<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>MIT &#8211; Robohub</title>
	<atom:link href="https://robohub.org/tag/mit/feed/" rel="self" type="application/rss+xml" />
	<link>https://robohub.org</link>
	<description>Connecting the robotics community to the world</description>
	<lastBuildDate>Mon, 19 Oct 2026 23:05:34 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.4</generator>
	<item>
		<title>The Force was strong in this robot competition</title>
		<link>https://robohub.org/the-force-was-strong-in-this-robot-competition/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Thu, 18 May 2017 09:30:00 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[events]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/the-force-was-strong-in-this-robot-competition/</guid>

					<description><![CDATA[MechE class ends semester with ingeniously designed robots battling on a &#8220;Star Wars&#8221;-themed playing field.]]></description>
										<content:encoded><![CDATA[<div id="attachment_78577" style="width: 649px" class="wp-caption aligncenter"><img fetchpriority="high" decoding="async" aria-describedby="caption-attachment-78577" class="size-full wp-image-78577" src="http://robohub.org/wp-content/uploads/2017/05/MIT-Force-event.jpg" alt="" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/05/MIT-Force-event.jpg 639w, https://robohub.org/wp-content/uploads/2017/05/MIT-Force-event-425x283.jpg 425w" sizes="(max-width: 639px) 100vw, 639px" /><p id="caption-attachment-78577" class="wp-caption-text">An Imperial Snowtrooper inspects a competitor’s entry at the 2017 MIT Mechanical Engineering 2.007 Student Design Final Robot Competition. Photo: Tony Pulsone</p></div>
<p>Thursday night, dozens of robots designed and built by undergraduates in a mechanical engineering class endured hours of intense, boisterous, and often jubilant competition as they scrambled to rack up points in one-on-one clashes on special “Star Wars”-themed playing arenas.<span id="more-78485"></span></p>
<p>As has often happened in these contests — which have been going on, and constantly evolving, <a href="http://news.mit.edu/2015/mechanical-engineering-rite-of-passage-1215" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">since 1970</a> — the ultimate winner in the single-elimination tournament was not the one that’d most consistently racked up the highest scores all evening. Rather, it was a high-scoring bot that triumphed when its competitor missed a crucial scoring opportunity because its starting position was just slightly out of alignment.</p>
<p>The class, 2.007 (Design and Manufacturing I), which has 165 mostly sophomore students, begins by giving each student an identical kit of parts, from which they each have to create a robot to carry out a variety of tasks to score points. This year, in a nod to the 40th anniversary of the first “Star Wars” film, released in 1977, the robots crawled around and over a replica of a “Star Wars” X-wing Starfighter. Students could earn points by pulling up a sliding frame to rescue prisoners trapped in carbonite; by dumping Imperial stormtroopers into a trash trench; by activating a cantina band; or by spinning up one or both of two large cylindrical thrusters on the wings. Students could choose which tasks to have their robot try to accomplish, and had just one semester to design, test, and operate their bot.</p>
<p>The devices could be pre-programmed to carry out set tasks, but could also be manually controlled through a radio-linked controller. As in past years, the open-ended nature of the assignment — and the variety of different ways to score — led to a wide range of strategies and designs, spanning from tall towers that would extend by telescoping out or with hinged sections, to elevator-like lifting devices, to small and nimble bots that scurried around to carry out multiple tasks, to an array of arms and devices for grasping or turning the different pieces. They sported names like Dodocopter, Bonnie and Clyde, Pitfall, Torque Toilet, Spinit to Winit, and Nicki Spinaj.</p>
<p>Students could earn extra points by accomplishing any of the tasks during an initial period when the robot had to perform autonomously, before the start of a manually remote-controlled round. The students were allowed to create multiple robots to carry out different tasks, as long as they were all made from the basic kit of parts, and all fit within a designated starting area. Most of the students opted to build two devices, and some even made three.</p>
<p>Second-place finisher Richard Moyer, with his small but powerful and robust robot called Tornado, consistently scored 960.5 points in every round (the highest score achieved by any of the bots), by spinning both the lower and upper thrusters to their maximum speeds — and by using the lower thruster during the high-scoring autonomous period. But on the final matchup, Tornado was just slightly out of place in the starting box, and missed the thruster, losing out on that big initial score.</p>
<p>The robot used a simple but reliable design, which sported a single horizontally-mounted drive wheel that it used to spin both the lower and upper thrusters, and also to activate an elevator mechanism that carried it from one wing to the other. It was “like the Swiss army knife of robots,” thanks to this multifunction device, said Sangbae Kim, an associate professor of mechanical engineering and co-instructor of the course, who was dressed as the “Star Wars” wookie, Chewbacca.</p>
<p>The grand-prize winner, Tom Frejowski, also built a compact, powerful robot that concentrated on the spinning task, and scored 640 in the final round to take home the top trophy (a replica of the MIT dome). Frejowski’s robot, in order to ensure that it made a straight shot from the starting position to the thruster to line up just right to spin the heavy cylinder, used a single motor to drive both of its front wheels, which helped him earn consistent high scores. “That’s how he goes dead straight every time,” said co-instructor Amos Winter, an assistant professor of mechanical engineering, who was dressed as Darth Vader and shared the emcee duties with Kim.</p>
<p>During the tournament, which took place in the Johnson Ice Rink, all of the course teachers and assistants were dressed in various “Star Wars” costumes, and a packed audience of fellow students, families, and visitors of all ages cheered their encouragement with great enthusiasm. During a break, each of the teaching assistants was presented with a special memento: a beaver-cut twig from a beaver dam in Nova Scotia, symbolizing MIT’s beaver mascot, and nature’s original mechanical engineer.</p>
<p>Echoing the sentiments of many students in the class, sophomore James Li said of the class in a pre-taped video: “I had a bit of building experience, but I never had to design and build anything of this complexity. … It was a great experience.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Teaching robots to teach other robots</title>
		<link>https://robohub.org/teaching-robots-to-teach-other-robots/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Wed, 10 May 2017 15:02:43 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[actuation]]></category>
		<category><![CDATA[AI-cognition]]></category>
		<category><![CDATA[announcements]]></category>
		<category><![CDATA[control]]></category>
		<category><![CDATA[manipulation]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[prototype]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[software]]></category>
		<guid isPermaLink="false">http://robohub.org/teaching-robots-to-teach-other-robots/</guid>

					<description><![CDATA[Most robots are programmed using one of two methods: learning from demonstration, in which they watch a task being done and then replicate it, or via motion-planning techniques like optimization or sampling, which require a programmer to explicitly specify a task’s goals and constraints. Both methods have drawbacks. Robots that learn from demonstration can’t easily [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_77790" style="width: 1810px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-77790" class="size-full wp-image-77790" src="http://robohub.org/wp-content/uploads/2017/05/2DArpino-Perez-discusses-her-work-teaching-Optimus-to-pick-up-a-bottle-Jason-Dorfman-MIT-CSAIL.jpg" alt="" width="1800" height="1200" srcset="https://robohub.org/wp-content/uploads/2017/05/2DArpino-Perez-discusses-her-work-teaching-Optimus-to-pick-up-a-bottle-Jason-Dorfman-MIT-CSAIL.jpg 1800w, https://robohub.org/wp-content/uploads/2017/05/2DArpino-Perez-discusses-her-work-teaching-Optimus-to-pick-up-a-bottle-Jason-Dorfman-MIT-CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/05/2DArpino-Perez-discusses-her-work-teaching-Optimus-to-pick-up-a-bottle-Jason-Dorfman-MIT-CSAIL-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2017/05/2DArpino-Perez-discusses-her-work-teaching-Optimus-to-pick-up-a-bottle-Jason-Dorfman-MIT-CSAIL-1024x683.jpg 1024w" sizes="(max-width: 1800px) 100vw, 1800px" /><p id="caption-attachment-77790" class="wp-caption-text">D&#8217;Arpino Perez discusses her work teaching Optimus to pick up a bottle. Image: Jason Dorfman, MIT CSAIL</p></div>
<p>Most robots are programmed using one of two methods: learning from demonstration, in which they watch a task being done and then replicate it, or via motion-planning techniques like optimization or sampling, which require a programmer to explicitly specify a task’s goals and constraints.</p>
<p>Both methods have drawbacks. Robots that learn from demonstration can’t easily transfer one skill they’ve learned to another situation and remain accurate. On the other hand, motion planning systems that use sampling or optimization can adapt to these changes, but are time-consuming, since they usually have to be hand-coded by expert programmers.</p>
<p>Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have recently developed a system that aims to bridge the two techniques: C-LEARN, which allows non-coders to teach robots a wider range of tasks simply by providing some information about how objects are typically manipulated and then showing the robot a single demo of the task. Importantly, this enables users to teach robots skills that can be automatically transferred to other robots with different “kinematics” (ways of moving) &#8211; a key time- and cost-saving measure for companies that want a range of robots to perform similar actions.</p>
<div class="keep-aspect"><iframe title="Teaching Robots to Teach Robots" width="500" height="281" src="https://www.youtube-nocookie.com/embed/QQplTBx6rV0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>“By combining the intuitiveness of learning from demonstration with the precision of motion-planning algorithms, this approach can help robots do new types of tasks that they haven’t been able to learn before, like multi-step assembly using both of their arms,” says Claudia Pérez-D’Arpino, a PhD student who wrote a paper on C-LEARN with MIT professor Julie Shah.</p>
<p>The team tested the system on Optimus, a new two-armed robot designed for bomb disposal that they programmed to perform tasks like opening doors, transporting objects and extracting objects from containers.</p>
<p>(The robot is made of components from multiple manufacturers, including a manipulation system by RE2, a Husky unmanned ground vehicle by Clearpath, 3-finger grippers by Robotiq and the multisense sensor from Carnegie Robotics that is used in the Atlas robot.)</p>
<p>In simulations they showed that Optimus’ learned skills could be seamlessly transferred to Atlas, <a href="http://news.mit.edu/2015/robotics-competition-algorithms-0611." target="_blank" rel="noopener noreferrer follow external" data-wpel-link="external">CSAIL’s six-foot-tall, 400-pound humanoid robot</a>.</p>
<p>The paper was recently accepted to the IEEE International Conference on Robotics and Automation (ICRA), which takes place May 29-June 3 in Singapore.</p>
<hr class="xh2  ">
<h3>How it works</h3>
<p>With C-LEARN the user first gives the robot a knowledge base of information on how to reach and grasp different objects that have different constraints. (The C in C-LEARN stands for “constraints.”) The operator then uses a 3D interface to show the robot a single demonstration of the specific task, which is represented by a sequence of relevant moments known as “keyframes.” By matching these keyframes with the knowledge base, the robot can automatically suggest motion plans for the operator to approve or edit as needed.</p>
<img decoding="async" class="alignnone size-full" src="https://j.gifs.com/0gk7RN.gif" width="480" height="270" />
<p>“This approach is actually very similar to how humans learn in terms of seeing how something’s done and connecting it to what we already know about the world,” says Pérez-D’Arpino. “We can’t magically learn from a single demonstration, so we take new information and match it to previous knowledge about our environment.”</p>
<p>One challenge was that existing constraints that could be learned from demonstrations weren’t accurate enough to enable robots to precisely manipulate objects. To overcome that, the researchers developed constraints inspired by computer-aided design (CAD) programs that can tell the robot if its hands should be parallel or perpendicular to the objects it is interacting with.</p>
<img decoding="async" class="alignnone size-full" src="https://j.gifs.com/AnGlDj.gif" width="640" height="360" />
<p>The team also showed that the robot performed significantly better in collaboration with humans. While the robot successfully executed tasks 87.5 percent of the time on its own, it did so 100 percent of the time when it had a operator that could correct minor sensory inaccuracies.</p>
<p>“Having a knowledge base is fairly common, but what’s not common is integrating it with learning from demonstration,” says Dmitry Berenson, an assistant professor of computer science at the University of Michigan who was not involved in the research. “That’s very helpful, because if you are dealing with the same objects over and over again, you don&#8217;t want to then have to start from scratch to teach the robot every new task.”</p>
<img decoding="async" class="alignnone size-full" src="https://j.gifs.com/RgqJ6w.gif" width="640" height="360" />
<p>The system is part of a larger wave of research focused on making LfD approaches more adaptive. If you’re a robot that has learned to take an object out of a tube from a demonstration, you might not be able to do it if there’s an obstacle in the way that requires you to move your arm differently. However, C-LEARN can do this, because it does not learn one specific way to perform the action.</p>
<p>“It’s good for the field that we&#8217;re moving away from directly imitating motion, towards actually trying to infer the principles behind the motion,” says Berenson. “By using these learned constraints in a motion planner, we can make systems that are far more flexible than those which just try to mimic what&#8217;s being demonstrated&#8221;</p>
<p>Shah says that advanced LfD methods could prove important in time-sensitive scenarios like bomb disposal and disaster response, where robots are currently tele-operated at the level of individual joint movements.</p>
<p>“Something as simple as picking up a box could take 20-30 minutes, which is significant for an emergency situation,” says Pérez-D’Arpino.</p>
<p>C-LEARN can’t yet handle certain advanced tasks, like avoiding collisions or planning for different step sequences for a given task. But the team is hopeful that incorporating more insights from human learning will give robots an even wider range of physical capabilities.</p>
<p>“Traditional programming of robots in real-world scenarios is difficult, tedious and requires a lot of domain knowledge,” says Shah. “It would be much more effective if we could train them more like how we train people: by giving them some basic knowledge and a single demonstration. This is an exciting step towards teaching robots to perform complex multi-arm and multi-step tasks necessary for assembly manufacturing and ship or aircraft maintenance.”</p>
<hr class="xh2  ">
<p><a href="https://drive.google.com/open?id=0B9HHfYresOgRUlpHeGlQY1U4SVE" target="_blank" rel="noopener noreferrer follow external" data-wpel-link="external">Click here</a> to access the full paper.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>CSAIL launches artificial intelligence initiative with industry</title>
		<link>https://robohub.org/csail-launches-artificial-intelligence-initiative-with-industry/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Wed, 12 Apr 2017 11:00:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[autonomous]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robots]]></category>
		<guid isPermaLink="false">http://robohub.org/csail-launches-artificial-intelligence-initiative-with-industry/</guid>

					<description><![CDATA[SystemsThatLearn@CSAIL aims to develop new &#8220;human-like systems&#8221; for data science and other fields.]]></description>
										<content:encoded><![CDATA[<div id="attachment_76039" style="width: 649px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/04/CSAIL-AI-systems-that-learn.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-76039" class="size-full wp-image-76039" src="http://robohub.org/wp-content/uploads/2017/04/CSAIL-AI-systems-that-learn.jpg" alt="" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/04/CSAIL-AI-systems-that-learn.jpg 639w, https://robohub.org/wp-content/uploads/2017/04/CSAIL-AI-systems-that-learn-425x283.jpg 425w" sizes="(max-width: 639px) 100vw, 639px" /></a><p id="caption-attachment-76039" class="wp-caption-text">MIT Professor Daniela Rus, director of CSAIL, said the goal of a new SystemsThatLearn@CSAIL initiative is &#8220;to create a new generation of AI tools that are deeply rooted in systems.&#8221; Photo: Jason Dorfman/MIT CSAIL</p></div>
<p>From self-driving cars to the internet of things, artificial intelligence (AI) has reached new levels of sophistication in recent years. With that in mind, this week MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) launched an industry collaboration focused on using machine learning to create functional human-like systems.<span id="more-75717"></span></p>
<p>Nearly 40 senior researchers will participate in the new “SystemsThatLearn@CSAIL” (STL) initiative alongside a range of organizations that include founding members BT, Microsoft, Nokia Bell Labs, Salesforce, and Schlumberger. Member companies will work with CSAIL scientists to suggest new lines of research and develop real-world applications.</p>
<p>“Developing capabilities in AI and machine learning are key to the future of fields like finance, energy, manufacturing, and health care,” says STL Executive Director Lori Glover. “While the demand for expertise is great, the supply of talent remains small and unevenly distributed. By democratizing the field of AI, SystemsThatLearn@CSAIL is an effort to address that skills gap.”</p>
<p>STL builds on CSAIL’s <a href="http://bigdata.csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Big Data Initiative</a>, which developed tools for handling complex datasets. While many machine-learning solutions are trained and deployed in separate phases, STL aims to integrate these processes, focusing on a range of resources to handle distributed data and computing power.</p>
<p>Another goal is to make key aspects of data science less laborious. A <a href="http://visit.crowdflower.com/rs/416-ZBE-142/images/CrowdFlower_DataScienceReport_2016.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">2016 report</a> found that data scientists spend 80 percent of their time collecting and organizing data, and only 20 percent analyzing it.</p>
<p>“By promoting industry interaction with academia, we’re hoping to create new tools and systems that can increase productivity by automating much of the tedious work of data science,” says MIT Professor Samuel Madden, one of STL’s two faculty leads alongside Professor Tommi Jaakkola. “We are already seeing that areas like autonomous vehicles and personalized health care have the potential to transform entire industries.”</p>
<p>In her opening remarks, CSAIL Director Daniela Rus described AI and systems researchers as two communities that would benefit from stronger collaboration.</p>
<p>“Our grand vision is to create a new generation of AI tools that are deeply rooted in systems and that can make those systems better,” Rus said. “My aspiration is to get to a place where machine learning becomes a normal part of what an operating system does.”</p>
<p>One STL project is the data discovery tool “<a href="http://news.mit.edu/2017/system-finds-links-related-data-digital-files-querying-filtering-0119" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Data Civilizer</a>,” which allows organizations to discover related datasets from thousands of distinct business databases and files. Another is “Model DB,” a machine-learning management system that saves time for data scientists and lets them easily correlate performance on particular training examples with specific model features.</p>
<p>According to STL Technical Director Stephen Buckley, many of the software tools they develop will be released under MIT’s open source license.</p>
<p>“The ultimate aim is to democratize access and use of machine learning tools, without requiring advanced knowledge of the underlying technologies,” says Buckley.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Toward printable, sensor-laden “skin” for robots</title>
		<link>https://robohub.org/toward-printable-sensor-laden-skin-for-robots/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Mon, 27 Mar 2017 10:37:00 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robots]]></category>
		<guid isPermaLink="false">http://robohub.org/toward-printable-sensor-laden-skin-for-robots/</guid>

					<description><![CDATA[New 3-D-printed device mimics the goldbug beetle, which changes color when prodded.]]></description>
										<content:encoded><![CDATA[<div id="attachment_74705" style="width: 648px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-03.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-74705" class="size-full wp-image-74705" src="http://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-03.jpg" alt="" width="638" height="426" srcset="https://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-03.jpg 638w, https://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-03-425x284.jpg 425w" sizes="(max-width: 638px) 100vw, 638px" /></a><p id="caption-attachment-74705" class="wp-caption-text">Researchers have designed and built a device that responds to mechanical stresses by changing the color of a spot on its surface. Image: Subramanian Sundaram</p></div>
<p>In this age of smartphones and tablet computers, touch-sensitive surfaces are everywhere. They’re also brittle, as people with cracked phone screens everywhere can attest.</p>
<p>Covering a robot — or an airplane or a bridge — with sensors will require a technology that is both flexible and cost-effective to manufacture in bulk. A team of researchers at MIT’s Computer Science and Artificial Intelligence Laboratory thinks that 3-D printing could be the answer.</p>
<p>In an attempt to demonstrate the feasibility of flexible, printable electronics that combine sensors and processing circuitry and can act on their environments, the researchers have designed and built a device that responds to mechanical stresses by changing the color of a spot on its surface.</p>
<div id="attachment_74706" style="width: 649px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-02.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-74706" class="wp-image-74706 size-full" src="http://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-02.jpg" alt="" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-02.jpg 639w, https://robohub.org/wp-content/uploads/2017/03/MIT-Printable-Gold-Bug-02-425x283.jpg 425w" sizes="(max-width: 639px) 100vw, 639px" /></a><p id="caption-attachment-74706" class="wp-caption-text">The components that make up the printable device. Image: Subramanian Sundaram</p></div>
<p>The device was inspired by the golden tortoise beetle, or “goldbug,” an insect whose exterior usually appears golden but turns reddish orange if the insect is poked or prodded — that is, mechanically stressed.</p>
<p>“In nature, networks of sensors and interconnects are called sensorimotor pathways,” says <a href="http://web.mit.edu/subras/www/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Subramanian Sundaram</a>, an MIT graduate student in electrical engineering and computer science (EECS), who led the project. “We were trying to see whether we could replicate sensorimotor pathways inside a 3-D-printed object. So we considered the simplest organism we could find.”</p>
<p>The researchers present their new design in the latest issue of the journal <em>Advanced Materials Technologies</em>. Sundaram is the first author <a href="http://web.mit.edu/subras/www/ADMT_17.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">on the paper,</a> and the senior authors are Sundaram’s advisor, <a href="http://people.csail.mit.edu/wojciech/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Wojciech Matusik</a>, an associate professor of EECS; and Marc Baldo, a professor of EECS and director of the Research Laboratory of Electronics. Joining them on the paper are Pitchaya Sitthi-Amorn, a former postdoc in Matusik’s lab; Ziwen Jiang, an undergraduate EECS student; and David Kim, a technical assistant in Matusik’s <a href="http://cfg.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Computational Fabrication Group</a>.</p>
<p><strong>Bottom up</strong></p>
<p>Printable electronics, in which flexible circuitry is deposited on some type of plastic substrate, has been a major area of research for decades. But Sundaram says that the ability to print the substrate itself greatly increases the range of devices the technique can yield.</p>
<p>For one thing, the choice of substrate limits the types of materials that can be deposited on top of it. Because a printed substrate could consist of many materials, interlocked in intricate but regular patterns, it broadens the range of functional materials that printable electronics can use.</p>
<p>Printed substrates also open the possibility of devices that, although printed as flat sheets, can fold themselves up into more complex, three-dimensional shapes. Printable robots that spontaneously self-assemble when heated, for instance, are a  topic of <a href="http://news.mit.edu/2014/bake-your-own-robot-0530" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">ongoing research</a> at the CSAIL Distributed Robotics Laboratory, led by Daniela Rus, the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT.</p>
<p>“We believe that only if you’re able to print the underlying substrate can you begin to think about printing a more complex shape,” Sundaram says.</p>
<p><strong>Selective signaling</strong></p>
<p>The MIT researchers’ new device is approximately T-shaped, but with a wide, squat base and an elongated crossbar. The crossbar is made from an elastic plastic, with a strip of silver running its length; in the researchers’ experiments, electrodes were connected to the crossbar’s ends. The base of the T is made from a more rigid plastic. It includes two printed transistors and what the researchers call a “pixel,” a circle of semiconducting polymer whose color changes when the crossbars stretch, modifying the electrical resistance of the silver strip.</p>
<p>In fact, the transistors and the pixel are made from the same material; the transistors also change color slightly when the crossbars stretch. The effect is more dramatic in the pixel, however, because the transistors amplify the electrical signal from the crossbar. Demonstrating working transistors was essential, Sundaram says, because large, dense sensor arrays require some capacity for onboard signal processing.</p>
<p>“You wouldn’t want to connect all the sensors to your main computer, because then you would have tons of data coming in,” he says. “You want to be able to make clever connections and to select just the relevant signals.”</p>
<p>To build the device, the researchers used the <a href="http://news.mit.edu/2015/multifab-3-d-print-10-materials-0824" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">MultiFab</a>, a custom 3-D printer developed by Matusik’s group. The MultiFab already included two different “print heads,” one for emitting hot materials and one for cool, and an array of ultraviolet light-emitting diodes. Using ultraviolet radiation to “cure” fluids deposited by the print heads produces the device’s substrate.</p>
<p>Sundaram added a copper-and-ceramic heater, which was necessary to deposit the semiconducting plastic: The plastic is suspended in a fluid that’s sprayed onto the device surface, and the heater evaporates the fluid, leaving behind a layer of plastic only 200 nanometers thick.</p>
<p><strong>Fluid boundaries</strong></p>
<p>A transistor consists of semiconductor channel on top of which sits a “gate,” a metal wire that, when charged, generates an electric field that switches the semiconductor between its electrically conductive and nonconductive states. In a standard transistor, there’s an insulator between the gate and the semiconductor, to prevent the gate current from leaking into the semiconductor channel.</p>
<p>The transistors in the MIT researchers’ device instead separate the gate and the semiconductor with a layer of water containing a potassium salt. Charging the gate drives potassium ions into the semiconductor, changing its conductivity.</p>
<p>The layer of saltwater lowers the device’s operational voltage, so that it can be powered with an ordinary 1.5-volt battery. But it does render the device less durable. “I think we can probably get it to work stably for two months, maybe,” Sundaram says. “One option is to replace that liquid with something between a solid and a liquid, like a <a href="http://news.mit.edu/2017/living-sensors-your-fingertips-0215" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">hydrogel</a>, perhaps. But that’s something we would work on later. This is an initial demonstration.”</p>
<p>“I am very impressed with both the concept and the realization of the system,” says Hagen Klauk, who leads the Organic Electronic Research Group at the Max Planck Institute for Solid State Research, in Stuttgart, Germany. “The approach of printing an entire optoelectronic system — including the substrate and all the components — by depositing all the materials, including solids and liquids, by 3-D printing is certainly novel, interesting, and useful, and the demonstration of the functional system confirms that the approach is also doable. By fabricating the substrate on the fly, the approach is particularly useful for improvised manufacturing environments where dedicated substrate materials may not be available.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Engineers design “tree-on-a-chip”</title>
		<link>https://robohub.org/engineers-design-tree-on-a-chip/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Wed, 22 Mar 2017 10:00:37 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robots]]></category>
		<guid isPermaLink="false">http://robohub.org/engineers-design-tree-on-a-chip/</guid>

					<description><![CDATA[Microfluidic device generates passive hydraulic power, may be used to make small robots move.]]></description>
										<content:encoded><![CDATA[<div id="attachment_74332" style="width: 649px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/03/MIT-Tree-on-Chip_0.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-74332" class="size-full wp-image-74332" src="http://robohub.org/wp-content/uploads/2017/03/MIT-Tree-on-Chip_0.jpg" alt="" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/03/MIT-Tree-on-Chip_0.jpg 639w, https://robohub.org/wp-content/uploads/2017/03/MIT-Tree-on-Chip_0-425x283.jpg 425w" sizes="(max-width: 639px) 100vw, 639px" /></a><p id="caption-attachment-74332" class="wp-caption-text">Engineers have designed a microfluidic device they call a “tree-on-a-chip,” which mimics the pumping mechanism of trees and other plants.</p></div>
<p>Trees and other plants, from towering redwoods to diminutive daisies, are nature’s hydraulic pumps. They are constantly pulling water up from their roots to the topmost leaves, and pumping sugars produced by their leaves back down to the roots. This constant stream of nutrients is shuttled through a system of tissues called xylem and phloem, which are packed together in woody, parallel conduits.</p>
<p>Now engineers at MIT and their collaborators have designed a microfluidic device they call a “tree-on-a-chip,” which mimics the pumping mechanism of trees and plants. Like its natural counterparts, the chip operates passively, requiring no moving parts or external pumps. It is able to pump water and sugars through the chip at a steady flow rate for several days. The results are published this week in <em>Nature Plants</em>.</p>
<p>Anette “Peko&#8221; Hosoi, professor and associate department head for operations in MIT’s Department of Mechanical Engineering, says the chip’s passive pumping may be leveraged as a simple hydraulic actuator for small robots. Engineers have found it difficult and expensive to make tiny, movable parts and pumps to power complex movements in small robots. The team’s new pumping mechanism may enable robots whose motions are propelled by inexpensive, sugar-powered pumps.</p>
<p>“The goal of this work is cheap complexity, like one sees in nature,” Hosoi says. “It’s easy to add another leaf or xylem channel in a tree. In small robotics, everything is hard, from manufacturing, to integration, to actuation. If we could make the building blocks that enable cheap complexity, that would be super exciting. I think these [microfluidic pumps] are a step in that direction.”</p>
<p>Hosoi’s co-authors on the paper are lead author Jean Comtet, a former graduate student in MIT’s Department of Mechanical Engineering; Kaare Jensen of the Technical University of Denmark; and Robert Turgeon and Abraham Stroock, both of Cornell University.</p>
<p><strong>A hydraulic lift</strong></p>
<p>The group’s tree-inspired work grew out of a project on hydraulic robots powered by pumping fluids. Hosoi was interested in designing hydraulic robots at the small scale, that could perform actions similar to much bigger robots like Boston Dynamic’s Big Dog, a four-legged, Saint Bernard-sized robot that runs and jumps over rough terrain, powered by hydraulic actuators.</p>
<p>“For small systems, it’s often expensive to manufacture tiny moving pieces,” Hosoi says. “So we thought, ‘What if we could make a small-scale hydraulic system that could generate large pressures, with no moving parts?’ And then we asked, ‘Does anything do this in nature?’ It turns out that trees do.”</p>
<p>The general understanding among biologists has been that water, propelled by surface tension, travels up a tree’s channels of xylem, then diffuses through a semipermeable membrane and down into channels of phloem that contain sugar and other nutrients.</p>
<p>The more sugar there is in the phloem, the more water flows from xylem to phloem to balance out the sugar-to-water gradient, in a passive process known as osmosis. The resulting water flow flushes nutrients down to the roots. Trees and plants are thought to maintain this pumping process as more water is drawn up from their roots.</p>
<p>“This simple model of xylem and phloem has been well-known for decades,” Hosoi says. “From a qualitative point of view, this makes sense. But when you actually run the numbers, you realize this simple model does not allow for steady flow.”</p>
<p>In fact, engineers have previously attempted to design tree-inspired microfluidic pumps, fabricating parts that mimic xylem and phloem. But they found that these designs quickly stopped pumping within minutes.</p>
<p>It was Hosoi’s student Comtet who identified a third essential part to a tree’s pumping system: its leaves, which produce sugars through photosynthesis. Comtet’s model includes this additional source of sugars that diffuse from the leaves into a plant’s phloem, increasing the sugar-to-water gradient, which in turn maintains a constant osmotic pressure, circulating water and nutrients continuously throughout a tree.</p>
<p><strong>Running on sugar</strong></p>
<p>With Comtet’s hypothesis in mind, Hosoi and her team designed their tree-on-a-chip, a microfluidic pump that mimics a tree’s xylem, phloem, and most importantly, its sugar-producing leaves.</p>
<p>To make the chip, the researchers sandwiched together two plastic slides, through which they drilled small channels to represent xylem and phloem. They filled the xylem channel with water, and the phloem channel with water and sugar, then separated the two slides with a semipermeable material to mimic the membrane between xylem and phloem. They placed another membrane over the slide containing the phloem channel, and set a sugar cube on top to represent the additional source of sugar diffusing from a tree’s leaves into the phloem. They hooked the chip up to a tube, which fed water from a tank into the chip.</p>
<p>With this simple setup, the chip was able to passively pump water from the tank through the chip and out into a beaker, at a constant flow rate for several days, as opposed to previous designs that only pumped for several minutes.</p>
<p>“As soon as we put this sugar source in, we had it running for days at a steady state,” Hosoi says. “That’s exactly what we need. We want a device we can actually put in a robot.”</p>
<p>Hosoi envisions that the tree-on-a-chip pump may be built into a small robot to produce hydraulically powered motions, without requiring active pumps or parts.</p>
<p>“If you design your robot in a smart way, you could absolutely stick a sugar cube on it and let it go,” Hosoi says.</p>
<p>This research was supported, in part, by the Defense Advance Research Projects Agency.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Security for multirobot systems</title>
		<link>https://robohub.org/security-for-multirobot-systems/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Fri, 17 Mar 2017 12:30:57 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[security]]></category>
		<category><![CDATA[software]]></category>
		<guid isPermaLink="false">http://robohub.org/security-for-multirobot-systems/</guid>

