T-S fuzzy-neural control for robot manipulators

Abstract

This paper proposes a novel method of on-line modeling and control through the Takagi-Sugeno (T-S) fuzzy-neural model for a class of general n-link robot manipulators. Compared with the previous method, the main contribution of this paper is an investigation of the more general robot systems using on-line adaptive T-S fuzzy-neural controller. Specifically, the general robot systems are exactly formed a linearized system via the mean value theorem, and then the T-S fuzzy-neural model can approximate the linearized system. Also, we propose an on-line identification algorithm and put significant emphasis on robust tracking controller design using an adaptive scheme for the robot systems. Finally, an example including two cases is provided to demonstrate feasibility and robustness of the proposed method.