Neuro-adaptive tracking control algorithms for a class of nonlinear systems

Presents a neural network (NN) based adaptive control method for a class of nonlinear dynamic systems. Two NN units are incorporated into control scheme which are shown to be effective in attenuating NN reconstruction error and other lumped system uncertainties. Since the control scheme is based upon the worst case that the NNs might behave, it exhibits a “fail-safe” feature, which enhances the reliability of the NN-based control scheme. Stable online weights tuning algorithms are derived based on Lyapunov stability theory. The control method is extended to robotic systems