					<description><![CDATA[New technique could protect robot teams&#8217; communication networks from malicious hackers.]]></description>
										<content:encoded><![CDATA[<div id="attachment_74020" style="width: 649px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-74020" class="size-full wp-image-74020" src="http://robohub.org/wp-content/uploads/2017/03/MIT-Robo-Spoof-1_0.jpg" alt="" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/03/MIT-Robo-Spoof-1_0.jpg 639w, https://robohub.org/wp-content/uploads/2017/03/MIT-Robo-Spoof-1_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/03/MIT-Robo-Spoof-1_0-450x300.jpg 450w" sizes="(max-width: 639px) 100vw, 639px" /><p id="caption-attachment-74020" class="wp-caption-text">Researchers including MIT professor Daniela Rus (left) and research scientist Stephanie Gil (right) have developed a technique for preventing malicious hackers from commandeering robot teams’ communication networks. To verify the theoretical predictions, the researchers implemented their system using a battery of distributed Wi-Fi transmitters and an autonomous helicopter. Image: M. Scott Brauer.</p></div>
<p>Distributed <a href="http://news.mit.edu/2011/distributed-computing-0608" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">planning</a>, <a href="http://news.mit.edu/2016/human-robot-rescue-teams-0217" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">communication</a>, and <a href="http://news.mit.edu/2016/algorithm-robot-teams-moving-obstacles-0421" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">control</a> algorithms for autonomous robots make up a <a href="http://news.mit.edu/2015/algorithm-helps-robots-handle-uncertainty-0602" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">major</a> <a href="http://news.mit.edu/2014/collaborative-learning-for-robots-0625" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">area</a> of <a href="http://news.mit.edu/2011/robot-algorithm-0503" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">research</a> in computer science. But in the literature on multirobot systems, security has gotten relatively short shrift.</p>
<p>In the latest issue of the journal <em>Autonomous Robots</em>, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory and their colleagues present a new technique for preventing malicious hackers from commandeering robot teams’ communication networks. The technique could provide an added layer of security in systems that encrypt communications, or an alternative in circumstances in which encryption is impractical.</p>
<p>“The robotics community has focused on making multirobot systems autonomous and increasingly more capable by developing the science of autonomy. In some sense we have not done enough about systems-level issues like cybersecurity and privacy,” says Daniela Rus, an Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT and senior author on the new paper.</p>
<p>“But when we deploy multirobot systems in real applications, we expose them to all the issues that current computer systems are exposed to,” she adds. “If you take over a computer system, you can make it release private data — and you can do a lot of other bad things. A cybersecurity attack on a robot has all the perils of attacks on computer systems, plus the robot could be controlled to take potentially damaging action in the physical world. So in some sense there is even more urgency that we think about this problem.”</p>
<hr class="xh2  ">
<p><strong>Identity theft</strong></p>
<p>Most planning algorithms in multirobot systems rely on some kind of voting procedure to determine a course of action. Each robot makes a recommendation based on its own limited, local observations, and the recommendations are aggregated to yield a final decision.</p>
<p>A natural way for a hacker to infiltrate a multirobot system would be to impersonate a large number of robots on the network and cast enough spurious votes to tip the collective decision, a technique called “spoofing.” The researchers’ new system analyzes the distinctive ways in which robots’ wireless transmissions interact with the environment, to assign each of them its own radio “fingerprint.” If the system identifies multiple votes as coming from the same transmitter, it can discount them as probably fraudulent.</p>
<p>“There are two ways to think of it,” says Stephanie Gil, a research scientist in Rus’ Distributed Robotics Lab and a co-author on the new paper. “In some cases cryptography is too difficult to implement in a decentralized form. Perhaps you just don’t have that central key authority that you can secure, and you have agents continually entering or exiting the network, so that a key-passing scheme becomes much more challenging to implement. In that case, we can still provide protection.</p>
<p>“And in case you can implement a cryptographic scheme, then if one of the agents with the key gets compromised, we can still provide  protection by mitigating and even quantifying the maximum amount of damage that can be done by the adversary.”</p>
<hr class="xh2  ">
<p><strong>Hold your ground</strong></p>
<p>In their paper, the researchers consider a problem known as “coverage,” in which robots position themselves to distribute some service across a geographic area — communication links, monitoring, or the like. In this case, each robot’s “vote” is simply its report of its position, which the other robots use to determine their own.</p>
<p>The paper includes a theoretical analysis that compares the results of a common coverage algorithm under normal circumstances and the results produced when the new system is actively thwarting a spoofing attack. Even when 75 percent of the robots in the system have been infiltrated by such an attack, the robots’ positions are within 3 centimeters of what they should be. To verify the theoretical predictions, the researchers also implemented their system using a battery of distributed Wi-Fi transmitters and an autonomous helicopter.</p>
<p>“This generalizes naturally to other types of algorithms beyond coverage,” Rus says.</p>
<p>The new system grew out of an earlier project involving Rus, Gil, Dina Katabi — who is the other Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science at MIT — and Swarun Kumar, who earned master’s and doctoral degrees at MIT before moving to Carnegie Mellon University. That project sought to use Wi-Fi signals to determine transmitters’ locations and to <a href="https://groups.csail.mit.edu/drl/wiki/images/8/88/Ijrr_2014_final.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">repair</a> <a href="http://news.mit.edu/2011/exp-ad-hoc-0310" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">ad hoc</a> communication networks. On the new paper, the same quartet of researchers is joined by MIT Lincoln Laboratory’s Mark Mazumder.</p>
<p>Typically, radio-based location determination requires an array of receiving antennas. A radio signal traveling through the air reaches each of the antennas at a slightly different time, a difference that shows up in the phase of the received signals, or the alignment of the crests and troughs of their electromagnetic waves. From this phase information, it’s possible to determine the direction from which the signal arrived.</p>
<hr class="xh2  ">
<p><strong>Space vs. time</strong></p>
<p>A bank of antennas, however, is too bulky for an autonomous helicopter to ferry around. The MIT researchers found a way to make accurate location measurements using only <a href="http://groups.csail.mit.edu/drl/wiki/images/6/6a/sgil_mobicom2014.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">two antennas</a>, spaced about 8 inches apart. Those antennas must move through space in order to simulate measurements from multiple antennas. That’s a requirement that autonomous robots meet easily. In the experiments reported in the new paper, for instance, the autonomous helicopter hovered in place and rotated around its axis in order to make its measurements.</p>
<p>When a Wi-Fi transmitter broadcasts a signal, some of it travels in a direct path toward the receiver, but much of it bounces off of obstacles in the environment, arriving at the receiver from different directions. For location determination, that’s a problem, but for radio fingerprinting, it’s an advantage: The different energies of signals arriving from different directions give each transmitter a distinctive profile.</p>
<p>There’s still some room for error in the receiver’s measurements, however, so the researchers’ new system doesn’t completely ignore probably fraudulent transmissions. Instead, it discounts them in proportion to its certainty that they have the same source. The new paper’s theoretical analysis shows that, for a range of reasonable assumptions about measurement ambiguities, the system will thwart spoofing attacks without unduly punishing valid transmissions that happen to have similar fingerprints.</p>
<p>“The work has important implications, as many systems of this type are on the horizon — networked autonomous driving cars, Amazon delivery drones, et cetera,” says David Hsu, a professor of computer science at the National University of Singapore. “Security would be a major issue for such systems, even more so than today’s networked computers. This solution is creative and departs completely from traditional defense mechanisms.”</p>
<hr class="xh2  ">
<p><em>If you enjoyed this article from CSAIL, you might also be interested in:</em></p>
<ul>
<li><a href="http://robohub.org/mind-control-correcting-robot-mistakes-using-eeg-brain-signals/" target="_blank" data-wpel-link="internal">Mind control: Correcting robot mistakes using EEG brain signals</a></li>
<li><a href="http://robohub.org/mit-csails-6-foot-tall-nasa-humanoid-robot-has-landed/" target="_blank" data-wpel-link="internal">MIT CSAIL’s 6-foot-tall NASA humanoid robot has landed</a></li>
<li><a href="http://robohub.org/researchers-add-a-splash-of-human-intuition-to-planning-algorithms/" target="_blank" data-wpel-link="internal">Researchers add a splash of human intuition to planning algorithms</a></li>
<li><a href="http://robohub.org/wearable-ai-that-can-detect-the-tone-of-a-conversation/" target="_blank" data-wpel-link="internal">Wearable AI that can detect the tone of a conversation</a></li>
<li><a href="http://robohub.org/ingestible-robots-glasses-free-3-d-and-computers-that-explain-themselves/" target="_blank" data-wpel-link="internal">Ingestible robots, glasses-free 3-D, and computers that explain themselves</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" target="_blank" data-wpel-link="internal">the latest robotics news</a> on Robohub, or <a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Mind control: Correcting robot mistakes using EEG brain signals</title>
		<link>https://robohub.org/mind-control-correcting-robot-mistakes-using-eeg-brain-signals/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Mon, 06 Mar 2017 15:05:28 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[AI-cognition]]></category>
		<category><![CDATA[announcements]]></category>
		<category><![CDATA[control]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[human-robot interaction]]></category>
		<category><![CDATA[manipulation]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[prototype]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/mind-control-correcting-robot-mistakes-using-eeg-brain-signals/</guid>

					<description><![CDATA[For robots to do what we want, they need to understand us. Too often, this means having to meet them halfway: teaching them the intricacies of human language, for example, or giving them explicit commands for very specific tasks. But what if we could develop robots that were a more natural extension of us and [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_72669" style="width: 910px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-72669" class="size-full wp-image-72669" src="http://robohub.org/wp-content/uploads/2017/03/1The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL.jpg" alt="" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2017/03/1The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL.jpg 900w, https://robohub.org/wp-content/uploads/2017/03/1The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/03/1The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2017/03/1The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /><p id="caption-attachment-72669" class="wp-caption-text">The feedback system enables human operators to correct the robot&#8217;s choice in real-time &#8211; Jason Dorfman, MIT CSAIL</p></div>
<p>For robots to do what we want, they need to understand us. Too often, this means having to meet them halfway: teaching them the intricacies of human language, for example, or giving them explicit commands for very specific tasks. But what if we could develop robots that were a more natural extension of us and that could actually do whatever we are thinking?<span id="more-72667"></span></p>
<p>A team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University is working on this problem, creating a feedback system that lets people correct robot mistakes instantly with nothing more than their brains.</p>
<div class="keep-aspect"><iframe title="Brain-controlled Robots" width="500" height="281" src="https://www.youtube-nocookie.com/embed/Zd9WhJPa2Ok?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Using data from an electroencephalography (EEG) monitor that records brain activity, the system can detect if a person notices an error as a robot performs an object-sorting task. The team’s novel machine-learning algorithms enable the system to classify brain waves in the space of 10 to 30 milliseconds.</p>
<p>While the system currently handles relatively simple binary-choice activities, the paper’s senior author says that the work suggests that we could one day control robots in much more intuitive ways.</p>
<p>“Imagine being able to instantaneously tell a robot to do a certain action, without needing to type a command, push a button or even say a word,” says CSAIL director Daniela Rus. “A streamlined approach like that would improve our abilities to supervise factory robots, driverless cars and other technologies we haven’t even invented yet.”</p>
<img decoding="async" class="alignnone size-full" src="https://j.gifs.com/Y6RGZ2.gif" width="640" height="360" />
<p>In the current study the team used a humanoid robot named “Baxter” from Rethink Robotics, the company led by former CSAIL director and iRobot co-founder Rodney Brooks.</p>
<p>The paper presenting the work was written by BU PhD candidate Andres F. Salazar-Gomez, CSAIL PhD candidate Joseph DelPreto, and CSAIL research scientist Stephanie Gil under the supervision of Rus and BU professor Frank H. Guenther.  The paper was recently accepted to the IEEE International Conference on Robotics and Automation (ICRA) taking place in Singapore this May.</p>
<p>Past work in EEG-controlled robotics has required training humans to “think” in a prescribed way that computers can recognize. For example, an operator might have to look at one of two bright light displays, each of which corresponds to a different task for the robot to execute.</p>
<img decoding="async" class="alignnone size-full" src="https://j.gifs.com/g5PgKk.gif" width="640" height="360" />
<p>The downside to this method is that the training process and the act of modulating one’s thoughts can be taxing, particularly for people who supervise tasks in navigation or construction that require intense concentration.</p>
<p>Rus’ team wanted to make the experience more natural. To do that, they focused on brain signals called “error-related potentials” (ErrPs), which are generated whenever our brains notice a mistake. As the robot indicates which choice it plans to make, the system uses ErrPs to determine if the human agrees with the decision.</p>
<div id="attachment_72671" style="width: 910px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-72671" class="size-full wp-image-72671" src="http://robohub.org/wp-content/uploads/2017/03/2The-team-uses-EEG-brain-signals-to-detect-if-the-person-notices-a-mistake-Jason-Dorfman-MIT-CSAIL.jpg" alt="" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2017/03/2The-team-uses-EEG-brain-signals-to-detect-if-the-person-notices-a-mistake-Jason-Dorfman-MIT-CSAIL.jpg 900w, https://robohub.org/wp-content/uploads/2017/03/2The-team-uses-EEG-brain-signals-to-detect-if-the-person-notices-a-mistake-Jason-Dorfman-MIT-CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/03/2The-team-uses-EEG-brain-signals-to-detect-if-the-person-notices-a-mistake-Jason-Dorfman-MIT-CSAIL-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2017/03/2The-team-uses-EEG-brain-signals-to-detect-if-the-person-notices-a-mistake-Jason-Dorfman-MIT-CSAIL-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /><p id="caption-attachment-72671" class="wp-caption-text">The team uses EEG brain signals to detect if the person notices a mistake &#8211; Jason Dorfman, MIT CSAIL</p></div>
<p>“As you watch the robot, all you have to do is mentally agree or disagree with what it is doing,” says Rus. “You don’t have to train yourself to think in a certain way &#8211;  the machine adapts to you, and not the other way around.”</p>
<p>ErrP signals are extremely faint, which means that the system has to be fine-tuned enough to both classify the signal and incorporate it into the feedback loop for the human operator.</p>
<p>In addition to monitoring the initial ErrPs, the team also sought to detect “secondary errors” that occur when the system doesn’t notice the human’s original correction.</p>
<p>“If the robot’s not sure about its decision, it can trigger a human response to get a more accurate answer,” says Gil. “These signals can dramatically improve accuracy, creating a continuous dialogue between human and robot in communicating their choices.”</p>
<div id="attachment_72673" style="width: 910px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-72673" class="size-full wp-image-72673" src="http://robohub.org/wp-content/uploads/2017/03/3The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL2.jpg" alt="" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2017/03/3The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL2.jpg 900w, https://robohub.org/wp-content/uploads/2017/03/3The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL2-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/03/3The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL2-768x512.jpg 768w, https://robohub.org/wp-content/uploads/2017/03/3The-feedback-system-enables-human-operators-to-correct-the-robots-choice-in-real-time-Jason-Dorfman-MIT-CSAIL2-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /><p id="caption-attachment-72673" class="wp-caption-text">The feedback system enables human operators to correct the robot&#8217;s choice in real-time &#8211; Jason Dorfman, MIT CSAIL2</p></div>
<p>While the system cannot yet recognize secondary errors in real time, Gil expects the model to be able to improve to upwards of 90 percent accuracy once it can.</p>
<p>In addition, since ErrP signals have been shown to be proportional to how egregious the robot’s mistake is, the team believes that future systems could extend to more complex multiple-choice tasks.</p>
<p>Salazar-Gomez notes that the system could even be useful for people who can’t communicate verbally: a task like spelling could be accomplished via a series of several discrete binary choices, which he likens to an advanced form of the blinking that allowed stroke victim Jean-Dominique Bauby to write his memoir “The Diving Bell and the Butterfly.”</p>
<p>“This work brings us closer to developing effective tools for brain-controlled robots and prostheses,” says Wolfram Burgard, a professor of computer science at the University of Freiburg who was not involved in the research. “Given how difficult it can be to translate human language into a meaningful signal for robots, work in this area could have a truly profound impact on the future of human-robot collaboration.&#8221;</p>
<p>Read the <a href="http://groups.csail.mit.edu/drl/wiki/images/e/ec/Correcting_Robot_Mistakes_in_Real_Time_Using_EEG_Signals.pdf" target="_blank" rel="noopener follow external noreferrer" data-wpel-link="external">paper here.</a></p>
<p>The project was funded in part by Boeing and the National Science Foundation.</p>
<hr class="xh2  ">
<p><em>If you enjoyed this article from CSAIL, you might also be interested in:</em></p>
<ul>
<li><a href="http://robohub.org/mit-csails-6-foot-tall-nasa-humanoid-robot-has-landed/" target="_blank" data-wpel-link="internal" rel="noopener">MIT CSAIL’s 6-foot-tall NASA humanoid robot has landed</a></li>
<li><a href="http://robohub.org/researchers-add-a-splash-of-human-intuition-to-planning-algorithms/" target="_blank" rel="noopener" data-wpel-link="internal">Researchers add a splash of human intuition to planning algorithms</a></li>
<li><a href="http://robohub.org/wearable-ai-that-can-detect-the-tone-of-a-conversation/" target="_blank" rel="noopener" data-wpel-link="internal">Wearable AI that can detect the tone of a conversation</a></li>
<li><a href="http://robohub.org/ingestible-robots-glasses-free-3-d-and-computers-that-explain-themselves/" target="_blank" rel="noopener" data-wpel-link="internal">Ingestible robots, glasses-free 3-D, and computers that explain themselves</a></li>
<li><a href="http://robohub.org/design-your-own-custom-drone/" target="_blank" rel="noopener" data-wpel-link="internal">Design, simulate and build a custom drone</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" target="_blank" data-wpel-link="internal" rel="noopener">the latest robotics news</a> on Robohub, or <a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Data Civilizer system links data scattered across files for easy querying</title>
		<link>https://robohub.org/data-civilizer-system-links-data-scattered-across-files-for-easy-querying/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Tue, 24 Jan 2017 11:13:00 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[Big Data]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/data-civilizer-system-links-data-scattered-across-files-for-easy-querying/</guid>

					<description><![CDATA[System finds and links related data scattered across digital files, for easy querying and filtering.]]></description>
										<content:encoded><![CDATA[<div id="attachment_69906" style="width: 649px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/01/MIT-DataCivilizer_0.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-69906" class="size-full wp-image-69906" src="http://robohub.org/wp-content/uploads/2017/01/MIT-DataCivilizer_0.jpg" alt="A new system called Data Civilizer automatically finds connections among many different data tables and allows users to perform database-style queries across all of them. The results of the queries can then be saved as new, orderly data sets that may draw information from dozens or even thousands of different tables." width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/01/MIT-DataCivilizer_0.jpg 639w, https://robohub.org/wp-content/uploads/2017/01/MIT-DataCivilizer_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2017/01/MIT-DataCivilizer_0-450x300.jpg 450w" sizes="(max-width: 639px) 100vw, 639px" /></a><p id="caption-attachment-69906" class="wp-caption-text">A new system called Data Civilizer automatically finds connections among many different data tables and allows users to perform database-style queries across all of them. The results of the queries can then be saved as new, orderly data sets that may draw information from dozens or even thousands of different tables.</p></div>
<p>The age of big data has seen a <a href="http://news.mit.edu/2015/algorithm-shrinks-big-data-0520" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">host</a> of <a href="http://news.mit.edu/2016/automating-big-data-analysis-1021" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">new</a> <a href="http://news.mit.edu/2016/making-big-data-manageable-1214" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">techniques</a> for <a href="http://news.mit.edu/2016/finding-patterns-corrupted-data-1026" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">analyzing</a> large data sets. But before any of those techniques can be applied, the target data has to be aggregated, organized, and cleaned up.</p>
<p>That turns out to be a shockingly time-consuming task. In a 2016 survey, 80 data scientists told the company CrowdFlower that, on average, they spent 80 percent of their time collecting and organizing data and only 20 percent analyzing it.<span id="more-69787"></span></p>
<p>An international team of computer scientists hopes to change that, with a new system called Data Civilizer, which automatically finds connections among many different data tables and allows users to perform database-style queries across all of them. The results of the queries can then be saved as new, orderly data sets that may draw information from dozens or even thousands of different tables.</p>
<p>“Modern organizations have many thousands of data sets spread across files, spreadsheets, databases, data lakes, and other software systems,” says Sam Madden, an MIT professor of electrical engineering and computer science and faculty director of MIT’s <a href="http://news.mit.edu/2012/big-data-csail-intel-center-0531" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">bigdata@CSAIL</a> initiative. “Civilizer helps analysts in these organizations quickly find data sets that contain information that is relevant to them and, more importantly, combine related data sets together to create new, unified data sets that consolidate data of interest for some analysis.”</p>
<p>The researchers presented their system last week at the Conference on Innovative Data Systems Research. The lead authors <a href="http://cidrdb.org/cidr2017/papers/p44-deng-cidr17.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">on the paper </a>are Dong Deng and Raul Castro Fernandez, both postdocs at MIT’s Computer Science and Artificial Intelligence Laboratory; Madden is one of the senior authors. They’re joined by six other researchers from Technical University of Berlin, Nanyang Technological University, the University of Waterloo, and the Qatar Computing Research Institute. Although he’s not a co-author, MIT adjunct professor of electrical engineering and computer science Michael Stonebraker, who in 2014 won the Turing Award — the highest honor in computer science — contributed to the work as well.</p>
<p><strong>Pairs and permutations </strong></p>
<p>Data Civilizer assumes that the data it’s consolidating is arranged in tables. As Madden explains, in the database community, there’s a sizable literature on automatically converting data to tabular form, so that wasn’t the focus of the new research. Similarly, while the prototype of the system can extract tabular data from several different types of files, getting it to work with every conceivable spreadsheet or database program was not the researchers’ immediate priority. “That part is engineering,” Madden says.</p>
<p>The system begins by analyzing every column of every table at its disposal. First, it produces a statistical summary of the data in each column. For numerical data, that might include a distribution of the frequency with which different values occur; the range of values; and the “cardinality” of the values, or the number of different values the column contains. For textual data, a summary would include a list of the most frequently occurring words in the column and the number of different words. Data Civilizer also keeps a master index of every word occurring in every table and the tables that contain it.</p>
<p>Then the system compares all of the column summaries against each other, identifying pairs of columns that appear to have commonalities — similar data ranges, similar sets of words, and the like. It assigns every pair of columns a similarity score and, on that basis, produces a map, rather like a network diagram, that traces out the connections between individual columns and between the tables that contain them.</p>
<p><strong>Tracing a path</strong></p>
<p>A user can then compose a query and, on the fly, Data Civilizer will traverse the map to find related data. Suppose, for instance, a pharmaceutical company has hundreds of tables that refer to a drug by its brand name, hundreds that refer to its chemical compound, and a handful that use an in-house ID number. Now suppose that the ID number and the brand name never show up in the same table, but there’s at least one table linking the ID number and the chemical compound, and one linking the chemical compound and the brand name. With Data Civilizer, a query on the brand name will also pull up data from tables that use just the ID number.</p>
<p>Some of the linkages identified by Data Civilizer may turn out to be spurious. But the user can discard data that don’t fit a query while keeping the rest. Once the data have been pruned, the user can save the results as their own data file.</p>
<p>“Data Civilizer is an interesting technology that potentially will help data scientists address an important problem that arises due to the increasing availability of data — identifying which data sets to include in an analysis,” says Iain Wallace, a senior informatics analyst at the drug company Merck. “The larger an organization, the more acute this problem becomes.”</p>
<p>“We are currently exploring how to use Civilizer as a harmonization layer on top of a variety of chemical-biology datasets,” Wallace continues. “These datasets typically link compounds, diseases, and targets together. One use case is to identify which table contains information about a specific compound and what additional information is available about that compound in other related datasets. Civilizer helps us by allowing full text search over all the columns and then identifying related columns automatically. By using Civilizer, we should be easily able to add additional data sources and update our analysis very quickly.”</p>
<p>Read the <a href="http://cidrdb.org/cidr2017/papers/p44-deng-cidr17.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">paper here.</a></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Combining automation and mobility to create a smarter world</title>
		<link>https://robohub.org/combining-automation-and-mobility-to-create-a-smarter-world/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Fri, 20 Jan 2017 14:12:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[Automation]]></category>
		<category><![CDATA[automotive]]></category>
		<category><![CDATA[Daniela Rus]]></category>
		<category><![CDATA[LIDAR]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[robohub focus on autonomous driving]]></category>
		<guid isPermaLink="false">http://robohub.org/combining-automation-and-mobility-to-create-a-smarter-world/</guid>

					<description><![CDATA[MIT Professor Daniela Rus combines automation and mobility to create a smarter world.]]></description>
										<content:encoded><![CDATA[<div id="attachment_69830" style="width: 649px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2017/01/daniela-rus-smart-mit-singapore-00_0.jpeg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-69830" class="size-full wp-image-69830" src="http://robohub.org/wp-content/uploads/2017/01/daniela-rus-smart-mit-singapore-00_0.jpeg" alt="Professor Daniela Rus stands with autonomous SMART vehicles on the MIT campus. Photo: SMART" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2017/01/daniela-rus-smart-mit-singapore-00_0.jpeg 639w, https://robohub.org/wp-content/uploads/2017/01/daniela-rus-smart-mit-singapore-00_0-425x283.jpeg 425w, https://robohub.org/wp-content/uploads/2017/01/daniela-rus-smart-mit-singapore-00_0-450x300.jpeg 450w" sizes="(max-width: 639px) 100vw, 639px" /></a><p id="caption-attachment-69830" class="wp-caption-text">Professor Daniela Rus stands with autonomous SMART vehicles on the MIT campus. Photo: SMART</p></div>
<p>By: Catherine Marguerite | Singapore-MIT Alliance for Research and Technology</p>
<p><a href="http://danielarus.csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Daniela Rus</a> loves Singapore. As the MIT professor sits down in her Frank Gehry-designed office in Cambridge, Massachusetts, to talk about her research conducted in Singapore, her face starts to relax in a big smile.</p>
<div class="sprfocus7"><a class="sprfocusl" href="/tag/robohub-focus-on-autonomous-driving/" data-wpel-link="internal"> </a></div>
<p>Her story with Singapore started in the summer of 2010, when she made her first visit to one of the most futuristic and forward-looking cities in the world. “It was love at first sight,” says the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and <a href="http://www.csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Computer Science and the director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).</a> That summer, she came to Singapore to join the Singapore-MIT Alliance for Research and Technology (SMART) as the first principal investigator in residence for the Future of Urban Mobility Research Program.</p>
<p>“In 2010, nobody was talking about autonomous driving. We were pioneers in developing and deploying the first mobility on demand for people with self-driving golf buggies,” says Rus. “And look where we stand today! Every single car maker is investing millions of dollars to advance autonomous driving. Singapore did not hesitate to provide us, at an early stage, with all the financial, logistical, and transportation resources to facilitate our work.”</p>
<p>Since her first visit, Rus has returned each year to follow up on the research, and has been involved in leading revolutionary projects for the future of urban mobility. “Our team worked tremendously hard on self-driving technologies, and we are now presenting a wide range of different devices that allow autonomous and secure mobility,” she says. “Our objective today is to make taking a driverless car for a spin as easy as programming a smartphone. A simple interaction between the human and machine will provide a transportation butler.”</p>
<p>The first mobility devices her team worked on were self-driving golf buggies. Two years ago, these buggies advanced to a point where the group decided to open them to the public in a trial that lasted one week at the Chinese Gardens, an idea facilitated by Singapore’s Land and Transportation Agency (LTA). Over the course of a week, more than 500 people booked rides from the comfort of their homes and came to the Chinese Gardens at the designated time and spot to experience mobility-on-demand with robots.</p>
<div class="keep-aspect"><iframe title="Driverless Buggies at the Singapore Chinese Gardens" width="500" height="281" src="https://www.youtube-nocookie.com/embed/aSm027Rzj9E?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The test was conducted around winding paths trafficked by pedestrians, bicyclists, and the occasional monitor lizard. The experiments also tested an online booking system that enabled visitors to schedule pickups and drop-offs around the garden, automatically routing and redeploying the vehicles to accommodate all the requests. The public’s response was joyful and positive, and this brought the team renewed enthusiasm to take the technology to the next level.</p>
<p>Since the Chinese Gardens public trial, the autonomous car group has introduced a few other self-driving vehicles: a self-driving city car, and two personal mobility robots, a self-driving scooter and a self-driving wheelchair. Each of these vehicles was created in three phases: In the first phase, the vehicle was converted to drive-by-wire control, which allows a computer to control acceleration, braking, and steering of the car. In the second phase, the vehicle drives on each of the pathways in its operation environment and makes a map using features detected by the sensors. In the third phase, the vehicle uses the map to compute a path from the customer’s pick-up point to the customer’s drop-off point and proceeds to drive along the path, localizing continuously and avoiding any other cars, people, and unexpected obstacles. The devices also used traffic data from LTA to model traffic patterns and to study the benefits of ride-sharing systems.</p>
<p>Last April, the team conducted a new test with the public at MIT. This time, they deployed a self-driving scooter that allowed users to use the same autonomy system indoors as well as outdoors. The trial included autonomous rides in MIT’s Infinite Corridor. A significant challenge in this type of space is localization, or accurately knowing the location of the robot in a long and plain corridor that does not have many distinctive features. The system proved to work very well in this type of environment, and the trial completed the demonstration of a comprehensive uniform autonomous mobility system.</p>
<div class="keep-aspect"><iframe title="SMART Self Driving Mobility Scooter" width="500" height="281" src="https://www.youtube-nocookie.com/embed/_6otshNzqqo?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>“One can easily see the usefulness of such a system between self-driving city cars, golf buggies, and scooters,” Rus says. “A mobility-impaired user could, for example, use a self-driving scooter to get down the hall and through the lobby of an apartment building, take a self-driving golf buggy across the building&#8217;s parking lot, and pick up an autonomous car on the public roads to go to a similarly equipped amusement park or shopping centre.”</p>
<p>Daniela Rus, a Class of 2002 MacArthur Fellow and member of the USA National Academy of Engineering, knows that each successful step into urban mobility will bring a positive contribution of artificial intelligence to the public. According to the World Health Organization, 3,400 people die each day in the world from traffic-related accidents.</p>
<p>“It is a new space race,” she says, convinced that autonomy is part of the solution to safe transportation. Daniela Rus will continue visiting her beloved Singapore, where she particularly enjoys the food, the beautiful flowers, the kindness of its people, and the smartness of its youth. “Singapore is definitely a model in many fields,” she concludes.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Design, simulate and build a custom drone</title>
		<link>https://robohub.org/design-your-own-custom-drone/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Mon, 05 Dec 2016 15:00:52 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[announcements]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[prototype]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[UAVs & drones]]></category>
		<guid isPermaLink="false">http://robohub.org/design-your-own-custom-drone/</guid>

					<description><![CDATA[This fall’s new FAA regulations have made drone flight easier than ever for both companies and consumers. But what if the drones out on the market aren’t exactly what you want? A new system from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) is the first to allow users to design, simulate and build their [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_68565" style="width: 910px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/11/PhD-student-Tao-Du-watching-the-bunnycopter-take-off-credit-Jason-Dorfman-MIT-CSAIL.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-68565" class="size-full wp-image-68565" src="http://robohub.org/wp-content/uploads/2016/11/PhD-student-Tao-Du-watching-the-bunnycopter-take-off-credit-Jason-Dorfman-MIT-CSAIL.jpg" alt="PhD student Tao Du watching the bunnycopter take off . Image credit: Jason Dorfman, MIT CSAIL" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2016/11/PhD-student-Tao-Du-watching-the-bunnycopter-take-off-credit-Jason-Dorfman-MIT-CSAIL.jpg 900w, https://robohub.org/wp-content/uploads/2016/11/PhD-student-Tao-Du-watching-the-bunnycopter-take-off-credit-Jason-Dorfman-MIT-CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/11/PhD-student-Tao-Du-watching-the-bunnycopter-take-off-credit-Jason-Dorfman-MIT-CSAIL-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /></a><p id="caption-attachment-68565" class="wp-caption-text">PhD student Tao Du watching the bunnycopter take off . Image credit: Jason Dorfman, MIT CSAIL</p></div>
<p>This fall’s <a href="https://www.faa.gov/uas/" target="_blank" data-saferedirecturl="https://www.google.com/url?hl=en&amp;q=https://www.faa.gov/uas/&amp;source=gmail&amp;ust=1480608553852000&amp;usg=AFQjCNF6ZsS_L-9OZwD42ckj8-N_StAFJQ" data-wpel-link="external" rel="follow external noopener noreferrer">new FAA regulations</a> have made drone flight easier than ever for both companies and consumers. But what if the drones out on the market aren’t exactly what you want?</p>
<p>A new system from MIT’s Computer Science and Artificial Intelligence Laboratory (<a href="https://www.csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">CSAIL</a>) is the first to allow users to design, simulate and build their own custom drone. Users can change the size, shape and structure of their drone based on the specific needs they have for payload, cost, flight time, battery usage and other factors.<span id="more-68562"></span><br />
To demonstrate, researchers created a range of unusual-looking drones, including a five-rotor “pentacopter” and a rabbit-shaped “bunnycopter” with rotors of different sizes and heights.</p>
<div class="keep-aspect"><iframe title="Design Your Own Drones" width="500" height="281" src="https://www.youtube-nocookie.com/embed/oTKABMVlaCw?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>“This system opens up new possibilities for how drones look and function,” says MIT professor <a href="http://people.csail.mit.edu/wojciech/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Wojciech Matusik</a>, who oversaw the project in CSAIL’s <a href="http://cfg.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Computational Fabrication Group</a>. “It’s no longer a one-size-fits-all approach for people who want to make and use drones for particular purposes.”</p>
<a href="https://j.gifs.com/Lg0g74.gif" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" class="aligncenter" src="https://j.gifs.com/Lg0g74.gif" alt="" width="640" height="360" /></a>
<p>The interface lets users design drones with different rotors and rods. It also provides guarantees that its drones can take off, hover and land (which is no simple task considering the intricate technical trade-offs associated with drone weight, shape and control).</p>
<p>“For example, adding more rotors generally lets you carry more weight, but you also need to think about how to balance the drone to make sure it doesn’t tip,” says PhD student <a href="http://cfg.mit.edu/content/tao-du" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Tao Du</a>, who is first author on a related paper about the system. “Irregularly-shaped drones are very difficult to stabilize, which means that they require establishing very complex control parameters.”</p>
<p>Du and Matusik co-authored a paper with PhD student <a href="http://people.csail.mit.edu/aschulz/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Adriana Schulz</a>, postdoctoral researcher <a href="http://people.csail.mit.edu/boolzhu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Bo Zhu</a> and assistant professor <a href="http://berndbickel.com/about-me/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Bernd Bickel</a> of <a href="https://ist.ac.at/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">IST Austria</a>. It will be presented this week at the annual <a href="https://sa2016.siggraph.org/en/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">SIGGRAPH Asia conference</a> in Macao, China.</p>
<p><b>How it works</b><b><br />
</b>Today’s commercial drones only come in a small range of options, typically with an even number of upward-facing rotors. But there are many emerging use cases for other kinds of drones. For example, having an odd number of rotors might create a clearer view for a drone’s camera, or allow the drone to carry objects with unusual shapes.</p>
<p>Designing these less conventional drones, however, often requires expertise in multiple disciplines, including control systems, fabrication and electronics.</p>
<p>“Developing multicopters like these that are actually flyable involves a lot of trial-and-error, tweaking the balance between all the propellers and rotors,” says Du. “It would be more or less impossible for an amateur user, especially one without any computer-science background.”</p>
<a href="https://j.gifs.com/66G6W9.gif" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" class="aligncenter" src="https://j.gifs.com/66G6W9.gif" alt="" width="640" height="360" /></a>
<p>But the CSAIL group’s new system makes the process much easier. Users design drones by choosing from a database of parts and specifying their needs for things like payload, cost and battery usage. The system computes the sizes of design elements like rod lengths and motor angles, and looks at metrics such as torque and thrust to determine whether the design will actually work. It also uses an “LQR controller” that takes information about a drone’s characteristics and surroundings to optimize its flight plan.</p>
<p>One of the project’s core challenges stemmed from the fact that a drone’s shape and structure (its “geometry”) is usually strongly tied to how it has been programmed to move (its “control”). To overcome this, researchers used what’s called an “alternating direction method,” which means that they reduced the number of variables by fixing some of them and optimizing the rest. This allowed the team to decouple the variables of geometry and control in a way that optimizes the drone’s performance.</p>
<p>“Once you decouple these variables, you turn a very complicated optimization problem into two easy sub-problems that we already have techniques for solving,” says Du.</p>
<p>Du envisions future versions of the system that could proactively give design suggestions, like recommending where a rotor should go to accommodate a desired payload.</p>
<p>“This is the first system in which users can interactively design a drone that incorporates both geometry and control,” says <a href="https://www.autodeskresearch.com/people/nobuyuki-umetani" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Nobuyuki Umetani</a>, a research scientist at <a href="http://www.autodesk.com/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Autodesk, Inc</a> who was not involved in the paper. “This is very exciting work that has the potential to change the way people design.”</p>
<p>The project was supported in part by the <a href="https://www.nsf.gov/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">National Science Foundation</a>, the <a href="http://www.wpafb.af.mil/afrl" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Air Force Research Laboratory</a> and the <a href="https://ec.europa.eu/programmes/horizon2020/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">European Union’s Horizon 2020</a> research and innovation program.</p>
<p>Click <a href="http://cfg.mit.edu/sites/cfg.mit.edu/files/copter.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">here to read the full paper.</a></p>
<hr class="xh2  ">
<p><em>If you enjoyed this article, you might also be interested in:</em></p>
<ul>
<li><a href="http://robohub.org/emerging-patchwork-of-regulation-of-uas-operations-near-critical-infrastructure/" target="_blank" data-wpel-link="internal">Emerging patchwork of regulation of UAS operations near critical infrastructure</a></li>
<li><a href="http://robohub.org/protecting-infrastructure-and-innovation-under-section-2209-of-the-faa-extension/" target="_blank" data-wpel-link="internal">Protecting infrastructure and innovation, under Section 2209 of the FAA extension</a></li>
<li><a href="http://robohub.org/why-dji-is-succeeding-in-making-and-selling-drones-and-3dr-didnt/" target="_blank" data-wpel-link="internal">Why DJI is succeeding in making and selling drones and 3DR didn’t</a></li>
<li><a href="http://robohub.org/mit-csails-6-foot-tall-nasa-humanoid-robot-has-landed/" target="_blank" data-wpel-link="internal">MIT CSAIL’s 6-foot-tall NASA humanoid robot has landed</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" target="_blank" data-wpel-link="internal">the latest robotics news</a> on Robohub, or <a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>How the brain recognizes faces</title>
		<link>https://robohub.org/how-the-brain-recognizes-faces/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Thu, 01 Dec 2016 18:00:00 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<category><![CDATA[news]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[AI-cognition]]></category>
		<category><![CDATA[announcements]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/how-the-brain-recognizes-faces/</guid>

