Robot Uses Evil Alter Ego to Learn Reliable Grasping

Adversarial grasping helps robots learn better ways of picking up and holding onto objects

4 min read

Robot Adversaries for Learning Tasks
CMU and Google researchers are using an adversarial training strategy based on game theory and deep learning to improve manipulation tasks such as grasping. The adversary can be a robot that tries to disrupt another robot grasping an object (as in the photo above), or it can be one of the arms of a dual-armed robot trying to snatch the object from the other arm.
Image: CMU