Stable discrete-time neural control for robots using adaptive bounding techniques

A neural network (NN)-based adaptive control law is proposed in this paper for the tracking control of an n-link robot manipulator with unknown dynamic nonlinearities. Locally-generalized neural networks are employed to approximate the plant nonlinearities, and a bound on the network reconstruction error is assumed to be unknown. The proposed NN-based adaptive control approach integrates a NN approach with an adaptive implementation of the dynamic sliding mode control, includes a simple estimation law for the upper bound on the NN reconstruction error and an additional control input to be updated as a function of the estimation. Using the Lyapunov stability theory, the uniform ultimate boundedness of the tracking error is proved