Researchers at the Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a system that allows robots to do many different pick-and-place tasks, without having ever seen the objects with which they are interacting.
The new approach, Keypoint Affordance Manipulation (KPAM), detects a collection of coordinates on an object, which provide information the robot needs to determine what to do with that object.
This method can help a robot to handle variation between objects.
Said MIT researcher Russ Tedrake, "Understanding just a little bit more about the object, the location of a few key points, is enough to enable a wide range of useful manipulation tasks."
From MIT Computer Science & Artificial Intelligence Lab
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA