Tag Archives: we
#439608 Atlas Shows Most Impressive Parkour ...
Boston Dynamics has just posted a couple of new videos showing their Atlas humanoid robot doing some of the most impressive parkour we've yet seen. Let's watch!
Parkour is the perfect sandbox for the Atlas team at Boston Dynamics to experiment with new behaviors. In this video our humanoid robots demonstrate their whole-body athletics, maintaining its balance through a variety of rapidly changing, high-energy activities. Through jumps, balance beams, and vaults, we demonstrate how we push Atlas to its limits to discover the next generation of mobility, perception, and athletic intelligence.There are a couple of new and exciting things in this video. First, Atlas is doing some serious work with its upper body by vaulting over that bar. It's not supporting its entire weight with one arm, since it's jumping, but it's doing what looks like some fairly complex balancing and weight management using all four of its limbs at once. Most of what we've seen from Atlas up to this point has been lower body focused, and while the robot has used its arms for forward rolls and stuff, those moves have been simpler than what we're seeing here. Aaron Saunders, Boston Dynamics' VP of Engineering, suggested to us earlier this year that the Atlas team would be working on more upper-body stuff, it looks like they're now delivering. We're expecting that Atlas will continue to improve in this direction, and that at some point it'll be able to do the equivalent of a pull-up, which will open up a much wider variety of behaviors.
The second big new thing is that Atlas is now leveraging perception much more heavily, according to Scott Kuindersma, the Atlas team lead at Boston Dynamics, who wrote about it in a blog post:
“Atlas's moves are driven by perception now, and they weren't back then,” Kuindersma explains. “For example, the previous floor routine and dance videos were about capturing our ability to create a variety of dynamic moves and chain them together into a routine that we could run over and over again. In that case, the robot's control system still has to make lots of critical adjustments on the fly to maintain balance and posture goals, but the robot was not sensing and reacting to its environment.”
In this iteration of parkour, the robot is adapting behaviors in its repertoire based on what it sees. This means the engineers don't need to pre-program jumping motions for all possible platforms and gaps the robot might encounter. Instead, the team creates a smaller number of template behaviors that can be matched to the environment and executed online.This is a pretty big deal. Without perception, Atlas was running its routines blind—as long as the environment was kept more or less completely static, the robot would do okay, but obviously that's a major limitation. What Atlas is doing in this new video is still somewhat limited, in the sense that it's still relying on template behaviors created by humans rather than doing true dynamic planning, but this represents a lot of progress.
One other thing that's worth paying attention to is how Boston Dynamics thinks of humanoid robots:
“Humanoids are interesting from a couple perspectives,” Kuindersma says. “First, they capture our vision of a go-anywhere, do-anything robot of the future. They may not be the best design for any particular task, but if you wanted to build one platform that could perform a wide variety of physical tasks, we already know that a human form factor is capable of doing that.”This tends to be the justification for humanoid robots, along with the idea that you need a humanoid form factor to operate in human environments. But Kuindersma is absolutely right when he says that humanoids may not be the best design for any particular task, and at least in the near term, practical commercial robots tend not to be generalists. Even Boston Dynamic's dog-like robot Spot, with its capable legged mobility, is suited primarily to a narrow range of specific tasks—it's great for situations where legs are necessary, but otherwise it's complex and expensive and wheels often do better. I think it's very important that Boston Dynamics is working towards a go-anywhere, do-anything robot, but it's also important to keep expectations in check, and remember that even robots like Atlas are (I would argue) a decade or more away from this generalist vision.
Meanwhile, Boston Dynamics seems, for better or worse, to be moving away from their habit of surprise posting crazy robot videos with zero explanation. Along with the new parkour video, Boston Dynamics has put together a second behind the scenes video:
Can I just say that I love how absolutely trashed the skins on these robots look? That's how you know good work is getting done.
There's a bunch more detail in this blog post, and we sent Boston Dynamics a couple of questions, too. We'll update this post when we hear back later today. Continue reading
#439110 Robotic Exoskeletons Could One Day Walk ...
Engineers, using artificial intelligence and wearable cameras, now aim to help robotic exoskeletons walk by themselves.
Increasingly, researchers around the world are developing lower-body exoskeletons to help people walk. These are essentially walking robots users can strap to their legs to help them move.
One problem with such exoskeletons: They often depend on manual controls to switch from one mode of locomotion to another, such as from sitting to standing, or standing to walking, or walking on the ground to walking up or down stairs. Relying on joysticks or smartphone apps every time you want to switch the way you want to move can prove awkward and mentally taxing, says Brokoslaw Laschowski, a robotics researcher at the University of Waterloo in Canada.
Scientists are working on automated ways to help exoskeletons recognize when to switch locomotion modes — for instance, using sensors attached to legs that can detect bioelectric signals sent from your brain to your muscles telling them to move. However, this approach comes with a number of challenges, such as how how skin conductivity can change as a person’s skin gets sweatier or dries off.
Now several research groups are experimenting with a new approach: fitting exoskeleton users with wearable cameras to provide the machines with vision data that will let them operate autonomously. Artificial intelligence (AI) software can analyze this data to recognize stairs, doors, and other features of the surrounding environment and calculate how best to respond.
Laschowski leads the ExoNet project, the first open-source database of high-resolution wearable camera images of human locomotion scenarios. It holds more than 5.6 million images of indoor and outdoor real-world walking environments. The team used this data to train deep-learning algorithms; their convolutional neural networks can already automatically recognize different walking environments with 73 percent accuracy “despite the large variance in different surfaces and objects sensed by the wearable camera,” Laschowski notes.
According to Laschowski, a potential limitation of their work their reliance on conventional 2-D images, whereas depth cameras could also capture potentially useful distance data. He and his collaborators ultimately chose not to rely on depth cameras for a number of reasons, including the fact that the accuracy of depth measurements typically degrades in outdoor lighting and with increasing distance, he says.
In similar work, researchers in North Carolina had volunteers with cameras either mounted on their eyeglasses or strapped onto their knees walk through a variety of indoor and outdoor settings to capture the kind of image data exoskeletons might use to see the world around them. The aim? “To automate motion,” says Edgar Lobaton an electrical engineering researcher at North Carolina State University. He says they are focusing on how AI software might reduce uncertainty due to factors such as motion blur or overexposed images “to ensure safe operation. We want to ensure that we can really rely on the vision and AI portion before integrating it into the hardware.”
In the future, Laschowski and his colleagues will focus on improving the accuracy of their environmental analysis software with low computational and memory storage requirements, which are important for onboard, real-time operations on robotic exoskeletons. Lobaton and his team also seek to account for uncertainty introduced into their visual systems by movements .
Ultimately, the ExoNet researchers want to explore how AI software can transmit commands to exoskeletons so they can perform tasks such as climbing stairs or avoiding obstacles based on a system’s analysis of a user's current movements and the upcoming terrain. With autonomous cars as inspiration, they are seeking to develop autonomous exoskeletons that can handle the walking task without human input, Laschowski says.
However, Laschowski adds, “User safety is of the utmost importance, especially considering that we're working with individuals with mobility impairments,” resulting perhaps from advanced age or physical disabilities.
“The exoskeleton user will always have the ability to override the system should the classification algorithm or controller make a wrong decision.” Continue reading
#439105 This Robot Taught Itself to Walk in a ...
Recently, in a Berkeley lab, a robot called Cassie taught itself to walk, a little like a toddler might. Through trial and error, it learned to move in a simulated world. Then its handlers sent it strolling through a minefield of real-world tests to see how it’d fare.
And, as it turns out, it fared pretty damn well. With no further fine-tuning, the robot—which is basically just a pair of legs—was able to walk in all directions, squat down while walking, right itself when pushed off balance, and adjust to different kinds of surfaces.
It’s the first time a machine learning approach known as reinforcement learning has been so successfully applied in two-legged robots.
This likely isn’t the first robot video you’ve seen, nor the most polished.
For years, the internet has been enthralled by videos of robots doing far more than walking and regaining their balance. All that is table stakes these days. Boston Dynamics, the heavyweight champ of robot videos, regularly releases mind-blowing footage of robots doing parkour, back flips, and complex dance routines. At times, it can seem the world of iRobot is just around the corner.
This sense of awe is well-earned. Boston Dynamics is one of the world’s top makers of advanced robots.
But they still have to meticulously hand program and choreograph the movements of the robots in their videos. This is a powerful approach, and the Boston Dynamics team has done incredible things with it.
In real-world situations, however, robots need to be robust and resilient. They need to regularly deal with the unexpected, and no amount of choreography will do. Which is how, it’s hoped, machine learning can help.
Reinforcement learning has been most famously exploited by Alphabet’s DeepMind to train algorithms that thrash humans at some the most difficult games. Simplistically, it’s modeled on the way we learn. Touch the stove, get burned, don’t touch the damn thing again; say please, get a jelly bean, politely ask for another.
In Cassie’s case, the Berkeley team used reinforcement learning to train an algorithm to walk in a simulation. It’s not the first AI to learn to walk in this manner. But going from simulation to the real world doesn’t always translate.
Subtle differences between the two can (literally) trip up a fledgling robot as it tries out its sim skills for the first time.
To overcome this challenge, the researchers used two simulations instead of one. The first simulation, an open source training environment called MuJoCo, was where the algorithm drew upon a large library of possible movements and, through trial and error, learned to apply them. The second simulation, called Matlab SimMechanics, served as a low-stakes testing ground that more precisely matched real-world conditions.
Once the algorithm was good enough, it graduated to Cassie.
And amazingly, it didn’t need further polishing. Said another way, when it was born into the physical world—it knew how to walk just fine. In addition, it was also quite robust. The researchers write that two motors in Cassie’s knee malfunctioned during the experiment, but the robot was able to adjust and keep on trucking.
Other labs have been hard at work applying machine learning to robotics.
Last year Google used reinforcement learning to train a (simpler) four-legged robot. And OpenAI has used it with robotic arms. Boston Dynamics, too, will likely explore ways to augment their robots with machine learning. New approaches—like this one aimed at training multi-skilled robots or this one offering continuous learning beyond training—may also move the dial. It’s early yet, however, and there’s no telling when machine learning will exceed more traditional methods.
And in the meantime, Boston Dynamics bots are testing the commercial waters.
Still, robotics researchers, who were not part of the Berkeley team, think the approach is promising. Edward Johns, head of Imperial College London’s Robot Learning Lab, told MIT Technology Review, “This is one of the most successful examples I have seen.”
The Berkeley team hopes to build on that success by trying out “more dynamic and agile behaviors.” So, might a self-taught parkour-Cassie be headed our way? We’ll see.
Image Credit: University of California Berkeley Hybrid Robotics via YouTube Continue reading