Adaptive tracking controller design for robotic systems using Gaussian wavelet networks

Abstract

An adaptive tracking control design for robotic systems using Gaussian wavelet networks is proposed. A Gaussian wavelet network with accurate approximation capability is employed to approximate the unknown dynamics of robotic systems by using an adaptive learning algorithm that can learn the parameters of the dilation and translation of Gaussian wavelet functions. Depending on the finite number of wavelet basis functions which result in inevitable approximation errors, a robust control law is provided to guarantee the stability of the closed-loop robotic system that can be proved by Lyapunov theory. Finally, the effectiveness of the Gaussian wavelet network-based control approach is illustrated through comparative simulations on a six-link robot manipulator.