In a step toward robots that can learn on the fly like humans do, a new approach expands training data sets for robots that work with soft objects like ropes and fabrics, or in cluttered environments.

It could cut learning time for new materials and environments down to a few hours rather than a week or two.

In simulations, the expanded training data set improved the success rate of a robot looping a rope around an engine block by more than 40% and nearly doubled the successes of a physical robot for a similar task.

That task is among those a robot mechanic would need to be able to do with ease. But using today’s methods, learning how to manipulate each unfamiliar hose or belt would require huge amounts of data, likely gathered for days or weeks, says Dmitry Berenson, an associate professor of robotics at the University of Michigan and senior author of a paper the researchers presented at Robotics: Science and Systems.

In that time, the robot would play around with the hose—stretching it, bringing the ends together, looping it around obstacles and so on—until it understood all the ways the hose could move.

“If the robot needs to play with the hose for a long time before being able to install it, that’s not going to work for many applications,” Berenson says.

Indeed, human mechanics would likely be unimpressed with a robot coworker that needed that kind of time. So Berenson and Peter Mitrano, a doctoral student in robotics, put a twist on an optimization algorithm to enable a computer to make some of the generalizations we humans do—predicting how dynamics observed in one instance might repeat in others.

In one example, the robot pushed cylinders on a crowded surface. In some cases, the cylinder didn’t hit anything, while in others, it collided with other cylinders and they moved in response.

By: Kate McAlpine

FULL ARTICLE: https://www.nextgov.com/emerging-tech/2022/07/fake-data-gets-robots-learn-new-stuff-faster/368994/