU Mountain&#038;Sea (from China Agricultural University) who are currently leading the small division competition, and are in fourth place in the large division. </p>
<div class="keep-aspect"><iframe title="RoboCup2026 Humanoid League Large Size-CAU Mountain&amp;Sea" width="500" height="281" src="https://www.youtube-nocookie.com/embed/0rix-r1KS-s?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p>Yesterday&#8217;s play saw the first issuing of a red card. The robot received two yellow cards for unsafe challenges and was removed from play on safety grounds. You can see a clip of the second foul in question <a href="https://www.youtube.com/live/vOOgxyIMYE4?t=61s" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<p>In terms of the vital statistics of the robots, the heaviest and tallest robot is <em>HERoEHS&#8217;s</em> <a href="https://eng.arobot4all.com/ALICE4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ALICE 4</a> robot, weighing in at 48kg and measuring 160cm tall. There is a big jump down in weight to the second heaviest bot, which is team <em>BigHeroX&#8217;s</em> Z4 bipedal humanoid, at 37kg. A number of teams are using the 35kg Unitree G1. At the other end of the spectrum, the lightest and shortest robot is <em>ITAndroids&#8217;</em> Chape, at just 3.8kg and 53cm tall.</p>
<p><div style="width: 960px;" class="wp-video"><video class="wp-video-shortcode" id="video-220462-10" width="960" height="540" preload="metadata" controls="controls"><source type="video/mp4" src="https://aihub.org/wp-content/uploads/2026/07/My-Movie-5.mp4?_=10" /><a href="https://aihub.org/wp-content/uploads/2026/07/My-Movie-5.mp4" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">https://aihub.org/wp-content/uploads/2026/07/My-Movie-5.mp4</a></video></div></p>
<p>With the seeding rounds almost complete (the knockout rounds start tomorrow) the competitions are hotting up nicely. After four competed rounds in the small division, <em>CAU Mountain&#038;Sea</em> is the only team to win all four matches, and sits atop the table with 12 points, and impressively only conceding one goal. <em>Hamburg Bit-Bots</em> and <em>GeoHBots</em> are in second and third place respectively, having both won three games and lost one. </p>
<p>The middle division has fast established itself as one of the most compelling competitions. <em>B-Human</em> has taken a commanding lead, winning all four matches so far with a +35 goal difference. Behind them, there are four teams on nine points: <em>HTWK Robots</em>, <em>Rhoban</em>, <em>whIRLwind Amsterdam</em>, and <em>THMOS</em>. </p>
<p>Over in the large division, teams have completed three rounds of seeding, with just one further round to come tomorrow. At this stage <em>Tsinghua Hephaestus</em> is the only perfect team, sitting on nine points. Behind them, two teams have each won two matches and drawn the third: <em>PCMS-HRG</em> and <em>Robo-Erectus</em>.</p>
<p>Once the seeding rounds have been completed, 12 teams from each division will make it forward to the knockout stages, with the quarter finals taking place in the evening. </p>
<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-scaled.jpg" alt="" width="2560" height="1928" class="alignnone size-full wp-image-20622" srcset="https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-scaled.jpg 2560w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-300x226.jpg 300w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-1024x771.jpg 1024w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-768x578.jpg 768w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-1536x1157.jpg 1536w, https://aihub.org/wp-content/uploads/2026/07/PXL_20260701_233342769-2048x1542.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<hr>
<p><em>Many thanks to JT Genter for providing the photos, videos, and facts for this article.</em></p>
]]></content:encoded>
					
		
		<enclosure url="https://aihub.org/wp-content/uploads/2026/07/My-Movie-5.mp4" length="7878843" type="video/mp4" />

			</item>
		<item>
		<title>Reflections from ICRA 2026</title>
		<link>https://robohub.org/reflections-from-icra-2026/</link>
		
		<dc:creator><![CDATA[Ella Scallan]]></dc:creator>
		<pubDate>Thu, 02 Jul 2026 15:20:41 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220297</guid>

