Legged Robots

This story by Landon Hall was first published in the&nbsp;<a href="https://viterbischool.usc.edu/news/2024/04/teaching-robots-to-walk-on-the-moon-and-maybe-rescue-one-another/" target="_blank">USC Viterbi School of Engineering newsroom</a>.Georgia Tech alumna&nbsp;Feifei Qian&nbsp;(M.S. PHYS 2011, Ph.D. ECE 2015), an assistant professor of electrical and computer engineering at the USC Viterbi School of Engineering and School of Advanced Computing, leads the NASA LASSIE project alongside co-investigator&nbsp;Frances Rivera-Hernández, an assistant professor in the School of Earth and Atmospheric Sciences at Georgia Tech.&nbsp;Sharissa Thompson, a graduate student at Georgia Tech, is a student intern on the NASA Curiosity Rover project.The Palmer Glacier on Oregon’s Mount Hood isn’t the moon, but it’s a good place to practice.Some 6,000 feet up the snow-capped mountain, located about 70 miles east of Portland, a multidisciplinary team from the University of Southern California, Texas A&amp;M University, Georgia Institute of Technology, Oregon State University, Temple University, the University of Pennsylvania, and NASA gathered to turn loose a four-legged robot named Spirit into the wild.The team that included engineers, cognitive scientists, geoscientists, and planetary scientists field-tested Spirit as part of the LASSIE Project: Legged Autonomous Surface Science in Analog Environments. Spirit covered a variety of challenging terrains, using his spindly metal legs to amble over, across, and over around shifting dirt, slushy snow, and boulders during five days of testing in summer 2023. Sometimes he expertly traversed the hillside, while at other moments he teetered and fell over — all part of the process to better understand the substrate properties and learn to better walk on these extreme terrains. The practice time Spirit logged produced data that will be used to train future robots for use on intergalactic surfaces, like Earth’s moon and perhaps planets in our solar system.“A legged robot needs to be able to detect what is happening when it interacts with the ground underneath, and rapidly adjust its locomotion strategies accordingly,” says Feifei Qian, an assistant professor of electrical and computer engineering at the USC Viterbi School of Engineering and School of Advanced Computing, which is leading the project funded by NASA. “When the robot leg slips on ice or sinks into soft snow, it inspires us to look for new principles and strategies that can push the boundary of human knowledge and enable new technology. We learn and improve from the observed failures.”Watch this&nbsp;<a href="https://www.youtube.com/watch?v=wBTyelFFE1A" target="_blank">5-minute video</a>&nbsp;produced for the team by documentary filmmaker Sean Grasso.<iframe width="640" height="360" src="https://www.youtube.com/embed/wBTyelFFE1A?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> Spirit learns from every step.“Similar to the way that when we walk on uneven surfaces as humans, we can sort of detect how the ground is shifting beneath our feet, a legged robot is capable of the exact same thing,” says Cristina Wilson, a cognitive scientist at Oregon State University.<h2>The more machines the merrier</h2>Qian’s group doesn’t intend to stop at just one robot, wandering the wilderness alone. She and her former colleagues at Penn, Cynthia Sung, Mark Yim, Daniel Koditschek, and Douglas Jerolmack, received a two-year, $2 million grant from NASA they’re calling the TRUSSES Project: Temporarily, Robots Unite to Surmount Sandy Entrapments, Then Separate. They want to help the space agency put teams of robots on the Moon and have them work together on tasks. They would take the knowledge they came in with, and the data they collect on the mission, and communicate those details to each other.“They would sense how the ground conditions are,” Qian says, “and then exchange that information with one another, and collectively form a map of locomotion risk estimation. The team of robots can then use this traversal risk map to inform their planetary explorations: ‘There is an extremely soft sand patch that might be high-risk for wheeled rovers. Come over here, this might be a safer area.’ ”The robots in mind for this kind of work would be more than just Spirit: There would be a wheeled rover (great for payload and long distances), a Hexapedal robot (intermediate payload but better mobility than the wheeled), and dog-like ones like the rugged version of Spirit (highest mobility, shorter distances). And here’s the coolest part of that research, the part that sounds like something the Transformers would do. Or at least a team of castaways on Survivor: If one got in a jam, made immovable by loose dirt or a rock or a ravine, his bot-mates would arrive and link together and form a bridge, or a pyramid, to hoist their pal to safety. And then back to work.“When they plan for the strategy to pull the robot up, they’ll decide what force to exert and what position the robot should go to, while also compiling the terrain information,” Qian says. “That’s the key idea of how to use these capabilities: to both prevent and recover from locomotion failures in extreme terrain.”<h2>Back to Mount Hood</h2>Spirit gets around a variety of natural environments, to learn how to better move on challenging terrains. Qian has let him off his leash on Southern California beaches, and the multi-university team has field-tested him in the soft granules of White Sands National Park in New Mexico. But <a href="https://youtu.be/wBTyelFFE1A" target="_blank">the video</a> shot at Mount Hood shows just how otherworldly that landscape can be in these planetary-analog environments. This provides Spirit with plenty of opportunities to learn on earth, before potentially exploring other planets.“You look around us, it would be very hard to drive up this,” Ryan Ewing, a geologist from NASA Johnson Space Center, <a href="https://youtu.be/wBTyelFFE1A?feature=shared" target="_blank">shares</a>. “But as a legged being, as humans, we can step around it easily. A dog could walk around it easily. So this project is the proving ground that we can enable new science and new mobility on environments that are like other planets.”In fact, a dog is indeed frisking about: Howard, Wilson’s German shepherd, wandered about, with the kind of agility Spirit could only dream of.“We are going to observe how Howard moves in different types of snow and ice conditions,” Qian <a href="https://youtu.be/wBTyelFFE1A?feature=shared" target="_blank">says</a>. “What exactly, out of those combined motions, allows him to succeed on challenging terrain?”The LASSIE Project calls for two more trips for Spirit: to Mount Hood this summer, and to White Sands next year. The TRUSSES team, from USC and Penn, also plans to visit White Sands next year with Spirit and the other, new, multitasking robots. Imagine WALL-E with friends.<hr>The NASA PSTAR (Planetary Science and Technology Through Analog Research) number for this project is 80NSSC22K1313.

