ThangLong Mai, YaoNan Wang, and ThanhQuyen Ngo
Fuzzy neural networks, wavelet neural networks, adaptive robust control, robot manipulators
In this paper, we propose an adaptive tracking control strategy for robot manipulators using fuzzy wavelet neural networks (FWNNs). The purpose of this approach is to ensure the tracking errors of the robot control system asymptotically converge to zero. The FWNNs are applied for approximating the unknown/uncertain dynamics of the robotic system. In addition, an adaptive robust compensator is proposed to eliminate uncertainties that consist of the unknown approximation errors and disturbances. The design of the adaptive online-learning algorithms for the FWNNs and the robust compensator is determined by using the Lyapunov stability theorem. Therefore, the proposed controller proves that it not only can guarantee the stability and robustness but also the tracking performance of the robot manipulators control system. The effectiveness and robustness of the proposed method are verified by comparative simulation and experimental results.
Important Links:
Go Back
