For a robot, it was a remarkable trick. When first presented with that pile of clutter, the arm did not know how to pick up a single object. But equipped with a camera that looked down into the bin, the Google system analyzed its own progress during about 14 hours of trial and error.Google covers the project in more technical detail on its AI blog.
The arm eventually learned to toss items into the right bins about 85 percent of the time. When the researchers tried the same task, their accuracy rate was about 80 percent.
It may sound simple enough, but writing computer code to tell a machine how to do that would be extremely difficult. “It is learning more complicated things than I could ever think about,” said Shuran Song, one the primary researchers on the project.
Google TossingBot tosses objects in the right box (video)
Posted on Wednesday, March 27 2019 @ 12:16 CET by Thomas De Maesschalck
The sale of Boston Dynamics doesn't mean Google is no longer experimenting with robots. Many of the employees of the former robotics team are now working on different, simpler robots that take advantage of machine learning to speed up tasks. NY Times got to see a new robot that can pick up random objects in a box, and throw it into a smaller bin a few feet away.