Neural network-based optimal adaptive tracking using genetic algorithms

Sisil Kumarawadu, Keigo Watanabe, Kiyotaka Izumi, Kazuo Kiguchi

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN-based adaptive control, are ingeniously combined using GAs to achieve high-performance output tracking. GA is used to make the maximum use of different performance characteristics of two self-adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.

Original languageEnglish
Pages (from-to)372-384
Number of pages13
JournalAsian Journal of Control
Volume8
Issue number4
Publication statusPublished - Dec 2006
Externally publishedYes

Fingerprint

Genetic algorithms
Neural networks
Switching functions
Variable structure control
Binoculars
Robotics
Robots
Computer simulation

Keywords

  • Gaussian-sum networks
  • Genetic algorithms
  • Neural networks
  • Robot control
  • Softmax function

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Control and Systems Engineering

Cite this

Neural network-based optimal adaptive tracking using genetic algorithms. / Kumarawadu, Sisil; Watanabe, Keigo; Izumi, Kiyotaka; Kiguchi, Kazuo.

In: Asian Journal of Control, Vol. 8, No. 4, 12.2006, p. 372-384.

Research output: Contribution to journalArticle

Kumarawadu, S, Watanabe, K, Izumi, K & Kiguchi, K 2006, 'Neural network-based optimal adaptive tracking using genetic algorithms', Asian Journal of Control, vol. 8, no. 4, pp. 372-384.
Kumarawadu, Sisil ; Watanabe, Keigo ; Izumi, Kiyotaka ; Kiguchi, Kazuo. / Neural network-based optimal adaptive tracking using genetic algorithms. In: Asian Journal of Control. 2006 ; Vol. 8, No. 4. pp. 372-384.
@article{c07e622a3eac4c818ff2e4a517e1cce3,
title = "Neural network-based optimal adaptive tracking using genetic algorithms",
abstract = "This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN-based adaptive control, are ingeniously combined using GAs to achieve high-performance output tracking. GA is used to make the maximum use of different performance characteristics of two self-adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.",
keywords = "Gaussian-sum networks, Genetic algorithms, Neural networks, Robot control, Softmax function",
author = "Sisil Kumarawadu and Keigo Watanabe and Kiyotaka Izumi and Kazuo Kiguchi",
year = "2006",
month = "12",
language = "English",
volume = "8",
pages = "372--384",
journal = "Asian Journal of Control",
issn = "1561-8625",
publisher = "National Taiwan University (IEEB)",
number = "4",

}

TY - JOUR

T1 - Neural network-based optimal adaptive tracking using genetic algorithms

AU - Kumarawadu, Sisil

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

AU - Kiguchi, Kazuo

PY - 2006/12

Y1 - 2006/12

N2 - This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN-based adaptive control, are ingeniously combined using GAs to achieve high-performance output tracking. GA is used to make the maximum use of different performance characteristics of two self-adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.

AB - This paper presents the use of neural networks (NNs) and genetic algorithms (GAs) to enhance the output tracking performance of partly known robotic systems. Two of the most potential approaches of adaptive control, i.e., the concept of variable structure control (VSC) and NN-based adaptive control, are ingeniously combined using GAs to achieve high-performance output tracking. GA is used to make the maximum use of different performance characteristics of two self-adaptive NN modules by finding the switching function which best combines them. The method will be valid for any rigid revolute robot system. Computer simulations on our active binocular head are included for illustration and verification.

KW - Gaussian-sum networks

KW - Genetic algorithms

KW - Neural networks

KW - Robot control

KW - Softmax function

UR - http://www.scopus.com/inward/record.url?scp=33847378881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847378881&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33847378881

VL - 8

SP - 372

EP - 384

JO - Asian Journal of Control

JF - Asian Journal of Control

SN - 1561-8625

IS - 4

ER -