|
A NEURAL NETWORK-BASED ADAPTIVE SLIDING MODE CONTROL FOR ROBOT MANIPULATORS
Yugang Niu†, Xingyu wang†, and Chengwu Yang‡
† School of Information, East China University of Science and Technology, Shanghai, 200237, P.R.C
‡ School of Power Engineering, Nanjing University of Science and Technology, Nanjing, 210094, P.R.C
An adaptive sliding mode tracking controller using neural network is proposed for robot with uncertainties. In this new control scheme, a RBF neural network is used to adaptively learn system uncertainties bounds in the Lyapunov sense, and then the outputs of neural network is used to adjust the switching gain. This new controller can guarantee both strong robustness with respect to system nonlinearities and uncertainties and the asymptotic convergence of the tracking error to zero.
Keywords: Manipulators, neural networks, adaptive control, sliding-mode control, robustness
Session slot T-Th-E15: Application of Robust Control III/Area code 2e : Robust Control
 | 