Swarm robot control by evolving artificial neural networks with small world topologies

• Ohkura Kazuhiro

  Hiroshima University

• Matsuda Tomoya

  Hiroshima University

• Yasuda Toshiyuki

  Hiroshima University

• Matsumura Yoshiyuki

  Shinshu University

抄録

Swarm robot control is not an easy task for a human programmer, because the robot group behavior is emerged as a result of many and asynchronous unexpected local interactions between autonomous robots. In this paper, we approach to this problem of designing robot controllers by using evolving artificial neural networks (EANNs). From our preliminary computer simulations, it has been found that the topology of the hidden layer plays an important role of the evolvability of an EANN. Therefore, we conduct a series of computer simulations to show that an EANN having the small world properties in the hidden layer performs better than EANNs with the hidden layer of regular topologies or other conventional feed forward neural network controllers from the viewpoint of the generalization capability.

収録刊行物

• SCIS & ISIS

  SCIS & ISIS 2008 (0), 1888-1893, 2008

  日本知能情報ファジィ学会

キーワード

• Swarm Intelligence
• evolving artificial neural networks
• small world

詳細情報

• CRID: 1390282680566561536
• NII論文ID: 130004672856
• DOI: 10.14864/softscis.2008.0.1888.0
• 本文言語コード: en
• データソース種別:
  • JaLC
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可