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 to know whether humanoid robots 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, fold it neatly and recover when the sleeve slips from its hand?

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.

Running fast 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.

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.

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.

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.

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.

Why one robot cannot simply copy another

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.

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.

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.

Sensors are important too. One robot may have sensitive touch sensors in its fingers. Another may rely mainly on cameras.

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.

Research projects such as Open X-Embodiment 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.

What should count as progress?

The Humanoid Robot Games are valuable because they make robotics visible and show how quickly the technology is moving.

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?

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.

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.

The most important race for humanoid robots may not be against the clock. It may be against the laundry pile.

Wai-keung Fung, Senior Lecturer in Electronics Robotics & Control Engineering, Cardiff Metropolitan University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

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 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.

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 small autonomous robot, then make it survive increasingly difficult mazes. Simple… right? Until you actually have to build one.

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?”

But to be honest, looking back, the technical part wasn’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.

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’s funny how quickly that happens at these events. You arrive knowing very few people. A few days later, you’re discussing robots, arguing about how to fix things, sharing stories and making plans to meet again.

We also got to spend some time at the Institute for Safe Autonomy, which was a brilliant setting for the hackathon. There’s something quite fitting about asking a room full of technical people to make a tiny autonomous robot behave itself.

A huge thank you to (always witty ‘n’ 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.

And finally Emily, Joolz, Michael and Eugen, I’m very glad a robotics hackathon turned into a York friendship trip :-)

For now, I’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’t always the things you planned to build.

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 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.

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.

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.

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.

Dr Macdonald said: “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.

“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.

“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.”

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 Augmenting Zoomorphic Robotics with Affect, or AZRA, which can overlay augmented-reality sounds and animations over the bodies of real-world social robots to prototype new appearances and functionalities.

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.

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.

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.

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.

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.

“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.”

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.

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.

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.

“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.”

The team’s paper, titled ‘Anime, Animal or Animal Crossing? Comparing Aesthetic Styles for Zoomorphic Robot Faces and Sounds using Augmented Reality’, will be presented at the ACM International Conference on Mobile Human-Computer Interaction conference in Swansea, Wales on Thursday 3 September.

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).

This article is republished from the University of Glasgow under a Creative Commons license. Read the original article here.

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, 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.

By Emmet Cole

“Robotics and automation” is a pairing heard often around these parts. It puts the “RA” 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?

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.

The excerpts below have been lightly edited for clarity.

Sabine Hauert: We often use the phrase “robotics and automation,” 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?

Mariateresa Pedone: 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.

Sabine Hauert: 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?

David Garzon Ramos: 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.

Sabine Hauert: Would that make robotics a subcategory of automation?

David Garzon Ramos: 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.

Claudio Pacchierotti: 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.

Sabine Hauert: 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.

Ellen Rumley: 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?

Claudio Pacchierotti: I introduce this question when I teach robotics to elementary school children. The first activity is simply: “Is this a robot?” 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.

Ellen Rumley: 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.

Sabine Hauert: 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.

Amy Eguchi: 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 “AI microwave.” Is that a robot, or is it simply automation?

Sabine Hauert: So, the answer may depend partly on what people encounter in everyday life.

Amy Eguchi: 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.

Sabine Hauert: 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.

David Garzon Ramos: The language also changes with research trends. Now that I write proposals, I use terms such as “physical AI” and “embodiment,” 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.

Sabine Hauert: 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.

David Garzon Ramos: I think it depends on the purpose. If you are speaking to children, “robot” may immediately create interest, while “automation process” may not. “Physical AI” 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.

Sabine Hauert: 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.

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? Drop us a line and we may share your insights in a future feature article.

Propeller-powered underwater vehicles have long helped scientists explore and monitor aquatic environments. But they’re limited by their own mechanics: spinning blades can snag on vegetation, stir up sediment, and startle the wildlife they’re often sent to study, making them poorly suited to shallow creeks, dense weeds, or close encounters with fish.

That’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.

A team of engineers at EPFL and New York University (NYU) says it has found a way to solve that problem. They’ve unveiled ScaFi (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.

“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,” says Nana Obayashi, first author on the study published in npj Robotics. “The environments we care about don’t come in one size, so we don’t think the tools should either.”

Currently an assistant professor of mechanical and aerospace engineering at the NYU Center for Robotics and Embodied Intelligence, Obayashi led the project while completing her PhD in the Computational Robot Design & Fabrication Lab, led by Josie Hughes, in EPFL’s School of Engineering.

ScaFi at 0.6, 1.1, and 2.9 meters long. 2026 CREATE Lab EPFL. CC BY SA-4.0.

Studying different environments systematically

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’s end, producing the “S”-shaped bend required for fish-like swimming motion.

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.

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’s hard to study systematically in animals or custom-made robots alike.

Into the water!

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 Unsteady Flow Diagnostics Lab, 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.

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.

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.

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.

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.

Funding

This research was partially funded by the European Union’s Horizon 2020 program under Marie Skłodowska-Curie grant agreement No. 945363.

Reference

Obayashi, N., Anastasiadis, A., Gumowski, J. et al. ScaFi: length-scalable, compliant, parametric robotic fish design for operation in multiple environmental niches. npj Robot (2026).

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 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.

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. 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.
• Pose estimation. Provides an accurate six degrees of freedom pose estimation of 3D parts.
• Motion planning. Logic auto-generates efficient paths while avoiding collisions.
• Grasp planning. 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.
• Simulation services. These aim to provide a straightforward way to test and troubleshoot robotic solutions that update as you build.
• Camera calibration. Automates how a robot’s camera can be calibrated and physically aligned
• Intrinsic-ROS drivers. Pre-configured, ROS-compatible drivers for supported robots, grippers, and 3D cameras.

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.

You can download Intrinsic Core on GitHub here.

The 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026) will be held from 27 September – 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 – 30 September:

• Elena De Momi – Open Questions on the Road to Autonomous Surgery
• Naomi Fitter – Socially-Informed Context Awareness for Robots in Human-Populated Settings
• Greg Chirikjian – From Hyper-Redundancy to Robot Imagination and Affordance Learning
• Genta Suzuki – Fujitsu Kozuchi Physical OS: A Research Strategy for Scalable Physical AI
• Gaurav Bansal – Title to be confirmed
• Al Rizzi – Developing Advanced Robot Capability at the RAI Institute
• Yekai Sun – Tokens of the Physical World: Accelerating Intelligence Emergence via Multimodal Embodied Data
• He Wang – Towards the AlphaGo and ChatGPT Moments of Embodied AI
• Jen Jen Chung – All data are equal, but some data are more equal than others
• Yigit Menguc – Soft Robotics, Tensegrity, and the People Who Love Them
• Robin Murphy – Rethinking Disaster Robotics: The Open Questions That Matter Now
• Gina Olson – Embracing Design Complexity: A Biomimetic Approach to (Soft?) Snake Robots
• Tim Bretl – How you can be part of a revolution in composite manufacturing
• Lael Odhner – Big bets in manipulation systems: where is the frontier today?
• David Held – Robots That Learn After Deployment: Designing Policies for Fast Adaptation
• Ankur Mehta – Robotics problems that robotics can’t solve
• Brittany Duncan – Patterns from the Field: how contextual lessons can inform robot design
• Ralph Hollis – Lorentz Levitation Technology for Fine Motion Robotics, Haptic Interaction, and Vibration Isolation
• Genki Yamauchi – From Big Sites to Every Site: Extending Construction Robotics to the Work Done by Hand
• Nancy Pollard – Title to be confirmed

Forums

Community discussion sessions open to all attendees, these forums will be held on Monday 28 and Tuesday 29 September.

• Monday 28 (afternoon): US Government Funding
• Tuesday 29 (morning): Robotics Education: Experiential Learning
• Tuesday 29 (afternoon): Is Robotics Underinvesting in Its Own Foundations?

Plenary panels

Three plenary panels will be held:

• Monday 28: Start-ups and entrepreneurship
• Tuesday 29: Space
• Wednesday 30: Should robots be generalists or specialists?

Workshops and tutorials

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 here.

Introduction to science communication

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 here.

Find out more

• Conference webpage
• Technical tours
• Competitions

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 marathon and sprint runners outpacing elite athletes (1). 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 (2, 3). These public debuts serve to both normalize automation in everyday civilian life (4) while projecting international soft power.

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 (5). 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 (6, 7), China aims to pioneer a new era of industrial leadership while mitigating a long-term structural gap through a state-orchestrated robotics surge.

Five-Year Plans (FYPs)

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 (8). The FYPs have been influential in strengthening the nation’s manufacturing base and is now playing a defining role in advancing Chinese robotics.

FYP13 & FYP14: Made in China

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 (9). 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 (10). 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 (11). While many international critics condemned these subsidies as market distortion and imposed sanctions as a response (12), paradoxically this intensified Beijing’s efforts towards a sovereign tech sector.

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&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 (13, 14), and domestic suppliers for industrial robots became market leaders for the first time (15). 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&D clusters in Shanghai, hardware manufacturing bases in the Yangtze River Delta (16) and a growing startup ecosystem in Shenzhen (17) – 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 (18).

Bottlenecks in Precision Hardware & Semiconductors

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 (5), and even less so – at 15% – for high-end machine tools (19). 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 (20), where precision manufacturing traditions are backed by decades of institutional standards and specialized labor (21, 22). The incoming 15th FYP does address this shortcoming, however, and prioritizes China’s advancement of precision hardware in the coming years (23).

Concurrently, Beijing fell short of its goal to achieve 70% self-sufficiency in semiconductor manufacturing, missing the mark by an estimated 40% (24). 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 (25). Against the backdrop of export controls from the U.S. and rising tensions across the Taiwan Strait—the global leader of semiconductor manufacturing (26) – Beijing’s pursuit of computational autonomy serves to protect itself against supply chain chokepoints that could derail its incoming robotics plans.

FYP15: Embodied AI with a Human Form

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 (27, 28). 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 (23).

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” (29). 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 (30). And as physical embodiment of AI, robots are expected to soon play a pivotal role in these directives (23). 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 (31).

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 (32, 33), 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 (34, 35). Owing also to the hardware surplus and supply chain synergies resulting from the EV push (36), 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 (37, 38). 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.

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.

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 (39). In these hubs, humanoids from various domestic manufacturers are pooled to train basic skills – such as grasping and transport – in simulated real-world scenarios (40). 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 (41).

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 (42). Because policy-driven supply currently outpaces market demand, only a fraction of today’s 150+ companies are expected to survive the coming years (43, 44). While parallel R&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.

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 (45).

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.

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.

Ellen H. Rumley – Policy Analyst

Allison Okamura – Vice President

IEEE RAS Science & Technology Watch Board

References

1. Ye, Ziyin. “Yearender: China’s Humanoid Robots Step from Spectacle toward Scalable Industrial Reality.” Xinhua, 31 Dec. 2025.
2. Che, Chang. “Inside China’s Robotics Revolution.” The Guardian, 19 Mar. 2026.
3. Yang, Zeyi. “Food Delivery by Drone Is Just Part of Daily Life in Shenzhen.” MIT Technology Review, 23 May 2023.
4. “How Different Countries Perceive Robots: An Original Survey.” Mitsubishi Research Institute, Feb. 2025.
5. Grant-Chapman, Hugh, et al. “Is China leading the Robotics Revolution?” ChinaPower Project, Center for Strategic and International Studies, 12 Feb. 2026.
6. “Robotics Revolution Driving Industrial Transformation.” China Daily, 10 Sept. 2025.
7. Bao, Anniek. “China’s K-Visa Plans Spark Worries of a Talent Flood.” CNBC, 1 Oct. 2025.
8. Yin, Ju and Xu, Jia. “Made in China 2025 and Industrial Upgrade.” SpringerLink, Springer, 2023.
9. Kuo, Kaiser. “Made in China 2.0: The future of global manufacturing?” World Economic Forum / J.H. Whitney & Co., 26 June 2025.
10. Amodio, Francesco, et al. “How China Became the World’s Factory: Trade, Industrial Policy, and Growth.” VoxDev, 18 Feb. 2026.
11. Xiang, Shuhui, et al. “Two Decades of Chinese Industrial Subsidies.” VoxEU, Centre for Economic Policy Research, 7 Jan. 2026.
12. “Made in China 2025 Dropped: Media Analysis.” MacroPolo, 15 Mar. 2019.
13. Tobe, Frank. “2014 Was Another Record Year for Robotics.” The Robot Report, 11 Apr. 2014.
14. Kim, Jenny, et al. “World Robotics R&D Programs.” International Federation of Robotics, 1 Jan. 2025.
15. “Top 5 Global Robotics Trends 2026.” International Federation of Robotics, 8 Jan. 2026.
16. Andreoni, Antonio, et al. “China’s Industrial Policy and Robotics Automation.” Global Media and Communication, SAGE Publications, 2 Aug. 2024.
17. Chang, Wendy, et al. “Embodied AI: China’s Ambitious Path to Transform Its Robotics Industry.” Mercator Institute for China Studies (MERICS), 30 Apr. 2026.
18. Gaudiaut, Tristan. “China’s Dominant Share in Global Mining Production of Critical Minerals.” Statista, 5 Nov. 2025.
19. “Was Made in China 2025 Successful?” Rhodium Group, 5 May 2025.
20. “Made in China 2025: Evaluating China’s Performance.” U.S.-China Economic and Security Review Commission, 14 Nov. 2025.
21. Tsuwa, Hideo, et al. “Precision Engineering and Industrial Automation Development.” Precision Engineering, ScienceDirect, Jan. 1979.
22. Lampe, Hannes W., et al. “Product Innovation and Industrial Policy in Emerging Markets.” Journal of Product Innovation Management, Wiley, 27 Nov. 2024.
23. Cheung, Sunny. “China’s New Five-Year Plan Prioritizes Robotics: The World Should Pay Attention.” The Diplomat, Mar. 2026.
24. 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.
25. MacCarthy, Mark. “Ball Game’s Over: The US Is Out of the AI Chip Market in China.” Brookings Institution, 17 Jun. 2026.
26. Mickle, Tripp. “Taiwan, China, Chips, and Silicon Valley.” The New York Times, 24 Feb. 2026.
27. “China Makes AI-Powered Robots Core of National Strategy.” International Federation of Robotics, 5 May 2026.
28. Cheung, Sunny. “New Military-Civil Fusion Body for PRC Robotics Ecosystem.” China Brief, Jamestown Foundation, 18 Dec. 2025.
29. “State Council Policy Briefing on Technological Advancement and Industry Guidelines.” The State Council of the People’s Republic of China, 21 Aug. 2025.
30. Martin, Nik. “China Chips and Semiconductor Industry: US Technology Constraints and Artificial Intelligence.” Deutsche Welle, 20 Apr. 2026.
31. “China’s 15th Five Year Plan Explorer.” China FYP.
32. “Huawei Backs GigaAI in Latest Bet on China’s Booming Humanoid Robot Sector.” China Biz Insider, 28 Nov. 2025.
33. Cheng, Evelyn. “Alibaba Leads $100 Million Investment in Chinese Humanoid Robot Startup.” CNBC, 8 Sept. 2025.
34. Zhang, Tong, et al. “Empirical Analysis of Technological Innovation and Robotics Integration.” Journal of Asian Economics, ScienceDirect.
35. Lu, Fengming and Ma, Xiao. “Rise of China’s EV Industry.” The China Journal, No. 96, Jul. 2026.
36. Tobin, Meaghan and Keith Bradsher, Keith. “Why It’s Nearly Impossible to Build a Robot Without China.” The New York Times, 11 Jun. 2026.
37. Ye, Alice. “China’s Humanoid Robot Dominance: What It Means for the Global Economy.” China Biz Insider, 20 May 2026.
38. Tao, Ni. “Humanoid Robots in China: Progress, Limits, and Reality.” Cheung Kong Graduate School of Business, 23 Jan. 2026.
39. Zhou, Viola and Lo, Kinling. “Inside China’s Robot Training Centers for Workers.” Rest of World, 7 Jan. 2026.
40. Yiyi, Zhang. “China Ramps Up Embodied AI and Next-Gen Robotics Ecosystem.” Global Times, 27 Jul. 2026.
41. Hannas, William C., et al. China’s Embodied AI Development and Strategic Roadmaps. GovWhitePapers, 1 Dec. 2025.
42. Tobin, Meaghan and Wu, Xinyun. “Unitree and UBTech Lead China’s Robotics Expansion.” The New York Times, 17 Dec. 2025.
43. Chen, Laurie, et al. “China’s Humanoid Robots Aren’t Smart Enough to Take Your Job Yet.” Reuters, 27 Aug. 2026.
44. Jonas, Adam et al. “The Humanoid 100: Mapping the Humanoid Robot Value Chain.” Morgan Stanley Research, 6 Feb. 2025.
45. “China Robot Maker Unitree’s Post-Listing Slump Sparks Bubble Fears.” Reuters, 24 Aug. 2026.

By Ashwin R. Vasavada

Lights blink on as I enter the Rover Operations Center at NASA’s Jet Propulsion Laboratory in Pasadena, California, at 7:30 a.m. I’m the first to arrive, even though I already feel late.

Sometime during the night on Earth, the Curiosity rover 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.

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.

As Curiosity’s project scientist, 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.

NASA Curiosity project scientist Ashwin Vasavada guides this tour of the rover’s view of the Martian surface.

Reading the rocks

NASA created Curiosity 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.

JPL responded with the car-size, drill-equipped Curiosity rover. NASA added a suite of scientific instruments and a science team from the United States and around the world.

NASA sent Curiosity to Mars’ Gale Crater 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 sheltered flowing streams and sparkling lakes.

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 millions of years 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.

Samples Curiosity drilled from the lake sediments contain small organic – meaning carbon-based – molecules, the raw materials for potential life. 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 capable of supporting life. Determining conclusively whether life actually took hold will require bringing such rocks back to laboratories on Earth.

Preparing a plan

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 other signs of ancient water. These images suggest that perhaps even Mars’ dry period provided habitats for life.

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 rough offroad driving, 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.

Polygon fractures with honeycomblike textures, discovered by NASA’s Curiosity Mars rover. NASA/JPL-Caltech/MSSS

What I’m looking at now is taking my breath away. Instead of smooth slabs, every surface around the rover is textured by small polygons, 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.

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.

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.

Engineering the uplink

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.

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 NASA’s Deep Space Network in a few hours. There’s still a lot to do, but the team is in the homestretch for the day.

On Mars, the horizon is starting to brighten. Before too long, Curiosity will be expecting to hear from us.

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.

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 energy it helps produce, can it really be considered sustainable?

In a 2025 article published in Science, Aude Billard, head of the Learning Algorithms and Systems Lab in EPFL’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.

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.

“Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges.”

– Mirko Kovač, Laboratory of Sustainability Robotics

Beyond sustainable robotics

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.

Mirko Kovač heads the joint Laboratory of Sustainability Robotics at Empa and EPFL’s School of Architecture, Civil and Environmental Engineering. In a cover article recently published in Nature Machine Intelligence, 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).

“Our ambition is not to simply make robots more sustainable; they must actively contribute to solving sustainability challenges,” Kovač says.

The three core principles of Sustainability Robotics. 2026 LSR/EPFL – CC BY SA 4.0

Minimally invasive, accessible…

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 minimally invasive, universally accessible, and symbiotic, creating value for people as well as economies and ecosystems.

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.

For example, the eel-inspired Envirobot, from Auke Ijspeert’s Biorobotics Lab, supports environmental research by targeting the autonomous monitoring of water quality. The project reflects the lab’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.

The eel-inspired Envirobot from the Biorobotics Lab supports environmental research by targeting the autonomous monitoring of water quality. 2017 Alain Herzog / EPFL – CC BY SA 4.0.

Engineers in the Laboratory of Intelligent Systems, led by Dario Floreano, have developed an aquatic robot made from fish food. 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.

This edible robot from the Laboratory for Intelligent Systems is an alternative to electronic environmental monitoring devices. EPFL – CC-BY-SA 4.0.

…and symbiotic

Sustainability Robotics’ concept of symbiosis also raises questions about how robots can create value across multiple domains. One example is the RoboFood 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.

“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.”

Edible robotic teddy bears, created by the LIS at EPFL – 2025 EPFL/Jamani Caillet – CC-BY-SA 4.0.

Another example comes from the built environment. In the Lab for Creative Computation, Stefana Parascho investigates 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 more adaptive and collaborative human-robot interactions.

In addition to materials and applications, research in the Computational Design and Fabrication (CREATE) 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 quadruped robot PAWS. 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.

Once set in motion, the CREATE Lab’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.

A new measure of performance

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’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’s overall impact.”

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.

In that sense, sustainability may become one of the most important performance metrics for the next generation of robots.

References

• Aude G. Billard. Designing and using robots for environmental sustainability. Science 388, eadx2444 (2025).
• Song, S., Mazzolai, B. & Kovač, M. A manifesto for Sustainability Robotics. Nature Machine Intelligence (2026).
• Empa press release
• Envirobot: A bio-inspired environmental monitoring platform. IEEE/OES Conference on Autonomous Underwater Vehicles (AUV), Tokyo, Japan (2016), pp. 1-6.
• RoboFood
• Skevaki, E., Duong, E., Yang, HB. et al. Crafting structural timber trusses from irregular offcuts via human–robot interaction. Construction Robotics 10, 20 (2026).
• Stefana Parascho. Construction Robotics: From Automation to Collaboration. Annual Review of Control, Robotics, and Autonomous Systems 6:183-204. 2023.
• Stella, F., Achkar, M.M., Della Santina, C. et al. Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity. Nature Machine Intelligence 7, 386–399 (2025).
• Zhang, S., Kwak, B., Zhu, R. et al. Edible aquatic robots with Marangoni propulsion. Nature Communications 16, 4238 (2025).

The 2026 IEEE International Conference on Robotics & Automation (ICRA) was held in Vienna from the 1 – 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 and keynote tutorials.

Watch here.

Available to watch are the following:

• Plenary talks
• Ken Goldberg – A Tale of Two Cultures: Can Agentic Coding Close the Gap?
• Barbara Mazzolai – Natural Revolution: Biological Principles for Frugal and Sustainable Robotics
• Roland Siegwart – Aerial Robots – From Omnidirectional Flight to Physical Interaction at Height
• Keynote sessions
• Autonomous Vehicles & Navigation
• Medical & Healthcare Robotics
• Robot Perception & Spatial AI
• Manipulation, Humanoids, Embodied Design
• Robot Learning, Planning & Foundation Models
• Human-Robot Interaction
• Industry keynote sessions
• Awards
• Keynote tutorials
• Panels
• Panel 1 – From Humanoid Robotics Research to Startup Creation: The Role of Public Funding
• Panel 2 – Advancing Sustainability in Robotics: From Green Design to Real-World Impact
• Panel 3 – Building Sustainable and Trustworthy AI for Automation
• Panel 4 – Publish or Perish: Surviving the Paper Deluge – Is AI the solution? If not, what is the Solution?
• Panel 5 – “Robots for All” in a Fragmented World: Competing Global Visions and Shared Futures from Europe, Asia, and the United States
• Panel 6 – Impact and Financial Return on Humanoid Investment

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 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.

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 TechCrunch, the research is being funded by one or more companies in the electric and autonomous vehicle industries.

Together, the stories highlight the ongoing tension between US security concerns and its robotics industry’s continuing dependence on Chinese hardware.

Motorless shape shifters

Don’t cancel any Shenzhen travel plans just yet, but engineers at Princeton have unveiled a motorless, origami-inspired robot that can roll, crawl, and change shape through a combination of magnetic control and multistable geometry.

Project lead Glaucio Paulino told Princeton Engineering:

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.

Managing expectations

Robot deployments can fail for many reasons, 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.

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.

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.

A Drexel-led study 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.

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.

Counterintuitively:

[…] 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.

Read the full Science Robotics paper here.

Beyond automotive

For decades, the automotive sector has been the leading segment for robotics adoption. That’s still the case, but as the latest North American Q2 figures from the Association for Advancing Automation (A3) show, automotive OEM’s share is continuing to slide as robots diversify across other industry segments.

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.

Recycling robots

IEEE Spectrum profiled an automated recycling system developed by researchers at Germany’s Karlsruhe Institute of Technology. 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.

All eyes on China

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.

The WRC, 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.

Unitree supplied much of the spectacle with its remarkably fast “Superman” humanoid and an extraordinary stock-market debut. Its shares closed 460% above the IPO price, although by August 28 they had fallen almost 30% -another lesson in managing expectations. CEO Wang Xingxing also predicted that robotics is approaching a “ChatGPT moment”.

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…

…and some genuinely impressive technology demonstrations.

After watching several hours of livestreams 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.

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 Mr. Magoo-like quality. Technology demonstration aside, there isn’t much call for either in industrial applications.

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.

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.

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.

These slower, less spectacular competitions tested the precision, perception and adaptability humanoids will need before they can perform useful work in factories and warehouses.

All that said, everybody needs a humanoid riding a giant quadruped.

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 robotics platform, designed a laser-cut chassis, integrated motors and sensors, and developed its control software in MicroPython.

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.

The programme also included a tour of the Institute for Safe Autonomy, collaborative development sessions, final presentations and robot demonstrations.

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.

Thank you to Rob Woolley, the University of York team and everyone who participated and contributed to the event.

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 release of Boston Dynamics’ Atlas executing the ‘Ghost Rabona’ soccer kick highlights the increasingly natural movements of humanoids (1). At the other end of the spectrum, academic researchers are redefining the limits of miniaturization and building robots at the micrometer scale (2). Private and government funding propel foundational research forward, leading to breakthroughs in both hardware and software across U.S. labs and corporations (3, 4). Such progress reaffirms the U.S. as an intellectual and innovative powerhouse, a reputation that carries large geopolitical weight.

But retaining a lead solely in the R&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 (5, 6). Ramping up domestic production will require a heavily coordinated effort between government, industry, and academics – a pivot from traditional U.S. technology strategy.

Free market and military capital

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 (7). 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 (8).

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 (9). 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 (10, 11). 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 (12).

A bottleneck for domestic manufacturing

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&D and specialized military platforms, its mandate stops short of supporting commercial scaling efforts necessary to implement technologies for broader civilian and industrial applications.

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) (13), 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 (14). Contrast this with Japan, which relies on foreign imports for a mere 2% of its domestic installations (15).

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 (16). This reality makes robotics manufacturing a target for foreign adversaries, since foreign supply chains introduce operational chokepoints.

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 NSPM-33 (a national security memorandum directed to executive agencies) mandating federally funded research institutions to establish strict internal compliance frameworks (17). 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 (18). As another example, in early 2026 lawmakers proposed the bipartisan American Security Robotics Act, a bill designed to ban the federal procurement and operation of unmanned ground vehicles and humanoids manufactured by foreign adversaries, specifically targeting China (19).

Getting by without a government-led national robotics strategy

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 (20). Today, there is a similar pressure mounting for the federal government to coordinate a sovereign robotics pipeline via a unified national roadmap.

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 (21). 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 DARPA Grand Challenges, 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.

This structural fragmentation may soon change as political attention shifts towards treating robotics as a critical sector (22). In 2025, four state representatives re-launched the bipartisan Congressional Robotics Caucus as a platform for members of Congress to stay informed over the diverse issues surrounding robotics policy (23). In June 2026, legislators formally introduced the bipartisan National Commission on Robotics Act, which calls for an independent commission of 18 robotics experts tasked with providing evidence-based policy to accelerate domestic development (24). 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 Unleashing American Drone Dominance Order (25), the Golden Dome for America Order (26), and the Launching the Genesis Mission Order (27).

Robotics strategies from non-government actors

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.

In 2025, A3 (Association for Advancing Automation) released their Vision for a U.S. National Robotics and Automation Strategy (28), 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.

Complementing these industry goals, in 2025 the nonpartisan thinktank, Special Competitive Studies Project (SCSP), has released their Memos to the President – National Robotics Strategy (29). 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 National Security Commission on Robotics for Advanced Manufacturing 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 (30).

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 (31). 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 Global Robotics Technology Roadmap 2025–2035, an independent positions paper synthesizing government and industry strategies across Europe, Asia, and the United States (32).)

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 (33, 34). 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 (35).

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.

Thanks for reading. For our next article we will be delving into China’s national robotic strategies – stay tuned.

Ellen H. Rumley – Policy Analyst

Allison Okamura – Vice President

IEEE RAS Science & Technology Watch Board

References

1. Boston Dynamics and Hyundai. School of Football | The Ghost Rabona | Boston Dynamics x Hyundai. YouTube, 2026.
2. University of Pennsylvania School of Engineering and Applied Science. “Penn and UMich Create World’s Smallest Programmable Autonomous Robots.” Penn Engineering Today, 2024.
3. “7 Cool NSF-Funded Robots That Are Advancing Science and Helping Society.” S. National Science Foundation, 7 Apr. 2021.
4. “AI 50 List: Top Artificial Intelligence Companies.” Forbes, 2026.
5. Atkinson, Robert D. A Time to Act: Policies to Strengthen the US Robotics Industry. Information Technology and Innovation Foundation (ITIF), 2025.
6. Association for Advancing Automation (A3). Policy Recommendations and Advocacy Principles for the U.S. Automate.org, 2025.
7. Consumer Technology Association. “Tech Sector Supports 18 Million US Jobs, Represents 12% of GDP, Says CTA.” CTA Press Releases, 2026.
8. Brookings Institution. Hardware and Software: A New Perspective on the Past and Future of Economic Growth. Brookings, 2024.
9. United States Department of Defense. Comptroller Budget Materials: Fiscal Year 2026. 2025.
10. Marrow, Michael. “DoD Plans Largest-Ever Investment in Drones, Anti-Drone Weapons.” DefenseScoop, 21 Apr. 2026.
11. Smith, Matt. “Humanoid Robots and Military AI Take the Field in Ukraine War.” CNBC, 30 May 2026.
12. Reuters Defense Bureau. “Iran Could Disrupt Strait of Hormuz with Drones Within Months.” Reuters, 4 Mar. 2026.
13. International Federation of Robotics. “US Robot Industry Returns to Double-Digit Growth.” IFR Press Releases, 2026.
14. McKinsey Global Institute. Ramping Up Manufacturing in America? McKinsey & Company, 2026.
15. International Federation of Robotics. “Japan Is World’s Number One Robot Maker.” IFR Press Releases, 2022.
16. Stanford University. Stanford Emerging Technologies Review 2026. 19 Feb. 2026.
17. National Science and Technology Council. Guidance for Implementation of National Security Presidential Memorandum 33 (NSPM-33). Jan. 2022.
18. White House Office of Science and Technology Policy. Guidelines for Foreign Talent Recruitment Programs. Feb. 2024.
19. United States, Congress, House. American Security Robotics Act. 119th Congress, H.R. 8189. Government Publishing Office, 2026.
20. Center for Strategic and International Studies. Innovation Lightbulb: Tracking CHIPS Act Incentives. CSIS, 2025.
21. Center for Strategic and International Studies. “Why the United States Needs Robots to Rebuild.” CSIS Strategic Technologies Blog, 2025.
22. Politico Pro Staff. “White House and Congressional Frameworks Shift Toward AI and Robotics.” Politico, 3 Dec. 2025.
23. United States, Congress, House of Representatives. “McGovern, Latta, Stevens, Obernolte Announce Re-Launch of Congressional Robotics Caucus.” Office of Congressman Jim McGovern, May 2025.
24. United States, Congress, House. National Commission on Robotics Act. 119th Congress, June 2026, H.R. 7334.
25. S. Army News Service. “Drone Dominance Program Receives First Order; Gauntlet II Gets Underway.” Defense Department News, 2026.
26. Congressional Budget Office. Cost Estimate and Analysis of the Golden Dome Air Defense Framework. May 2026.
27. S. Department of Energy. “Energy Department Advances Investments in AI and Robotics for Scientific Discovery.” DOE News, 2025.
28. Association for Advancing Automation. “A3 Policy Recommendations and Advocacy Principles for the U.S.” April 2024.
29. Special Competitive Studies Project. Memos to the President: National Robot Strategy. SCSP, 2025.
30. “Boston Dynamics Joins U.S. Robot Strategy Think Tank Led by Ex-Google CEO.” Seoul Economic Daily, March 2026.
31. Christensen, Henrik, et al. Robotics for a Better Tomorrow: 2024 US National Robotics Roadmap. UC San Diego / Academic Coalition, 2024.
32. Christensen, Henrik. Global Robotics Technology Roadmap 2025–2035. Independent Position Paper, 2025.
33. Appelbaum, Binyamin. “What Replaces Deported Immigrant Workers? Not Americans.” The New York Times, Feb. 2026.
34. Pew Research Center. “Key Findings About How Americans View Artificial Intelligence and Automated Systems.” Pew Short Reads, 12 Mar. 2026.
35. “Unions Furious as GM Replaces 1,000 Factory Zero Workers with 50 Robots.” Yahoo News, June 2026.

