Animals are adept at adapting to injury, but it is not true with robots. A broken part can render a robot useless.
But scientists come up with a new algorithm, where robots can learn how to deal with damage all on their own. The algorithm is so effective that a robot with broken leg can actually learn to run even faster than it did before the injury.
Jeff McClune of the University of Wyoming and the study co-author said, “You can step on it and then in the course of one or two minutes, it figures out a new way to walk and then it’s up and off to the races again.”
Such robots will be useful in situations that involve dangerous conditions where it isn’t safe to send people.
McClune said, “Robots will provide tremendous benefits to society by doing jobs that are very dangerous for humans to do, like putting out forest fires and finding survivors after earthquakes, but they’re not going to be very helpful unless they are able to soldier on when something goes wrong.”
The algorithm allows the broken leg robot to run a set of experiments on itself. For example, if the six-legged robot losses a leg, the pattern of movements that it employed to get around before will not work so well. But there are still thousands of possible different patterns of movements that use only five legs. Simple trial and error would eventually lead the robot to the best new strategy, but with so many possibilities this would take quite a while.
This algorithm helps to streamline the trial and error process so that it can recover in few minutes or seconds.
McClune said, “You can already use our algorithm on some of the robots that are already deployed in the world. For example, in our paper we experimented on a robotic arm that has to place things in bins, so if some of the motors break it can still do its job.”
Robots that can perform complex tasks like looking for disaster survivors are still many years away, but if it becomes a reality this algorithm will be able to help them use their advanced abilities in the face of damages or unforeseen conditions.
McClune added, “The real payoff will be once we have robots that are more advanced, but to see it adapt in front of your eyes in a short amount of time, that’s practical for the field and it’s tremendously exciting.”