Research on sliding mode control for robotic manipulator based on RBF neural network

In this paper, a new RBF based sliding mode controller is proposed for the joint trajectory tracking of robotic manipulators with uncertainties and disturbances. A RBF neural network is employed to approximate the nonlinear uncertainties in the mode, adaptive laws of the parameters are established, and the approximation error is compensated by designing a sliding mode controller, in which a generalized error factor is introduced. As a result, the chattering is eliminated and error performance is improved. The stability of closed-loop system and the asymptotic convergence of tracking error are guaranteed based on the Lyapunov theory. Simulation results demonstrate the effectiveness and robustness of the proposed control strategy.