Trajectory tracking control of robot manipulator based on RBF neural network and fuzzy sliding mode

Aimed at the nonlinearity and uncertainty of the manipulator system, a RBF (radial basis function) neural network-based fuzzy sliding-mode control method was proposed in this paper, in order to make the manipulator track the given trajectory at an ideal dynamic quality. In this method, the equivalent part of the sliding-mode control is approximated by the RBF neural network, in which no model information is required. Meanwhile, a fuzzy controller is developed to make adaptive adjustment of the sliding-mode control’s switching gains according to the distance between the current motor point and the sliding-mode surface, thus effectively the problem of chattering is solved. This method has, to some extent, improved the performance of response and tracking, and reduced the time of adjustment and chattering of input control. The system stability is verified by Lyapunov’s theorem. The simulation result suggests that the algorithm designed for the three-degree-of-freedom (3DOF) manipulator system is effective.