Researchers at Georgia Tech have teamed up with NASA and five peer institutions to teach dog-like robots to navigate craters of the moon and other challenging planetary surfaces.

Good Dog: LASSIE Spirit Learns to Walk on the Moon

In Singapore, DEEP Robotics, in collaboration with its official partner EGP, is participating in the AMR SPPG Tunnel Project of the Singapore Powergrid (SPPG). This project utilizes quadruped robots for power tunnel inspections and integrates related detection systems to provide early warnings for emergencies. This marks the first time domestically-produced quadruped robots have been involved in overseas power industry applications. The relevant team has conducted extensive training and deployment locally.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2OTA1MDQ4LeWbvueJhzEucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib"><blockquote>“Additionally, in South Korea, a factory production line management project employs DEEP Robotics quadruped robots for line meter recognition, tray handling, and component picking” said Zheng Dongxin, Product Manager of DEEP Robotics.</blockquote><h3>Quadruped Robot Applications in 26 Provinces and Cities in China</h3>Public information shows that DEEP Robotics' industrial-grade quadruped robot has served more than 100 clients in 26 provinces and cities in China including Guangzhou, Beijing, Shanghai, Hebei, Shandong, Zhejiang, Hubei, and Anhui. Moreover, in countries such as Singapore, South Korea and more, several DEEP Robotics industry projects have also been implemented, marking the first overseas industry application of domestically-produced quadruped robots.During the recent Spring Festival, quadruped robots stood guard at a certain ±800kV converter station in Hunan Province. Faced with significantly increased pressure on power guarantee during the Spring Festival, it utilized its superior full-process autonomous inspection capabilities and 24-hour all-weather operation capabilities. Equipped with a dual-light gimbal and a series of equipment modules, it replaced humans in conducting inspections in complex and dangerous industrial environments, helping companies identify potential risks, ensuring the smooth operation of Spring Festival power maintenance, and allowing everyone to celebrate the festival with peace of mind.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2NzY4NjYwLeWbvueJhzIuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib">In a substation in Anhui, the "robot dog + drone" low-altitude integrated intelligent operation and maintenance inspection was carried out, achieving autonomous inspection, automatic defect identification, timely detection of equipment operation abnormalities, and improving the reliable power supply capacity of the substation.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2Nzg1OTMyLeWbvueJhzMucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib">At a power station in Guangdong, quadruped robots conducted inspections tirelessly against wind and rain. Compared with traditional intelligent robots, its inspection point quantity increased by 60%. Equipped with dual-light gimbal cameras, it can identify 30 types of power equipment defects and read 9 types of meter readings. Previously, to achieve full coverage of intelligent equipment in substations, at least 9 intelligent robots were required. Now, with just one quadruped robot, it can be achieved, saving 70% of the investment in intelligent operation and maintenance costs. Unlike drones, quadruped robots have rich external device mounting capabilities. The project team attempted to mount a high-precision force-controlled six-axis mechanical arm on the robot body, enabling it to assist in maintenance, support emergency safety operations, and perform emergency breaker operations with high precision under extreme conditions.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2ODA3OTY4LeWbvueJhzQuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib">In a 220 kV cable tunnel in Fujian, maintenance personnel used quadruped cable inspection robots to comprehensively diagnose the health of power equipment. According to media reports, it can timely detect 95% of cable line surface defects, overheating faults, and channel fires, significantly improving inspection efficiency.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2ODQ0MzExLeWbvueJhzUucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib">At the receiving-end station of a ±1100 kV ultra-high voltage direct current transmission line in Anhui, maintenance personnel used quadruped robots and other intelligent devices to conduct inspections to ensure the safe operation of power equipment. With the help of intelligent AI algorithms, autonomous collection, identification, calculation, and diagnostic analysis of equipment status and other data can be achieved.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzEzNTA2ODY2MjIwLeWbvueJhzYucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 100%px;" class="fr-fic fr-dib">In the 8-meter underground power gallery in Hangzhou, since the 19th Asian Games, DEEP Robotics’ quadruped robots have been working for more than half a year. State Grid Zhejiang Electric Power Research Institute, DEEP Robotics, MY Software, and other units have collaborated to perceive the environmental conditions such as temperature and humidity, harmful gas concentrations, and smoke density in the gallery through quadruped robots, and real-time monitoring of cable operation indicators such as protective layer circulation, partial discharge, and operating temperature. With the help of daily intelligent autonomous inspection and weekly intelligent active detection of new equipment, staff only need to inspect once every six months and conduct live measurements once a year, making the work process more streamlined and the inspection results more accurate.Looking at the world, as the wave of "Robot + AI" sweeps across the globe, global industry giants are also accelerating digitization and preparing for quadruped robot industry application projects. Whether the application potential of quadruped robots will explode in 2024 remains to be seen, but it is worth looking forward to! Additionally, DEEP Robotics (Hall 5 D46-3) is set to participate in the Hannover Messe in Germany from April 22nd to 26th. At the event, the quadruped robot will make its debut, showcasing its capabilities. Industrial scenes often involve significant dangers and tedious tasks. Challenges such as stairs, outdoor harsh weather conditions, extreme temperatures, darkness, and other adverse environments hinder traditional robots from entering industrial sites for operations. However, DEEP Robotics' quadruped robot can effectively address these issues.

In Singapore, DEEP Robotics, in collaboration with its official partner EGP, is participating in the AMR SPPG Tunnel Project of the Singapore Powergrid. This project utilizes quadruped robots for power tunnel inspections and integrates related detection systems to provide warnings for emergencies.

