Robot Hand Learns Real World Moves in Virtual Training

Robot Hand Learns Real World Moves in Virtual Training
Dactyl, a system for manipulating objects, uses a ShadowRobot Dexterous hand made in the UK to hold a 3D-printed and spraypainted block, as seen in this photo provided July 30, 2018. OpenAI/Handout via REUTERS
|Updated:

Researchers backed by Tesla Inc. founder Elon Musk and Silicon Valley financier Sam Altman have found a novel way to use software to teach a human-like robotic hand new tasks, a discovery that could eventually make it more economical to train robots to do things that are easy for humans.

Researchers at OpenAI, a nonprofit artificial intelligence research group founded in 2015, said on Monday they had taught a robotic hand to rotate a lettered, multicolored block until a desired side of the block faces upward.