The RBF neural network control for the uncertain robotic manipulator

Abstract

A new control strategy is proposed for unknown robotic manipulators in this paper. The control scheme combines RBF neural network algorithm and sliding mode. The controller used respective RBFNN to approach the structural and parameters uncertainty, the system stability is ensured by the sliding mode control, and the robust control focus compensate effectively to eliminate the network approximation error. As for the chattering in the sliding mode control, a hyperbolic function is applied to replace the symbols to eliminate the chattering phenomenon effectively and decrease the control input when the precision error is permit. The stability of the control system was ensured by Lyapunov method. The tracking error asymptotic converges to zero. The simulation studies verify the effectiveness of the proposed algorithm.