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 played by Diane Morgan. Linda is designed to provide daily support and companionship, with predictably comic results.

As researchers in social care, ageing and human-centred robotics, we obviously watched Ann Droid with a keen eye. Beneath the jokes are questions that researchers are already tackling.

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.

The BBC’s Ann Droid sitcom.

A social enterprise in south-west England has been piloting Comfort Companions in partnership with Age UK South Gloucestershire. AI-generated personas offer conversation and guidance to older people living alone and at risk of loneliness.

It runs alongside 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.

Physical robots are being tested too. West Berkshire Council has been running a trial using robotic pets in its care homes.

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.

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.

Can a machine make you less lonely?

It’s worth considering this distinction because loneliness is not simply the same as being alone. It’s a personal feeling that our relationships are insufficient, accompanied by a desire for more or better social contact.

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.

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.

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.

Robots are much better at some tasks than others. A machine may be able to play chess, for example, but picking up an unfamiliar household object in the real world remains surprisingly difficult.

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.

A review 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.

Would we trust a robot carer?

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.

Research 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.

In 1970, the roboticist Masahiro Mori proposed 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.

Ann Droid – dinner with the robot-in-law.

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.

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?

Maria Jose Galvez Trigo, Senior Lecturer (Associate Professor) in Human-Centred Robotics and AI, Cardiff University and Paul Willis, Professor of Social Care, Cardiff University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

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 NASA’s IM-3 launch, 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.

Engineers test whether the CADRE rovers can drive and coordinate on their own at NASA’s Jet Propulsion Laboratory in Pasadena, Calif. NASA/JPL-Caltech.

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.

That achievement will matter well beyond this mission, because NASA is scoping out future missions to the lunar South Pole, where water in the form of ice sits locked in craters 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 lunar economy built around fuel depots and life support made on the Moon.

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.

I’m an aerospace engineering Ph.D. candidate researching guidance, navigation and control 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.

Why Earth cannot drive

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.

Spotty communication doesn’t just make trying to drive annoying. It can cost the rover power it cannot recover.

A polar rover runs on a finite illumination budget. Solar panels charge the battery only while the Sun is up, and on the Moon sunrise is not a daily event. Night lasts about two Earth weeks, 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.

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.

Why the pole is the hard case

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.

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.

Temperatures inside permanently shadowed regions drop below minus 274 degrees Fahrenheit (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 every grain sharp and jagged.

That dust grinds at the wheel bearings and works past the seals. Keeping it out of the rover’s moving parts is still an unsolved problem. 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.

Why one rover is not enough

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 distribute that risk 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.

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.

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 they could continue together.

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.

What remains uncertain

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 developing ways for rovers to navigate without satellite positioning and to make decisions onboard, but that software still has to be tested on the surface.

Meanwhile, as of mid-August 2026, China’s Chang’e-7 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.

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.

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.

Wanjiku Chebet Kanjumba, Ph.D. Candidate in Aerospace Engineering, University of Florida

This article is republished from The Conversation under a Creative Commons license. Read the original article.

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 know it.

Panel chair Aude Billard 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.”

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.

Kunpeng Yao presented a case study funded by IEEE RAS Science and Technology Watch Board. 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.

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.

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.

Yao summarized one lesson neatly: notability should be judged against the state of the art, not against “the newest vocabulary.”

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.

Degrees of hallucination

One question is whether large language models can help with literature review. Nadia Figueroa 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.

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.

“The danger currently is not fake citations,” observed Figueroa. “It’s fake understanding.”

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.

Salami and sandcastles

Meanwhile, Greg Dudek 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.

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.

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.

His preferred remedy is simple in principle but difficult in practice: publish fewer, more integrated papers.

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.”

Re-designing peer review?

Renaud Detry 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.

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.

Visibility is not value

Dongheui Lee 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.

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.

Beyond the gatekeeper model

The most radical question came from Shigeki Sugano, 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.

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.

“The question is not whether peer review is valuable,” he argued. “The question is whether it must remain the only gate to visibility.”

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.

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.

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.

The open question

One major question remains: what happens to robotics research if papers continue to be published at the current rate?

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.

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.

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.

This article originally appeared on IEEE RAS.

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 new study published in the journal Science Robotics, we had 50 people hold conversations and make joint decisions with the commercial humanoid robot Pepper, 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.

For some participants, the robot was animated, using gestures, eye contact and nods. For others, it stayed motionless.

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.

We found that when people interacted with an expressive robot that violated interaction norms, their oxytocin 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.

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.

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.

Reading someone’s brain during a real conversation is hard because the conventional method requires lying motionless inside an MRI scanner. Instead, we used functional near-infrared spectroscopy, a portable sensor worn on the forehead that tracks oxygen levels in the brain while people move and talk normally.

The two brain regions we closely watched were the dorsolateral prefrontal cortex and the medial prefrontal cortex. The dorsolateral prefrontal cortex monitors uncertainty and flags when expectations or norms get broken. The medial prefrontal cortex supports “mentalizing,” the everyday work of inferring what another party intends.

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.

Why it matters

Robots are moving into homes, hospitals and workplaces, 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.

However, research is beginning to show that that assumption is faulty. 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.

A motionless robot’s error looks mechanical, while the same error from an animated robot engages the machinery you use to judge people.

What other research is being done

Researchers increasingly treat trust as a multilevel phenomenon – spanning individuals, relationships, networks of people and societies – rather than a single attitude.

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 depend on the context, uncertainty and perceived threat.

Others are using wearable brain imaging systems to study social cognition in natural encounters between people, which isn’t possible when subjects are in scanners like MRI machines.

What’s next

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.

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.

The Research Brief is a short take about interesting academic work.

Hasan Ayaz, Professor of Biomedical Engineering, Science and Health Systems, Drexel University; Ewart J. de Visser, Technical Director, Warfighter Effectiveness Research Center, United States Air Force Academy; Frank Krueger, Professor of Systems Social Neuroscience, George Mason University, and Yigit Topoglu, Research Scientist, Warfighter Effectiveness Research Center, United States Air Force Academy

This article is republished from The Conversation under a Creative Commons license. Read the original article.

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 sides using machines designed by Booster Robotics.

You can watch highlights of the match below:

Back in 1997, RoboCup’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.

“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.”

Find out more:

• Team B-Human YouTube channel
• Team HTWK Robots YouTube channel
• While the World Watches Soccer, Robots Made History in Incheon – RoboCup Federation article about the match
• RoboCup Federation website

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 awkward questions, starting with this one: How sustainable are robots themselves?

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.

The Robotics Eco-Label project, led by Bram Vanderborght 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.

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 five metrics: 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 here.)

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.

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.

Robotics Eco-Label is just one of the IEEE RAS Sustainability Grant-funded projects showcased at ICRA in June. The grants are a key component of IEEE RAS’ broader effort to make sustainability a more visible part of robotics research, education, design, and deployment.

Are you buying more robot than you need?

Sometimes, sustainable robotics starts with better purchasing decisions. This includes avoiding overspecification; that is, buying robots that are larger or more capable than necessary.

Matching robots to their intended workload can reduce unused capacity, avoid unnecessary material use, and cut wasted energy over a robot’s life cycle.

That principle underpins the work of an IEEE RAS-funded team, led by Antun Skuric, that has developed an open-source platform for assessing the sustainability of collaborative robots.

To use it, you define a required workspace, payload, and trajectory, and the platform identifies the minimum-mass robot that satisfies your application requirements.

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.

Can robots really help communities overcome energy poverty?

Energy poverty and inefficient solar energy utilization are major challenges in Nigeria, where more than 90 million people lack reliable electricity access.

The SolarPeer 360 project, led by Umar Adetola Abdulganiyy, 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.

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.

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.”

SolarPeer links smart solar capture through tracking, controlled and metered distribution through embedded electronics, and behavior optimization through data, interfaces, and AI guidance.

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.

Beyond the lab, the team deployed five community mini-systems and ran a solar training and empowerment workshop that reached more than 500 students.

Can Caretta work faster?

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.

That’s part of the reasoning behind the ‘Caretta’ project, led by Mustafa Kemal Ambar, which brought robotics and sustainability education to students aged 8 to 16 on the island of Cyprus.

Inspired by the Caretta sea turtle, the project produced a functional robot prototype 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.

Treating the beach as both a test site and a classroom, students saw how engineering connects to local environmental problems and community needs.

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.”

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.

Want to learn more?

RAS University now has a free new class on Sustainable Robotics, you can learn more here.

You can also follow activities from the Sustainability and Climate Change Committee, including upcoming grant calls here.

This article originally appeared on IEEE RAS.

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) to oscillate back and forth. At certain frequencies, these oscillations become much stronger, producing the familiar humming sound.

Now, researchers in the MicroBioRobotic Systems (MICROBS) 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 has been published in Science Advances.

“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.”

The MICROBS Lab’s sound-powered boat. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

Miniature boats and microfliers

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.

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.

The MICROBS Lab’s microflier. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

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.

Using a 3D nanoprinting technique, the team built ‘microfliers’: 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.

A microflier in flight. 2026 EPFL/MICROBS – CC-BY-SA 4.0.

Toward sound-responsive robotics

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.

“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.

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.

Reference

Acoustic resonators as wireless actuators in air for small-scale robots, Junsun Hwang et al., Science Advances (2026).

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 why is it an interesting area for study?

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?

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.

The paper proposes a research agenda that brings these traditions into one loop. A foundation world model 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’s feedback could reject an unsafe update, request data from an uncertain region, or trigger a revision of the model.

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.

What is your vision for foundation world models?

To me, foundation 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.

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.

I’d want such a model to have three key properties. First, it should be calibrated: 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 compositional: verified local dynamics, behaviors, and certificates should be reusable when a new task is assembled. Third, it should be semantically queryable: 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.

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.

How does this vision differ from current models?

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.

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?”

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.

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.

Could you give an example of how such a model might work?

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.

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.

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.

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.

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.

What do you think the impact of such a framework on multi-agent systems could be?

Multi-agent systems make the problem both more urgent and more difficult. Each learning agent is a moving part of every other agent’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.

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.

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.

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.

About Florent

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 Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments received the Best Blue Sky Paper Award at AAMAS 2026.

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 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.

Natural disasters, aging, and economic competition

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 (3), geological disturbances remain inevitable. As such, disaster mitigation and response are high priorities that serve as motivation for robotics development in Japan (4). 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 (5).

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 (6). According to government roadmaps (4), 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 (7).

Japan has a mature robotics industry, claiming the title of the largest manufacturer and exporter of industrial robots for the last half century (8). 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 (9). 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.

Society 5.0

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 Society 5.0) (10). The directive is set by the Science and Technology Basic Plan, a large-scale roadmap updated every five years (with 2026 marking the transition into the 7th Plan). An additional Integrated Innovation Strategy is used as an annually-updated agile document for integrating urgent priorities into the larger Basic Plan.

Super cities

Japan is investing heavily into research on human-robot interactions, so that users are embedded early on into technological design considerations of Society 5.0. Accordingly, in 2020 the Japanese Parliament passed the Super City Amendment, 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 (11, 12). 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, Woven City, which provides a campus for employees to work, live, and even raise a family (13).

Moonshot programs

Japan also utilizes high-risk, high-impact research roadmaps with 30-year timelines, called Moonshot Programs, to encourage bold technological solutions for the future (14). 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.

Goal 1 of the Moonshot Program is to Overcome Limitations of Body, Brain, Space, and Time, a goal largely focused on the creation of Cybernetic Avatars – 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 Co-Evolution of Robots and AI. 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.

Humanoids and physical AI

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 (15). Japan had in fact led humanoid research decades back (16), already developing Honda’s famous Asimo in 2000 (17) – 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 (18).

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) (19).

In March 2026, Japan has also included updates to their Integrated Innovation Strategy (20), with plans to install R&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.

Strategic relations with the USA

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 (21). 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 (22).

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 (23). 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 (24).

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 (25), which demands the ramp-up of domestic R&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.

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.

On that note – our next month’s article will feature robotics strategies from the USA. Thanks for reading, and stay tuned.

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.

Ellen H. Rumley – Policy Analyst

Allison Okamura – Vice President

IEEE RAS Science & Technology Watch Board

References

[1] Hornyak, T. N. (2006). Loving the Machine: The Art and Science of Japanese Robots. Tokyo: Kodansha International.

[2] Mitsubishi Research Institute. (2022). How different countries perceive robots: An original survey.

[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.

[4] Cabinet Office, Government of Japan. (2025). Integrated innovation strategy 2025. [5] Encyclopaedia Britannica. (2026, March 9). Fukushima accident.

[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.

[7] Speed, J. Japan aims to take in 1.23M foreign workers under labor migration programs. The Japan Times.

[8] Nasdaq. (2021, October 25). Japan’s robot dominance.

[9] International Federation of Robotics. (2022, March 10). Japan is world’s number one robot maker.

[10] Cabinet Office, Government of Japan. (2016). The 5th Science and Technology Basic Plan (2016–2020).

[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).

[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.

[13] Toyota Motor Corporation. (2025, September 25). Toyota Woven City officially launches as a test course for the future of mobility [Press release].

[14] Japan Science and Technology Agency. (n.d.). Moonshot R&D | TOP.

[15] Kuniyoshi, Y. (2025, October 28). Appendix 3: PD’s policy (Moonshot Goal 3). Japan Science and Technology Agency (JST).

[16] Waseda University. (2026, May 8). The robots of Waseda: A 50-year journey in humanoid innovation. Waseda University News.

[17] Honda Motor Co., Ltd. (n.d.). History of robotics development. Honda Global Corporate Website.

[18] Morgan Stanley Research. (2025, May). Humanoids: A $5 trillion market. Morgan Stanley Investment Management.

[19] Nohara, Yoshiaki, and Komaki Ito. “Japan to quadruple spending support for chips and AI in budget.” The Japan Times, 26 Dec. 2025.

[20] The Japan News. (2024, May 20). Japanese govt to set up global hubs for AI robotics research.

[21] Cabinet Secretariat. (2022, December 16). National security strategy of Japan [Provisional translation].

[22] Fujitsu. (2025, October 3). Fujitsu expands strategic collaboration with NVIDIA to deliver full-stack AI infrastructure [Press release].

[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.

[25] Cabinet Office, Government of Japan. (2026, March 27). The 7th science, technology, and innovation basic plan (FY2026–FY2030) [Cabinet Decision].

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.

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.

In this study, an international joint team comprising researchers from EPFL (Switzerland), Duke University (USA), and Instituto Superior Tecnico (Portugal) developed a larval zebrafish-inspired robotic platform (ZBot) to systematically investigate the intrinsic characteristics and performance advantages of bout-and-glide intermittent swimming compared to continuous swimming.

This research focused on four scientific questions:

1. Which neural control mechanism underlies intermittent swimming locomotion?
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.

Figure 1. ZBot and real larval zebrafish.

2. Can intermittent bout-and-glide swimming achieve higher energy efficiency than continuous tail-beating swimming, and if so, under which conditions?

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..

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 digital twin simulation, simZFish.

Figure 2. 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.

3. 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?

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 (<1000) indicates the fluid dynamics in viscous regime, where the moving object experiences the viscous force to a high degree. A higher Reynolds number (>1000) indicates the fluid dynamics in inertial-dominated regime, where inertial forces overwhelm viscous forces.

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 < Re < 87.5) only 1/30 of that in normal water (1 CP, 64000 < Re < 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.

Video 1. ZBot was tested in fluids of different viscosities (by mixing water with carboxymethyl cellulose sodium salt)

4. What mechanisms lead to the energy efficiency of intermittent swimming?

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.

A popular reason for this energy saving is that intermittent swimming enhances the transfer of energy from kinematic tail movements to the body’s dynamic displacement in the liquid. This “fluid dynamics” 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.

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.

Importance of this research

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.

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.

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’t usually get to in my day-to-day work.

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.

One of the standout parts of the week was getting into Imperial’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.

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’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’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.

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’ve learned a lot from. A special thank you also to Marie Daniels for her support and guidance throughout the application process.

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.

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 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).

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.

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.

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.

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).

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.

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.

Some topics we will delve into include:

• the outstanding priorities and strategies of various country’s robotics roadmaps.
• the potential target audiences and intended outcomes of their readership.
• the influence of geopolitical tensions on roadmap strategies.

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.