					<description><![CDATA[Machine-learning system spontaneously reproduces aspects of human neurology.]]></description>
										<content:encoded><![CDATA[<div id="attachment_68643" style="width: 910px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/12/facerecognition.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-68643" class="size-full wp-image-68643" src="http://robohub.org/wp-content/uploads/2016/12/facerecognition.jpg" alt="Tomaso Poggio, a professor of brain and cognitive sciences at MIT and director of the Center for Brains, Minds, and Machines, has long thought that the brain must produce “invariant” representations of faces and other objects, meaning representations that are indifferent to objects’ orientation in space, their distance from the viewer, or their location in the visual field. Image Credit: Massachusetts Institute of Technology" width="900" height="540" srcset="https://robohub.org/wp-content/uploads/2016/12/facerecognition.jpg 900w, https://robohub.org/wp-content/uploads/2016/12/facerecognition-425x255.jpg 425w, https://robohub.org/wp-content/uploads/2016/12/facerecognition-500x300.jpg 500w" sizes="(max-width: 900px) 100vw, 900px" /></a><p id="caption-attachment-68643" class="wp-caption-text">Image: Massachusetts Institute of Technology</p></div>
<p>MIT researchers and their colleagues have developed a new computational model of the human brain’s face-recognition mechanism that seems to capture aspects of human neurology that previous models have missed.<span id="more-68625"></span></p>
<p>The researchers designed a machine-learning system that implemented their model, and they trained it to recognize particular faces by feeding it a battery of sample images. They found that the trained system included an intermediate processing step that represented a face’s degree of rotation — say, 45 degrees from center — but not the direction — left or right.</p>
<p>This property wasn’t built into the system; it emerged spontaneously from the training process. But it duplicates an experimentally observed feature of the primate face-processing mechanism. The researchers consider this an indication that their system and the brain are doing something similar.</p>
<p>“This is not a proof that we understand what’s going on,” says Tomaso Poggio, a professor of brain and cognitive sciences at MIT and director of the Center for Brains, Minds, and Machines (CBMM), a multi-institution research consortium funded by the National Science Foundation and headquartered at MIT. “Models are kind of cartoons of reality, especially in biology. So I would be surprised if things turn out to be this simple. But I think it’s strong evidence that we are on the right track.”</p>
<p>Indeed, the researchers’ new paper includes a mathematical proof that the particular type of machine-learning system they use, which was intended to offer what Poggio calls a “biologically plausible” model of the nervous system, will inevitably yield intermediary representations that are indifferent to angle of rotation.</p>
<p>Poggio, who is also a primary investigator at MIT’s McGovern Institute for Brain Research, is the senior author on a paper describing the new work, which appeared today in the journal <em>Computational Biology</em>. He’s joined on the paper by several other members of both the CBMM and the McGovern Institute: first author Joel Leibo, a researcher at Google DeepMind, who earned his PhD in brain and cognitive sciences from MIT with Poggio as his advisor; Qianli Liao, an MIT graduate student in electrical engineering and computer science; Fabio Anselmi, a postdoc in the IIT@MIT Laboratory for Computational and Statistical Learning, a joint venture of MIT and the Italian Institute of Technology; and Winrich Freiwald, an associate professor at the Rockefeller University.</p>
<div class="keep-aspect"><iframe title="View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric..." width="500" height="281" src="https://www.youtube-nocookie.com/embed/EftRACg0grE?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p><strong>Emergent properties</strong></p>
<p>The new paper is “a nice illustration of what we want to do in [CBMM], which is this integration of machine learning and computer science on one hand, neurophysiology on the other, and aspects of human behavior,” Poggio says. “That means not only what algorithms does the brain use, but what are the circuits in the brain that implement these algorithms.”</p>
<p>Poggio has long believed that the brain must produce “invariant” representations of faces and other objects, meaning representations that are indifferent to objects’ orientation in space, their distance from the viewer, or their location in the visual field. Magnetic resonance scans of human and monkey brains suggested as much, but in 2010, Freiwald published a study describing the neuroanatomy of macaque monkeys’ face-recognition mechanism in much greater detail.</p>
<p>Freiwald showed that information from the monkey’s optic nerves passes through a series of brain locations, each of which is less sensitive to face orientation than the last. Neurons in the first region fire only in response to particular face orientations; neurons in the final region fire regardless of the face’s orientation — an invariant representation.</p>
<p>But neurons in an intermediate region appear to be “mirror symmetric”: That is, they’re sensitive to the angle of face rotation without respect to direction. In the first region, one cluster of neurons will fire if a face is rotated 45 degrees to the left, and a different cluster will fire if it’s rotated 45 degrees to the right. In the final region, the same cluster of neurons will fire whether the face is rotated 30 degrees, 45 degrees, 90 degrees, or anywhere in-between. But in the intermediate region, a particular cluster of neurons will fire if the face is rotated by 45 degrees in either direction, another if it’s rotated 30 degrees, and so on.</p>
<p>This is the behavior that the researchers’ machine-learning system reproduced. “It was not a model that was trying to explain mirror symmetry,” Poggio says. “This model was trying to explain invariance, and in the process, there is this other property that pops out.”</p>
<p><strong>Neural training</strong></p>
<p>The researchers’ machine-learning system is a neural network, so called because it roughly approximates the architecture of the human brain. A neural network consists of very simple processing units, arranged into layers, that are densely connected to the processing units — or nodes — in the layers above and below. Data are fed into the bottom layer of the network, which processes them in some way and feeds them to the next layer, and so on. During training, the output of the top layer is correlated with some classification criterion — say, correctly determining whether a given image depicts a particular person.</p>
<p>In earlier work, Poggio’s group had trained neural networks to produce invariant representations by, essentially, memorizing a representative set of orientations for just a handful of faces, which Poggio calls “templates.” When the network was presented with a new face, it would measure its difference from these templates. That difference would be smallest for the templates whose orientations were the same as that of the new face, and the output of their associated nodes would end up dominating the information signal by the time it reached the top layer. The measured difference between the new face and the stored faces gives the new face a kind of identifying signature.</p>
<p>In experiments, this approach produced invariant representations: A face’s signature turned out to be roughly the same no matter its orientation. But the mechanism — memorizing templates — was not, Poggio says, biologically plausible.</p>
<p>So instead, the new network uses a variation on Hebb’s rule, which is often described in the neurological literature as “neurons that fire together wire together.” That means that during training, as the weights of the connections between nodes are being adjusted to produce more accurate outputs, nodes that react in concert to particular stimuli end up contributing more to the final output than nodes that react independently (or not at all).</p>
<p>This approach, too, ended up yielding invariant representations. But the middle layers of the network also duplicated the mirror-symmetric responses of the intermediate visual-processing regions of the primate brain.</p>
<p>“I think it’s a significant step forward,” says Christof Koch, president and chief scientific officer at the Allen Institute for Brain Science. “In this day and age, when everything is dominated by either big data or huge computer simulations, this shows you how a principled understanding of learning can explain some puzzling findings.”</p>
<p>“They’re very careful,” Koch adds. “They’re only looking at the feed-forward pathway — in other words, the first 80, 100 milliseconds. The monkey opens its eyes, and within 80 to 100 milliseconds, it can recognize a face and push a button signaling that. The question is what goes on in those 80 to 100 milliseconds, and the model that they have seems to explain that quite well.”</p>
<hr class="xh2  ">
<p><em>If you enjoyed this article, you might also be interested in:</em></p>
<ul>
<li><a href="http://robohub.org/the-human-brain-vs-the-digital-brain-a-case-for-visual-inspections/" target="_blank" data-wpel-link="internal">The human brain vs. the digital brain: A case for visual inspections</a></li>
<li><a href="http://robohub.org/assistive-robot-operated-via-a-brain-computer-interface/" target="_blank" data-wpel-link="internal">Assistive robot operated via a brain-computer interface</a></li>
<li><a href="http://robohub.org/virtual-race-competing-in-brain-computer-interface-at-cybathlon/" target="_blank" data-wpel-link="internal">Virtual race: Competing in Brain Computer Interface at Cybathlon</a></li>
<li><a href="http://robohub.org/can-a-brain-computer-interface-convert-your-thoughts-to-text/" target="_blank" data-wpel-link="internal">Can a brain-computer interface convert your thoughts to text?</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" target="_blank" data-wpel-link="internal">the latest robotics news</a> on Robohub, or <a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Professor Emeritus Whitman Richards dies at 84</title>
		<link>https://robohub.org/professor-emeritus-whitman-richards-dies-at-84/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Tue, 18 Oct 2016 10:48:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<guid isPermaLink="false">http://robohub.org/professor-emeritus-whitman-richards-dies-at-84/</guid>

					<description><![CDATA[Longtime professor and beloved advisor was known for advances in experimental and theoretical studies of vision, perception, and cognition.]]></description>
										<content:encoded><![CDATA[<div id="attachment_67241" style="width: 659px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/10/whitman-richards-mit_0.jpeg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-67241" class="wp-image-67241 size-full" src="http://robohub.org/wp-content/uploads/2016/10/whitman-richards-mit_0.jpeg" alt="whitman-richards-mit_0" width="649" height="426" srcset="https://robohub.org/wp-content/uploads/2016/10/whitman-richards-mit_0.jpeg 649w, https://robohub.org/wp-content/uploads/2016/10/whitman-richards-mit_0-425x279.jpeg 425w, https://robohub.org/wp-content/uploads/2016/10/whitman-richards-mit_0-457x300.jpeg 457w" sizes="(max-width: 649px) 100vw, 649px" /></a><p id="caption-attachment-67241" class="wp-caption-text">Whitman Richards. Photo: Webb Chappell/MIT Media Lab</p></div>
<p>Whitman Richards &#8217;53, PhD &#8217;65, professor emeritus of cognitive sciences and of media arts and sciences and principal investigator in the Computer Science and Artificial Intelligence Laboratory, died on Sept. 16 after a long battle with myelofibrosis. One of the first four PhD graduates of the Department of Brain and Cognitive Sciences (BCS), his more than 60 years at MIT were marked by a dedication to the experimental and theoretical study of vision, perception, and cognition.</p>
<p>Richards began his affiliation with MIT as an undergraduate, matriculating in 1950. His decision to return to MIT for graduate work was greatly inspired by a meeting with BCS founder and then department head Professor Hans-Lukas Teuber.</p>
<p>“In the 1960’s, with the advent of accessible computer technology, the development of information theory, and the single electrode, there was renewed excitement about prospects for modeling and understanding mind and brain,” Richards said in a 2004 interview. “Teuber’s charisma and broad vision for a new psychol­ogy was a powerful draw [to the department]. …There was a unique opportunity for a non-traditional grounding in a discipline otherwise mired in tradition.”</p>
<p>Richards’ early research pursued traditional psychophysical experimental methods to study the mechanisms of color perception and stereovision. In the 1970s, his research direction and methodology shifted dramatically after meeting noted physiologist David Marr, who he eventually recruited to MIT. Instead of relying on the traditional experimental methods that had characterized his early career, Richards, Marr, and colleagues began to look for the deep, underlying mathematical principles that allowed a human or artificial visual system to look at the world and make accurate inferences about what the system saw or perceived.</p>
<p>“The breadth of his research was really quite remarkable,” says Josh Tenenbaum, MIT professor of computational cognitive science and former Richards graduate student. “As his career developed, he transitioned from studying the parts of vision that are very close to neural mechanisms, to computational representations of perception, to Bayesian statistical models of perception and cognition. He became almost a computational social scientist — he was incredibly flexible in his thinking.”</p>
<p>Richards’ passionate advocacy for the computational approach to studying visual perception helped to create and nurture the department’s early computational research initiatives.</p>
<p>“Whit’s connection with David Marr back in the late &#8217;70s is really the genesis of modern computational social science today,” says MIT Professor Alex Pentland, the Toshiba Professor of Media Arts and Science and a former Richards graduate student.</p>
<p>Alongside his impressive research legacy, which includes the publication of eight books and over 200 articles, Richards was also regarded by his students and colleagues as a superlative mentor. Many of his former students have found success in a variety of different fields, including psychology, cognitive science, computer science, media, computer graphics, and the defense industry.</p>
<p>“Whitman was an incredibly dedicated advisor. His strategy was to have very few students and make a huge personal investment in each of them,” says John Rubin, a former graduate student of Richards and current executive producer with Tangled Bank Studios at the Howard Hughes Medical Institute. “He was really great at keeping enthusiasm high in his lab, which took all kinds of forms, but included croquet parties at his home, which were terrifically fun. He was always available and, in fact, it was hard for me to keep up with the amount of time he wanted to devote to our joint work! He was indefatigable and devoted.”</p>
<p>Richards is survived by his wife of 54 years, Waltraud Weller Richards, and three daughters: Diana Richards Doyle and husband Mark S. Doyle of Green Cove Springs, Florida; Sylvia Richards-Gerngross and husband Tillman Gerngross of Hanover, New Hampshire; and Eleanor &#8220;Nora&#8221; Richards Bender and husband Thomas A. Bender of Dedham, Massachusetts. He is also survived by his two siblings: Lincoln K. Richards and wife Gerda of Wellesley, Massachusetts, and Sylvia Richards Messner of Cave Creek, Arizona; and by two grandchildren, Morgan Kelly Doyle and Serafina Richards-Gerngross. Memorial services will be private.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Designing and deploying a fleet of autonomous boats on the canals of Amsterdam</title>
		<link>https://robohub.org/designing-and-deploying-a-fleet-of-autonomous-boats-on-the-canals-of-amsterdam/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Tue, 20 Sep 2016 10:30:00 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/designing-and-deploying-a-fleet-of-autonomous-boats-on-the-canals-of-amsterdam/</guid>

					<description><![CDATA[MIT, AMS Institute will collaborate to solve complex urban problems for Amsterdam with the development of autonomous "roboats."]]></description>
										<content:encoded><![CDATA[<div id="attachment_66353" style="width: 910px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/09/amsterdam-canals-mit-ams-roboat.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-66353" class="wp-image-66353 size-full" src="http://robohub.org/wp-content/uploads/2016/09/amsterdam-canals-mit-ams-roboat.jpg" alt="" width="900" height="689" srcset="https://robohub.org/wp-content/uploads/2016/09/amsterdam-canals-mit-ams-roboat.jpg 900w, https://robohub.org/wp-content/uploads/2016/09/amsterdam-canals-mit-ams-roboat-425x325.jpg 425w, https://robohub.org/wp-content/uploads/2016/09/amsterdam-canals-mit-ams-roboat-392x300.jpg 392w" sizes="(max-width: 900px) 100vw, 900px" /></a><p id="caption-attachment-66353" class="wp-caption-text">Photo courtesy of AMS.</p></div>
<p>MIT has signed an agreement to engage in research collaborations with the Amsterdam Institute for Advanced Metropolitan Solutions (AMS) in the Netherlands. The collaboration’s flagship project, led by researchers from multiple departments at MIT, will be to develop a fleet of autonomous boats for the city’s canals.</p>
<p>Based in Amsterdam, <a href="http://www.ams-amsterdam.com/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">the AMS Institute</a> brings together a consortium of public and private partners to tackle complex urban challenges such as water, energy, waste, food, data, and mobility. MIT joins with two research institutions in the Netherlands — the Delft University of Technology and Wageningen University and Research Center — as the core academic partners who will use the city as a living laboratory and test bed.</p>
<p>An interdisciplinary team from MIT has assembled to lead the collaboration’s first project: ROBOAT, an effort to develop a fleet of autonomous boats, or “roboats,” to investigate how urban waterways can be used to improve the city’s function and quality of life.</p>
<div id="attachment_66355" style="width: 910px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/09/roboat-mit-senseable-city.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-66355" class="size-full wp-image-66355" src="http://robohub.org/wp-content/uploads/2016/09/roboat-mit-senseable-city.jpg" alt="The new ROBOAT project will investigate how urban waterways can be used to improve the city’s function and quality of life. Photo: SENSEable City Lab" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2016/09/roboat-mit-senseable-city.jpg 900w, https://robohub.org/wp-content/uploads/2016/09/roboat-mit-senseable-city-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/09/roboat-mit-senseable-city-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /></a><p id="caption-attachment-66355" class="wp-caption-text">The new ROBOAT project will investigate how urban waterways can be used to improve the city’s function and quality of life. Photo: SENSEable City Lab</p></div>
<p>The <a href="http://senseable.mit.edu/roboat" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">ROBOAT project</a> will develop a logistics platform for people and goods, superimposing a dynamic infrastructure over one the world’s most famous water cities. “This project imagines a fleet of autonomous boats for the transportation of goods and people that can also cooperate to produce temporary floating infrastructure, such as on-demand bridges or stages that can be assembled or disassembled in a matter of hours,” says Carlo Ratti, professor of the practice of urban technologies in the MIT Department of Urban Studies and Planning (DUSP).</p>
<p>In addition to infrastructure and transport, ROBOAT will also deploy environmental sensing to monitor water quality and offer data for assessing and predicting issues related to public health, pollution, and the environment. “Water is the bearer of life. By focusing on the water system of the city, ROBOAT can create opportunities for new environmental sensing methods and climate adaptation. This will help secure the city’s quality of life and lasting functionality,” says Arjan van Timmeren, professor and scientific director at AMS, who also envisions a multitude of possibilities for a network of roboats, from real-time sensing similar to the MIT <a href="http://underworlds.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Underworlds</a> project to retrieving the 12,000 bicycles or cleaning up the floating waste that ends up in the Dutch city’s canals each year.</p>
<p>Joining Ratti from MIT as co-principal investigators are Daniela Rus, professor of electrical engineering and computer science and director of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL); Andrew Whittle, the Edmund K. Turner Professor in Civil Engineering in the Department of Civil and Environmental Engineering; and Dennis Frenchman, the Class of 1922 Professor of Urban Design and Planning and director of the DesignX program in the MIT School of Architecture and Planning.</p>
<div id="attachment_66356" style="width: 497px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/09/MIT-AMS-Faculty-lo-res.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-66356" class="size-full wp-image-66356" src="http://robohub.org/wp-content/uploads/2016/09/MIT-AMS-Faculty-lo-res.jpg" alt="The ROBOAT project will be led at MIT by an interdisciplinary team: (clockwise, from top left) Daniela Rus, professor of electrical engineering and computer science and director of the Computer Science and Artificial Intelligence Laboratory; Dennis Frenchman, the Class of 1922 Professor of Urban Design and Planning and director of the DesignX program in the School of Architecture and Planning; Andrew Whittle, the Edmund K. Turner Professor in Civil Engineering in the Department of Civil and Environmental Engineering; and Carlo Ratti, professor of the practice of urban technologies in the Department of Urban Studies and Planning." width="487" height="426" srcset="https://robohub.org/wp-content/uploads/2016/09/MIT-AMS-Faculty-lo-res.jpg 487w, https://robohub.org/wp-content/uploads/2016/09/MIT-AMS-Faculty-lo-res-425x372.jpg 425w, https://robohub.org/wp-content/uploads/2016/09/MIT-AMS-Faculty-lo-res-343x300.jpg 343w" sizes="(max-width: 487px) 100vw, 487px" /></a><p id="caption-attachment-66356" class="wp-caption-text">The ROBOAT project will be led at MIT by an interdisciplinary team: (clockwise, from top left) Daniela Rus, professor of electrical engineering and computer science and director of the Computer Science and Artificial Intelligence Laboratory; Dennis Frenchman, the Class of 1922 Professor of Urban Design and Planning and director of the DesignX program in the School of Architecture and Planning; Andrew Whittle, the Edmund K. Turner Professor in Civil Engineering in the Department of Civil and Environmental Engineering; and Carlo Ratti, professor of the practice of urban technologies in the Department of Urban Studies and Planning.</p></div>
<p>At AMS, Van Timmeren and Stephan van Dijk, research program manager, will coordinate the involvement of another 12 groups of researchers from TU Delft and Wageningen UR. Along with the City of Amsterdam, Waternet, the public water utility of Amsterdam and surrounding areas, will participate in the research.</p>
<p>The first prototypes of autonomous boats, or “roboats,” are expected to be tested in Amsterdam in 2017. The project’s initial phase will last for five years.</p>
<p>With nearly one-quarter of the city covered by water, Amsterdam is an ideal place for developing ROBOAT, according to the researchers. The canal system was once the key functional urban infrastructure of the city and today still plays a major role in recreation and tourism. Amsterdam’s waters, including bridges, canals, and the IJ river and its docks, offer plenty of opportunity to help solve current issues with transportation, mobility, and water quality.</p>
<div id="attachment_66354" style="width: 910px" class="wp-caption aligncenter"><a href="http://robohub.org/wp-content/uploads/2016/09/waterways.jpg" data-wpel-link="internal"><img decoding="async" aria-describedby="caption-attachment-66354" class="size-full wp-image-66354" src="http://robohub.org/wp-content/uploads/2016/09/waterways.jpg" alt="Photo courtesy of AMS." width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2016/09/waterways.jpg 900w, https://robohub.org/wp-content/uploads/2016/09/waterways-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/09/waterways-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /></a><p id="caption-attachment-66354" class="wp-caption-text">Photo courtesy of AMS.</p></div>
<p>With 80 percent of global economic output generated around coasts, riverbanks, and deltas and 60 percent of the world population living in these areas, researchers anticipate that outcomes from the ROBOAT projects could become a reference for other urban areas around the world and a source of international entrepreneurial initiatives and start-ups in which autonomy enters the marine world.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>MIT, Lockheed Martin launch long-term research collaboration</title>
		<link>https://robohub.org/mit-lockheed-martin-launch-long-term-research-collaboration/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Tue, 17 May 2016 15:50:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[business]]></category>
		<category><![CDATA[MIT]]></category>
		<guid isPermaLink="false">http://robohub.org/mit-lockheed-martin-launch-long-term-research-collaboration/</guid>

					<description><![CDATA[Initial focus will be on transformative technologies, autonomy, and robotics.]]></description>
										<content:encoded><![CDATA[<div id="attachment_62584" style="width: 649px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-62584" class="size-full wp-image-62584" src="http://robohub.org/wp-content/uploads/2016/05/mit-lockheed-martin-signing_0.jpg" alt="Lockheed Martin CTO Keoki Jackson '89, SM '92, ScD '97 (center, left) and MIT AeroAstro department head Jaime Peraire congratulate each other after signing a research collaboration agreement between the two organizations. Initial research will focus on robotics and autonomous systems. Photo: William Litant/MIT AeroAstro" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2016/05/mit-lockheed-martin-signing_0.jpg 639w, https://robohub.org/wp-content/uploads/2016/05/mit-lockheed-martin-signing_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/05/mit-lockheed-martin-signing_0-450x300.jpg 450w" sizes="(max-width: 639px) 100vw, 639px" /><p id="caption-attachment-62584" class="wp-caption-text">Lockheed Martin CTO Keoki Jackson &#8217;89, SM &#8217;92, ScD &#8217;97 (center, left) and MIT AeroAstro department head Jaime Peraire congratulate each other after signing a research collaboration agreement between the two organizations. Initial research will focus on robotics and autonomous systems.<br />Photo: William Litant/MIT AeroAstro</p></div>
<p>In a new collaborative initiative in autonomy and robotics, MIT and <a href="http://www.lockheedmartin.com/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Lockheed Martin</a> scientists will focus on innovations needed to enable generation-after-next autonomous systems. Improvements in human/machine teaming and navigation in complex environments are among the research challenges that Lockheed Martin is inviting MIT faculty and their students to help solve.<span id="more-62557"></span></p>
<p>“We have a valued relationship with MIT and are looking forward to moving to this next chapter and partnering with world-class researchers,” said Keoki Jackson &#8217;89, SM &#8217;92, ScD &#8217;97, Lockheed Martin&#8217;s chief technology officer. “We are focused on advancing technology and recruiting top talent, both of which are crucial for creating the next generation of aerospace systems.”</p>
<p>A master agreement between MIT and Lockheed Martin, led by the Institute’s Department of Aeronautics and Astronautics (AeroAstro), and in collaboration with MIT’s Computer Science and Artificial Intelligence Laboratory, was formalized May 13 at a signing ceremony on campus. It provides a multiyear framework between MIT and Lockheed Martin for collaborative research, exchange of visiting scientists, support of student undergraduate research opportunities, fellowships, and internships at Lockheed Martin.</p>
<p>“We’re making the investment today, not just in research and development of the technologies that could have the most impact on future generations, but in the talent of these amazing individuals that will truly shape the future,” said Padraig Moloney &#8217;00, Lockheed Martin program manager and architect of the new initiative. “We’re confident that our relationship and collaboration in these technical areas will influence the fields of autonomy and robotics for the next 15-20 years.”</p>
<p>AeroAstro department head Jaime Peraire said, “We’re delighted with this new agreement, which furthers a relationship between MIT AeroAstro and Lockheed Martin that goes back many years. It formalizes our partnership, and aligns with MIT’s mode of conducting research and education by melding academic rigor with real engineering challenges and applications.”</p>
<p>Initial research will be conducted by AeroAstro professors Jonathan How, Nick Roy, Sertac Karaman, Julie Shah, and Russ Tedrake and Department of Mechanical Engineering Professor Sangbae Kim.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>MIT CSAIL’s 6-foot-tall NASA humanoid robot has landed</title>
		<link>https://robohub.org/mit-csails-6-foot-tall-nasa-humanoid-robot-has-landed/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Thu, 28 Apr 2016 14:24:06 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[space]]></category>
		<guid isPermaLink="false">http://robohub.org/mit-csails-6-foot-tall-nasa-humanoid-robot-has-landed/</guid>

					<description><![CDATA[By Adam Conner-Simons, MIT CSAIL This week MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) received an unusual package: a six-foot-tall, 300-pound humanoid robot that NASA hopes to have serve on future space missions to Mars and beyond. A team of researchers led by CSAIL principal investigator Russ Tedrake will program their new “Valkyrie” robot [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="aligncenter size-full wp-image-62007" src="http://robohub.org/wp-content/uploads/2016/04/Valkyrie.jpg" alt="Valkyrie" width="1200" height="608" srcset="https://robohub.org/wp-content/uploads/2016/04/Valkyrie.jpg 1200w, https://robohub.org/wp-content/uploads/2016/04/Valkyrie-425x215.jpg 425w, https://robohub.org/wp-content/uploads/2016/04/Valkyrie-1024x519.jpg 1024w, https://robohub.org/wp-content/uploads/2016/04/Valkyrie-500x253.jpg 500w" sizes="(max-width: 1200px) 100vw, 1200px" />
<p><strong>By Adam Conner-Simons, MIT CSAIL</strong></p>
<p>This week MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) received an unusual package: a six-foot-tall, 300-pound humanoid robot that NASA hopes to have serve on future space missions to Mars and beyond.<span id="more-61997"></span></p>
<p>A team of researchers led by CSAIL principal investigator Russ Tedrake will program their new “Valkyrie” robot to autonomously perform a variety of challenging tasks that would allow it to help or even replace astronauts on missions.</p>
<div class="keep-aspect"><iframe title="Assembling NASA&#039;s Valkyrie robot" width="500" height="281" src="https://www.youtube-nocookie.com/embed/V2MEFDalpZw?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Valkyrie is fully electric, with four body cameras, 28 torque-controlled joints and 44 degrees of freedom. The robot boasts more than 200 individual sensors, including 38 on each hand (six on each palm, and eight along each of its four fingers).</p>
<p>Other researchers participating in the project include professors Leslie Kaelbling and Tomas Lozano-Perez, who will conduct work on high-level autonomy.</p>
<p>&#8220;Our work is about vetting the robot and seeing what it is capable of,” says Tedrake, whose team received a two-year research grant from NASA for the project. “If we can integrate the autonomy work with our planning and control algorithms, it could result in an unprecedented level of autonomous capabilities for a humanoid robot.’</p>
<img decoding="async" class="aligncenter size-full wp-image-62014" src="http://robohub.org/wp-content/uploads/2016/04/robot-nasa2.jpg" alt="robot-nasa2" width="900" height="1016" srcset="https://robohub.org/wp-content/uploads/2016/04/robot-nasa2.jpg 900w, https://robohub.org/wp-content/uploads/2016/04/robot-nasa2-376x425.jpg 376w, https://robohub.org/wp-content/uploads/2016/04/robot-nasa2-266x300.jpg 266w" sizes="(max-width: 900px) 100vw, 900px" />
<p>&nbsp;</p>
<p>Tedrake’s team at CSAIL’s <a href="http://groups.csail.mit.edu/locomotion/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Robot Locomotion Group</a> has extensive experience developing autonomous robots. The group spent the last three years doing research as part of <a href="http://news.mit.edu/2015/mit-team-places-sixth-darpa-robotics-challenge-0608" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">the DARPA Robotics Challenge</a>, where they programmed another six-foot-tall robot named Atlas to complete a series of tasks that included opening doors, turning valves, drilling holes, climbing stairs and driving a car.</p>
<p>Besides the CSAIL team, NASA also awarded a Valkyrie robot to Northeastern University in conjunction with the University of Massachusetts at Lowell.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Wireless localizer could mean safer drones and password-free WiFi</title>
		<link>https://robohub.org/wireless-localizer-could-mean-safer-drones-and-password-free-wifi/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Fri, 01 Apr 2016 12:35:52 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/wireless-localizer-could-mean-safer-drones-and-password-free-wifi/</guid>

