• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2020 Fiscal Year Final Research Report

Analyses of collective intelligence with non-AI approaches

Research Project

  • PDF
Project/Area Number 18K06410
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 45040:Ecology and environment-related
Research InstitutionUniversity of Tsukuba

Principal Investigator

TOQUENAGA Yukihiko  筑波大学, 生命環境系, 准教授 (90237074)

Project Period (FY) 2018-04-01 – 2021-03-31
Keywords人工知能 / 集合知 / minimalist boid / コロニー形成 / ネットワークカメラ
Outline of Final Research Achievements

This project proposed three algorithms with the non-AI collective approach. The first one is minimized Boid that only used signal strengths of agents and achieved equivalent performance (gathering, leader following, and reunion after splitting by obstacles) of the original Boid algorithm without using any spatial information. Minimized Boid was successfully implemented to Toio in the real world. The second algorithm used classical image analyses for counting the number of herons and egrets in long-term footages with network cameras. The final algorithm used only flight paths of foraging bumblebees for estimating their nest locations.

Free Research Field

理論生物学

Academic Significance and Societal Importance of the Research Achievements

Boidアルゴリズムは群行動の基本モデルとして長らく活用されて来たが、現実に群れている生物はxyz座標を知ることがないという前提が等閑にされてきた。minimized Boidは全ての個体が自分と他人の座標をまったく知らなくても、Boidのように振舞えることを示した点で、より単純な仕組みで群ロボットなどを実装出来る可能性を示した。また、深層学習などが全盛の中、解像度がそこそこの映像からでも対象生物の個体数推定が出来ることや、訪花個体の飛行経路だけから送粉社会性昆虫の巣の位置を推定出来る方法など、実用性の高いアルゴリズムが提出出来たことは意義深い。

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi