Visual Collision Detection for Corrective Movements during Grasping on a Humanoid Robot

We present an approach for visually detecting collisions between a robot's hand and an object during grasping. This allows to detect unintended premature collisions between parts of the hand and the object which might lead to failure of the grasp if they went unnoticed. Our approach is based on visually perceiving that the object starts to move, and is thus a good complement for force-based contact detection which fails e.g. in the case of grasping light objects that don't resist the applied force but are just pushed away. Our visual collision detection approach tracks the hand in the robot's camera images and analyzes the optical flow in its vicinity. When a collision is perceived, the most probable part of the hand to have caused it is estimated, and a corrective motion is executed. We evaluate the detection together with different reaction strategies on the humanoid robot ARMAR-III. The results show that the detection of failures during grasp execution and their correction allow the robot to successfully finish the grasp attempts in almost all of the cases in which it would otherwise have failed.