ロボット群れのための視覚ベース距離・方位・向き推定システムの設計
Design of a vision based range bearing and heading system for robot swarms
非対称パターンの受動ランドマークとカメラ画像解析により、群れ内ロボットの距離・方位・向きを低コストで推定する視覚システムを開発し、精度を検証した。
著者: Hamid Majidi Balanji, Emre Yilmaz, Omer Cakmak, Ali Emre Turgut
分類: cs.RO
原文アブストラクト
An essential problem of swarm robotics is how members of the swarm knows the positions of other robots. The main aim of this research is to develop a cost-effective and simple vision-based system to detect the range, bearing, and heading of the robots inside a swarm using a multi-purpose passive landmark. A small Zumo robot equipped with Raspberry Pi, PiCamera is utilized for the implementation of the algorithm, and different kinds of multipurpose passive landmarks with nonsymmetrical patterns, which give reliable information about the range, bearing and heading in a single unit, are designed. By comparing the recorded features obtained from image analysis of the landmark through systematical experimentation and the actual measurements, correlations are obtained, and algorithms converting those features into range, bearing and heading are designed. The reliability and accuracy of algorithms are tested and errors are found within an acceptable range.
