Learning precise 3D reaching in a humanoid robot

In this paper we discuss the implementation of a precise reaching controller on an upper-torso humanoid robot. The proposed solution is based on a learning strategy which does not rely on a priori models of the kinematics of the arm nor of that of the head. After learning, the robot can reach for visually identified objects in 3-D space by integrating an open loop and a closed loop component; the open loop controller allows ballistic movements, while the closed loop one performs precise positioning of the hand in visual space. Differently from other approaches we handle the critical case of redundancy in the head and the arm and propose a solution that although preliminary possesses some biological relevance.