Adaptive stabilization of neural control for robot traj ectory tracking

A neural network (NN)-based adaptive control law is proposed for the tracking control of an n-link robot manipulator with unknown dynamic nonli nearities. Basis ftnction-like nets are employed to approximate the plant nonli nearilties, and the bound on the NN reconstruction error is assurred to be unknown. The proposed NN-based adaptive control approach integrates an NN approach with an adaptive implementation of discrete variable structure control with a simple estimation law to estimate the upper bound on the NN reconstruction error and an additional control input to be updated as a function of the estimate. Lyapunov stability theory is used to prove the uni form ultimate boundedness of the tracking error.