Robotics Roadmap Issue #1

Ellen H. Rumley – Policy Analyst
Allison Okamura – Vice President

IEEE RAS Science & Technology Watch Board

References

[1] Saurabh Vaidya, Prashant Ambad, Santosh Bhosle, Industry 4.0 – A Glimpse, Procedia Manufacturing, Volume 20, 2018, Pages 233-238, ISSN 2351-9789.
[2] International Federation of Robotics (2025). World Robotics 2025 – Service Robots.
[3] International Federation of Robotics. (2024). Executive summary: World robotics R&D programs (Version 4).
[4] Special Competitive Studies Project (SCSP). (2025). “Who’s Ahead, Who’s Behind, and Where We Are Headed Next in the U.S.-China Technology Competition?”
[5] D. J. Hicks and R. Simmons, “The National Robotics Initiative: A Five-Year Retrospective,” in IEEE Robotics & Automation Magazine, vol. 26, no. 3, pp. 70-77, Sept. 2019.
[6] Christensen, Henrik, et al. A Roadmap for US Robotics – Robotics for a Better Tomorrow. UC San Diego, Computing Community Consortium and Engineering Research Visioning Alliance, Apr. 2024.
[7] Fredrik Heintz, Nabil Belbachir, and Edward Curry, “Strategic Research, Innovation, and Deployment Agenda 2025-2027”, February 2024, Brussels, ADRA.
[8] State Council of the People’s Republic of China. (2015). Made in China 2025. Beijing: State Council.
[9] D. Araiza-Illan et al., “A Road Map for Responsible Robotics: Promoting Human Agency and Collaborative Efforts,” in IEEE Robotics & Automation Magazine, vol. 32, no. 4, pp. 12-24, Dec. 2025.

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 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.

Led by Associate Professor Lum Guo Zhan from NTU’s School of Mechanical and Aerospace Engineering (MAE), the work was recently published in the academic journal Advanced Materials.

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.

“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.

Mini robots are being studied worldwide as a possible way to make minimally invasive surgical and medical procedures safer, less painful and more precise.

Such devices could one day allow doctors to carry out targeted surgeries deep inside the body without large cuts or bulky surgical instruments.

Overcoming a key robotics challenge

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.

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.

These materials are embedded with magnetic microparticles measuring 5 micrometres each, allowing different parts of the robot to respond to magnetic fields.

At the centre of the device is a magnetic module that can be magnetised, demagnetised and remagnetised in different directions.

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.

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.

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.

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.

Most miniature magnetic robots are also limited to five degrees of freedom. They can only move along three axes and rotate in two directions.

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.

Unlike slime-like mini robots, the NTU robot has a solid but flexible body, making it sturdier and easier to retrieve after use.

Tested on biological tissues

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.

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.

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.

The team also evaluated the biocompatibility of the robot’s materials by exposing them to human skin cells under laboratory conditions.

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.

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.

Assoc Prof Lum is also working with surgeons to understand how mini robotic systems could eventually fit into real clinical workflows.

“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.

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.”

Read the work in full

Miniature Soft Robot With Magnetically Reprogrammable Surgical Functions, Chelsea Shan Xian Ng, Yu Xuan Yeoh, Nicholas Yong Wei Foo, Keerthana Radhakrishnan, Guo Zhan Lum.

By Alex Shipps

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.

“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).

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 “SceneSmith” 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.

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 GPT-5.2. 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.

“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 paper 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.”

Talk to my agent

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.

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.

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.

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.

Behind the scenes

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.

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.

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.

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 “HSM” and “Holodeck,” SceneSmith made environments with more objects, including a private office, a pottery store, and even a Minecraft-themed gaming room.

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.

A system of many talents

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.

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.

“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.”

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.

The team presented their findings as a spotlight at the 2026 International Conference on Machine Learning.

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 “advanced robotic devices” from receiving the equipment authorization needed for sale in the United States, citing supply-chain vulnerabilities and cybersecurity risks.

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.

Existing authorized models are unaffected for now, and exemptions or conditional approvals may be available.

Reaction is predictably mixed. Georg Stieler, a global robotics advisor and managing director for Asia at STM, told The Robot Report:

“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.”

Meanwhile, John Moolenaar, a Michigan Republican who chairs the House ​Select Committee on China, told Reuters that the FCC move “protects our country and strengthens our nation’s robotics industry.”

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.

Expect this story to run and run over the coming weeks, with many peaks and valleys for various stakeholders.

Speaking of peaks and valleys, Unitree Robotics’ newly launched Super Athlete AS2-W seems to handle them quite well…

Ghostly smudges, puffins & growing ivy

Researchers at Northwestern University 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.

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.

Meanwhile, researchers at MIT and EPFL 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.

Inspired by diving birds including puffins and petrels, the Flapping-wing Aerial Aquatic Vehicle 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.

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 in July 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.

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.

Humanoid, all too humanoid

Returning to the topic of valleys for a moment, it was uncanny valley time on social media in July following a showcase of the Origin F1 at WAIC 2026 in Shanghai.

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.

LG Display provided a contrasting design vision at K-Display 2026, presenting a curved OLED “face” for humanoid robots that communicates through deliberately artificial expressions rather than attempting to pass as human.

A new Bayesian model of the uncanny valley published in July might provide robot designers with a framework for handling uncanny valley design issues in future.

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.”

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.

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 Pythonesque results…

Historic RoboCup match

On July 5, at RoboCup 2026, 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.

RoboCup’s long-term objective is gloriously ambitious:

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.

Do you think RoboCup’s objective is attainable? Will robots ever prevail over human tiki-taka? Drop us a line at ras@ieee.org.

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.

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.

A joint team from EPFL (Switzerland), Duke University (USA), and the Instituto Superior Técnico (Portugal) took on this challenge by creating a realistic larval zebrafish simulation and a biomimetic robot, published in Science Robotics. 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.

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.

A blueprint from the living fish brain
The starting point was work in the Naumann Lab at Duke, 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 best-fit wiring diagram of the brain-scale OMR pathways.

Drawing on other insights about neural processing in the vertebrate retina and spinal cord, Dr. Xiangxiao Liu and Luca Zunino 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.

simZFish: a brain you can take apart
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.

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 “bout gate” releases a burst of tail beats, producing the characteristic burst-and-glide swimming of real larval zebrafish.

Because every part is simulated, researchers can change any aspect of simZFish’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 “minimal essential elements” for OMR behavior.

Figure 1. 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.

The body is part of the computation
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 “aperture problem”. 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.

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 “reveals” 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.

Closing the loop: a prediction sends the neuroscientists back to the microscope

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, Dr. Matthew Loring, showed these visual stimuli to real zebrafish, they barely turned.

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.

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. “simZFish narrows the search, and the animal experiments verify the predictions, and together they complete the puzzle of the neural circuit,” said EPFL’s Auke Ijspeert, who directs the Biorobotics Laboratory (BioRob) at EPFL.

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.

Into the wild: a robot that keeps up with the current using vision alone
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 ZBot, 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.

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 “eyes” were switched off and just 20 seconds when it drifted with the motors off (Figure 2, Video 1).

Figure 2. ZBot swimming in the Chamberonne River, Canton de Vaud, Switzerland.

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 “lateral line” network of sensory organs along the side of the fish body to detect water flow. “This is the first proof that effective rheotaxis can be achieved using visual neural circuits alone,” noted Professor Ijspeert.

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).

Why it matters for robotics
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.

The same bio-inspired burst-and-glide control of the ZBot underlies a companion study by the team showing that intermittent swimming saves energy, 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.

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.

Even so, the approach the team built offers a powerful template for connecting brains, bodies, and behavior. “By integrating simulation, robotics, and animal experiments, we get a far more complete view of an animal’s neural model,” 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.

Paper and team information
You can access the simZFish open-source platform here and explore more work on the Naumann Lab Github.

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.

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, 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.

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.

Propulsion module and payload capsule

The nanorobot, which the team describes in the journal Advanced Functional Materials, 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.

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.

A DNA-based molecular Velcro system

One of the nanorobots, imaged with a Transmission Electron Microscope. (Image: Voichita Mihali).

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.

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.

Targeted attack on cancer cells and other applications

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.

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.
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).

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.

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.

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.

Reference

Multiplex Modular Nanorobotic Systems with Catalytic Activity under Magnetic Navigation, Voichita Mihali et al., Advanced Functional Materials (2026).

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 Billard, Renaud Detry, Nadia Figueroa, Maximilian Foriest, Dongheui Lee, Kunpeng Yao
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.

Summary

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

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.

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.

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.

Publications growth

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.

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).

This article originally appeared on IEEE RAS.

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 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.

Published in Nature Communications and Advanced Science, 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.

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.

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.

Team leader, Scientia Associate Professor Thanh Nho Do, from UNSW’s School of Biomedical Engineering and UNSW Medical Robotics Lab, says the work is important because cardiovascular disease remains the world’s leading cause of death.

“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.

“Because it affects people in different ways, developing medical devices to improve heart function is challenging.

“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.

“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.”

Recreating the beating heart

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.

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.

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.

“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.

“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.

“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.”

The system allows researchers to actively adjust the tension in the artificial papillary muscles that support the mitral valve.

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.

Mimicking human heart disease

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.

Healthy valve function produced normal pressure and flow patterns, while introducing disease caused characteristic changes seen in patients.

“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.

“Critically, we were able to adjust mitral valve function by controlling papillary muscle length.

“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.

“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.”

Scientia Professor Nigel Lovell, Head of School of Biomedical Engineering & 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.”

The researchers also used the system to test a newly developed soft robotic cardiac catheter inside the beating model.

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.

Credit: UNSW/Richard Freeman.

Reducing reliance on animal models

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.

“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.

“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.

“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.

“HFpEF disease that makes up 50% of heart failure cases deserves its own mechanical treatment options.”

More importantly, the model successfully reproduced many of the changes seen in HFpEF, including changes in heart function and blood flow.

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.

The researchers also envision a future in which patient-specific versions of the model could be created using medical imaging data.

These personalised models could help clinicians evaluate different devices and treatment approaches before operating, improving surgical planning and potentially leading to better outcomes.

“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.

“We are looking forward to validating these concepts and pushing towards clinical adoption in the future.”

Dr James Davies and Scientia Associate Professor Thanh Nho Do in their laboratory. Credit: UNSW/Richard Freeman.

Future validation

While the study demonstrates the technology’s potential, the researchers stress that the current model is still a proof of concept rather than a finished clinical tool.

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.

Most importantly, the platform must be validated against real patient data.

“The most important next step is deeper validation against clinical data,” Professor Do says.

“The current studies demonstrate strong proof-of-concept performance.

“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.”

The team, which also includes Professor Christopher Hayward, a heart failure and transplant cardiologist at St Vicent’s Hospital Sydney, as well as Professor Jelena Rnjak-Kovacina and Scientia Associate Professor Hoang-Phuong Phan from UNSW, hope that with further development of this technology it can be adopted in clinical settings.

“Rather than viewing the current model as a finished clinical tool, we see it as an enabling platform,” Dr Davies added.

“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.”

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 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.

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.

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 IEEE Transactions on Medical Robotics and Bionics, in which the research team presents the robot.

Fewer appointments at the dentist

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.

Dr Yukiko Tomooka mounting the dental robot on a model patient. Photo: University of Basel, Catherine Weyer.

Remarkably precise dental robot

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.

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.

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.

Sensors and camera to follow

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.

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.

Read the work in full

Miniature Intraoral Robot (MIR) for Minimally Invasive Tooth Preparation, Yukiko Tomooka, Carina Schmidt, Jenni Hjerppe, Marc Balmer, Ronald Jung, Raphael Mohler, Ahmet Yildiz, Murali Karnam, Manuela Eugster, Georg Rauter, IEEE Transactions on Medical Robotics and Bionics (2026).

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.

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.

We spoke with lead author Benjamin Calmé about the team’s work.

Q: 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?

Benjamin Calmé: 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.

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.

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.”

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.

Q: For readers outside soft robotics, what is a “growing robot”?

Benjamin Calmé: 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.

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.

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.

Q: What problems does this work address?

Benjamin Calmé: 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.

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.

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.

Q: Your paper highlights pressure-free growth. Why is this important?

Benjamin Calmé: Safety is one reason, and controllability is another.

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.

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.

Now we can grow and steer simultaneously, which makes the system faster and more usable.

Q: What is novel about your approach compared with previous systems?

Benjamin Calmé: 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.

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.

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.

Q: How does the real-time shape control system operate?

Benjamin Calmé: 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.

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.

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.

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.

Q: The paper also demonstrates retroflexion and biome sampling in an ex vivo stomach model. Why are those meaningful milestones?

Benjamin Calmé: 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.

Q: What were the biggest engineering hurdles?

Benjamin Calmé: 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.

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.

Q: What comes next, and how close is clinical use?

Benjamin Calmé: We are especially interested in neural and spinal applications, where precise placement of electrodes could help restore function after injury.

We are still early in development. A realistic near-term target is robust pre-clinical performance: safety, biocompatibility, and successful in-vivo demonstrations.

Clinical adoption takes much longer because regulation must be rigorous. That is appropriate when patient safety is involved.

Q: How would you explain this advance to a non-technical person?

Benjamin Calmé: 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.

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.

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.

The paper, “Pressure-free Magnetic Soft Growing Robot with Real-Time Shape Control and Sensing for Biome Sampling,” appears in the proceedings of the 2026 IEEE 9th International Conference on Soft Robotics (RoboSoft).

This article originally appeared on IEEE RAS.

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.

In our work, we take a different route. We build an Interactive World Simulator: 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.

The key idea is that, if the simulator is faithful enough, we could unlock two long-standing bottlenecks in robot learning:

– Data generation for training becomes cheap, because we can collect demonstrations inside the simulator.
– Policy evaluation becomes scalable and reproducible, because we can roll many policies through the simulator under identical conditions.

What the world simulator can do
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.

A few examples of what the model captures:

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.

Mug grasping: it captures fine-grained effects such as the mug slipping out of the gripper, or the handle being nudged and rotated.

Pile sweeping: it can generate video for multiple viewpoints consistently

You can try this directly on our project page: just open a browser and play with it using your keyboard!

How we built the interactive world simulator

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.

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.

How is it different from prior works?

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.

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.

Application 1: scalable data generation

If our simulator is good enough, can demonstrations collected using this world model actually replace real demonstrations for training imitation learning policies?

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.

Application 2: faithful policy evaluation

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.

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.

Looking forward

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.

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.

By Holly Hartigan

A team of Cornell undergraduates beat 95 other teams to take the grand prize at The Farm Robotics Challenge with their invention: an autonomous robot that kills weeds with electricity.

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.

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.

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?”

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.

“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.”

The problem of weeds

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.

“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.”

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.

Selin provided feedback to the students as they developed their robot and said he is excited to try out Rootline’s new technology.

“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.”

The interdisciplinary nature of robots

“Robotics is many different systems in one,” Kurz said. “It is interdisciplinary by definition.”

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.

Neiss said the way the team came together felt a bit like destiny.

“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.

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 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.

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.

Their results, published in Science, 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.

Image copyright: Raphael Zufferey.

“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.”

Flight mechanics

Zufferey began working on the robot as a postdoctoral fellow in the Laboratory of Intelligent Systems (LIS) and Biorobotics Lab (BioRob) 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 AURA Lab, which focuses on engineering bioinspired aerial and aquatic vehicles. The study also includes co-authors from Northwest Indian College (USA).

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.

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.

Image copyright: Raphael Zufferey.

Like a bird, but without feet

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.”

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.

Reference

Leaping out of the water: Aerial-aquatic locomotion with flapping wings, Raphael Zufferey, Simon L. Jeger, Moritz Hüsser, Fernando Ruiz, Anthony Lapsansky, Auke Ijspeert, Dario Floreano, Science (2026).

By Jennifer Chu

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.

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.

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.

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.

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.

“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.”

Zhao, Gengxi Lu, and their colleagues present the wristband’s new design in a paper which appeared in Nature Electronics. 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.

Seeing strings

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.

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.

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.

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.

“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.”

Mapping manipulation

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.

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.

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.

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.

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.

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.

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.

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.

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.

“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 intuitive and versatile controls for virtual reality and robotic hands.”

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 Singapore National Research Foundation through the Singapore-MIT Alliance for Research and Technology.

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 an exciting first day!

Incheon Convention Center (Songdo Convensia)

For the full schedule, visit:
https://t.co/T5mjdVMhH3#RoboCup2026 #RoboCup #Robotics #AI pic.twitter.com/wHZkfM69jL

— RoboCup Federation (@robocup_org) July 1, 2026

View this post on Instagram

A post shared by RoboCup Federation (@robocup.official)

View this post on Instagram

A post shared by BerlinUnited (@berlin_united_robocup)

Can't make it to Incheon? We've got you covered!

Starting July 2, follow all the excitement of RoboCup 2026 live from anywhere in the world!

