Hybrid neural network and variable structure control for robot

Author

Mingjiang, Xie ; Wei, Tan ; Songjiao, Shi ; Ying, Dai

Author_Institution

Dept. of Autom., Shanghai Jiaotong Univ., China

Volume

2

fYear

2000

fDate

2000

Firstpage

1342

Abstract

This paper proposes a neural-network and continuous sliding mode hybrid control method for robot manipulators, which has a unknown model. First, a feedforward neural network is used to learn the characteristics of the robot system (or specially its inverse dynamics) for accurate trajectory following and smooth torque control. Then, a saturated-function-based continuous sliding mode controller is used to guarantee the convergence of the tracking errors, reduces or even eliminates the chattering. Simulations of a two-link robot are given to illustrated the good transient performance and smooth control torque

Keywords

feedforward neural nets; manipulator dynamics; neurocontrollers; stability; torque control; tracking; transient response; variable structure systems; convergence; feedforward neural network; inverse dynamics; robustness; sliding mode; torque control; trajectory tracking; transient response; two-link manipulators; variable structure control; Automatic control; Control systems; Feedforward neural networks; Feedforward systems; Manipulator dynamics; Neural networks; Robot control; Robotics and automation; Sliding mode control; Torque control;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on

Conference_Location

Hefei

Print_ISBN

0-7803-5995-X

Type

conf

DOI

10.1109/WCICA.2000.863463

Filename

863463