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. […]

Quanta Magazine  February 14, 2018 Researchers at the Georgia Institute of Technology are experimenting with flapping robots called “smarticles” which can’t move on their own. But when a lot of these objects are put together they start to work as a unit. Researchers are learning how to control these systems so that when the swarm comes together, its members can carry out complex behaviors without any centralized direction. Other efforts in the field of self-organizing robots include “droplet-size robots” being developed at the University of Colorado, “Kilobot swarms” at Harvard University, and “swarmanoids” out of a pioneering lab in Belgium… […]