Boots Full of Nickels Help Mini Cheetah Land on its Feet
As quadrupedal robots learn to do more and more dynamic tasks, they’re likely to spend more and more time not on their feet. Not falling over, necessarily (although that’s inevitable of course, because they’re legged robots after all)—but just being in flight in one way or another. The most risky of flight phases would be a fall from a substantial height, because it’s almost certain to break your very expensive robot and any payload it might have.
Falls being bad is not a problem unique to robots, and it’s not surprising that quadrupeds in nature have already solved it. Or at least, it’s already been solved by cats, which are able to reliably land on their feet to mitigate fall damage. To teach quadrupedal robots this trick, roboticists from the University of Notre Dame have been teaching a Mini Cheetah quadruped some mid-air self-righting skills, with the aid of boots full of nickels.
If this research looks a little bit familiar, it’s because we recently covered some work from ETH Zurich that looked at using legs to reorient their SpaceBok quadruped in microgravity. This work with Mini Cheetah has to contend with Earth gravity, however, which puts some fairly severe time constraints on the whole reorientation thing with the penalty for failure being a smashed-up robot rather than just a weird bounce. When we asked the ETH Zurich researchers what might improve the performance of SpaceBok, they told us that “heavy shoes would definitely help,” and it looks like the folks from Notre Dame had the same idea, which they were able to implement on Mini Cheetah.
Mini Cheetah’s legs (like the legs of many robots) were specifically designed to be lightweight because they have to move quickly, and you want to minimize the mass that moves back and forth with every step to make the robot as efficient as possible. But for a robot to reorient itself in mid air, it’s got to start swinging as much mass around as it can. Each of Mini Cheetah’s legs has been modified with 3D printed boots, packed with two rolls of American nickels each, adding about 500g to each foot—enough to move the robot around like it needs to. The reason why nickel boots are important is because the only way that Mini Cheetah has of changing its orientation while falling is by flailing its legs around. When its legs move one way, its body will move the other way, and the heavier the legs are, the more force they can exert on the body.
As with everything robotics, getting the hardware to do what you want it to do is only half the battle. Or sometimes much, much less than half the battle. The challenge with Mini Cheetah flipping itself over is that it has a very, very small amount of time to figure out how to do it properly. It has to detect that it’s falling, figure out what orientation it’s in, make a plan of how to get itself feet down, and then execute on that plan successfully. The robot doesn’t have enough time to put a whole heck of a lot of thought into things as it starts to plummet, so the technique that the researchers came up with to enable it to do what it needs to do is called a “reflex” approach. Vince Kurtz, first author on the paper describing this technique, explains how it works:
While trajectory optimization algorithms keep getting better and better, they still aren’t quite fast enough to find a solution from scratch in the fraction of a second between when the robot detects a fall and when it needs to start a recovery motion. We got around this by dropping the robot a bunch of times in simulation, where we can take as much time as we need to find a solution, and training a neural network to imitate the trajectory optimizer. The trained neural network maps initial orientations to trajectories that land the robot on its feet. We call this the “reflex” approach, since the neural network has basically learned an automatic response that can be executed when the robot detects that it’s falling.
This technique works quite well, but there are a few constraints, most of which wouldn’t seem so bad if we weren’t comparing quadrupedal robots to quadrupedal animals. Cats are just, like, super competent at what they do, says Kurtz, and being able to mimic their ability to rapidly twist themselves into a favorable landing configuration from any starting orientation is just going to be really hard for a robot to pull off:
The more I do robotics research the more I appreciate how amazing nature is, and this project is a great example of that. Cats can do a full 180° rotation when dropped from about shoulder height. Our robot ran up against torque limits when rotating 90° from about 10ft off the ground. Using the full 3D motion would be a big improvement (rotating sideways should be easier because the robot’s moment of inertia is smaller in that direction), though I’d be surprised if that alone got us to cat-level performance.
The biggest challenge that I see in going from 2D to 3D is self-collisions. Keeping the robot from hitting itself seems like it should be simple, but self-collisions turn out to impose rather nasty non-convex constraints that make it numerically difficult (though not impossible) for trajectory optimization algorithms to find high-quality solutions.
Lastly, we asked Kurtz to talk a bit about whether it’s worth exploring flexible actuated spines for quadrupedal robots. We know that such spines offer many advantages (a distant relative of Mini Cheetah had one, for example), but that they’re also quite complex. So is it worth it?
This is an interesting question. Certainly in the case of the falling cat problem a flexible spine would help, both in terms of having a naturally flexible mass distribution and in terms of controller design, since we might be able to directly imitate the “bend-and-twist” motion of cats. Similarly, a flexible spine might help for tasks with large flight phases, like the jumping in space problems discussed in the ETH paper.
With that being said, mid-air reorientation is not the primary task of most quadruped robots, and it’s not obvious to me that a flexible spine would help much for walking, running, or scrambling over uneven terrain. Also, existing hardware platforms with rigid backs like the Mini Cheetah are quite capable and I think we still haven’t unlocked the full potential of these robots. Control algorithms are still the primary limiting factor for today’s legged robots, and adding a flexible spine would probably make for even more difficult control problems.
Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics, by Vince Kurtz, He Li, Patrick M. Wensing, and Hai Lin from University of Notre Dame, is available on arXiv.