					<description><![CDATA[By Adam Conner-Simons &#124; CSAIL We’ve all been there, impatiently twiddling our thumbs while trying to locate a WiFi signal. But what if, instead, the WiFi could locate us? According to researchers at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL), it could mean safer drones, smarter homes and password-free WiFi. In a new paper, a [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_61092" style="width: 910px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-61092" class="size-full wp-image-61092" src="http://robohub.org/wp-content/uploads/2016/04/wireless-drone-csail.jpg" alt=" According to CSAIL researchers, a new wireless technology they've developed could mean safer drones, smarter homes and password-free WiFi. Source: MITCSAIL" width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2016/04/wireless-drone-csail.jpg 900w, https://robohub.org/wp-content/uploads/2016/04/wireless-drone-csail-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/04/wireless-drone-csail-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /><p id="caption-attachment-61092" class="wp-caption-text">According to CSAIL researchers, a new wireless technology they&#8217;ve developed could mean safer drones, smarter homes and password-free WiFi. Source: MIT/CSAIL</p></div>
<p><strong>By Adam Conner-Simons | CSAIL </strong></p>
<p>We’ve all been there, impatiently twiddling our thumbs while trying to locate a WiFi signal. But what if, instead, the WiFi could locate <strong>us</strong>?<span id="more-61091"></span></p>
<p>According to researchers at MIT’s <a href="http://csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Computer Science and Artificial Intelligence Lab</a> (CSAIL), it could mean safer drones, smarter homes and password-free WiFi.</p>
<p><a href="https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-vasisht.pdf" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">In a new paper,</a> a research team led by professor Dina Katabi presents a system called Chronos that enables a single WiFi access point to locate users to within tens of centimeters, without any external sensors.</p>
<div class="keep-aspect"><iframe title="Wireless Localization with &quot;Chronos&quot;" width="500" height="281" src="https://www.youtube-nocookie.com/embed/cJx7ewEyuzo?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The group demonstrated Chronos in an apartment and a cafe, while also showing off a drone that maintains a safe distance from its user with a margin of error of about four centimeters.</p>
<p>“From developing drones that are safer for people to be around, to tracking where family members are in your house, Chronos could open up new avenues for using WiFi in robotics, home automation and more,” says PhD student Deepak Vasisht, who is first author on the paper alongside Katabi and former PhD student Swarun Kumar, who is now an assistant professor at Carnegie Mellon University. “Designing a system that enables one WiFi node to locate another is an important step for wireless technology.”</p>
<p>Experiments conducted in a two-bedroom apartment with four occupants show that Chronos can correctly identify which room a resident is in 94 percent of the time. For the cafe demo, the system was 97 percent accurate in distinguishing in-store customers from out-of-store intruders &#8211; meaning it could be used by small businesses to prevent non-customers from stealing their WiFi. (32 percent of Americans have copped to this cyber-crime.)</p>
<p>Chronos locates users by calculating the “time-of-flight” that it takes for data to travel from the user to an access point. The system is 20 times more accurate than existing systems, computing time-of-flight with an average error of 0.47 nanoseconds, or half than one-billionth of a second.</p>
<p>Vasisht presented the paper at this month’s USENIX Symposium on Networked Systems Design and Implementation (NSDI &#8217;16).</p>
<h2><strong>How it works</strong></h2>
<p>Existing localization methods have required four or five WiFi access points. This is because today’s WiFi devices don’t have wide enough bandwidth to measure time-of-flight, and so researchers have only been able to determine someone’s position by triangulating multiple angles relative to the person.</p>
<p>What Chronos adds is the ability to calculate not just the angle, but the actual distance from a user to an access point, as determined by multiplying the time-of-flight by the speed of light.</p>
<p>“Knowing both the distance and the angle allows you to compute the user’s position using just one access point,” says Deepak Vasisht. “This is encouraging news for the many small businesses and consumers that don’t have the luxury of owning several access points.”</p>
<p>Exploiting the fact that WiFi lets you hop on different frequency channels, the team programmed the system to jump from channel to channel, gathering many different measurements of the distance between access points and the user. Chronos then automatically “stitches” together these measurements to determine the distance.</p>
<p>“By devising a method to rapidly hop across these channels that span almost one gigahertz of bandwidth, Chronos can measure time-of-flight with sub-nanosecond accuracy, emulating with commercial WiFi what has previously needed an expensive ultra-wideband radio,” says Venkat Padmanabhan. a principal researcher at Microsoft Research India. “This is an impressive breakthrough and promises to be a key enabler for applications such as high-accuracy indoor localization.”</p>
<p>That said, getting an accurate time-of-flight with this method still isn’t easy, due to three sets of delays that happen during the transfer.</p>
<p>First, when you wirelessly send a piece of web data, there is a delay in detecting the presence of the “packet” that is hard to distinguish from the actual time-of-flight. To account for it, the team exploits the fact that WiFi uses an encoding method that transmits bits of packets on several even smaller frequencies.</p>
<p>Secondly, if you’re indoors the WiFi signals can bounce off walls and furniture, meaning that the receiver gets several copies of the signal that each experience different times-of-flight. To identify the actual direct path, researchers developed a mechanism to algorithmically determine the delays experienced by all of these copies. From there, they can identify the path with the smallest time-of-flight as the direct path.</p>
<p>Lastly, the team’s channel-hopping approach leads to one other complication: every time Chronos hops to a new band, the hardware resets, adding a delay known as a “phase offset.” To address this the team used the fact that in WiFi, you get an acknowledgement back for each data packet that your phone sends. The team uses these acknowledgements to intelligently cancel out the phase offsets.</p>
<p>The success of Chronos suggests that WiFi-based positioning could help for other situations where there are limited or inaccessible sensors, like finding lost devices or controlling large fleets of drones.</p>
<p>“Imagine having a system like this at home that can continuously adapt the heating and cooling depending on number of people in the home and where they are” says Katabi. “Eliminating the need for cooperation between WiFi routers opens up many exciting new applications for localization.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Enabling human-robot rescue teams</title>
		<link>https://robohub.org/enabling-human-robot-rescue-teams/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Thu, 18 Feb 2016 19:40:00 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/enabling-human-robot-rescue-teams/</guid>

					<description><![CDATA[System could help prevent robots from overwhelming human teammates with information.]]></description>
										<content:encoded><![CDATA[<div id="attachment_59646" style="width: 958px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-59646" class="wp-image-59646 size-full" src="http://robohub.org/wp-content/uploads/2016/02/MIT-Human-Robot-Teamwork.jpg" alt="Credits image: Jose-Luis Olivares/MIT" width="948" height="632" srcset="https://robohub.org/wp-content/uploads/2016/02/MIT-Human-Robot-Teamwork.jpg 948w, https://robohub.org/wp-content/uploads/2016/02/MIT-Human-Robot-Teamwork-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/02/MIT-Human-Robot-Teamwork-450x300.jpg 450w" sizes="(max-width: 948px) 100vw, 948px" /><p id="caption-attachment-59646" class="wp-caption-text">Communication system could make it easier to design systems that enable humans and robots to work together in emergency-response teams. Credits image: Jose-Luis Olivares/MIT</p></div>
<p><em>By Larry Hardesty, <a href="http://news.mit.edu/2016/human-robot-rescue-teams-0217" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">MIT CSAIL</a></em></p>
<p>Autonomous robots performing a joint task send each other continual updates: “I’ve passed through a door and am turning 90 degrees right.” “After advancing 2 feet I’ve encountered a wall. I’m turning 90 degrees right.” “After advancing 4 feet I’ve encountered a wall.” And so on.</p>
<p><span id="more-59609"></span></p>
<p>Computers, of course, have no trouble filing this information away until they need it. But such a barrage of data would drive a human being crazy.</p>
<p>At the annual meeting of the Association for the Advancement of Artificial Intelligence last weekend, researchers at MIT’s <a href="http://csail.mit.edu/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Computer Science and Artificial Intelligence Laboratory</a> (CSAIL) presented a new way of modeling robot collaboration that reduces the need for communication by 60 percent. They believe that their model could make it easier to design systems that enable humans and robots to work together — in, for example, emergency-response teams.</p>
<p>“We haven’t implemented it yet in human-robot teams,” says <a href="http://people.csail.mit.edu/julie_a_shah/Welcome.html" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Julie Shah</a>, an associate professor of aeronautics and astronautics and one of the paper’s two authors. “But it’s very exciting, because you can imagine: You’ve just reduced the number of communications by 60 percent, and presumably those other communications weren’t really necessary toward the person achieving their part of the task in that team.”</p>
<p>The work could have also have implications for multirobot collaborations that don’t involve humans. Communication consumes some power, which is always a consideration in battery-powered devices, but in some circumstances, the cost of processing new information could be a much more severe resource drain.</p>
<p>In a multiagent system — the computer science term for any collaboration among autonomous agents, electronic or otherwise — each agent must maintain a model of the current state of the world, as well as a model of what each of the other agents takes to be the state of the world. These days, agents are also expected to factor in the probabilities that their models are accurate. On the basis of those probabilities, they have to decide whether or not to modify their behaviors.</p>
<h2><strong>Communication costs</strong></h2>
<p>In some scenarios, a robot’s decision to broadcast a new item of information could force its fellows to update their models and churn through all those probabilities again. If the information is inessential, broadcasting it could introduce serious delays, to no purpose. And the MIT researchers’ work suggests that 60 percent of communications in multiagent systems may be inessential.</p>
<p>The state-of-the-art method for modeling multiagent systems is called a decentralized partially observable Markov decision process, or Dec-POMDP. A Dec-POMDP factors in several types of uncertainty; not only does it consider whether an agent’s view of the world is correct and whether its estimate of its fellows’ worldviews is correct, it also considers whether any action it takes will be successful. The robot may plan, for instance, to move forward 20 feet but find that crosswinds blow it off course.</p>
<p>Dec-POMDPs generally assume some prior knowledge about the environment in which the agents will be operating. Because Shah and Vaibhav Unhelkar, a graduate student in aeronautics and astronautics and first author on the new paper, were designing a system with emergency-response applications in mind, they couldn’t make that assumption. Emergency-response teams will usually be entering unfamiliar environments, and the very nature of the emergency could render the best prior information obsolete.</p>
<p>Adding the requirement of mapping the environment on the fly, however, makes the problem of computing a multiagent plan prohibitively time consuming. So Shah and Unhelkar’s system ignores uncertainty about actions’ effectiveness and assumes that whatever an agent attempts to do, it will do.</p>
<h2><strong>Balancing act</strong></h2>
<p>When an agent acquires a new item of information — that, for instance, a given passage through a building is blocked — it has three choices: it can ignore the information; it can use it but not broadcast it; or it can use it and broadcast it.</p>
<p>Each of these choices has benefits but imposes costs. In Shah and Unhelkar’s model, communication is a cost. But if an agent incorporates new information into its own model of the world and doesn’t broadcast it, it also incurs a cost, as its worldview becomes more difficult for its fellows to estimate correctly. For every new item of information an agent acquires, Shah and Unhelkar’s system performs that cost-benefit analysis, based on the agent’s model of the world, its expectations of its fellows’ actions, and the likelihood of accomplishing the joint goal more efficiently.</p>
<p>The researchers tested their system on more than 300 computer simulations of rescue tasks in unfamiliar environments. A version of their system that permitted extensive communication completed the tasks at a rate between 2 and 10 percent higher than the version that reduced communication by 60 percent.</p>
<p>In the experiments, however, all the agents were electronic. “What I’d be willing to bet, although we have to wait until we do the human-subject experiments, is that the human-robot team will fail miserably if the system is just telling the person all sorts of spurious information all the time,” Shah says. “For human-robot teams, I think that this algorithm is going to make the difference between a team that can function effectively versus a team that just plain can’t.”</p>
<p>In a separate research project, members of Shah’s group have asked teams of human subjects to execute similar virtual rescue missions that computer systems did in the experiments reported in the new paper. Using machine-learning algorithms, the researchers have mined the results for statistics on human communication patterns, which can be incorporated into the new model to more explicitly accommodate human-robot teams.</p>
<p>“It is well-understood that in human teams, when one team member gains new information, broadcasting this new information to all team members is generally not a good solution, especially when the cost of communication is high,” says Tim Miller, an assistant professor of computing and information systems at the University of Melbourne in Australia. “This work has applications outside of multiagent systems, reaching into the critical area of human-agent collaboration, where communication can be costly, but more importantly, human team members are quickly overloaded if presented with too much information.”</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Motion-planning algorithms allow drones to make hairpin turns in a simulated &#8220;forest&#8221;</title>
		<link>https://robohub.org/motion-planning-algorithms-allow-drones-to-make-hairpin-turns-in-a-simulated-forest/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Tue, 19 Jan 2016 16:24:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[control]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[UAVs & drones]]></category>
		<guid isPermaLink="false">http://robohub.org/motion-planning-algorithms-allow-drones-to-make-hairpin-turns-in-a-simulated-forest/</guid>

					<description><![CDATA[Motion-planning algorithms from the Computer Science and Artificial Intelligence Lab allow drones to fly in dense environments and avoid dozens of objects.]]></description>
										<content:encoded><![CDATA[<div id="attachment_58812" style="width: 810px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-58812" class="size-full wp-image-58812" src="http://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor_algorithm_CSAIL.jpg" alt="In a forest simulation, algorithms segment space into “obstacle-free regions” and then link them together to find a single collision-free route. Photo courtesy of CSAIL researchers." width="800" height="533" srcset="https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor_algorithm_CSAIL.jpg 800w, https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor_algorithm_CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor_algorithm_CSAIL-450x300.jpg 450w" sizes="(max-width: 800px) 100vw, 800px" /><p id="caption-attachment-58812" class="wp-caption-text">In a forest simulation, algorithms segment space into “obstacle-free regions” and then link them together to find a single collision-free route.<br />Photo courtesy of CSAIL researchers.</p></div>
<p>Adam Conner-Simons | <a href="http://news.mit.edu/2016/csail-drones-do-donuts-figure-eights-around-obstacles-0119" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">CSAIL</a></p>
<p>Getting drones to fly around without hitting things is no small task. Obstacle-detection and motion-planning are two of computer science’s trickiest challenges, because of the complexity involved in creating real-time flight plans that avoid obstacles and handle surprises like wind and weather. In a pair of projects announced this week, researchers from MIT’s <a href="http://csail.mit.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Computer Science and Artificial Intelligence Laboratory</a> (CSAIL) demonstrated software that allow drones to stop on a dime to make hairpin movements over, under, and around some 26 distinct obstacles in a simulated “forest.”<span id="more-58785"></span></p>
<p>One team’s video shows a small quadrotor doing donuts and figure-eights through an obstacle course of strings and PVC pipes. Weighing just over an ounce and clocking in at 3 and a half inches from rotor to rotor, the drone can fly through the 10-square-foot space at speeds upwards of 1 meter per second.</p>
<div class="keep-aspect"><iframe title="Planning and Navigation for Drone Flight" width="500" height="281" src="https://www.youtube-nocookie.com/embed/dpNV-zmjvkc?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The team’s algorithms &#8212; which are <a href="http://github.com/blandry/crazyflie-tools" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">available online</a> and were previously used to plan footsteps for CSAIL’s Atlas robot at last year&#8217;s <a href="http://news.mit.edu/2015/robotics-competition-algorithms-0611" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">DARPA Robotics Challenge </a>&#8212; segment space into “obstacle-free regions” and then link them together to find a single collision-free route.</p>
<p>“Rather than plan paths based on the number of obstacles in the environment, it’s much more manageable to look at the inverse: the segments of space that are ‘free’ for the drone to travel through,” says recent graduate Benoit Landry &#8217;14 MNG &#8217;15, who was first author on a related paper just accepted to the IEEE International Conference on Robotics and Automation (ICRA). “Using free-space segments is a more ‘glass-half-full’ approach that works far better for drones in small, cluttered spaces.”</p>
<p>In a second CSAIL project, PhD student Anirudha Majumdar showed off a fixed-wing plane that is guaranteed to avoid obstacles without any advanced knowledge of the space, and even in the face of wind gusts and other dynamics. His approach was to pre-program a library of dozens of distinct “funnels” that represent the worst-case behavior of the system, calculated via a rigorous verification algorithm.</p>
<p>“As the drone flies, it continuously searches through the library to stitch together a series of paths that are computationally guaranteed to avoid obstacles,” says Majumdar, who was lead author on a related technical report. “Many of the individual funnels will not be collision-free, but with a large-enough library you can be certain that your route will be clear.”</p>
<p>Both papers were co-authored by MIT professor Russ Tedrake; the ICRA paper, which will be presented in May in Sweden, was also co-written by PhD students Robin Deits and Peter R. Florence.</p>
<p><strong>Drones in high-density </strong></p>
<p>A bird might make it seem simple, but flight is a highly complicated endeavor. A flying object can change position in six distinct directions — forward/backward (“surge”), up/down (“heave”), left/right (“sway”), and by rotating front-to-back (“pitch”), side-to-side (“roll”), and horizontally (“yaw”).</p>
<p>“At every moment in time there are 12 distinct numbers needed to describe where the system it is and how quickly it is moving, on top of simultaneously tracking other objects in the space that could get in your way,” says Majumdar. “Most techniques typically can’t handle this sort of complexity in real-time.”</p>
<p>One common motion-planning approach is to sample the whole space through algorithms like the “<a href="http://en.wikipedia.org/wiki/Rapidly_exploring_random_tree" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">rapidly-exploring random tree</a>.” Although often effective, sampling-based approaches are generally less efficient and have trouble navigating small gaps between obstacles.</p>
<p>Landry’s team opted to use Deits’ new free-space-based technique, which he calls the “Iterative Regional Inflation by semidefinite programming” algorithm (IRIS). They then coupled IRIS with a “mixed-integer semidefinite program” (MISDP) that assigns specific flight movements to each “space-free region” and then executes the full plan.</p>
<p>To sense its surroundings, the drone used motion-capture optical sensors and an on-board inertial measurement unit (IMU) that help estimate the precise positioning of obstacles.</p>
<p>“I’m most impressed by the team’s ingenious technique of combining on- and off-board sensors to determine the drone&#8217;s location,” says Jingjin Yu, an assistant professor of computer science at Rutgers University. “This is key to the system’s ability to create unique routes for each set of obstacles.&#8221;</p>
<p>In its current form, MISDP has been optimized such that it can’t do real-time planning; it takes an average of 10 minutes to create a route for the obstacle course. But Landry says that making certain sacrifices would let them generate plans much more quickly.</p>
<p>“For example, you could define ‘free-space regions’ more broadly as links between areas where two or more free-space regions overlap,” says Landry. “That would let you solve for a general motion-plan through those links, and then fill in the details with specific paths inside of the chosen regions. Currently we solve both problems at the same time to lower energy consumption, but if we wanted to run plans faster that would be a good option.”</p>
<p>Majumdar’s <a href="http://github.com/RobotLocomotion/drake/tree/master/drake/examples/Quadrotor" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">software</a>, meanwhile, generates more conservative plans, but can do so in real-time. He first developed a library of 40 to 50 trajectories that are each given an outer bound that the drone is guaranteed to remain within. These bounds can be visualized as ”funnels” that the planning algorithm chooses between to stitch together a sequence of steps that allow the drone to plan its flying on the fly.</p>
<p>A flexible approach like this comes with a high level of guarantees that the software will work, even in the face of uncertainties with both the surroundings and the hardware itself. The algorithm can easily be extended to drones of different sizes and payloads, as well as ground vehicles and walking robots.</p>
<p>As for the environment, imagine the drone choosing between making a forceful roll maneuver that will avoid a tree by a large margin, versus flying straight and avoiding a tree by a small amount.</p>
<p>“A traditional approach might prefer the first since avoiding obstacles by a significant amount seems ‘safer,’” Majumdar says. “But a move like that actually may be riskier because it’s more susceptible to wind gusts. Our method makes these decisions in real-time, which is critical if we want drones to move out of the labs and operate in real-world scenarios.”</p>
<p><strong>A clear path to avoiding obstacles</strong></p>
<div id="attachment_58817" style="width: 958px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-58817" class="size-full wp-image-58817" src="http://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor-CSAIL.jpg" alt="A planner searches a library of pre-computed funnels and selects one that doesn't intersect with the obstacles. Photo courtesy of CSAIL researchers." width="948" height="632" srcset="https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor-CSAIL.jpg 948w, https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor-CSAIL-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2016/01/MIT-Quadrotor-CSAIL-450x300.jpg 450w" sizes="(max-width: 948px) 100vw, 948px" /><p id="caption-attachment-58817" class="wp-caption-text">In a related project, a planner searches a library of pre-computed funnels and selects one that doesn&#8217;t intersect with the obstacles.<br />Photo courtesy of CSAIL researchers.</p></div>
<p>CSAIL researchers have been working on this problem for many years. Professor Nick Roy has been honing algorithms for drones to <a href="http://news.mit.edu/2012/autonomous-robotic-plane-flies-indoors-0810" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">develop maps and avoid objects in real-time</a>; in November a team led by PhD student Andrew Barry published a video demonstrating algorithms that <a href="http://www.youtube.com/watch?v=_qah8oIzCwk" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">allow a drone to dart between trees</a> at speeds of 30 miles per hour.</p>
<p>While these two drones cannot travel quite as fast as Barry’s, their maneuvers are generally more complex, meaning that they can navigate in smaller, denser environments.</p>
<p>“Enabling dynamic flight of small, off-the-shelf quadcopters is a marvelous achievement, and one that has many potential applications,” Yu says. “With additional development, I can imagine these machines being used as probes in hard-to-reach places, from exploring caves to doing search-and-rescue in collapsed buildings.”</p>
<p>Landry, who now works for <a href="http://3drobotics.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">3D Robotics</a> in California, is hopeful that other academics will build on and refine the researchers’ work, which is all open-source and available on github.</p>
<p>“A big challenge for industry is determining which technologies are actually mature enough to use in real products,” Landry says. “The best way to do that is to conduct experiments that focus on all of the corner cases and can demonstrate that algorithms like these will actually work 99.999 percent of the time.”</p>
<p>Landry&#8217;s work was partially supported by the Siebel Scholars Foundation, while Majumdar&#8217;s work was supported by a grant from the Office of Naval Research.</p>
<p class="p1"><strong><span class="s1">Papers<br />
</span></strong></p>
<ul>
<li class="p1"><span class="s1"><a href="http://groups.csail.mit.edu/robotics-center/public_papers/Landry15b.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Aggressive quadrotor flight through cluttered environments using mixed integer programming”</a></span></li>
<li class="p1"><a href="http://arxiv.org/pdf/1601.04037v1.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Funnel Libraries for Real-Time Robust Feedback Motion Planning</a></li>
</ul>
<hr class="xh2  ">
<p><i>If you liked this post, you may also be interested in:</i></p>
<ul>
<li><a title="“Shrinking bull’s-eye” algorithm speeds up complex modeling from days to hours" href="http://robohub.org/shrinking-bulls-eye-algorithm-speeds-up-complex-modeling-from-days-to-hours/" rel="bookmark" data-wpel-link="internal">“Shrinking bull’s-eye” algorithm speeds up complex modeling from days to hours</a></li>
<li><a title="Talking Machines: The Master Algorithm, with UW’s Pedro Domingos" href="http://robohub.org/talking-machines-the-master-algorithm-with-uws-pedro-domingos/" rel="bookmark" data-wpel-link="internal">The Master Algorithm, with UW’s Pedro Domingos</a></li>
<li> <a title="Quadrocopter failsafe algorithm: Recovery after propeller loss" href="http://robohub.org/quadrocopter-failsafe-algorithm-recovery-after-propeller-loss/" rel="bookmark" data-wpel-link="internal">Quadrocopter failsafe algorithm: Recovery after propeller loss</a></li>
<li><a title="‘Tailsitter’ flying robot hovers and recovers easily thanks to new algorithm" href="http://robohub.org/tailsitter-flying-robot-hovers-and-recovers-easily-thanks-to-new-algorithm/" rel="bookmark" data-wpel-link="internal">‘Tailsitter’ flying robot hovers and recovers easily thanks to new algorithm</a></li>
<li><a title="Embodied quadrotors" href="http://robohub.org/robots-embodied-quadrotors/" rel="bookmark" data-wpel-link="internal">Robots Podcast #194: Embodied quadrotors, with Davide Scaramuzza</a></li>
</ul>
<p><i>See all </i><a href="http://robohub.org/" data-wpel-link="internal"><i>the latest robotics news</i></a><i> on Robohub, or </i><a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external"><i>sign up for our weekly newsletter</i></a><i>.</i></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>From pencil and paper to hands-on making, a brief history of MIT&#8217;s legendary MechE 2.007</title>
		<link>https://robohub.org/from-pencil-and-paper-to-hands-on-making-a-brief-history-of-mits-legendary-meche-2-007/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Wed, 16 Dec 2015 20:19:01 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<category><![CDATA[opinions]]></category>
		<category><![CDATA[competitions]]></category>
		<category><![CDATA[history of robotics]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/from-pencil-and-paper-to-hands-on-making-a-brief-history-of-mits-legendary-meche-2-007/</guid>

					<description><![CDATA[Since the 1970s, Department of Mechanical Engineering course 2.007 has introduced undergraduate students to hands-on designing and building.]]></description>
										<content:encoded><![CDATA[<div id="attachment_57844" style="width: 910px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-57844" class="size-full wp-image-57844" src="http://robohub.org/wp-content/uploads/2015/12/mit-mechanical-engineering-2.70-1979_0.jpg" alt="An excited crowd cheers for students in 2.70 (the precursor of 2.007) as they compete in the final competition in 1979. Photo courtesy of the MIT Museum." width="900" height="600" srcset="https://robohub.org/wp-content/uploads/2015/12/mit-mechanical-engineering-2.70-1979_0.jpg 900w, https://robohub.org/wp-content/uploads/2015/12/mit-mechanical-engineering-2.70-1979_0-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2015/12/mit-mechanical-engineering-2.70-1979_0-450x300.jpg 450w" sizes="(max-width: 900px) 100vw, 900px" /><p id="caption-attachment-57844" class="wp-caption-text">An excited crowd cheers for students in 2.70 (the precursor of 2.007) as they compete in the final competition in 1979. Photo courtesy of the MIT Museum.</p></div>
<p>Alissa Mallinson | <a href="http://news.mit.edu/2015/mechanical-engineering-rite-of-passage-1215" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Department of Mechanical Engineering</a></p>
<p>It&#8217;s hard to ignore the fact that a worldwide maker movement is well underway. Over the past 10 or so years, community Maker Faires have become all the rage; fabrication shops have popped up around the world for both professionals and hobbyists; and websites, tools, and toys catering to do-it-yourselfers are on the rise.<span id="more-57810"></span></p>
<p>It’s easy to appreciate how a love for making became wildly popular again, especially as STEAM (science, technology, engineering, art, and math) is increasingly and passionately promoted and embraced around the world.</p>
<p>Of course, at MIT — particularly in the Department of Mechanical Engineering (MechE) — it’s been this way since 1865.</p>
<p>It was around that time that MIT was founded by scientist and educator William Barton Rogers, who had a different idea about how to educate and learn. He founded MIT to teach not only the ability to think critically but also how to apply that thinking to real-world problems — to teach craftsmen and farmers as well as engineers and academics. From that moment on, it’s been in MechE DNA to upend traditional ways of teaching and to democratize science and technology for the betterment of all.</p>
<p>So the motto was coined (“mens et manus,” or “mind and hand”), the seal was drawn (the scholar and the smith), and by the 1970s, when Professor Emeritus Woodie Flowers was transforming course 2.70 — now 2.007 (Design and Manufacturing) — into a project-based, get-your-hands-dirty, build-competition experience, MechE’s reputation for innovative education was already solidified. Yet the magnitude of transforming a design and manufacturing class from a mostly pencil-and-paper experience to one of fun and hands-on building was a profound paradigm shift in engineering education.</p>
<div class="keep-aspect"><iframe title="The Birth of a Hands-On Education" width="500" height="281" src="https://www.youtube-nocookie.com/embed/dDbPwLODAx0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Knowledge is of course essential, Flowers says, because uninformed imagination can be quite dangerous, but at the same time, “nobody is getting hired to solve the multiple-choice problems at the end of the chapter.”</p>
<p>He created a class to prepare students not only to design an object but also to build it. From the beginning, 2.007 was meant to develop students’ competence and self-confidence as design engineers, while emphasizing the creative design process and the application of physical laws.</p>
<p>“I learned from my father that doing things in a different way was often fruitful, and the underpinnings of all my educational efforts is to allow people a path to change their self-image,” Flowers says. “Students might struggle with equations and other rigorous elements of an MIT education, but in 2.007 they can be superstars.”</p>
<p>The first challenges were purely mechanical traps and contraptions, using a universal set of materials pre-determined by Flowers, and the students loved it. Their creations went head-to-head at end-of-year competitions that became the most attended events at the Institute.</p>
<p>Since then, several faculty members have followed in Flowers’ footsteps as instructor of 2.70/2.007, including Professor Emeritus David Gordon; Wilson; former Professor Harry West; Professor Alex Slocum; and Professor Dan Frey, each imbuing the class with a bit of their own style and personality. Along the way, the contraption competition became a robot competition, mechanical components became electromechanical ones, wires became remote controllers, and autonomous challenges were introduced.</p>
<p>And yet, says Assistant Professor Amos Winter, “The fundamental principles of 2.007 haven’t changed. Because core mechanical principles like forces, energy, bearings, and shafts work the same as they always have and haven’t gone out of style. Whether a car uses internal combustion or is a hybrid, it still comes down to transferring power to the road.”</p>
<p>In 2013, Professor Dan Frey passed the torch to Associate Professor Sangbae Kim and Winter, who are co-instructing the class. Kim is a renowned expert in biomimetics and robotics, and Winter is a leader in designing technologies for developing and emerging markets. Together the two have made several curriculum updates to the class, including eliminating exams and adding weekly written homework, weekly physical homework, and an oral design review.</p>
<p>As is the tradition now, the class ends in a final robot competition in which students compete against each other to see whose robot can win the most points. Each student is required to enter the competition, but only 32 finalists will enter the ring on competition day.</p>
<p>“The most exciting thing about 2.007 is that the students get to build their own personal robot and compete in front of an audience of more than 500 people,” Kim says. “We create a new theme every year, having in mind a particular physical task that will require the students to apply the theories they’ve learned to specific engineering functions and transfer their knowledge from paper to working robot.&#8221;</p>
<p>This spring&#8217;s competition was called “Hack to the Future,” a nod to the classic film “Back to the Future,” which had its 30th anniversary this fall. Using a universal kit of tools and materials, students were challenged to build a robot that could collect plutonium, climb the Clock Tower, slide Doc Brown down a cable, and open a DeLorean door. As always students each developed their own strategies for gaining points, and the student whose robot earned the most points at the end of each duel progressed to the next round until there was only one champion left standing: Alison Edwards, whose robot was efficient and reliable.</p>
<p>“I hope students in 2.007 walk away from the class with engineering intuition,” Winter says. “I want them to go out into the world around them and almost have a kind of superpower — to see what’s going on behind face value, like forces, and stresses, and energy transfer. It’s that kind of intuition that we try to build by bringing real-world examples into the classroom and showing them how to match theory with what actually happens.”</p>
<hr class="xh2  ">
<p><i>If you liked this article, you may also be interested in:</i></p>
<ul>
<li><a title="Talking Machines: History of machine learning, w. Geoffrey Hinton, Yoshua Bengio, Yann LeCun" href="http://robohub.org/talking-machines-history-of-machine-learning-w-geoffrey-hinton-yoshua-bengio-yann-lecun/" rel="bookmark" data-wpel-link="internal">Talking Machines: History of machine learning, w. Geoffrey Hinton, Yoshua Bengio, Yann LeCun</a></li>
<li><a title="NSF’s 40-year history supporting US robotics research" href="http://robohub.org/nsfs-40-year-history-supporting-us-robotics-research/" rel="bookmark" data-wpel-link="internal">NSF’s 40-year history supporting US robotics research</a></li>
<li><a title="The evolution of assembly lines: A brief history" href="http://robohub.org/the-evolution-of-assembly-lines-a-brief-history/" rel="bookmark" data-wpel-link="internal">The evolution of assembly lines: A brief history</a></li>
<li><a title="Funding high risk proposals at the National Science Foundation: A brief history" href="http://robohub.org/funding-high-risk-proposals-at-the-national-science-foundation-a-brief-history/" rel="bookmark" data-wpel-link="internal">Funding high risk proposals at the National Science Foundation: A brief history</a></li>
<li><a title="Father of robotics Joseph F. Engelberger dies at age 90" href="http://robohub.org/father-of-robotics-joseph-f-engelberger-dies-at-age-90/" rel="bookmark" data-wpel-link="internal">Father of robotics Joseph F. Engelberger dies at age 90</a></li>
</ul>
<p><i>See all </i><a href="http://robohub.org/" data-wpel-link="internal"><i>the latest robotics news</i></a><i> on Robohub, or </i><a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external"><i>sign up for our weekly newsletter</i></a><i>.</i></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>CSAIL shows off demos to 150 high-schoolers for “Hour of Code”</title>
		<link>https://robohub.org/csail-shows-off-demos-to-150-high-schoolers-for-hour-of-code/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Tue, 15 Dec 2015 19:55:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[events]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[STEM]]></category>
		<guid isPermaLink="false">http://robohub.org/csail-shows-off-demos-to-150-high-schoolers-for-hour-of-code/</guid>