DEEP Robotics Lands Applications in Singapore and South Korea! Will Quadruped Robots Experience an Application Boom?

You’ve all heard of – or, more likely, seen – a precision scan by now.In short, it’s a digital model of what is usually a real-world object, system or process. When done well, for all intents and purposes, the scan is indistinguishable from the real deal. That means it can be used in simulations, for change detection, maintenance – and a whole lot more.There are, of course, existing options out there – and some very good ones.But working with partners, InDro Robotics has created a solution for industries we believe will set a new bar for routine, autonomous 2D and 3D digital captures. It’s a big deal – with significant and positive implications for clients across multiple sectors.“This is an overarching solution with use-cases across a wide variety of verticals,” says InDro Robotics Vice-President Peter King.“We’ve done comprehensive testing of this full-stack solution, and the results have been phenomenal. We are now preparing to roll this out to clients in the industrial sector and beyond.”Below: <a href="https://indrorobotics.ca/precisionscanning/" target="_blank" rel="noopener noreferrer">InDro’s precision scan solution</a>, working a warehouse in California<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1712764391157-A8A5300-scaled.webp" style="width: 100%px;" class="fr-fic fr-dib" alt="Digital Twin Scanning Robot"><h3 id="isPasted">Comprehensive Digital Twin Solution</h3>InDro’s new industrial scanning solution for digital twin creation brings millimetre-precision to the capturing process.Using a quadruped as a platform, InDro has outfitted the robot with the latest in sensors, including a new Leica LiDAR unit (the system includes three LiDAR units, plus depth cameras and more). The system is capable of true GPS-denied SLAM, exploring a brand new environment while capturing a high-precision 3D or 2D scan.What’s more, with an onboard Machine Vision library, the system is capable of object detection and classification. Use-cases include:<ul><li>Building a precise plan of a manufacturing or warehousing space</li><li>3PL (Third Party Logistics) applications</li><li>Change detection for construction, inventory</li><li>Scans in GPS-denied locations, such as mines or caves (and even some buildings)</li></ul>And that is literally just scratching the surface.“From a manufacturing point of view, for example, if we create a very accurate precision scan, a digital copy of an entire facility can then be used to remanufacture another manufacturing facility,” says King.&nbsp;<h3>Existing Solutions&nbsp;</h3>We’ve all seen digital twins before. Often these are captures of the exteriors or buildings or some other infrastructure (bridges, power lines, pipelines, railroads etc.) where the client is looking for change detection. What is different during this scan vs. the previous one? Is the anomaly going to present an immediate or future problem? Is construction proceeding at the correct pace? Is it time to oder more drywall?Such scans, clearly, can provide very useful data.Though robots (and drones) have been stepping into the interior scanning space, the robotics industry (with few exceptions) is in the early phase of both implementation and adoption. This means many sites still rely on manual scanning: A human being walking around the space with a handheld sensor (usually LiDAR) that creates a point cloud.“Traditionally, this has been done manually,” explains King. “In a lot of cases, it’s required really expensive professionals to travel to come on-site with their own very expensive equipment.”InDro’s precision scan – despite being a complex and comprehensive solution – offers a simpler and more cost-efficient means of capture. Quite simply, our robot is deployed on site to explore the areas the client wants captured. That could be a warehouse floor or an entire, multi-level building. When the robot needs to take a break and re-charge, it returns to its base for a wireless power-up.“It’s traditionally been extremely costly to go and collect this data,” says King. “What we’re offering is a service where we bring the robot, let it work throughout its day, and process the data. Clients will get their scans more affordably, more efficiently – and be in a position to do it more frequently in a cost-effective manner.”<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1712764457272-A8A5304-scaled.webp" style="width: 100%px;" class="fr-fic fr-dib" alt="Digital Twin Solution"><h3 id="isPasted">Fast, Efficient, Accurate</h3>There’s a wide array of businesses, particularly in supply chain and manufacturing, that frequently update their 2D floor plans. When new tooling or machinery is installed or other physical changes to the location infrastructure take place, companies need to update their digital twin to reflect those alterations. Typically, this is still done manually.“A 2D CAD model is generally done by somebody that’s doing measurements by hand,” says VP King.Wouldn’t it be easier (and less prone to error) to have a fully autonomous robot do the work?“With this precision scan we would let the quadruped run in that new area – wherever things have changed – and automatically update their old file and have a fresh and accurate 2D CAD within a number of hours.”&nbsp;<h3>Tightly Integrated Solution</h3>InDro’s precision scanning solution was built from the ground up to be robust, reliable and – above all – highly accurate. It’s also fast, capable of capturing a 2D scan of even a large facility in less time than a single human shift. (2D scans are often of greater importance, pending the sector, but our solution is equally capable with 3D captures.)“The goal in developing this product has always been about giving clients affordable access to the best and most integrated technology,” says King. “We now have a full-stack solution available for on-demand scans, whether 2D or 3D, indoors or outdoors, and at a price point that makes this a true value proposition for our customers.”Below: Another look at InDro’s new precision scanning solution:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1712764517883-A8A5296-scaled.webp" style="width: 100%px;" class="fr-fic fr-dib" alt="Precision Scanning for Digital Twins"><h3 id="isPasted">InDro's Take</h3>We’re obviously proud of this technological accomplishment. We’ve proven this solution both internally and in large warehouse settings in the US – and are gearing up for commercial deployment at scale.“R&amp;D is an exciting but also challenging space,” says InDro Robotics CEO Philip Reece.“We are very selective in the projects we pursue – choosing to innovate and build things only when there’s a clear purpose or a clear client. In this case, it was obvious there was a need for an autonomous, precise solution for companies that require regular or even one-off scans. We are confident in our solution – because we’ve seen the results.”There is, of course, much more behind the technology. But we have to balance how much we reveal with the competitive nature of the market. We can, however, state that this is a proven solution that produces incredible results.Interested in more information? Contact us <a href="https://indrorobotics.ca/connectwithanexpert/" target="_blank">here.</a>