Where to watch:
YouTube: @RoboCup
Twitch: robocupofficial#RoboCup2026 #RoboCup #LiveStreaming #Robotics #AI #Incheon pic.twitter.com/p3wm8mr3CV

— RoboCup Federation (@robocup_org) July 1, 2026

View this post on Instagram

A post shared by RoboCupJunior Egypt (@rcjegypt)

Little Booster K1, trying to get up after falling mid football game!
#robocup2026

[image or embed]

— Raghav Arora (@ra-aurora.bsky.social) 6 July 2026 at 05:05

View this post on Instagram

A post shared by Colegio Leonardo Da Vinci (@davinci_colegio)

View this post on Instagram

A post shared by Tech United (@techunitedeindhoven)

Big win at #RoboCup2026!

4 Mini Pi plus teams reached the Top 8, with Hamburg Bit-Bots taking .

Open platforms accelerate robotics. #HumanoidRobots #Robotics #OpenSource #EmbodiedAI #ROS2 #Automation #PhysicalAI pic.twitter.com/BAZeQGHuNp

— High Torque Robotics (@HTrobotics) July 5, 2026

View this post on Instagram

A post shared by B-Human (@bhumnbhumn)

View this post on Instagram

A post shared by Fernanda Bufon Färber (@fernandabufon)

Straight from RoboCup 2026, at Incheon, Korea.
We added an external lidar, and a literal backpack to the booster T1 to achieve accurate indoor localisation and navigation.
@texasrobotics.bsky.social #Robocup2026

[image or embed]

— Raghav Arora (@ra-aurora.bsky.social) 6 July 2026 at 05:01

View this post on Instagram

A post shared by Robot Club Toulon (@robotclubtoulon)

A team from China's Tsinghua University successfully defended its Humanoid League title at RoboCup 2026 on Sunday in South Korea. #RoboCup2026 #HumanoidLeague #TsinghuaUniversity #robotsoccer pic.twitter.com/88gKYpxL3J

— China Xinhua News (@XHNews) July 6, 2026

View this post on Instagram

A post shared by autonOhm (@autonohm_official)

This is RoboCup 2026!

Nearly 3,000 participants from 40 countries, united by one passion: advancing robotics and artificial intelligence!
Thank you to everyone who is part of this incredible journey! #RoboCup2026 #Robotics #AI #Incheon pic.twitter.com/X5enZLypmF

— RoboCup Federation (@robocup_org) July 4, 2026

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

1. Invic, Wuhan University, China
2. Hamburg Bit-Bots, Universität Hamburg, Germany
3. GeoHBots, School of Artificial Intelligence, China University of Geosciences, China

Middle division

1. B-Human, Universität Bremen and German Research Center for Artificial Intelligence (DFKI), Germany
2. HTWK Robots, Leipzig University of Applied Sciences, Germany
3. Rhoban, University of Bordeaux, France

Large division

1. Tsinghua Hephaestus, Tsinghua University, China
2. CAU Mountain&Sea, China Agricultural University, China
3. Water, Beijing Information Science & Technology University, China

You can watch the action from one of the semi-finals in the middle division, which saw HTWK take on Rhoban.

In the final of the middle division, HTWK took on B-Human:

In addition to the main competitions, there were five league-wide awards:

• Best Customized Humanoid Award: HERoEHS (ALICE 4th version)
• Best Humanoid Software Award: B-Human (Game Controller)
• Open Research Challenge: Ruhrbot Devils (AI Camera Platform for Embedded 2D/3D Game Analysis in RoboCup HSL)
• Best Innovation Award: Bahia Robotics Team
• Best Referee Award: Anastasia Prisacaru (Berlin United)

Hear from Team Hephaestus of Tsinghua University, who won the large division:

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 here.

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 taking part are geographically widespread, ranging from Colombia to Malaysia, from Germany to Australia.

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 here. As a taster, here is the qualification video from team CAU Mountain&Sea (from China Agricultural University) who are currently leading the small division competition, and are in fourth place in the large division.

Yesterday’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 here.

In terms of the vital statistics of the robots, the heaviest and tallest robot is HERoEHS’s ALICE 4 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 BigHeroX’s 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 ITAndroids’ Chape, at just 3.8kg and 53cm tall.

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, CAU Mountain&Sea is the only team to win all four matches, and sits atop the table with 12 points, and impressively only conceding one goal. Hamburg Bit-Bots and GeoHBots are in second and third place respectively, having both won three games and lost one.

The middle division has fast established itself as one of the most compelling competitions. B-Human 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: HTWK Robots, Rhoban, whIRLwind Amsterdam, and THMOS.

Over in the large division, teams have completed three rounds of seeding, with just one further round to come tomorrow. At this stage Tsinghua Hephaestus is the only perfect team, sitting on nine points. Behind them, two teams have each won two matches and drawn the third: PCMS-HRG and Robo-Erectus.

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.

Many thanks to JT Genter for providing the photos, videos, and facts for this article.

The host venue for ICRA 2026: Messe Wien, also known as VIECON.

Workshop on robot ethics

My week at ICRA began with the 2nd ICRA 2026 Workshop on Robot Ethics: Ethical, Legal and User Perspectives in Robotics & Automation (WOROBET). 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. 

Yasuhisa Hirata, Professor at Tohoku University, began by presenting his vision of a world with physically assistive robots, such as detachable exoskeletons or cycling wheelchairs. These tools can affect people’s sense of self-efficacy and motivation, and there are a host of ethical implications that come with this – how do you help people just enough to build their confidence, without slipping into deception? 

We then heard from Prof. Minoru Asada from Osaka University, who discussed his aim to implement pain signals into robots, 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? 

Alan Winfield, 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 framework for social robot accident investigation. 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 unethical robots via malicious hacking. The theme that we must focus on human morality, as opposed to machine morality, was repeated throughout the day. 

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 Praminda Caleb-Solly, 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 robots in social care will become a more urgent need in the years to come, these questions may become more salient. 

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.

Welcome to the jungle – the robot exhibition floor

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. 

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.

The cute.

The slightly uncanny.

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 D1-modular robot from Direct Drive. Unlike most robot dogs, it can split into two halves, with the ability to jump, twist, and traverse difficult terrain. 

Sharpa’s North 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. Enchanted Tools’ 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. Tesollo’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 Vinrobotics’ humanoid offering was reminiscent of the Cybermen, with its gently wheezing joints, but the team assured me it was much friendlier. The pint-sized Boosters were almost always playing football, not far from their similarly sized Agibot cousins. 

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 unlock whole new swathes of tasks to automate – and who wouldn’t want a robot folding their laundry? 

Industrial challenges: solving dexterity 

Tackling the dexterity challenge really defined the industrial talks for me this year. A talk by ARIA’s program director, Prof. Jenny Read, demonstrated how the UK government is already laying the groundwork here.

They outlined their funding proposals as part of their Smarter Robot Bodies program, which is split into two branches: robot locomotion and robot dexterity. 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. 

One standout innovation in the realm of dexterity was TARS, 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. 

TARS’ DexHand. Image credits: TARS.

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 – despite the technical abilities of all the robots on the floor, few were able to perform tasks which required such fine motor skills. 

TARS robot zipping up a rucksack.

On Thursday, Dr Wenchao Ding 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. 

Plenary talks

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. 

Ken Goldberg 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 close the data gap 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 – 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. 

According to Goldberg, the two dominant cultures in engineering – 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 art to robotics and automation. 

He outlined four possible solutions to the data gap:

1. Simulations – these work incredibly well for locomotion and body control, but less so for manipulation due to the number of forces and instabilities involved.
2. World models – they do not currently properly capture the physics, and hallucinations can be problematic. 
3. Human teleoperation – 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. 
4. Real data from functioning robots – this is less commonly used, but can be powerful. 

Prof Goldberg described how he used the fourth approach in his robotic delivery packing company, Ambi Robotics, for 22 years. Picking up bags is an example of variational automation –  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 – 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. 

During Thursday’s keynote on Robot Learning, Planning & Foundation Models, Stefanie Tellex 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 her work creating robots that can understand complex, goal-based commands in only  partially observed, dynamic environments, and outlined the grounded Turing test – a reimagining of the Turing test for embodied AI. 

An example of a robot performing a goal-based task in a dynamic environment. Credits: Tellex et al, 2026.

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. 

Science communications crash course

One of my favourite parts of ICRA was delivering the Science Communications Crash Course. Along with Robohub Executive Trustee Sabine Hauert, IEEE Spectrum Senior Editor Evan Ackerman, and IEEE Spectrum Community Manager Kohava Mendelsohn, 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 – 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. 

Sabine kicking off the science communications crash course. Image credits: Taraja Arnold

Delivering my part of the course. Image credits: Taraja Arnold

Art and robotics 

The arts and robotics section was rich and interesting. There was a lot to visually take in, with constant background music from a robotic saxophone. 

Masatoshi Hamanaka’s robotic saxophone. Image credits: ©Denes Erdos – Your Event Photographer

PET – marked by a large “PET ME” sign – 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. 

Rhombus Research 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 Silke Grabinger explored human-robot interaction via her piece, AREYOUARE. 

Silke Grabinger performing AREYOUARE. Image credits: ©Denes Erdos – Your Event Photographer

I’d also like to acknowledge some of the video creators I met there. YouTubers Back to Engineering and the. Amazing, PhD are making some fantastic videos about physical AI. 

Nothing lasts forever – ending with the robot parade 

ICRA 2026 ended with the robot parade, which attracted quite a crowd. See if you can spot the panda, dragon, and headless humanoid!

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. 

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 – we may need to face the questions that they raise sooner than we think. 

Note: Where image and video credits are not stated, they belong to Ella Scallan.

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 of daily updates, we’ll be bringing you the latest results, videos, and news from the humanoid soccer league.

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.

The first two days of competition are be devoted to the seeding round. Teams play using the Swiss-system of ranking to decide who gets through to the knockout stages.

Livestreams from the different fields of play can be found here.

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: GeoHBots, CAU Mountain&Sea, and Hamburg Bit-Bots. There are also three teams in the middle division who have claimed the six point haul: B-Human, RoboRoos, and HTWK Robots.

You can watch a short summary of the first day, including some of the robots in action, from KBS News:

This short video from RoboCup gives a flavour of the day’s happenings, which also featured the opening ceremony.

View this post on Instagram

A post shared by RoboCup Federation (@robocup.official)

We will be back tomorrow with further updates on competition results, some highlights from the day, and insights into how the event is progressing.

Useful links

• RoboCup 2026 homepage
• Humanoid league YouTube channel
• Humanoid league results page
• RoboCupSoccer homepage

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’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.

The leagues and their competitions

You can find out more about the different leagues and the competition schedules and details at these links:

• RoboCupSoccer
  • Humanoid
  • Middle size
  • Small size
  • Simulation
• RoboCupRescue
  • Robot
  • Simulation
• RoboCup@Home
• Industrial
• RoboCupJunior
  • Soccer
  • Onstage
  • Rescue

WEROB

A workshop focused on sharing projects, experiences, and innovations in educational robotics. This session is geared towards students, mentors, and educators. Find out more here.

Symposium

The RoboCup symposium will take place on 6 July. More information can be found here.

There will be two keynote talks:

• Hyun Myung, Spatial Intelligence for Autonomous Robot Navigation in the Wild
• Gentiane Venture, From function to meaning: Making robots that understand and belong

Find out more at the event website.

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?

In this special live recording at the Great Exhibition Road Festival 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.

George Mylonas is an Associate Professor in Robotics and Technology in Cancer at Imperial College London, and the director of the Human-centred Automation, Robotics and Monitoring in Surgery lab at The Hamlyn Centre, Institute of Global Health Innovation and the Department of Surgery & 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.

Antonia Tzemanaki is a Senior Lecturer in Robotics at the University of Bristol and a core member of the Bristol Robotics Laboratory. She leads the Dexterous Manipulation and Wearable Robotics group 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.

Tom Vercauteren is a Professor of Interventional Image Computing at King’s College London, where he leads the Contextual Artificial Intelligence for Computer Assisted Interventions research group. 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.

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 brain to evoke images of faces and specific objects in the users instead of simply evoking spots of light. The models developed at EPFL were used by Dutch researchers for live trials on sighted monkeys. The preliminary results, presented in April at the International Conference on Learning Representations, show very promising implications for vision in humans as well.

“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.”

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.

“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.”

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.

Towards restoring meaningful sight

“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.”

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.

“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.”

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.

“The monkey saw an image already, and then we were able to basically distort it to change the perception in somewhat predictable ways,” says Schrimpf. “The bigger goal will be to evoke a percept from scratch: to make someone see something meaningful even when their eyes aren’t delivering a usable image.”

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.

“Cochlear implants are great, but they are also not perfect in many ways, and they don’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.”

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 more than 130 teams from around the world.

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.

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.

As wildfires become more frequent and severe worldwide, AURA Foresight is developing technology that helps stop fires before they become disasters. The team’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.

Detect Early. Verify Quickly. Intervene Immediately.

AURA Foresight combines fixed sensors, artificial intelligence and swarms of autonomous flying robots into a seamless detect–verify–act capability.

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.

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.

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.

Key advantages include:

• Out-of-the-box deployment with minimal setup requirements.
• Adaptability to any environment, from forests and remote wilderness to critical infrastructure corridors.
• Scalability from a handful to dozens of flying robots, depending on operational needs.
• Compatibility with different aircraft and robot platforms, avoiding vendor lock-in.
• Built on commercially available technologies, making advanced wildfire protection accessible and achievable for organisations of all sizes.

The result is a system that can help agencies move from passive monitoring and delayed response to proactive, automated intervention.

Developed With Firefighters, For Firefighters

AURA Foresight’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.

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.

“It’s amazing what can be achieved when great people come together around a shared purpose,” said Dr Georgios Tzoumas, Team Co-Lead of AURA Foresight and Research Fellow at the University of Bristol.

“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’re showing that it’s possible to tackle wildfires while they’re still small, before they grow out of control. We can’t wait to demonstrate our technology in the field in Alaska.”

A Global Consortium Combining Expertise from the UK and Australia

AURA Foresight is a unique international collaboration bringing together AURA in the United Kingdom and Fire Foresight in Australia.

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.

Fire Foresight 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”.

Together, these partners combine world-leading expertise in swarm robotics, autonomous systems, artificial intelligence, computer vision, aerial robotics, wildfire operations and field deployment.

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’s most pressing climate challenges.

As destructive wildfires continue to increase in frequency and severity around the world, AURA Foresight’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.

Our motto is – “Detect early. Verify quickly. Intervene immediately. Stop wildfires before they become disasters.” Fingers crossed for a good performance in our finals this weekend!

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 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.

By Adam Zewe

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. 

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.

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. 

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.

The trajectory planner is also efficient enough for real-time flight using only the robot’s onboard computer and sensors. 

Named 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.

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.

“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.

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 professor of aeronautics and astronautics and a principal investigator in the Laboratory for Information and Decision Systems (LIDS) and the Aerospace Controls Laboratory (ACL) at MIT. The research appears in IEEE Robotics and Automation Letters.

Overcoming trade-offs           

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.

“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.

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. 

But many existing systems force tradeoffs that limit performance. 

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.      

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.

To do this, they overcame a key challenge that limits many open-source systems. 

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.

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.

A MIGHTY method

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.

“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.

The researchers used a clever technique to reduce this computational overhead. 

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.

“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.

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.

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. 

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.

“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.

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.

“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.

This research was funded, in part, by the United States Army Research Laboratory and the Defense Science and Technology Agency in Singapore.

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 motion. The research, published May 20 in Science Robotics, demonstrates a robotic system that resembles soft matter, continuously deforming and reorganizing as it moves, driven by what researchers call mechanical intelligence.

“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.”

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.

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.

“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.”

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.

“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’s being jostled and then use an audible buzz to slow down nearby modules while it catches up. It’s as simple as that.”

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.

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.

“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.”

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, 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.

