Variable structure control for 6-6 parallel manipulators based on cascaded CMAC

Abstract

This paper proposes a novel control scheme with focus on the uncertainty of the complex robot system, which combines a cascaded cerebellar model articulation controller (CMAC) with variable structure control (VSC). Firstly, an improved CMAC is used to learn the uncertainty of the robot system, and it is used as a feed-forward compensator, fast tracking error convergence and better learning stability is obtained through the use of cascaded CMAC. Then, a VSC term is used to reduce the effect of CMAC estimate error and unrepeatable disturbances. The control law is chosen based on the Lyapunov direct method. Simulation of 6-6 parallel manipulator trajectory tracking shows that good stability and accuracy are obtained.