Dynamic selection of evolved neural controllers for higher behaviors of mobile robot

Kyung Joong Kim, Sung-Bae Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

There has been extensive research of developing the controller for a mobile robot Especially, several researchers have constructed the mobile robot controller that can avoid obstacles, evade predators, or catch moving prey by evolutionary algorithms such as genetic algorithm and genetic programming. In this line of research, we have also developed a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, the direct evolution has a difficulty that the controller cannot generalize well to new environments. We attempt to solve it by incremental evolution, which starts with simpler environments and gradually develops the controller with more general and complex environments. We combine several behaviors evolved or programmed by dynamic selection mechanism for higher behaviors. In this paper, we evaluate the performance of robot using Khepera simulator. Simulation results show the possibility of easily developing higher behaviors by integrating CAM-Brain behavior modules.

Original languageEnglish
Title of host publicationProceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation
Subtitle of host publicationIntegrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001
EditorsHong Zhang, Peter Xiaoping Liu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages467-472
Number of pages6
ISBN (Electronic)0780372034
DOIs
Publication statusPublished - 2001 Jan 1
EventIEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2001 - Banff, Canada
Duration: 2001 Jul 292001 Aug 1

Publication series

NameProceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA
Volume2001-January

Other

OtherIEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2001
CountryCanada
CityBanff
Period01/7/2901/8/1

Fingerprint

Mobile Robot
Mobile robots
Controller
Controllers
Computer aided manufacturing
Brain
Genetic programming
Cellular automata
Predator
Prey
Genetic Programming
Evolutionary algorithms
Cellular Automata
Evolutionary Algorithms
Simulator
Simulators
Robot
Genetic algorithms
Genetic Algorithm
Robots

All Science Journal Classification (ASJC) codes

  • Computational Mathematics

Cite this

Kim, K. J., & Cho, S-B. (2001). Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. In H. Zhang, & P. X. Liu (Eds.), Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation: Integrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001 (pp. 467-472). [1013246] (Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA; Vol. 2001-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIRA.2001.1013246
Kim, Kyung Joong ; Cho, Sung-Bae. / Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation: Integrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001. editor / Hong Zhang ; Peter Xiaoping Liu. Institute of Electrical and Electronics Engineers Inc., 2001. pp. 467-472 (Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA).
@inproceedings{bed4bb7e37314ab28a0d0b6bd662f476,
title = "Dynamic selection of evolved neural controllers for higher behaviors of mobile robot",
abstract = "There has been extensive research of developing the controller for a mobile robot Especially, several researchers have constructed the mobile robot controller that can avoid obstacles, evade predators, or catch moving prey by evolutionary algorithms such as genetic algorithm and genetic programming. In this line of research, we have also developed a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, the direct evolution has a difficulty that the controller cannot generalize well to new environments. We attempt to solve it by incremental evolution, which starts with simpler environments and gradually develops the controller with more general and complex environments. We combine several behaviors evolved or programmed by dynamic selection mechanism for higher behaviors. In this paper, we evaluate the performance of robot using Khepera simulator. Simulation results show the possibility of easily developing higher behaviors by integrating CAM-Brain behavior modules.",
author = "Kim, {Kyung Joong} and Sung-Bae Cho",
year = "2001",
month = "1",
day = "1",
doi = "10.1109/CIRA.2001.1013246",
language = "English",
series = "Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "467--472",
editor = "Hong Zhang and Liu, {Peter Xiaoping}",
booktitle = "Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation",
address = "United States",

}

Kim, KJ & Cho, S-B 2001, Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. in H Zhang & PX Liu (eds), Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation: Integrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001., 1013246, Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA, vol. 2001-January, Institute of Electrical and Electronics Engineers Inc., pp. 467-472, IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2001, Banff, Canada, 01/7/29. https://doi.org/10.1109/CIRA.2001.1013246

Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. / Kim, Kyung Joong; Cho, Sung-Bae.

Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation: Integrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001. ed. / Hong Zhang; Peter Xiaoping Liu. Institute of Electrical and Electronics Engineers Inc., 2001. p. 467-472 1013246 (Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA; Vol. 2001-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Dynamic selection of evolved neural controllers for higher behaviors of mobile robot

AU - Kim, Kyung Joong

AU - Cho, Sung-Bae

PY - 2001/1/1

Y1 - 2001/1/1

N2 - There has been extensive research of developing the controller for a mobile robot Especially, several researchers have constructed the mobile robot controller that can avoid obstacles, evade predators, or catch moving prey by evolutionary algorithms such as genetic algorithm and genetic programming. In this line of research, we have also developed a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, the direct evolution has a difficulty that the controller cannot generalize well to new environments. We attempt to solve it by incremental evolution, which starts with simpler environments and gradually develops the controller with more general and complex environments. We combine several behaviors evolved or programmed by dynamic selection mechanism for higher behaviors. In this paper, we evaluate the performance of robot using Khepera simulator. Simulation results show the possibility of easily developing higher behaviors by integrating CAM-Brain behavior modules.

AB - There has been extensive research of developing the controller for a mobile robot Especially, several researchers have constructed the mobile robot controller that can avoid obstacles, evade predators, or catch moving prey by evolutionary algorithms such as genetic algorithm and genetic programming. In this line of research, we have also developed a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, the direct evolution has a difficulty that the controller cannot generalize well to new environments. We attempt to solve it by incremental evolution, which starts with simpler environments and gradually develops the controller with more general and complex environments. We combine several behaviors evolved or programmed by dynamic selection mechanism for higher behaviors. In this paper, we evaluate the performance of robot using Khepera simulator. Simulation results show the possibility of easily developing higher behaviors by integrating CAM-Brain behavior modules.

UR - http://www.scopus.com/inward/record.url?scp=84867114325&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867114325&partnerID=8YFLogxK

U2 - 10.1109/CIRA.2001.1013246

DO - 10.1109/CIRA.2001.1013246

M3 - Conference contribution

T3 - Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA

SP - 467

EP - 472

BT - Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation

A2 - Zhang, Hong

A2 - Liu, Peter Xiaoping

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim KJ, Cho S-B. Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. In Zhang H, Liu PX, editors, Proceedings - 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation: Integrating Intelligent Machines with Humans for a Better Tomorrow, CIRA 2001. Institute of Electrical and Electronics Engineers Inc. 2001. p. 467-472. 1013246. (Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA). https://doi.org/10.1109/CIRA.2001.1013246