日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

飛行自律/探査arXiv:2103.05798

未知領域探査のための堅牢な衝突回避型軽量飛行自律システム

Robust Collision-free Lightweight Aerial Autonomy for Unknown Area Exploration

シェア:XThreadsFacebookLINEはてブBluesky

LiDARとESDFベースのグリッド探索で局所終点を選び、小型ドローンが未知の坑道内を衝突せず自律探査する手法を提案し、実鉱山やDARPA地下トンネル競技で実証した。

著者: Sunggoo Jung, Hanseob Lee, David Hyunchul Shim, Ali-akbar Agha-mohammadi

分類: cs.RO

原文アブストラクト

Collision-free path planning is an essential requirement for autonomous exploration in unknown environments, especially when operating in confined spaces or near obstacles. This study presents an autonomous exploration technique using a small drone. A local end-point selection method is designed using LiDAR range measurement and then generates the path from the current position to the selected end-point. The generated path shows the consistent collision-free path in real-time by adopting the Euclidean signed distance field-based grid-search method. The simulation results consistently showed the safety, and reliability of the proposed path-planning method. Real-world experiments are conducted in three different mines, demonstrating successful autonomous exploration flight in environments with various structural conditions. The results showed the high capability of the proposed flight autonomy framework for lightweight aerial-robot systems. Besides, our drone performs an autonomous mission during our entry at the Tunnel Circuit competition (Phase 1) of the DARPA Subterranean Challenge.

  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. 3GXO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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI