Adaptive control of robot manipulators using an incremental fuzzy system

An adaptive control using an incremental fuzzy system is proposed in this paper. The overall controller is comprised of a conventional PD controller and a fuzzy controller which learns the inverse dynamics model of the robot manipulator. The structure and parameters of the fuzzy controller are determined dynamically by using an incremental hyperplane-based fuzzy clustering. Its parameters are further refined to compensate for the unmodeled dynamics of the system. The proposed control scheme is applied to control a two-link robot manipulator. The simulation results show that the proposed method can give favorable tracking performance by incorporating of an incremental learning and an adaptive control technique.