Unveiling a Distinctive Approach for Digital Twin Creation and Industrial Scanning

A New Solution for Autonomous Digital Twins and Industrial Scanning

ANYmal has for some time had no problem coping with the stony terrain of Swiss hiking trails. Now researchers at ETH Zurich have taught this quadrupedal robot some new skills: it is proving rather adept at parkour, a sport based on using athletic manoeuvres to smoothly negotiate obstacles in an urban environment, which has become very popular. ANYmal is also proficient at dealing with the tricky terrain commonly found on building sites or in disaster areas.To teach ANYmal these new skills, two teams, both from the group led by ETH Professor Marco Hutter of the Department of Mechanical and Process Engineering, followed different approaches.<h2>Exhausting the mechanical options</h2>Working in one of the teams is ETH doctoral student Nikita Rudin, who does parkour in his free time. “Before the project started, several of my researcher colleagues thought that legged robots had already reached the limits of their development potential,” he says, “but I had a different opinion. In fact, I was sure that a lot more could be done with the mechanics of legged robots.”With his own parkour experience in mind, Rudin set out to further push the boundaries of what ANYmal could do. And he succeeded, by using machine learning to teach the quadrupedal robot new skills. ANYmal can now scale obstacles and perform dynamic manoeuvres to jump back down from them.<iframe width="640" height="360" src="https://www.youtube.com/embed/REvNnUzVDAA?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;</iframe>(Video: ETH Zurich / Nicole Davidson)In the process, ANYmal learned like a child would – through trial and error. Now, when presented with an obstacle, ANYmal uses its camera and artificial neural network to determine what kind of impediment it’s dealing with. It then performs movements that seem likely to succeed based on its previous training.Is that the full extent of what’s technically possible? Rudin suggests that this is largely the case for each individual new skill. But he adds that this still leaves plenty of potential improvements. These include allowing the robot to move beyond solving predefined problems and instead asking it to negotiate difficult terrain like rubble-strewn disaster areas.<h2>Combining new and traditional technologies</h2>Getting ANYmal ready for precisely that kind of application was the goal of the other project, conducted by Rudin’s colleague and fellow ETH doctoral student Fabian Jenelten. But rather than relying on machine learning alone, Jenelten combined it with a tried-and-tested approach used in control engineering known as model-based control. This provides an easier way of teaching the robot accurate manoeuvres, such as how to recognise and get past gaps and recesses in piles of rubble. In turn, machine learning helps the robot master movement patterns that it can then flexibly apply in unexpected situations. “Combining both approaches lets us get the most out of ANYmal,” Jenelten says.As a result, the quadrupedal robot is now better at gaining a sure footing on slippery surfaces or unstable boulders. ANYmal is soon also to be deployed on building sites or anywhere that is too dangerous for people – for instance to inspect a collapsed house in a disaster area.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzExNDk3MTQwNDIwLWltYWdlLmltYWdlZm9ybWF0LjEyODYuMTg0OTg5MDA4Ny5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 100%px;" class="fr-fic fr-dib">ANYmal on a civil defence training ground. (Photograph: ETH Zurich / Fabian Jenelten)<hr><h2 id="isPasted">References</h2>Hoeller D, Rudin N, Sako D, Hutter M: ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots, Science Robotics, 13 March 2024, doi: <a href="https://doi.org/10.1126/scirobotics.adi7566" target="_blank">external page10.1126/scirobotics.adi7566call_made</a>Jenelten F, He J, Farshidian F, Hutter M: DTC: Deep Tracking Control. Science Robotics 2024, 17: eadh5401, doi: <a href="https://doi.org/10.1126/scirobotics.adh5401" target="_blank">external page10.1126/scirobotics.adh5401call_made</a>

The quadrupedal robot ANYmal practises parkour in a hall at ETH Zurich. (Photograph: ETH Zurich / Nikita Rudin)

The quadrupedal robot ANYmal went back to school and has learned a lot. ETH Zurich researchers used machine learning to teach it new skills: the robot can now climb over obstacles and successfully negotiate pitfalls.

ANYmal can do parkour and walk across rubble

The New B2 and Go2

A Look at the Newest Unitree Quadrupeds

Small robots are important tools for the investigation and inspection of, well, small spaces. They can carefully place their steps, allowing them to navigate around obstacles, capabilities larger robots do not always possess. This can enable them to inspect machinery or search through rubble in disaster scenarios that other robots cannot reach. However, due to their size constraints, building small robots that can steer themselves and carry their own power sources is difficult.<a href="https://engineering.cmu.edu/directory/bios/johnson-aaron.html" target="_blank">Aaron Johnson</a>, an associate professor of <a href="https://www.meche.engineering.cmu.edu/index.html" rel="noopener" target="_blank">mechanical engineeringOpens in new window</a>, and <a href="https://engineering.cmu.edu/directory/bios/bergbreiter-sarah.html" target="_blank">Sarah Bergbreiter</a>, a professor of mechanical engineering, and their team of researchers revolutionized the field with the construction of “Mugatu,” the first steerable bipedal robot that contains only a single motor. Mugatu is also self-contained and self-starting; open-loop stable in its gait; and has controlled left, right, and straight steering. The design uses two rigid bodies and one actuator, a simple walker design that is still capable of complex motions of other robots.<iframe width="640" height="360" src="https://www.youtube.com/embed/RLjmxp9vyTY?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;&nbsp;&nbsp;&nbsp;</iframe>“The first direction of the project was aimed at simplifying the way robots walk as much as possible,” says first author James Kyle, a recent mechanical engineering master’s and bachelor’s graduate. “Once we understand how scaling affects locomotion, it can be extremely useful for taking something that already exists and scaling it up or down to do things like fit through smaller pipes or carry more load.”Another team member, undergraduate mechanical engineering student Kendall Hart, worked on the robot’s current sensor, the part of the robot that allowed the team to calculate the total cost of transport, the amount of energy used over a certain distance. “Before I came into the lab, I had a vague understanding of MATLAB, (a programming and numeric computing platform) but working on this project allowed me to apply what I learned in class. When we were working on implementing the current sensor, there was a lot of debugging there, but now it’s made me more confident in debugging without my mentors,” Hart says.<blockquote>What makes the project so special and so impactful in the community is because it’s never been seen before.<cite>Kendall Hart, <cite id="isPasted">student (junior)<cite id="isPasted">, Mechanical Engineering</cite></cite> </cite></blockquote>Nicknamed “The LEGO Project,” the team aims to eventually get these walkers down to the size of a LEGO. “It’s going to take a while because the mechanics of everything changes as you start down-sizing,” Hart says. “But what makes the project so special and so impactful in the community is because it’s never been seen before.” The drastic simplification of this walking device combined with its single degree of freedom is a promising step (pun intended) toward highly-efficient small robots.The collaborators on this project include James Kyle, Justin Y. Kim, Kendall Hart, Sarah Bergbreiter, and Aaron Johnson.

A team of mechanical engineering researchers create “Mugatu,” the first steerable bipedal robot with only one motor.

Big picture, small robot

On November 3, Unitree Robotics released the new industrial quadruped robot B2, continuing to lead the global quadruped robot industry application.

Unitree Robotics Releases Industrial Quadruped Robot B2, Breaking Through Limits with Hyper Evolution!

In this episode, we discuss a joint endeavor led by ETH Zurich to leverage robotic teams to explore the lunar surface for precious materials.

Podcast: Robotic Pioneers on the Moon's Surface

Unitree launched its first humanoid robot H1 on August 15. Showcasing six months of hard work, the H1 humanoid stands about 71 inches (1800mm) tall, but only weighs about 100 lbs (47kg) and boasts unmatched power.

Meet the Unitree H1: a humanoid general-purpose robot starts a new industrial revolution!

On 12 July, Unitree unveiled its latest quadruped robot - the Unitree Go2, which features embodied AI technology, standard 4D ultra-wide LiDAR and GPT empowerment. This product is expected to revolutionize the consumer-grade quadruped robots industry, leading to a transformation of the sector.  

Revolution: A New Quadruped Robot of Embodied AI

This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/d276c196-937b-457c-ace1-49478d943a8b?dark=false" class="fr-draggable" data-gtm-yt-inspected-10="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>On the Moon, there are raw materials that humanity could one day mine and use. Various space agencies, such as the European Space Agency (ESA), are already planning missions to better explore Earth’s satellite and find minerals. This calls for appropriate exploration vehicles. Swiss researchers led by ETH Zurich are now pursuing the idea of sending not just one solitary rover on an exploration tour, but rather an entire team of vehicles and flying devices that complement each other.The researchers equipped three ANYmal – a type of legged robot developed at ETH – with a range of measuring and analysis instruments that would potentially make them suitable exploration devices in the future. They tested these robots on various terrains in Switzerland and at the European Space Resources Innovation Centre (ESRIC) in Luxembourg, where, a few months ago, the Swiss team won a European competition for lunar exploration robots together with colleagues from Germany. The competition involved finding and identifying minerals on a test site modelled after the surface of the Moon. In the latest issue of the journal <a href="https://doi.org/10.1126/scirobotics.ade9548" target="_blank">Science Robotics</a>, the scientists describe how they go about exploring an unknown terrain using a team of robots.<h2>Insurance against failure</h2>“Using multiple robots has two advantages,” explains Philip Arm, a doctoral student in the group led by ETH Professor Marco Hutter. “The individual robots can take on specialised tasks and perform them simultaneously. Moreover, thanks to its redundancy, a robot team is able to compensate for a teammate’s failure.” Redundancy in this case means that important measuring equipment is installed on several robots. In other words, redundancy and specialisation are opposing goals. “Getting the benefits of both is a matter of finding the right balance,” Arm says.<iframe width="640" height="360" src="https://www.youtube.com/embed/bqwbQzVrzkQ?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true" data-gtm-yt-inspected-10="true" id="168277725" title="Robots for Lunar Exploration">&nbsp;</iframe>(Video: ETH Zurich with footage from the University of Zurich / IT Services, MELS)&nbsp;The researchers at ETH Zurich and the Universities of Basel, Bern and Zurich solved this problem by equipping two of the legged robots as specialists. One robot was programmed to be particularly good at mapping the terrain and classifying the geology. It used a laser scanner and several cameras – some of them capable of spectral analysis – to gather initial clues about the mineral composition of the rock. The other specialist robot was taught to precisely identify rocks using a Raman spectrometer and a microscopy camera.The third robot was a generalist: it was able to both map the terrain and identify rocks, which meant that it had a broader range of tasks than the specialists. However, its equipment meant that it could perform these tasks with less precision. “This makes it possible to complete the mission should any one of the robots malfunction,” Arm says.<h2>Combination is key</h2>At the ESRIC and ESA Space Resources Challenge, the jury was particularly impressed that the researchers had built redundancy into their exploration system to make it resilient to potential failures. As a prize, the Swiss scientists and their colleagues from the FZI Research Center for Information Technology in Karlsruhe, were awarded a one-year research contract to further develop this technology. In addition to legged robots, this work will also involve robots with wheels, building on the FZI researchers’ experience with such robots.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg5MzI0NTY5ODI1LWltYWdlLmltYWdlZm9ybWF0LjEyODYuMTE1MTEzNjAzNC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">The Swiss team with one of their legged robots and astronaut Matthias Maurer (centre) at the Space Resources Challenge. (Photograph: ETH Zurich)&nbsp;“Legged robots like our ANYmal cope well in rocky and steep terrain, for example when it comes to climbing down into a crater,” explains Hendrik Kolvenbach, a senior scientist in Professor Hutter’s group. Robots with wheels are at a disadvantage in these kinds of conditions, but they can move faster on less challenging terrain. For a future mission, it would therefore make sense to combine robots that differ in terms of their mode of locomotion. Flying robots could also be added to the team.The researchers also plan to make the robots more autonomous. Presently, all data from the robots flows into a control centre, where an operator assigns tasks to the individual robots. In the future, semi-autonomous robots could directly assign certain tasks to each other, with control and intervention options for the operator.<hr><h2 id="isPasted">Reference</h2>Arm P, Waibel G, Preisig J, Tuna T, Zhou R, Bickel V, Ligeza G, Miki T, Kehl F, Kolvenbach H, Hutter M: Scientific Exploration of Challenging Planetary Analog Environments with a Team of Legged Robots. Science Robotics, 12 June 2023, doi: <a href="https://doi.org/10.1126/scirobotics.ade9548" target="_blank">10.1126/scirobotics.ade9548</a>