					<description><![CDATA[From the 1st-5th June, the robots descended on Vienna. The 2026 IEEE International Conference on Robotics &#38; Automation (ICRA) brought together the top minds in robotics for one short week to showcase the latest technologies, form new collaborations, and exchange ideas. Held at the Messe Wien, a stone’s throw from the bank of the Danube, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><span style="font-weight: 400;">From the 1st-5th June, the robots descended on Vienna. The </span><a href="https://2026.ieee-icra.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">2026 IEEE International Conference on Robotics &amp; Automation</span></a><span style="font-weight: 400;"> (ICRA) brought together the top minds in robotics for one short week to showcase the latest technologies, form new collaborations, and exchange ideas. Held at the Messe Wien, a stone’s throw from the bank of the Danube, ICRA proved to be equal parts technological marvel and thought-provoking discussion. </span></p>
<p><img decoding="async" class="wp-image-220320" src="https://robohub.org/wp-content/uploads/2026/06/VIECON.jpg" alt="" /><br />
The host venue for ICRA 2026: Messe Wien, also known as VIECON.</p>
<p><b>Workshop on robot ethics</b></p>
<p><span style="font-weight: 400;">My week at ICRA began with the </span><a href="https://sites.google.com/view/icra2026-workshop-robot-ethics" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">2nd ICRA 2026 Workshop on Robot Ethics: Ethical, Legal and User Perspectives in Robotics &amp; Automation (WOROBET)</span></a><span style="font-weight: 400;">. WOROBET provided a space for researchers to share ideas, thoughts, and concerns on the future of robot-human interaction, and how to create ethical frameworks to navigate this rapidly changing technology. </span></p>
<p><a href="https://w3.tohoku.ac.jp/moonshot/en/project_e/hirata_e/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Yasuhisa Hirata</span></a><span style="font-weight: 400;">, Professor at Tohoku University, began by presenting his vision of a world with physically assistive robots, such as </span><a href="https://www.youtube.com/watch?v=BCgCHQhertA" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">detachable exoskeletons or cycling wheelchairs</span></a><span style="font-weight: 400;">. These tools can affect people’s sense of self-efficacy and motivation, and there are a host of ethical implications that come with this &#8211; how do you help people just enough to build their confidence, without slipping into deception? </span></p>
<p><span style="font-weight: 400;">We then heard from Prof. Minoru Asada from Osaka University, who discussed his aim to </span><a href="https://link.springer.com/article/10.1007/s12369-014-0253-z#Sec12" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">implement pain signals into robots</span></a><span style="font-weight: 400;">, so they can experience the world as we do. This was a highly interesting and niche proposition that brought up more ethical questions than we have answers for at the moment. Perhaps most pertinent to a technical conference: is a sense of embodied morality necessary for true intelligence? </span></p>
<p><a href="https://people.uwe.ac.uk/Person/AlanWinfield" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Alan Winfield</span></a><span style="font-weight: 400;">, Professor of Robot Ethics at UWE Bristol, presented a vision of robotics that acted as a counterweight to Prof. Asada’s: robots as tools, not potential beings. This also somewhat reflects differing attitudes in Eastern vs Western cultures. Thinking about the practical issues we are likely to face in the near term, he outlined a </span><a href="https://ebooks.iospress.nl/doi/10.3233/FAIA241511" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">framework for social robot accident investigation</span></a><span style="font-weight: 400;">. In his view, robot ethics is not just an engineering problem, but requires appropriate social and governance frameworks, just as we do for aviation. His talk also emphasised the risk that programming ethics into robots runs the risk of removing moral responsibility from the roboticist, and can always give rise to </span><a href="https://arxiv.org/abs/1606.02583" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">unethical robots</span></a> <span style="font-weight: 400;">via malicious hacking. The theme that we must focus on human morality, as opposed to machine morality, was repeated throughout the day. </span></p>
<p><span style="font-weight: 400;">After a morning of differing ideas and visions of what robot-human interaction could be, we were invited to ground this into a real robot social care scenario by </span><a href="https://www.nottingham.ac.uk/computerscience/people/praminda.caleb-solly" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Praminda Caleb-Solly</span></a><span style="font-weight: 400;">, Professor of Embodied Intelligence at the University of Nottingham. In this red-teaming exercise, we examined the safety risks and possible mitigations of an assistive robot for a schoolteacher recovering from a stroke at home. Our group discussion circled around human agency: how ethical is it to make design choices for people that take away some of their autonomy, in the name of their best interests? As </span><a href="https://www.researchgate.net/publication/338644594_Robotics_in_social_care_a_connected_care_ecosystem_for_independent_living" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">robots in social care</span></a><span style="font-weight: 400;"> will become a more urgent need in the years to come, these questions may become more salient. </span></p>
<p>I left WOROBET with plenty to think about, and a renewed sense of appreciation for the ethicists who are already grappling with the problems that are to come. I hope that progress in robot ethics keeps pace with progress in robotics, so that we are well prepared as robots become more of a part of our daily lives.</p>
<p><b>Welcome to the jungle &#8211; the robot exhibition floor</b></p>
<p><span style="font-weight: 400;">Every time you entered the exhibition hall, you were greeted by one of the child-sized Booster robots, either playing football, dancing, or demonstrating some kung fu. They were always an endearing welcome to the sea of robots. </span></p>
<p><div style="width: 630px;" class="wp-video"><video class="wp-video-shortcode" id="video-220297-11" width="630" height="1120" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/06/Booster-teddy-bear-hat_compressed.mp4?_=11" /><a href="https://robohub.org/wp-content/uploads/2026/06/Booster-teddy-bear-hat_compressed.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/06/Booster-teddy-bear-hat_compressed.mp4</a></video></div></p>
<p><span style="font-weight: 400;">The robots ranged from the endearing to the uncanny, but the common thread was their technical capabilities were astounding. Veteran attendees consistently remarked on how much the robots had improved year on year.</span></p>
<table style="width: 100%;">
<tbody>
<tr>
<td style="width: 40%; vertical-align: top; padding-right: 10px;"><div style="width: 250px;" class="wp-video"><video class="wp-video-shortcode" id="video-220297-12" width="250" height="360" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/06/booster-reading-a-dings-catalogye.mp4?_=12" />]<a href="https://robohub.org/wp-content/uploads/2026/06/booster-reading-a-dings-catalogye.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/06/booster-reading-a-dings-catalogye.mp4</a></video></div></p>
<p>The cute.</td>
<td style="width: 60%; vertical-align: top;"><img decoding="async" class="" src="https://robohub.org/wp-content/uploads/2026/06/sinister-humanoid.jpg" alt="" />The slightly uncanny.</td>
</tr>
</tbody>
</table>
<p><span style="font-weight: 400;">The below clips show the robots that most caught my eye. After admiring a phosphorescent, Stranger Things-esque robotic flower display, I was blown away by the </span><a href="https://www.youtube.com/watch?v=rj-FdG_j4rY" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">D1-modular robot</span></a><span style="font-weight: 400;"> from Direct Drive. Unlike most robot dogs, it can split into two halves, with the ability to jump, twist, and traverse difficult terrain. </span></p>
<p><iframe title="YouTube Short" src="https://www.youtube-nocookie.com/embed/h1d4NK6OcEg" width="630" height="1120" frameborder="0" allowfullscreen="allowfullscreen"><span data-mce-type="bookmark" style="display: inline-block; width: 0px; overflow: hidden; line-height: 0;" class="mce_SELRES_start">﻿</span><br />
</iframe></p>
<p><a href="https://www.sharpa.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Sharpa’s North</span></a><span style="font-weight: 400;"> was always a friendly face, waving and making love-hearts at visitors to its booth. Around the back of the booth, you could even challenge it to a round at blackjack. We saw humanoids zipping up rucksacks and trying to fold laundry. </span><a href="https://enchanted.tools/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Enchanted Tools’</span></a><span style="font-weight: 400;"> social care robot, Mirokaï, was an unusual sight among the mass of black and steel, with a bright orange body, feline ears and an orange, furry face. </span><a href="https://en.tesollo.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Tesollo</span></a><span style="font-weight: 400;">’s humanoid spent much of its time at ICRA using its long, wavering arms to pick up fruit and drop it into baskets, with impressive dexterity. Vietnamese company </span><a href="https://vinrobotics.net/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Vinrobotics</span></a><span style="font-weight: 400;">’ humanoid offering was reminiscent of the Cybermen, with its gently wheezing joints, but the team assured me it was much friendlier. The pint-sized </span><a href="https://www.booster.tech/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Boosters</span></a><span style="font-weight: 400;"> were almost always playing football, not far from their similarly sized </span><a href="https://www.agibot.com/?gad_source=1&amp;gad_campaignid=23867350457&amp;gbraid=0AAAABC0KuBD6OmZCdeCwFZLn43hhldLgP&amp;gclid=CjwKCAjwgO7RBhBKEiwAZNP85gTcKKGoWPBtuG08kxP5WFI8RKNVjFYBujSHSvY2MVjhJgoJ1htPjBoC4dQQAvD_BwE" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Agibot</span></a><span style="font-weight: 400;"> cousins. </span></p>
<p><iframe title="YouTube Short" src="https://www.youtube-nocookie.com/embed/E9psTOpIPRk" width="630" height="1120" frameborder="0" allowfullscreen="allowfullscreen"><br />
</iframe></p>
<p><span style="font-weight: 400;">However, humanoids didn’t steal the show this year, as they have done previously. The big trend this year was robotic hands, and the levels of dexterity were truly impressive. Closing the gap between human and robot abilities here would </span><a href="https://www.weforum.org/stories/2026/06/why-hand-dexterity-remains-a-barrier-to-automation/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">unlock</span></a><span style="font-weight: 400;"> whole new swathes of tasks to automate &#8211; and who wouldn’t want a robot folding their laundry? </span></p>
<p><iframe title="YouTube Short" src="https://www.youtube-nocookie.com/embed/roiQ05rBSpc" width="630" height="1120" frameborder="0" allowfullscreen="allowfullscreen"><br />
</iframe></p>
<p><b>Industrial challenges: solving dexterity </b></p>
<p><span style="font-weight: 400;">Tackling the dexterity challenge really defined the industrial talks for me this year. A talk by <a href="https://aria.org.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">ARIA</a>’s program director, Prof. Jenny Read, demonstrated how the UK government is already laying the groundwork here.</span></p>
<p><span style="font-weight: 400;">They outlined their funding proposals as part of their <a href="https://aria.org.uk/opportunity-spaces/smarter-robot-bodies" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Smarter Robot Bodies program</a>, which is split into two branches: <a href="https://aria.org.uk/media/3yglnoch/programme-thesis_robot-locomotion.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robot locomotion</a> and <a href="https://aria.org.uk/media/xamlbwdo/aria-robotic-dexterity-programme-thesis.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robot dexterity</a>. The robot locomotion branch aims to enable robots to traverse messy, unpredictable physical environments, while the robot dexterity branch will try to break the bottleneck of adept physical manipulation by robotic hands. With the programme set to launch in early 2027, it’ll be exciting to see what kind of innovations this attracts. </span></p>
<p>One standout innovation in the realm of dexterity <span style="font-weight: 400;">was <a href="https://wiyh.tars-ai.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">TARS</a>, a record-setting newcomer in the Chinese robotics market. Co-founded by Dr Ding Wenchao just 18 months ago, TARS has already raised the most funding in angel and pre-seed rounds of any company in the Chinese embodied intelligence sector, and achieved a Guinness World Record for robotic flexible wiring-harness insertion completed in one hour. </span></p>
<p><img decoding="async" class="wp-image-220318" src="https://robohub.org/wp-content/uploads/2026/06/TARS-hand-425x284.jpeg" alt="" width="780" height="521" srcset="https://robohub.org/wp-content/uploads/2026/06/TARS-hand-425x284.jpeg 425w, https://robohub.org/wp-content/uploads/2026/06/TARS-hand-1024x684.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/06/TARS-hand-768x513.jpeg 768w, https://robohub.org/wp-content/uploads/2026/06/TARS-hand-1536x1026.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/06/TARS-hand.jpeg 1617w" sizes="(max-width: 780px) 100vw, 780px" /></p>
<p>TARS&#8217; DexHand. Image credits: TARS.</p>
<p><span style="font-weight: 400;">DexHand is a 1:1 model of the human hand, even replicating the 21 degrees of freedom we have in the wrist joint and hand. According to TARS, “it can interpret tactile data to distinguish slipperiness, roughness, and hardness in real time and perform 26 English alphabet hand gestures with high-precision finger control.” I was given the chance to control the hand using my own, and was impressed by how well it emulated my own movements. I was also impressed by their humanoid zipping up a backpack &#8211; despite the technical abilities of all the robots on the floor, few were able to perform tasks which required such fine motor skills. </span></p>
<p><div style="width: 630px;" class="wp-video"><video class="wp-video-shortcode" id="video-220297-13" width="630" height="1120" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/06/TARS-zipping-backpack_compressed.mp4?_=13" /><a href="https://robohub.org/wp-content/uploads/2026/06/TARS-zipping-backpack_compressed.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/06/TARS-zipping-backpack_compressed.mp4</a></video></div></p>
<p>TARS robot zipping up a rucksack.</p>
<p><span style="font-weight: 400;">On Thursday, <a href="https://wenchaoding.github.io/personal/index.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Dr Wenchao Ding</a> delivered an industry keynote where he presented TARS’ roadmap, charting the path from academia to industrial deployment. With an impressive academic team behind them, TARS may be one to watch. </span></p>
<p><b>Plenary talks</b></p>
<p><span style="font-weight: 400;">Aside from the wealth of invention and innovation taking place in the exhibition hall, the breadth and depth of academic research at ICRA was fantastic. The plenaries especially gave an insight into the research trends that are currently defining the field. </span></p>
<p><a href="https://goldberg.berkeley.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Ken Goldberg</span></a><span style="font-weight: 400;"> delivered an electrifying plenary, titled “A Tale of Two Cultures:  Can Agentic Coding Close the Gap?” In this talk, he called for a step change to </span><a href="https://www.science.org/doi/full/10.1126/scirobotics.aea7390" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">close the data gap</span></a><span style="font-weight: 400;"> faced by robot manipulation. With the rise of diffusion models and LLMs, it is clear that big data has solved computer vision and language. He challenged the audience &#8211; when will the ChatGPT moment for robotics come? With state spaces larger than 50 dimensions in robotics, there is not enough training data to close this gap. Currently, the data required to train vision-language models is equivalent to 100,000 years of real physical experience. </span></p>
<p><span style="font-weight: 400;">According to Goldberg, the two dominant cultures in engineering &#8211; model free “good old fashioned” engineering (GOFE), and, the currently more popular model based engineering.  GOFE encapsulates rigorous engineering methods that pre-date AI, but may have been slightly forgotten about in the AI wave of recent years. He highlighted how in his career he has always been working to bridge the gap between two cultures: from science and </span><a href="https://goldberg.berkeley.edu/art/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">art </span></a><span style="font-weight: 400;">to robotics and </span><a href="https://autolab.berkeley.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">automation</span></a><span style="font-weight: 400;">. </span></p>
<p><span style="font-weight: 400;">He outlined four possible solutions to the data gap:</span></p>
<ol>
<li style="font-weight: 400;" aria-level="1"><span style="font-weight: 400;">Simulations &#8211; these work incredibly well for locomotion and body control, but less so for manipulation due to the number of forces and instabilities involved.</span></li>
<li style="font-weight: 400;" aria-level="1"><span style="font-weight: 400;">World models &#8211; they do not currently properly capture the physics, and hallucinations can be problematic. </span></li>
<li style="font-weight: 400;" aria-level="1"><span style="font-weight: 400;">Human teleoperation &#8211; this is currently big business and a good way to obtain high quality data. However, the largest dataset is currently only equivalent to a year’s worth of data. </span></li>
<li style="font-weight: 400;" aria-level="1"><span style="font-weight: 400;">Real data from functioning robots &#8211; this is less commonly used, but can be powerful. </span></li>
</ol>
<p><span style="font-weight: 400;">Prof Goldberg described how he used the fourth approach in his robotic delivery packing company, </span><a href="https://www.ambirobotics.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Ambi Robotics</span></a><span style="font-weight: 400;">, for 22 years. Picking up bags is an example of variational automation &#8211;  one task is done repeatedly, but with different initial conditions each time. From this rich dataset, they created a generative model to train robots in the best way to pick up bags. Here, they close the gap between model-free and model-based methods &#8211; Ambi exploits both to achieve industry-leading results. This plenary served as a call for other researchers to use their own production data to do the same. </span></p>
<p><span style="font-weight: 400;">During Thursday’s keynote on Robot Learning, Planning &amp; Foundation Models, </span><a href="https://vivo.brown.edu/display/stellex" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Stefanie Tellex</span></a><span style="font-weight: 400;"> from Brown University gave a compelling talk titled “Towards Complex Language in Partially Observed Environments”. While current research is bounded in known, predictable scenarios, using action-based language, this does not reflect what the real world is like, nor how people would naturally communicate with robots. Prof. Tellex described </span><a href="https://dl.acm.org/doi/pdf/10.1145/3757279.3785585" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">her work</span></a><span style="font-weight: 400;"> creating robots that can understand complex, goal-based commands in only  partially observed, dynamic environments, and outlined the </span><a href="https://davidjosephwatkins.com/files/tellexwatkins2026.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">grounded Turing test </span></a><span style="font-weight: 400;">&#8211; a reimagining of the Turing test for embodied AI. </span></p>
<p><img decoding="async" class="alignnone wp-image-220319" src="https://robohub.org/wp-content/uploads/2026/06/Tellex-spot-red-cup-425x236.png" alt="" width="791" height="439" srcset="https://robohub.org/wp-content/uploads/2026/06/Tellex-spot-red-cup-425x236.png 425w, https://robohub.org/wp-content/uploads/2026/06/Tellex-spot-red-cup-1024x568.png 1024w, https://robohub.org/wp-content/uploads/2026/06/Tellex-spot-red-cup-768x426.png 768w, https://robohub.org/wp-content/uploads/2026/06/Tellex-spot-red-cup.png 1288w" sizes="(max-width: 791px) 100vw, 791px" /></p>
<p><span style="font-weight: 400;">An example of a robot performing a goal-based task in a dynamic environment. Credits: </span><a href="https://dl.acm.org/doi/pdf/10.1145/3757279.3785585" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Tellex et al, 2026</span></a><span style="font-weight: 400;">.</span></p>
<p><span style="font-weight: 400;">Both plenaries spoke to current pinch points in robotics: data, reasoning, and operating in complex real-world environments. It’ll be interesting to see what solutions are developed in the coming years. </span></p>
<p><b>Science communications crash course</b></p>
<p><span style="font-weight: 400;">One of my favourite parts of ICRA was delivering the Science Communications Crash Course. Along with Robohub Executive Trustee </span><a href="https://robohub.org/author/sabinehauert/" data-wpel-link="internal"><span style="font-weight: 400;">Sabine Hauert</span></a><span style="font-weight: 400;">, IEEE Spectrum Senior Editor </span><a href="https://spectrum.ieee.org/u/evan-ackerman" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Evan Ackerman</span></a><span style="font-weight: 400;">, and IEEE Spectrum Community Manager </span><a href="https://kohavamendelsohn.wordpress.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Kohava Mendelsohn</span></a><span style="font-weight: 400;">, we gave our guidance on effective science communication to an audience of 100 academics. It was encouraging to see so many people interested in communicating their research effectively &#8211; it is a crucial skill, especially in the era of AI and robotics when mainstream narratives can be hijacked by doom-mongering, hype, and corporate interests. More academics communicating their work clearly and neutrally will go a long way to grounding our societal discussion in technical reality, not sci-fi futures. </span></p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/sabine-kicking-off-the-session.jpg" alt="" /><br />
Sabine kicking off the science communications crash course. Image credits: Taraja Arnold</p>
<p><img decoding="async" class="" src="https://robohub.org/wp-content/uploads/2026/06/delivering-sci-comms-1.jpg"  /><br />
Delivering my part of the course. Image credits: Taraja Arnold</p>
<p><b>Art and robotics </b></p>
<p><span style="font-weight: 400;">The arts and robotics section was rich and interesting. There was a lot to visually take in, with constant background music from a <a href="https://robohorizon.uk/en-gb/videos/this-robot-saxophonist-may-have-more-soul-than-kenny-g/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robotic saxophone</a>. </span></p>
<p><img decoding="async" class="" src="https://robohub.org/wp-content/uploads/2026/06/robot-sax3.jpg" alt=""  /><br />
Masatoshi Hamanaka&#8217;s robotic saxophone. Image credits: ©Denes Erdos &#8211; <a href="https://youreventphoto.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Your Event Photographer</a></p>
<p><a href="https://devicist.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">PET</span></a><span style="font-weight: 400;"> &#8211; marked by a large “PET ME” sign &#8211; was a white and orange mass of connecting, rotating pyramids, that gently pulsed and hummed in response to touch, responding by curling towards or away from you depending on how you touched it, The effect was strangely lifelike. </span></p>
<p><a href="https://www.rhombus-research.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Rhombus Research</span></a><span style="font-weight: 400;"> presented “Reptile: A Bio-Mimetic Choreography Engine for V2X and A2X Swarms”. This artistic simulation visualises the contracts negotiated within autonomous vehicle and swarm fleets in dreamy blue, browser-based visualisation. Performance artist and former Cirque de Soleil acrobat </span><a href="https://www.silkegrabinger.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Silke Grabinger</span></a><span style="font-weight: 400;"> explored human-robot interaction via her piece, </span><a href="https://www.youtube.com/shorts/DOzrh-f4F7k" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">AREYOUARE</span></a><span style="font-weight: 400;">. </span></p>
<p><img decoding="async" class="" src="https://robohub.org/wp-content/uploads/2026/06/silke.jpg" alt=""  /></p>
<p>Silke Grabinger performing AREYOUARE. Image credits: ©Denes Erdos &#8211; <a href="https://youreventphoto.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Your Event Photographer</a></p>
<p><span style="font-weight: 400;">I’d also like to acknowledge some of the video creators I met there. YouTubers </span><a href="https://www.youtube.com/@backtoengineering" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">Back to Engineering</span></a><span style="font-weight: 400;"> and </span><a href="https://www.youtube.com/channel/UCqACjGMfxB2b64aF2U7FEBg" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><span style="font-weight: 400;">the. Amazing, PhD</span></a><span style="font-weight: 400;"> are making some fantastic videos about physical AI. </span></p>
<p><b>Nothing lasts forever &#8211; ending with the robot parade </b></p>
<p><span style="font-weight: 400;">ICRA 2026 ended with the robot parade, which attracted quite a crowd. See if you can spot the panda, dragon, and headless humanoid!</span></p>
<p><iframe title="YouTube Short" src="https://www.youtube-nocookie.com/embed/Pc48Ox0j81A" width="630" height="1120" frameborder="0" allowfullscreen="allowfullscreen"><span data-mce-type="bookmark" style="display: inline-block; width: 0px; overflow: hidden; line-height: 0;" class="mce_SELRES_start">﻿</span><br />
</iframe></p>
<p><span style="font-weight: 400;">Seeing all the robots gathered together was a real spectacle. The technology on display was state-of-the-art, and it only improves year on year. What struck me most was the sense that robotics is moving from proving what is possible to tackling the remaining barriers to real-world deployment. Across the exhibition floor, industry keynotes, and plenary talks, the focus was often on the same challenges: dexterity, data, and operating reliably in complex environments. Solving these bottlenecks will open up new avenues to real-world applications of robots. </span></p>
<p><span style="font-weight: 400;">While workshops such as WOROBET highlighted important questions around ethics, agency, and governance, the overwhelming emphasis at ICRA 2026 was on capability. Researchers and companies alike are working to close the gap between what robots can do in carefully controlled demonstrations and what they can do in the messy reality of the world outside the lab. Judging by the pace of progress on display in Vienna, that gap may be narrowing faster than many of us expected. I hope that the kinds of conversations around human-robot interaction and ethics that were commonplace at WOROBET and in the Arts exhibition space will become more mainstream &#8211; we may need to face the questions that they raise sooner than we think. </span></p>
<p><span style="font-weight: 400;"><strong>Note: </strong>Where image and video credits are not stated, they belong to Ella Scallan.</span></p>
]]></content:encoded>
					