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 for Human-LLM Agent Teams: A Multi-Stakeholder Lens, Mireia Yurrita, Davide Dell’Anna, Pradeep K. Murukannaiah, Catholijn M Jonker, and Pinar Yolum

Nominees

• UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles, 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
• Ratio-Based Signaling for Source-Victim Separation in Swarm Fault Detection, Longyin Cui
• The Impossibility of Strategyproof Rank Aggregation, Manuel Eberl and Patrick Lederer
• Generalized Per-Agent Advantage Estimation for Multi-Agent Policy Optimization, Seongmin Kim, Giseung Park, Woojun Kim, Jiwon Jeon, Seungyul Han, and Youngchul Sung
• R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memory, Maoyuan Li, Zhongsheng Wang, Haoyuan Li, and Jiamou Liu
• Defection at First Sight: Learning Partner Selection in Optional Social Dilemmas without Prior Information, Benedict Russell, Chin-wing Leung, and Paolo Turrini
• Characterizing Consensuses in Belief Flow Networks, Nicolas Schwind, Gauvain Bourgne, and Katsumi Inoue
• Grassroots Federation: Fair Democratic Governance at Scale, Nimrod Talmon and Ehud Shapiro
• Health Facility Location in Ethiopia: Leveraging LLMs to Integrate Expert Knowledge into Algorithmic Planning, Yohai Trabelsi, Guojun Xiong, Fentabil Getnet, Stéphane Verguet, and Milind Tambe
• MeCo: Enhancing LLM-Empowered Multi-Robot Collaboration via Similar Task Memoization, Baiqing Wang, Helei Cui, Bo Zhang, Xiaolong Zheng, Bin Guo, and Zhiwen Yu

Pragnesh Jay Modi Best Student Paper Award

Winner

• Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps, Anwesha Das, John Duff, Jörg Hoffmann, and Vera Demberg

Nominees

• Efficiently Computing Equilibria in Budget-Aggregation Games, Patrick Becker, Alexander Fries, Matthias Greger, and Erel Segal-Halevi
• Building Large-Scale Drone Defenses from Small-Team Strategies, Grant Douglas, Stephen Franklin, Claudia Szabo, and Mingyu Guo
• Robust Counterfactual Inference in Markov Decision Processes, Jessica Lally, Milad Kazemi, and Nicola Paoletti
• Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery, Yue Zhang, Zhe Chen, Daniel Harabor, Pierre Le Bodic, and Peter J. Stuckey
• Reputation as a Solution to Cooperation Collapse in LLM-based MASs, Siyue Ren, Wanli Fu, Xinkun Zou, Chen Shen, Yi Cai, Chu Chen, Zhen Wang, and Shuyue Hu

Blue Sky Ideas Award

Winner

• Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments, Florent Delgrange

Nominees

• Guiding Sociotechnical Systems toward Value-Norm Equilibrium, Nirav Ajmeri, Marina De Vos, Davide Dell’Anna, Pradeep K. Murukannaiah, Vivek Nallur, Luis Gustavo Nardin, and Munindar P. Singh
• The Dynamic Turn in Strategy Logics, Rustam Galimullin, Maksim Gladyshev, Munyque Mittelmann, and Nima Motamed

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 & 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.

Henrik I Christensen, Professor of Computer Science & 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 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.

Key headline findings of this roadmap are:

• The global robotics market reached $53.2B in 2024 and is on a trajectory to $178.7B by 2033.
• 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.
• Vision-Language-Action (VLA) models are the most consequential algorithmic development of the current period, enabling cross-embodiment generalization for the first time.
• 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.
• 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.
• 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.

The 52-page comprehensive document covers the following sub-topics:

• Introduction and scope. Motivation and methodology.
• Global market baseline.
• State of the art: academic research landscape. Embodied AI, foundation models, reinforcement learning, navigation, manipulation and sensing, bio-inspired locomotion, multi-robot systems, and human-robot collaboration.
• Enabling technologies: cross-cutting advances. Materials science and soft robotics, computing infrastructure, perception and sensing.
• Regional technology strategies. Europe, Asia, USA.
• Technology roadmap 2025–2035. Algorithms and AI, hardware and actuation, materials and manufacturing, and systems, safety and deployment.
• Sector-specific analysis, observations, and recommendations. Manufacturing, logistics, healthcare, agriculture, mining, construction, service robots.
• Cross-cutting strategic themes. The humanoid convergence race, sustainability, workforce and societal impacts, geopolitical technology risks.
• Recommended research priorities by region. Covering Europe, USA and Asia.

You can read the roadmap in full here.

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 “human-in-the-loop” analytics, RoboChem Flex caters to all synthesis laboratories, large or small. The paper provides all the information to build their own system.

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.”

Cost down, versatility up

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.

“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.”

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.”

3D printed components and a “human-in-the-loop” option

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’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.

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.

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.

Professor Timothy Noël introducing RoboChem Flex.

Robochem Flex case studies

• Optimization of pyrrole trifluoromethylation using adaptive weighted exploration and NMR analysis.
• Deoxygenative C–H functionalization via hypervolume optimization using HPLC analysis.
• Noisy hypervolume optimization of photocatalytic isotope labelling using Raman Spectroscopy.
• Selective enzymatic reduction of a diketone using HITL and dual acquisition batching.
• Optimization of Buchwald-Hartwig aminations via transfer learning and ligand featurization.
• Multi-objective optimization of an enantioselective photocatalytic [2+2] cycloaddition using chiral HPLC.

All code used for RoboChem Flex is openly available via GitHub. 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.

Read the work in full

A flexible and affordable self-driving laboratory for automated reaction optimization, 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 & Timothy Noël, Nature Synthesis (2026).

Claire chatted to Ahti Heinla from Starship Technologies about their AI-powered delivery robots that operate independently on streets and pavements.

Ahti Heinla is the co-founder and CEO of Starship Technologies, the world’s leading autonomous delivery company building AI-powered robots that operate fully independently in real-world environments. One of the original engineers behind Skype’s billion-dollar success, Ahti later made a quiet pivot into robotics, spending the past decade advancing practical, consumer-facing AI. Under his leadership, Starship has completed more than 10 million autonomous deliveries with a fleet of over 2,700 robots navigating streets, pavements, weather, and people, without human intervention.

Consider the chief difference between living systems and electronics: The first is generally soft and squishy, while the latter is hard and rigid. Now, in work that could impact human-machine interfaces, biocompatible devices, soft robotics, and more, MIT engineers and colleagues have developed a soft, flexible gel that dramatically changes its conductivity upon the application of light.

Enter the growing field of ionotronics, which involves transferring data through ions, or charged molecules. Electronics does the same, with electrons. But while the latter is well established, ionotronics is still being developed, with one huge exception: living systems. The cells in our bodies communicate with a variety of ions, from potassium to sodium.

Ionotronics, in turn, can provide a bridge between electronics and biological tissues. Potential applications range from soft wearable technology to human-machine interfaces

“We’ve found a mechanism to dynamically control local ion population in a soft material,” says Thomas J. Wallin, the John F. Elliott Career Development Professor in MIT’s Department of Materials Science and Engineering and leader of the work. “That could allow a system that is self-adaptive to environmental stimuli, in this case light.” In other words, the system could automatically change in response to changes in light, which could allow complex signal processing in soft materials.

An open-access paper about the work was published online recently in Nature Communications.

A growing field

Although others have developed ionotronic materials with high conductivities that allow the quick movement of ions, those conductivities cannot be controlled. “What we’re doing is using light to switch a soft material from insulating to something that is 400 times more conductive,” says Xu Liu, first author of the paper and former MIT postdoc in materials science and engineering who is now an incoming assistant professor at King’s College London.

Key to the work is a class of materials known as photo-ion generators (PIGs). These can become some 1,000 times more conductive upon the application of light. The MIT team optimized a way to incorporate a PIG into polyurethane rubber by first dissolving a PIG powder into a solvent, and then using a swelling method to get it into the rubber.

Much potential

In the material reported in the current work, the change in conductivity is irreversible. But Liu is confident that future versions could switch back and forth between insulating and conducting states.

She notes that the current material was developed using only one kind of PIG, polymer (the polyurethane rubber), and solvent, but there are many other kinds of all three. So there is great potential for creating even better light-responsive soft materials.

Liu also notes the potential for developing soft materials that respond to other environmental stimuli, such as heat or magnetism. “We’re inspired to do more work in this field by changing the driving force from light to other forms of environmental stimuli,” she says.

“Our work has the potential to lead to the creation of a subfield that we call soft photo-ionotronics,” Liu continues. “We are also very excited about the opportunities from our work to create new soft machines impacting soft wearable technology, human-machine interfaces, robotics, biomedicine, and other fields.”

Additional authors of the paper are Steven M. Adelmund, Shahriar Safaee, and Wenyang Pan of Reality Labs at Meta. 

Read the work in full

Soft photo-ionotronics, Xu Liu, Steven M. Adelmund, Shahriar Safaee, Wenyang Pan & Thomas J. Wallin, Nature Communications (2026).

By David Nutt

When assessing the ripeness of fruit, sight and smell can tell you a lot, but the best indicator is often how the fruit feels.

Cornell researchers used stretchable fiber-optic sensors to create a soft robot gripper that can predict the ripeness of strawberries by touch, then gently twist them off their branch or vine without causing any damage.

The technology, developed in the lab of Rob Shepherd, the John F. Carr Professor of Mechanical Engineering in the Cornell Duffield College of Engineering, could lead to more resilient and ecological food production and increase the availability of fruit species that are difficult to cultivate.

Shepherd’s Organic Robotics Lab previously demonstrated the potential of stretchable fiber-optic sensors to give soft robotic systems the ability to feel the same dynamic, tactile sensations that enable humans to navigate the natural world. In recent years, the team has expanded into agriculture, designing a soft robotic gripper that injects living plant leaves with sensors that help it detect and communicate with its environment.

“The great thing about Cornell is we’re a really great agriculture school, and a lot of avenues are opening up because of it,” Shepherd said. “It really allows us to uniquely combine our robotics expertise with our agricultural prominence.”

To develop a way to evaluate and handle fruit with care, Shepherd’s team partnered with Marvin Pritts, professor of horticulture and global development in the College of Agriculture and Life Sciences, who specializes in developing sustainable production methods for berry crops.

In order to train and test their gripper, they needed a model fruit. And for that, they turned to the strawberry.

“You can accurately tell when strawberries are ripe by their color,” Shepherd said. “So we could train our model to know if it’s ripe based on touch, then validate our model by looking at the color. And Anand was able to accurately estimate whether it was the right time to pick strawberries based off of the stiffness he measured.”

The soft robot gripper has an equally soft touch. The gripper is equipped with two different fiber-optic sensors, one to measure the curvature of the finger, and the other to measure the pressure at the fingertip. This way the robot can estimate the shape of an object and adjust its grip accordingly to grasp the ripe fruit without bruising it.

“The fiber-optic strain gauges have the same mechanical properties as the grippers that are using them. So it’s kind of like the flesh feels the fruit, rather than having separate sensors,” Shepherd said.

The researchers also included a planetary gear mechanism so, once the fruit is grasped, the robot wrist can rotate and twist the strawberry off its vine, instead of pulling or plucking it, which can strain and damage the fruit.

This soft-gripping technology, developed in the Organic Robotics Lab, could lead to more resilient and ecological food production and increase the availability of fruit species that are difficult to cultivate. Credit: Anand Mishra.

For cases in which touch isn’t enough, the researchers installed a camera in the gripper’s palm to find fruit that are occluded by leaves or other vegetation. However, the device will be particularly handy when ripeness can’t be detected visually, such as for avocadoes, pineapples or – Shepherd’s favorite – pawpaws.

“The problem with pawpaws is you can’t see when they’re ripe, and they ripen so fast that if you’re not there at the right time, you just miss them,” he said. “And you can’t harvest and ship them, because they don’t survive shipping very well, either. That’s one reason we don’t have pawpaws in grocery stores. But this can help with that.”

The technology could have an even greater impact on sustainable farming practices.

“Robots will allow us to do things we cannot do economically right now. We have row crops because row crops fit our machines. But if we have a larger amount of smaller robots, we can have mixed cropping of different species that support each other,” Shepherd said. “Instead of having soy one year and corn the next, you can have them both. Or you could have interspersed species that are resistant to pestilence, that help block infestations and reduce the amount of pesticides and fertilizer. You can have drought resistance from canopy species.

“It’s very complicated to manage a farm that way,” he said, “and robots could allow us to do that.”

The research was supported by the National Science Foundation Center for Research on Programmable Plant Systems (CROPPS) and the Cornell Institute for Digital Agriculture.

Claire chatted to Josie Hughes from École Polytechnique Fédérale de Lausanne about using AI to develop new designs for robotic manipulators.

Josie Hughes is an Assistant Professor at EPFL, where she established the CREATE Lab in 2021. She completed her PhD in the Bio-inspired Robotics Lab at the University of Cambridge, examining the role of passivity in bio-inspired manipulators. Her research focuses on developing novel design paradigms for designing robot structures that exploit their physicality and interactions with the environment. This includes the development of robotic hands, soft manipulators, and automation systems for applications focused on sustainability and science.

The recently launched Robotics Café is a weekly online seminar series to bring together researchers, students and industry practitioners working in the field of autonomous robotics. One of the key aims of the initiative is to provide a dedicated platform for students to present and disseminate their work, enabling broader visibility and impact across academia and industry.

Organised by P.B. Sujit (IISER Bhopal), Sandeep Manjanna (Plaksha University) and Aditya Paranjape (Monash University), the talks take place every Thursday from 17:00-18:00 Indian Standard Time. The link to watch the presentations live via Google Meet is here. Alternatively, you can catch the recordings on the Robotics Café YouTube channel.

The series kicked off with a talk from Professor Debasish Ghose (Indian Institute of Science) entitled: AERObotics: The Art of Catching Objects in the Air. The presentation explored the fascinating intersection of guidance theory and aerial robotics.

In the second lecture, Professor Arun Kumar Singh (University of Tartu) spoke about leveraging predictive uncertainty for model-based planning and control.

Find out more:

• Robotics Café webpage
• To receive updates you can sign up to the mailing list.

By Kartikeya Walia, Nottingham Trent University

A table tennis robot has outperformed elite players in recent evaluations. The robot, called Ace, marks a significant step toward artificial intelligence (AI) systems that can operate in fast, uncertain, real-world environments.

In the tests, the autonomous robot won three out of five matches against elite players – competitive athletes with over ten years’ experience and an average of 20 hours weekly training. The robot, developed by Sony AI, lost both matches against players in professional Japanese leagues, but did win a game against one of them. The system is described in detail in a recent paper published in Nature.

AI has spent decades mastering games. It has repeatedly outperformed the best humans in everything from complex video games like StarCraft II to chess – where modern programs now far exceed human ratings.

Landmark systems such as Deep Blue and AlphaGo have confirmed that, given clear rules and enough data, AI can achieve superhuman performance. But these victories all shared one key feature: they happened in controlled, digital environments.

At first glance, table tennis might seem like an unusual benchmark for artificial intelligence. In reality, it is one of the most demanding imaginable. The ball can travel faster than 20 metres per second, giving players less than half a second to react.

On top of that, spin introduces enormous complexity. A ball rotating at extreme speeds can curve mid-air and rebound unpredictably off the table. For humans, interpreting spin is largely intuitive. For robots, it has been a longstanding obstacle.

This robot can beat you at table tennis (Nature).

Earlier table tennis robotic systems such as Forpheus, developed by Japanese company Omron, addressed this by simplifying the game – using controlled ball launchers, limiting movement, or ignoring spin altogether. More recent iterations have aimed for interaction, but still operate under constrained conditions.

Ace does none of this. It plays with standard equipment, on a regulation table,
against human opponents who are free to use the full range of shots.

How Ace works

Ace’s performance relies on three key innovations: how it sees the world, how it
decides what to do, and how it carries out those actions. First, let’s deal with how Ace sees the world. Traditional cameras struggle with fast motion, often producing a blur or missing critical details.

Ace instead uses three “event-based” vision sensors, which detect changes in light rather than capturing full images at fixed intervals. These are complemented by nine high-speed cameras that track the environment, including the opponent and their racket.

Together, these systems enable high-speed gaze control (the technology that enables a robot to direct its sensors to focus on specific things) and allow the robot to follow the ball with exceptional real-time precision.

By tracking markings on the ball, where professional players can generate spin approaching 9,000 revolutions per minute (rpm), the system can estimate spin in real time, something that has long challenged robotic systems.

How Ace’s gaze control system works (Sony AI and Nature).

The second important innovation is how Ace decides what to do. Knowing where the ball is going is only half the problem; the robot must also respond instantly. Ace uses deep reinforcement learning, trained in simulation over millions of virtual rallies, including self-play.

It continuously generates movement commands for its multi-jointed robotic arm, recalculating trajectories every few tens of milliseconds while avoiding collisions with the table or itself.

The third innovation is how Ace carries out its actions. To match the speed of human elite players, the robot is built around a high-performance arm combining two prismatic (sliding) and six revolute (rotational) joints. This enables rapid sideways motion and precise striking. There is both a table tennis racket and a mechanism for ball handling, allowing one-armed serves.