					<description><![CDATA[Robots, 3-D printers, and a surprise guest aim to get students excited about computer science.]]></description>
										<content:encoded><![CDATA[<div id="attachment_57798" style="width: 1010px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-57798" class="size-full wp-image-57798" src="http://robohub.org/wp-content/uploads/2015/12/CSAIL_MIT_Hour_of_Code.jpg" alt="Students watch CSAIL researchers show off a &quot;garden&quot; made of dozens of distinct origami robots that move and change color to demonstrate complex programming algorithms. Photo: Jason Dorfman/CSAIL" width="1000" height="667" srcset="https://robohub.org/wp-content/uploads/2015/12/CSAIL_MIT_Hour_of_Code.jpg 1000w, https://robohub.org/wp-content/uploads/2015/12/CSAIL_MIT_Hour_of_Code-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2015/12/CSAIL_MIT_Hour_of_Code-450x300.jpg 450w" sizes="(max-width: 1000px) 100vw, 1000px" /><p id="caption-attachment-57798" class="wp-caption-text">Students watch CSAIL researchers show off a &#8220;garden&#8221; made of dozens of distinct origami robots that move and change color to demonstrate complex programming algorithms. Photo: Jason Dorfman/CSAIL</p></div>
<p>By Adam Conner-Simmons | <a href="http://news.mit.edu/2015/csail-shows-demos-150-high-schoolers-hour-code-1214" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">CSAIL </a></p>
<p>Last Friday, MIT&#8217;s Computer Science and Artificial Intelligence Laboratory (CSAIL) hosted 150 local high school students for its second annual “Hour of Code” event, tied to the international initiative focused on getting kids interested in programming.<span id="more-57746"></span></p>
<p>Researchers showed off robots, 3-D-printing technology, and other projects to math and computer science students from schools throughout the greater Boston area, including Cambridge, Charlestown, Roxbury, and Somerville.</p>
<p>The event also included a surprise video message from John Green, author of the bestselling young-adult novels-turned-movies “The Fault In Our Stars” and “Papertowns.” Green commended the students on participating the event and elaborated on why coding is important.</p>
<p>“I cannot emphasize enough how much I believe in learning computer science, not least because I am basically a first-grader when it comes to computer literacy,” Green said. “These days STEM education is vital to being able to understand the world around us and interact with it effectively.”</p>
<p>Among the projects on display were “<a href="http://news.mit.edu/2015/multifab-3-d-print-10-materials-0824" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MultiFab</a>,” a 3-D-printer that can print using a record 10 different materials at once; Atlas, a 6-foot-tall, 400-pound humanoid robot that can open doors, climb stairs and drive a car; and a wireless device that can <a href="http://www.csail.mit.edu/RF_capture" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">detect, track and identify individuals</a> from the other side of a wall.</p>
<p>CSAIL Director Daniela Rus kicked off the event by inviting three graduate students to speak about how they got involved in programming and why coding is fun, exciting, and important.</p>
<p>&#8220;I like to think being able to code is sort of like having a superpower,” Rus said. “Researchers here can see through walls with wireless, create objects that nobody would have ever thought possible, and develop robots that shape-shift like Transformers and fly through trees at 30 miles per hour.”</p>
<p>To date approximately 150 million students have done an hour of programming as part of the Hour of Code, which was launched in 2013 by the organization <a href="http://code.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">code.org</a> and takes place during Computer Science Education Week. Companies such as Apple and Microsoft have also jumped onboard with special programs, while last year U.S. President Barack Obama became the <a href="http://www.wired.com/2014/12/obama-becomes-first-president-write-computer-program/?mbid=social_fb" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">first sitting president to write a line of code</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>NASA gives MIT a humanoid robot to develop software for future space missions</title>
		<link>https://robohub.org/nasa-gives-mit-a-humanoid-robot-to-develop-software-for-future-space-missions/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Wed, 18 Nov 2015 16:56:01 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[DRC]]></category>
		<category><![CDATA[humanoids]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[NASA]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[space]]></category>
		<guid isPermaLink="false">http://robohub.org/nasa-gives-mit-a-humanoid-robot-to-develop-software-for-future-space-missions/</guid>

					<description><![CDATA[Team led by Professor Russ Tedrake of CSAIL to develop algorithms for 6-foot-tall &#8220;Valkyrie&#8221; robot to travel to Mars and beyond.]]></description>
										<content:encoded><![CDATA[<div id="attachment_56506" style="width: 930px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-56506" class="size-full wp-image-56506" src="http://robohub.org/wp-content/uploads/2015/11/valkyrie-robot-NASA.jpg" alt="NASA's &quot;Valkyrie&quot; robot is 6 feet tall and weighs 290 pounds. Researchers at MIT's Computer Science and Artificial Intelligence Laboratory will test and develop the bot for future space missions. Photo: NASA" width="920" height="526" srcset="https://robohub.org/wp-content/uploads/2015/11/valkyrie-robot-NASA.jpg 920w, https://robohub.org/wp-content/uploads/2015/11/valkyrie-robot-NASA-425x243.jpg 425w, https://robohub.org/wp-content/uploads/2015/11/valkyrie-robot-NASA-175x100.jpg 175w, https://robohub.org/wp-content/uploads/2015/11/valkyrie-robot-NASA-500x286.jpg 500w" sizes="(max-width: 920px) 100vw, 920px" /><p id="caption-attachment-56506" class="wp-caption-text">NASA&#8217;s &#8220;Valkyrie&#8221; robot is 6 feet tall and weighs 290 pounds. Researchers at MIT&#8217;s Computer Science and Artificial Intelligence Laboratory will test and develop the bot for future space missions. Photo: NASA</p></div>
<p><em>By Adam Conner-Simons, <a href="http://news.mit.edu/2015/nasa-gives-mit-humanoid-robot-future-space-missions-1117" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT CSAIL</a></em></p>
<p>NASA <a href="https://www.nasa.gov/press-release/nasa-awards-two-robots-to-university-groups-for-rd-upgrades" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">announced</a> yesterday that MIT’s <a href="http://csail.mit.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Computer Science and Artificial Intelligence Laboratory</a> (CSAIL) is one of two university research groups nationwide that will receive a 6-foot, 290-pound humanoid robot to test and develop for future space missions to Mars and beyond.<span id="more-56487"></span></p>
<p>A group led by CSAIL principal investigator <a href="https://groups.csail.mit.edu/locomotion/russt.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Russ Tedrake</a> will develop algorithms for the robot, known as “Valkyrie” or “R5,” as part of NASA’s upcoming Space Robotics Challenge, which aims to create more dexterous autonomous robots that can help or even take the place of humans “extreme space” missions. (NASA’s challenge is divided into a virtual competition using robotic simulations, and a physical competition using the robot.)</p>
<p>Tedrake’s team, which was selected from groups that were entered in this year’s Defense Advanced Research Projects Agency (DARPA) Robotics Challenge, will receive as much as $250,000 a year for two years from NASA’s Space Technology Mission Directive.</p>
<p><strong>Exploring deep space by bot</strong></p>
<p>NASA says it is interested in humanoid robots because they can help or even replace astronauts working in extreme space environments. Robots like R5 could be used in future missions either as precursor robots performing mission tasks before humans arrive or as human-assistive robots collaborating with the human crew. While R5 was initially designed to complete disaster-relief maneuvers, its main goal is now to prove itself worthy of even trickier terrain: deep-space exploration.</p>
<p>“Advances in robotics, including human-robotic collaboration, are critical to developing the capabilities required for our journey to Mars,” said Steve Jurczyk, associate administrator for the Space Technology Mission Directorate (STMD) at NASA Headquarters in Washington, in a NASA press release. “We are excited to engage these university research groups to help NASA with this next big step in robotics technology development.”</p>
<p><strong>Autonomy for autos, robots and more</strong></p>
<p>As head of CSAIL’s <a href="http://groups.csail.mit.edu/locomotion/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Robot Locomotion Group</a>, Tedrake has extensive experience with autonomous robots. Over the past three years he led a team of more than 20 researchers to develop algorithms for a government competition to get another 6-foot-tall humanoid robot named Atlas to open doors, turn valves, drill holes, climb stairs, scramble over cinder blocks, and drive a car — all in the space of one hour.</p>
<p>Tedrake is also part of CSAIL’s new $25 million Toyota-funded research center for autonomous cars, specifically focused on advanced decision-making algorithms and systems that allow vehicles to perceive and navigate their surroundings safely, without human input. The larger collaboration will be coordinated by Gill Pratt PhD ’89, a former MIT professor who most recently served as program director at DARPA’s Defense Sciences Office.</p>
<p>In addition to Tedrake’s team at CSAIL, NASA also awarded a R5 robot to a team led by Taskin Padir at Northeastern University.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>“Shrinking bull’s-eye” algorithm speeds up complex modeling from days to hours</title>
		<link>https://robohub.org/shrinking-bulls-eye-algorithm-speeds-up-complex-modeling-from-days-to-hours/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Tue, 17 Nov 2015 15:12:29 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[Algorithm]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[modeling]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/shrinking-bulls-eye-algorithm-speeds-up-complex-modeling-from-days-to-hours/</guid>

					<description><![CDATA[Jennifer Chu &#124; MIT News Office  To work with computational models is to work in a world of unknowns: Models that simulate complex physical processes — from Earth’s changing climate to the performance of hypersonic combustion engines — are staggeringly complex, sometimes incorporating hundreds of parameters, each of which describes a piece of the larger [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_56456" style="width: 649px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-56456" class="size-full wp-image-56456" src="http://robohub.org/wp-content/uploads/2015/11/MIT_Modeling_Unknown_Data_Weather_Forecasting_Algorithm_Parameters.jpg" alt="Stills from the Weather Research and Forecasting Model. Image: Wikipedia/Almoz" width="639" height="426" srcset="https://robohub.org/wp-content/uploads/2015/11/MIT_Modeling_Unknown_Data_Weather_Forecasting_Algorithm_Parameters.jpg 639w, https://robohub.org/wp-content/uploads/2015/11/MIT_Modeling_Unknown_Data_Weather_Forecasting_Algorithm_Parameters-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2015/11/MIT_Modeling_Unknown_Data_Weather_Forecasting_Algorithm_Parameters-450x300.jpg 450w" sizes="(max-width: 639px) 100vw, 639px" /><p id="caption-attachment-56456" class="wp-caption-text">Stills from the Weather Research and Forecasting Model. Image: Wikipedia/Almoz</p></div>
<div style="clear:both"></div>
<p><em>Jennifer Chu | </em><a href="http://news.mit.edu/2015/shrinking-bulls-eye-algorithm-speeds-complex-modeling-days-hours-1116" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><em>MIT News Office</em> </a></p>
<p>To work with computational models is to work in a world of unknowns: Models that simulate complex physical processes — from Earth’s changing climate to the performance of hypersonic combustion engines — are staggeringly complex, sometimes incorporating hundreds of parameters, each of which describes a piece of the larger process.<span id="more-56455"></span></p>
<p>Parameters are often question marks within their models, their contributions to the whole largely unknown. To estimate the value of each unknown parameter requires plugging in hundreds, if not thousands, of values, and running the model each time to narrow in on an accurate value — a computation that can take days, and sometimes weeks.</p>
<p>Now MIT researchers have developed a new algorithm that vastly reduces the computation of virtually any computational model. The algorithm may be thought of as a shrinking bull’s-eye that, over several runs of a model, and in combination with some relevant data points, incrementally narrows in on its target: a probability distribution of values for each unknown parameter.</p>
<p>With this method, the researchers were able to arrive at the same answer as a classic computational approaches, but 200 times faster.</p>
<p>Youssef Marzouk, an associate professor of aeronautics and astronautics, says the algorithm is versatile enough to apply to a wide range of computationally intensive problems.</p>
<p>“We’re somewhat flexible about the particular application,” Marzouk says. “These models exist in a vast array of fields, from engineering and geophysics to subsurface modeling, very often with unknown parameters. We want to treat the model as a black box and say, ‘Can we accelerate this process in some way?’ That’s what our algorithm does.”</p>
<p>Marzouk and his colleagues — recent PhD graduate Patrick Conrad, Natesh Pillai from Harvard University, and Aaron Smith from the University of Ottawa — have published their findings this week in the <em>Journal of the American Statistical Association.</em></p>
<p><strong>Modeling “Monopoly”</strong></p>
<p>In working with complicated models involving multiple unknown parameters, computer scientists typically employ a technique called Markov chain Monte Carlo (MCMC) analysis — a statistical sampling method that is often explained in the context of the board game “Monopoly.”</p>
<p>To plan out a monopoly, you want to know which properties players land on most often — essentially, an unknown parameter. Each space on the board has a probability of being landed on, determined by the rules of the game, the positions of each player, and the roll of two dice. To determine the probability distribution on the board — the range of chances each space has of being landed on — you could roll the die hundreds of times.</p>
<p>If you roll the die enough times, you can get a pretty good idea of where players will most likely land. This, essentially, is how an MCMC analysis works: by running a model over and over, with different inputs, to determine a probability distribution for one unknown parameter. For more complicated models involving multiple unknowns, the same method could take days to weeks to compute an answer.</p>
<p><strong>Shrinking bull’s-eye</strong></p>
<p>With their new algorithm, Marzouk and his colleagues aim to significantly speed up the conventional sampling process.</p>
<p>“What our algorithm does is short-circuits this model and puts in an approximate model,” Marzouk explains. “It may be orders of magnitude cheaper to evaluate.”</p>
<p>The algorithm can be applied to any complex model to quickly determine the probability distribution, or the most likely values, for an unknown parameter. Like the MCMC analysis, the algorithm runs a given model with various inputs — though sparingly, as this process can be quite time-consuming. To speed the process up, the algorithm also uses relevant data to help narrow in on approximate values for unknown parameters.</p>
<p>In the context of “Monopoly,” imagine that the board is essentially a three-dimensional terrain, with each space represented as a peak or valley. The higher a space’s peak, the higher the probability that space is a popular landing spot. To figure out the exact contours of the board — the probability distribution — the algorithm rolls the die at each turn and alternates between using the computationally expensive model and the approximation. With each roll of the die, the algorithm refers back to the relevant data and any previous evaluations of the model that have been collected.</p>
<p>At the beginning of the analysis, the algorithm essentially draws large, vague bull’s-eyes over the board’s entire terrain. After successive runs with either the model or the data, the algorithm’s bull’s-eyes progressively shrink, zeroing in on the peaks in the terrain — the spaces, or values, that are most likely to represent the unknown parameter.</p>
<p><strong>“Outside the normal”</strong></p>
<p>The group tested the algorithm on two relatively complex models, each with a handful of unknown parameters. On average, the algorithm arrived at the same answer as each model, but 200 times faster.</p>
<p>“What this means in the long run is, things that you thought were not tractable can now become doable,” Marzouk says. “For an intractable problem, if you had two months and a huge computer, you could get some answer, but you would not necessarily know how accurate it was. Now for the first time, we can say that if you run our algorithm, you can guarantee that you’ll find the right answer, and you might be able to do it in a day. Previously that guarantee was absent.”</p>
<p>Marzouk and his colleagues have applied the algorithm to a complex model for simulating movement of sea ice in Antarctica, involving 24 unknown parameters, and found that the algorithm is 60 times faster arriving at an estimate than current methods. He plans to test the algorithm next on models of combustion systems for supersonic jets.</p>
<p>“This is a super-expensive model for a very futuristic technology,” Marzouk says. “There might be hundreds of unknown parameters, because you’re operating outside the normal regime. That’s exciting to us.”</p>
<p>This research was supported, in part, by the Department of Energy.</p>
<p><em><span class="s1">Reprinted with permission of <a class="ext-link" title="" href="http://reprinted%20with%20permission%20of%20mit%20news%22%20and%20a%20link%20to%20the%20mit%20news%20homepage%20%28http//newsoffice.mit.edu/);" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">MIT News.</a></span></em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Artificial whisker reveals source of harbor seal’s uncanny prey-sensing ability</title>
		<link>https://robohub.org/artificial-whisker-reveals-source-of-harbor-seals-uncanny-prey-sensing-ability/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Thu, 22 Oct 2015 19:01:59 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[bio-inspired]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[sensing]]></category>
		<guid isPermaLink="false">http://robohub.org/artificial-whisker-reveals-source-of-harbor-seals-uncanny-prey-sensing-ability/</guid>

					<description><![CDATA[Study finds a whisker&#8217;s &#8220;slaloming&#8221; motion helps seals track and chase prey.]]></description>
										<content:encoded><![CDATA[<p><em><img decoding="async" class="aligncenter size-full wp-image-55556" src="http://robohub.org/wp-content/uploads/2015/10/Seal-whisker-inspired-Sensing-YouTube.jpg" alt="Seal-whisker-inspired-Sensing---YouTube" width="1000" height="497" srcset="https://robohub.org/wp-content/uploads/2015/10/Seal-whisker-inspired-Sensing-YouTube.jpg 1000w, https://robohub.org/wp-content/uploads/2015/10/Seal-whisker-inspired-Sensing-YouTube-425x211.jpg 425w, https://robohub.org/wp-content/uploads/2015/10/Seal-whisker-inspired-Sensing-YouTube-500x249.jpg 500w" sizes="(max-width: 1000px) 100vw, 1000px" />by Jennifer Chu | <a href="http://news.mit.edu/2015/whisker-slaloming-harbor-seal-catch-prey-1016" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT News Office</a> </em></p>
<p>Harbor seals have an amazingly fine-tuned sense for detecting prey, as marine biologists have noted for years. Even when blindfolded, trained seals are able to chase the precise path of an object that swam by 30 seconds earlier. Scientists have suspected that the seal’s laser-like tracking ability is due in part to its antennae-like whiskers.<span id="more-55453"></span></p>
<p>Now engineers at MIT have fabricated and tested a large-scale model of a harbor seal’s whisker, and identified a mechanism that may explain how seals sense their environment and track their prey.</p>
<div class="keep-aspect"><iframe title="Seal-whisker-inspired Sensing" width="500" height="281" src="https://www.youtube-nocookie.com/embed/FE9U0b2fjOA?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>The team found that a seal’s whiskers serve two main functions in sensing the environment: first remaining still in response to a seal’s own movements through the water, and then oscillating in a “slaloming” motion in response to the turbulence left by a moving object.</p>
<p>In their experiments, the researchers observed that once the fabricated whisker enters the wake left by a passing object, it starts vibrating at the same frequency as the wake’s passing vortices. Careful visualizations show that the whisker “slaloms” among the vortices, like a skier zigzagging between flags.</p>
<p>The research shows that this slaloming allows the whisker to extract energy from the wake, causing it to vibrate at the precise frequency of the wake — a mechanism that may give seals a clue to an object’s path, its size, and even its shape.</p>
<p>Michael Triantafyllou, the William I. Koch Professor in MIT’s Department of Mechanical Engineering, says that biologically inspired sensors, modeled after the harbor seal’s whiskers, may aid underwater vehicles in tracking schools of fish, as well as sources of pollution — a goal that he is currently working toward.</p>
<p>He and former graduate student Heather Beem, whose PhD thesis formed the basis of the work, have published their results in the <em>Journal of Fluid Mechanics.</em></p>
<div class="cms-placeholder-content-video"></div>
<p><strong>A “quieting effect”</strong></p>
<p>The harbor seal’s whiskers are unique in shape: Even to the naked eye, an individual whisker appears not uniform, but wavy. Under a magnifying glass, the pattern is more intricate, with an elliptical cross-section that varies in size along its span.</p>
<p>“It’s marvelous to see this intricate pattern, it’s not just a straight antenna — it’s a perfect sinusoid,” Triantafyllou says.</p>
<p>He and Beem proposed that a whisker’s curiously geometric morphology may play a part in a seal’s exceptional sensitivity.</p>
<p>Using 3-D printing techniques, Beem reproduced the seal’s wavy morphology at a much larger scale, in order to accurately measure its response to various wakes. She tested the whisker’s vibration properties in a 30-meter-long tank of water with a moving track suspended above the water.</p>
<p>In her experiments, Beem first attached the artificial whisker to the moving track, allowing the whisker to freely vibrate in the water as it moved down the length of the tank.</p>
<p>While most long, thin rods tend to create large vortices, or eddies, as they move through water, forming a pattern that’s well-known in fluid mechanics, Beem found that the wavy pattern of the whisker’s geometry created much weaker vortices, enabling the whisker to move silently, with very little vibration, through the water.</p>
<p>The whisker’s morphology, the researchers found, may help the seal block out its own disturbance as it moves through water.</p>
<p>“It’s like having the ability to stick your head out of a car window, and have there be no noise, so that your ears don’t ring: It’s a quieting effect,” Triantafyllou says.</p>
<p><strong>A whisker sensor</strong></p>
<p>To test how a whisker reacts to external stimuli, Beem conducted a second set of experiments in which she attached a large, long circular cylinder ahead of the whisker. As the cylinder moved down the tank, it created large eddies, similar to the patterns generated by a passing fish.</p>
<p>In response, she found that the whisker, when following the cylinder, vibrated significantly, moving in a slaloming pattern among the wake vortices. As she varied the speed of the moving track, the whisker quickly adapted, vibrating at precisely the frequency of the cylinder’s changing vortices.</p>
<p>“The geometry of the whisker allows for this phenomenon of being able to move very silently through the water if the water’s calm, and extract energy from the fish’s wake in order to vibrate a lot,” Beem says. “Now we have an idea of how it’s possible that seals can find fish that they can’t see.”</p>
<p>Triantafyllou says artificial whiskers may be useful as low-power sensors for underwater vehicles.</p>
<p>“We already have a few sensors that can detect velocity, but now that we know better what they can do, we can use them to track sources of pollution and the like,” Triantafyllou says. “By having several whiskers on a vehicle, like the seal, you can, for example, detect a faraway plume, and track it all the way to the end.”</p>
<p>This research was supported in part by the Office of Naval Research, the Singapore-MIT Alliance for Research and Technology, and the MIT Sea Grant program.</p>
<p><em><span class="s1">Reprinted with permission of <a class="ext-link" title="" href="http://reprinted%20with%20permission%20of%20mit%20news%22%20and%20a%20link%20to%20the%20mit%20news%20homepage%20%28http//newsoffice.mit.edu/);" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external">MIT News.</a></span></em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Should cars be fully driverless? No, says MIT engineer and historian David Mindell</title>
		<link>https://robohub.org/should-cars-be-fully-driverless-no-says-mit-engineer-and-historian-david-mindell/</link>
		
		<dc:creator><![CDATA[MIT News]]></dc:creator>
		<pubDate>Thu, 15 Oct 2015 21:07:10 +0000</pubDate>
				<category><![CDATA[opinions]]></category>
		<category><![CDATA[automotive]]></category>
		<category><![CDATA[books]]></category>
		<category><![CDATA[HRI]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[politics]]></category>
		<guid isPermaLink="false">http://robohub.org/should-cars-be-fully-driverless-no-says-mit-engineer-and-historian-david-mindell/</guid>

					<description><![CDATA[by Peter Dizikes &#124; MIT News Office If you follow technology news — or even if you don’t — you have probably heard that numerous companies have been trying to develop driverless cars for a decade or more. These fully automated vehicles could potentially be safer than regular cars, and might add various efficiencies to [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_55174" style="width: 958px" class="wp-caption aligncenter"><a href="http://www.amazon.com/gp/product/0525426973/ref=as_li_qf_sp_asin_il_tl?ie=UTF8&amp;camp=1789&amp;creative=9325&amp;creativeASIN=0525426973&amp;linkCode=as2&amp;tag=therobpod-20&amp;linkId=5MH466TFXFYHIIDP" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"><img decoding="async" aria-describedby="caption-attachment-55174" class="wp-image-55174 size-full" src="http://robohub.org/wp-content/uploads/2015/10/MIT-OurRobots_Our_Selves_David_Mindell.jpg" alt="MIT-OurRobots_Our_Selves_David_Mindell" width="948" height="632" srcset="https://robohub.org/wp-content/uploads/2015/10/MIT-OurRobots_Our_Selves_David_Mindell.jpg 948w, https://robohub.org/wp-content/uploads/2015/10/MIT-OurRobots_Our_Selves_David_Mindell-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2015/10/MIT-OurRobots_Our_Selves_David_Mindell-450x300.jpg 450w" sizes="(max-width: 948px) 100vw, 948px" /></a><p id="caption-attachment-55174" class="wp-caption-text">David Mindell and the cover of “<a href="http://www.amazon.com/gp/product/0525426973/ref=as_li_qf_sp_asin_il_tl?ie=UTF8&amp;camp=1789&amp;creative=9325&amp;creativeASIN=0525426973&amp;linkCode=as2&amp;tag=therobpod-20&amp;linkId=5MH466TFXFYHIIDP" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Our Robots, Ourselves</a>” (Viking/Penguin). Photo (Mindell): Len Rubenstein</p></div>
<p><em>by Peter Dizikes | <a href="http://news.mit.edu/2015/no-driverless-cars-1013" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT News Office</a> </em></p>
<p>If you follow technology news — or even if you don’t — you have probably heard that numerous companies have been trying to develop driverless cars for a decade or more. These fully automated vehicles could potentially be safer than regular cars, and might add various efficiencies to our roads, like smoother-flowing traffic.</p>
<p>Or so it is often claimed. But the promise of artificial intelligence, advanced sensors, and self-driving cars could be achieved without full autonomy, argue scholars with deep expertise in automation and technology — including David Mindell, an MIT professor and author of a new book on the subject.<span id="more-55173"></span></p>
<p>If robotics in extreme environments are any guide, Mindell says, self-driving cars should not be fully self-driving. That idea, he notes, is belied by decades of examples involving spacecraft, underwater exploration, air travel, and more. In each of those spheres, fully automated vehicles have frequently been promised, yet the most state-of-the-art products still have a driver or pilot somewhere in the network. This is one reason Mindell thinks cars are not on the road to complete automation.</p>
<p>“That’s just proven to be a loser of an approach in a lot of other domains,” Mindell says. “I’m not arguing this from first principles. There are 40 years’ worth of examples.”</p>
<p>Now Mindell, the Frances and David Dibner Professor of the History of Engineering and Manufacturing in MIT’s Program in Science, Technology, and Society, and also a professor in MIT’s Department of Aeronautics and Astronautics, has detailed the history in his new book, “<a href="http://www.amazon.com/gp/product/0525426973/ref=as_li_qf_sp_asin_il_tl?ie=UTF8&amp;camp=1789&amp;creative=9325&amp;creativeASIN=0525426973&amp;linkCode=as2&amp;tag=therobpod-20&amp;linkId=5MH466TFXFYHIIDP" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Our Robots, Ourselves</a>,” released on Oct. 13 by Viking Books.</p>
<p>To be clear, Mindell thinks that “it’s reasonable to hope” that technology will help cars “reduce the workload” of drivers in incremental ways in the future. But total automation, he thinks, is not the logical endpoint of vehicle development.</p>
<p>“The book is about a different idea of progress,” Mindell says. “There’s an idea that progress in robotics leads to full autonomy. That may be a valuable idea to guide research … but when automated and autonomous systems get into the real world, that’s not the direction they head. We need to rethink the notion of progress, not as progress toward full autonomy, but as progress toward trusted, transparent, reliable, safe autonomy that is fully interactive: The car does what I want it to do, and only when I want it to do it.”</p>
<p><strong>Shooting for the “perfect 5”</strong></p>
<p>To see why Mindell thinks history shows us that automation is not the endpoint of vehicular development, consider the case of undersea exploration. For decades, engineers and scientists thought that fully automated submersibles would be a step forward from the seemingly risky work of deep-sea journeys.</p>
<p>Instead, something unexpected happened with submersibles: Technological progress, including improved communications technologies, made it less useful to have fully automated vehicles sweeping across the sea floor. Instead, Mindell notes, submersibles “are more effective when they have even a little communication” with people monitoring and controlling them.</p>
<p>Or consider the Apollo program, which put U.S. astronauts on the moon six different times. Originally, Mindell notes, the expectation was that moon missions would be fully automated, with astronauts nothing more than passengers. But in the end — and partly due to the feedback of the astronauts themselves — astronauts handled many critical functions, including the moon landings.</p>
<p>“The sophistication of the computer and the software was used not to push people out, but to give them true control over the landing,” Mindell says.</p>
<p>And then there are airplanes. Commercial airliners do have many automated systems, such as cruise control-type features and even systems that can automate landings in certain circumstances. But it still takes highly trained pilots to manage those systems, make critical decisions in the cockpit — and, yes, frequently to steer the planes.</p>
<p>“Commercial aviation is incredibly safe,” says Mindell, himself a qualified civil aviation pilot with more than 1,000 hours of flying time to his credit. “Part of the reason is there are a lot of highly technical systems, but those systems are all imperfect, and the people are the glue that hold the system together. Airline pilots are constantly making small corrections, picking up mistakes, correcting the air traffic controllers.”</p>
<p>Drawing on a concept developed by MIT professor of mechanical engineering Tom Sheridan, Mindell notes that the level of automation in a project can be judged on a scale from 1 to 10 — and aiming for 10, he contends, does not necessarily lead to more success in any given endeavor, compared to a happy medium of technology and person. In the space program, Mindell reflects, “The digital computer in Apollo allowed them to make a less automated spacecraft that was closer to the perfect 5.”</p>
<p><strong>Full automation a “20th-century narrative”</strong></p>
<p>So why, in the case of cars, are we back to a point where many people are envisioning a driverless future? In a way, Mindell says, this vision of the future belongs squarely to the past.</p>
<p>“I think the narrative of full autonomy is a 20th-century narrative,” Mindell says. “It’s a narrative of industrial mechanization that’s kind of filtered its way through the 20th century, supported by 20th-century science fiction. These narratives can and should change.”</p>
<p>Still, the idea of total automation is the approach taken by Google, most notably, in its development of self-driving cars. Yet as Mindell also observes, there are many challenges to the Google model: Its cars must identify all nearby objects correctly, need perfectly updated mapping systems, and must avoid all software glitches.</p>
<p>Ultimately, Mindell writes, “Google’s utopian autonomy is a more brittle, less functional solution than a rich, human-centered automation.” He predicts that the fully driverless model will not be the most successful, both for technical and social reasons.</p>
<p>“The notion of ceding control of something as fundamental to life as driving to a big, opaque corporation — people are not comfortable with that,” he says. Additionally, other companies and research groups looking at automating cars are “very clearly not going for the Google approach to fully driverless cars.”</p>
<p>Other scholars have found “Our Robots, Ourselves” to be valuable. Ian Bogost, a professor of media studies and interactive computing at Georgia Tech, calls the book “a lucid, hype-free exploration of how robotic automation really works” in tandem with human design and operation.</p>
<p>Mindell says he is eager to see how technologists, especially robotics engineers, react to the book. Among the places where Mindell is scheduled to speak on his current book tour are Microsoft and, yes, Google. In time, Mindell says, he believes his perspective will come to be more widely accepted, and that full automation on the roads will not seem as desirable a goal.</p>
<p>“I think the public discourse is slowly coming around to there is another way to do it,” Mindell concludes.</p>
<p class="p1"><em><span class="s1">Reprinted with permission of <a href="http://Reprinted with permission of MIT News&quot; and a link to the MIT News homepage (http://newsoffice.mit.edu/);" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT News.</a></span></em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Rock Print: A zero-waste 3D-printed structure made only of rock and thread</title>
		<link>https://robohub.org/rock-print-a-zero-waste-3d-printed-structure-made-only-of-rock-and-thread/</link>
		
		<dc:creator><![CDATA[Marianne Lucien]]></dc:creator>
		<pubDate>Wed, 07 Oct 2015 20:14:49 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[3D printing]]></category>
		<category><![CDATA[architectural robotics]]></category>
		<category><![CDATA[ETH Zurich]]></category>
		<category><![CDATA[Gramazio & Kohler]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[Switzerland]]></category>
		<guid isPermaLink="false">http://robohub.org/rock-print-a-zero-waste-3d-printed-structure-made-only-of-rock-and-thread/</guid>