		
		<enclosure url="https://robohub.org/wp-content/uploads/2026/06/Booster-teddy-bear-hat_compressed.mp4" length="7561625" type="video/mp4" />
<enclosure url="https://robohub.org/wp-content/uploads/2026/06/booster-reading-a-dings-catalogye.mp4" length="6861850" type="video/mp4" />
<enclosure url="https://robohub.org/wp-content/uploads/2026/06/TARS-zipping-backpack_compressed.mp4" length="2397284" type="video/mp4" />

			</item>
		<item>
		<title>#RoboCup2026 – humanoid league day 1</title>
		<link>https://robohub.org/robocup2026-humanoid-league-day-1/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Thu, 02 Jul 2026 14:14:34 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<category><![CDATA[RoboCup2026]]></category>
		<guid isPermaLink="false">https://aihub.org/?p=20573</guid>

					<description><![CDATA[Image credit: RoboCup Federation. RoboCup 2026 kicked off today in Incheon, South Korea, with the league competitions running until 5 July. It’s an exciting time for RoboCup, as there have been some updates to the leagues and competition format. Most prominently, the soccer leagues will have a primary focus on humanoid robots. In a series […]]]></description>
										<content:encoded><![CDATA[<p><img fetchpriority="high" decoding="async" src="https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration.jpeg" alt="" width="2048" height="2048" class="alignnone size-full wp-image-20575" srcset="https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration.jpeg 2048w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-300x300.jpeg 300w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-1024x1024.jpeg 1024w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-150x150.jpeg 150w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-768x768.jpeg 768w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-1536x1536.jpeg 1536w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-24x24.jpeg 24w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-48x48.jpeg 48w, https://aihub.org/wp-content/uploads/2026/07/soccer_Celebration-96x96.jpeg 96w" sizes="(max-width: 2048px) 100vw, 2048px" /><em>Image credit: RoboCup Federation.</em></p>
<p><a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026</a> kicked off today in Incheon, South Korea, with the league competitions running until 5 July. It’s an exciting time for RoboCup, as there have been some <a href="https://www.robocup.org/news/181" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">updates</a> to the leagues and competition format. Most prominently, the soccer leagues will have a primary focus on humanoid robots. In a series of daily updates, we&#8217;ll be bringing you the latest results, videos, and news from the humanoid soccer league. </p>
<p>This year, the humanoid league is split into three sizes: large division, middle division, and small division. There are 18 teams participating the small division, 16 in the middle, and an impressive 22 competing in the large division. </p>
<p>The first two days of competition are be devoted to the seeding round. Teams play using the <a href="https://en.wikipedia.org/wiki/Swiss-system_tournament" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Swiss-system</a> of ranking to decide who gets through to the knockout stages. </p>
<p>Livestreams from the different fields of play can be found <a href="https://www.youtube.com/@robocuphsl" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<p>At the end of the first day of competition, teams in the small and middle divisions have played two games each, with the large division ending the day part way through the second round. Early leaders in the small division, with the full six points from two games are: <em>GeoHBots</em>, <em>CAU Mountain&#038;Sea</em>, and <em>Hamburg Bit-Bots</em>. There are also three teams in the middle division who have claimed the six point haul: <em>B-Human</em>, <em>RoboRoos</em>, and <em>HTWK Robots</em>.</p>
<p>You can watch a short summary of the first day, including some of the robots in action, from KBS News:</p>
<div class="keep-aspect"><iframe title="최고 AI 로봇 가린다…로보컵 인천서 개막 [9시 뉴스] / KBS  2026.07.02." width="500" height="281" src="https://www.youtube-nocookie.com/embed/AMRVocUPfes?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
</p>
<p>This short video from RoboCup gives a flavour of the day&#8217;s happenings, which also featured the opening ceremony. </p>
<blockquote class="instagram-media" data-instgrm-captioned data-instgrm-permalink="https://www.instagram.com/reel/DaSr0zXT9Z8/?utm_source=ig_embed&amp;utm_campaign=loading" data-instgrm-version="14" style=" background:#FFF; border:0; border-radius:3px; box-shadow:0 0 1px 0 rgba(0,0,0,0.5),0 1px 10px 0 rgba(0,0,0,0.15); margin: 1px; max-width:540px; min-width:326px; padding:0; width:99.375%; width:-webkit-calc(100% - 2px); width:calc(100% - 2px);">
<div style="padding:16px;"> <a href="https://www.instagram.com/reel/DaSr0zXT9Z8/?utm_source=ig_embed&amp;utm_campaign=loading" style=" background:#FFFFFF; line-height:0; padding:0 0; text-align:center; text-decoration:none; width:100%;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> </p>
<div style=" display: flex; flex-direction: row; align-items: center;">
<div style="background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 40px; margin-right: 14px; width: 40px;"></div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 100px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 60px;"></div>
</div>
</div>
<div style="padding: 19% 0;"></div>
<div style="display:block; height:50px; margin:0 auto 12px; width:50px;"><svg width="50px" height="50px" viewBox="0 0 60 60" version="1.1" xmlns="https://www.w3.org/2000/svg" xmlns:xlink="https://www.w3.org/1999/xlink"><g stroke="none" stroke-width="1" fill="none" fill-rule="evenodd"><g transform="translate(-511.000000, -20.000000)" fill="#000000"><g><path d="M556.869,30.41 C554.814,30.41 553.148,32.076 553.148,34.131 C553.148,36.186 554.814,37.852 556.869,37.852 C558.924,37.852 560.59,36.186 560.59,34.131 C560.59,32.076 558.924,30.41 556.869,30.41 M541,60.657 C535.114,60.657 530.342,55.887 530.342,50 C530.342,44.114 535.114,39.342 541,39.342 C546.887,39.342 551.658,44.114 551.658,50 C551.658,55.887 546.887,60.657 541,60.657 M541,33.886 C532.1,33.886 524.886,41.1 524.886,50 C524.886,58.899 532.1,66.113 541,66.113 C549.9,66.113 557.115,58.899 557.115,50 C557.115,41.1 549.9,33.886 541,33.886 M565.378,62.101 C565.244,65.022 564.756,66.606 564.346,67.663 C563.803,69.06 563.154,70.057 562.106,71.106 C561.058,72.155 560.06,72.803 558.662,73.347 C557.607,73.757 556.021,74.244 553.102,74.378 C549.944,74.521 548.997,74.552 541,74.552 C533.003,74.552 532.056,74.521 528.898,74.378 C525.979,74.244 524.393,73.757 523.338,73.347 C521.94,72.803 520.942,72.155 519.894,71.106 C518.846,70.057 518.197,69.06 517.654,67.663 C517.244,66.606 516.755,65.022 516.623,62.101 C516.479,58.943 516.448,57.996 516.448,50 C516.448,42.003 516.479,41.056 516.623,37.899 C516.755,34.978 517.244,33.391 517.654,32.338 C518.197,30.938 518.846,29.942 519.894,28.894 C520.942,27.846 521.94,27.196 523.338,26.654 C524.393,26.244 525.979,25.756 528.898,25.623 C532.057,25.479 533.004,25.448 541,25.448 C548.997,25.448 549.943,25.479 553.102,25.623 C556.021,25.756 557.607,26.244 558.662,26.654 C560.06,27.196 561.058,27.846 562.106,28.894 C563.154,29.942 563.803,30.938 564.346,32.338 C564.756,33.391 565.244,34.978 565.378,37.899 C565.522,41.056 565.552,42.003 565.552,50 C565.552,57.996 565.522,58.943 565.378,62.101 M570.82,37.631 C570.674,34.438 570.167,32.258 569.425,30.349 C568.659,28.377 567.633,26.702 565.965,25.035 C564.297,23.368 562.623,22.342 560.652,21.575 C558.743,20.834 556.562,20.326 553.369,20.18 C550.169,20.033 549.148,20 541,20 C532.853,20 531.831,20.033 528.631,20.18 C525.438,20.326 523.257,20.834 521.349,21.575 C519.376,22.342 517.703,23.368 516.035,25.035 C514.368,26.702 513.342,28.377 512.574,30.349 C511.834,32.258 511.326,34.438 511.181,37.631 C511.035,40.831 511,41.851 511,50 C511,58.147 511.035,59.17 511.181,62.369 C511.326,65.562 511.834,67.743 512.574,69.651 C513.342,71.625 514.368,73.296 516.035,74.965 C517.703,76.634 519.376,77.658 521.349,78.425 C523.257,79.167 525.438,79.673 528.631,79.82 C531.831,79.965 532.853,80.001 541,80.001 C549.148,80.001 550.169,79.965 553.369,79.82 C556.562,79.673 558.743,79.167 560.652,78.425 C562.623,77.658 564.297,76.634 565.965,74.965 C567.633,73.296 568.659,71.625 569.425,69.651 C570.167,67.743 570.674,65.562 570.82,62.369 C570.966,59.17 571,58.147 571,50 C571,41.851 570.966,40.831 570.82,37.631"></path></g></g></g></svg></div>
<div style="padding-top: 8px;">
<div style=" color:#3897f0; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:550; line-height:18px;">View this post on Instagram</div>
</div>
<div style="padding: 12.5% 0;"></div>
<div style="display: flex; flex-direction: row; margin-bottom: 14px; align-items: center;">
<div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(0px) translateY(7px);"></div>
<div style="background-color: #F4F4F4; height: 12.5px; transform: rotate(-45deg) translateX(3px) translateY(1px); width: 12.5px; flex-grow: 0; margin-right: 14px; margin-left: 2px;"></div>
<div style="background-color: #F4F4F4; border-radius: 50%; height: 12.5px; width: 12.5px; transform: translateX(9px) translateY(-18px);"></div>
</div>
<div style="margin-left: 8px;">
<div style=" background-color: #F4F4F4; border-radius: 50%; flex-grow: 0; height: 20px; width: 20px;"></div>
<div style=" width: 0; height: 0; border-top: 2px solid transparent; border-left: 6px solid #f4f4f4; border-bottom: 2px solid transparent; transform: translateX(16px) translateY(-4px) rotate(30deg)"></div>
</div>
<div style="margin-left: auto;">
<div style=" width: 0px; border-top: 8px solid #F4F4F4; border-right: 8px solid transparent; transform: translateY(16px);"></div>
<div style=" background-color: #F4F4F4; flex-grow: 0; height: 12px; width: 16px; transform: translateY(-4px);"></div>
<div style=" width: 0; height: 0; border-top: 8px solid #F4F4F4; border-left: 8px solid transparent; transform: translateY(-4px) translateX(8px);"></div>
</div>
</div>
<div style="display: flex; flex-direction: column; flex-grow: 1; justify-content: center; margin-bottom: 24px;">
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; margin-bottom: 6px; width: 224px;"></div>
<div style=" background-color: #F4F4F4; border-radius: 4px; flex-grow: 0; height: 14px; width: 144px;"></div>
</div>
<p></a></p>
<p style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; line-height:17px; margin-bottom:0; margin-top:8px; overflow:hidden; padding:8px 0 7px; text-align:center; text-overflow:ellipsis; white-space:nowrap;"><a href="https://www.instagram.com/reel/DaSr0zXT9Z8/?utm_source=ig_embed&amp;utm_campaign=loading" style=" color:#c9c8cd; font-family:Arial,sans-serif; font-size:14px; font-style:normal; font-weight:normal; line-height:17px; text-decoration:none;" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A post shared by RoboCup Federation (@robocup.official)</a></p>
</div>
</blockquote>
<p><script async src="https://www.instagram.com/embed.js"></script></p>
<p>We will be back tomorrow with further updates on competition results, some highlights from the day, and insights into how the event is progressing.</p>
<h4>Useful links</h4>
<ul>
<li><a href="https://2026.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup 2026 homepage</a></li>
<li><a href="https://www.youtube.com/@robocuphsl" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Humanoid league YouTube channel</a></li>
<li><a href="https://hsl.robocup.org/results-2026/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Humanoid league results page</a></li>
<li><a href="https://2026.robocup.org/leagues/robocupsoccer/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCupSoccer homepage</a></li>
</ul>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>What&#8217;s coming up at #RoboCup2026?</title>
		<link>https://robohub.org/whats-coming-up-at-robocup2026/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Mon, 29 Jun 2026 08:03:25 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[RoboCup]]></category>
		<category><![CDATA[RoboCup2026]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220072</guid>

