Abstract:

A new adaptive sliding mode controller using neural networks is proposed for the robust tracking controller design of an n link manipulator with unknown dynamics nonlinearities. The controller employs Gaussian radial basis function(RBF) neural networks to adaptively compensate for the plant nonlinearities. The system stability and tracking error convergence are proved using stability theory that yields a stable parameter learning law. Finally, the effectiveness of the proposed control approach is illustrated through simulation studies.

Key words: manipulators, adaptiveness, sliding mode control, neural networks