日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

群制御arXiv:1611.05092

多角形環境における複数ガードによる侵入者追跡のための分割戦略とタスク割当

Partitioning Strategies and Task Allocation for Target-tracking with Multiple Guards in Polygonal Environments

シェア:XThreadsFacebookLINEはてブBluesky

全方向カメラを搭載した複数の移動ガードで多角形環境内の侵入者を常時追跡するため、環境を分割して各ガードに割り当てるアルゴリズムを提案し、必要なガード数と速度の上限を導出した。

著者: Hamid Emadi, Tianshuang Gao, Sourabh Bhattacharya

分類: cs.RO

原文アブストラクト

This paper presents an algorithm to deploy a team of {\it free} guards equipped with omni-directional cameras for tracking a bounded speed intruder inside a simply-connected polygonal environment. The proposed algorithm partitions the environment into smaller polygons, and assigns a guard to each partition so that the intruder is visible to at least one guard at all times. Based on the concept of {\it dynamic zones} introduced in this paper, we propose event-triggered strategies for the guards to track the intruder. We show that the number of guards deployed by the algorithm for tracking is strictly less than $\lfloor {\frac{n}{3}} \rfloor$ which is sufficient and sometimes necessary for coverage. We derive an upper bound on the speed of the mobile guard required for successful tracking which depends on the intruder's speed, the road map of the mobile guards, and geometry of the environment. Finally, we extend the aforementioned analysis to orthogonal polygons, and show that the upper bound on the number of guards deployed for tracking is strictly less than $\lfloor {\frac{n}{4}} \rfloor$ which is sufficient and sometimes necessary for the coverage problem.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI