Mit teaches robotic hands to reorient 2,000 objects in one hand

Researchers at the MIT Computer Science and Artificial Intelligence Lab are working to create a realistic, robotic hand. The program can reorient over 2,000 different objects without prior knowledge of the object’s shape. Scientists taught the robot to counteract gravity gradually. First, they learned in a simulation without gravity. Then, researchers incrementally began to account for gravity.

CSAIL developed a program that trained a robot hand to solve a Rubik’s Cube. The program was the most effective with simple, round objects, like marbles, with an almost 100% success rate. Not surprisingly, the program struggled the most with complex objects,. The success rate for objects like these was 30%. The program operated entirely within simulated scenarios.

Related Articles


Please enter your comment!
Please enter your name here

Stay Connected


Latest Articles