Collaborative Assessment and Feedback Engine

36483606864 bb91528323 k
Eugene Pang

September 5, 2017

3066863 inline i 3 our aspiring robot overlords are still klutzes

While machines continue to reduce much of the drudgery that humans endure, there are still some problems which remain extremely difficult for roboticists and other engineers to solve. Why is it that some technologies such as virtual reality and self-driving cars are becoming a reality, but we still do not have anything like Rosie the robot maid from The Jetsons?

In this recent interview at Fast Company, IEOR Professor & Chair Ken Goldberg shows how one of the simplest tasks for humans — grasping an object — is an extremely difficult job for a robot.  Ken also discusses the work being done at the Berkeley AUTOLAB, where his research team have created Dex-Net 1.0, a cloud-based network of 3D objects that use Big Data tools to help teach robots to improve their dexterity.

Read the whole story "Why It's So Hard for Robots to Get a Grip" at Fast Company