					<description><![CDATA[This year, RoboCup will be held in Incheon, South Korea, from 2-6 July. The event will see teams take part in competitions, training sessions, and a symposium. It&#8217;s an exciting time for RoboCup, as there have been some updates to the leagues and competition format. Most prominently, the soccer leagues will have a primary focus [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://aihub.org/wp-content/uploads/2026/05/Screenshot-2026-05-29-at-10.35.28.jpeg" alt="" width="1854" height="966" class="alignnone size-full wp-image-20407" /></p>
<p>This year, <a href="https://2026.robocup.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup will be held in Incheon, South Korea</a>, from 2-6 July. The event will see teams take part in competitions, training sessions, and a symposium. </p>
<p>It&#8217;s an exciting time for RoboCup, as there have been some <a href="https://www.robocup.org/news/181" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">updates to the leagues and competition format</a>. Most prominently, the soccer leagues will have a primary focus on humanoid robots.</p>
<h3>The leagues and their competitions</h3>
<p>You can find out more about the different leagues and the competition schedules and details at these links:</p>
<ul>
<li>RoboCupSoccer
<ul>
<li><a href="https://hsl.robocup.org" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Humanoid</a></li>
<li><a href="https://msl.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Middle size</a></li>
<li><a href="https://ssl.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Small size</a></li>
<li><a href="https://ssim.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Simulation</a></li>
</ul>
</li>
<li>RoboCupRescue
<ul>
<li><a href="https://rrl.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Robot</a></li>
<li><a href="https://rescuesim.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Simulation</a></li>
</ul>
</li>
<li><a href="http://athome.robocup.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">RoboCup@Home</a></li>
<li><a href="https://robocup.org/leagues/36" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Industrial</a></li>
<li>RoboCupJunior
<ul>
<li><a href="https://junior.robocup.org/soccer/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Soccer</a></li>
<li><a href="https://junior.robocup.org/onstage/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Onstage</a></li>
<li><a href="https://junior.robocup.org/rescue/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Rescue</a></li>
</ul>
</li>
</ul>
<h3>WEROB</h3>
<p>A workshop focused on sharing projects, experiences, and innovations in educational robotics. This session is geared towards students, mentors, and educators. Find out more <a href="https://2026.robocup.org/werob/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
<h3>Symposium</h3>
<p>The RoboCup symposium will take place on 6 July. More information can be found <a href="https://2026.robocup.org/symposium/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>. </p>
<p>There will be two keynote talks:</p>
<ul>
<li><strong>Hyun Myung</strong>, Spatial Intelligence for Autonomous Robot Navigation in the Wild</li>
<li><strong>Gentiane Venture</strong>, From function to meaning: Making robots that understand and belong</li>
</ul>
<p>Find out more at the <a href="https://2026.robocup.org/symposium/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">event website</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 162 &#8211; The robot doctor will see you now</title>
		<link>https://robohub.org/robot-talk-episode-162-the-robot-doctor-will-see-you-now/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 26 Jun 2026 11:22:25 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220287</guid>

					<description><![CDATA[Since the first robot-assisted surgery was performed, over 40 years ago, major advances in robotics, computer vision and artificial intelligence have fundamentally changed medicine and healthcare. Innovative new technologies are already aiding skilled medical professionals in diagnosis, surgery, rehabilitation and beyond. But many questions remain: What ethical issues arise as medical tools become increasingly autonomous? [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone size-medium wp-image-220295" src="https://robohub.org/wp-content/uploads/2026/06/Group-Photo-425x361.png" alt="" width="425" height="361" srcset="https://robohub.org/wp-content/uploads/2026/06/Group-Photo-425x361.png 425w, https://robohub.org/wp-content/uploads/2026/06/Group-Photo-1024x869.png 1024w, https://robohub.org/wp-content/uploads/2026/06/Group-Photo-768x652.png 768w, https://robohub.org/wp-content/uploads/2026/06/Group-Photo-1536x1303.png 1536w, https://robohub.org/wp-content/uploads/2026/06/Group-Photo-2048x1738.png 2048w" sizes="(max-width: 425px) 100vw, 425px" /></p>
<p>Since the first robot-assisted surgery was performed, over 40 years ago, major advances in robotics, computer vision and artificial intelligence have fundamentally changed medicine and healthcare. Innovative new technologies are already aiding skilled medical professionals in diagnosis, surgery, rehabilitation and beyond. But many questions remain: What ethical issues arise as medical tools become increasingly autonomous? How do we regulate technologies that can learn and change over time? And how can we ensure that cutting-edge medical devices are accessible to all?</p>
<p>In this special live recording at the <a href="https://www.greatexhibitionroadfestival.co.uk/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Great Exhibition Road Festival</a> in London, Claire chatted to George Mylonas (Imperial College London), Antonia Tzemanaki (University of Bristol) and Tom Vercauteren (King’s College London) about robotics and AI in medicine and healthcare.</p>
<p><iframe src="https://play.libsyn.com/embed/episode/id/41791270/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe></p>
<p><a href="https://profiles.imperial.ac.uk/george.mylonas" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external"><strong>George Mylonas</strong></a> is an Associate Professor in Robotics and Technology in Cancer at Imperial College London, and the director of the <a href="https://www.imperial.ac.uk/hamlyn-centre/research/research-groups/human-centred-automation-robotics-and-monitoring/" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external">Human-centred Automation, Robotics and Monitoring in Surgery lab</a> at The Hamlyn Centre, Institute of Global Health Innovation and the Department of Surgery &amp; Cancer, Faculty of Medicine. He is leading research in the areas of surgical robotics, soft robotics, minimal access surgical technology, perceptual human-robot and human-computer interfaces, and smart data-driven operating theatres. He is a member of the European Association of Endoscopic Surgery Technology Committee.</p>
<p><a href="https://research-information.bris.ac.uk/en/persons/antonia-tzemanaki/" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external"><strong>Antonia Tzemanaki</strong></a> is a Senior Lecturer in Robotics at the University of Bristol and a core member of the Bristol Robotics Laboratory. She leads the <a href="https://www.dexterousrobotlab.com/" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external">Dexterous Manipulation and Wearable Robotics group</a> which develops robotic simulators and interventions, including robotic needle steering, abdominal, urology, skull and hand models, for surgical and physical therapy treatments of disease including cancers, neurological, prostate and urinary disorders. The group provides wide expertise in precision manipulation, robot hands, hand exoskeletons, kinematics, haptics and wearable robotics, especially with applications in surgery, preventative medicine, rehabilitation, physiotherapy and dexterous tele-operation.</p>
<p><a href="https://www.kcl.ac.uk/people/tom-vercauteren" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external"><strong>Tom Vercauteren</strong></a> is a Professor of Interventional Image Computing at King’s College London, where he leads the <a href="https://cai4cai.ml/" target="_blank" rel="noreferrer noopener follow external" data-wpel-link="external">Contextual Artificial Intelligence for Computer Assisted Interventions research group</a>. His research focuses on medical image computing, machine learning and imaging for surgery and interventional sciences. He is also co-founder and Chief Scientific Officer of Hypervision Surgical, a spin-out company developing safe, non-invasive optical imaging for use during surgery. His work is now used in hundreds of hospitals worldwide. Tom is also a supporter of open-source software and patient involvement.</p>
<p>&nbsp;</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>AI brings object-level vision prosthetics closer to reality</title>
		<link>https://robohub.org/ai-brings-object-level-vision-prosthetics-closer-to-reality/</link>
		
		<dc:creator><![CDATA[EPFL]]></dc:creator>
		<pubDate>Tue, 23 Jun 2026 10:09:29 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220103</guid>

					<description><![CDATA[Image credit: By Jeff Dahl &#8211; Own work by uploader, Based on the public domain document: [1], CC BY-SA 3.0, Link By Stephanie Parker This research from the NeuroAI Lab of Martin Schrimpf, part of EPFL’s Schools of Computer and Communication Sciences and Life Sciences, uses AI models to predict exactly where to stimulate the [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.59.14-1024x719.jpeg" alt="" width="1024" height="719" class="alignnone size-large wp-image-220104" srcset="https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.59.14-1024x719.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.59.14-425x299.jpeg 425w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.59.14-768x539.jpeg 768w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.59.14.jpeg 1082w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Image credit: By <a href="//commons.wikimedia.org/wiki/User:Jeff_Dahl" title="User:Jeff Dahl" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Jeff Dahl</a> &#8211; Own work by uploader, Based on the public domain document: <a rel="nofollow external noopener noreferrer" class="external autonumber" href="http://www.i-see.org/block_letter_eye_chart.pdf" data-wpel-link="external" target="_blank">[1]</a>, <a href="https://creativecommons.org/licenses/by-sa/3.0" title="Creative Commons Attribution-Share Alike 3.0" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">CC BY-SA 3.0</a>, <a href="https://commons.wikimedia.org/w/index.php?curid=4262200" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Link</a></em></p>
<p><strong>By Stephanie Parker</strong></p>
<p>This research from the NeuroAI Lab of Martin Schrimpf, part of EPFL’s Schools of <a href="https://www.epfl.ch/schools/ic/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Computer and Communication Sciences</a> and <a href="https://www.epfl.ch/schools/sv/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Life Sciences</a>, uses AI models to predict exactly where to stimulate the brain to evoke images of faces and specific objects in the users instead of simply evoking spots of light. The <a href="https://arxiv.org/abs/2510.03684" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">models</a> developed at EPFL were used by Dutch researchers for live trials on sighted monkeys. The preliminary results, presented in April at the <a href="https://iclr.cc/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">International Conference on Learning Representations</a>, show very promising implications for vision in humans as well.</p>
<p>“The motivation for this project is that there are many people with visual deficits that are irreparable, in the sense that somewhere along the visual processing stream, starting with the retina, there is a deficit which cannot be repaired,” says Johannes Mehrer, a scientist in the NeuroAI lab who led the research. “One way of tackling this problem is to develop a visual prosthesis.”</p>
<p>There are multiple kinds of visual prosthetics including retinal, optical nerve, and cortical. Retinal prosthetics are placed somewhere on the retina, and optical nerve prosthetics are used when the retina is too damaged for an implant and the optical nerve can be stimulated instead. When neither the retina nor optical nerve can be implanted, cortical prosthetics are used. These bypass the retina and optical nerve entirely and work instead by stimulating the visual cortex, using electrodes to “draw” images onto it. However, thus far, this approach is limited in that it targets lower-level regions of the brain where it is only possible to project light flashes and simple shapes. There are also hardware constraints because multiple electrodes are needed to stimulate different areas at the same time, but only a certain number of electrodes can be used in one area.</p>
<p>“The images they can elicit, in this case simple symbols, are really limited in their complexity,” Mehrer explains. “At the moment, existing approaches to visual prostheses couldn’t elicit the percept of a more complex visual object such as a house or a car.”</p>
<p>Higher-level visual regions of the brain underlie the processing of more complex objects and could thus serve as a target for a new generation of visual prostheses allowing for eliciting images of faces, houses, and other objects. However, these higher-level regions are less accessible, because it is not known exactly where and how to stimulate them. This is where the AI model comes in.</p>
<h4>Towards restoring meaningful sight</h4>
<p>“We had the idea to use an artificial neural network, in this case a specific type called a topographic neural network, to test various patterns of brain stimulations in these higher-level regions of the brain and simulate their outcomes,” Mehrer says. “We can then run all sorts of simulations using different combinations of different parameters that would otherwise take up a lot of experimental time and would cost a lot of money.”</p>
<p>The EPFL researchers, working entirely on computers, set up a model to select the best combination of images with the specific pattern of stimulation. Following their results, a team of resarchers in Amsterdam decided to test the model’s prediction on two of their monkeys who already had implants for other experiments not involving EPFL.</p>
<p>“Our model turned out to be quite efficient in predicting which stimulation pattern would yield a strong effect on the monkeys’ behavior with respect to visual object recognition,” says Martin Schrimpf, head of the NeuroAI Lab. “Our models can do the image selection, but the more crucial part is that given an image, it can tell us what the optimal stimulation pattern for a particular desired behavior is.”</p>
<p>What the researchers have been able to show so far with this work is that they can shape object perception, meaning that if a visual stimulus is presented, they can bias its representation in the brain. However, they cannot yet create object perception out of nothing. Stimulating the cortex while there is no visual stimulus presented would be their next step towards restoring meaningful sight to the blind.</p>
<p>&#8220;The monkey saw an image already, and then we were able to basically distort it to change the perception in somewhat predictable ways,&#8221; says Schrimpf. &#8220;The bigger goal will be to evoke a percept from scratch: to make someone see something meaningful even when their eyes aren&#8217;t delivering a usable image.&#8221;</p>
<p>This work showing that model-guided brain stimulation could lead to more advanced visual prosthetics could also be applied to hearing prosthetics. Through a grant from the Horton Health Foundation, Schrimpf and his team will next investigate if this kind of modeling works for auditory stimulation.</p>
<p>“Cochlear implants are great, but they are also not perfect in many ways, and they don&#8217;t really fully restore auditory processing,” says Schrimpf. “Our idea is to develop these kinds of topographic models that can predict what stimulation does to neural activity for auditory processing as well.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>AURA Foresight Reaches Global XPRIZE Wildfire Finals in Alaska</title>
		<link>https://robohub.org/aura-foresight-reaches-global-xprize-wildfire-finals-in-alaska/</link>
		
