Adaptive control of two-link manipulator via dynamic neural network

Author

Yu, Wen ; Poznyak, Alexander S. ; Sanchez, Edgar N.

Author_Institution

Seccion de Control Autom., CINVESTAV-IPN, Mexico City, Mexico

Volume

4

fYear

1999

fDate

1999

Firstpage

2516

Abstract

A neurocontrol method for robot manipulators is presented. A single-layer dynamic neural network is used to estimate the unknown manipulators, then a direct linearization controller is derived based on the neuro identifier. Because the approximation capability is limited, another PD-like controller is applied to compensate the unmodeled dynamics. The main contribution of the paper is that the boundness of the identification error and tracking error are established

Keywords

Riccati equations; adaptive control; identification; manipulator dynamics; matrix algebra; neurocontrollers; two-term control; PD-like controller; approximation capability; boundness; direct linearization controller; dynamic neural network; identification error; neuro identifier; neurocontrol method; robot manipulators; single-layer network; tracking error; two-link manipulator; unmodeled dynamics; Adaptive control; Manipulator dynamics; Neural networks; Optimal control; Robots; Robust control; Robust stability; Sliding mode control; Symmetric matrices; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 1999. Proceedings of the 1999

Conference_Location

San Diego, CA

ISSN

0743-1619

Print_ISBN

0-7803-4990-3

Type

conf

DOI

10.1109/ACC.1999.786507

Filename

786507