Neural learning and dynamical selection of redundant solutions for inverse kinematic control

Abstract

We introduce a novel recurrent neural network controller that learns and maintains multiple solutions of the inverse kinematics. Redundancies are resolved dynamically by means of multi-stable attractor dynamics. The associative net- work comprises a combined forward and inverse model of the robot's kinematics and enables flexible selection of control spaces by mixing constraints in task space and joint space. The network is integrated into a feedforward-feedback control framework which enables dynamical movement generation. We show results for the humanoid robot iCub in simulation.