Evolutionary design of behavior for mobile robot using multi-objective genetic programming

Manabu Hashimoto, Yasutaka Tsuji, Eiji Kondo

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper describes an evolutionary approach to design a mobile robot behavior using multi-objective genetic programming. Genetic programming (GP) has a tendency to create programs with unnecessarily large size. This problem in GP is called bloat and increases computational efforts. We introduce a multi-objective optimization technique to GP as a mean of controlling bloat, where a program size is treated as an independent objective besides another objective (fitness) and the modified domiance relation is used in evolutionary Pareto optimization. The proposed multi-objective GP can not only reduce bloat, but also avoid the problem of over-learning often found when applying GP to a behavior design of robots. The effectiveness of the proposed GP is demonstrated through the simulation and the real-world experiment using Khepera robot.

Original languageEnglish
Pages (from-to)3236-3243
Number of pages8
JournalNihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
Volume70
Issue number11
Publication statusPublished - Nov 2004

Fingerprint

Genetic programming
Mobile robots
Robots
Multiobjective optimization

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering

Cite this

@article{149d060bb3cf4fe585c88feccee6c825,
title = "Evolutionary design of behavior for mobile robot using multi-objective genetic programming",
abstract = "This paper describes an evolutionary approach to design a mobile robot behavior using multi-objective genetic programming. Genetic programming (GP) has a tendency to create programs with unnecessarily large size. This problem in GP is called bloat and increases computational efforts. We introduce a multi-objective optimization technique to GP as a mean of controlling bloat, where a program size is treated as an independent objective besides another objective (fitness) and the modified domiance relation is used in evolutionary Pareto optimization. The proposed multi-objective GP can not only reduce bloat, but also avoid the problem of over-learning often found when applying GP to a behavior design of robots. The effectiveness of the proposed GP is demonstrated through the simulation and the real-world experiment using Khepera robot.",
author = "Manabu Hashimoto and Yasutaka Tsuji and Eiji Kondo",
year = "2004",
month = "11",
language = "English",
volume = "70",
pages = "3236--3243",
journal = "Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",
issn = "0387-5024",
publisher = "The Japan Society of Mechanical Engineers",
number = "11",

}

TY - JOUR

T1 - Evolutionary design of behavior for mobile robot using multi-objective genetic programming

AU - Hashimoto, Manabu

AU - Tsuji, Yasutaka

AU - Kondo, Eiji

PY - 2004/11

Y1 - 2004/11

N2 - This paper describes an evolutionary approach to design a mobile robot behavior using multi-objective genetic programming. Genetic programming (GP) has a tendency to create programs with unnecessarily large size. This problem in GP is called bloat and increases computational efforts. We introduce a multi-objective optimization technique to GP as a mean of controlling bloat, where a program size is treated as an independent objective besides another objective (fitness) and the modified domiance relation is used in evolutionary Pareto optimization. The proposed multi-objective GP can not only reduce bloat, but also avoid the problem of over-learning often found when applying GP to a behavior design of robots. The effectiveness of the proposed GP is demonstrated through the simulation and the real-world experiment using Khepera robot.

AB - This paper describes an evolutionary approach to design a mobile robot behavior using multi-objective genetic programming. Genetic programming (GP) has a tendency to create programs with unnecessarily large size. This problem in GP is called bloat and increases computational efforts. We introduce a multi-objective optimization technique to GP as a mean of controlling bloat, where a program size is treated as an independent objective besides another objective (fitness) and the modified domiance relation is used in evolutionary Pareto optimization. The proposed multi-objective GP can not only reduce bloat, but also avoid the problem of over-learning often found when applying GP to a behavior design of robots. The effectiveness of the proposed GP is demonstrated through the simulation and the real-world experiment using Khepera robot.

UR - http://www.scopus.com/inward/record.url?scp=12444262264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12444262264&partnerID=8YFLogxK

M3 - Article

VL - 70

SP - 3236

EP - 3243

JO - Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

JF - Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

SN - 0387-5024

IS - 11

ER -