Crucially, the system is engineered for high-speed interaction: lightweight structures and optimised actuation (the mechanisms in a robot that convert energy into mechanical force) allow Ace to return balls at speeds approaching 20 metres per second. This enables sustained, competitive rallies with skilled human players.

Ace makes a split section change when the ball hits the net (Sony AI and Nature).

What makes this particularly notable is the transition from simulation to reality. Many AI systems perform well in virtual environments but fail when exposed to real-world noise and uncertainty. Ace demonstrates that this “sim-to-real” gap can be meaningfully reduced.

One moment during a rally with an elite player illustrates the way that Ace has leapt over this gap. When a predicted ball trajectory suddenly changed after clipping the net, Ace reacted almost instantly, returning the shot and winning the point. What makes Ace particularly significant is therefore not just its performance, but its ability to operate reliably under real-world uncertainty.

Why this matters beyond sport

A robot returning high-speed topspin shots may be entertaining, but the implications go far beyond table tennis. In manufacturing, for example, robots are typically confined to highly structured tasks.

The real challenge is adaptability, handling irregular objects, responding to variation. This is particularly relevant for next-generation robots operating in unstructured environments.

To function effectively in homes, hospitals or construction sites, robots must be able to predict, adapt and respond to constantly changing conditions. The same predictive and control capabilities that allow Ace to respond to unpredictable shots could enable more flexible, responsive automation.

Most industrial robots are kept behind safety barriers because they cannot respond to unexpected human behaviour. Zhu Difeng

There are also implications for human–robot interaction. Most industrial robots are kept behind safety barriers because they cannot react quickly or reliably enough to unexpected human behaviour. Ace operates at the edge of human reaction time, suggesting a future where robots can safely collaborate with people in shared spaces.

More broadly, this work represents a shift in what AI is expected to do. The next frontier is not just intelligence in abstract problem-solving, but intelligence embedded in the physical world. The gap between simulations and reality needs filling, and this is a big step forward.

What humans still do better

Professional players were still able to exploit Ace’s limitations – particularly in reach, speed, and the ability to handle extreme or highly deceptive shots. This highlights that intelligence is not just about prediction and control, but also about physical embodiment. Humans combine perception, movement and strategy in ways that remain difficult to replicate.

Interestingly, systems like Ace may end up enhancing human performance rather
than replacing it. As one former Olympic player observed after facing the robot,
seeing it return seemingly impossible shots suggests humans might be capable of more than previously thought.

Kartikeya Walia, Senior Lecturer, Department of Engineering, Nottingham Trent University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Claire chatted to Gavin Kenneally from Ghost Robotics about robot dogs for defence, security, and public safety.

Gavin Kenneally is the Co-Founder and CEO of Ghost Robotics, a company that has gained a reputation for pushing the boundaries of legged robotics technology. In his current role, Gavin spearheads a team of highly skilled engineers and researchers who share his passion for creating advanced robotics systems. Previously, he was Head of Product at Ghost Robotics, responsible for the mechanical design of the company’s flagship product: the Vision 60 Q-UGV. Gavin has a PhD in Mechanical Engineering from the University of Pennsylvania and has authored six academic papers.

By C Huygelen

Leiden researchers Professor Daniela Kraft and Mengshi Wei have created microscopic robots that move without sensors, software, or external control. Instead, their behaviour emerges entirely from their shape and the way they interact with their environment. This class of robots opens up entirely new possibilities for biomedical applications.

Close-up of the microrobot.

Inspired by nature

Inspiration to build these robots came from nature. Kraft: “Animals like worms and snakes constantly adapt their shape as they move, which helps them to navigate their environments. Macroscopic robots similarly use flexibility for their function. However, until now, microrobots were either small and rigid, or large and flexible. We wondered if we could realize small and flexible microrobots in our lab.”

Tiny, flexible, and surprisingly capable

To find out, they designed a soft, chain-like structure made up of flexibly connected segments, and printed it using a 3D microprinter. To the researchers’ surprise, switching on an electric field made the chains move. When it starts to swim, its flexibility gives it a life-like appearance.

The team had a lot of fun testing what these robots could do. “When the robot is slowed down or even stopped, it starts to wave its tail as if it wants to break free,” Wei says. “This happens, because the elements in the back still want to move, and they can do so because of their flexibility.”

The movements these microrobots make

“But that was not all”, adds Kraft. “We discovered there’s continuous feedback between the shape and motion of the robot: the shape influences how it moves, and its movements in turn alters its shape. This microrobot therefore senses how the environment changes its body and reacts to it, making it appear life-like. This means that we don’t need microscopic electronics for integrating smart abilities.”

Wei noted that “when our microrobot encounters an obstacle, it automatically searches for another route. And when two robots meet, they naturally steer away from each other.” The robots can even move in dense environments and move objects that hinder their motion out of their way.

How the microrobots move in compex environments

Possible future research and applications

The ability of these microrobots to autonomously navigate complex environments opens exciting possibilities for biomedical applications, from targeted drug delivery to minimally invasive medical procedures and diagnostics.

Kraft: “We now need to fully understand how such dynamic and functional behavior emerge. This knowledge will help us develop more advanced microrobots and devices, but also to better understand the physics of biological microswimmers and organisms.”

Facts and figures

• Structure: A very flexible chain of self-propelling elements
• Material: Synthetic, 3D-printed in our lab on a Nanoscribe 3D-printer
• Size of the elements: 5 µm
• Size of the bar-joints: 0.5 µm*
• Movement: self propelled elements
• Speed: 7 µm/second

*To compare, a human hair is around 70-100µm thick. This is 3D-printing at the very edge of what is technically possible.

Reference

Life-like behavior emerging in active and flexible microstructures, Mengshi Wei and Daniela J. Kraft.

By Celia Luterbacher

In today’s manufacturing environments, upgrading a robot fleet often means starting from scratch – not only replacing hardware, but also reprogramming tasks. Even when two robots are built to perform similar jobs, different joint arrangements or movement limits mean that a task programmed for one robot often can’t be used on another. Enabling skills to transfer directly between robots could make these systems more sustainable and cost-efficient.

To meet this challenge, researchers in the Learning Algorithms and Systems Laboratory (LASA) in EPFL’s School of Engineering have developed a new robotic control framework called Kinematic Intelligence. The method takes a human-demonstrated task, mathematically converts it into a general movement strategy, and then adapts it so that different robots can perform it based on their physical design. The research has been published in Science Robotics.

“This work addresses a long-standing challenge in robotics: how to transfer a learned skill across robots with different mechanical structures, while guaranteeing safe and predictable behavior,” says LASA head Aude Billard. “This approach could significantly reduce the time and expertise needed to deploy robots in real-world settings.”

Kinematic Intelligence for transferable robot learning

To build their framework, the researchers first took human-demonstrated object‑manipulation tasks – such as placing, pushing and throwing – and recorded them using motion-capture technology. Then, they mathematically converted these recorded tasks into general movement strategies. They also developed a systematic classification of the physical limits of different robot designs, including how far their joints can move and which positions they must avoid to remain stable. The framework then uses this classification to automatically tailor the general movement strategies to different robot bodies, ensuring they can carry out tasks safely within their mechanical limits.

In an assembly line experiment, a human demonstrated a task by pushing a wooden block off a conveyor belt onto a workbench, placing it on a table, and finally throwing it into a basket. By using Kinematic Intelligence, three completely different commercial robots were able to reproduce this same sequence safely and reliably.

“Each robot handled different steps of the task, and the system performed successfully even when the step allocation was changed,” explains LASA PhD student and co-first author Sthithpragya Gupta. “Each robot interprets the same skill in its own way, but always within safe and feasible limits.”

Towards scalable and future-ready robotics

The researchers aim to extend the framework to settings such as human-robot collaboration and natural language-based interaction. For example, Kinematic Intelligence could allow a person to instruct a robot with simple commands at home, with no need for technical programming. The approach is also relevant for emerging robotic platforms, where rapid hardware evolution means that today’s machines may soon be replaced by newer versions. Enabling seamless transfer of skills across such platforms could play a key role in making them practical and scalable.

“Our goal is to remove the need for technical expertise while still ensuring safe and reliable operation,” summarizes LASA scientist and co-first author Durgesh Haribhau Salunkhe. “The user brings the idea and the desired behavior, and the robot should take care of the rest.”

Reference

Demonstrate once, execute on many: Kinematic intelligence for cross-robot skill transfer, S Gupta, D H Salunkhe, A Billard, Science Robotics (2026).

Claire chatted to Melissa Greeff from Queen’s University about autonomous navigation and learning for drones.

Melissa Greeff is an Assistant Professor in Electrical and Computer Engineering at Queen’s University. She leads Robora Lab and is also an Ingenuity Labs Robotics and AI Institute member. Her research interests include aerial robots, vision-based navigation, and safe learning-based control. Melissa’s expertise is in building autonomous aerial systems including previous experience in conducting field trials at various locations across Canada. She was listed as one of 50 women in robotics you need to know about in 2023 by the Women in Robotics organization.

By David Nutt

The way bugs and birds flap their wings may look effortless, but the dynamics that keep them aloft are dizzyingly complex and difficult to quantify.

Cornell researchers created a computational model that shows the effect of insects’ morphology on stabilizing their flight. The findings could lead to a new way to understand the evolution of animal flight while also providing a blueprint for designing flapping-wing robots.

The study published May 1 in Proceedings of the National Academy of Sciences. The research was led by Z. Jane Wang, professor of physics and mechanical and aerospace engineering in the College of Arts and Sciences and Cornell Duffield College of Engineering, respectively.

The effort began more than a decade ago, when Wang set out to understand how the neural circuitry in fruit flies evolved to control flight stability. By creating a 3D computational simulation, Wang’s team showed that fruit flies sense the orientation of their bodies every time they beat their wings, about one beat every 4 milliseconds, in order to stabilize themselves.

However, in order to study flight stability in all insects, the researchers would need to build an efficient computational tool to simulate a huge number of species.

“Previous studies, including ours, have always started with models of real insects, so we’re limited by the things we observe,” Wang said. “We miss all the other configurations that are also possible for flight.”

Wang and Owen Wetherbee, the new paper’s first author, distilled the 3D model into a new version that retained the key physics of the body-wing coupling and unsteady aerodynamics. The resulting equations revealed the critical physical parameters: wing to body mass ratio, wing loading, wing hinge position, wing beat frequency and wing motion amplitude. Taken together, they form what Wang calls a “five-dimensional morphological and kinematic space.”

“The power of this model is to give us something much more explicit than what we had before,” she said. “We knew the fundamental physics. By capturing the essential physics in the new model, we can understand each piece conceptually as well as facilitate computation to explore a large parameter space.”

The analyses of the computational results in 5D resulted in two explicit formula that provide a succinct metric for stability. These criteria capture the subtle and often ignored coupling between wing inertia and the body, which depends on the interplay among wing flap frequency, hinge placement, and wing and body mass ratios in order to achieve a kind of anti-resonance state. This sweet spot allows the flapping winged animal to control its body oscillations and remain aloft – a state known as passively stable flight – despite air perturbations that would normally cause it to tumble.

“All of a sudden, we found that many forms of flapping flight have passive stability, which surprised us initially, because works so far showed that most insects, except one or two, are passively unstable, hence the necessity for neural circuitry to control them,” Wang said. “But when we expanded the morphological space, we realized that what we studied before are but a few dots in this new view.”

Now that the researchers can characterize the stability boundary, they can offer a concrete design principle for realizing stable flapping flight in robots – something that has stumped roboticists for decades.

“In principle, this offers a completely new route for designing a robotic flapping-winged machine,” Wang said. “Instead of relying on extensive feedback control, which is only partially successful, our results suggest that we can tune the shape and the frequency of the flapping devices such that, according to these two rules, we may find the flyers are passively stable already. This would greatly simplify flight control.”

The new model allows this design work to be done with faster and simpler computation, and the ability to model stability traits also points to a new way for classifying winged animals and charting their evolution.

“During evolution, various traits are selected, but we don’t have much idea about what they are, let alone understand why they are being selected and how they evolve, apart from a very few examples, such as an eye,” Wang said. “This project brings new quantitative methods to study these very big questions in both biology and robotics. Mathematical modeling allows us to go beyond our own ideas and preconceptions to tackle these large questions.”

The research was supported by the National Science Foundation.

By Adam Zewe

Robotically assembled building blocks could be a more environmentally friendly method for erecting large-scale structures than some existing construction techniques, according to a new study by MIT researchers.

The team conducted a feasibility study to evaluate the efficiency of constructing a simple building using “voxels,” which are modular 3D subunits that assemble into complex, durable structures.

After studying the performance of multiple voxels, the researchers developed three new designs intended to streamline building construction. They also produced a robotic assembler and a user-friendly interface for generating voxel-based building layouts and feeding instructions to the robots.

Their results indicate this voxel-based robotic assembly system could reduce embodied carbon — all of the carbon emitted during the lifecycle of building materials — by as much as 82 percent, compared with popular techniques like 3D concrete printing, precast modular concrete, and steel framing. The system would also be competitive in terms of cost and construction time. However, the choice of materials used to manufacture the voxels does play a major role in their carbon footprint and cost.

While scalability, durability, long-term robustness, and important considerations like fire resistance remain to be explored before such a system could be widely deployed, the researchers say these initial results highlight the potential of this approach for automated, on-site construction.

“I’m particularly excited about how the robotic assembly of discrete lattices can enable a practical way to apply digital fabrication to the built environment in a way that can let us build much more efficiently and sustainably,” says Miana Smith, a graduate student in the Center for Bits and Atoms (CBA) at MIT and lead author the study.

She is joined on the paper by Paul Richard, a graduate student at École Polytechnique Fédérale de Lausanne in Switzerland and former visiting researcher at MIT; Alfonso Parra Rubio, a CBA graduate student; and senior author Neil Gershenfeld, an MIT professor and the director of the CBA. The research appears in Automation in Construction.

Designing better building blocks

Over the past several years, researchers in the Center for Bits and Atoms have been developing voxels, which are lattice-structured building blocks that can be assembled into objects with high strength and stiffness, like airplane wings, wind turbine blades, and space structures.

“Here, we are taking aerospace principles and applying them to buildings. Why don’t we make buildings as efficiently as we make airplanes?” Gershenfeld says, based on prior work his lab has done on voxel assembly with NASA, Airbus, and Boeing.

To explore the feasibility of voxel-based assembly strategies for buildings, the researchers first evaluated the mechanical performance and sustainability of eight existing voxel designs, including a cuboctahedron made from glass-reinforced nylon and a Kelvin lattice made from steel.

Based on those evaluations, they developed a set of three voxels using a new geometry that could be more easily assembled robotically into a larger structure. The new design, based on a high-strength and high-stiffness octet lattice, mechanically self-aligns into rigid structures.

“The interlocking nature of these voxels means we can get nice mechanical properties without needing to have a lot of connectors in the system, so the construction process can run a lot faster,” Smith says.

To accelerate construction, they designed a robotic assembly system based on inchworm-like robots that crawl across a voxel structure by anchoring and extending their bodies. These Modular Inchworm Lattice Assembler robots, or MILAbots, use grippers on each end to place voxel building blocks and engage the snap-fit connections.

“The robots can assemble the voxels by dropping them into place and then stepping on them to have the pieces interlock. We can do precise maneuvers based on the mechanical relationship between the robots and the voxels,” Smith explains.

The team studied the embodied carbon needed to fabricate their new voxel designs using three materials: plastic, plywood, and steel. Then they evaluated the throughput and cost of using the robotic assembly system to build a simple, one-story building. The researchers compared these estimates with the performance of other construction methods.

The MILAbot’s unique legs, seen here in close up. “The robots can assemble the voxels by dropping them into place and then stepping on them to have the pieces interlock,” Miana Smith explains. Credit: Courtesy of the researchers.

Potential environmental benefits

They found that most existing voxels, and especially those made from plastics, performed poorly compared to existing methods in terms of sustainability, but the steel and wood voxels they designed offered significant environmental benefits.

For instance, utilizing their steel voxels would generate only 36 percent of the embodied carbon required for 3D concrete printing and 52 percent of the embodied carbon of precast concrete. The plywood voxels had the lowest carbon footprint, requiring about 17 percent and 24 percent of the embodied carbon needed, respectively.

“There is still a potential viable option for a plastics-based voxel approach, we just have to be a bit more strategic about which types of plastics, infills, and geometries we use,” Smith says.

In addition, projected on-site assembly time for the steel and wood voxel approaches averaged 99 hours, whereas existing construction methods averaged 155 hours.

These speed benefits rely on the distributed nature of voxel-based assembly. While one MILAbot working alone is far slower than existing techniques, with a team of 20 robots working in parallel, the system catches up to or surpasses existing automation methods at a lower cost.

