日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

UAV探索arXiv:2012.14649

ピーコック探索:制御効率の良い軌道を用いたUAVの軽量探索

Peacock Exploration: A Lightweight Exploration for UAV using Control-Efficient Trajectory

シェア:XThreadsFacebookLINEはてブBluesky

クジャクの尾のような事前計算済みミニマムスナップ軌道とOctoMapを使い、RGB-Dカメラ搭載UAVが未知の3D環境をO(logN)計算量で探索する軽量手法を提案し、迷路環境で最先端手法と比較した。

著者: EungChang Mason Lee, Duckyu Choi, Hyun Myung

分類: cs.RO

原文アブストラクト

Unmanned Aerial Vehicles have received much attention in recent years due to its wide range of applications, such as exploration of an unknown environment to acquire a 3D map without prior knowledge of it. Existing exploration methods have been largely challenged by computationally heavy probabilistic path planning. Similarly, kinodynamic constraints or proper sensors considering the payload for UAVs were not considered. In this paper, to solve those issues and to consider the limited payload and computational resource of UAVs, we propose "Peacock Exploration": A lightweight exploration method for UAVs using precomputed minimum snap trajectories which look like a peacock's tail. Using the widely known, control efficient minimum snap trajectories and OctoMap, the UAV equipped with a RGB-D camera can explore unknown 3D environments without any prior knowledge or human-guidance with only O(logN) computational complexity. It also adopts the receding horizon approach and simple, heuristic scoring criteria. The proposed algorithm's performance is demonstrated by exploring a challenging 3D maze environment and compared with a state-of-the-art 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. 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. 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

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