Controlling multi-link manipulators by fuzzy selection of dynamic models

T. Nanayakkara, K. Watanabe, Kazuo Kiguchi, K. Izumi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

A method for the identification of complex nonlinear dynamics of a multi-link robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs) in the absence of input torque information is proposed. The RKGNNs constructed using shape adaptive radial basis functions are trained by an evolutionary algorithm. Due to the fact that the main function network is divided into sub-networks to represent the dynamic properties of the manipulator, the neural networks have greater information, processing capacity and can be tested for properties such as positive definiteness of the inertia matrix. Dynamics of a three-link manipulator are identified using only their input-output position and velocity data, and promising control results are obtained to prove the effectiveness of the proposed method in capturing highly nonlinear dynamics of a multi-link manipulator.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
PublisherIEEE Computer Society
Pages638-643
Number of pages6
Volume1
DOIs
Publication statusPublished - Jan 1 2000
Externally publishedYes

Fingerprint

Manipulators
Dynamic models
Neural networks
Evolutionary algorithms
Torque
Robots

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Nanayakkara, T., Watanabe, K., Kiguchi, K., & Izumi, K. (2000). Controlling multi-link manipulators by fuzzy selection of dynamic models. In IECON Proceedings (Industrial Electronics Conference) (Vol. 1, pp. 638-643). [973224] IEEE Computer Society. https://doi.org/10.1109/IECON.2000.973224

Controlling multi-link manipulators by fuzzy selection of dynamic models. / Nanayakkara, T.; Watanabe, K.; Kiguchi, Kazuo; Izumi, K.

IECON Proceedings (Industrial Electronics Conference). Vol. 1 IEEE Computer Society, 2000. p. 638-643 973224.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nanayakkara, T, Watanabe, K, Kiguchi, K & Izumi, K 2000, Controlling multi-link manipulators by fuzzy selection of dynamic models. in IECON Proceedings (Industrial Electronics Conference). vol. 1, 973224, IEEE Computer Society, pp. 638-643. https://doi.org/10.1109/IECON.2000.973224
Nanayakkara T, Watanabe K, Kiguchi K, Izumi K. Controlling multi-link manipulators by fuzzy selection of dynamic models. In IECON Proceedings (Industrial Electronics Conference). Vol. 1. IEEE Computer Society. 2000. p. 638-643. 973224 https://doi.org/10.1109/IECON.2000.973224
Nanayakkara, T. ; Watanabe, K. ; Kiguchi, Kazuo ; Izumi, K. / Controlling multi-link manipulators by fuzzy selection of dynamic models. IECON Proceedings (Industrial Electronics Conference). Vol. 1 IEEE Computer Society, 2000. pp. 638-643
@inproceedings{c47cd195072444bea9cee74dc9178c1e,
title = "Controlling multi-link manipulators by fuzzy selection of dynamic models",
abstract = "A method for the identification of complex nonlinear dynamics of a multi-link robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs) in the absence of input torque information is proposed. The RKGNNs constructed using shape adaptive radial basis functions are trained by an evolutionary algorithm. Due to the fact that the main function network is divided into sub-networks to represent the dynamic properties of the manipulator, the neural networks have greater information, processing capacity and can be tested for properties such as positive definiteness of the inertia matrix. Dynamics of a three-link manipulator are identified using only their input-output position and velocity data, and promising control results are obtained to prove the effectiveness of the proposed method in capturing highly nonlinear dynamics of a multi-link manipulator.",
author = "T. Nanayakkara and K. Watanabe and Kazuo Kiguchi and K. Izumi",
year = "2000",
month = "1",
day = "1",
doi = "10.1109/IECON.2000.973224",
language = "English",
volume = "1",
pages = "638--643",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Controlling multi-link manipulators by fuzzy selection of dynamic models

AU - Nanayakkara, T.

AU - Watanabe, K.

AU - Kiguchi, Kazuo

AU - Izumi, K.

PY - 2000/1/1

Y1 - 2000/1/1

N2 - A method for the identification of complex nonlinear dynamics of a multi-link robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs) in the absence of input torque information is proposed. The RKGNNs constructed using shape adaptive radial basis functions are trained by an evolutionary algorithm. Due to the fact that the main function network is divided into sub-networks to represent the dynamic properties of the manipulator, the neural networks have greater information, processing capacity and can be tested for properties such as positive definiteness of the inertia matrix. Dynamics of a three-link manipulator are identified using only their input-output position and velocity data, and promising control results are obtained to prove the effectiveness of the proposed method in capturing highly nonlinear dynamics of a multi-link manipulator.

AB - A method for the identification of complex nonlinear dynamics of a multi-link robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs) in the absence of input torque information is proposed. The RKGNNs constructed using shape adaptive radial basis functions are trained by an evolutionary algorithm. Due to the fact that the main function network is divided into sub-networks to represent the dynamic properties of the manipulator, the neural networks have greater information, processing capacity and can be tested for properties such as positive definiteness of the inertia matrix. Dynamics of a three-link manipulator are identified using only their input-output position and velocity data, and promising control results are obtained to prove the effectiveness of the proposed method in capturing highly nonlinear dynamics of a multi-link manipulator.

UR - http://www.scopus.com/inward/record.url?scp=84969174952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969174952&partnerID=8YFLogxK

U2 - 10.1109/IECON.2000.973224

DO - 10.1109/IECON.2000.973224

M3 - Conference contribution

AN - SCOPUS:84969174952

VL - 1

SP - 638

EP - 643

BT - IECON Proceedings (Industrial Electronics Conference)

PB - IEEE Computer Society

ER -