Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks

Hiroshi Nakamura; Akio Ishiguro; Yoshiki Uchilkawa

doi:10.1109/CEC.2000.870290

Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks

Hiroshi Nakamura, Akio Ishiguro, Yoshiki Uchilkawa

Research output: Contribution to conference › Paper › peer-review

9 Citations (Scopus)

Abstract

Recently, the evolutionary robotics (ER) approach has been attracting lots of concern in the fields of robotics and artificial life, since it can automatically synthesize controllers by taking the embodiment and the interaction dynamics between the robot and its environment. However, the ER approach still has serious problems that have to be solved. In this study, we particularly focus on one of the critical problems in the ER: plasticity vs. stability dilemma. In order to alleviate this problem, we investigate the effectiveness of the dynamically-rearranging neural networks by taking a peg-collecting task, which requires appropriate sequence of behavior to accomplish the task, as a practical example.

Original language	English
Pages	158-165
Number of pages	8
DOIs	https://doi.org/10.1109/CEC.2000.870290
Publication status	Published - 2000
Externally published	Yes
Event	2000 Congress on Evolutionary Computation, CEC 2000 - San Diego, CA, United States Duration: 2000 Jul 16 → 2000 Jul 19

Other

Other	2000 Congress on Evolutionary Computation, CEC 2000
Country/Territory	United States
City	San Diego, CA
Period	00/7/16 → 00/7/19

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science(all)
Engineering(all)

Access to Document

10.1109/CEC.2000.870290

Cite this

@conference{35213a5a997148549f0eb4f50ce204d3,

title = "Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks",

abstract = "Recently, the evolutionary robotics (ER) approach has been attracting lots of concern in the fields of robotics and artificial life, since it can automatically synthesize controllers by taking the embodiment and the interaction dynamics between the robot and its environment. However, the ER approach still has serious problems that have to be solved. In this study, we particularly focus on one of the critical problems in the ER: plasticity vs. stability dilemma. In order to alleviate this problem, we investigate the effectiveness of the dynamically-rearranging neural networks by taking a peg-collecting task, which requires appropriate sequence of behavior to accomplish the task, as a practical example.",

author = "Hiroshi Nakamura and Akio Ishiguro and Yoshiki Uchilkawa",

year = "2000",

doi = "10.1109/CEC.2000.870290",

language = "English",

pages = "158--165",

note = "2000 Congress on Evolutionary Computation, CEC 2000 ; Conference date: 16-07-2000 Through 19-07-2000",

}

TY - CONF

T1 - Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks

AU - Nakamura, Hiroshi

AU - Ishiguro, Akio

AU - Uchilkawa, Yoshiki

PY - 2000

Y1 - 2000

N2 - Recently, the evolutionary robotics (ER) approach has been attracting lots of concern in the fields of robotics and artificial life, since it can automatically synthesize controllers by taking the embodiment and the interaction dynamics between the robot and its environment. However, the ER approach still has serious problems that have to be solved. In this study, we particularly focus on one of the critical problems in the ER: plasticity vs. stability dilemma. In order to alleviate this problem, we investigate the effectiveness of the dynamically-rearranging neural networks by taking a peg-collecting task, which requires appropriate sequence of behavior to accomplish the task, as a practical example.

AB - Recently, the evolutionary robotics (ER) approach has been attracting lots of concern in the fields of robotics and artificial life, since it can automatically synthesize controllers by taking the embodiment and the interaction dynamics between the robot and its environment. However, the ER approach still has serious problems that have to be solved. In this study, we particularly focus on one of the critical problems in the ER: plasticity vs. stability dilemma. In order to alleviate this problem, we investigate the effectiveness of the dynamically-rearranging neural networks by taking a peg-collecting task, which requires appropriate sequence of behavior to accomplish the task, as a practical example.

UR - http://www.scopus.com/inward/record.url?scp=0033676660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033676660&partnerID=8YFLogxK

U2 - 10.1109/CEC.2000.870290

DO - 10.1109/CEC.2000.870290

M3 - Paper

AN - SCOPUS:0033676660

SP - 158

EP - 165

T2 - 2000 Congress on Evolutionary Computation, CEC 2000

Y2 - 16 July 2000 through 19 July 2000

ER -

Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this