2023 Fiscal Year Final Research Report

Just the right intelligence: Low Computational Cost Action Selection Algorithm of a Robotic Swarm based on Nematodes

Research Project

PDF

Project/Area Number	21K18697
Research Category	Grant-in-Aid for Challenging Research (Exploratory)
Allocation Type	Multi-year Fund
Review Section	Medium-sized Section 20:Mechanical dynamics, robotics, and related fields
Research Institution	Tokyo Institute of Technology
Principal Investigator	Kurabayashi Daisuke 東京工業大学, 工学院, 教授 (00334508)
Co-Investigator(Kenkyū-buntansha)	服部佑哉呉工業高等専門学校, 電気情報工学分野, 准教授 (30709803)
Project Period (FY)	2021-07-09 – 2024-03-31
Keywords	生物規範システム / 自律ロボット / 線虫
Outline of Final Research Achievements	The objective of this study is to construct an algorithm for a robotic swarm that enables adaptive and efficient cooperative behavior. By focusing on the nematode C. elegans, we observed chemotactic behaviors and identified their dependency on the local density of animals. Despite having only 302 neural cells, C. elegans can modify their behaviors adaptively. We believe C. elegans serves as a relevant model for adaptive robotic swarms. Based on our observations, we formulated a probabilistic behavior selection model depending on the local density and verified it through simulations using benchmark potential functions. As a result, we found that the proposed algorithm improved search efficiency, relying solely on local information. We concluded that this study contributes to the development of a control system for autonomous robotic swarms that enables efficient behavior selection, by which communication or computation costs are reduced.
Free Research Field	制御工学
Academic Significance and Societal Importance of the Research Achievements	自律移動体が近傍状況に基づく自主的動作選択で協調的行動を可能にすることは，社会の隅々まで知能機械が用いられる近未来において，省通信資源・省計算エネルギーの面で重要である．本研究では，神経細胞を302個しか有しないが学習を含む適応的行動が可能な線虫C. elegansに着目し，これに基づいてロボット群の協調的かつ効率的な行動アルゴリズムを構築した．結果として，局所的な情報にのみ基づく行動でも協調行動の効率を向上させることができた．このことは，限られた計算・通信資源で行動様式を適応的に変容させる自律型ロボットシステムの構成方法解明に貢献するものだと考える．