Tag Archives: interacting
#437608 Video Friday: Agility Robotics Raises ...
Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):
IROS 2020 – October 25-29, 2020 – [Online]
ROS World 2020 – November 12, 2020 – [Online]
CYBATHLON 2020 – November 13-14, 2020 – [Online]
ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA
Let us know if you have suggestions for next week, and enjoy today’s videos.
Digit is now in full commercial production and we’re excited to announce a $20M funding rounding round co-led by DCVC and Playground Global!
Digits for everyone!
[ Agility Robotics ]
A flexible rover that has both ability to travel long distances and rappel down hard-to-reach areas of scientific interest has undergone a field test in the Mojave Desert in California to showcase its versatility. Composed of two Axel robots, DuAxel is designed to explore crater walls, pits, scarps, vents and other extreme terrain on the moon, Mars and beyond.
This technology demonstration developed at NASA’s Jet Propulsion Laboratory in Southern California showcases the robot’s ability to split in two and send one of its halves — a two-wheeled Axle robot — over an otherwise inaccessible slope, using a tether as support and to supply power.
The rappelling Axel can then autonomously seek out areas to study, safely overcome slopes and rocky obstacles, and then return to dock with its other half before driving to another destination. Although the rover doesn’t yet have a mission, key technologies are being developed that might, one day, help us explore the rocky planets and moons throughout the solar system.
[ JPL ]
A rectangular robot as tiny as a few human hairs can travel throughout a colon by doing back flips, Purdue University engineers have demonstrated in live animal models. Why the back flips? Because the goal is to use these robots to transport drugs in humans, whose colons and other organs have rough terrain. Side flips work, too. Why a back-flipping robot to transport drugs? Getting a drug directly to its target site could remove side effects, such as hair loss or stomach bleeding, that the drug may otherwise cause by interacting with other organs along the way.
[ Purdue ]
This video shows the latest results in the whole-body locomotion control of the humanoid robot iCub achieved by the Dynamic Interaction Control line at IIT-Istituto Italiano di Tecnologia in Genova (Italy). In particular, the iCub now keeps the balance while walking and receiving pushes from an external user. The implemented control algorithms also ensure the robot to remain compliant during locomotion and human-robot interaction, a fundamental property to lower the possibility to harm humans that share the robot surrounding environment.
This is super impressive, considering that iCub was only able to crawl and was still tethered not too long ago. Also, it seems to be blinking properly now, so it doesn’t look like it’s always sleepy.
[ IIT ]
This video shows a set of new tests we performed on Bolt. We conducted tests on 5 different scenarios, 1) walking forward/backward 2) uneven surface 3) soft surface 4) push recovery 5) slippage recovery. Thanks to our feedback control based on Model Predictive Control, the robot can perform walking in the presence of all these uncertainties. We will open-source all the codes in a near future.
[ ODRI ]
The title of this video is “Can you throw your robot into a lake?” The title of this video should be, “Can you throw your robot into a lake and drive it out again?”
[ Norlab ]
AeroVironment Successfully Completes Sunglider Solar HAPS Stratospheric Test Flight, Surpassing 60,000 Feet Altitude and Demonstrating Broadband Mobile Connectivity.
[ AeroVironment ]
We present CoVR, a novel robotic interface providing strong kinesthetic feedback (100 N) in a room-scale VR arena. It consists of a physical column mounted on a 2D Cartesian ceiling robot (XY displacements) with the capacity of (1) resisting to body-scaled users actions such as pushing or leaning; (2) acting on the users by pulling or transporting them as well as (3) carrying multiple potentially heavy objects (up to 80kg) that users can freely manipulate or make interact with each other.
[ DeepAI ]
In a new video, personnel from Swiss energy supply company Kraftwerke Oberhasli AG (KWO) explain how they were able to keep employees out of harm’s way by using Flyability’s Elios 2 to collect visual data while building a new dam.
[ Flyability ]
Enjoy our Ascento robot fail compilation! With every failure we experience, we learn more and we can improve our robot for its next iteration, which will come soon… Stay tuned for more!
FYI posting a robot fails video will pretty much guarantee you a spot in Video Friday!
[ Ascento ]
Humans are remarkably good at using chopsticks. The Guinness World Record witnessed a person using chopsticks to pick up 65 M&Ms in just a minute. We aim to collect demonstrations from humans and to teach robot to use chopsticks.
[ UW Personal Robotics Lab ]
A surprising amount of personality from these Yaskawa assembly robots.
[ Yaskawa ]
This paper presents the system design, modeling, and control of the Aerial Robotic Chain Manipulator. This new robot design offers the potential to exert strong forces and moments to the environment, carry and lift significant payloads, and simultaneously navigate through narrow corridors. The presented experimental studies include a valve rotation task, a pick-and-release task, and the verification of load oscillation suppression to demonstrate the stability and performance of the system.
[ ARL ]
Whether animals or plants, whether in the water, on land or in the air, nature provides the model for many technical innovations and inventions. This is summed up in the term bionics, which is a combination of the words ‘biology‘ and ‘electronics’. At Festo, learning from nature has a long history, as our Bionic Learning Network is based on using nature as the source for future technologies like robots, assistance systems or drive solutions.
[ Festo ]
Dogs! Selfies! Thousands of LEGO bricks! This video has it all.
[ LEGO ]
An IROS workshop talk on “Cassie and Mini Cheetah Autonomy” by Maani Ghaffari and Jessy Grizzle from the University of Michigan.
[ Michigan Robotics ]
David Schaefer’s Cozmo robots are back with this mind-blowing dance-off!
What you just saw represents hundreds of hours of work, David tells us: “I wrote over 10,000 lines of code to create the dance performance as I had to translate the beats per minute of the song into motor rotations in order to get the right precision needed to make the moves look sharp. The most challenging move was the SpongeBob SquareDance as any misstep would send the Cozmos crashing into each other. LOL! Fortunately for me, Cozmo robots are pretty resilient.”
[ Life with Cozmo ]
Thanks David!
This week’s GRASP on Robotics seminar is by Sangbae Kim from MIT, on “Robots with Physical Intelligence.”
While industrial robots are effective in repetitive, precise kinematic tasks in factories, the design and control of these robots are not suited for physically interactive performance that humans do easily. These tasks require ‘physical intelligence’ through complex dynamic interactions with environments whereas conventional robots are designed primarily for position control. In order to develop a robot with ‘physical intelligence’, we first need a new type of machines that allow dynamic interactions. This talk will discuss how the new design paradigm allows dynamic interactive tasks. As an embodiment of such a robot design paradigm, the latest version of the MIT Cheetah robots and force-feedback teleoperation arms will be presented.
[ GRASP ]
This week’s CMU Ri Seminar is by Kevin Lynch from Northwestern, on “Robotics and Biosystems.”
Research at the Center for Robotics and Biosystems at Northwestern University encompasses bio-inspiration, neuromechanics, human-machine systems, and swarm robotics, among other topics. In this talk I will give an overview of some of our recent work on in-hand manipulation, robot locomotion on yielding ground, and human-robot systems.
[ CMU RI ] Continue reading
Posted in Human Robots
#437596 IROS Robotics Conference Is Online Now ...
The 2020 International Conference on Intelligent Robots and Systems (IROS) was originally going to be held in Las Vegas this week. Like ICRA last spring, IROS has transitioned to a completely online conference, which is wonderful news: Now everyone everywhere can participate in IROS without having to spend a dime on travel.
IROS officially opened yesterday, and the best news is that registration is entirely free! We’ll take a quick look at what IROS has on offer this year, which includes some stuff that’s brand news to IROS.
Registration for IROS is super easy, and did we mention that it’s free? To register, just go here and fill out a quick and easy form. You don’t even have to be an IEEE Member or anything like that, although in our unbiased opinion, an IEEE membership is well worth it. Once you get the confirmation email, go to https://www.iros2020.org/ondemand/, put in the email address you used to register, and that’s it, you’ve got IROS!
Here are some highlights:
Plenaries and Keynotes
Without the normal space and time constraints, you won’t have to pick and choose between any of the three plenaries or 10 keynotes. Some of them are fancier than others, but we’re used to that sort of thing by now. It’s worth noting that all three plenaries (and three of the 10 keynotes) are given by extraordinarily talented women, which is excellent to see.
Technical Tracks
There are over 1,400 technical talks, divided up into 12 categories of 20 sessions each. Note that each of the 12 categories that you see on the main page can be scrolled through to show all 20 of the sessions; if there’s a bright red arrow pointing left or right you can scroll, and if the arrow is transparent, you’ve reached the end.
