Slashdot Mirror
RightHand Robotics Automates a New Type of Warehouse Work: Recognizing, Picking Up Items From Boxes (qz.com)
An anonymous reader quotes a report from Quartz: A startup called RightHand robotics recently began piloting technology that automates a task robots have previously struggled to master: recognizing and picking up items from boxes. RightHand can't say which companies are part of its pilot project and Amazon didn't reply to a request for comment. But the new technology could help the ecommerce giant with a problem that has long vexed it. Like robots elsewhere, Amazon's robots retrieve entire shelves and transport them to humans who pick out items from them. They can find and move a shelf that holds a box of shirts, but they aren't capable of removing the single shirt from that box to be packed into an order. In order to pick items from boxes, robots need to master the more complex task of identifying a wide range of objects and adjusting their grips accordingly. RightHand robotics, which was started by a team of researchers from Harvard Biorobotics Lab, the Yale Grab Lab, and MIT, built a solution called RightPick that, according to co-founder Leif Jentoft, can pick items at a rate of 500 to 600 per hour -- a speed on par with a human worker. It uses a machine learning background and a sensitized robot hand to recognize and handle thousands of items.
Robots that can see. And respond in sensible ways.
"Bin Picking" requires recognizing which objects are which, and what their orientation ("pose") is. Then plan a way to move to collect them.
That is an order of magnitude more sophisticate than simply moving in rigid, predefined ways to work on things that have been precisely positioned in advanced.
It opens up whole new fields of automation.
And it is not that new, bin picking robots have been around for a while. They are getting better. This is only a story because Amazon is doing it now.