SAN FRANCISCO--Ken Goldberg, a professor at UC Berkeley, and one of his graduate students, Jeff Mahler, recently demonstrated the latest version of a dexterous collaborative robot at EmTech Digital, an event held here this week organized by MIT Technology Review (MTR) and dedicated to artificial intelligence. The key to the robot's dexterity is not in its mechanical grippers but in its brain, reports the MTR website.
The robot uses software called Dex-Net to determine how to pick up even odd-looking objects with incredible efficiency. Because of this software, the robot can generalize from an object it has seen before to a new one. The robot will even nudge an item to get a better look at it if it isn’t sure how it should be grasped.