“One benefit of this method is how incremental it is. You can start building, and if it turns out you need a new room, you can just add onto the structure. It is also reversible, so if your use changes, you can dissemble the voxels and change the structure,” Gershenfeld says.

The researchers also developed an interface that enables users to input or hand-design a voxelized structure. The automatic system determines the paths the MILAbots should follow for construction and sends commands to the assemblers.

The next step in this project will be a larger testbed in Bhutan, using the “super fab lab” that CBA helped set up there to replicate the robots to test construction for a planned sustainable city, Gershenfeld says.

Left to right: Yeshey Wangmo Lepcha, Tshering Wangzom, and Miana Smith stand under an arch created with voxels, as part of a working visit from the Bhutanese team to MIT. Credit: Courtesy of the researchers.

Additional areas of future work include studying the stability of voxel structures under lateral loads, improving the design tool to account for the physics of the system, enhancing the MILAbots, and evaluating voxels that have integrated sheeting, insulation, or electrical and plumbing routing.

“Our work helps support why doing this type of distributed robot assembly might be a practical way to bring digital fabrication into building construction,” Smith says.

This work was funded, in part, by the MIT Center for Bits and Atoms Consortia.

Claire chatted to Andrew Philippides from the University of Sussex about what we can learn from ants and bees to improve robot navigation.

Andrew Philippides is a Professor of Biorobotics at the University of Sussex, where he co-directs the Centre for Computational Neuroscience and Robotics and the be.AI Leverhulme Doctoral centre for Biomimetic Embodied AI. His research combines biological experiments with robotics, modelling, and machine learning to understand how intelligent behaviour emerges from the interaction of body and brain acting in an environment. Focussing on visual navigation, he aims to understand the navigation and learning abilities of ants and bees to develop novel AI and biorobotic algorithms.

By Nitin Sanket, Worcester Polytechnic Institute

To help small aerial robots navigate in the dark and other low-visibility environments, my colleagues and I developed an ultrasound-based perception system inspired by bat echolocation.

Current robots rely heavily on cameras or light detection and ranging, known as lidar, or both. But these sensors fail in visually challenging conditions, such as smoke, fog, dust, snow or complete darkness.

I’m a scientific engineer who develops bio-inspired microrobots. To solve this challenge, my research team looked at nature’s experts at navigating in poor visibility: bats. They thrive in dark, damp and dusty caves and can detect obstacles as thin as a human hair using echolocation while weighing as little as two paper clips. They emit sound waves and listen to weak echoes reflected from objects.

However, enabling this sensing on aerial robots is extremely challenging because propellers generate a lot of noise. It is a bit like trying to listen to your friend while a jet engine is taking off next to you.

To overcome this issue, we present two key ideas. First, a physical acoustic shield inspired by bat’s ear cartilage reduces propeller noise around the acoustic sensors, which act like the robot’s ears. Second, a neural network called Saranga recovers weak echo signals from very noisy measurements by learning patterns over time, inspired by how bats process sound.

Together, these enable the robot to estimate obstacle locations in 3D and navigate safely using milliwatt-level sensing power.

Why it matters

These types of drones are very useful for search and rescue, especially in confined, dynamic and dangerous environments, because they are small and inexpensive. Search-and-rescue operations often happen in environments where visibility is very poor, such as forest fires, collapsed buildings, caves or dusty outdoor conditions. In these scenarios, traditional sensors like cameras and lidar often become unreliable.

Bats do not rely only on vision and instead use echolocation to perceive the world. Ultrasound sensing doesn’t depend on lighting conditions and works in smoke, dust and darkness.

Our work shows that it is possible to bring this capability to aerial robots despite strong onboard propeller noise. Sonar boosted by noise shielding and machine learning promises to enable a new class of small, low-cost robots that can operate in environments where current systems fail.

This research can enable highly functional, autonomous, tiny aerial robots for critical humanitarian applications, such as search and rescue, combating poaching and cave exploration. AI-enabled sonar navigation could lead to safer, faster and more cost-effective robots for time-sensitive operations where human or larger helicopter access is limited. This is a step toward being able to deploy swarms of aerial robots, much like groups of bats, to explore hazardous environments and search for survivors.

Breakthroughs in mathematical modeling, neural network design and sensor characterization will enable other low-power applications for these drones, such as environmental monitoring. Our work can reduce power by 1,000 times, weight by 10 times and cost by 100 times compared to current solutions.

What other research is being done

Most aerial navigation systems rely on cameras, depth sensors or lidar, which degrade in low visibility. Radar works in these conditions but is power-intensive for small drones. Prior work has explored ultrasound sensing mainly on ground robots, but applying it to aerial robots has been difficult due to propeller noise and weak signals.

What’s next

We are working on improving flying speed, sensing range and system size. We are also exploring new bio-inspired designs and combining ultrasound with other types of sensing.

Ultimately, our goal is to build reliable, low-power aerial robots that can operate reliably in dynamic environments and enable real-world deployment in search and rescue.

The Research Brief is a short take on interesting academic work.

Nitin Sanket, Assistant Professor of Robotics Engineering, Worcester Polytechnic Institute

This article is republished from The Conversation under a Creative Commons license. Read the original article.

By Michael Psenka, Mike Rabbat, Aditi Krishnapriyan, Yann LeCun, Amir Bar

GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we avoid brittle “state-input” gradients through high-dimensional vision models.

Large, learned world models are becoming increasingly capable. They can predict long sequences of future observations in high-dimensional visual spaces and generalize across tasks in ways that were difficult to imagine a few years ago. As these models scale, they start to look less like task-specific predictors and more like general-purpose simulators.

But having a powerful predictive model is not the same as being able to use it effectively for control/learning/planning. In practice, long-horizon planning with modern world models remains fragile: optimization becomes ill-conditioned, non-greedy structure creates bad local minima, and high-dimensional latent spaces introduce subtle failure modes.

In this blog post, I describe the problems that motivated this project and our approach to address them: why planning with modern world models can be surprisingly fragile, why long horizons are the real stress test, and what we changed to make gradient-based planning much more robust.

This blog post discusses work done with Mike Rabbat, Aditi Krishnapriyan, Yann LeCun, and Amir Bar (* denotes equal advisorship), where we propose GRASP.

What is a world model?

These days, the term “world model” is quite overloaded, and depending on the context can either mean an explicit dynamics model or some implicit, reliable internal state that a generative model relies on (e.g. when an LLM generates chess moves, whether there is some internal representation of the board). We give our loose working definition below.

Suppose you take actions and observe states (images, latent vectors, proprioception). A world model is a learned model that, given the current state and a sequence of future actions, predicts what will happen next. Formally, it defines a predictive distribution on a sequence of observed states and current action :

that approximates the environment’s true conditional . For this blog post, we’ll assume a Markovian model for simplicity (all results here can be extended to the more general case), and when the model is deterministic it reduces to a map over states:

In practice the state is often a learned latent representation (e.g., encoded from pixels), so the model operates in a (theoretically) compact, differentiable space. The key point is that a world model gives you a differentiable simulator; you can roll it forward under hypothetical action sequences and backpropagate through the predictions.

Planning: choosing actions by optimizing through the model

Given a start and a goal , the simplest planner chooses an action sequence by rolling out the model and minimizing terminal error:

Here we use as shorthand for the full rollout through the world model (dependence on model parameters is implicit):

In short horizons and low-dimensional systems, this can work reasonably well. But as horizons grow and models become larger and more expressive, its weaknesses become amplified.

So why doesn’t this just work at scale?

Why long-horizon planning is hard (even when everything is differentiable)

There are two separate pain points for the more general world model, plus a third that is specific to learned, deep learning-based models.

1) Long-horizon rollouts create deep, ill-conditioned computation graphs

Those familiar with backprop through time (BPTT) may notice that we’re differentiating through a model applied to itself repeatedly, which will lead to the exploding/vanishing gradients problem. Namely, if we take derivatives (note we’re differentiating vector-valued functions, resulting in Jacobians that we denote with ) with respect to earlier actions (e.g. ):

We see that the Jacobian’s conditioning scales exponentially with time :

leading to exploding or vanishing gradients.

2) The landscape is non-greedy and full of traps

At short horizons, the greedy solution, where we move straight toward the goal at every step, is often good enough. If you only need to plan a few steps ahead, the optimal trajectory usually doesn’t deviate much from “head toward ” at each step.

As horizons grow, two things happen. First, longer tasks are more likely to require non-greedy behavior: going around a wall, repositioning before pushing, backing up to take a better path. And as horizons grow, more of these non-greedy steps are typically needed. Second, the optimization space itself scales with horizon: , further expanding the space of local minima for the optimization problem.

A long-horizon fix: lifting the dynamics constraint

Suppose we treat the dynamics constraint as a soft constraint, and we instead optimize the following penalty function over both actions and states :

This is also sometimes called collocation in planning/robotics literature. Note the lifted formulation shares the same global minimizers as the original rollout objective (both are zero exactly when the trajectory is dynamically feasible). But the optimization landscapes are very different, and we get two immediate benefits:

• Each world model evaluation depends only on local variables, so all terms can be computed in parallel across time, resulting in a huge speed-up for longer horizons, and
• You no longer backpropagate through a single deep -step composition to get a learning signal, since the previous product of Jacobians now splits into a sum, e.g.:

Being able to optimize states directly also helps with exploration, as we can temporarily navigate through unphysical domains to find the optimal plan:

However, lunch is never free. And indeed, especially for deep learning-based world models, there is a critical issue that makes the above optimization quite difficult in practice.

An issue for deep learning-based world models: sensitivity of state-input gradients

The tl;dr of this section is: directly optimizing states through a deep learning-based is incredibly brittle, à la adversarial robustness. Even if you train your world model in a lower-dimensional state space, the training process for the world model makes unseen state landscapes very sharp, whether it be an unseen state itself or simply a normal/orthogonal direction to the data manifold.

Adversarial robustness and the “dimpled manifold” model

Adversarial robustness originally looked at classification models , and showed that by following the gradient of a particular logit from a base image (not of class ), you did not have to move far along to make classify as (Szegedy et al., 2014; Goodfellow et al., 2015):

Later work has painted a geometric picture for what’s going on: for data near a low-dimensional manifold , the training process controls behavior in tangential directions, but does not regularize behavior in orthogonal directions, thus leading to sensitive behavior (Stutz et al., 2019). Another way stated: has a reasonable Lipschitz constant when considering only tangential directions to the data manifold , but can have very high Lipschitz constants in normal directions. In fact, it often benefits the model to be sharper in these normal directions, so it can fit more complicated functions more precisely.

As a result, such adversarial examples are incredibly common even for a single given model. Further, this is not just a computer vision phenomenon; adversarial examples also appear in LLMs (Wallace et al., 2019) and in RL (Gleave et al., 2019).

While there are methods to train for more adversarially robust models, there is a known trade-off between model performance and adversarial robustness (Tsipras et al., 2019): especially in the presence of many weakly-correlated variables, the model must be sharper to achieve higher performance. Indeed, most modern training algorithms, whether in computer vision or LLMs, do not train adversarial robustness out. Thus, at least until deep learning sees a major regime change, this is a problem we’re stuck with.

Why is adversarial robustness an issue for world model planning?

Consider a single component of the dynamics loss we’re optimizing in the lifted state approach:

Let’s further focus on just the base state:

Since world models are typically trained on state/action trajectories , the state-data manifold for has dimensionality bounded by the action space:

where is some optional space of augmentations (e.g. translations/rotations). Thus, we can typically expect to be much lower than , and thus: it is very easy to find adversarial examples that hack any state to any other desired state.

As a result, the dynamics optimization

feels incredibly “sticky,” as the base points can easily trick into thinking it’s already made its local goal.¹

Our fix

This is where our new planner GRASP comes in. The main observation: while is untrustworthy and adversarial, the action space is usually low-dimensional and exhaustively trained, so is actually reasonable to optimize through and doesn’t suffer from the adversarial robustness issue!

At its core, GRASP builds a first-order lifted state / collocation-based planner that is only dependent on action Jacobians through the world model. We thus exploit the differentiability of learned world models , while not falling victim to the inherent sensitivity of the state Jacobians .

GRASP: Gradient RelAxed Stochastic Planner

As noted before, we start with the collocation planning objective, where we lift the states and relax dynamics into a penalty:

We then make two key additions.

Ingredient 1: Exploration by noising the state iterates

Even with a smoother objective, planning is nonconvex. We introduce exploration by injecting Gaussian noise into the virtual state updates during optimization.

A simple version:

Actions are still updated by non-stochastic descent:

The state noise helps you “hop” between basins in the lifted space, while the actions remain guided by gradients. We found that specifically noising states here (as opposed to actions) finds a good balance of exploration and the ability to find sharper minima.²

Ingredient 2: Reshape gradients: stop brittle state-input gradients, keep action gradients

As discussed, the fragile pathway is the gradient that flows into the state input of the world model, . The most straightforward way to do this initially is to just stop state gradients into directly:

• Let be the same value as , but with gradients stopped.

Define the stop-gradient dynamics loss:

This alone does not work. Notice now states only follow the previous state’s step, without anything forcing the base states to chase the next ones. As a result, there are trivial minima for just stopping at the origin, then only for the final action trying to get to the goal in one step.

Dense goal shaping

We can view the above issue as the goal’s signal being cut off entirely from previous states. One way to fix this is to simply add a dense goal term throughout prediction:

In normal settings this would over-bias towards the greedy solution of straight chasing the goal, but this is balanced in our setting by the stop-gradient dynamics loss’s bias towards feasible dynamics. The final objective is then as follows:

The result is a planning optimization objective that does not have dependence on state gradients.

Periodic “sync”: briefly return to true rollout gradients

The lifted stop-gradient objective is great for fast, guided exploration, but it’s still an approximation of the original serial rollout objective.

So every iterations, GRASP does a short refinement phase:

1. Roll out from using current actions , and take a few small gradient steps on the original serial loss:

The lifted-state optimization still provides the core of the optimization, while this refinement step adds some assistance to keep states and actions grounded towards real trajectories. This refinement step can of course be replaced with a serial planner of your choice (e.g. CEM); the core idea is to still get some of the benefit of the full-path synchronization of serial planners, while still mostly using the benefits of the lifted-state planning.

How GRASP addresses long-range planning

Collocation-based planners offer a natural fix for long-horizon planning, but this optimization is quite difficult through modern world models due to adversarial robustness issues. GRASP proposes a simple solution for a smoother collocation-based planner, alongside stable stochasticity for exploration. As a result, longer-horizon planning ends up not only succeeding more, but also finding such successes faster:

Push-T results. Success rate (%) / median time to success. Bold = best in row. Note the median success time will bias higher with higher success rate; GRASP manages to be faster despite higher success rate.

What’s next?

There is still plenty of work to be done for modern world model planners. We want to exploit the gradient structure of learned world models, and collocation (lifted-state optimization) is a natural approach for long-horizon planning, but it’s crucial to understand typical gradient structure here: smooth and informative action gradients and brittle state gradients. We view GRASP as an initial iteration for such planners.

Extension to diffusion-based world models (deeper latent timesteps can be viewed as smoothed versions of the world model itself), more sophisticated optimizers and noising strategies, and integrating GRASP into either a closed-loop system or RL policy learning for adaptive long-horizon planning are all natural and interesting next steps.

I do genuinely think it’s an exciting time to be working on world model planners. It’s a funny sweet spot where the background literature (planning and control overall) is incredibly mature and well-developed, but the current setting (pure planning optimization over modern, large-scale world models) is still heavily underexplored. But, once we figure out all the right ideas, world model planners will likely become as commonplace as RL.

For more details, read the full paper or visit the project website.

Citation

@article{psenka2026grasp,
  title={Parallel Stochastic Gradient-Based Planning for World Models},
  author={Michael Psenka and Michael Rabbat and Aditi Krishnapriyan and Yann LeCun and Amir Bar},
  year={2026},
  eprint={2602.00475},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2602.00475}
}

This article was initially published on the BAIR blog, and appears here with the authors’ permission.

Claire chatted to Chenying Liu from University of Oxford about how a robot’s physical form can actively contribute to sensing, processing, decision-making, and movement.

Chenying Liu is a Junior Research Fellow and an Associate Member of Faculty in the Department of Engineering Science at the University of Oxford. She leads an independent research programme focused on embodied physical intelligence, exploring how robot design can integrate geometry, materials, and control to enhance autonomy and robustness. Her work aims to develop more efficient and resilient robotic systems by embedding intelligence directly into their physical structures.