Meet the most nimble-fingered robot yet
Many researchers are working on ways for robots to learn to grasp and manipulate things by practicing over and over, but the process is very time-consuming. The research work on robotic deep learning by Prof. Ken Goldberg is featured on the cover of MIT Review in an article titled “Meet the Most Nimble-Fingered Robot Yet“. Instead of practicing in the real world, Prof. Ken Goldberg and colleagues have developed a robot that learns by feeding on a data set of more than a thousand objects that includes their 3-D shape, visual appearance, and the physics of grasping them. This data set was used to train the robot’s deep-learning system. Advances in control algorithms and machine-learning approaches, together with new hardware, are steadily building a foundation on which a new generation of robots will operate.