This Factory Robot Learns a New Job Overnight

MIT Technology Review:  Fanuc’s robot uses a technique known as deep reinforcement learning to train itself, over time, how to learn a new task. It tries picking up objects while capturing video footage of the process. Each time it succeeds or fails, it remembers how the object looked, knowledge that is used to refine a deep learning model, or a large neural network, that controls its action. Deep learning has proved to be a powerful approach in pattern recognition over the past few years.

“After eight hours or so it gets to 90 percent accuracy or above, which is almost the same as if an expert were to program it,” explains Shohei Hido, chief research officer at Preferred Networks, a Tokyo-based company specializing in machine learning. “It works overnight; the next morning it is tuned.”... (full story)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

ROBOTMASTER V7

ROBOTMASTER V7

Since Robotmaster V7 uses integrated CAD/CAM functionality, for the first time, the power of Robotmaster can be used by welding, cutting and other process experts without buying or learning complex CAD/CAM software. As in past versions, Robotmaster V7 imports paths, but now makes it even easier for end users to leverage any CAD/CAM tool choice. It is an intuitive tool that anyone could use, with or without robotics expertise. It bridges the gap between robots and manufacturing by providing easy programming solutions for part manufacturing.