On the session page, you’ll see an autoplaying advertisement (that you can mute but not stop), below which each talk has a preview slide, a link to a ~15 minute presentation video, and another link to a PDF of the paper. No supplementary videos are available, which is a bit disappointing. While you can leave a comment on the video, there’s no way of interacting with the author(s) directly through the IROS site, so you’ll have to check the paper for an email address if you want to ask a question.
Award Finalists
IROS has thoughtfully grouped all of the paper award finalists together into nine sessions. These are some truly outstanding papers, and it’s worth watching these sessions even if you’re not interested in specific subject matter.
Workshops and Tutorials
This stuff is a little more impacted by asynchronicity and on-demandedness, and some of the workshops and tutorials have already taken place. But IROS has done a good job at collecting videos of everything and making them easy to access, and the dedicated websites for the workshops and tutorials themselves sometimes have more detailed info. If you’re having trouble finding where the workshops and tutorial section is, try the “Entrance” drop-down menu up at the top.
IROS Original Series
In place of social events and lab tours, IROS this year has come up with the “IROS Original Series,” which “hosts unique content that would be difficult to see at in-person events.” Right now, there are some interviews with a diverse group of interesting roboticists, and hopefully more will show up later on.
Enjoy!
Everything on the IROS On-Demand site should be available for at least the next month, so there’s no need to try and watch a thousand presentations over three days (which is what we normally have to do). So, relax, and enjoy yourself a bit by browsing all the options. And additional content will be made available over the next several weeks, so make sure to check back often to see what’s new.
[ IROS 2020 ] Continue reading
Posted in Human Robots
#437269 DeepMind’s Newest AI Programs Itself ...
When Deep Blue defeated world chess champion Garry Kasparov in 1997, it may have seemed artificial intelligence had finally arrived. A computer had just taken down one of the top chess players of all time. But it wasn’t to be.
Though Deep Blue was meticulously programmed top-to-bottom to play chess, the approach was too labor-intensive, too dependent on clear rules and bounded possibilities to succeed at more complex games, let alone in the real world. The next revolution would take a decade and a half, when vastly more computing power and data revived machine learning, an old idea in artificial intelligence just waiting for the world to catch up.
Today, machine learning dominates, mostly by way of a family of algorithms called deep learning, while symbolic AI, the dominant approach in Deep Blue’s day, has faded into the background.
Key to deep learning’s success is the fact the algorithms basically write themselves. Given some high-level programming and a dataset, they learn from experience. No engineer anticipates every possibility in code. The algorithms just figure it.
Now, Alphabet’s DeepMind is taking this automation further by developing deep learning algorithms that can handle programming tasks which have been, to date, the sole domain of the world’s top computer scientists (and take them years to write).
In a paper recently published on the pre-print server arXiv, a database for research papers that haven’t been peer reviewed yet, the DeepMind team described a new deep reinforcement learning algorithm that was able to discover its own value function—a critical programming rule in deep reinforcement learning—from scratch.
Surprisingly, the algorithm was also effective beyond the simple environments it trained in, going on to play Atari games—a different, more complicated task—at a level that was, at times, competitive with human-designed algorithms and achieving superhuman levels of play in 14 games.
DeepMind says the approach could accelerate the development of reinforcement learning algorithms and even lead to a shift in focus, where instead of spending years writing the algorithms themselves, researchers work to perfect the environments in which they train.
Pavlov’s Digital Dog
First, a little background.
Three main deep learning approaches are supervised, unsupervised, and reinforcement learning.
The first two consume huge amounts of data (like images or articles), look for patterns in the data, and use those patterns to inform actions (like identifying an image of a cat). To us, this is a pretty alien way to learn about the world. Not only would it be mind-numbingly dull to review millions of cat images, it’d take us years or more to do what these programs do in hours or days. And of course, we can learn what a cat looks like from just a few examples. So why bother?
While supervised and unsupervised deep learning emphasize the machine in machine learning, reinforcement learning is a bit more biological. It actually is the way we learn. Confronted with several possible actions, we predict which will be most rewarding based on experience—weighing the pleasure of eating a chocolate chip cookie against avoiding a cavity and trip to the dentist.
In deep reinforcement learning, algorithms go through a similar process as they take action. In the Atari game Breakout, for instance, a player guides a paddle to bounce a ball at a ceiling of bricks, trying to break as many as possible. When playing Breakout, should an algorithm move the paddle left or right? To decide, it runs a projection—this is the value function—of which direction will maximize the total points, or rewards, it can earn.