		<dc:creator><![CDATA[Sabine Hauert]]></dc:creator>
		<pubDate>Fri, 19 Jun 2026 16:42:23 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[swarm]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220225</guid>

					<description><![CDATA[One of only four teams remaining from more than 130 competitors worldwide, our team AURA Foresight is developing autonomous technology to stop wildfires before they grow out of control. AURA Foresight has been selected as a finalist in the prestigious XPRIZE Wildfire Autonomous Wildfire Response competition, emerging as one of just four teams remaining from [&#8230;]]]></description>
										<content:encoded><![CDATA[<p>One of only four teams remaining from more than 130 competitors worldwide, our team <a href="https://assets-us-01.kc-usercontent.com/9bc15d1f-8a5c-007d-b507-e3496e85af86/b4944471-84e0-4140-8073-200b9e32f530/XPWF_FinalistTeams_Autonomous_6.12.2026-2.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">AURA Foresight</a> is developing autonomous technology to stop wildfires before they grow out of control.</p>
<p>AURA Foresight has been selected as a finalist in the prestigious <a href="https://www.xprize.org/competitions/wildfire" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">XPRIZE Wildfire Autonomous Wildfire Response competition</a>, emerging as one of just four teams remaining from more than 130 teams from around the world.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/IMG_4466-scaled.jpg" alt="" width="2560" height="1920" class="aligncenter size-full wp-image-220230" srcset="https://robohub.org/wp-content/uploads/2026/06/IMG_4466-scaled.jpg 2560w, https://robohub.org/wp-content/uploads/2026/06/IMG_4466-425x319.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/IMG_4466-1024x768.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/IMG_4466-768x576.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/IMG_4466-1536x1152.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/IMG_4466-2048x1536.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>XPRIZE Wildfire is a four-year, US$11 million global competition designed to accelerate breakthrough technologies capable of ending destructive wildfires. The Autonomous Wildfire Response track, worth US$5 million, challenges teams to autonomously detect, verify and respond to wildfire ignitions across a 1,000 km² landscape within just ten minutes. The finals will take place in Nenana, Alaska, where teams will demonstrate their technologies in realistic wildfire response scenarios.</p>
<p>Being selected as a finalist places AURA Foresight among a small group of innovators developing the next generation of tools to help communities, land managers and firefighters respond to wildfires faster and more effectively.</p>
<p>As wildfires become more frequent and severe worldwide, AURA Foresight is developing technology that helps stop fires before they become disasters. The team&#8217;s autonomous wildfire intelligence and intervention system is designed to detect ignitions within minutes and coordinate a rapid response while fires are still small and manageable.</p>
<div class="keep-aspect"><iframe title="AURA Foresight at XPRIZE Wildfire Finals" width="500" height="281" src="https://www.youtube-nocookie.com/embed/Y-91z4estdk?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p><strong>Detect Early. Verify Quickly. Intervene Immediately.</strong></p>
<p>AURA Foresight combines fixed sensors, artificial intelligence and swarms of autonomous flying robots into a seamless detect–verify–act capability.</p>
<p>Rather than fighting large wildfires after they have taken hold, the system is designed to identify potential ignitions, verify threats and intervene at the earliest possible stage, when a small spark can still be safely contained before becoming a major incident.</p>
<p>The platform continuously monitors landscapes using optical and thermal sensors, automatically identifies potential ignitions using AI, dispatches flying robots to verify threats, and coordinates rapid intervention before small fires can grow into destructive wildfires.</p>
<p>Unlike many wildfire technologies that rely on specialised infrastructure or proprietary hardware, AURA Foresight has been designed from the outset to be practical, affordable and easy to deploy.</p>
<p>Key advantages include:</p>
<ul>
<li>Out-of-the-box deployment with minimal setup requirements.</li>
<li>Adaptability to any environment, from forests and remote wilderness to critical infrastructure corridors.</li>
<li>Scalability from a handful to dozens of flying robots, depending on operational needs.</li>
<li>Compatibility with different aircraft and robot platforms, avoiding vendor lock-in.</li>
<li>Built on commercially available technologies, making advanced wildfire protection accessible and achievable for organisations of all sizes.</li>
</ul>
<p>The result is a system that can help agencies move from passive monitoring and delayed response to proactive, automated intervention.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b.jpg" alt="" width="1600" height="1200" class="aligncenter size-full wp-image-220239" srcset="https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b.jpg 1600w, https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b-425x319.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b-1024x768.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b-768x576.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/e81ba181-ba35-4a23-ac97-e06d90bd679b-1536x1152.jpg 1536w" sizes="(max-width: 1600px) 100vw, 1600px" /><br />
<img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6.jpg" alt="" width="1600" height="1066" class="aligncenter size-full wp-image-220245" srcset="https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6.jpg 1600w, https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6-1024x682.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/08a5ac1c-4088-4ffa-b1e2-18dc23c28fa6-1536x1023.jpg 1536w" sizes="(max-width: 1600px) 100vw, 1600px" /></p>
<p><strong>Developed With Firefighters, For Firefighters</strong></p>
<p>AURA Foresight&#8217;s approach is shaped by close collaboration with firefighters and emergency response professionals. The consortium works directly with Lancashire Fire and Rescue Service in the United Kingdom and with wildfire response experts in Canada and Australia to ensure the technology addresses real operational challenges and integrates effectively into existing emergency response workflows.</p>
<p>This combination of frontline expertise and advanced robotics helps ensure that the technology remains focused on supporting firefighters and enhancing their capabilities in the field.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-scaled.jpg" alt="" width="2560" height="1730" class="aligncenter size-full wp-image-220235" srcset="https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-scaled.jpg 2560w, https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-425x287.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-1024x692.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-768x519.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-1536x1038.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/01fbbf91-5b58-43df-b678-cd58781f4eb0-2048x1384.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>&#8220;It&#8217;s amazing what can be achieved when great people come together around a shared purpose,&#8221; said Dr Georgios Tzoumas, Team Co-Lead of AURA Foresight and Research Fellow at the University of Bristol.</p>
<p>&#8220;Our team has been working on autonomous wildfire detection and intervention technologies for more than six years. Reaching the XPRIZE finals is an exciting milestone because it feels like the solution is finally within reach. By combining AI, swarm robotics and close collaboration with firefighters, we&#8217;re showing that it&#8217;s possible to tackle wildfires while they&#8217;re still small, before they grow out of control. We can&#8217;t wait to demonstrate our technology in the field in Alaska.&#8221;</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/Yinan-scaled.jpg" alt="" width="2560" height="1701" class="aligncenter size-full wp-image-220236" srcset="https://robohub.org/wp-content/uploads/2026/06/Yinan-scaled.jpg 2560w, https://robohub.org/wp-content/uploads/2026/06/Yinan-425x282.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/Yinan-1024x680.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/Yinan-768x510.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/Yinan-1536x1020.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/Yinan-2048x1361.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p><strong>A Global Consortium Combining Expertise from the UK and Australia</strong></p>
<p>AURA Foresight is a unique international collaboration bringing together AURA in the United Kingdom and Fire Foresight in Australia.</p>
<p>The consortium includes the University of Bristol, Bristol Robotics Laboratory, the University of Sheffield, Lancashire Fire and Rescue Service, Fire Foresight, SkyFly Drones, Southern Denmark University, Manchester University, Indicium Dynamics, Robotic Cats, Taz Drone Solutions and Little Place Labs.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2.jpg" alt="" width="1600" height="1066" class="aligncenter size-full wp-image-220233" srcset="https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2.jpg 1600w, https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2-1024x682.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/31a50649-5eb9-4387-82bc-0b6f28845929-2-1536x1023.jpg 1536w" sizes="(max-width: 1600px) 100vw, 1600px" /></p>
<p><a href="https://www.fireforesight.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Fire Foresight</a> CEO Rob Vernon commented, “Our approach with the XPRIZE competition has been to bring all the pieces of the wildfire jigsaw puzzle together, and that capability only truly scales when it’s done with partners from around the world and on the ground. In Australia, we have been building the largest network of bushfire detection capabilities and the partnerships that we’ve formed, and continue to form, through this competition allow us to focus our attention on the autonomous mitigation and suppression capabilities, so desperately needed to address the challenges faced by wildfire and climate change”.</p>
<div class="keep-aspect"><iframe title="XPRIZE - Pre Alaska Deployment - Full Video with Music" width="500" height="281" src="https://www.youtube-nocookie.com/embed/f3_KTJrPy2s?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Together, these partners combine world-leading expertise in swarm robotics, autonomous systems, artificial intelligence, computer vision, aerial robotics, wildfire operations and field deployment.</p>
<p>By bringing together researchers, engineers, firefighters and technology innovators from across two continents, AURA Foresight is demonstrating how international collaboration can accelerate solutions to one of the world&#8217;s most pressing climate challenges.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/698c7d29-b248-4448-997a-3ca26d9d84e3.jpg" alt="" width="1200" height="1600" class="aligncenter size-full wp-image-220243" srcset="https://robohub.org/wp-content/uploads/2026/06/698c7d29-b248-4448-997a-3ca26d9d84e3.jpg 1200w, https://robohub.org/wp-content/uploads/2026/06/698c7d29-b248-4448-997a-3ca26d9d84e3-319x425.jpg 319w, https://robohub.org/wp-content/uploads/2026/06/698c7d29-b248-4448-997a-3ca26d9d84e3-768x1024.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/698c7d29-b248-4448-997a-3ca26d9d84e3-1152x1536.jpg 1152w" sizes="(max-width: 1200px) 100vw, 1200px" /></p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/a030ce8f-d7c5-41e5-ba00-1a691c62d889.jpg" alt="" width="1500" height="2000" class="aligncenter size-full wp-image-220241" srcset="https://robohub.org/wp-content/uploads/2026/06/a030ce8f-d7c5-41e5-ba00-1a691c62d889.jpg 1500w, https://robohub.org/wp-content/uploads/2026/06/a030ce8f-d7c5-41e5-ba00-1a691c62d889-319x425.jpg 319w, https://robohub.org/wp-content/uploads/2026/06/a030ce8f-d7c5-41e5-ba00-1a691c62d889-768x1024.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/a030ce8f-d7c5-41e5-ba00-1a691c62d889-1152x1536.jpg 1152w" sizes="(max-width: 1500px) 100vw, 1500px" /></p>
<p>As destructive wildfires continue to increase in frequency and severity around the world, AURA Foresight&#8217;s progression to the XPRIZE Wildfire finals highlights a new approach to wildfire management: tackling fires in their earliest moments, before they can grow out of control and threaten communities, ecosystems and critical infrastructure.</p>
<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/4dadea27-e13e-4de5-8b92-af1f185f9ac3-3.jpg" alt="" width="1536" height="2048" class="aligncenter size-full wp-image-220234" srcset="https://robohub.org/wp-content/uploads/2026/06/4dadea27-e13e-4de5-8b92-af1f185f9ac3-3.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/4dadea27-e13e-4de5-8b92-af1f185f9ac3-3-319x425.jpg 319w, https://robohub.org/wp-content/uploads/2026/06/4dadea27-e13e-4de5-8b92-af1f185f9ac3-3-768x1024.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/4dadea27-e13e-4de5-8b92-af1f185f9ac3-3-1152x1536.jpg 1152w" sizes="(max-width: 1536px) 100vw, 1536px" /><br />
<img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-scaled.jpg" alt="" width="2560" height="1959" class="aligncenter size-full wp-image-220246" srcset="https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-scaled.jpg 2560w, https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-425x325.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-1024x783.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-768x588.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-1536x1175.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/IMG_4281-4-2048x1567.jpg 2048w" sizes="(max-width: 2560px) 100vw, 2560px" /></p>
<p>Our motto is &#8211; &#8220;Detect early. Verify quickly. Intervene immediately. Stop wildfires before they become disasters.&#8221; Fingers crossed for a good performance in our finals this weekend! </p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 161 &#8211; Collaborative haptic systems, with Allison Okamura</title>
		<link>https://robohub.org/robot-talk-episode-161-collaborative-haptic-systems-with-allison-okamura/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 19 Jun 2026 12:07:34 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220188</guid>

