Robot manipulator contact force control application of fuzzy-neural network

Kazuo Kiguchi, Toshio Fukuda

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

A lot of researches have been done on fuzzy-neural control, the combination of neural networks control which has a learning ability from experiments and fuzzy control which has an ability of dealing with human knowledge, in order to make up for each other's weak points. In this paper, fuzzy-neural controller is introduced for robot manipulator contact force control to an unknown environment. A robot manipulator controller, which approaches, contacts and applies force to the environment, is designed using fuzzy logic in order to realize human like control and then modeled as a neural network to adjust membership functions and rules in order to achieve desired contact force control. Error between desired force and measured force and momentum of robot manipulator are used as input signals of the controller. Simulation has done using a 3DOF planar robot manipulator to confirm the effectiveness of the controller for the tasks of approach, contact and force control.

Original languageEnglish
Pages (from-to)875-880
Number of pages6
JournalUnknown Journal
Volume1
Publication statusPublished - 1995
Externally publishedYes

Fingerprint

Fuzzy neural networks
Force control
Manipulators
Robots
Controllers
fuzzy mathematics
momentum
learning
Neural networks
Membership functions
Fuzzy control
Fuzzy logic
simulation
Momentum
experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering

Cite this

Robot manipulator contact force control application of fuzzy-neural network. / Kiguchi, Kazuo; Fukuda, Toshio.

In: Unknown Journal, Vol. 1, 1995, p. 875-880.

Research output: Contribution to journalArticle

@article{c94dd080d519497f98b50184d276bde4,
title = "Robot manipulator contact force control application of fuzzy-neural network",
abstract = "A lot of researches have been done on fuzzy-neural control, the combination of neural networks control which has a learning ability from experiments and fuzzy control which has an ability of dealing with human knowledge, in order to make up for each other's weak points. In this paper, fuzzy-neural controller is introduced for robot manipulator contact force control to an unknown environment. A robot manipulator controller, which approaches, contacts and applies force to the environment, is designed using fuzzy logic in order to realize human like control and then modeled as a neural network to adjust membership functions and rules in order to achieve desired contact force control. Error between desired force and measured force and momentum of robot manipulator are used as input signals of the controller. Simulation has done using a 3DOF planar robot manipulator to confirm the effectiveness of the controller for the tasks of approach, contact and force control.",
author = "Kazuo Kiguchi and Toshio Fukuda",
year = "1995",
language = "English",
volume = "1",
pages = "875--880",
journal = "Quaternary International",
issn = "1040-6182",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Robot manipulator contact force control application of fuzzy-neural network

AU - Kiguchi, Kazuo

AU - Fukuda, Toshio

PY - 1995

Y1 - 1995

N2 - A lot of researches have been done on fuzzy-neural control, the combination of neural networks control which has a learning ability from experiments and fuzzy control which has an ability of dealing with human knowledge, in order to make up for each other's weak points. In this paper, fuzzy-neural controller is introduced for robot manipulator contact force control to an unknown environment. A robot manipulator controller, which approaches, contacts and applies force to the environment, is designed using fuzzy logic in order to realize human like control and then modeled as a neural network to adjust membership functions and rules in order to achieve desired contact force control. Error between desired force and measured force and momentum of robot manipulator are used as input signals of the controller. Simulation has done using a 3DOF planar robot manipulator to confirm the effectiveness of the controller for the tasks of approach, contact and force control.

AB - A lot of researches have been done on fuzzy-neural control, the combination of neural networks control which has a learning ability from experiments and fuzzy control which has an ability of dealing with human knowledge, in order to make up for each other's weak points. In this paper, fuzzy-neural controller is introduced for robot manipulator contact force control to an unknown environment. A robot manipulator controller, which approaches, contacts and applies force to the environment, is designed using fuzzy logic in order to realize human like control and then modeled as a neural network to adjust membership functions and rules in order to achieve desired contact force control. Error between desired force and measured force and momentum of robot manipulator are used as input signals of the controller. Simulation has done using a 3DOF planar robot manipulator to confirm the effectiveness of the controller for the tasks of approach, contact and force control.

UR - http://www.scopus.com/inward/record.url?scp=0029182138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029182138&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029182138

VL - 1

SP - 875

EP - 880

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

ER -