Move by move, game by game, an algorithm combines experience and value function to learn which actions bring greater rewards and improves its play, until eventually, it becomes an uncanny Breakout player.
Learning to Learn (Very Meta)
So, a key to deep reinforcement learning is developing a good value function. And that’s difficult. According to the DeepMind team, it takes years of manual research to write the rules guiding algorithmic actions—which is why automating the process is so alluring. Their new Learned Policy Gradient (LPG) algorithm makes solid progress in that direction.
LPG trained in a number of toy environments. Most of these were “gridworlds”—literally two-dimensional grids with objects in some squares. The AI moves square to square and earns points or punishments as it encounters objects. The grids vary in size, and the distribution of objects is either set or random. The training environments offer opportunities to learn fundamental lessons for reinforcement learning algorithms.
Only in LPG’s case, it had no value function to guide that learning.
Instead, LPG has what DeepMind calls a “meta-learner.” You might think of this as an algorithm within an algorithm that, by interacting with its environment, discovers both “what to predict,” thereby forming its version of a value function, and “how to learn from it,” applying its newly discovered value function to each decision it makes in the future.
Prior work in the area has had some success, but according to DeepMind, LPG is the first algorithm to discover reinforcement learning rules from scratch and to generalize beyond training. The latter was particularly surprising because Atari games are so different from the simple worlds LPG trained in—that is, it had never seen anything like an Atari game.
Time to Hand Over the Reins? Not Just Yet
LPG is still behind advanced human-designed algorithms, the researchers said. But it outperformed a human-designed benchmark in training and even some Atari games, which suggests it isn’t strictly worse, just that it specializes in some environments.
This is where there’s room for improvement and more research.
The more environments LPG saw, the more it could successfully generalize. Intriguingly, the researchers speculate that with enough well-designed training environments, the approach might yield a general-purpose reinforcement learning algorithm.
At the least, though, they say further automation of algorithm discovery—that is, algorithms learning to learn—will accelerate the field. In the near term, it can help researchers more quickly develop hand-designed algorithms. Further out, as self-discovered algorithms like LPG improve, engineers may shift from manually developing the algorithms themselves to building the environments where they learn.
Deep learning long ago left Deep Blue in the dust at games. Perhaps algorithms learning to learn will be a winning strategy in the real world too.
Image credit: Mike Szczepanski / Unsplash Continue reading
Posted in Human Robots
#436462 Robotic Exoskeletons, Like This One, Are ...
When you imagine an exoskeleton, chances are it might look a bit like the Guardian XO from Sarcos Robotics. The XO is literally a robot you wear (or maybe, it wears you). The suit’s powered limbs sense your movements and match their position to yours with little latency to give you effortless superstrength and endurance—lifting 200 pounds will feel like 10.
A vision of robots and humankind working together in harmony. Now, isn’t that nice?
Of course, there isn’t anything terribly novel about an exoskeleton. We’ve seen plenty of concepts and demonstrations in the last decade. These include light exoskeletons tailored to industrial settings—some of which are being tested out by the likes of Honda—and healthcare exoskeletons that support the elderly or folks with disabilities.
Full-body powered robotic exoskeletons are a bit rarer, which makes the Sarcos suit pretty cool to look at. But like all things in robotics, practicality matters as much as vision. It’s worth asking: Will anyone buy and use the thing? Is it more than a concept video?
Sarcos thinks so, and they’re excited about it. “If you were to ask the question, what does 30 years and $300 million look like,” Sarcos CEO, Ben Wolff, told IEEE Spectrum, “you’re going to see it downstairs.”
The XO appears to check a few key boxes. For one, it’s user friendly. According to Sarcos, it only takes a few minutes for the uninitiated to strap in and get up to speed. Feeling comfortable doing work with the suit takes a few hours. This is thanks to a high degree of sensor-based automation that allows the robot to seamlessly match its user’s movements.
The XO can also operate for more than a few minutes. It has two hours of battery life, and with spares on hand, it can go all day. The batteries are hot-swappable, meaning you can replace a drained battery with a new one without shutting the system down.