					<description><![CDATA[Claire chatted to Allison Okamura from Stanford University about developing advanced robotic systems for haptic (touch) interaction. Allison Okamura is the Richard W. Weiland Professor of Engineering at Stanford University. Her academic interests include haptics, teleoperation, virtual reality, medical robotics, soft robotics, rehabilitation, and education. Allison is Director of Graduate Studies for Mechanical Engineering at [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone size-medium wp-image-220190" src="https://robohub.org/wp-content/uploads/2026/06/Allison-Okamura-386x425.jpg" alt="" width="386" height="425" srcset="https://robohub.org/wp-content/uploads/2026/06/Allison-Okamura-386x425.jpg 386w, https://robohub.org/wp-content/uploads/2026/06/Allison-Okamura.jpg 630w" sizes="(max-width: 386px) 100vw, 386px" /></p>
<p>Claire chatted to Allison Okamura from Stanford University about developing advanced robotic systems for haptic (touch) interaction.</p>
<p><iframe src="https://play.libsyn.com/embed/episode/id/41665545/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe></p>
<p><a title="" href="https://profiles.stanford.edu/allison-okamura" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Allison Okamura</a> is the Richard W. Weiland Professor of Engineering at Stanford University. Her academic interests include haptics, teleoperation, virtual reality, medical robotics, soft robotics, rehabilitation, and education. Allison is Director of Graduate Studies for Mechanical Engineering at Stanford University, a deputy director of the Wu Tsai Stanford Neurosciences Institute, a Science Fellow of the Hoover Institution and a founding faculty member and executive committee member of the Stanford Robotics Center.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>New research enables a robot to chart a better course</title>
		<link>https://robohub.org/new-research-enables-a-robot-to-chart-a-better-course/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Wed, 17 Jun 2026 10:06:45 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://news.mit.edu/2026/new-research-enables-robot-to-chart-better-course-0519</guid>

					<description><![CDATA[By rapidly generating a smooth path plan that cuts travel time and avoids obstacles, the open-source “MIGHTY” system could streamline disaster recovery and parcel delivery.]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/05/MIT-MightyPlanner-01-press_0.jpg" alt="" width="900" height="600" class="alignnone size-full wp-image-220078" srcset="https://robohub.org/wp-content/uploads/2026/05/MIT-MightyPlanner-01-press_0.jpg 900w, https://robohub.org/wp-content/uploads/2026/05/MIT-MightyPlanner-01-press_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2026/05/MIT-MightyPlanner-01-press_0-768x512.jpg 768w" sizes="(max-width: 900px) 100vw, 900px" /><em>A figure shows multiple flight pathways as a UAV starts from the center and flies toward 24 goals (dots around perimeter). The flight pathways are mainly red and end in cool colors, showing reduced speed. The rainbow clouds represent obstacles, with cooler colors representing taller obstacles. Credit: Courtesy of the researchers.</em></p>
<p><strong>By Adam Zewe</strong></p>
<p>In the aftermath of a devastating earthquake, unpiloted aerial vehicles (UAVs) could fly through a collapsed building to map the scene, giving rescuers information they need to quickly reach survivors.&nbsp;</p>
<p>But this remains an extremely challenging problem for an autonomous robot, which would need to swiftly adjust its trajectory to avoid sudden obstacles while staying on course.</p>
<p>Researchers from MIT and the University of Pennsylvania developed a new trajectory-planning system that tackles both challenges at once. Their technique enables a UAV to react to obstacles in milliseconds while staying on a smooth flight path that minimizes travel time.&nbsp;</p>
<p>Their system uses a new mathematical formulation that ensures the robot travels safely to its destination along a feasible path, and that is less computationally intensive than other techniques. In this way, it generates smoother trajectories faster than state-of-the-art methods.</p>
<p>The trajectory planner is also efficient enough for real-time flight using only the robot’s onboard computer and sensors.&nbsp;</p>
<p>Named&nbsp;MIGHTY, the open-source system does not require proprietary software packages that can cost hundreds of thousands of dollars. It could be more readily deployed in a wider variety of real-world settings.</p>
<p>In addition to search-and-rescue, MIGHTY could be utilized in applications like last-mile delivery in urban spaces, where UAVs need to avoid buildings, wires, and people, or in industrial inspection of complex structures, such as wind turbines.</p>
<p>“MIGHTY achieves comparable or better performance using only open-source tools, which means any researcher, student, or company — anywhere in the world — can use it freely. By removing this cost barrier, MIGHTY helps democratize high-performance trajectory planning and opens the door for a much broader community to build on this work,” says Kota Kondo, an aeronautics and astronautics graduate student and lead author of a paper on this trajectory planner.</p>
<p>Kondo is joined on the paper by Yuwei Wu, a graduate student at the University of Pennsylvania; Vijay Kumar, a professor at UPenn; and senior author Jonathan P. How, a Ford&nbsp;professor of aeronautics and astronautics and a principal investigator in the Laboratory for Information and Decision Systems (LIDS) and the Aerospace Controls Laboratory (ACL)&nbsp;at MIT. The research <a href="https://ieeexplore.ieee.org/document/11474851" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">appears in <em>IEEE Robotics and Automation Letters</em></a>.</p>
<p><strong>Overcoming trade-offs</strong>&nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp;&nbsp;</p>
<p>When Kondo was a child, the Fukushima Daiichi nuclear accident occurred following the Great East Japan Earthquake. With school cancelled, Kondo was stuck at home and watched the news every day as workers explored and secured the reactor site. Some workers still had to enter hazardous areas to contain the damage and assess the situation, exposing them to high doses of radioactive material.</p>
<p>“I became passionate about creating autonomous robots that can go into these dynamic and dangerous situations, then come back and report to humans who stay out of harm’s way,” Kondo says.</p>
<p>This task requires a strong trajectory planner, which is software that decides the path a robot should follow to safely get from point A to point B.&nbsp;</p>
<p>But many existing systems force tradeoffs that limit performance.&nbsp;</p>
<p>While some commercial systems can rapidly generate smooth trajectories, they can cost hundreds of thousands of dollars. Open-source alternatives often underperform compared to commercial solvers or are difficult to use.&nbsp;&nbsp; &nbsp; &nbsp;</p>
<p>With MIGHTY, Kondo and his colleagues developed an open-source system that produces high-quality, smooth trajectories while reacting to obstacles in real-time, and which runs fast enough for flight using only onboard components.</p>
<p>To do this, they overcame a key challenge that limits many open-source systems.&nbsp;</p>
<p>These methods usually estimate how long it will take the robot to get from point A to point B as a first step. From that fixed estimation of travel time, the planner finds the best path to reach the destination.</p>
<p>While using a fixed travel time allows the planner to rapidly generate a trajectory, it has drawbacks. For one, if the UAV must go far out of its way to avoid obstacles, it could be forced to crank up the speed to meet the fixed travel-time budget. This makes it harder to avoid sudden hazards.</p>
<p><strong>A MIGHTY method</strong></p>
<p>Instead, MIGHTY uses a mathematical technique, called a Hermite spline, that optimizes the travel time and flight path together, in a single step, to form a smooth trajectory that can be precisely controlled.</p>
<p>“Optimizing the spatial and temporal components together gets us better results, but now the optimization becomes so much bigger that it is harder to solve in a feasible amount of time,” Kondo says.</p>
<p>The researchers used a clever technique to reduce this computational overhead.&nbsp;</p>
<p>Instead of generating a trajectory from scratch each time, MIGHTY makes an initial guess of a trajectory. Then it refines the trajectory through an iterative optimization, using a map of the scene generated by the UAV’s lidar sensors.</p>
<p>“We can make a decent guess of what the trajectory should be, which is a lot faster than generating the entire thing from nothing,” Kondo says.</p>
<p>This enables MIGHTY to react in real-time to unknown obstacles while keeping the trajectory smooth and minimizing travel time. The system utilizes the UAV’s onboard components, which is important for applications where a robot might travel far from a base station.</p>
<p>In simulated experiments, MIGHTY needed only about 90 percent of the computation time required by state-of-the-art methods, while safely reaching its destination about 15 percent faster than these approaches.&nbsp;</p>
<p>When they tested the system on real robots, it reached a speed of 6.7 meters per second while avoiding every obstacle that appeared in its path.</p>
<p>“With MIGHTY, everything is integrated in one piece. It doesn’t need to talk to any other piece of software to get a solution. This helps us be even faster than some of the commercial solvers,” Kondo says.</p>
<p>In the future, the researchers want to enhance MIGHTY so it can be used to control multiple robots at once and conduct more flight experiments in challenging environments. They hope to continue improving the open-source system based on user feedback.</p>
<p>“MIGHTY makes an important contribution to agile robot navigation by revisiting the trajectory representation itself. Hermite splines have already been successfully used in visual simultaneous localization and mapping, and it is nice to see their advantages now being exploited for trajectory planning in mobile robots. By enabling joint optimization of path geometry, timing, velocity, and acceleration while retaining local control of the trajectory, MIGHTY gives robots more freedom to compute fast, dynamically feasible motions in cluttered environments,” says Davide Scaramuzza, professor and director of the Robotics and Perception Group at the University of Zurich, who was not involved with this research.</p>
<p>This research was funded, in part, by the United States Army Research Laboratory and the Defense Science and Technology Agency in Singapore.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Entangled robotic matter with cohesive motion</title>
		<link>https://robohub.org/entangled-robotic-matter-with-cohesive-motion/</link>
		
		<dc:creator><![CDATA[Cornell University]]></dc:creator>
		<pubDate>Mon, 15 Jun 2026 10:06:23 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220091</guid>

