Experimental Evaluation of a Sectorial Fuzzy Controller Plus Adaptive Neural Network Compensation Applied to a 2-DOF Robot Manipulator

Abstract

Abstract In this paper we propose a novel control architecture that employs an adaptive neural network (NN) for feedforward compensation and a sectorial fuzzy controller in the feedback loop applied to the trajectory tracking control of robot manipulators. Both simulation and experimental results are presented in comparison with the original classic Proportional-Derivative (PD) plus feedforward controller, from which this new proposal is based, and two preliminary versions of the application of feedforward sectorial fuzzy control and feedforward adaptive neural nonlinear PD control to the trajectory tracking control of a two-degree of freedom (2-DOF) robot manipulator. The proposed controller has, in general, better performance than its counterparts in terms of transient response and steady-state error while it maintains one of the main characteristics of fuzzy controllers: Its tolerance to parameter deviation.