The suit is aimed at manufacturing, where workers are regularly moving heavy stuff around. Additionally, Wolff told CNET, the suit could see military use. But that doesn’t mean Avatar-style combat. The XO, Wolff said, is primarily about logistics (lifting and moving heavy loads) and isn’t designed to be armored, so it won’t likely see the front lines.
The system will set customers back $100,000 a year to rent, which sounds like a lot, but for industrial or military purposes, the six-figure rental may not deter would-be customers if the suit proves itself a useful bit of equipment. (And it’s reasonable to imagine the price coming down as the technology becomes more commonplace and competitors arrive.)
Sarcos got into exoskeletons a couple decades ago and was originally funded by the military (like many robotics endeavors). Videos hit YouTube as long ago as 2008, but after announcing the company was taking orders for the XO earlier this year, Sarcos says they’ll deliver the first alpha units in January, which is a notable milestone.
Broadly, robotics has advanced a lot in recent years. YouTube sensations like Boston Dynamics have regularly earned millions of views (and inevitably, headlines stoking robot fear). They went from tethered treadmill sessions to untethered backflips off boxes. While today’s robots really are vastly superior to their ancestors, they’ve struggled to prove themselves useful. A counterpoint to flashy YouTube videos, the DARPA Robotics Challenge gave birth to another meme altogether. Robots falling over. Often and awkwardly.
This year marks some of the first commercial fruits of a few decades’ research. Boston Dynamics recently started offering its robot dog, Spot, to select customers in 2019. Whether this proves to be a headline-worthy flash in the pan or something sustainable remains to be seen. But between robots with more autonomy and exoskeletons like the XO, the exoskeleton variety will likely be easier to make more practical for various uses.
Whereas autonomous robots require highly advanced automation to navigate uncertain and ever-changing conditions—automation which, at the moment, remains largely elusive (though the likes of Google are pairing the latest AI with robots to tackle the problem)—an exoskeleton mainly requires physical automation. The really hard bits, like navigating and recognizing and interacting with objects, are outsourced to its human operator.
As it turns out, for today’s robots the best AI is still us. We may yet get chipper automatons like Rosy the Robot, but until then, for complicated applications, we’ll strap into our mechs for their strength and endurance, and they’ll wear us for our brains.
Image Credit: Sarcos Robotics Continue reading
Posted in Human Robots
#436426 Video Friday: This Robot Refuses to Fall ...
Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):
Robotic Arena – January 25, 2020 – Wrocław, Poland
DARPA SubT Urban Circuit – February 18-27, 2020 – Olympia, Wash., USA
Let us know if you have suggestions for next week, and enjoy today’s videos.
In case you somehow missed the massive Skydio 2 review we posted earlier this week, the first batches of the drone are now shipping. Each drone gets a lot of attention before it goes out the door, and here’s a behind-the-scenes clip of the process.
[ Skydio ]
Sphero RVR is one of the 15 robots on our robot gift guide this year. Here’s a new video Sphero just released showing some of the things you can do with the robot.
[ RVR ]
NimbRo-OP2 has some impressive recovery skills from the obligatory research-motivated robot abuse.
[ NimbRo ]
Teams seeking to qualify for the Virtual Urban Circuit of the Subterranean Challenge can access practice worlds to test their approaches prior to submitting solutions for the competition. This video previews three of the practice environments.
[ DARPA SubT ]
Stretchable skin-like robots that can be rolled up and put in your pocket have been developed by a University of Bristol team using a new way of embedding artificial muscles and electrical adhesion into soft materials.
[ Bristol ]
Happy Holidays from ABB!
Helping New York celebrate the festive season, twelve ABB robots are interacting with visitors to Bloomingdale’s iconic holiday celebration at their 59th Street flagship store. ABB’s robots are the main attraction in three of Bloomingdale’s twelve-holiday window displays at Lexington and Third Avenue, as ABB demonstrates the potential for its robotics and automation technology to revolutionize visual merchandising and make the retail experience more dynamic and whimsical.
[ ABB ]
We introduce pelican eel–inspired dual-morphing architectures that embody quasi-sequential behaviors of origami unfolding and skin stretching in response to fluid pressure. In the proposed system, fluid paths were enclosed and guided by a set of entirely stretchable origami units that imitate the morphing principle of the pelican eel’s stretchable and foldable frames. This geometric and elastomeric design of fluid networks, in which fluid pressure acts in the direction that the whole body deploys first, resulted in a quasi-sequential dual-morphing response. To verify the effectiveness of our design rule, we built an artificial creature mimicking a pelican eel and reproduced biomimetic dual-morphing behavior.
And here’s a real pelican eel:
[ Science Robotics ]
Delft Dynamics’ updated anti-drone system involves a tether, mid-air net gun, and even a parachute.
[ Delft Dynamics ]
Teleoperation is a great way of helping robots with complex tasks, especially if you can do it through motion capture. But what if you’re teleoperating a non-anthropomorphic robot? Columbia’s ROAM Lab is working on it.
[ Paper ] via [ ROAM Lab ]
I don’t know how I missed this video last year because it’s got a steely robot hand squeezing a cute lil’ chick.
[ MotionLib ] via [ RobotStart ]
In this video we present results of a trajectory generation method for autonomous overtaking of unexpected obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example when overtaking unexpected objects on the vehicle’s ego lane on a two-way street. In this case, a human driver would first make sure that the opposite lane is free and that there is enough room to successfully execute the maneuver, and then it would cut into the opposite lane in order to execute the maneuver successfully. We consider the practical problem of autonomous overtaking when the coverage of the perception system is impaired due to occlusion.
[ Paper ]
New weirdness from Toio!
[ Toio ]
Palo Alto City Library won a technology innovation award! Watch to see how Senior Librarian Dan Lou is using Misty to enhance their technology programs to inspire and educate customers.
[ Misty Robotics ]
We consider the problem of reorienting a rigid object with arbitrary known shape on a table using a two-finger pinch gripper. Reorienting problem is challenging because of its non-smoothness and high dimensionality. In this work, we focus on solving reorienting using pivoting, in which we allow the grasped object to rotate between fingers. Pivoting decouples the gripper rotation from the object motion, making it possible to reorient an object under strict robot workspace constraints.
[ CMU ]
How can a mobile robot be a good pedestrian without bumping into you on the sidewalk? It must be hard for a robot to navigate in crowded environments since the flow of traffic follows implied social rules. But researchers from MIT developed an algorithm that teaches mobile robots to maneuver in crowds of people, respecting their natural behaviour.
[ Roboy Research Reviews ]
What happens when humans and robots make art together? In this awe-inspiring talk, artist Sougwen Chung shows how she “taught” her artistic style to a machine — and shares the results of their collaboration after making an unexpected discovery: robots make mistakes, too. “Part of the beauty of human and machine systems is their inherent, shared fallibility,” she says.
[ TED ]
Last month at the Cooper Union in New York City, IEEE TechEthics hosted a public panel session on the facts and misperceptions of autonomous vehicles, part of the IEEE TechEthics Conversations Series. The speakers were: Jason Borenstein from Georgia Tech; Missy Cummings from Duke University; Jack Pokrzywa from SAE; and Heather M. Roff from Johns Hopkins Applied Physics Laboratory. The panel was moderated by Mark A. Vasquez, program manager for IEEE TechEthics.
[ IEEE TechEthics ]
Two videos this week from Lex Fridman’s AI podcast: Noam Chomsky, and Whitney Cummings.
[ AI Podcast ]
This week’s CMU RI Seminar comes from Jeff Clune at the University of Wyoming, on “Improving Robot and Deep Reinforcement Learning via Quality Diversity and Open-Ended Algorithms.”
Quality Diversity (QD) algorithms are those that seek to produce a diverse set of high-performing solutions to problems. I will describe them and a number of their positive attributes. I will then summarize our Nature paper on how they, when combined with Bayesian Optimization, produce a learning algorithm that enables robots, after being damaged, to adapt in 1-2 minutes in order to continue performing their mission, yielding state-of-the-art robot damage recovery. I will next describe our QD-based Go-Explore algorithm, which dramatically improves the ability of deep reinforcement learning algorithms to solve previously unsolvable problems wherein reward signals are sparse, meaning that intelligent exploration is required. Go-Explore solves Montezuma’s Revenge, considered by many to be a major AI research challenge. Finally, I will motivate research into open-ended algorithms, which seek to innovate endlessly, and introduce our POET algorithm, which generates its own training challenges while learning to solve them, automatically creating a curricula for robots to learn an expanding set of diverse skills. POET creates and solves challenges that are unsolvable with traditional deep reinforcement learning techniques.
[ CMU RI ] Continue reading
Posted in Human Robots