A team is greater than the sum of its parts – the trio of legged robots during a test in a Swiss gravel quarry. (Photograph: ETH Zurich / Takahiro Miki)

Swiss engineers are training legged robots for future lunar missions that will search for minerals and raw materials. To ensure that the robots can continue to work even if one of them malfunctions, the researchers are teaching them teamwork.

Robot team on lunar exploration tour

<h3 id="isPasted"><iframe width="640" height="360" src="https://www.youtube.com/embed/Qozjbn0nE-I?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></h3><h3>Background</h3>Cable tunnels are essential for urban power transmission, especially for ultra-high-voltage cables requiring complex networks and flexible layouts. However, cable tunnels also face many challenges in terms of construction and maintenance, such as seepage, gas explosion, dust pollution, and partial discharge.&nbsp;Traditional cable tunnel inspection methods are labour-intensive, time-consuming, subjective, and unsafe. They usually involve many trained operators to conduct regular inspections for hours, shortening the time for analyzing reports for the day. Moreover, the operators have to enter the tunnel environment that may be full of poisonous gases, high-voltage cables, and other electrical equipment, which greatly threatens their health and safety.Therefore, there is an urgent need for a new technology that can improve the efficiency, accuracy, and safety of cable tunnel inspection. <h3 id="isPasted"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg5MDY1NTc3NjMxLURlZXAgUm9ib3RpY3MgMS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">X20 has the capability to traverse rugged terrain Solution</h3>DEEP Robotics is a leading company in the field of quadruped robot industrial applications in China, which cooperates with Jiangsu Mingyue Software Technology to develop an intelligent cable tunnel inspection system that integrates various detection methods such as partial discharge, temperature detection, video monitoring, and defect warning. The system uses a four-legged robot equipped with partial discharge sensors on the robotic arm and a Bi-spectrum camera to inspect multiple cables along a planned route in the tunnel environment and upload the data in real-time. The system can greatly reduce the number of times and frequency of inspection personnel entering the cable tunnel and improve maintenance efficiency and safety.The X20 robot dog can perform automatic inspection tasks according to the preset path and tasks. During the inspection, the robot uses LiDAR and depth cameras to detect the terrain and can turn around, climb stairs and obstacle avoidance. The six-degree-of-freedom robotic arm can flexibly perform cable detection work with trajectory restorations in a narrow tunnel space.The partial discharge detection device can detect discharge signals from 0 MHz to 100 MHz, and accurately identify surface discharge, corona discharge and internal discharge of cables within 200 meters, providing early warning of risks to ensure safe operation.&nbsp;The Bi-spectrum camera features video monitoring and infrared temperature scouting for video and photo capture, identifying temperature differences with an AI algorithm to find out overheated points for early warning.All collected data can be transmitted to the server in real-time through network devices and timely synchronize information with the staff responsible for monitoring in the background, providing data support for further decision analysis for maintenance personnel. <img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg5MDY1NjU1NTgwLURlZXAgUm9ib3RpY3MgMy5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">Partial discharge detection with a robotic arm <h3>Benefits</h3>The X20 intelligent cable tunnel inspection system with mobile partial discharge detection has brought many benefits to the power industry, such as:&bull; &nbsp; &nbsp;Improving the efficiency of cable tunnel inspection by reducing the time of inspection and data analysis.&bull; &nbsp; &nbsp;Improving the accuracy of cable tunnel inspection by using objective and quantitative data from multiple sensors instead of relying on subjective and qualitative judgments from human operators.&bull; &nbsp; &nbsp;Improving the safety of cable tunnel inspection by minimizing the exposure of human operators to hazardous environments such as poisonous gases, high-voltage cables, and other electrical equipment.&bull; &nbsp; &nbsp;Improving the reliability and safety of the power supply by detecting and preventing potential faults caused by partial discharge in advance, avoiding fire or breakdown accidents.

The X20 robot dog can perform automatic inspection tasks according to the preset path and tasks. During the inspection, the robot uses LiDAR and depth cameras to detect the terrain, and has the ability to turn around, climb stairs, and obstacle avoidance. 

