Design of Fuzzy-Neural-Network-Inherited Backstepping Control for Robot Manipulator Including Actuator Dynamics

Abstract

This study presents the design and analysis of an intelligent control system that inherits the systematic and recursive design methodology for an n-link robot manipulator, including actuator dynamics, in order to achieve a high-precision position tracking with a firm stability and robustness. First, the coupled higher order dynamic model of an n-link robot manipulator is introduced briefly. Then, a conventional backstepping control (BSC) scheme is developed for the joint position tracking of the robot manipulator. Moreover, a fuzzy-neural-network-inherited BSC (FNNIBSC) scheme is proposed to relax the requirement of detailed system information to improve the robustness of BSC and to deal with the serious chattering that is caused by the discontinuous function. In the FNNIBSC strategy, the FNN framework is designed to mimic the BSC law, and adaptive tuning algorithms for network parameters are derived in the sense of the projection algorithm and Lyapunov stability theorem to ensure the network convergence as well as stable control performance. Numerical simulations and experimental results of a two-link robot manipulator that are actuated by dc servomotors are provided to justify the claims of the proposed FNNIBSC system, and the superiority of the proposed FNNIBSC scheme is also evaluated by quantitative comparison with previous intelligent control schemes.