Continuous-time decentralized wavelet neural control for a 2 DOF robot manipulator

Abstract

This paper presents a decentralized wavelet neural control scheme for trajectory tracking of a two degrees of freedom (DOF) vertical robot manipulator. A decentralized recurrent wavelet first order neural network (RWFONN) structure is proposed to identify online, in a series-parallel configuration and using the filtered error (FE) training algorithm, the dynamics behavior of the plant. Based on the RWFONN subsystem, a local neural controller is designed via backstepping approach. The performance of the decentralized wavelet neural controller is validated via simulation.