How X20 Robot Dog Intelligent Cable Tunnel Inspection System Complete Mobile Detection

One of the newest versions of its dexterous intelligent robot dog, Lite3, has now launched in Europe. It combines advanced mobility and an open modular structure for education, research and innovative entertainment.&nbsp;<iframe width="640" height="360" src="https://www.youtube.com/embed/NNkxlKLMoMM?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe>The new Lite3 series offers four product models: a basic model designed for technology enthusiasts; and three more advanced versions intended for scientific study purposes. With new features that include DEEP Robotics&rsquo; latest proprietary limb joints, control systems and advanced algorithms, Lite3 has a more powerful, quick and durable movement capability. It also offers robust scalability that can be ramped up by installing more modules.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1685346634643-1E57E160-8E6D-4B25-BF27-ED02B809BE3D-11136-000001DE250C2148.png" style="width: 300px;" class="fr-fic fr-dib">Lite3 product parametersMajor design upgradeThe new version incorporates significant technological advances on Lite2. The latest robot dog has proprietary leg-joint technology that provides far greater strength and drive, with torque increased by 50%. The high-torque joint drive module offers extremely high torque density, response bandwidth and reversed transmission efficiency, enhanced rotation stability, and less power consumption.&nbsp;The payload of Lite3 is 40% greater than that of its predecessor. It can carry loads of up to 7.5 kilograms. Its endurance in terms of time and range has nearly doubled. The Lite3 can operate for up to 90 minutes and has a range of 5km.&nbsp;The Lite3 features an industrial-level real-time control system with depth optimization, a first for the product lineup, with overall computing power increased threefold. The Lite 3 can climb steps up to 15 cm in height, close to the current maximum for a quadruped robot of its size, and runs at a peak speed of 4ms-1. It can also perform horizontal jumps, high jumps, front flips and other similarly difficult manoeuvres. The algorithm upgrades make its movement more agile and responsive. <img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjg0ODIzNjcyNTA5LTMucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 516px;" class="fr-fic fr-dib">Lite 3: Advanced mobilities of high jumps, horizontal jumps, and front flips<h3 id="isPasted">How can quadruped robots help with academic research?</h3>Quadruped robots can be beneficial for academic research. They differ from two-legged, wheeled or tracked robots because they can navigate multiple terrains and perform high-risk tasks without endangering human life. Quadruped robots can be used in various fields, such as locomotion and biomechanics studies, refining robotics algorithms and control systems, artificial intelligence and machine learning, and human-robot interaction. These robots can provide researchers with valuable insights and help advance scientific knowledge across multiple disciplines.DEEP Robotics&rsquo; robot dogs are already used by some universities, including Tsinghua, Peking and Edinburgh, and University College London. The new Lite3 is positioned to be affordable for research purposes as well as for robotics enthusiasts.<h3>Open modular structure</h3>The open modular structure and interfaces of the Lite3 make it highly scalable and flexible in its capabilities. Modules such as ones for Real-Time Kinematic (RTK), artificial intelligence, edge processing and other types of sensors can be readily added.&nbsp;To enhance its navigation across very challenging terrain, the Lite3 provides levelled&ndash;perception capability interfaces (SDK, API) combined with LiDAR (Light Detection and Ranging) and depth camera to develop auto-navigation, auto-stop, obstacle avoidance, visual positioning, 3D scanning and other perceptional abilities.&nbsp; To find out more about where you can purchase a Lite3 quadruped robot, visit our <a href="https://www.deeprobotics.cn/en/index/product1.html" rel="noopener noreferrer" target="_blank">website</a>.

Lite3: new technology for increased strength, agility, mobility, speed, navigation, and endurance

Advanced mobility and modular functions allow complex moves such as front flipping.

Quadruped robot with advanced front flipping mobility

Jueying X20 can complete unmanned detection and rescue tasks in harsh conditions

With the flexibility to deliver unmanned detection and rescue services, Jueying X20 is designed for the complex terrain of a post-earthquake landscape, the insides of vulnerable debris buildings, tunnel traffic accidents, and in toxic, hypoxia, and high-density smoke environments created by chemical pollution or disaster event.

