Adaptation of the visuo-motor coordination

Abstract

In this paper, a method is presented for the online learning of visually guided movements. The algorithms presented have been tested with a manipulator tracking manoeuvering targets. Three parameters critical for the visuo-motor coordination are learned in less than one hour with repeated movements. After this learning phase, the robot performs smooth and fast reaching movements and can easily drop small objects into the waggon of a moving model train, independently of the trajectory.