A dexterous multi-fingered robot has been created at the University of California. It practiced using virtual objects in a simulated world and learned what kind of grip should work for different items by studying a vast data set of 3-D shapes and suitable grasps. When a new object is placed in front of it, the robot?s deep-learning system quickly figures out what grasp the arm should use. The creation of this robot shows how machine learning and the cloud could revolutionise manual work where precision and consistency are key.
https://www.technologyreview.com/s/607931/meet-the-most-nimble-fingered-robot-yet/
idealist
Jonathan Chrimes