Evolutionary construction of swarm intelligence in a robotic swarm

2015 Fiscal Year Final Research Report

• Project/Area Number: 25330307
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent robotics
• Research Institution: Hiroshima University
• Principal Investigator: OHKURA KAZUHIRO 広島大学, 工学(系)研究科(研究院), 教授 (40252788)
• Co-Investigator(Kenkyū-buntansha): YASUDA TOSHIYUKI 広島大学, 大学院工学研究院, 助教 (60435451)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: ロボティックスワーム / 群れ行動 / 進化型人工神経回路網 / 集合知

Outline of Final Research Achievements

In order to design the robot controller in a robotic swarm by an evolutionary artificial neural network, two types of computational resources are provided for conducting simulated experiments. In this project, we have done the first step toward the areas of evaluation and analysis of swarm intelligence in evolutionary robotic swarms. We have also done the physical robotic swarm experiments with faster processing to develop expected swarm behavior. In addition, the results of the artificial evolution of robotic swarm have been transferred to the physical robotic swarm to develop the similar swarm behavior. We believe that this project contributed to find the basics of the methodology of swarm intelligence by artificial evolution.

Free Research Field

自律システム学