Evolved neural networks based on cellular automata for sensory-motor controller

Kyung Joong Kim, Sung-Bae Cho

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Constructing the controller of a mobile robot has several issues to be addressed: how to automate behavior generation procedure, how to insert available domain knowledge effectively, and how to hybrid these methods in an integrated manner. 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 design the controller that conducts complex behaviors. In order to overcome this shortcoming, we propose an incremental evolution method for neural networks based on cellular automata and a method of combining several evolved modules by a rule-based approach. The incremental evolution method evolves the neural network by starting with simple environment and gradually making it more complex. The multi-modules integration method can make complex behaviors by combining several modules evolved or programmed to do simple behaviors. Simulation results show the potential of the incremental evolution and multi-module integration methods as sophisticated techniques to make the evolved neural network to do complex behaviors. In this paper, we attempt to investigate the applicability of cellular automata-based neural networks and propose sophisticated techniques for the generation of high-level behaviors.

Original languageEnglish
Pages (from-to)2193-2207
Number of pages15
JournalNeurocomputing
Volume69
Issue number16-18
DOIs
Publication statusPublished - 2006 Oct 1

Fingerprint

Cellular automata
Neural networks
Controllers
Mobile robots
Genetic programming
Genetic algorithms

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

@article{4108331e347e41faaf0d8f49a57289a0,
title = "Evolved neural networks based on cellular automata for sensory-motor controller",
abstract = "Constructing the controller of a mobile robot has several issues to be addressed: how to automate behavior generation procedure, how to insert available domain knowledge effectively, and how to hybrid these methods in an integrated manner. 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 design the controller that conducts complex behaviors. In order to overcome this shortcoming, we propose an incremental evolution method for neural networks based on cellular automata and a method of combining several evolved modules by a rule-based approach. The incremental evolution method evolves the neural network by starting with simple environment and gradually making it more complex. The multi-modules integration method can make complex behaviors by combining several modules evolved or programmed to do simple behaviors. Simulation results show the potential of the incremental evolution and multi-module integration methods as sophisticated techniques to make the evolved neural network to do complex behaviors. In this paper, we attempt to investigate the applicability of cellular automata-based neural networks and propose sophisticated techniques for the generation of high-level behaviors.",
author = "Kim, {Kyung Joong} and Sung-Bae Cho",
year = "2006",
month = "10",
day = "1",
doi = "10.1016/j.neucom.2005.07.013",
language = "English",
volume = "69",
pages = "2193--2207",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "16-18",

}

Evolved neural networks based on cellular automata for sensory-motor controller. / Kim, Kyung Joong; Cho, Sung-Bae.

In: Neurocomputing, Vol. 69, No. 16-18, 01.10.2006, p. 2193-2207.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolved neural networks based on cellular automata for sensory-motor controller

AU - Kim, Kyung Joong

AU - Cho, Sung-Bae

PY - 2006/10/1

Y1 - 2006/10/1

N2 - Constructing the controller of a mobile robot has several issues to be addressed: how to automate behavior generation procedure, how to insert available domain knowledge effectively, and how to hybrid these methods in an integrated manner. 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 design the controller that conducts complex behaviors. In order to overcome this shortcoming, we propose an incremental evolution method for neural networks based on cellular automata and a method of combining several evolved modules by a rule-based approach. The incremental evolution method evolves the neural network by starting with simple environment and gradually making it more complex. The multi-modules integration method can make complex behaviors by combining several modules evolved or programmed to do simple behaviors. Simulation results show the potential of the incremental evolution and multi-module integration methods as sophisticated techniques to make the evolved neural network to do complex behaviors. In this paper, we attempt to investigate the applicability of cellular automata-based neural networks and propose sophisticated techniques for the generation of high-level behaviors.

AB - Constructing the controller of a mobile robot has several issues to be addressed: how to automate behavior generation procedure, how to insert available domain knowledge effectively, and how to hybrid these methods in an integrated manner. 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 design the controller that conducts complex behaviors. In order to overcome this shortcoming, we propose an incremental evolution method for neural networks based on cellular automata and a method of combining several evolved modules by a rule-based approach. The incremental evolution method evolves the neural network by starting with simple environment and gradually making it more complex. The multi-modules integration method can make complex behaviors by combining several modules evolved or programmed to do simple behaviors. Simulation results show the potential of the incremental evolution and multi-module integration methods as sophisticated techniques to make the evolved neural network to do complex behaviors. In this paper, we attempt to investigate the applicability of cellular automata-based neural networks and propose sophisticated techniques for the generation of high-level behaviors.

UR - http://www.scopus.com/inward/record.url?scp=33748432097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748432097&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2005.07.013

DO - 10.1016/j.neucom.2005.07.013

M3 - Article

VL - 69

SP - 2193

EP - 2207

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 16-18

ER -