Flexible structural learning control of a robotic manipulator using artificial neural networks

Mohammad Teshnehlab, Keigo Watanabe

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A method for learning control of robotic manipulators based on self-tuning of computed torque gains using artificial neural networks (ANN) has been developed. Two issues were given emphasis: the first concerns the sigmoid unit function used to achieve flexibility in ANN structure; and the second is a learning algorithm for the sigmoid function that is similar to the backpropagation algorithms. A simulation is demonstrated to evaluate the newly proposed structure by applying the method to construct an adaptive computed torque controller for a two-link manipulator.

Original languageEnglish
Pages (from-to)510-521
Number of pages12
JournalJSME International Journal, Series C: Dynamics, Control, Robotics, Design and Menufacturing
Volume38
Issue number3
Publication statusPublished - Sep 1995
Externally publishedYes

Fingerprint

Manipulators
Robotics
Torque
Neural networks
Backpropagation algorithms
Learning algorithms
Tuning
Controllers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

@article{27f7f25e8a524f598fb71542ce598bd5,
title = "Flexible structural learning control of a robotic manipulator using artificial neural networks",
abstract = "A method for learning control of robotic manipulators based on self-tuning of computed torque gains using artificial neural networks (ANN) has been developed. Two issues were given emphasis: the first concerns the sigmoid unit function used to achieve flexibility in ANN structure; and the second is a learning algorithm for the sigmoid function that is similar to the backpropagation algorithms. A simulation is demonstrated to evaluate the newly proposed structure by applying the method to construct an adaptive computed torque controller for a two-link manipulator.",
author = "Mohammad Teshnehlab and Keigo Watanabe",
year = "1995",
month = "9",
language = "English",
volume = "38",
pages = "510--521",
journal = "JSME International Journal, Series 3: Vibration, Control Engineering, Engineering for Industry",
issn = "0914-8825",
publisher = "Japan Society of Mechanical Engineers",
number = "3",

}

TY - JOUR

T1 - Flexible structural learning control of a robotic manipulator using artificial neural networks

AU - Teshnehlab, Mohammad

AU - Watanabe, Keigo

PY - 1995/9

Y1 - 1995/9

N2 - A method for learning control of robotic manipulators based on self-tuning of computed torque gains using artificial neural networks (ANN) has been developed. Two issues were given emphasis: the first concerns the sigmoid unit function used to achieve flexibility in ANN structure; and the second is a learning algorithm for the sigmoid function that is similar to the backpropagation algorithms. A simulation is demonstrated to evaluate the newly proposed structure by applying the method to construct an adaptive computed torque controller for a two-link manipulator.

AB - A method for learning control of robotic manipulators based on self-tuning of computed torque gains using artificial neural networks (ANN) has been developed. Two issues were given emphasis: the first concerns the sigmoid unit function used to achieve flexibility in ANN structure; and the second is a learning algorithm for the sigmoid function that is similar to the backpropagation algorithms. A simulation is demonstrated to evaluate the newly proposed structure by applying the method to construct an adaptive computed torque controller for a two-link manipulator.

UR - http://www.scopus.com/inward/record.url?scp=0029373550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029373550&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029373550

VL - 38

SP - 510

EP - 521

JO - JSME International Journal, Series 3: Vibration, Control Engineering, Engineering for Industry

JF - JSME International Journal, Series 3: Vibration, Control Engineering, Engineering for Industry

SN - 0914-8825

IS - 3

ER -