A neural network based feedforward adaptive controller for robots

Author

Carelli, Ricardo ; Camacho, Eduardo F. ; Patino, Daniel

Author_Institution

Univ. Nacional de San Juan, Argentina

Volume

25

Issue

9

fYear

1995

fDate

9/1/1995 12:00:00 AM

Firstpage

1281

Lastpage

1288

Abstract

In this paper, an adaptive controller for robot manipulators which uses neural networks is presented. The proposed control scheme is based on PD feedback plus a feedforward compensation of full robot dynamics. The feedforward signal is obtained by summing up the weighted outputs of a set of fixed multilayer neural nets. The controller is adaptive to robot dynamics and payload uncertainties. A stability analysis which takes into account neural network learning errors is included. Simulation results showing the feasibility and performance of the approach are given

Keywords

adaptive control; compensation; feedback; feedforward; manipulator dynamics; multilayer perceptrons; neurocontrollers; stability; two-term control; PD feedback; feedforward compensation; fixed multilayer neural nets; learning errors; neural network based feedforward adaptive controller; payload uncertainties; robot dynamics; robot manipulators; stability analysis; Adaptive control; Adaptive systems; Feedforward neural networks; Manipulator dynamics; Multi-layer neural network; Neural networks; Neurofeedback; Payloads; Programmable control; Robot control;

fLanguage

English

Journal_Title

Systems, Man and Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9472

Type

jour

DOI

10.1109/21.400506

Filename

400506