Adaptive neural sliding mode control with prescribed performance of robotic manipulators subject to backlash hysteresis

Abstract

Robust and precise control of robot systems are still challenging problems due to the existence of uncertainties and backlash hysteresis. To deal with the problems, an adaptive neural sliding mode control with prescribed performance is proposed for robotic manipulators. A finite-time nonsingular terminal sliding mode control combined with a new prescribed performance function (PPF) is developed to guarantee the transient and steady-state performance of the closed-loop system. Based on the sliding mode variable, an adaptive law is presented to effectively estimate the bound of system uncertainties where the prior knowledge of uncertainties is not needed. To approximate nonlinear function and unknown dynamics, the Gaussian radial basis function neural networks(RBFNNs) is introduced to compensate the lumped nonlinearities. All signals of the closed-loop system are proven to be uniformly ultimately bounded (UUB) by Lyapunov analysis. Finally, comparative simulations are conducted to illustrate superiority and reliability of the proposed control strategy.

Wavelet neural network sliding mode control of two rigid joint robot manipulator

“…In order to meet the requirements of control performance, various advanced control technologies could be applied to the controllers of robotic manipulators. 1 Racking control of robot manipulators, which is required to provide high accuracy, stability and safety, in the presence of huge uncertainties, disturbance has been a critical issue in both academic and industrial applications. How to improve the tracking performance and transient response for robot manipulators, particularly in the presence of external disturbance and possible actuation failures is still a challenge research community.…”