					<description><![CDATA[By Syl Kacapyr Cornell engineers have developed a robotic collective that behaves less like a machine and more like a material that flows, reshapes and adapts to its environment without centralized control. The system, called the Cross-Link Collective, consists of dozens of small robots that have limited mobility individually, but together exhibit coordinated and sustained [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.38.29-1024x766.jpeg" alt="" width="1024" height="766" class="alignnone size-large wp-image-220092" srcset="https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.38.29-1024x766.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.38.29-425x318.jpeg 425w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.38.29-768x574.jpeg 768w, https://robohub.org/wp-content/uploads/2026/06/Screenshot-2026-06-03-at-10.38.29.jpeg 1522w" sizes="(max-width: 1024px) 100vw, 1024px" /><br />
<strong>By Syl Kacapyr</strong></p>
<p>Cornell engineers have developed a robotic collective that behaves less like a machine and more like a material that flows, reshapes and adapts to its environment without centralized control.</p>
<p>The system, called the Cross-Link Collective, consists of dozens of small robots that have limited mobility individually, but together exhibit coordinated and sustained motion. The research, <a href="https://www.science.org/doi/10.1126/scirobotics.aec6393" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">published May 20 in Science Robotics</a>, demonstrates a robotic system that resembles soft matter, continuously deforming and reorganizing as it moves, driven by what researchers call mechanical intelligence.</p>
<p>“Instead of relying on explicit computation and communication, the system shifts the intelligence into the shape of the robots and their physical interactions,” said corresponding author Kirstin Petersen, associate professor of electrical and computer engineering and the Aref and Manon Lahham Faculty Fellow in the Cornell Duffield College of Engineering. “We’re leveraging the contact dynamics to let useful behaviors emerge, so the system naturally settles into configurations that reduce internal stresses and improve motion.”</p>
<p>Each robotic module measures about 200 millimeters in length and 20 millimeters in width, and contains a small motor that drives it to oscillate between two shapes, an “I” and a “U.” These oscillations generate forces against the ground, allowing the modules to inch forward and jostle into one another. At each end of the module are weak Velcro patches, enabling them to temporarily latch and unlatch onto neighboring modules.</p>
<p>On their own, the modules move slowly and inefficiently. But when they entangle into chains, they begin to move collectively, self-organizing into shifting configurations that prove resilient in challenging environments.</p>
<p><div style="width: 1280px;" class="wp-video"><video class="wp-video-shortcode" id="video-220091-14" width="1280" height="720" preload="metadata" controls="controls"><source type="video/mp4" src="https://robohub.org/wp-content/uploads/2026/06/WithControl_Rep1_100X-HD_1080-WEB-H264_4000.mp4?_=14" /><a href="https://robohub.org/wp-content/uploads/2026/06/WithControl_Rep1_100X-HD_1080-WEB-H264_4000.mp4" data-wpel-link="internal">https://robohub.org/wp-content/uploads/2026/06/WithControl_Rep1_100X-HD_1080-WEB-H264_4000.mp4</a></video></div><br />
<br />
On incline surfaces, chains of robotic modules moved more reliably than individuals, which often stalled depending on their orientation. In obstacle fields, the collective behaved like a flowing material in which connections formed to maintain cohesion, then broke apart to prevent jamming.</p>
<p>“It doesn’t matter if one module has a compromised battery or fails for other reasons,” said lead author Danna Ma, visiting lecturer in electrical and computer engineering. “The system stays functional because it can adapt. It is redundant and doesn’t depend on any single module.”</p>
<p>Despite the minimal approach, the researchers showed that even a small amount of computation can improve system properties. To enhance cohesion, isolated modules emit an audible distress signal, prompting nearby modules to slow down and allow the straggler to reconnect.</p>
<p>“There is no centralized sensing or control,” Ma said. “Each module can infer when it has lost contact with the group by how much it&#8217;s being jostled and then use an audible buzz to slow down nearby modules while it catches up. It&#8217;s as simple as that.”</p>
<p>Co-authors at the Georgia Institute of Technology developed the original design of the module, which Petersen and Ma refined over years of experimentation and statistical analysis to improve its ability to entangle and operate in large numbers. That process revealed how even subtle changes in module size and other characteristics can influence how effectively they connect and move as a group.</p>
<p>The Cross-Link Collective draws inspiration from active gels – materials whose molecular links continually form and dissolve while maintaining overall structure. The findings could help inspire new forms of soft-matter engineering, though the researchers mostly see the system as a tool for studying how mechanical intelligence can give rise to resilient emergent behaviors in robot collectives.</p>
<p>“It’s helpful for us to start thinking about what we can encode into the physics of a system itself, as robots are increasingly applied to real-world scenarios that are highly unreliable and dynamic,” Petersen said. “Counterintuitively, by giving up exact control over configurations and coordination, we gain a surprising range of useful behaviors.”</p>
]]></content:encoded>
					
		
		<enclosure url="https://robohub.org/wp-content/uploads/2026/06/WithControl_Rep1_100X-HD_1080-WEB-H264_4000.mp4" length="2395172" type="video/mp4" />

			</item>
		<item>
		<title>Robot Talk Episode 160 &#8211; Robotic blacksmiths, with Edward Mehr</title>
		<link>https://robohub.org/robot-talk-episode-160-robotic-blacksmiths-with-edward-mehr/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 12 Jun 2026 11:58:22 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220136</guid>

					<description><![CDATA[Claire chatted to Edward Mehr from Machina Labs about their RoboCraftsman that shapes complex metal parts for the aerospace, defence, and automotive industries. Edward Mehr is an entrepreneur and engineer specializing in advanced manufacturing, robotics, and artificial intelligence. As the Co-Founder and CEO of Machina Labs, he leads efforts to integrate AI-driven robotics into flexible, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone size-medium wp-image-220138" src="https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-425x368.jpg" alt="" width="425" height="368" srcset="https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-425x368.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-1024x886.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-768x665.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-1536x1330.jpg 1536w, https://robohub.org/wp-content/uploads/2026/06/Ed-Mehr-2048x1773.jpg 2048w" sizes="(max-width: 425px) 100vw, 425px" /></p>
<p>Claire chatted to Edward Mehr from Machina Labs about their RoboCraftsman that shapes complex metal parts for the aerospace, defence, and automotive industries.</p>
<p><iframe src="https://play.libsyn.com/embed/episode/id/41574465/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe></p>
<p>Edward Mehr is an entrepreneur and engineer specializing in advanced manufacturing, robotics, and artificial intelligence. As the Co-Founder and CEO of <a title="" href="https://machinalabs.ai" target="_blank" rel="noopener follow external noreferrer" data-wpel-link="external">Machina Labs</a>, he leads efforts to integrate AI-driven robotics into flexible, on-demand production systems. Under his leadership, Machina Labs is reshaping how industries such as aerospace, defence, and automotive approach metal forming and modern manufacturing. Before founding Machina Labs, Ed worked at leading technology companies, including Relativity Space, Averon, SpaceX, Google, and Microsoft.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Congratulations to the #AAMAS2026 best paper award winners</title>
		<link>https://robohub.org/congratulations-to-the-aamas2026-best-paper-award-winners/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Mon, 08 Jun 2026 10:02:11 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220089</guid>

					<description><![CDATA[The AAMAS 2026 best paper awards were presented at the 25th International Conference on Autonomous Agents and Multiagent Systems, which took place from 25-29 May 2025 in Paphos, Cyprus. The winners and nominees in the three categories (best paper, best student paper, best blue sky paper) are as follows: Best Paper Award Winner Developing Guidelines [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2025/05/winner-1548239_1280-1024x682.jpg" alt="" width="1024" height="682" class="alignnone size-large wp-image-214220" srcset="https://robohub.org/wp-content/uploads/2025/05/winner-1548239_1280-1024x682.jpg 1024w, https://robohub.org/wp-content/uploads/2025/05/winner-1548239_1280-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2025/05/winner-1548239_1280-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2025/05/winner-1548239_1280.jpg 1280w" sizes="(max-width: 1024px) 100vw, 1024px" /></p>
<p>The <a href="https://cyprusconferences.org/aamas2026/awards/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">AAMAS 2026 best paper awards</a> were presented at the <a href="https://cyprusconferences.org/aamas2026/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">25th International Conference on Autonomous Agents and Multiagent Systems</a>, which took place from 25-29 May 2025 in Paphos, Cyprus. The winners and nominees in the three categories (best paper, best student paper, best blue sky paper) are as follows:</p>
<hr>
<h3>Best Paper Award</h3>
<p></p>
<h4>Winner</h4>
<ul>
<li><strong>Developing Guidelines for Human-LLM Agent Teams: A Multi-Stakeholder Lens</strong>, <em>Mireia Yurrita, Davide Dell&#8217;Anna, Pradeep K. Murukannaiah, Catholijn M Jonker, and Pinar Yolum</em></li>
</ul>
<h4>Nominees</h4>
<ul>
<li><strong>UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles</strong>, <em>Neel P. Bhatt, Po-han Li, Kushagra Gupta, Rohan Siva, Daniel Milan, Alexander Todd Hogue, Sandeep P. Chinchali, David Fridovich-Keil, Zhangyang Wang, and Ufuk Topcu</em></li>
<li><strong>Ratio-Based Signaling for Source-Victim Separation in Swarm Fault Detection</strong>, <em>Longyin Cui</em></li>
<li><strong>The Impossibility of Strategyproof Rank Aggregation</strong>, <em>Manuel Eberl and Patrick Lederer</em></li>
<li><strong>Generalized Per-Agent Advantage Estimation for Multi-Agent Policy Optimization</strong>, <em>Seongmin Kim, Giseung Park, Woojun Kim, Jiwon Jeon, Seungyul Han, and Youngchul Sung</em></li>
<li><strong>R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory</strong>, <em>Maoyuan Li, Zhongsheng Wang, Haoyuan Li, and Jiamou Liu</em></li>
<li><strong>Defection at First Sight: Learning Partner Selection in Optional Social Dilemmas without Prior Information</strong>, <em>Benedict Russell, Chin-wing Leung, and Paolo Turrini</em></li>
<li><strong>Characterizing Consensuses in Belief Flow Networks</strong>, <em>Nicolas Schwind, Gauvain Bourgne, and Katsumi Inoue</em></li>
<li><strong>Grassroots Federation: Fair Democratic Governance at Scale</strong>, <em>Nimrod Talmon and Ehud Shapiro</em></li>
<li><strong>Health Facility Location in Ethiopia: Leveraging LLMs to Integrate Expert Knowledge into Algorithmic Planning</strong>, <em>Yohai Trabelsi, Guojun Xiong, Fentabil Getnet, Stéphane Verguet, and Milind Tambe</em></li>
<li><strong>MeCo: Enhancing LLM-Empowered Multi-Robot Collaboration via Similar Task Memoization</strong>, <em>Baiqing Wang, Helei Cui, Bo Zhang, Xiaolong Zheng, Bin Guo, and Zhiwen Yu</em></li>
</ul>
<hr>
<h3>Pragnesh Jay Modi Best Student Paper Award</h3>
<p></p>
<h4>Winner</h4>
<ul>
<li><strong>Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps</strong>, <em>Anwesha Das, John Duff, Jörg Hoffmann, and Vera Demberg</em></li>
</ul>
<h4>Nominees</h4>
<ul>
<li><strong>Efficiently Computing Equilibria in Budget-Aggregation Games</strong>, <em>Patrick Becker, Alexander Fries, Matthias Greger, and Erel Segal-Halevi</em></li>
<li><strong>Building Large-Scale Drone Defenses from Small-Team Strategies</strong>, <em>Grant Douglas, Stephen Franklin, Claudia Szabo, and Mingyu Guo</em></li>
<li><strong>Robust Counterfactual Inference in Markov Decision Processes</strong>, <em>Jessica Lally, Milad Kazemi, and Nicola Paoletti</em></li>
<li><strong>Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery</strong>, <em>Yue Zhang, Zhe Chen, Daniel Harabor, Pierre Le Bodic, and Peter J. Stuckey</em></li>
<li><strong>Reputation as a Solution to Cooperation Collapse in LLM-based MASs</strong>, <em>Siyue Ren, Wanli Fu, Xinkun Zou, Chen Shen, Yi Cai, Chu Chen, Zhen Wang, and Shuyue Hu</em></li>
</ul>
<hr>
<h3>Blue Sky Ideas Award</h3>
<p></p>
<h4>Winner</h4>
<ul>
<li><strong>Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments</strong>, <em>Florent Delgrange</em></li>
</ul>
<h4>Nominees</h4>
<ul>
<li><strong>Guiding Sociotechnical Systems toward Value-Norm Equilibrium</strong>, <em>Nirav Ajmeri, Marina De Vos, Davide Dell’Anna, Pradeep K. Murukannaiah, Vivek Nallur, Luis Gustavo Nardin, and Munindar P. Singh</em></li>
<li><strong>The Dynamic Turn in Strategy Logics</strong>, <em>Rustam Galimullin, Maksim Gladyshev, Munyque Mittelmann, and Nima Motamed</em></li>
</ul>
<hr>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robot Talk Episode 159 &#8211; Robot sensing and manipulation, with Maria Koskinopoulou</title>
		<link>https://robohub.org/robot-talk-episode-159-robot-sensing-and-manipulation-with-maria-koskinopoulou/</link>
		
		<dc:creator><![CDATA[Robot Talk]]></dc:creator>
		<pubDate>Fri, 05 Jun 2026 11:57:36 +0000</pubDate>
				<category><![CDATA[interviews]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220067</guid>

					<description><![CDATA[Claire chatted to Maria Koskinopoulou from Heriot-Watt University about autonomous robotic manipulators for surgery, industry, and beyond. Maria Koskinopoulou is an Assistant Professor in Robotics and Computer Vision at Heriot-Watt University. She co-leads the ARM²Lab – Autonomous Robotic Manipulation &#38; Multi-Agent Systems Lab at Heriot-Watt and the National Robotarium, alongside Ignacio Carlucho. Her research interests [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="alignnone size-medium wp-image-220107" src="https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2-425x407.jpg" alt="" width="425" height="407" srcset="https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2-425x407.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2-1024x982.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2-768x736.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2-24x24.jpg 24w, https://robohub.org/wp-content/uploads/2026/06/Maria-Koskinopoulou-2.jpg 1280w" sizes="(max-width: 425px) 100vw, 425px" /></p>
<p>Claire chatted to Maria Koskinopoulou from Heriot-Watt University about autonomous robotic manipulators for surgery, industry, and beyond.</p>
<p><iframe src="https://play.libsyn.com/embed/episode/id/41521050/height/128/theme/modern/size/standard/thumbnail/yes/custom-color/ffffff/time-start/00:00:00/playlist-height/200/direction/backward/download/yes" height="128" width="100%"  style="border: none;"></iframe></p>
<p><a title="" href="https://sites.google.com/view/mariakoskinopoulou" target="_blank" rel="noopener follow external noreferrer" data-wpel-link="external">Maria Koskinopoulou</a> is an Assistant Professor in Robotics and Computer Vision at Heriot-Watt University. She co-leads the ARM²Lab – Autonomous Robotic Manipulation &amp; Multi-Agent Systems Lab at Heriot-Watt and the National Robotarium, alongside Ignacio Carlucho. Her research interests include robotic manipulation, perception, robot vision, medical robotics, human-robot interaction, and machine learning. She is involved in major UKRI and EU-funded research projects advancing robotic manipulation, surgical and underwater robotics, autonomous assembly, and waste sorting.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Global robotics technology roadmap</title>
		<link>https://robohub.org/global-robotics-technology-roadmap/</link>
		