					<description><![CDATA[Inspired to take 3D printing technology to new heights, ETH Zurich and MIT researchers create &#8220;Rock Print&#8221; &#8212; a full-scale architectural installation on display at the Chicago Architecture Biennial until January 3, 2016. Standing over 13 feet (4 metres) high in the Chicago Cultural Center, the monolithic Rock Print installation with its rough and elegant contours confirms that [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_54885" style="width: 1010px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-54885" class="wp-image-54885 size-full" src="http://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_022.jpg" alt="RockPrint_ETHZ_MIT_022" width="1000" height="1498" srcset="https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_022.jpg 1000w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_022-284x425.jpg 284w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_022-684x1024.jpg 684w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_022-200x300.jpg 200w" sizes="(max-width: 1000px) 100vw, 1000px" /><p id="caption-attachment-54885" class="wp-caption-text">Rock Print, Architectural installation at the Chicago Architecture Biennial 2015 from Gramazio Kohler Research, ETH Zurich and the Self-Assembly Lab, MIT</p></div>
<p>Inspired to take 3D printing technology to new heights, ETH Zurich and MIT researchers create &#8220;Rock Print&#8221; &#8212; a full-scale architectural installation on display at the Chicago Architecture Biennial until January 3, 2016.</p>
<p><span id="more-54880"></span></p>
<p>Standing over 13 feet (4 metres) high in the Chicago Cultural Center, the monolithic Rock Print installation with its rough and elegant contours confirms that collaboration inspires &#8220;State of the Art Architecture&#8221; – the theme of the inaugural <a title="Chicago Architecture Biennial" href="http://chicagoarchitecturebiennial.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Chicago Architecture Biennial</a>.</p>
<p>Born out of a 2012 University of Chicago conference that brought architects, engineers, material scientists, and physicists together, Rock Print demonstrates a principle called &#8220;jamming&#8221; that refers to aggregate granular materials, like gravel that are quite literally crammed together in such a way that they hold their form and shape like a solid, even though their molecular properties are closer (in terms of behaviour) to a liquid substance.</p>
<p>&#8220;Jamming&#8221; together, researchers from <a title="Gramazio Kohler Research" href="http://gramaziokohler.arch.ethz.ch/web/forschung/e/0/0/0/297.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Gramazio Kohler Research, ETH Zurich</a> and <a title="Self-Assembly Lab at MIT" href="http://www.selfassemblylab.net/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Skylar Tibbits&#8217; Self-Assembly Lab at the Massachusetts Institute of Technology (MIT)</a> produced, Rock Print – a zero waste and fully reversible architectural installation for the inauguration of the Chicago Architecture Biennial that opened on 3 October 2015.</p>
<img decoding="async" class="aligncenter size-full wp-image-54886" src="http://robohub.org/wp-content/uploads/2015/10/ETHZ_RockPrint_Teaser.jpg" alt="ETHZ_RockPrint_Teaser" width="1000" height="662" srcset="https://robohub.org/wp-content/uploads/2015/10/ETHZ_RockPrint_Teaser.jpg 1000w, https://robohub.org/wp-content/uploads/2015/10/ETHZ_RockPrint_Teaser-425x281.jpg 425w, https://robohub.org/wp-content/uploads/2015/10/ETHZ_RockPrint_Teaser-453x300.jpg 453w" sizes="(max-width: 1000px) 100vw, 1000px" />
<h2>Inspired by 3D print technology</h2>
<p>&#8220;Rock Print is a proof of concept that takes current robotic fabrication technology and applies it to a full-scale architectural project,&#8221; said Andreas Thoma, ETH Zurich.</p>
<p>Petrus Aejmelaeus-Lindstroem, lead researcher for the project at ETH Zurich added, &#8220;The project shows the capacity of a 3D printing process to create a geometrically-complex construction using two simple components found in everyday life &#8211; string and rocks.&#8221;</p>
<p>The environmentally conscious ETH and MIT installation team used a custom robotic fabrication setup to lay down nearly 5 miles (9.1 km) of a recycled textile string in a complex pattern guided by a specifically designed algorithm. Like making lasagne, the string is alternated with layers of a loose standard concrete aggregate (rocks) from the Swiss company <a title="Misapor" href="http://www.misapor.ch/EN/Home.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Misapor</a>. The company makes self-insulating concrete using crushed glass, additives, and a heating process that expands the glass into a foam-like aggregate of mostly air.</p>
<p>While the foam glass is a fraction of the weight of conventional gravel aggregate, Rock Print weighs in at slightly less than one tonne (970 kg to be exact). The weight is a delicate balance – a lighter weight material is necessary for an indoor installation, but the structure of the installation depends on weight to provide strength to the compressional forces that maintain its shape and to compensate for the relatively weak tensional forces.</p>
<img decoding="async" class="aligncenter size-full wp-image-54887" src="http://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_028.jpg" alt="RockPrint_ETHZ_MIT_028" width="1000" height="1498" srcset="https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_028.jpg 1000w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_028-284x425.jpg 284w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_028-684x1024.jpg 684w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_028-200x300.jpg 200w" sizes="(max-width: 1000px) 100vw, 1000px" />
<p>&nbsp;</p>
<h2>New possibilities for the future of architecture</h2>
<p>Matthias Kohler, who also serves as the Director of the <a title="NCCR Digital Fabrication" href="https://www.arch.ethz.ch/en/forschung/nationale-und-internationale-forschungsschwerpunkte/digitale-fabrikation--nfs-.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">National Competence Centre in Research (NCCR) Digital Fabrication</a>, commented on how 3D printing technology may influence architecture in the future stating, &#8220;3D printing technology is an inspiration for the future of architecture as it brings together resource efficient additive building principles with new possibilities for design. Such technology enables production of complex forms and intricate details of building elements at a minimal cost. Today&#8217;s commercially available 3D printing technologies are not yet suitable for the scale needed for architecture or its economic and structural demands.&#8221;</p>
<p>The Rock Print installation challenges and expands the scope of 3D printing to an architectural scale by introducing robotic fabrication and the use of inexpensive, reconfigurable bulk construction materials. This approach attempts to open new possibilities for future architecture – using advanced digital fabrication technology to build with sustainable and locally available materials.</p>
<p>Kohler says, &#8220;There is still a lot of interdisciplinary research needed to fully understand and leverage future digital fabrication principles at a full building scale, but after ten intensive years of research in the field, I am positive that such new principles will not only lead to exciting architecture projects, but also to a new digital building culture &#8211; possibly to a socially relevant transformation of our built environment.&#8221;</p>
<p><iframe src="https://player.vimeo.com/video/141097712" width="500" height="281" frameborder="0" allowfullscreen="allowfullscreen"></iframe></p>
<p>&nbsp;</p>
<h2>Gramazio Kohler Research, ETH Zurich</h2>
<p>The research group headed by Professors Fabio Gramazio and Matthias Kohler at ETH Zurich examines the changes in architectural production that result from the introduction of digital manufacturing techniques. The main focus is ground-breaking research into computational design, constructive systems and their synthesis through the use of novel robotic fabrication technologies. Lindstroem and Thoma indicated that Rock Print was made possible through the collaborative knowledge of architects, engineers, and computational physicists. Prof. Dr. Hans J. Herrmann and Dr. Falk Wittel from ETH Zurich&#8217;s Institute for Building Materials and Prof. Dr. Heinrich Jaeger from the University of Chicago consulted on the project.</p>
<p><a title="Gramazio Kohler Research" href="http://www.gramaziokohler.arch.ethz.ch/web/e/forschung/297.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Gramazio Kohler Research &#8211; Rock Print project page</a></p>
<p>&nbsp;</p>
<h2>Chicago Architecture Biennial 2015</h2>
<p>Rock Print is on display throughout the biennial that runs through 3 January 2016 in the Chicago Cultural Center – the former public library across from the stunning Millennium Park in the heart of the city. Famous for its contemporary architecture and landmark skyscrapers, the <a title="Chicago Architecture Biennial" href="http://chicagoarchitecturebiennial.org/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Chicago Architecture Biennial</a> celebrates with the theme, &#8220;State of the Art in Architecture&#8221; providing a platform for ground-breaking architectural projects and spatial experiments that demonstrate how creativity and innovation can radically transform our lived experience. It offers an opportunity to take stock of more than 70 architectural projects and experiments from 30 countries around the world. Rock Print represents the Swiss-US collaboration at the forefront of innovation in architecture.</p>
<img decoding="async" class="aligncenter size-full wp-image-54889" src="http://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_026.jpg" alt="RockPrint_ETHZ_MIT_026" width="1000" height="668" srcset="https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_026.jpg 1000w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_026-425x284.jpg 425w, https://robohub.org/wp-content/uploads/2015/10/RockPrint_ETHZ_MIT_026-449x300.jpg 449w" sizes="(max-width: 1000px) 100vw, 1000px" />
<hr class="xh2  ">
<p><i>If you liked this article, you may also be interested in:</i></p>
<ul>
<li><a title="New Master of Advanced Studies (MAS) in architecture and digital fabrication at ETHZ" href="http://robohub.org/new-master-of-advanced-studies-mas-in-architecture-and-digital-fabrication-at-ethz/" rel="bookmark" data-wpel-link="internal">New Master of Advanced Studies (MAS) in architecture and digital fabrication at ETHZ</a></li>
<li><a title="Watch flying machines weave a rope bridge you can walk on" href="http://robohub.org/watch-flying-machines-weave-a-rope-bridge-you-can-walk-on/" rel="bookmark" data-wpel-link="internal">Watch flying machines weave a rope bridge you can walk on</a></li>
<li><a title="Architectural robots: The shape of the robots that will shape your home" href="http://robohub.org/architectural-robotics-shape-of-the-robots-that-will-shape-your-home-in-dom-reconfigurable-spaces/" rel="bookmark" data-wpel-link="internal">Architectural robots: The shape of the robots that will shape your home</a>
<p>&nbsp;</li>
<li><a href="http://robohub.org/swiss-to-invest-almost-chf30-million-in-digital-fabrication-research-over-next-4-years/" data-wpel-link="internal">Swiss to invest almost CHF30 million in digital fabrication research over next 4 years</a></li>
</ul>
<p><i>See all </i><a href="http://robohub.org/" data-wpel-link="internal"><i>the latest robotics news</i></a><i> on Robohub, or </i><a class="ext-link" title="" href="http://eepurl.com/t-UEf" target="_blank" rel="external follow noopener noreferrer" data-wpel-link="external"><i>sign up for our weekly newsletter</i></a><i>.</i></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Soft robotic gripper can pick up and identify wide array of objects</title>
		<link>https://robohub.org/soft-robotic-gripper-can-pick-up-and-identify-wide-array-of-objects/</link>
		
		<dc:creator><![CDATA[CSAIL MIT]]></dc:creator>
		<pubDate>Fri, 02 Oct 2015 08:05:03 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robohub focus on soft robotics]]></category>
		<guid isPermaLink="false">http://robohub.org/soft-robotic-gripper-can-pick-up-and-identify-wide-array-of-objects/</guid>

					<description><![CDATA[By Adam Conner-Simons, MIT CSAIL Robots have many strong suits, but delicacy traditionally hasn’t been one of them. Rigid limbs and digits make it difficult for them to grasp, hold, and manipulate a range of everyday objects without dropping or crushing them. Recently, CSAIL researchers have discovered that the solution may be to turn to [&#8230;]]]></description>
										<content:encoded><![CDATA[<div id="attachment_54618" style="width: 535px" class="wp-caption alignnone"><img decoding="async" aria-describedby="caption-attachment-54618" src="http://robohub.org/wp-content/uploads/2015/10/IMG_8709.jpg" alt="Team&#039;s silicone rubber gripper can pick up egg, CD &amp; paper, and identify objects by touch alone" width="525" height="350" class="size-full wp-image-54618" srcset="https://robohub.org/wp-content/uploads/2015/10/IMG_8709.jpg 525w, https://robohub.org/wp-content/uploads/2015/10/IMG_8709-425x283.jpg 425w, https://robohub.org/wp-content/uploads/2015/10/IMG_8709-450x300.jpg 450w" sizes="(max-width: 525px) 100vw, 525px" /><p id="caption-attachment-54618" class="wp-caption-text">Team&#8217;s silicone rubber gripper can pick up egg, CD &#038; paper, and identify objects by touch alone</p></div>
<p><em>By Adam Conner-Simons, MIT CSAIL</em></p>
<p>Robots have many strong suits, but delicacy traditionally hasn’t been one of them. Rigid limbs and digits make it difficult for them to grasp, hold, and manipulate a range of everyday objects without dropping or crushing them.</p>
<p>Recently, CSAIL researchers have discovered that the solution may be to turn to a substance more commonly associated with new buildings and Silly Putty: silicone.<span id="more-54616"></span></p>
<p>At a conference this month, researchers from CSAIL Director Daniela Rus’ Distributed Robotics Lab demonstrated a 3-D-printed robotic hand made out of silicone rubber that can lift and handle objects as delicate as an egg and as thin as a compact disc.</p>
<p>Just as impressively, its three fingers have special sensors that can estimate the size and shape of an object accurately enough to identify it from a set of multiple items.</p>
<div class="keep-aspect"><iframe title="A Modular Soft Robotic Gripper" width="500" height="281" src="https://www.youtube-nocookie.com/embed/Y5kZO8SSxVw?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>“Robots are often limited in what they can do because of how hard it is to interact with objects of different sizes and materials,” Rus says. “Grasping is an important step in being able to do useful tasks; with this work we set out to develop both the soft hands and the supporting control and planning systems that make dynamic grasping possible.&#8221;</p>
<p>The paper, which was co-written by Rus and graduate student Bianca Homberg, PhD candidate Robert Katzschmann, and postdoc Mehmet Dogar, will be presented at this month’s International Conference on Intelligent Robots and Systems.</p>
<p> &nbsp; </p>
<p><strong>The hard science of soft robots</strong></p>
<p>The gripper, which can also pick up such items as a tennis ball, a Rubik&#8217;s cube and a Beanie Baby, is part of a larger body of work out of Rus’ lab at CSAIL aimed at showing the value of so-called “soft robots” made of unconventional materials such as silicone, paper, and fiber.</p>
<p>Researchers say that soft robots have a number of advantages over “hard” robots, including the ability to handle irregularly-shaped objects, squeeze into tight spaces, and readily recover from collisions.</p>
<div class="sprfocus11"><a class="sprfocusl" href="/tag/robohub-focus-on-soft-robotics/" data-wpel-link="internal"> </a></div>
<p>“A robot with rigid hands will have much more trouble with tasks like picking up an object,” Homberg says. “This is because it has to have a good model of the object and spend a lot of time thinking about precisely how it will perform the grasp.”</p>
<p>Soft robots represent an intriguing new alternative. However, one downside to their extra flexibility (or “compliance”) is that they often have difficulty accurately measuring where an object is, or even if they have successfully picked it up at all.</p>
<p>That’s where the CSAIL team’s “bend sensors” come in. When the gripper hones in an object, the fingers send back location data based on their curvature. Using this data, the robot can pick up an unknown object and compare it to the existing clusters of data points that represent past objects. With just three data points from a single grasp, the robot’s algorithms can distinguish between objects as similar in size as a cup and a lemonade bottle.</p>
<p>“As a human, if you’re blindfolded and you pick something up, you can feel it and still understand what it is,” says Katzschmann. “We want to develop a similar skill in robots — essentially, giving them ‘sight’ without them actually being able to see.”</p>
<p>The team is hopeful that, with further sensor advances, the system could eventually identify dozens of distinct objects, and be programmed to interact with them differently depending on their size, shape, and function.       </p>
<p>&nbsp; </p>
<p><strong>How it works</strong></p>
<p>Researchers control the gripper via a series of pistons that push pressurized air through the silicone fingers. The pistons cause little bubbles to expand in the fingers, spurring them to stretch and bend.</p>
<p>The hand can grip using two types of grasps: “enveloping grasps,” where the object is entirely contained within the gripper, and “pinch grasps,” where the object is held by the tips of the fingers.</p>
<p>Outfitted for the popular Baxter manufacturing robot, the gripper significantly outperformed Baxter’s default gripper, which was unable to pick up a CD or piece of paper and was prone to completely crushing items like a soda can.</p>
<p>Like Rus’ previous robotic arm, the fingers are made of silicone rubber, which was chosen because of its qualities of being both relatively stiff, but also flexible enough to expand with the pressure from the pistons. Meanwhile, the gripper’s interface and exterior finger-molds are 3-D-printed, which means the system will work on virtually any robotic platform.</p>
<p>In the future, Rus says the team plans to put more time into improving and adding more sensors that will allow the gripper to identify a wider variety of objects.</p>
<p>“If we want robots in human-centered environments, they need to be more adaptive and able to interact with objects whose shape and placement are not precisely known,” Rus says. “Our dream is to develop a robot that, like a human, can approach an unknown object, big or small, determine its approximate shape and size, and figure out how to interface with it in one seamless motion.”</p>
<p>This work was done in the Distributed Robotics Laboratory at MIT with support from The Boeing Company and the National Science Foundation.</p>
<p><strong>RELATED</strong></p>
<p><a href="http://groups.csail.mit.edu/drl/wiki/images/2/27/Homberg_et_al._-_2015_-_Haptic_Identification_of_Objects_using_a_Modular_Soft_Robotic_Gripper.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Paper: “Haptic Identification of Objects using a Modular Soft Robotic Gripper”</a></p>
<p><a href="http://bhomberg.github.io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Bianca Homberg</a></p>
<p><a href="https://www.csail.mit.edu/user/876" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Daniela Rus</a></p>
<p><a href="http://groups.csail.mit.edu/drl/wiki/index.php?title=Main_Page" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Distributed Robotics Lab</a></p>
<p><a href="https://www.csail.mit.edu/baxter_soft_robotic_gripper" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">[article on csail.mit.edu]</a></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Former DARPA Program Manager Gill Pratt to direct Toyota&#8217;s new $50M robotics investment</title>
		<link>https://robohub.org/former-darpa-program-manager-gill-pratt-to-direct-toyotas-new-50m-robotics-investment/</link>
		
		<dc:creator><![CDATA[Ioannis K. Erripis]]></dc:creator>
		<pubDate>Fri, 04 Sep 2015 21:54:08 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[automotive]]></category>
		<category><![CDATA[business]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[DARPA]]></category>
		<category><![CDATA[DRC]]></category>
		<category><![CDATA[Gill Pratt]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robohub focus on autonomous driving]]></category>
		<category><![CDATA[Stanford]]></category>
		<category><![CDATA[Toyota]]></category>
		<guid isPermaLink="false">http://robohub.org/former-darpa-program-manager-gill-pratt-to-direct-toyotas-new-50m-robotics-investment/</guid>

					<description><![CDATA[In a surprise move today, Toyota held a press conference (see video below) announcing a substantial investment in robotics and AI research to develop &#8220;advanced driving support&#8221; technology, with former Program Manager of DARPA&#8217;s DRC Gill Pratt directing the overall project as Executive Technical Advisor. Toyota will allocate USD$50M over the next five years in a partnership with MIT’s CSAIL [&#8230;]]]></description>
										<content:encoded><![CDATA[<img decoding="async" class="alignnone size-full wp-image-53548" src="http://robohub.org/wp-content/uploads/2015/09/toyota.jpg" alt="toyota" width="900" height="500" srcset="https://robohub.org/wp-content/uploads/2015/09/toyota.jpg 900w, https://robohub.org/wp-content/uploads/2015/09/toyota-425x236.jpg 425w, https://robohub.org/wp-content/uploads/2015/09/toyota-500x278.jpg 500w" sizes="(max-width: 900px) 100vw, 900px" />
<p>In a surprise move today, Toyota held a press conference (see video below) announcing a substantial investment in robotics and AI research to develop <strong>&#8220;advanced driving support&#8221;</strong> technology, with former Program Manager of DARPA&#8217;s DRC Gill Pratt directing the overall project as Executive Technical Advisor. Toyota will allocate USD$50M over the next five years in a partnership with MIT’s CSAIL (headed by Daniela Rus) and Stanford&#8217;s SAIL (headed by Fei-Fei Li) to develop research facilities in Stanford and Cambridge.</p>
<p><span id="more-53547"></span></p>
<p>Two main themes from the press conference underline the tone of this effort:</p>
<p>First, <span  class="tweetquote"><a href="https://twitter.com/home/?status=Toyota doesn’t refer to autonomous cars but to ‘advanced driving support’ https://robohub.org/former-darpa-program-manager-gill-pratt-to-direct-toyotas-new-50m-robotics-investment/ @Robohub " target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer"> Toyota doesn’t refer to autonomous cars but to ‘advanced driving support’&nbsp;</a></span>. And this makes sense because, unlike Google (with its fully autonomous car), Toyota’s origins are in car manufacturing and not in software development. Car manufacturers have for some time been<a href="http://robohub.org/the-car-in-your-driveway-may-be-more-autonomous-than-you-think/" data-wpel-link="internal"> introducing ever rising levels of autonomy in their cars</a> and Toyota is following that vector. There are legal advantages to having the driving be ultimately responsible for the car&#8217;s movements and therefor any possible accidents; when a vehicle doesn&#8217;t respond as expected, a costly product liability suit could follow, as <a href="https://en.wikipedia.org/wiki/2009%E2%80%9311_Toyota_vehicle_recalls" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Toyota well knows</a>. Thus what appears at one level to be a more conservative approach to autonomy on the road may in essence be a way to bypass potential legal nightmares and bring autonomous driving technology to the market sooner.</p>
<div class="sprfocus7"><a class="sprfocusl" href="/tag/robohub-focus-on-autonomous-driving/" data-wpel-link="internal"> </a></div>
<p>Kiyotaka Ise, Toyota Motor Corporation Senior Managing Officer, repeatedly stated hybrid cars as an example of a specific technology that Toyota pioneered (along with Honda) and brought to market even while it was borderline unprofitable due to its large cost at the time. This offers a possible hint of what may follow.</p>
<p>The second interesting point made clear during Toyota&#8217;s Q&amp;A is that this project is only part of the auto manufacturer&#8217;s investment in the field. $50M is a lot of money, but for a profitable car maker the size of Toyota, it isn’t much. It looks like Toyota wants to establish a strong presence in the US by collaborating with two of the best research centers in the world (the budget will be equally split between the two universities) &#8230; but being a truly global company, it is developing other projects elsewhere as well. It’s worth mentioning that almost all large car manufacturers have similar research projects, and they usually collaborate with research institutes, universities or with each other.</p>
<p>In this respect, Toyota&#8217;s decision to bring on Pratt as the project lead appears astute. Pratt&#8217;s high visibility role as Program Manager of DARPA&#8217;s DRC has left him with significant experience managing and promoting large, big-budget projects, and has provided him with deep connections into US research labs.</p>
<p>You can <a href="http://corporatenews.pressroom.toyota.com/releases/toyota+establishes+ai+research+centers+mit+stanford.htm" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">read Toyota&#8217;s press release here</a> for all the details. Automaton has also an excellent coverage of the story (see <a href="http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/toyota-announces-major-push-into-ai-and-robotics" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Toyota Announces Major Push Into AI and Robotics, Wants Cars That Never Crash</a>) and says they will be releasing more in-depth stories about the deal early next week. You can watch the full press conference below:</p>
<div class=" "><iframe class="wp-embedded-content" sandbox="allow-scripts" security="restricted" title="Artificial Intelligence Research Collaboration" src="https://livestream.com/accounts/1607005/events/4315201/videos/98177858/player?width=640&#038;height=360&#038;autoPlay=true&#038;mute=false#?secret=GMER4qDtfx" data-secret="GMER4qDtfx" width="640" height="360" frameborder="0" scrolling="no"></iframe></div>
<p></p>
<p><iframe class="youtube-player" src="http://livestream.com/accounts/1607005/events/4315201/videos/98177858/player?autoPlay=false&amp;height=360&amp;mute=false&amp;width=640" width="640" height="360" frameborder="0" scrolling="no"></iframe></p>
<p>&nbsp;</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>ep.187: Cheetah 2, with  Sangbae Kim  </title>
		<link>https://robohub.org/robots-cheetah-2/</link>
		
		<dc:creator><![CDATA[Audrow Nash]]></dc:creator>
		<pubDate>Fri, 24 Jul 2015 18:47:45 +0000</pubDate>
				<category><![CDATA[podcast]]></category>
		<category><![CDATA[events]]></category>
		<category><![CDATA[ICRA 2015]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<guid isPermaLink="false">http://robohub.org/robots-podcast-cheetah-2-with-sangbae-kim/</guid>

