Designing tough robos? Let them grow as humans do
Washington: In a new study, a University of Vermont robotics expert explains that the process of building a robust robot should start right from being a baby, just as in humans.
Josh Bongard created both simulated and actual robots that, like tadpoles becoming frogs, change their body forms while learning how to walk.
Year after year, his simulated robots also evolved, spending less time in “infant” tadpole-like forms and more time in “adult” four-legged forms, becoming abler than ones with fixed body forms.
“This paper shows that body change, morphological change, actually helps us design better robots,” Bongard said.
In some ways, they are too much like people for people to easily understand them, he says.
“They have lots of moving parts. And their brains, like our brains, have lots of distributed materials: there’s neurons and there’s sensors and motors and they’re all turning on and off in parallel and the emergent behaviour from the complex system which is a robot, is some useful task like clearing up a construction site or laying pavement for a new road,” Bongard said.
Bongard used a computer simulation to release a series of robots that move about in a 3-dimensional space.
“It looks like a modern video game,” he says. Each creature -- or, rather, generations of the creatures -- then run a software routine, called a genetic algorithm, that experiments with various motions until it develops a slither, shuffle, or walking gait -- based on its body plan -- that can get it to the light source without tipping over.
“The robots have 12 moving parts. They look like the simplified skeleton of a mammal: it’s got a jointed spine and then you have four sticks -- the legs -- sticking out,” Bongard said.
“The snake and reptilian robots are, in essence, training wheels,” said Bongard, “they allow evolution to find motion patterns quicker, because those kinds of robots can’t fall over. So evolution only has to solve the movement problem, but not the balance problem, initially. Then gradually over time it’s able to tackle the balance problem after already solving the movement problem.”
In effect, the robots are being ‘raised’ as humans, who are taught how to roll, then crawl and, finally, walk.
This is proven by results of Bongard’s study: the changing robots were not only faster in getting to the final goal, but afterward were more able to deal with new kinds of challenges that they hadn’t before faced, like efforts to tip them over.
“This is an inheritance from traditional artificial intelligence in which computer programs were developed that had no body with which to affect, and be affected by, the world.”
The study appears in the January 10 online edition of the Proceedings of the National Academy of Sciences.