CONTROL OF THE TRAJECTORY OF A PLANAR ROBOT USING RECURRENT HYBRID NETWORKS

This paper describes the use of recurrent neural networks in the contr ol of a simulated planar two-jointed robot arm. Recurrent networks hav e feedback connections and thus an inherent memory for dynamics which makes them suitable for dynamic system modelling. A feature of the net works adopted is their hybrid hidden layer which includes both linear and non-linear neurons. This facilitates learning of the inverse dynam ics model of the robot which can be thought of as comprising a linear and a non-linear part. Following a brief description of the control pr oblem and alternative PID and computed-torque control schemes, the pro posed neural network and neural controller will be detailed. The resul ts presented show the superior ability of the proposed neural control scheme at adapting to changes in the dynamics parameters of the robot. (C) 1998 Elsevier Science Ltd. All rights reserved.