NEURO-ADAPTIVE CONTROL WITH APPLICATION TO ROBOTIC SYSTEMS

This article presents a highly model-independent neural network (NN)-b ased adaptive control method for a class of nonlinear dynamic systems. Two NN units are incorporated into the control scheme which are shown to be effective in attenuating NN reconstruction error and other lump ed system uncertainties. Because the control scheme is based on the wo rst case behavior of the NNs, it exhibits a ''fail-safe'' feature, whi ch enhances the reliability of the NN-based control scheme. Stable on- line weight-tuning algorithms are derived based on Lyapunov stability theory. The control method is extended to robotic systems and simulati on on a three-joint robot is presented. (C) 1997 John Wiley & Sons, In c.