					<description><![CDATA[In this episode, Audrow Nash interviews Sangbae Kim, from the Massachusetts Institute of Technology (MIT), at the International Conference of Robotics and Automation (ICRA) 2015. They speak about an electrically powered quadruped called the Cheetah 2.]]></description>
										<content:encoded><![CDATA[<img src="https://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim.jpg"/><img decoding="async" class="aligncenter size-full wp-image-52355" src="http://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim.jpg" alt="MIT-Cheetah-2_Sangbae_Kim" width="744" height="426" srcset="https://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim.jpg 744w, https://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim-425x243.jpg 425w, https://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim-175x100.jpg 175w, https://robohub.org/wp-content/uploads/2015/07/MIT-Cheetah-2_Sangbae_Kim-500x286.jpg 500w" sizes="(max-width: 744px) 100vw, 744px" />
<p><iframe src="https://w.soundcloud.com/player/?url=https%3A//api.soundcloud.com/tracks/293620476&amp;color=ff5500&amp;auto_play=false&amp;hide_related=false&amp;show_comments=true&amp;show_user=true&amp;show_reposts=false" width="100%" height="166" frameborder="no" scrolling="no"></iframe></p>
<p><strong>Transcript included.</strong></p>
<p>In this episode, Audrow Nash interviews Sangbae Kim, from the Massachusetts Institute of Technology (MIT), at the International Conference of Robotics and Automation (ICRA) 2015. They speak about an electrically-powered quadruped called the Cheetah 2.</p>
<p><span id="more-52340"></span></p>
<div class="keep-aspect"><iframe title="MIT Robotic Cheetah" width="500" height="281" src="https://www.youtube-nocookie.com/embed/XMKQbqnXXhQ?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>&nbsp;</p>
<p><strong>Sangbae Kim</strong></p>
<p><img decoding="async" class=" wp-image-5091 size-thumbnail alignleft" src="http://www.robotspodcast.com/podcast/uploaded_images/sangbae-133x150.jpg" alt="sangbae" width="133" height="150" />Prof. Sangbae Kim is the director of the <em>Biomimetic Robotics Laboratory</em> and an Associate Professor of Mechanical Engineering at MIT. His research focuses on the bio-inspired robotic platform design by extracting principles from complex biological systems. Kim’s achievements on bio-inspired robot development include the world‘s first directional adhesive inspired from gecko lizards, and a climbing robot, Stickybot, that utilizes the directional adhesives to climb smooth surfaces featured in TIME’s best inventions in 2006. The MIT Cheetah achieves stable outdoor running at an efficiency of animals, employing biomechanical principles from studies of best runners in nature. This achievement was covered by more than 200 articles. He is a recipient of King-Sun Fu Memorial Best Transactions on Robotics Paper Award (2008), DARPA YFA(2013), and NSF CAREER (2014) award.</p>
<p><strong>Links:</strong></p>
<ul>
<li><a class="mp3" href="http://feeds.soundcloud.com/stream/293620476-robotspodcast-robots-cheetah-2.mp3" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Download mp3 (20.1 MB)</a></li>
<li><a class="rss" title="Subscribe to Robots podcast RSS feed using iTunes" href="http://feeds.feedburner.com/robotspodcast" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Subscribe to Robots using iTunes</a></li>
<li><a class="rss" title="Subscribe to Robots podcast RSS feed using other feed readers" href="http://feeds.feedburner.com/robotspodcast" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Subscribe to Robots using RSS</a></li>
<li><a class="www" href="http://biomimetics.mit.edu/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT Biomimetic Robotics Lab</a></li>
</ul>
<hr class="xh2  ">
<h2>Transcript</h2>
<p><strong>Audrow Nash:</strong> I’m at ICRA 2015 with Professor Kim from MIT. Professor Kim, would you introduce yourself?</p>
<p><strong>Sangbae Kim:</strong> I’m an associate professor in Mechanical Engineering at MIT. I’ve been working on bio-inspired robots focusing on locomotion capability.</p>
<p><strong>Audrow Nash:</strong> What is the goal and motivation of your research?</p>
<p><strong>Sangbae Kim:</strong> Our motivation is to be able to develop a robot that can move around in a dangerous environment like Fukushima or a building on fire, so that we can send in a robot without worrying about putting a human in danger. Robotic technology stems from manufacturing applications, but in these applications robots don’t need to move in an unstructured environment; they are mostly moving on a rail or not moving around at all. We need a robot that can actually move around unstructured environments.</p>
<p>We’ve been focusing on locomotion capability because that’s currently a missing component in robotics technology. With the MIT Cheetah robot we developed a lot of component technology specifically for locomotion. Right now we’re moving a little beyond just locomotion or walking – we’re trying to combine this with vision so the robot can actually navigate by itself.</p>
<p><strong>Audrow Nash:</strong> Let’s talk a bit about the Cheetah 2. Can you describe it for us?</p>
<p><strong>Sangbae Kim:</strong> Cheetah 2 is the second generation of MIT Cheetah. We started five years ago, and we envisioned developing an electrically powered legged robot, because there was no electrically powered robot that could run or jump at that time. Most of the electrically powered robots out there are very slow. Boston Dynamics developed their hydraulic version; it’s vastly successful but very noisy and very inefficient. We did some investigation into the area and found huge potential. We started developing our all-electronic components … electric motors, electric driver amplifier, driver motor … and the locomotion algorithms about five years ago.</p>
<p>Cheetah 2 is the latest version of the Cheetah, and it has a custom motor designed by our MIT team.</p>
<p><strong>Audrow Nash:</strong> Starting from the very general  … it looks like a cheetah. It’s a quadruped …</p>
<p><strong>Sangbae Kim:</strong> Yes, it looks like a quadruped; we modeled it on a cheetah but it looks quite different from a cheetah. It’s really hard to be close to an animal. If you look at the many quadrupeds that run really well, their morphologies are not that different. We don’t actually have that exotic flexible cheetah spine.</p>
<p><strong>Audrow Nash:</strong> It’s a rigid back?</p>
<p><strong>Sangbae Kim:</strong> Yes, it’s a rigid back right now.</p>
<p><strong>Audrow Nash:</strong> There’s one joint on the back?</p>
<p><strong>Sangbae Kim:</strong> Cheetah 1 had this joint with a differential power drive, but we actually designed that and used it in Cheetah 2. So that mitigates the stiffness in the structure integrity. Cheetah 2 is a rather simpler design but is more capable. Cheetah 2 can run outside and it’s about 33 kilograms and about a meter long, about 80 centimeters high. It’s like Big Dog in size and it keeps on running up to 6 meters per second without a vision sensor. We believe that with the vision sensor it can go up to 10 meters per second.</p>
<p><strong>Audrow Nash:</strong> What would the vision sensor do?</p>
<p><strong>Sangbae Kim:</strong> It will detect the ground height more accurately. So far most running is done without having any vision, which means you’re robot is blind. Basically you close your eyes and you run as fast as possible, and it’s much more dangerous. It’s very important to have the contact angle of the leg be accurate, and as you get faster and faster that accuracy requirement becomes severe. With blind control we could get only 6 meters per second, but the mechanical capability of the robot is way beyond that. I think 10 meters per second, no problem.</p>
<p>Currently the Cheetah has vision sensors; we have a LIDAR that can detect an obstacle and it will adjust its step to jump over it properly, autonomously.</p>
<p><strong>Audrow Nash:</strong> What are the differences between Cheetah 1 and Cheetah 2?</p>
<p><strong>Sangbae Kim:</strong> There are some differences. Cheetah 1 mostly runs on a track with some support, whereas Cheetah 2 is fully 3D. Cheetah 1 is held in a plane so it can’t fall sideways but it can go only up and down and rotate. It’s more like a 2D robot. And its motor is less powerful because it’s a commercially available motor. It also has an exotic spine structure so it can actually use it’s spine in a galloping gait. There are some difference in the motors in the legs, and a big difference in the algorithms.</p>
<p><strong>Audrow Nash:</strong> Can you talk a little bit about that?</p>
<p><strong>Sangbae Kim:</strong> In Cheetah 1 we use very simple algorithm; we define a trajectory and then apply some sort of impedance, like vertical impedance, stiffness and damper. We just follow the trajectory based on the impedance, which is just a push and tracking gain.</p>
<p>Cheetah 2 is completely different; it does not rely too much on position tracking. As soon as the feet hit the ground, the ground stance control is not heavily dependent on position tracking, we are mostly prescribing force. We call that impulse planning.</p>
<p>In locomotion the fundamental requirement is that we have to fight against gravity. You don’t want to fall; you have to keep your body up. Then you’re constantly losing momentum by gravity. If you’re standing, gravity pulls you down so you need to generate the same amount of force to cancel that. If you’re running, you need to generate that same amount of impulse in a shorter amount of time because you’re staying on the ground a much shorter time than when you’re standing.</p>
<p>We calculate how much impulse I need to generate each step, depending on my speed, depending on my gait, and we actually prescribe that force profile to master our impulse on each step. That’s a basic control algorithm, so during the stance, force control is dominating whereas Cheetah 1 is still position tracking with this virtual spring control.</p>
<p><strong>Audrow Nash:</strong> So for Cheetah 2 you’re planning how hard you’re pushing the foot into the ground … how much force you’re doing?</p>
<p><strong>Sangbae Kim:</strong> Yes, we give some sort of force profile as a function of time.</p>
<p><strong>Audrow Nash:</strong> And it’s time-dependent, the rate that it’s running?</p>
<p><strong>Sangbae Kim:</strong> It’s time dependent, yes.</p>
<p><strong>Audrow Nash:</strong> The DARPA Robotics Challenge involves humanoids. What are the advantages of using a quadruped over a biped?</p>
<p><strong>Sangbae Kim:</strong> I’m a strong believer in quadrupeds. I think bipeds are just inherently less stable because we have a smaller polygon and the numbers of legs are less. In a quadruped you can stand with the one leg up, and you still have a tripod. The majority of the mammals in the world are quadrupeds. It’s hard to draw evolutionary reasons, but they have much more versatile capabilities.</p>
<p>Of course the human has amazing capabilities to go over rough terrain but they can become quadruped; if you’re going rock climbing and then you see those enthusiasts that are running off, and jumping off buildings …</p>
<p><strong>Audrow Nash:</strong> The Parkour people?</p>
<p><strong>Sangbae Kim:</strong> Yes, that’s actually quadruped locomotion, not biped. I think quadruped has a huge potential of becoming a major mode of locomotion. If you see the DARPA Robotic Challenge, I think you will see a lot of teams actually use four legs or some sort of wide support polygon to ensure there’s stability.</p>
<p><strong>Audrow Nash:</strong> Can you talk a bit about the actuators on the Cheetah 2?</p>
<p><strong>Sangbae Kim:</strong> That’s probably the one component we spent the most time on and probably why I started this project. In leg locomotion there’s a predominant model called a ‘spring-loaded inverted pendulum’, and it’s a very remarkable model that has enlightened a lot of researchers.</p>
<p><strong>Audrow Nash:</strong> Can you describe it?</p>
<p><strong>Sangbae Kim:</strong> It’s like a poker stick, basically. If you look at human running or animal running, it’s very complex; there are so many joints and a lot of pieces are moving in different ways …</p>
<p><strong>Audrow Nash:</strong> Elastic tendons and everything  …</p>
<p><strong>Sangbae Kim: </strong>Yes. Then these bio mechanic researchers in the late 70s and 80s found that, even though there are very complex and multi-body systems interacting with the ground, the bottom line is that your center of mass … your final trajectory during the stance … pretty much looks like a poker stick. It’s as if the entire leg becomes a spring; the system is a mass with a spring leg bouncing off the ground, and that describes pretty much the fundamental mechanics of most runners. It’s basically a reduced model of running, but it surprisingly covers many species and many type of running.</p>
<p>People started to realize, “Wow, so I don’t need to design these 20 muscles and 7 jointed legs to mimic human or animal running. You can just have a spring that takes care of everything.” This is theoretically true, but stability wasn’t very good, so a lot of people were trying to mimic this spring.</p>
<p>That’s when we started building the hypothesis that we’re not trying to control our leg to be like a spring; we’re probably controlling force. And that’s why we started developing this actuator, which has a very small gear ratio and a very specialized motor that can generate high torque per mass. We’re trying to maximize the force bandwidth; how quickly you can change force and at the same time maximize the transparency. Transparency means the mechanical impedance between the actuator force to the end effector …basically the electromagnetic component, which is an electric motor between the stator and the rotor. If you count all the masses and the frictions and inertia from there, all the way to the foot, that inertia and friction will mitigate the force transmission.</p>
<p><strong>Audrow Nash:</strong> So some force is lost by the arm or the leg moving?</p>
<p><strong>Sangbae Kim:</strong> Exactly. If you look at 99% of the robotic systems in the world, including manufacturing robots, that transparency is nearly zero. If somebody pushes the robotic arm, the motor cannot feel that, which means your motor cannot actually control force properly at the end effector. So what’s the solution? They add force sensors and then get the feedback. But that’s a very dangerous idea when the robot actually interacts with the ground because it’s non-collocated sensing.</p>
<p><strong>Audrow Nash:</strong> Can you explain non-collocated sensing?</p>
<p><strong>Sangbae Kim:</strong> Non-collocated sensing is when you’re trying to control the force at the end effector but your force is transmitted far away and there are dynamics between them, or there is delay between them. If you try to close the loop through this non-collocated sensing, there’s going to be inherent instability. It’s a very well known phenomenon. In the 90s, people showed how to develop better controllers to deal with contact instability by developing different control algorithms.</p>
<p><strong>Audrow Nash:</strong> And so you make it elastic, in a sense, through the spring?</p>
<p><strong>Sangbae Kim:</strong> We make it collocated. We don’t sense anything at the end effector; we sense through the actuator and then minimize the transmission. It turns out that is actually much closer to animals because from our muscle to our end effector, there’s almost no transmission and your Golgi tendon is combined with your muscle, which is a force sensor, and that can sense pretty much almost everything in the end effector. It’s not well proven, but think of when a human is running and balancing how much we are relying on the skin force sensor …</p>
<p><strong>Audrow Nash:</strong> So it’s mostly muscles as sensors?</p>
<p><strong>Sangbae Kim:</strong> Mostly muscle force for perception. Of course the skin sensor should detect the ground, in an “I know my foot is on the ground” kind of cue … but I don’t think the actual accurate measurement force should be done in the muscle. Imagine you have a different type of shoe on, or you tie your shoe laces a bit stronger today, and then you have to adjust your step … that probably doesn’t make sense right? In our case it’s a very practical reason. Non-collocated force sensing is not practical or feasible especially when we need high gain and high performance. Any force sensor in the foot will be destroyed in less than 30 minutes.</p>
<p>Locomotion is surprisingly violent. With the MIT Cheetah, peak force is about 500-600 Newtons. That’s happening 4 times in a second. This means you’re holding your robot and hammering the end effector at 4 hertz at 500Newtons, which is a 50 Kilogram force.</p>
<p><strong>Audrow Nash:</strong> And how do you not strip your gears with all of this?</p>
<p><strong>Sangbae Kim:</strong> That’s the key of our low-impedance transmission.</p>
<p><strong>Audrow Nash:</strong> Low-impedance in what sense?</p>
<p><strong>Sangbae Kim:</strong> Low inertia, low friction, where there’s no stiffness. The inertia and the friction is most of it.</p>
<p>If you’re going back to the conventional robotics there’s like 200:2 gear reduction, a special harmonic drive, and those cause enormous inertia. If you do that the robot is going to break somewhere. Those forces cannot really transmit. In our case your rotor can just give, so our electromagnetic interaction will be the only one that receives the force. We can even regenerate power, which is how we save energy when we’re running.</p>
<p><strong>Audrow Nash:</strong> So a spring is in series with the motor …</p>
<p><strong>Sangbae Kim:</strong> We don’t have a spring in our system.</p>
<p><strong>Audrow Nash:</strong> But the tendon system that you have …</p>
<p><strong>Sangbae Kim:</strong> No, those are harder than steel. There’s no single mechanical compliance in our system, except for the paw … the foot has little rubber pads to minimize the impact of vibration … but beyond that part, everything is rigid.</p>
<p><strong>Audrow Nash:</strong> Where’s the energy storage that you’re talking about?</p>
<p><strong>Sangbae Kim:</strong> All the energy can transfer to the motor side because there’s very little inertia, very little impedance. The motor will regenerate the energy and then restore it to the battery. It’s pretty much like electrical wheels. When they brake, when they do negative work and energy goes back to the battery. That’s the key element: maximizing transparency, which makes our force bandwidth maximum at the same time that it makes it inherently much more robust against impact, because the energy is restored rather than just breaking the gear.</p>
<p><strong>Audrow Nash:</strong> So in our skeletal system, we do a little bit of energy storage because of the elastic component to our composition?</p>
<p><strong>Sangbae Kim:</strong> That’s very different, yes.</p>
<p><strong>Audrow Nash:</strong> But you are taking the force that’s generated back and instead of storing it in a tendon system it’s going back to the battery.</p>
<p><strong>Sangbae Kim:</strong> Exactly.</p>
<p><strong>Audrow Nash:</strong> Are there conversions lost in this?</p>
<p><strong>Sangbae Kim: </strong>There are some conversion losses, yes.</p>
<p><strong>Audrow Nash: </strong>But you’ve shown in your talk the efficiency of this system, and it’s remarkably efficient and comparable to biology.</p>
<p><strong>Sangbae Kim:</strong> Our robots are far more efficient than most of the robots …</p>
<p><strong>Audrow Nash:</strong> Could you place the efficiency of the Cheetah 2 compared to other animals and robotics systems?</p>
<p><strong>Sangbae Kim:</strong> The cost of transport is a proper measurement of the efficiency in locomotion, and human is at about 0.3, which is pretty good. One thing I need to mention though is, this number is dependent on mass. For example, horses are better than humans, and rats or dogs are worse than humans because they’re lighter. So bigger animals tend to have a smaller number and cheetahs are like 0.4 and our robot is 0.5-0.45.</p>
<p><strong>Audrow Nash:</strong> An actual cheetah is 0.4, and your cheetah is too?</p>
<p><strong>Sangbae Kim:</strong> An actual cheetah is 0.4, and our cheetah is 0.45. It’s nearly same. The Honda ASIMO, which is one of the most remarkable robots, is at 2, so about 7 times worse.</p>
<p><strong>Audrow Nash:</strong> How about Big Dog?</p>
<p><strong>Sangbae Kim:</strong> Big Dog is at about 15.</p>
<p><strong>Audrow Nash:</strong> With its hydraulic actuators, it’s at 15?</p>
<p><strong>Sangbae Kim:</strong> Yes, it’s about 30 times worse than the actual animal. They’re heavier so they need to compare with their matching animal … I don’t have the exact number.</p>
<p>We’re nearly matching animal efficiency. I think this is because of our unique actuation system. The major cause for this efficiency is probably not regeneration, but light transmission. You have far fewer components and you lose very little through the transmission. That allows you to move fast.</p>
<p>As you mentioned, animals and humans should be better because they’re restoring energy; they should be more efficient. But that’s not really true because animals are more transparent in a sense. If I push you, and you relax your muscle, you can make your muscle impedance almost zero. Which means when you’re storing energy in the muscle tendon, your muscle should actually hold the force. Muscle is very good at holding force but it still needs to consume energy. Which is same for our system, but we can regenerate the energy whereas the muscle cannot.</p>
<p>Another thing is that the animal efficiency of 0.4 I mentioned is a measure through the metabolic energy, which is measured through the oxygen consumption and estimated energy you need to consume. This involves so many other processes, and then we’re comparing with our electricity consumption, which is technically not fair in my opinion because electricity is a refined source of fuel compared to fat or the sugar we consume. There’s a lot of inefficiency energy loss though this process. They break down the sugar to make ATP, and if you measure efficiency from ATP consumption to mechanical it’s probably a different story. I think that if you use an electric motor you should beat any animal by a factor of 2 or so.</p>
<p>I think our robot is not nearly optimized, and this is one data point we just built. We didn’t actually put any effort to make the robot more efficient. We paid attention to those principles when we designed it, so that’s probably one of the reasons it’s efficient, but we didn’t add any components or mechanisms optimized for algorithms to make it more efficient. I believe that we can increase efficiency by a factor of 2.</p>
<p><strong>Audrow Nash:</strong> How?</p>
<p><strong>Sangbae Kim:</strong> A couple of things like control optimization  …</p>
<p><strong>Audrow Nash:</strong> What do you mean by that?</p>
<p><strong>Sangbae Kim:</strong> You can actually optimize for your energy consumption. Our controllers are not optimized at all, so we haven’t studied that yet. In the MIT Cheetah, the major source of energy loss is caused by force generation, which means it’s just torque generation. This is very consistent with the biomechanics data … animals consuming 70% of energy in just producing force, which means that your energy is not going to be proportional to your mechanical work. Mechanical work is a bad metric in locomotion because we do a lot of negative work and then we don’t know how to actually deal with those negative work.</p>
<p>In MIT Cheetah it’s very easy because we know how much energy is actually restored and how much energy is burnt. We can measure every single bit of it. The one way to save energy is adding parallel springs, not series elastic. Series elastic doesn’t really save force generation, but parallel springs do. We actually have a paper about adding parallel springs.</p>
<p><strong>Audrow Nash:</strong> Can you describe what a parallel spring would be?</p>
<p><strong>Sangbae Kim:</strong> If you think about a desk lamp, it has springs on the joints so that it balances itself. It doesn’t have an actuator but it holds the position pretty well; you can move it around and still it can hold the position pretty well, because there’s a little friction at the joint. But those springs are actually compensating for the gravity.</p>
<p>We can do the same thing on the Cheetah leg because the majority of the energy consumption is caused by generating vertical force, fighting against the gravity. We add a spring in parallel to the actuator to help to generate the vertical gravitational force and that will reduce the requirements of torque generation in the motor. Then they will reduce residual heating dramatically.</p>
<p><strong>Audrow Nash:</strong> And that will make the cheetah significantly more efficient.</p>
<p><strong>Sangbae Kim: </strong>Significantly more efficient, yes.</p>
<p><strong>Audrow Nash:</strong> Can you give me a comparison of electric motors versus muscles?</p>
<p><strong>Sangbae Kim:</strong> That’s one of the most interesting things we learned through the MIT Cheetah project. We naively started with the idea that “Wow we might be able to build a robot that runs like an animal but we can also learn how animals work through the system.” That’s actually one of the inspiring aspects of this project.</p>
<p>But the more we study and we see the measurements, we realize how much the electric motor is different from our biological muscle. Now I’m thinking it’s kind of obvious, but there are huge differences. For example, quadrupeds have many different gaits, like the running gait, a canter gallop and a bound, and each gait has its own specific preferred speed.</p>
<p>When they run 3 meters per second they want to run in a trot, but when they’re running faster they want to switch to galloping. We don’t know exactly why, but we have some speculations and hypothesis.</p>
<p><strong>Audrow Nash:</strong> These gaits, they’re different modes of running. So we walk and then jog and then run. But there’s not really something between walking and jogging for us. Is this what you mean by gaits? So in quadrupeds …  it would be walking and galloping and trotting.</p>
<p><strong>Sangbae Kim:</strong> There are many gaits but the major ones are walking, trotting, cantering and galloping. And for each of these the foot pattern is different. There’s some data that shows that animals really don’t want to run certain gaits at certain speeds. We don’t know exactly why but they probably don’t want to run this way because the energy consumption is pretty high.</p>
<p>Our electric robot is actually very insensitive to gait and we realized the electric motors are much less picky in a way. For example, our torque generation and torque capability is independent from position. If you grab an electric motor, it doesn’t matter what position you are in, you can generate the same torque. You can generate the same torque according to speed as well: if you have a high enough voltage source, you can generate exactly the same torque at any speed. If you look at the muscles, the speed and then force and position, they highly couple each other. For example, your biceps can generate the biggest force if your elbow angle is 120 degrees, Then if your arms get stretched more and then become straight, your biceps muscle force becomes very small. When the biceps contract all the way to the shoulder length, your force generation can also drop significantly.</p>
<p>There’s also velocity-dependent force capability. When a muscle is contracted fast, your force generation capability drops very low and the muscle can generate a much higher force when it is expanding; when it’s doing negative work, it can generate much higher force. We don’t know exactly the energy consumption associated with that, but the maximum capability is heavily dependent on velocity and position. Which made us think that all this motion regeneration should be highly dependent on this muscle function. The electric motor doesn’t have that, so we start seeing this vast difference in energy consumption and capability. For example, when you run or you’re cycling the legs seems to have high energy consumption, and when you run fast at some point you feel like you cannot recycle your leg fast enough.</p>
<p>In the MIT Cheetah case, recycling leg energy consumption is very small, less than 10%. It’s probably because you can generate torque in any position, whereas when the leg is in the maximum stretched position, your force capability is very bad. We are not very good at moving back and forth due to that reason, so probably we need to include other parts of muscles and resonate using many different muscles. Whereas electric motors don’t need this many muscles; one motor is enough.</p>
<p>This relates to the spine. The cheetah uses its spine dramatically when its running fast and a lot of scientists are interested in that aspect. I don’t have any answer but my speculation is that it’s because the muscles have a very short range of operation. As I said on the biceps, you only have high force capabilities for 20-30 degrees, and for the rest of the range you don’t.</p>
<p>In order to generate high power movement like jumping or throwing a ball or swinging a bat, you need to include many muscles in a series fashion. I read a couple of papers showing that in a golf swing the maximum muscle activities are not happening at the same time, they are happening sequentially. Start from the ankle, to the leg and then fire, fire, fire and then going up, climbing up your body and your back muscle and then going to your arm. It’s sequentially activating, because probably one muscle cannot generate momentum for a long period of time because it has a fixed amount of good range of motion. Thinking about galloping, you need to swing your leg probably nearly as fast as 70 miles per hour to run 70 miles per hour, and one muscle cannot generate that kind of speed. So you probably need to include many muscles, and even more joints because more joints add speed. You can probably increase your speed by adding one more joint, which is where the spine comes in I think. In the electric motor case, it doesn’t really matter, because the speed is much cheaper in electric motors.</p>
<p>As I said, in muscles, your force drops if your speed increases, but in electric motor it’s not like that. You can actually generate the same amount of torque in high speed as well.</p>
<p><strong>Audrow Nash:</strong> So what does this mean?</p>
<p><strong>Sangbae Kim:</strong> The electric motor is actually way easier to use because everything is nearly linear and is less dependent on position and velocity. I think it’s actually more capable and a more powerful actuator than a human muscle. Although we are now still not capable … we’re still not as good as muscle in different aspects, for example force density. The muscles driving our fingers or jaw are not high power muscles but can generate really high force with a very small amount of mass. One finger can handle some people’s mass, but the muscles that are in charge of that finger are very minimal – it’s less than 100 grams or something. They are not high power but they are very high force and still very transparent. They can actually relax very quickly; we cannot generate that kind of actuator through an electric motor yet. So force density yes, but power density I think we actually exceed the human muscle.</p>
<p><strong>Audrow Nash:</strong> Thank you.</p>
<p><strong>Sangbae Kim:</strong> Thank you.</p>
<p><i>All audio interviews are transcribed and edited for clarity with great care, however, we cannot assume responsibility for their accuracy.</i></p>
]]></content:encoded>
					
		
		<enclosure url="http://feeds.soundcloud.com/stream/293620476-robotspodcast-robots-cheetah-2.mp3" length="0" type="audio/mpeg" />

			</item>
		<item>
		<title>SMART begins live public robocar tests in Singapore today</title>
		<link>https://robohub.org/smart-begins-live-public-robocar-tests-in-singapore-today/</link>
		
		<dc:creator><![CDATA[Brad Templeton, Robocars.com]]></dc:creator>
		<pubDate>Thu, 23 Oct 2014 19:56:33 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[automotive]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[robohub focus on autonomous driving]]></category>
		<category><![CDATA[Singapore]]></category>
		<guid isPermaLink="false">http://robohub.org/smart-begins-live-public-robocar-tests-in-singapore-today/</guid>

					<description><![CDATA[In late August, I visited Singapore to give an address at a special conference announcing a government sponsored collaboration involving their Ministry of Transport, the Land Transport Authority and A-STAR, the government funded national R&#38;D centre...]]></description>
										<content:encoded><![CDATA[<div id="attachment_40335" style="width: 810px" class="wp-caption aligncenter"><img decoding="async" aria-describedby="caption-attachment-40335" class="wp-image-40335 " alt="SMART-Driverless-buggy_electric-bike_201014" src="http://robohub.org/wp-content/uploads/2014/10/SMART-Driverless-buggy_electric-bike_201014.jpg" width="800" height="492" srcset="https://robohub.org/wp-content/uploads/2014/10/SMART-Driverless-buggy_electric-bike_201014.jpg 800w, https://robohub.org/wp-content/uploads/2014/10/SMART-Driverless-buggy_electric-bike_201014-425x261.jpg 425w, https://robohub.org/wp-content/uploads/2014/10/SMART-Driverless-buggy_electric-bike_201014-487x300.jpg 487w" sizes="(max-width: 800px) 100vw, 800px" /><p id="caption-attachment-40335" class="wp-caption-text"><a href="http://smart.mit.edu/news-a-events/press-room/article/51-first-driverless-vehicles-for-public-launched.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> SMART-NUS</a> enhanced driverless buggy. The steering wheel has been removed and replaced with an in-vehicle touchscreen for alternate selection of destination. Researchers will shadow the buggy on electric bicycles during the demo.</p></div>
<p>Robocar R&amp;D is moving fast in Singapore, and this week, the National University of Singapore (NUS) announced they will be doing a <a href="http://phys.org/news/2014-10-driverless-vehicles-singapore.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">live public demo of their autonomous golf carts</a> over a course with 10 stops in the Singapore Chinese and Japanese Gardens. The public will be able to <a href="http://www.smartnusav.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">book rides online</a>, and then summon and direct the vehicles with their phones. The vehicles will have a touch tablet where the steering wheel will go. Rides will be free, and will take place Oct. 23-25, Oct. 30-31 and Nov. 1.<span id="more-40297"></span></p>
<img decoding="async" class="aligncenter size-full wp-image-40341" alt="live283390_smartfmhi-res-16" src="http://robohub.org/wp-content/uploads/2014/10/live283390_smartfmhi-res-16.jpg" width="800" height="532" srcset="https://robohub.org/wp-content/uploads/2014/10/live283390_smartfmhi-res-16.jpg 800w, https://robohub.org/wp-content/uploads/2014/10/live283390_smartfmhi-res-16-425x282.jpg 425w, https://robohub.org/wp-content/uploads/2014/10/live283390_smartfmhi-res-16-451x300.jpg 451w" sizes="(max-width: 800px) 100vw, 800px" />
<p>This is not the first such public demo &#8211; the <a href="http://www.citymobil2.eu/en/City-activities/Small-Scale-Demonstration/Oristano/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">CityMobil2 demonstration</a> in Sardinia ran in August on a stretch of beachfront road blocked to cars but open to bicycles, service vehicles and pedestrians. Where the Sardinia project offered only a linear route, the Singapore project <a href="http://smart.mit.edu/news-a-events/press-room/article/51-first-driverless-vehicles-for-public-launched.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">press release</a> includes maps showing that the route is non-linear. Both projects have very low maximum driving speeds of 10km/hour.</p>
<div class="sprfocus7"><a class="sprfocusl" href="/tag/robohub-focus-on-autonomous-driving/" data-wpel-link="internal"> </a></div>
<p>The Singapore project will also mix with pedestrians, but the area is closed to cars and bicycles. (They have previously demonstrated not just detecting pedestrians but driving around them &#8211; provided they stay still, but it&#8217;s not clear whether the current project includes that ability). There will be two safety officers on bicycles riding behind the golf carts, able to shut them down if any problem presents, and speed will also be limited.</p>
<div class=" "><iframe title="In a nutshell" width="500" height="281" src="https://www.youtube-nocookie.com/embed/ln50KdTt25M?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Singapore is interesting because they have a long history of transportation innovation, and good reason for it. As a city-state, it’s almost all urban, and transportation is a real problem. That’s why congestion charging was first developed in Singapore. Other innovations have also been started there; for example, every vehicle in Singapore has a transponder, and they used for a variety of purposes including congestion tolling and seamless parking payment in almost all parking lots.</p>
<p>Six months ago I had the chance to visit <a href="http://www.a-star.edu.sg/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">A*STAR</a>, Singapore&#8217;s government funded national R&amp;D centre, as well as the car project at the National University of Singapore (NUS). Then in late August, I visited Singapore again to give an address at a special <a href="http://www.channelnewsasia.com/news/singapore/lta-a-star-agree-to/1332140.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">conference announcing a government-sponsored collaboration</a> involving their Ministry of Transport, the Land Transport Authority and A*STAR. I had a chance to meet the minister and sit down with officials to talk about their plans, and at the conference, there were demos of vehicles, including one from <a href="http://www.stengg.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Singapore Technologies</a>, which primarily does military contracting.</p>
<p>In spite of its history, Singapore tends toward conservatism — and this might dampen their pace of innovation. While this joint project is a good start, I advised them that, in my view, private projects will be able to move faster than public sector ones.</p>
<p>The NUS project is a collaboration with MIT, involving professor Emilio Frazzoli.</p>
<p><em>A version of this article originally appeared on <a href="http://ideas.4brad.com/live-public-test-singapore" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robocars.com</a>.</em></p>
<div class="divideronpost"></div>
<p><em>If you liked this article, you may also be interested in:</em></em></p>
<ul>
<li><a title="Lloyds Insurance report: Overcoming obstacles for driverless cars" href="http://robohub.org/lloyds-insurance-report-overcoming-obstacles-for-driverless-cars/" rel="bookmark" data-wpel-link="internal">Lloyds Insurance report: Overcoming obstacles for driverless cars</a></li>
<li><a title="The two cultures of robocars" href="http://robohub.org/the-two-cultures-of-robocars/" rel="bookmark" data-wpel-link="internal">The two cultures of robocars</a></li>
<li><a title="Deploying automated vehicles" href="http://robohub.org/deploying-automated-vehicles/" rel="bookmark" data-wpel-link="internal">Deploying automated vehicles</a></li>
<li><a title="Robots Podcast: Cruise" href="http://robohub.org/robots-cruise/" rel="bookmark" data-wpel-link="internal">Robots Podcast: Cruise</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" data-wpel-link="internal">the latest robotics news</a> on Robohub, or <a href="http://eepurl.com/t-UEf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>IROS 2014 Webcam: Research pitches from the interactive sessions (Part 2)</title>
		<link>https://robohub.org/iros-2014-webcam-research-pitches-from-the-interactive-sessions-part-2/</link>
		
		<dc:creator><![CDATA[Robohub Editors]]></dc:creator>
		<pubDate>Sat, 20 Sep 2014 22:16:39 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[events]]></category>
		<category><![CDATA[IROS 2014]]></category>
		<category><![CDATA[IROS 2014 Webcam]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[Righthand Robotics]]></category>
		<guid isPermaLink="false">http://robohub.org/iros-2014-webcam-research-pitches-from-the-interactive-sessions-part-2/</guid>

					<description><![CDATA[More pitches from the interactive sessions at IROS. See also Part 1. Sampriti Bhattacharyya MIT Compact, Tetherless ROV for In-Contact Inspection of Underwater Structures Josh Lane Purdue University MOTHERSHIP: A Serpentine Limb/Tread Hybrid Robot More info Yanzhe Cui Purdue University RrFrESH: A Self-Adaptation Framework to Support Fault Tolerance in Robot More info Ying Lu Rensselaer Polytechnic Institute [&#8230;]]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" class="size-full wp-image-38102" alt="IROS_Webcam" src="http://robohub.org/wp-content/uploads/2014/09/IROS_Webcam1.png" width="1000" height="500" srcset="https://robohub.org/wp-content/uploads/2014/09/IROS_Webcam1.png 1000w, https://robohub.org/wp-content/uploads/2014/09/IROS_Webcam1-425x212.png 425w, https://robohub.org/wp-content/uploads/2014/09/IROS_Webcam1-500x250.png 500w" sizes="(max-width: 1000px) 100vw, 1000px" />More pitches from the interactive sessions at IROS. See also <a href="http://robohub.org/iros-2014-webcam-research-pitches-from-the-interactive-sessions-part-1/" data-wpel-link="internal">Part 1</a>.<br />
<span id="more-38108"></span></p>
<div class="divideronpost"></div>
<p><strong>Sampriti Bhattacharyya</strong> MIT<br />
Compact, Tetherless ROV for In-Contact Inspection of Underwater Structures</p>
<div class=" "><iframe title="Sampriti Bhattacharyya _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/PiuRKQnmxX8?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<div style="clear: both;"></div>
<div class="divideronpost"></div>
<p><strong>Josh Lane</strong> Purdue University<br />
MOTHERSHIP: A Serpentine Limb/Tread Hybrid Robot</p>
<div class=" "><iframe title="Josh Lane _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/8VJSV4S2vaw?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<div style="clear: both;"></div>
<p><a href="http://web.ics.purdue.edu/~rvoyles/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">More info</a></p>
<div class="divideronpost"></div>
<p><strong>Yanzhe Cui</strong> Purdue University<br />
RrFrESH: A Self-Adaptation Framework to Support Fault Tolerance in Robot</p>
<div class=" "><iframe title="Yanzhe Cui _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/T4bxF68h3Qo?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<a href="http://web.ics.purdue.edu/~rvoyles/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">More info</a></p>
<div style="clear: both;"></div>
<div class="divideronpost"></div>
<p><strong>Ying Lu</strong> Rensselaer Polytechnic Institute<br />
On the Convergence of Fixed-point Iteration in Solving Complementarity Problems Arising in Robot Locomotion and Manipulation</p>
<div class=" "><iframe title="Ying Lu _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/LiaNDUouckY?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<a href="https://grasp.robotics.cs.rpi.edu/bpmd/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">More info</a></p>
<div style="clear: both;"></div>
<div class="divideronpost"></div>
<p><strong>Fei Chen</strong> Instituto Italiano di Tecnologia<br />
A Study on Data-Driven In-Hand Twisting Process Using a Novel Dexterous Robotic Gripper for Assembly Automation</p>
<div class=" "><iframe title="Fei Chen _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/_K7UPmw3li0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<a href="http://www.iit.it/it/advr-labs/advanced-industrial-automation.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">More info</a></p>
<div style="clear: both;"></div>
<div class="divideronpost"></div>
<p><strong>Leif Jentoft</strong> Righthand Robotics<br />
Not an official IROS14 paper, but a cool pitch none-the-less! Righthand Robotics was one of two hands selected for DRC Track A robots.</p>
<div class=" "><iframe title="Leif Jentoft _ IROS 2014" width="500" height="281" src="https://www.youtube-nocookie.com/embed/9Qux4jEujy8?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
<a href="http://www.righthandrobotics.com/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">More info</a></p>
<div style="clear: both;"></div>
<div class="divideronpost"></div>
<p><a href="http://robohub.org/tag/iros-2014/" data-wpel-link="internal">Check out all our IROS14 coverage.</a></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Self-contained soft-bodied robotic fish</title>
		<link>https://robohub.org/self-contained-soft-bodied-robotic-fish/</link>
		
		<dc:creator><![CDATA[Daniel Faggella]]></dc:creator>
		<pubDate>Wed, 19 Mar 2014 13:41:21 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[bio-inspired]]></category>
		<category><![CDATA[bioinspired]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[Daniela Rus]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[soft robotics]]></category>
		<guid isPermaLink="false">http://techemergence.com/?p=831</guid>

					<description><![CDATA[What looks like a fish, swims like a fish but isn’t a fish? The latest in soft-bodied robots created by team of engineers of the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology.
The team, comprised...]]></description>
										<content:encoded><![CDATA[<p>What looks like a fish, swims like a fish but isn’t a fish? The latest in soft-bodied robots created by team of engineers of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology.<span id="more-28762"></span></p>
<p>The team, comprised of Daniela Rus, Professor of Electrical Engineering and Computer Science and Director of CSAIL, Cagdas Onal, Assistant Professor of Mechanical Engineering at the Worcester Polytechnic Institute, and Andrew Marchese, a doctoral candidate in engineering at <a href="http://web.mit.edu/newsoffice/2014/soft-robotic-fish-moves-like-the-real-thing-0313.html" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">MIT,</a> created the robot to be autonomous. This means it has all the necessary sensing, actuation and computation on board. Its flexible body is made of silicone rubber. The robot fish is able to swish from side to side as onboard gas inflates and deflates different parts of its body. This means that the robot is flexible and can maneuver like a real fish—making a full C-turn with its body in just 100 milliseconds.</p>
<div class=" "><iframe title="Autonomous, self-contained soft robotic fish at MIT" width="500" height="281" src="https://www.youtube-nocookie.com/embed/BSA_zb1ajes?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>According to Rus, this type of soft robot is inherently safe, saying “As robots penetrate the physical world and start interacting with people more and more, it’s much easier to make robots safe if their bodies are so wonderfully soft that there’s no danger if they whack you.&#8221;</p>
<p>The fish can perform 20-30 agile escape maneuvers before its carbon dioxide canister runs out. The team is working on an updated version that will be able to swim for around 30 minutes using water to inflate its interior channels rather than carbon dioxide.</p>
<p>In the not so distant future, the fish-bot could be put to use for covert science missions where it might be able to infiltrate schools of real fish to collect data about their behavior.<b>  </b></p>
<p>The field of soft <a href="http://techemergence.com/sensitive-robotics-eduardo-torres-jara/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">robotics</a> holds great potential for the development of smart machines that can adjust their shape and size to fit variable environments and interact with living things without causing them harm. Possible applications include: mine detection, assistive healthcare, search and rescue missions and space instrument repair.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Robotic bartender assembles personalized drinks, monitors alcohol consumption, and takes social mixing to a whole new level</title>
		<link>https://robohub.org/robotic-bartender-assembles-personalized-drinks-monitors-alcohol-consumption-and-takes-social-mixing-to-a-whole-new-level/</link>
		
		<dc:creator><![CDATA[Hallie Siegel]]></dc:creator>
		<pubDate>Thu, 16 May 2013 05:18:34 +0000</pubDate>
				<category><![CDATA[news]]></category>
		<category><![CDATA[arts & entertainment]]></category>
		<category><![CDATA[human-robot interaction]]></category>
		<category><![CDATA[industrial]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[research]]></category>
		<category><![CDATA[sensing]]></category>
		<guid isPermaLink="false">http://robohub.org/?p=14149</guid>

