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

Hiroshi Nakamura, Akio Ishiguro, Yoshiki Uchilkawa

Research output: Contribution to conferencePaperpeer-review

6 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 languageEnglish
Pages158-165
Number of pages8
DOIs
Publication statusPublished - 2000 Jan 1
Externally publishedYes
Event2000 Congress on Evolutionary Computation, CEC 2000 - San Diego, CA, United States
Duration: 2000 Jul 162000 Jul 19

Other

Other2000 Congress on Evolutionary Computation, CEC 2000
CountryUnited States
CitySan Diego, CA
Period00/7/1600/7/19

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Evolutionary construction of behavior arbitration mechanisms based on dynamically-rearranging neural networks'. Together they form a unique fingerprint.

Cite this