		<dc:creator><![CDATA[Lucy Smith]]></dc:creator>
		<pubDate>Wed, 03 Jun 2026 09:13:54 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220029</guid>

					<description><![CDATA[Deborah Lupton / Pop Chips / Licenced by CC-BY 4.0. Henrik I Christensen, Professor of Computer Science &#038; Engineering at University of California San Diego, has recently released a global robotics technology roadmap. This position paper focuses on Asia, Europe, and America and outlines the current state-of-the-art in robotics, and highlights the main opportunities. The [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/06/DeborahLupton-PopChips-1280x678-1-1024x542.jpg" alt="A repeating pattern of a photograph of a silicon chip, recoloured so that it is multi-coloured, in the style of pop art." width="1024" height="542" class="alignnone size-large wp-image-220070" srcset="https://robohub.org/wp-content/uploads/2026/06/DeborahLupton-PopChips-1280x678-1-1024x542.jpg 1024w, https://robohub.org/wp-content/uploads/2026/06/DeborahLupton-PopChips-1280x678-1-425x225.jpg 425w, https://robohub.org/wp-content/uploads/2026/06/DeborahLupton-PopChips-1280x678-1-768x407.jpg 768w, https://robohub.org/wp-content/uploads/2026/06/DeborahLupton-PopChips-1280x678-1.jpg 1280w" sizes="(max-width: 1024px) 100vw, 1024px" /><em><a href="https://zenodo.org/records/18929888" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Deborah Lupton</a> / <a href="https://betterimagesofai.org/images?artist=DeborahLupton&#038;title=PopChips" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Pop Chips</a> / <a href="https://creativecommons.org/licenses/by/4.0/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Licenced by CC-BY 4.0</a></em>.</p>
<p><a href="https://hichristensen.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Henrik I Christensen</a>, Professor of Computer Science &#038; Engineering at University of California San Diego, has recently released a <a href="https://hichristensen.com/pdf/global_robotics_roadmap_2025.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">global robotics technology roadmap</a>. This position paper focuses on Asia, Europe, and America and outlines the current state-of-the-art in robotics, and highlights the main opportunities.</p>
<p>The roadmap draws on robotics research and industry data to identify a global technology trajectory for the decade 2025–2035. It integrates findings from leading robotics conferences (such as ICRA, IROS, RSS, CoRL), machine-learning venues (including NeurIPS, ICML), and journal publications, combined with market intelligence from trade organizations and regional government strategies. The document is structured for use by policymakers, technology strategists, research agencies, and industrial research and development leaders. It is based on a review of present research, industry statistics and numerous visits by Henrik to research labs across three continents.</p>
<p>Key headline findings of this roadmap are:</p>
<ul>
<li>The global robotics market reached $53.2B in 2024 and is on a trajectory to $178.7B by 2033. </li>
<li>Asia dominates industrial deployment (74% of global installations in 2024; China alone 54%), while Europe leads in safety-critical regulation and collaborative cobots, and the United States leads in AI-powered autonomy and defense robotics.</li>
<li>Vision-Language-Action (VLA) models are the most consequential algorithmic development of the current period, enabling cross-embodiment generalization for the first time.</li>
<li>Soft robotics and compliant mechanisms, enabled by liquid crystal elastomers (LCEs), electroactive polymers (EAPs), and self-healing hydrogels, are bridging the gap between rigid industrial systems and bio-compatible medical devices.</li>
<li>The humanoid robot segment, currently $370M in 2025, is projected to reach $6.5B by 2030 , with Chinese original equipment manufacturers (OEMs) and US technology companies racing to scale production.</li>
<li>Regulatory asymmetry is a critical geopolitical variable: the EU AI Act, the first comprehensive legal framework for high-risk AI systems, is reshaping humanoid robot design globally.</li>
</ul>
<p>The 52-page comprehensive document covers the following sub-topics:</p>
<ul>
<li><strong>Introduction and scope.</strong> Motivation and methodology.</li>
<li><strong>Global market baseline.</strong> </li>
<li><strong>State of the art: academic research landscape.</strong> Embodied AI, foundation models, reinforcement learning, navigation, manipulation and sensing, bio-inspired locomotion, multi-robot systems, and human-robot collaboration.</li>
<li><strong>Enabling technologies: cross-cutting advances.</strong> Materials science and soft robotics, computing infrastructure, perception and sensing.</li>
<li><strong>Regional technology strategies.</strong> Europe, Asia, USA.</li>
<li><strong>Technology roadmap 2025–2035.</strong> Algorithms and AI, hardware and actuation, materials and manufacturing, and systems, safety and deployment.</li>
<li><strong>Sector-specific analysis, observations, and recommendations.</strong> Manufacturing, logistics, healthcare, agriculture, mining, construction, service robots.</li>
<li><strong>Cross-cutting strategic themes.</strong> The humanoid convergence race, sustainability, workforce and societal impacts, geopolitical technology risks.</li>
<li><strong>Recommended research priorities by region.</strong> Covering Europe, USA and Asia. </li>
</ul>
<p>You can read the roadmap in full <a href="https://hichristensen.com/pdf/global_robotics_roadmap_2025.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>RoboChem Flex: democratisation of the autonomous synthesis robot</title>
		<link>https://robohub.org/robochem-flex-democratisation-of-the-autonomous-synthesis-robot/</link>
		
		<dc:creator><![CDATA[University Of Amsterdam]]></dc:creator>
		<pubDate>Tue, 02 Jun 2026 10:51:48 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<guid isPermaLink="false">https://robohub.org/?p=220024</guid>

					<description><![CDATA[Image credit: HIMS / Nature Synthesis. In a paper published in Nature Synthesis, researchers led by Professor Timothy Noël of the University of Amsterdam’s Van ’t Hoff Institute for Molecular Sciences present an advance in autonomous laboratory systems for synthesis optimisation. A versatile, modular design and the option for &#8220;human-in-the-loop&#8221; analytics, RoboChem Flex caters to [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49-1024x523.jpeg" alt="" width="1024" height="523" class="alignnone size-large wp-image-220025" srcset="https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49-1024x523.jpeg 1024w, https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49-425x217.jpeg 425w, https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49-768x392.jpeg 768w, https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49-1536x785.jpeg 1536w, https://robohub.org/wp-content/uploads/2026/05/Screenshot-2026-05-28-at-09.23.49.jpeg 1660w" sizes="(max-width: 1024px) 100vw, 1024px" /><em>Image credit: HIMS / Nature Synthesis</em>.</p>
<p>In a <a href="https://www.nature.com/articles/s44160-026-01053-0" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">paper published</a> in Nature Synthesis, researchers led by Professor Timothy Noël of the University of Amsterdam’s Van ’t Hoff Institute for Molecular Sciences present an advance in autonomous laboratory systems for synthesis optimisation. A versatile, modular design and the option for &#8220;human-in-the-loop&#8221; analytics, RoboChem Flex caters to all synthesis laboratories, large or small. The paper provides all the information to build their own system.</p>
<p>According to Professor Noël, this new version of the RoboChem concept developed by his group will democratise the use of autonomous, sophisticated AI-powered synthesis systems. Such systems are often very expensive, so that only well-funded institutions can afford them. “We find such an exclusive privilege counterproductive to science. Scientific progress requires scalable, cost-effective tools that empower researchers across all resource levels. So we have now developed our system to be widely used, also by less well-established groups, boosting research capabilities, innovation opportunities, and scientific influence.”</p>
<h4>Cost down, versatility up</h4>
<p>Presented in the journal Science in early 2024, the first RoboChem system featured an autonomous system for flow chemistry, coupled to a benchtop NMR system for analysis, and controlled by an integrated machine learning AI-unit. In their original paper, the group demonstrated RoboChem’s power in accelerating chemical discovery of molecules relevant to pharmaceutical and other applications. Working autonomously round the clock, the system can optimise the synthesis of ten to twenty molecules all by itself, something that would take a PhD student several months.</p>
<p>“We were very proud to present RoboChem’s capabilities in Science”, Noël says. “On the downside, the system cost us over 50,000 dollars, not even including the very expensive NMR equipment. We decided to find a way to reduce cost while at the same time enhancing its versatility.”</p>
<p>The result, now presented in Nature Synthesis, is RoboChem Flex. The paper provides all the information for labs across the world to build their own system. Combining an estimated cost of around $5000 with capabilities in fields as diverse as photocatalysis, biocatalysis, thermal cross-coupling and more, Noel considers his mission accomplished. “There are other affordable automated systems out there, but these sacrifice research potential by focusing on narrowly defined problems. We have demonstrated RoboChem Flex in six challenging case studies covering diverse fields of chemistry. Each case study demonstrates how RoboChem Flex can be specifically tailored to the problem at hand. And of course, we have checked the real-world applicability of the RoboChem Flex results by performing the proposed syntheses in our lab.”</p>
<h4>3D printed components and a &#8220;human-in-the-loop&#8221; option</h4>
<p>To ensure affordability and flexibility, RoboChem Flex uses readily available components or their 3D-printed counterparts. These not only significantly reduce costs but also allow for rapid customisation and iterative development. The communication between the hardware components is orchestrated by the dedicated OmniPlatypus package, developed in-house by Noël&#8217;s research group and open source. It ensures seamless modularity and enables a plug-and-play architecture with minimal coding effort required from the user.</p>
<p>At the software level, RoboChem-Flex features an integrated, highly modular Bayesian Optimisation (BO) agent. This allows its users to customise the AI-driven optimisation of the synthesis workflow to meet specific experimental goals. The platform also supports integration with a range of inline analytical instruments, including NMR, UHPLC-MS, and Raman spectroscopy. Such integration enables a fully autonomous closed-loop operation, capable of autonomous reaction optimisation 24 hours a day.</p>
<p>However, adding the inline analytics would represent a considerable investment that could significantly exceed the 5.000 dollar of the system itself. Therefore, the Noël group decided to also develop a cost-effective, 3D-printed liquid sampling unit. “This module enables the collection of reaction samples”, Noël explains, “which can then be analysed using already available analytical equipment that is often shared among multiple research groups.” This human-in-the-loop approach provides a practical and affordable entry point for laboratories. Thus, by equipping resource-limited research groups with tools on par with those in well-funded institutions, RoboChem-Flex aims to level the playing field and foster innovation at all scales.</p>
<div class="keep-aspect"><iframe title="Robochem FLEX EN" src="https://player.vimeo.com/video/1181501707?dnt=1&amp;app_id=122963" width="500" height="281" frameborder="0" allow="autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share" referrerpolicy="strict-origin-when-cross-origin"></iframe></div>
<p> <br />
<em>Professor Timothy Noël introducing RoboChem Flex.</em></p>
<h4>Robochem Flex case studies</h4>
<ul>
<li>Optimization of pyrrole trifluoromethylation using adaptive weighted exploration and NMR analysis.</li>
<li>Deoxygenative C–H functionalization via hypervolume optimization using HPLC analysis.</li>
<li>Noisy hypervolume optimization of photocatalytic isotope labelling using Raman Spectroscopy.</li>
<li>Selective enzymatic reduction of a diketone using HITL and dual acquisition batching.</li>
<li>Optimization of Buchwald-Hartwig aminations via transfer learning and ligand featurization.</li>
<li>Multi-objective optimization of an enantioselective photocatalytic [2+2] cycloaddition using chiral HPLC.</li>
</ul>
<p><em>All code used for RoboChem Flex is <a href="https://github.com/Noel-Research-Group/Robochem_Flex" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">openly available via GitHub</a>. This includes, amongst others, machine learning and optimisation code, graphical user interface software, device firmware and operational control code, 3D printing design files and schematics for hardware.</em></p>
<h4>Read the work in full</h4>
<p><a href="https://www.nature.com/articles/s44160-026-01053-0" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A flexible and affordable self-driving laboratory for automated reaction optimization</a>, <em>Simone Pilon, Elia Savino, Oliver M. Bayley, Michael Vanzella, Miguel Claros, Petros Siasiaridis, Junsong Liu, Florian Lukas, Matteo Damian, Vasilis Tseliou, Niccolò Intini, Aidan Slattery, Jesus SanJosé-Orduna, Tim den Hartog, Ron A. H. Peters, Andrea F. G. Gargano, Francesco G. Mutti &#038; Timothy Noël</em>, Nature Synthesis (2026).</p>
]]></content:encoded>
					
		
		
			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/?utm_source=w3tc&utm_medium=footer_comment&utm_campaign=free_plugin

Page Caching using Disk: Enhanced 

Served from: robohub.org @ 2026-11-18 14:35:57 by W3 Total Cache
-->