Decentralized control of robotic manipulators with neural networks

Author

Xiang, C. ; Siow, S.Y.

Author_Institution

Dept. of Electr. & Comput. Eng., National Univ. of Singapore, Lower Kent Ridge Road, Singapore

Volume

3

fYear

2004

fDate

6-9 Dec. 2004

Firstpage

2029

Abstract

A decentralized neuro-controller with feedback error learning is proposed in this paper to deal with robot manipulator tracking problem. The PD + nonlinear (NL) feedback law + robustifying signal ensure global stability while the neural networks are utilized to compensate the decentralized nonlinear terms in the robot manipulator dynamics so that both robustness and good tracking performance are achieved. In addition to the theoretical proof of global stability, the effectiveness of the proposed scheme is also demonstrated by comparing the tracking performance of the neuro-controller for a two-link robot manipulator with that of the conventional decentralized adaptive controller.

Keywords

PD control; adaptive control; decentralised control; feedback; manipulator dynamics; neurocontrollers; recurrent neural nets; PD control; conventional decentralized adaptive controller; decentralized control; decentralized neurocontroller; decentralized nonlinear terms; feedback error learning; global stability theoretical proof; neural networks; neurocontroller tracking; nonlinear feedback law; robot manipulator dynamics; robot manipulator tracking problem; robotic manipulators; robustifying signal; two link robot manipulator; Control systems; Distributed control; Error correction; Manipulator dynamics; Neural networks; Neurofeedback; Robots; Robust stability; Symmetric matrices; Torque;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation, Robotics and Vision Conference, 2004. ICARCV 2004 8th

Print_ISBN

0-7803-8653-1

Type

conf

DOI

10.1109/ICARCV.2004.1469475

Filename

1469475