London: Researchers have developed an algorithm that allows a robot to teach itself to walk with a broken or damaged leg.
When animals lose a limb, they learn to hobble remarkably quickly but when robots damage a leg, they become completely incapacitated.
Scientists Antoine Cully and Jean-Baptiste Mouret of the Sorbonne University in Paris and Jeff Clune of the University of Wyoming developed the algorithm that allowed a six-legged robot to learn to adjust to having one of its legs broken.
The robot learned to walk again in less than two minutes.
The robot tries to mimic animals to discover which leg is broken and then uses trial and error to figure out the best way to continue walking, `BBC News` reported.
The work could have a significant impact on the reliability and robustness of walking robots.
"This new technique will enable more robust, effective, autonomous robots," researchers said.