Science Daily January 30, 2019
Researchers at Columbia University have created a robot that learns what it is, from scratch, with zero prior knowledge of physics, geometry, or motor dynamics. After a brief period of “babbling,” and within about a day of intensive computing, the robot creates a self-simulation and uses that self-simulator internally to contemplate and adapt to different situations, handling new tasks as well as detecting and repairing damage in its own body. Using a four-degree-of-freedom articulated robotic arm, initially the robot moved randomly and collected approximately one thousand trajectories. Then used deep learning to create a self-model. After less than 35 hours of training, the self-model became consistent with the physical robot to within about four centimeters…read more. TECHNICAL ARTICLEÂ
Engineers create a robot that can ‘imagine’ itself
Posted in Autonomous systems and robotics and tagged Robotics.