					<description><![CDATA[You&#8217;re at a busy bar. You order your personalized cocktail through a smart phone app; a drink dispenser measures out the beverage according to your instructions and a Kuka robotic arm give it a shake (or stir), while another garnishes it with a slice of lemon; the made-to-order concoction is delivered to your waiting hand [&#8230;]]]></description>
										<content:encoded><![CDATA[<p>You&#8217;re at a busy bar. You order your personalized cocktail through a smart phone app; a drink dispenser measures out the beverage according to your instructions and a Kuka robotic arm give it a shake (or stir), while another garnishes it with a slice of lemon; the made-to-order concoction is delivered to your waiting hand via a slick little ten-lane conveyor belt. <span id="more-14149"></span><img decoding="async" class="alignleft" alt="MakrShakr_LucasWerthein_0104" src="http://robohub.org/wp-content/uploads/2013/05/MakrShakr_LucasWerthein_01041.jpg" /></p>
<div class="minitext">Makr Shakr Kuka robotic arm holding a martini shaker. Photo credit: Lucas Werthein.</div>
<p>The &#8216;mixology system&#8217; tracks your order from start to finish: a large display behind the bar shows you the number of drinks ahead of yours in the queue, the current wait time, and lets you know when your drink is ready to be picked up. It also shows you what&#8217;s popular to drink tonight among both the ladies and the gents in the crowd, and lets you influence drinking trends in realtime by incorporating your suggested tweaks on popular recipes.</p>
<p>This clearly isn&#8217;t your parents&#8217; neighbourhood watering hole, but it could be your kids&#8217; — or even yours if you are lucky enough to be at the <a href="https://developers.google.com/events/io/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Google I/O</a> After Hours event tonight in San Francisco. Welcome to <a href="http://www.makrshakr.com/" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Makr Shakr</a>, a bar for the &#8216;sense-able city&#8217; of tomorrow.</p>
<div class=" "><iframe title="Makr Shakr" width="500" height="281" src="https://www.youtube-nocookie.com/embed/gdvfDTZcHQM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p><strong>Drink as digitally/socially fabricated meme</strong><br />
Makr Shakr is one of MIT&#8217;s<a href="http://senseable.mit.edu" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer"> SENSEable City Lab</a> projects, where the goal is to study and anticipate how sensor technologies can inform and transform our built environments. The project&#8217;s creators say that it&#8217;s not about trying to replace bartenders with robots, or even about drinking; it&#8217;s about exploring the dynamics of consumption and social networks in the context of sensor and digital fabrication technologies. In other words, its a mini-lab for learning about how we, the social creatures that we are, might interact with each other and our environments in the sensor-augmented cities of tomorrow.</p>
<p>According to project leader Yaniv Turgeman, Makr Shakr was conceived as part research project, part art installation, part social experiment: &#8220;It is a research platform aimed at the <a href="http://en.wikipedia.org/wiki/The_Third_Industrial_Revolution" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">third industrial revolution</a>, where anyone can design, produce and influence culture. It&#8217;s also an installation meant to provoke and question our relationship with technology and creation … we&#8217;re experimenting with the idea of social co-creation and consumption.&#8221; Given Makr Shakr&#8217;s fundamental connection to crowdsourcing and social networks, it&#8217;s no wonder, then, that the project was invited to this year&#8217;s Google I/O event as a feature project.</p>
<p>As I write this article, Turgeman is busy with last minute preparations for Makr Shakr&#8217;s official launch at tonight&#8217;s Google I/O After Hours party, but I managed to track him down for a phone interview earlier this afternoon. He explained to me that point of the project was to take the phenomenon of <a href="http://en.wikipedia.org/wiki/Maker_culture" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">maker culture</a> and learn whether (and how) we can leverage it to socially create &#8220;bottom up culture&#8221;.</p>
<p>The SENSEable City Lab has many social and sensor networking projects at various stages of development (including elaborate plans for a <a href="http://en.expo2015.org" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">World Expo 2015</a> project that will explore how social connectivity can be used to influence the production, distribution, preparation, consumption and recycling of food), but when Google first approached the lab about developing a project specifically for the 2013 I/O event, the team chose Makr Shakr because drinking is a social and relatively discrete (and therefor easy to parameterize) activity; in other words, it&#8217;s an ideal context for studying how people interact with digitally-mediated social networks.</p>
<p>&#8220;Drinking happens to be a very social activity,&#8221; Turgeman said. &#8220;At a bar, you&#8217;re looking to meet people. You might think &#8216;hey that&#8217;s a great drink I just invented&#8217; and want to share it or iterate on it … by exploring the realtime behavioural dynamics in this situation, maybe we can learn something about how people interact with and influence each other&#8217;s consumption habits.&#8221;</p>
<img decoding="async" alt="MakrShakr_Superuber_Visualizations" src="http://robohub.org/wp-content/uploads/2013/05/MakrShakr_Superuber_Visualizations.jpg" />
<div class="minitext">Makr Shakr&#8217;s data visualization, showing the number of drinks in the queue, current wait time, drinks made and other details. Credit: Superuber Visualizations.</div>
<p>Digital fabrication is an important theme at the SENSEable City Lab, which regularly partners with industry in order to contextualize researchers where they can conduct real-world experiments. The kind of personalized, just-in-time digital fabrication and delivery exemplified by Makr Shakr (the &#8216;third industrial revolution&#8217; Turgeman refered to earlier in our conversation) is one that demands that big time players from the food and beverage sector take note. And some already have — in 2009 Coca-Cola launched <a href="http://www.coca-colafreestyle.com" target="_blank" data-wpel-link="external" rel="follow external noopener noreferrer">Freestyle</a>, a touchscreen-operated beverage dispenser that offers more than 100 of the company&#8217;s brands in a single dispensing device. But the big idea of Turgeman&#8217;s project is not to study delivery systems for custom drinks, it&#8217;s to study how cultural memes are created and promoted, and this is surely of interest to major brands like Coke and Bacardi, which are the main sponsors of the project.</p>
<p>In this context, Makr Shakr takes personalized branding to a whole new level. Says Turgeman: &#8220;The magic moment will be watching the formation of a bottom-up bar culture, as we close the loop between co-curating and co-producing in real time.&#8221; It&#8217;s not hard to imagine that, if Makr Shakr one day goes mainstream, advertisers and big brands will want a piece of the action. But as top-heavy players in a bottom-up world, the question that lingers is, will we let them?</p>
<p><strong>Bottom up culture, or Bottoms up culture?</strong><br />
<img decoding="async" class="alignleft  wp-image-14156" style="color: #333333; font-style: normal; line-height: 24px;" alt="MakrShakr_MaxTomasinelli_7534new" src="http://robohub.org/wp-content/uploads/2013/05/MakrShakr_MaxTomasinelli_7534new.jpg" width="346" height="229" srcset="https://robohub.org/wp-content/uploads/2013/05/MakrShakr_MaxTomasinelli_7534new.jpg 900w, https://robohub.org/wp-content/uploads/2013/05/MakrShakr_MaxTomasinelli_7534new-300x198.jpg 300w, https://robohub.org/wp-content/uploads/2013/05/MakrShakr_MaxTomasinelli_7534new-453x300.jpg 453w" sizes="(max-width: 346px) 100vw, 346px" /></p>
<div class="minitext">Makr Shakr beverage ready for pick up. Photo credit: Max Tomasinelli.</div>
<p>It&#8217;s not clear to me during our phone interview whether Turgeman sees the pun in his &#8216;bottom up&#8217; approach to influencing drinking culture, but it does get me prodding him about the claims on the Makr Shakr website that the system promotes responsible drinking by allowing people to self-monitor their alcohol consumption.</p>
<p>While this feature won&#8217;t be operational during the Google I/O event (they are expecting a crowd of 5000+ and didn&#8217;t want to overextend the system tonight) Turgeman explained that, yes, Makr Shakr can be used to track a person&#8217;s alcohol consumption. There&#8217;s no breathalizer unit to blow into (too uncouth, I imagine, not to mention the privacy issues and ick-factor); instead the system estimates your blood alcohol levels based on weight and height information you provide when you install the app on your phone, and the number of drinks that the system has served you.</p>
<p>The Makr Shakr phone app displays your blood alcohol level over time in a chart, but it also uses three simple icons to tell you whether you are safe &#8220;to drive, to walk or to talk,&#8221; because, as Turgeman points out, numbers might be meaningless to you, especially after a few drinks. &#8220;Sometimes you think you&#8217;re safe to drive when you&#8217;re not. When you&#8217;re being social, it&#8217;s hard to keep track of how many drinks you&#8217;ve had,&#8221; says Turgeman, and since that data is so easy to capture, &#8220;it&#8217;s a no-brainer that of course we should let people know.&#8221;  He also assures me that, as discretion is a must for bartenders, all data from the Makr Shakr app is anonymous (though users are able to share their age, gender, nationality, nickname and photo or avatar for social networking if they want to).</p>
<p>Though Makr Shakr will not demand that you turn over your car keys and order you a taxi if you&#8217;re over the legal limit, Turgeman says that it&#8217;s not a stretch that future iterations could interface with taxi-service apps like <a style="font-style: normal; line-height: 24px;" href="https://www.uber.com" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Uber</a>.</p>
<p>I&#8217;m told that Makr Shakr doesn&#8217;t take tips, but I&#8217;ll tip my hat to its makers all the same.</p>
<img decoding="async" alt="MakrShakr_MaxTomasinelli_7162ok" src="http://robohub.org/wp-content/uploads/2013/05/MakrShakr_MaxTomasinelli_7162ok.jpg" width="900" height="600" />
<div class="minitext">Makr Shakr at it&#8217;s unveiling in Milan. Photo credit: Max Tomasinelli.</div>
<p><em>[Credits: Project concept and design by MIT Senseable City Lab; Implementation bycarlorattiassociati | walter nicolino &amp; carlo ratti; Main partners &#8211; Coca-Cola and Barcardi. Technical partners &#8211; Kuka, Pentagram, SuperUber; Media partners &#8211; Domus, Wired; Videos by MyBossWas; Event in collaboration with Meet the Media Guru, and endorsed by: Comune di Milano, World Expo Milano 2015 – Energy for Life. Feeding the Planet. Photos: Lucas Werthein, Max Tomasinelli, My Boss Was. Full credits available at www.makrshakr.com.]</em></p>
<div class="divideronpost"></div>
<p><em>If you liked this article, you may also be interested in:</em></p>
<ul>
<li><a href="http://robohub.org/the-death-of-search-or-my-dysfunctional-relationship-with-siri/" data-wpel-link="internal">The death of search (or, My dysfunctional relationship with Siri)</a></li>
<li><a href="http://robohub.org/if-you-could-enhance-yourself-with-some-robotic-accessory-or-implant-what-would-it-be/" data-wpel-link="internal">If you could enhance yourself with some robotic accessory or implant, what would it be?</a></li>
<li><a href="http://robohub.org/robot-tourism-coming-soon-to-korea-masan-robot-land-project-finally-breaks-ground/" data-wpel-link="internal">Robot tourism coming soon to Korea: Masan Robot Land project finally breaks ground</a></li>
<li><a href="http://robohub.org/do-robots-need-heads/" data-wpel-link="internal">Do robots need heads?</a></li>
</ul>
<p><em>See all <a href="http://robohub.org/" data-wpel-link="internal">the latest robotics news</a> on Robohub, or <a href="http://eepurl.com/t-UEf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">sign up for our weekly newsletter</a>.</em></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>VLAB: Drones – The commercial era takes off, but breaking the law is going to blow-up in our faces</title>
		<link>https://robohub.org/vlab-drones-the-commercial-era-takes-off-but-breaking-the-law-is-going-to-blow-up-in-our-faces/</link>
		
		<dc:creator><![CDATA[Robert Morris]]></dc:creator>
		<pubDate>Tue, 26 Mar 2013 06:07:12 +0000</pubDate>
				<category><![CDATA[opinions]]></category>
		<category><![CDATA[3D Robotics]]></category>
		<category><![CDATA[business]]></category>
		<category><![CDATA[Chris Anderson]]></category>
		<category><![CDATA[DIY]]></category>
		<category><![CDATA[events]]></category>
		<category><![CDATA[FAA]]></category>
		<category><![CDATA[law]]></category>
		<category><![CDATA[military]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[policy]]></category>
		<category><![CDATA[politics]]></category>
		<category><![CDATA[social robotics]]></category>
		<category><![CDATA[Stanford]]></category>
		<category><![CDATA[UAS]]></category>
		<category><![CDATA[UAVs & drones]]></category>
		<guid isPermaLink="false">http://robocosmist.com/?p=406</guid>

					<description><![CDATA[Last Tuesday, I had the pleasure of attending VLAB: Drones &#8211; The Commercial Era Takes Off at Stanford GSB.   The event was truly fantastic and the panel was amazing.  The moderator was Chris Anderson, former editor at Wired and CEO of 3D rob...]]></description>
										<content:encoded><![CDATA[<p>Last Tuesday I had the pleasure of attending <a href="http://www.vlab.org/article.html?aid=463" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">VLAB: Drones – The Commercial Era Takes Off</a> at Stanford GSB. The event was truly fantastic and the panel was amazing. The moderator was <a href="http://about.me/andersonchris" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Chris Anderson</a>, former editor at Wired and CEO of 3D robotics. I’m really struck by how much he has become the face of the commercial drone industry. <span id="more-11421"></span>From his appearances on NPR and print media, he’s probably the most recognized drone advocate, and he makes some very powerful points. Fuelled by Moore’s Law and the cellphone industry supply chain,the drone/robotic era is coming and, though we’ve got to prepare for it, it doesn’t have to be scary.</p>
<p><img decoding="async" class="wp-image-409 alignleft" title="VLAB Drones Panel" alt="VLAB Drones Panel at Stanford GSB March 19th, 2013" src="http://robocosmist.files.wordpress.com/2013/03/vlab-drones-cropped1.jpg?w=420&amp;h=260" width="336" height="208" />In particular, Anderson promoted one idea that deserves the attention of the drone industry: that by operating in a legal &#8220;grey area&#8221; (read: deliberately violating regulations that are perceived as unreasonable and unenforceable) drone enthusiasts will force regulatory movement, and this is a good thing. Anderson gave two examples of circumstances that challenge current regulations: Lego Mindstorms being classified by regulators as a cruise missile guidance system (and hence violating export controls), and flying drones in contravention to the FAA regulations governing the use of unmanned aircraft.</p>
<p>Technologists in general (and Silicon Valley in particular) take a dim view of regulations promulgated under the old order (e.g. <a style="font-style: normal; line-height: 24px;" href="http://techcrunch.com/2013/03/17/uber-lyft-sidecar-and-the-so-called-safety-problem/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Lyft, Uber</a>, <a style="font-style: normal; line-height: 24px;" href="http://techcrunch.com/2012/11/09/airbnb-research-data-dump/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">AirBnB</a>), and it&#8217;s true that some aspects of the <a href="http://www.faa.gov/about/initiatives/uas/reg/media/frnotice_uas.pdf" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">FAA regulations</a> are out-of-date and no longer reasonable. But while I’m not completely outraged when technologists upend the status quo to make something new (and improved), this attitude works better in industries that don&#8217;t involve fast-flying heavy objects.</p>
<p>Let&#8217;s remember that the FAA’s primary goal is to keep people from getting killed by aircraft. When it comes to aircraft regulation – manned or unmanned – <a href="http://en.wikipedia.org/wiki/Colgan_Air_Flight_3407" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">people on the ground</a> are the main beneficiaries. We are not talking about regulating a relatively low-risk activity (like renting your room out with AirBnB); we are talking about regulating heavy objects hurtling over the heads of people who haven’t consented to be part of the experiment.</p>
<div class="calloutr">If we follow the path of breaking all the rules, someone is going to accidentally kill a sympathetic bystander. Beyond the personal tragedy this will create, such an accident will set back our industry and the benefits we can provide to society by a decade.</div>
<p>Our society rightly asks the government to ensure that activities that impose risk on others — especially those who did not consent — be minimized. We need to update our regulations, but aircraft operators need to respect the letter and spirit of the law as it stands.  What standards do we have if not the law? If we follow the path of breaking all the rules, someone is going to accidentally kill a sympathetic bystander. Beyond the personal tragedy this will create, such an accident will set back our industry and the benefits we can provide to society by a decade.</p>
<p>In Afghanistan, one of my planes almost smacked into a helicopter, but it was the helicopter – not the drone –  that had come, without clearance or radio calls, into an active artillery firing ROZ (restricted operating zone: this is an airspace control measure that makes sure that aircraft don’t run into artillery fire).  Similarly, the <a href="http://www.flightglobal.com/news/articles/auvsi-rq-7-likely-not-to-blame-for-c-130-collision-360993/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">first full-sized drone and manned aircraft collision</a> involved a C-130 violating airspace control measures around an airfield.</p>
<p>Pilots are not infallible and often break the rules. The best drone operators have a different safety culture: one where there is proper approval for everything, because every move will be recorded and second guessed. Military drone safety culture is a great example of this approach. I hope this culture will permeate the civilian unmanned aircraft community as well.</p>
<div class="calloutl">When we, as a civilian unmanned aircraft industry, can be counted on as strong safety partner, and when people in general and commercial aviation are learning safety lessons from us, there will be no more foot dragging. We will get our airspace and the drone revolution will finally be here.</div>
<p>Although breaking the rules might move us toward our unmanned enabled future a little bit faster, this is an incredibly dangerous path for our industry and our bystanders.  The closing thought of VLAB Drones was that unmanned aircraft will eventually make the airspace safer for all users.  The panel wondered if this was hyperbole, but it is inevitable when drones have a strong safety culture. Conversely, as long as we are the irresponsible jerks of the air, safety conscious regulators like the FAA will be unsupportive of us flying.  When we, as a civilian unmanned aircraft industry, can be counted on as strong safety partner, and when people in general and commercial aviation are learning safety lessons from us, there will be no more foot dragging. We will get our airspace and the drone revolution will finally be here.</p>
<p>In the meantime: seriously, don’t do anything that could kill anyone, please. Especially if it is illegal. You will ruin it for the rest of us.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Joichi Ito interviewed at World Economic Forum</title>
		<link>https://robohub.org/joichi-ito-interviewed-at-world-economic-forum/</link>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Sun, 27 Jan 2013 03:13:27 +0000</pubDate>
				<category><![CDATA[opinions]]></category>
		<category><![CDATA[Media Lab]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[World Economic Forum]]></category>
		<guid isPermaLink="false">http://robohub.org/?p=8015</guid>

					<description><![CDATA[Rana Foroohar, of Time Magazine, in the context of the World Economic Forum, interviewing Joichi Ito, Director of the MIT Media Lab. View on the WEF website]]></description>
										<content:encoded><![CDATA[<p><img decoding="async" src="http://robohub.org/wp-content/uploads/2013/01/Joi-Ito.jpeg"></img></p>
<p><a href="http://business.time.com/author/ranaforoohar/" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Rana Foroohar</a>, of Time Magazine, in the context of the World Economic Forum, <a href="http://www.weforum.org/videos/insight-idea-joichi-ito" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">interviewing</a> <a href="http://www.media.mit.edu/people/joi" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">Joichi Ito, Director of</a> <a href="http://www.media.mit.edu" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">the MIT Media Lab</a>.</p>
<p><a href="http://www.weforum.org/videos/insight-idea-joichi-ito" data-wpel-link="external" target="_blank" rel="follow external noopener noreferrer">View on the WEF website</a></p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Nanoparticle transport in tumors</title>
		<link>https://robohub.org/nanoparticle-transport-in-tumors/</link>
		
		<dc:creator><![CDATA[Sabine Hauert]]></dc:creator>
		<pubDate>Wed, 28 Nov 2012 05:32:17 +0000</pubDate>
				<category><![CDATA[education]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[Nanoparticles]]></category>
		<guid isPermaLink="false">http://robohub.org/?p=5840</guid>

					<description><![CDATA[The idea of nanorobots capable of navigating the body was popularized by the 1966 science fiction flick Fantastic Voyage. Since then, bio-engineers have imagined a variety of nanoparticles that can potentially transport therapies directly to tumors. The challenge is to get these nanoparticles to all the cancer cells they need to treat, in sufficient amounts, [&#8230;]]]></description>
										<content:encoded><![CDATA[<p>The idea of nanorobots capable of navigating the body was popularized by the 1966 science fiction flick <a href="http://www.imdb.com/title/tt0060397/" target="_blank" title="Fantastic Voyage" data-wpel-link="external" rel="follow external noopener noreferrer">Fantastic Voyage</a>. Since then, bio-engineers have imagined a variety of nanoparticles that can potentially transport therapies directly to tumors. The challenge is to get these nanoparticles to all the cancer cells they need to treat, in sufficient amounts, without causing side-effects on healthy tissue.<span id="more-5840"></span><br />
<br />
The video below presents the barriers nanoparticles need to overcome to reach tumor cells and current strategies being considered in research labs to help them along the way.<br />
</p>
<div class=" "><iframe title="Nanoparticle Transport in Tumors - Full Version" width="500" height="281" src="https://www.youtube-nocookie.com/embed/gBYkYzj7CKM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>If you don&#8217;t have 6+ minutes to spare, there is a shorter version <a href="http://youtu.be/CS2AyDM9q14" target="_blank" title="Nanoparticle Transport in Tumors" data-wpel-link="external" rel="follow external noopener noreferrer">here</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Tovbot&#8217;s Shimi at Google I/O</title>
		<link>https://robohub.org/tovbots-shimi-at-google-io/</link>
					<comments>https://robohub.org/tovbots-shimi-at-google-io/#respond</comments>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Fri, 29 Jun 2012 15:39:22 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[entertainment]]></category>
		<category><![CDATA[Georgia Tech]]></category>
		<category><![CDATA[Media Lab]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[music]]></category>
		<guid isPermaLink="false">http://alpha.robohub.org/?p=337</guid>

					<description><![CDATA[http://youtu.be/s6bs1rrOwxo Tovbot&#8217;s Shimi made its first public appearance two days ago at Google I/O, where not just one but three Shimis performed in perfect coordination. Tovbot was formed earlier this year by a group of robot researchers and entrepreneurs hailing from Georgia Tech, IDC in Israel, and MIT Media Lab. [Their] goal is to foster [&#8230;]]]></description>
										<content:encoded><![CDATA[<p>http://youtu.be/s6bs1rrOwxo<br />
<a target="_blank" href="http://tovbot.com/news/1/tovbot-to-unveil-robot-band-at-google-io-after-party" title="news item about Shimi&#039;s performance at Google I/O" data-wpel-link="external" rel="follow external noopener noreferrer">Tovbot&#8217;s Shimi</a> made its first public appearance two days ago at Google I/O, where not just one but three Shimis performed in perfect coordination. <a target="_blank" href="http://tovbot.com/t/aboutus" title="About Us on Tovbot website" data-wpel-link="external" rel="follow external noopener noreferrer">Tovbot</a> was formed earlier this year <q>by a group of robot researchers and entrepreneurs hailing from <a target="_blank" href="http://www.gtcmt.gatech.edu/" title="Georgia Tech Center for Music Technology" data-wpel-link="external" rel="follow external noopener noreferrer">Georgia Tech</a>, <a target="_blank" href="http://www.idc.co.il/" title="IDC website" data-wpel-link="external" rel="follow external noopener noreferrer">IDC in Israel</a>, and <a target="_blank" href="http://www.media.mit.edu/" title="MIT Media Lab website" data-wpel-link="external" rel="follow external noopener noreferrer">MIT Media Lab</a>. [Their] goal is to foster a new paradigm of personal robots &#8211; robots that don&#8217;t just clean your floors or your pool, but also interact with you on a personal, almost human level.</q> According to a <a target="_blank" href="http://mshci.gatech.edu/hg/item/137351" title="news item about Shimi on Georgia Tech&#039;s website" data-wpel-link="external" rel="follow external noopener noreferrer">news item on Georgia Tech&#8217;s website</a>, <q>Shimi, a musical companion developed by Georgia Tech’s Center for Music Technology, recommends songs, dances to the beat and keeps the music pumping based on listener feedback.</q> <a target="_blank" href="http://spectrum.ieee.org/automaton/robotics/home-robots/shimi-musical-robot-unveiled-at-google-io" title="Automaton article about Shimi" data-wpel-link="external" rel="follow external noopener noreferrer">Automaton has more detail.</a></p>
]]></content:encoded>
					
					<wfw:commentRss>https://robohub.org/tovbots-shimi-at-google-io/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>MIT&#8217;s Cheetah acquires new gates</title>
		<link>https://robohub.org/mits-cheetah-acquires-new-gates/</link>
					<comments>https://robohub.org/mits-cheetah-acquires-new-gates/#respond</comments>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Thu, 31 May 2012 16:04:45 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[Boston Dynamics]]></category>
		<category><![CDATA[DARPA]]></category>
		<category><![CDATA[MIT]]></category>
		<guid isPermaLink="false">http://alpha.robohub.org/?p=398</guid>

					<description><![CDATA[In early March, Boston Dynamics posted a video (shown below) showing the Cheetah robot they are developing for DARPA running at 18 miles per hour (a new record for a robot running on legs), without any stabilization straps attached. More recently the MIT Biomimetic Robotics Lab has posted videos of their version of the Cheetah, [&#8230;]]]></description>
										<content:encoded><![CDATA[<div class=" "><iframe title="Trot gait" width="500" height="375" src="https://www.youtube-nocookie.com/embed/U5_OUfCPZd0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
In early March, <a target="_blank" href="http://www.bostondynamics.com/" title="Boston Dynamics website" data-wpel-link="external" rel="follow external noopener noreferrer">Boston Dynamics</a> posted a video (shown below) showing the Cheetah robot they are developing for DARPA running at 18 miles per hour (a new record for a robot running on legs), without any stabilization straps attached.  More recently the <a target="_blank" href="http://sangbae.scripts.mit.edu/biomimetics/" title="MIT Biomimetic Robotics Lab page" data-wpel-link="external" rel="follow external noopener noreferrer">MIT Biomimetic Robotics Lab</a> has posted videos of their version of the Cheetah, first walking (no longer public, as of 08Aug2012), then trotting, with some stabilization (shown above). The MIT version appears to be more complex than the Boston Dynamics version, particularly in the way the legs are jointed, but also in the way the rear legs connect to the rest of the body, although it&#8217;s impossible to tell whether what appear to be vertebrae, in the MIT version, are actually functional as such, from the video alone.</p>
<p>Boston Dynamics&#8217; Cheetah running at 18 mph&#8230;</p>
<div class=" "><iframe title="Cheetah Robot Gallops at 18 mph" width="500" height="281" src="https://www.youtube-nocookie.com/embed/83ULlgpT1UQ?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
]]></content:encoded>
					
					<wfw:commentRss>https://robohub.org/mits-cheetah-acquires-new-gates/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>Aggressive flight using laser scanner, IMU, &#038; 3D map</title>
		<link>https://robohub.org/aggressive-flight-using-laser-scanner-imu-3d-map/</link>
					<comments>https://robohub.org/aggressive-flight-using-laser-scanner-imu-3d-map/#respond</comments>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Wed, 30 May 2012 16:13:31 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[CSAIL]]></category>
		<category><![CDATA[ICRA]]></category>
		<category><![CDATA[MAV]]></category>
		<category><![CDATA[MIT]]></category>
		<guid isPermaLink="false">http://alpha.robohub.org/?p=401</guid>

					<description><![CDATA[Evan Ackerman, writing for IEEE Spectrum&#8217;s Automaton blog, says Researchers at MIT CSAIL have decided that slow and obstacle-free flight is boring, so they’ve come up with a way to get MAVs navigating at high speed, indoors, around obstacles, without needing motion tracking or GPS or beacons or any of that nonsense. All they need [&#8230;]]]></description>
										<content:encoded><![CDATA[<div class=" "><iframe title="State-Estimation For Aggressive Flight in GPS-Denied environments using Onboard Sensing" width="500" height="281" src="https://www.youtube-nocookie.com/embed/VUeKKvKEvYI?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
Evan Ackerman, <a target="_blank" href="http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/laserequipped-mav-demonstrates-aggressive-autonomous-flight" title="Automaton article on MAV which navigates using a laser scanner, IMU, and pre-existing 3D map" data-wpel-link="external" rel="follow external noopener noreferrer">writing for IEEE Spectrum&#8217;s Automaton blog</a>, says</p>
<blockquote><p>Researchers at MIT CSAIL have decided that slow and obstacle-free flight is boring, so they’ve come up with a way to get MAVs navigating at high speed, indoors, around obstacles, without needing motion tracking or GPS or beacons or any of that nonsense. All they need is a little aircraft that can carry a planar laser rangefinder, an IMU, and a pre-existing 3D occupancy map that the MAV can localize itself in.</p></blockquote>
<p>This research has been conducted by the <a target="_blank" href="http://groups.csail.mit.edu/rrg/" title="Robust Robotics Group homepage" data-wpel-link="external" rel="follow external noopener noreferrer">Robust Robotics Group (RRG)</a>, led by <a target="_blank" href="http://web.mit.edu/aeroastro/people/roy.html" title="Professor Nicholas Roy&#039;s personal page" data-wpel-link="external" rel="follow external noopener noreferrer">Nicholas Roy</a>.  <a target="_blank" href="http://groups.csail.mit.edu/rrg/papers/icra12_aggressive_flight.pdf" title="paper on flight using laser scanning and IMU, presented at ICRA" data-wpel-link="external" rel="follow external noopener noreferrer">A paper explaining it in detail</a> was presented at <a target="_blank" href="http://icra2012.org/" title="ICRA 2012 website" data-wpel-link="external" rel="follow external noopener noreferrer">ICRA</a> by graduate student Adam Bry. <a target="_blank" href="http://youtu.be/7nUq28utuGM" title="YouTube video showing quadrotor using laser scanner" data-wpel-link="external" rel="follow external noopener noreferrer">A similar video using a quadrotor</a> (below) appears on the personal page of <a target="_blank" href="http://people.csail.mit.edu/stefie10/" title="Research Scientist Stefanie Tellex&#039;s personal page" data-wpel-link="external" rel="follow external noopener noreferrer">RRG Research Scientist Stefanie Tellex</a>, which is worth a visit for the cat video she&#8217;s also posted! (IMU = Inertial Measurement Unit)</p>
<p>A Voice-Commandable Robotic Helicopter&#8230;</p>
<div class=" "><iframe title="A Voice-Commandable Robotic Helicopter" width="500" height="281" src="https://www.youtube-nocookie.com/embed/7nUq28utuGM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
]]></content:encoded>
					
					<wfw:commentRss>https://robohub.org/aggressive-flight-using-laser-scanner-imu-3d-map/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>Catching up with robots</title>
		<link>https://robohub.org/catching-up-with-robots/</link>
					<comments>https://robohub.org/catching-up-with-robots/#respond</comments>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Mon, 28 May 2012 19:30:10 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[Adept]]></category>
		<category><![CDATA[autonomous]]></category>
		<category><![CDATA[DARPA]]></category>
		<category><![CDATA[Georgia Tech]]></category>
		<category><![CDATA[ICRA]]></category>
		<category><![CDATA[MIT]]></category>
		<category><![CDATA[RE2]]></category>
		<guid isPermaLink="false">http://alpha.robohub.org/?p=404</guid>

					<description><![CDATA[The above video, by Erico Guizzo and Evan Ackerman of IEEE Spectrum, and shows Patrick Rowe, of RE2 (RE-squared), the firm hired by DARPA to build the standard platform for their ARM program, putting a completed unit through its paces at ICRA. A small omni-roller suitable for use as one or more fingers of a [&#8230;]]]></description>
										<content:encoded><![CDATA[<div class=" "><iframe title="The DARPA ARM Robot" width="500" height="281" src="https://www.youtube-nocookie.com/embed/UpyKt6mClVA?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
The above video, by Erico Guizzo and Evan Ackerman of IEEE Spectrum, and shows Patrick Rowe, of <a target="_blank" href="http://www.resquared.com/" title="RE2 website" data-wpel-link="external" rel="follow external noopener noreferrer">RE2 (RE-squared)</a>, the firm hired by DARPA to build the standard platform for <a target="_blank" href="http://thearmrobot.com/aboutProgram.html" title="DARPA ARM Program website" data-wpel-link="external" rel="follow external noopener noreferrer">their ARM program</a>, putting a completed unit through its paces at ICRA.</p>
<p>A small omni-roller suitable for use as one or more fingers of a robotic hand&#8230;</p>
<div class=" "><iframe title="Robotic Omni-Finger" width="500" height="375" src="https://www.youtube-nocookie.com/embed/9nQZbxMANN4?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>An autonomous robotic fish for detecting and finding the source of pollution&#8230;<br />
http://youtu.be/z-XI9MrU1iM</p>
<p>MIT 6.141 Robotics Class Final Challenge for 2012&#8230;</p>
<div class=" "><iframe title="MIT 6.141 Robotics Class Final Challenge 2012" width="500" height="281" src="https://www.youtube-nocookie.com/embed/ll5xFCf2n_o?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Back to ICRA to watch an Adept mobile robot navigating the show floor&#8230;</p>
<div class=" "><iframe title="Mobile Robot Roams Show Floor" width="500" height="281" src="https://www.youtube-nocookie.com/embed/v6QVTIAUsf0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>Another Adept robot being used in research at Cornell&#8230;</p>
<div class=" "><iframe title="Learning to Place Objects: Organizing a Room" width="500" height="281" src="https://www.youtube-nocookie.com/embed/d5dNWjZ9lsM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
<p>And finally, Georgia Tech&#8217;s Travis doing a little dance&#8230;</p>
<div class=" "><iframe title="Travis Dances to the Star Wars Cantina Band" width="500" height="281" src="https://www.youtube-nocookie.com/embed/WpampRh6qX0?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p></p>
]]></content:encoded>
					
					<wfw:commentRss>https://robohub.org/catching-up-with-robots/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>MIT Mediated Matter Group: CNSILK</title>
		<link>https://robohub.org/mit-mediated-matter-group-cnsilk/</link>
					<comments>https://robohub.org/mit-mediated-matter-group-cnsilk/#respond</comments>
		
		<dc:creator><![CDATA[John Payne]]></dc:creator>
		<pubDate>Thu, 03 May 2012 16:09:07 +0000</pubDate>
				<category><![CDATA[articles]]></category>
		<category><![CDATA[Media Lab]]></category>
		<category><![CDATA[MIT]]></category>
		<guid isPermaLink="false">http://alpha.robohub.org/?p=462</guid>

					<description><![CDATA[The Mediated Matter Group within the MIT Media Lab, is dedicated to the development and application of novel processes that enable and support the design of physical matter, and its adaptability to environmental conditions in the creation of form. One of their projects, CNSILK: Computer Numerically Controlled Silk Cocoon Construction, explores the design and fabrication [&#8230;]]]></description>
										<content:encoded><![CDATA[<div class=" "><iframe title="Robotic spider weaves web at MIT Media Lab" width="500" height="281" src="https://www.youtube-nocookie.com/embed/JgeFLGfvrEM?feature=oembed" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe></div>
<p>
The <a target="_blank" href="http://www.media.mit.edu/research/groups/mediated-matter" data-wpel-link="external" rel="follow external noopener noreferrer">Mediated Matter Group</a> within the <a target="_blank" href="http://www.media.mit.edu/" data-wpel-link="external" rel="follow external noopener noreferrer">MIT Media Lab</a>, <q>is dedicated to the development and application of novel processes that enable and support the design of physical matter, and its adaptability to environmental conditions in the creation of form.</q> One of their projects, CNSILK: Computer Numerically Controlled Silk Cocoon Construction, <q>explores the design and fabrication potential of silk fibers—inspired by silkworm cocoons—for the construction of woven habitats.</q> While the material being applied in <a target="_blank" href="http://youtu.be/JgeFLGfvrEM" data-wpel-link="external" rel="follow external noopener noreferrer">the above video</a> may not be silk, the principles being applied to wrapping it around the interior of a tension-providing frame remain the same. <a target="_blank" href="http://phys.org/news/2012-04-robot-arm-mit-web-video.html" data-wpel-link="external" rel="follow external noopener noreferrer">Phys.org</a> has more detail.</p>
]]></content:encoded>
					
					<wfw:commentRss>https://robohub.org/mit-mediated-matter-group-cnsilk/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/?utm_source=w3tc&utm_medium=footer_comment&utm_campaign=free_plugin

Page Caching using Disk: Enhanced 

Served from: robohub.org @ 2026-11-15 02:21:39 by W3 Total Cache
-->