Repositioning control of robotic arms by learning

Abstract

The problem of moving a rigid robot between equilibrium points by means of a learning algorithm, which uses only the positioning error at the end of a trial, is investigated. After high gain feedback linearization of the robot dynamics, it is shown that simple, robust, finite dimensional learning algorithms can be set up to accomplish this task for unconstrained robots and robots subject to smooth bilateral constraints for which hybrid force control is of interest.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>