Radial-basis-functions neural network sliding mode control for underactuated manipulators

Abstract

This paper presents a neural network (NN) sliding mode control (NNSMC) and indirect adaptive technique Neural Network sliding mode control (IANSMC) for underactuated robot manipulators. The adaptive NN based on Radial Basis Functions (RBF) is used as an estimators to approximate uncertainties of the problem formulation. Adaptive learning algorithms in NNSMC are derived from the Lyapunov stability analysis. Sliding mode control and indirect adaptive technique (IANSMC) are combined to deal with modeling parameter uncertainties and bounded disturbances. The stability of the mixed controller is then proved. A radial basis function Neural Network is used to estimate system parameters and to compensate the uncertainties in the design of the sliding mode control. Neural network parameters are tuned on-line, with no off-line learning phase required. Discussions and comparisons between proposed controllers are presented. Simulation results show that the NNSM and IANSMC are betters than the traditional SMC to control underactuated manipulators.