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:1202.2261

フォーメーション構造を利用した固定目標探索のためのマルチロボット被覆

Multi-robot coverage to locate fixed targets using formation structures

シェア:XThreadsFacebookLINEはてブBluesky

未知環境で複数ロボットが横一列のフォーメーションを組み、障害物を避けつつ分割・再結合しながら全域を掃引して固定目標を探索するアルゴリズムを提案した。GPS搭載機や通信・記憶資源を最小限に抑える設計をシミュレーションで検証している。

著者: Jonathan Rogge, Dirk Aeyels

分類: cs.RO

原文アブストラクト

This paper develops an algorithm that guides a multi-robot system in an unknown environment in search of fixed targets. The area to be scanned contains an unknown number of convex obstacles of unknown size and shape. The algorithm covers the entire free space in a sweeping fashion and as such relies on the use of robot formations. The geometry of the robot group is a lateral line formation, which is allowed to split and rejoin when passing obstacles. It is our main goal to exploit this formation structure in order to reduce robot resources to a minimum. Each robot has a limited and finite amount of memory available. No information of the topography is recorded. Communication between two robots is only possible up to a maximum inter-robot distance, and if the line-of-sight between both robots is not obstructed. Broadcasting capabilities and indirect communication are not allowed. Supervisory control is prohibited. The number of robots equipped with GPS is kept as small as possible. Applications of the algorithm are mine field clearance, search-and-rescue missions, and intercept missions. Simulations are included and made available on the internet, demonstrating the flexibility of the algorithm.

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. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5GXO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

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