Adaptive position tracking control system based on recurrent fuzzy wavelet neural networks for robot manipulators

Abstract

In this article, we propose an adaptive recurrent fuzzy wavelet neural network control strategy to improve high-accuracy position tracking for robot manipulators. In order to deal with the unknown knowledge of the robot system problems, the adaptive recurrent fuzzy wavelet neural networks are applied in the main controller to approximate the unknown dynamics without the requirement of prior knowledge. In addition, an adaptive robust control law is also developed to eliminate uncertainties that consist of estimation errors and disturbances from the robot control system. The design of the adaptive online learning algorithms is determined using the Lyapunov stability theorem. Therefore, the proposed controller proves that it can guarantee not only the stability and robustness but also the tracking performance of the robot manipulators control system. The effectiveness and robustness of the proposed method are demonstrated by comparative simulation and experimental results.