Quadrupedal robots are becoming a familiar sight, but engineers are still working out the full capabilities of these machines. Now, a group of researchers from MIT says one way to improve their functionality might be to use AI to helpUsually, when engineers are creating the software that controls the movement of legged robots, they write a set of rules about how the machine should respond to certain inputs. So, if a robot’s sensors detectand so on.
As you can see, Mini Cheetah’s new running gait is a little ungainly. In fact, it looks like a puppy scrabbling to accelerate on a wooden floor. But, according to MIT PhD student Gabriel Margolis , this is because the AI isn’t optimizing for anything“RL finds one way to run fast, but given an underspecified reward function, it has no reason to prefer a gait that is ‘natural-looking’ or preferred by humans,” Margolis tellsover email.
Some companies that develop legged robots are already using these sorts of methods to design new controllers. Others, though, like Boston Dynamics, apparently rely on more traditional approaches. There are also faster-legged robots out there. Boston Dynamics’ Cheetah bot currently holds the record for a quadruped,— faster than Usain Bolt. However, not only is Cheetah a much bigger and more powerful machine than MIT’s Mini Cheetah, but it achieved its record running on a treadmill and mounted to a lever for stability. Without these advantages, maybe AI would give the machine a run for its money.Subscribe to get the best Verge-approved tech deals of the week.
When the student becomes the master! AI’s potential to learn is only surpassed by its potential to teach. FutureWithoutLimits
Lil dude is fast asf! The motion of it's gait makes it look like some sort of hybrid lizard-dog. Cool stuff.
Skynet? 😂