A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties)

Katsuya Kanai; Keisuke Somiya; Xueshan Gao; Koki Kikuchi; Hiroshi Kobayashi

doi:10.1299/kikaic.72.109

A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties)

Katsuya Kanai, Keisuke Somiya, Xueshan Gao, Koki Kikuchi, Hiroshi Kobayashi

School of Mechatronical Engineering

Chiba Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

This paper deals with a concept that effective robotic function emerges from not only intelligence but also the balance of morphology and intelligence through physical interaction with a changing environment. In this paper, the morphology of a robot is represented by the arrangement of two visual sensors and the intelligence is described as a decision tree of sensor inputs and motor outputs. Both of morphology and intelligence are automatically generated and evolved by genetic programming (GP) for a task of maintaining a certain distance between the robot and an object. The result shows that emergence of symmetry properties for functionality depends on the velocity ratio between the robot and the object.

Original language	English
Pages (from-to)	109-116
Number of pages	8
Journal	Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
Volume	72
Issue number	1
DOIs	https://doi.org/10.1299/kikaic.72.109
Publication status	Published - Jan 2006

Keywords

Emergent Function
Evolutionary Robot
Genetic Programming
Intelligence
Morphology
Symmetry Properties

Access to Document

10.1299/kikaic.72.109

Cite this

@article{9500cd16ec1046cabd09e99b255377ee,

title = "A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties)",

abstract = "This paper deals with a concept that effective robotic function emerges from not only intelligence but also the balance of morphology and intelligence through physical interaction with a changing environment. In this paper, the morphology of a robot is represented by the arrangement of two visual sensors and the intelligence is described as a decision tree of sensor inputs and motor outputs. Both of morphology and intelligence are automatically generated and evolved by genetic programming (GP) for a task of maintaining a certain distance between the robot and an object. The result shows that emergence of symmetry properties for functionality depends on the velocity ratio between the robot and the object.",

keywords = "Emergent Function, Evolutionary Robot, Genetic Programming, Intelligence, Morphology, Symmetry Properties",

author = "Katsuya Kanai and Keisuke Somiya and Xueshan Gao and Koki Kikuchi and Hiroshi Kobayashi",

year = "2006",

month = jan,

doi = "10.1299/kikaic.72.109",

language = "English",

volume = "72",

pages = "109--116",

journal = "Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",

issn = "0387-5024",

publisher = "Japan Society of Mechanical Engineers",

number = "1",

}

A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties). / Kanai, Katsuya; Somiya, Keisuke; Gao, Xueshan et al.
In: Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, Vol. 72, No. 1, 01.2006, p. 109-116.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties)

AU - Kanai, Katsuya

AU - Somiya, Keisuke

AU - Gao, Xueshan

AU - Kikuchi, Koki

AU - Kobayashi, Hiroshi

PY - 2006/1

Y1 - 2006/1

N2 - This paper deals with a concept that effective robotic function emerges from not only intelligence but also the balance of morphology and intelligence through physical interaction with a changing environment. In this paper, the morphology of a robot is represented by the arrangement of two visual sensors and the intelligence is described as a decision tree of sensor inputs and motor outputs. Both of morphology and intelligence are automatically generated and evolved by genetic programming (GP) for a task of maintaining a certain distance between the robot and an object. The result shows that emergence of symmetry properties for functionality depends on the velocity ratio between the robot and the object.

AB - This paper deals with a concept that effective robotic function emerges from not only intelligence but also the balance of morphology and intelligence through physical interaction with a changing environment. In this paper, the morphology of a robot is represented by the arrangement of two visual sensors and the intelligence is described as a decision tree of sensor inputs and motor outputs. Both of morphology and intelligence are automatically generated and evolved by genetic programming (GP) for a task of maintaining a certain distance between the robot and an object. The result shows that emergence of symmetry properties for functionality depends on the velocity ratio between the robot and the object.

KW - Emergent Function

KW - Evolutionary Robot

KW - Genetic Programming

KW - Intelligence

KW - Morphology

KW - Symmetry Properties

UR - http://www.scopus.com/inward/record.url?scp=33645139006&partnerID=8YFLogxK

U2 - 10.1299/kikaic.72.109

DO - 10.1299/kikaic.72.109

M3 - Article

AN - SCOPUS:33645139006

SN - 0387-5024

VL - 72

SP - 109

EP - 116

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

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

IS - 1

ER -

A study on evolutionary robotic system with reconfigurable morphology and intelligence (mechanism of emergent symmetry properties)

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this