Adaptive Recurrent Wavelet Fuzzy CMAC Tracking Control for De-icing Robot Manipulator

In this paper, a controller is proposed for a n-link robot manipulator to achieve the high-precision position tracking based on a recurrent wavelet fuzzy cerebellar model articulation controller (RWFCMAC) which is applied to imitate an ideal controller due to it incorporates the advantages of the wavelet decomposition property, dynamic response with a fuzzy CMAC fast learning ability and an adaptive single-input fuzzy compensator (ASIFC) is designed to attenuate the effect of the approximation error caused by the RWFCMAC approximator. The online tuning laws of RWFCMAC and ASIFC parameters are derived according to gradient descent method and lyapunov function so that the stability of the system can be guaranteed. Finally, through the simulation results demonstrate the effectiveness of the proposed control scheme for novel three-link De-Icing robot manipulator with unknown dynamic functions.