Evolving multiple sensory-motor controllers based on cellular neural network

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

There has been extensive work to construct an optimal neural network for controlling a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. However, evolutionary approaches have a difficulty to obtain the controller that conducts complex and general behaviors. In order to overcome this short-coming, we propose a method of combining several evolved modules by a rule-based approach. The multi-modules integration method can make complex and general behaviors by combining several modules evolved or programmed to do simple behavior. Experimental results show the potential of the multi-modules integration method as a sophisticated technique to make the evolved neural network to do complex and general behaviors.

Original languageEnglish
Pages2218-2222
Number of pages5
Publication statusPublished - 2001 Dec 1
EventJoint 9th IFSA World Congress and 20th NAFIPS International Conference - Vancouver, BC, Canada
Duration: 2001 Jul 252001 Jul 28

Other

OtherJoint 9th IFSA World Congress and 20th NAFIPS International Conference
CountryCanada
CityVancouver, BC
Period01/7/2501/7/28

Fingerprint

Cellular neural networks
Cellular Networks
Neural Networks
Neural networks
Controller
Module
Controllers
Genetic programming
Mobile robots
Genetic algorithms
Genetic Programming
Mobile Robot
Genetic Algorithm
Experimental Results

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Cho, S. B. (2001). Evolving multiple sensory-motor controllers based on cellular neural network. 2218-2222. Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada.
Cho, Sung Bae. / Evolving multiple sensory-motor controllers based on cellular neural network. Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada.5 p.
@conference{d1f8c4f4515d4db38630996081136f73,
title = "Evolving multiple sensory-motor controllers based on cellular neural network",
abstract = "There has been extensive work to construct an optimal neural network for controlling a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. However, evolutionary approaches have a difficulty to obtain the controller that conducts complex and general behaviors. In order to overcome this short-coming, we propose a method of combining several evolved modules by a rule-based approach. The multi-modules integration method can make complex and general behaviors by combining several modules evolved or programmed to do simple behavior. Experimental results show the potential of the multi-modules integration method as a sophisticated technique to make the evolved neural network to do complex and general behaviors.",
author = "Cho, {Sung Bae}",
year = "2001",
month = "12",
day = "1",
language = "English",
pages = "2218--2222",
note = "Joint 9th IFSA World Congress and 20th NAFIPS International Conference ; Conference date: 25-07-2001 Through 28-07-2001",

}

Cho, SB 2001, 'Evolving multiple sensory-motor controllers based on cellular neural network', Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada, 01/7/25 - 01/7/28 pp. 2218-2222.

Evolving multiple sensory-motor controllers based on cellular neural network. / Cho, Sung Bae.

2001. 2218-2222 Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Evolving multiple sensory-motor controllers based on cellular neural network

AU - Cho, Sung Bae

PY - 2001/12/1

Y1 - 2001/12/1

N2 - There has been extensive work to construct an optimal neural network for controlling a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. However, evolutionary approaches have a difficulty to obtain the controller that conducts complex and general behaviors. In order to overcome this short-coming, we propose a method of combining several evolved modules by a rule-based approach. The multi-modules integration method can make complex and general behaviors by combining several modules evolved or programmed to do simple behavior. Experimental results show the potential of the multi-modules integration method as a sophisticated technique to make the evolved neural network to do complex and general behaviors.

AB - There has been extensive work to construct an optimal neural network for controlling a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. However, evolutionary approaches have a difficulty to obtain the controller that conducts complex and general behaviors. In order to overcome this short-coming, we propose a method of combining several evolved modules by a rule-based approach. The multi-modules integration method can make complex and general behaviors by combining several modules evolved or programmed to do simple behavior. Experimental results show the potential of the multi-modules integration method as a sophisticated technique to make the evolved neural network to do complex and general behaviors.

UR - http://www.scopus.com/inward/record.url?scp=0035792466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035792466&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0035792466

SP - 2218

EP - 2222

ER -

Cho SB. Evolving multiple sensory-motor controllers based on cellular neural network. 2001. Paper presented at Joint 9th IFSA World Congress and 20th NAFIPS International Conference, Vancouver, BC, Canada.