Scienceblogtwo

Shikhar Bahl opened the refrigerator door while the robot observed. It observed his actions, the way the door swung open, the position of the refrigerator, and other details before evaluating the information and getting ready to imitate what Bahl had done. It first failed, occasionally entirely missing the handle, gripping it at the wrong place, or dragging it in the wrong direction. However, after some practice, the robot was successful in opening the door. "Imitation is a terrific approach to learn," said Bahl, a Ph.D. candidate at Carnegie Mellon University's Robotics Institute (RI). Although it's still a challenge, this effort significantly advances the possibility of allowing robots to learn by directly observing people. In-the-Wild Human Imitating Robot Learning, or WHIRL for short, is a novel technique that Bahl created with Deepak Pathak and Abhinav Gupta, both professors at the RI. The one-shot visual imitation algorithm WHIRL is effective. Robots are ideally...