London: Scientists have developed next-generation of robots that automatically recover from injury in less than two minutes by adapting like humans and animals. A video shows a six-legged robot that adapts to keep walking even if two of its legs are broken. It also shows a robotic arm that learned how to correctly place an object even with several broken motors. In contrast to today's robots, animals exhibit an amazing ability to adapt to injury. There are many three-legged dogs that can catch Frisbees, for example, and if your ankle is sprained, you quickly figure out a way to walk despite the injury.
The scientists took inspiration from these biological strategies. Before it is deployed, the robot uses a computer simulation of itself to create a detailed map of the space of high-performing behaviours. This map represents the robot's "intuitions" about different behaviours it can perform and their predicted value. If the robot is damaged, it uses these intuitions to guide a learning algorithm that conducts experiments to rapidly discover a compensatory behaviour that works despite the damage. The new algorithm is called "Intelligent Trial and Error."
"Once damaged, the robot becomes like a scientist," said lead author Antoine Cully from the Pierre and Marie Curie University in France."It has prior expectations about different behaviours 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. "Each behaviour it tries is like an experiment and, if one behaviour doesn't work, the robot is smart enough to rule out that entire type of behaviour and try a new type," Cully said. "For example, if walking, mostly on its hind legs, does not work well, it will next try walking mostly on its front legs.
What's surprising is how quickly it can learn a new way to walk. It's amazing to watch a robot go from crippled and flailing around to efficiently limping away in about two minutes," said Cully. The same Intelligent Trial and Error algorithm allows robots to adapt to unforeseen situations, including adapting to new environments and inventing new behaviours.
Jeff Clune from the University of Wyoming explained that "technically, Intelligent Trial and Error involves two steps: Creating the behaviour-performance map, and adapting to an unforeseen situation." This new technique will help develop more robust, effective, autonomous robots."It could enable the creation of robots that can help rescuers without requiring their continuous attention," Clune added.
