PR2 Robot Can Scan And Bag Your Groceries

Normally, when a robot wants to pick something up that it's never  seen before, it either has to download a 3D model of the object, make  its own 3D model and analyze it, or be trained by a human on the right  way to grip. Unfortunately, none of these things are really practical to  do in the fast paced world of grocery checkout lines.

Researchers at Stanford University have figured out that in order to  pick something up, all you really need to know is whether a piece of it  has the same basic shape as the shape of your gripper. If it does, then  you can mostly likely grip it tolerably well, and experimentally the  success rate is better than 90 percent. Best of all, you can extract  this shape information from one simple (and quick) 3D scan, even if  you've got a big cluttered pile of stuff. Once the robot has picked up  an object, it holds it up to its cameras to scan for the barcode, adds  it to your tab, and bags it for you. Watch a demo of their method  implemented on a PR2:

read the complete article on IEEEspectrum