NN/RISE-based asymptotic tracking control of uncertain nonlinear systems

This paper presents a novel control methodology for the tracking control of a high-order continuous time nonlinear systems with unknown dynamics and external disturbance. The control signal consists of the robust integral of the sign of the error (RISE) feedback signal multiplied with an adaptive gain plus neural network (NN) output. The two-layer NN learns the system dynamics in an online manner while residual reconstruction errors and the external bounded system disturbances are overcome by the RISE signal. Semi-global asymptotic tracking performance is theoretically guaranteed by using the Lyapunov standard method, while the NN weights and all other signals are shown to be bounded. Further, simulations results are present to illustrate the control performance.