UC Berkeley’s AUTOLAB robots get closer to human-like dexterity

MIT Technology Review: The most nimble-fingered machine yet shows how machine learning can teach robots to recognize and pick up different types of objects, a skill that could transform many factories and warehouses.

CITRIS People and Robots Director Ken Goldberg, along with graduate student Jeffrey Mahler, and researchers at the Laboratory for Automation Science and Engineering (AUTOLAB), created the Dex-Net robot (now in version 4.0), the most dexterous robot yet, which uses a 3D sensor, two arms to grasp with, and a cloud-based neural network trained to identify objects and choose the best points to grasp.

Read more >> 

Related Video (by CITRIS Media):