Jueying X20 Robot Dog Hazard Detection Rescue Solution

This article was first published on&nbsp;<a href="https://news.mit.edu/2023/legged-robotic-system-playing-soccer-various-terrains-0403" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>. &nbsp;<hr>If you&#39;ve ever played soccer with a robot, it&#39;s a familiar feeling. Sun glistens down on your face as the smell of grass permeates the air. You look around. A four-legged robot is hustling toward you, dribbling with determination.&nbsp;While the bot doesn&rsquo;t display a Lionel Messi-like level of ability, it&#39;s an impressive in-the-wild dribbling system nonetheless. Researchers from MIT&#39;s Improbable Artificial Intelligence Lab, part of the Computer Science and Artificial Intelligence Laboratory (CSAIL), have developed a legged robotic system that can dribble a soccer ball under the same conditions as humans. The bot used a mixture of onboard sensing and computing to traverse different natural terrains such as sand, gravel, mud, and snow, and adapt to their varied impact on the ball&rsquo;s motion. Like every committed athlete, &quot;DribbleBot&quot; could get up and recover the ball after falling.&nbsp;Programming robots to play soccer has been an active research area for some time. However, the team wanted to automatically learn how to actuate the legs during dribbling, to enable the discovery of hard-to-script skills for responding to diverse terrains like snow, gravel, sand, grass, and pavement. Enter, simulation.&nbsp;A robot, ball, and terrain are inside the simulation &mdash; a digital twin of the natural world. You can load in the bot and other assets and set physics parameters, and then it handles the forward simulation of the dynamics from there. Four thousand versions of the robot are simulated in parallel in real time, enabling data collection 4,000 times faster than using just one robot. That&#39;s a lot of data.&nbsp;<iframe width="640" height="360" src="https://www.youtube.com/embed/bV4ek-zI3CU?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe>Video: MIT CSAIL&nbsp;The robot starts without knowing how to dribble the ball &mdash; it just receives a reward when it does, or negative reinforcement when it messes up. So, it&#39;s essentially trying to figure out what sequence of forces it should apply with its legs. &quot;One aspect of this reinforcement learning approach is that we must design a good reward to facilitate the robot learning a successful dribbling behavior,&quot; says MIT PhD student Gabe Margolis, who co-led the work along with Yandong Ji, research assistant in the Improbable AI Lab. &quot;Once we&#39;ve designed that reward, then it&#39;s practice time for the robot: In real time, it&#39;s a couple of days, and in the simulator, hundreds of days. Over time it learns to get better and better at manipulating the soccer ball to match the desired velocity.&quot;&nbsp;The bot could also navigate unfamiliar terrains and recover from falls due to a recovery controller the team built into its system. This controller lets the robot get back up after a fall and switch back to its dribbling controller to continue pursuing the ball, helping it handle out-of-distribution disruptions and terrains.&nbsp;&quot;If you look around today, most robots are wheeled. But imagine that there&#39;s a disaster scenario, flooding, or an earthquake, and we want robots to aid humans in the search-and-rescue process. We need the machines to go over terrains that aren&#39;t flat, and wheeled robots can&#39;t traverse those landscapes,&quot; says Pulkit Agrawal, MIT professor, CSAIL principal investigator, and director of Improbable AI Lab.&quot; The whole point of studying legged robots is to go terrains outside the reach of current robotic systems,&quot; he adds. &quot;Our goal in developing algorithms for legged robots is to provide autonomy in challenging and complex terrains that are currently beyond the reach of robotic systems.&quot;&nbsp;The fascination with robot quadrupeds and soccer runs deep &mdash; Canadian professor Alan Mackworth first noted the idea in a paper entitled &quot;On Seeing Robots,&quot; presented at VI-92, 1992. Japanese researchers later organized a workshop on &quot;Grand Challenges in Artificial Intelligence,&quot; which led to discussions about using soccer to promote science and technology. The project was launched as the Robot J-League a year later, and global fervor quickly ensued. Shortly after that, &quot;RoboCup&quot; was born.&nbsp;Compared to walking alone, dribbling a soccer ball imposes more constraints on DribbleBot&#39;s motion and what terrains it can traverse. The robot must adapt its locomotion to apply forces to the ball to &nbsp;dribble. The interaction between the ball and the landscape could be different than the interaction between the robot and the landscape, such as thick grass or pavement. For example, a soccer ball will experience a drag force on grass that is not present on pavement, and an incline will apply an acceleration force, changing the ball&rsquo;s typical path. However, the bot&#39;s ability to traverse different terrains is often less affected by these differences in dynamics &mdash; as long as it doesn&#39;t slip &mdash; so the soccer test can be sensitive to variations in terrain that locomotion alone isn&#39;t.&nbsp;&quot;Past approaches simplify the dribbling problem, making a modeling assumption of flat, hard ground. The motion is also designed to be more static; the robot isn&rsquo;t trying to run and manipulate the ball simultaneously,&quot; says Ji. &quot;That&#39;s where more difficult dynamics enter the control problem. We tackled this by extending recent advances that have enabled better outdoor locomotion into this compound task which combines aspects of locomotion and dexterous manipulation together.&quot;On the hardware side, the robot has a set of sensors that let it perceive the environment, allowing it to feel where it is, &quot;understand&quot; its position, and &quot;see&quot; some of its surroundings. It has a set of actuators that lets it apply forces and move itself and objects. In between the sensors and actuators sits the computer, or &quot;brain,&quot; tasked with converting sensor data into actions, which it will apply through the motors. When the robot is running on snow, it doesn&#39;t see the snow but can feel it through its motor sensors. But soccer is a trickier feat than walking &mdash; so the team leveraged cameras on the robot&#39;s head and body for a new sensory modality of vision, in addition to the new motor skill. And then &mdash; we dribble.&nbsp;&quot;Our robot can go in the wild because it carries all its sensors, cameras, and compute on board. That required some innovations in terms of getting the whole controller to fit onto this onboard compute,&quot; says Margolis. &quot;That&#39;s one area where learning helps because we can run a lightweight neural network and train it to process noisy sensor data observed by the moving robot. This is in stark contrast with most robots today: Typically a robot arm is mounted on a fixed base and sits on a workbench with a giant computer plugged right into it. Neither the computer nor the sensors are in the robotic arm! So, the whole thing is weighty, hard to move around.&quot;There&#39;s still a long way to go in making these robots as agile as their counterparts in nature, and some terrains were challenging for DribbleBot. Currently, the controller is not trained in simulated environments that include slopes or stairs. The robot isn&#39;t perceiving the geometry of the terrain; it&#39;s only estimating its material contact properties, like friction. If there&#39;s a step up, for example, the robot will get stuck &mdash; it won&#39;t be able to lift the ball over the step, an area the team wants to explore in the future. The researchers are also excited to apply lessons learned during development of DribbleBot to other tasks that involve combined locomotion and object manipulation, quickly transporting diverse objects from place to place using the legs or arms.&ldquo;DribbleBot is an impressive demonstration of the feasibility of such a system in a complex problem space that requires dynamic whole-body control,&rdquo; says Vikash Kumar, a research scientist at Facebook AI Research who was not involved in the work. &ldquo;What&rsquo;s impressive about DribbleBot is that all sensorimotor skills are synthesized in real time on a low-cost system using onboard computational resources. While it exhibits remarkable agility and coordination, it&rsquo;s merely &#39;kick-off&rsquo; for the next era. Game-On!&rdquo;The research is supported by the DARPA Machine Common Sense Program, the MIT-IBM Watson AI Lab, the National Science Foundation Institute of Artificial Intelligence and Fundamental Interactions, the U.S. Air Force Research Laboratory, and the U.S. Air Force Artificial Intelligence Accelerator. The paper will be presented at the 2023 IEEE International Conference on Robotics and Automation (ICRA).<hr>&quot;Reprinted with permission of&nbsp;<a href="https://news.mit.edu/2023/legged-robotic-system-playing-soccer-various-terrains-0403" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>&quot; &nbsp;

Researchers created DribbleBot, a system for in-the-wild dribbling on diverse natural terrains including sand, gravel, mud, and snow using onboard sensing and computing. In addition to these football feats, such robots may someday aid humans in search-and-rescue missions. Photo: Mike Grimmett/MIT CSAIL

“DribbleBot” can maneuver a soccer ball on landscapes such as sand, gravel, mud, and snow, using reinforcement learning to adapt to varying ball dynamics.