Intelligent control of a 7-DOF manipulator based on model primitives

D. P.Thrishantha Nanayakkara, Keigo Watanabe, Kazuo Kiguchi, Reza Shadmehr

Research output: Contribution to conferencePaper

Abstract

This paper presents a method to control industrial redundant manipulators based on a method similar to the mechanism ascribed to the human motor system that adaptively combines motor primitives to control human body motions. The idea is to identify a set of local model primitives based on Runge-Kutta-Gill neural networks (RKGNNs) and control the manipulator based on an adaptive selection and fusion method. The adaptive selection is carried out using a resonance signal that recalls only the most relevant memory primitives given a situation, and adaptive fusion is carried out by a method based on fuzzy memberships. This method imitates few recent findings on how human motor skills are developed by adaptive combination of motor primitives. Experiments on an industrial manipulator with seven degrees of freedom shows that the proposed method is a potentially viable approach to model based control of redundant robot manipulators.

Original languageEnglish
Pages538-543
Number of pages6
Publication statusPublished - Dec 1 2002
Externally publishedYes
EventProceedings of the 2002 IEEE International Symposium on Intelligent Control - Vancouver, Canada
Duration: Oct 27 2002Oct 30 2002

Other

OtherProceedings of the 2002 IEEE International Symposium on Intelligent Control
CountryCanada
CityVancouver
Period10/27/0210/30/02

Fingerprint

Intelligent Control
Intelligent control
Manipulator
Manipulators
Industrial manipulators
Redundant Manipulator
Fusion reactions
Redundant manipulators
Fusion
Model
Fuzzy Membership
Neural Control
Model-based Control
Robot Manipulator
Robots
Runge-Kutta
Neural networks
Data storage equipment
Degree of freedom
Neural Networks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modelling and Simulation
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Nanayakkara, D. P. T., Watanabe, K., Kiguchi, K., & Shadmehr, R. (2002). Intelligent control of a 7-DOF manipulator based on model primitives. 538-543. Paper presented at Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, Canada.

Intelligent control of a 7-DOF manipulator based on model primitives. / Nanayakkara, D. P.Thrishantha; Watanabe, Keigo; Kiguchi, Kazuo; Shadmehr, Reza.

2002. 538-543 Paper presented at Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, Canada.

Research output: Contribution to conferencePaper

Nanayakkara, DPT, Watanabe, K, Kiguchi, K & Shadmehr, R 2002, 'Intelligent control of a 7-DOF manipulator based on model primitives', Paper presented at Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, Canada, 10/27/02 - 10/30/02 pp. 538-543.
Nanayakkara DPT, Watanabe K, Kiguchi K, Shadmehr R. Intelligent control of a 7-DOF manipulator based on model primitives. 2002. Paper presented at Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, Canada.
Nanayakkara, D. P.Thrishantha ; Watanabe, Keigo ; Kiguchi, Kazuo ; Shadmehr, Reza. / Intelligent control of a 7-DOF manipulator based on model primitives. Paper presented at Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, Canada.6 p.
@conference{c89b05f2392a446f85b963408a7bb485,
title = "Intelligent control of a 7-DOF manipulator based on model primitives",
abstract = "This paper presents a method to control industrial redundant manipulators based on a method similar to the mechanism ascribed to the human motor system that adaptively combines motor primitives to control human body motions. The idea is to identify a set of local model primitives based on Runge-Kutta-Gill neural networks (RKGNNs) and control the manipulator based on an adaptive selection and fusion method. The adaptive selection is carried out using a resonance signal that recalls only the most relevant memory primitives given a situation, and adaptive fusion is carried out by a method based on fuzzy memberships. This method imitates few recent findings on how human motor skills are developed by adaptive combination of motor primitives. Experiments on an industrial manipulator with seven degrees of freedom shows that the proposed method is a potentially viable approach to model based control of redundant robot manipulators.",
author = "Nanayakkara, {D. P.Thrishantha} and Keigo Watanabe and Kazuo Kiguchi and Reza Shadmehr",
year = "2002",
month = "12",
day = "1",
language = "English",
pages = "538--543",
note = "Proceedings of the 2002 IEEE International Symposium on Intelligent Control ; Conference date: 27-10-2002 Through 30-10-2002",

}

TY - CONF

T1 - Intelligent control of a 7-DOF manipulator based on model primitives

AU - Nanayakkara, D. P.Thrishantha

AU - Watanabe, Keigo

AU - Kiguchi, Kazuo

AU - Shadmehr, Reza

PY - 2002/12/1

Y1 - 2002/12/1

N2 - This paper presents a method to control industrial redundant manipulators based on a method similar to the mechanism ascribed to the human motor system that adaptively combines motor primitives to control human body motions. The idea is to identify a set of local model primitives based on Runge-Kutta-Gill neural networks (RKGNNs) and control the manipulator based on an adaptive selection and fusion method. The adaptive selection is carried out using a resonance signal that recalls only the most relevant memory primitives given a situation, and adaptive fusion is carried out by a method based on fuzzy memberships. This method imitates few recent findings on how human motor skills are developed by adaptive combination of motor primitives. Experiments on an industrial manipulator with seven degrees of freedom shows that the proposed method is a potentially viable approach to model based control of redundant robot manipulators.

AB - This paper presents a method to control industrial redundant manipulators based on a method similar to the mechanism ascribed to the human motor system that adaptively combines motor primitives to control human body motions. The idea is to identify a set of local model primitives based on Runge-Kutta-Gill neural networks (RKGNNs) and control the manipulator based on an adaptive selection and fusion method. The adaptive selection is carried out using a resonance signal that recalls only the most relevant memory primitives given a situation, and adaptive fusion is carried out by a method based on fuzzy memberships. This method imitates few recent findings on how human motor skills are developed by adaptive combination of motor primitives. Experiments on an industrial manipulator with seven degrees of freedom shows that the proposed method is a potentially viable approach to model based control of redundant robot manipulators.

UR - http://www.scopus.com/inward/record.url?scp=0036907063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036907063&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0036907063

SP - 538

EP - 543

ER -