Robots Recover from Damage in Minutes by Adapting and 'Healing' Body Parts

Robots could be huge for search and rescue missions and going to places where humans can't tread. Yet what happens if a robot is damaged in a dangerous area? It has to be able to adapt and now, scientists may have succeeded in creating a robot that does just that.

In contrast to today's robots, animals can learn to overcome or adapt to an injury. For example, dogs can learn to walk and function on three legs, and humans can learn to hobble around even with a sprained ankle.

"When injured, animals do not start learning from scratch," said Jean-Baptiste Mouret, one of the researchers, in a news release. "Instead, they have intuitions about different ways to behave. These intuitions allow them to intelligently select a few, different behaviors to try out and, after these tests they choose one that works in spite of the injury. We made robots that can do the same."

In this case, the researchers created a robot that uses a computer simulation of itself to create a detailed map of the space of high-performing behaviors, dubbed the Trial and Error algorithm. If the robot is damaged, it uses these "intuitions" to guide a learning algorithm that then conducts experiments to develop a compensatory behavior that will work despite the damage.

"Once damaged, the robot becomes like a scientist," said Antoine Cully, lead author of the new study. "It has prior expectations about different behaviors that might work, and begins testing them. However, these predictions come from the simulated, undamaged robot. It has to find out which of them work, not only in reality, but given the damage."

In this case, the new algorithm could be huge in terms of creating robots that can help rescuers without requiring their continuous attention. It also makes it easier to create personal robotic assistants that can continue to function even when a part is broken.

The findings are published in the journal Nature.

Related Stories

 Drone Flies Autonomously and Learns New Routes Using Navigation System

For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).