The adaptive sliding mode control based on a fuzzy neural network for manipulators

In this paper, a new control scheme for the computer control of a robot manipulator is provided (as shown in Fig. 1), where a fuzzy neural network is presented and employed to identify the robot dynamics,a feedforward control algorithm is designed to compensate for variations in mass, gravity, coriolis and centrifugal term, and the discrete sliding mode control is used to reduce further the remaining system uncertainty for precious position tracking. The whole control algorithms are developed in the discrete-time form, which is very suitable to the computer control of robot manipulators.