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/ジオフェンシングarXiv:2110.09453

複雑な動的ジオフェンシングのための新手法:UAV向けアルファシェイプとボロノイ図の活用

A New Approach to Complex Dynamic Geofencing for Unmanned Aerial Vehicles

シェア:XThreadsFacebookLINEはてブBluesky

既存の幾何学的ジオフェンシングが複雑な都市環境で精度不足である問題に対し、アルファシェイプとボロノイ図に基づく新アルゴリズムを提案し、OpenStreetMapとAirSim、低コストUAVで実環境性能を実証した。

著者: Vihangi Vagal, Konstantinos Markantonakis, Carlton Shepherd

分類: cs.RO, cs.CG

原文アブストラクト

The anticipated widespread use of unmanned aerial vehicles (UAVs) raises significant safety and security concerns, including trespassing in restricted areas, colliding with other UAVs, and disrupting high-traffic airspaces. To mitigate these risks, geofences have been proposed as one line of defence, which limit UAVs from flying into the perimeters of other UAVs and restricted locations. In this paper, we address the concern that existing geometric geofencing algorithms lack accuracy during the calculation of complex geofences, particularly in dynamic urban environments. We propose a new algorithm based on alpha shapes and Voronoi diagrams, which we integrate into an on-drone framework using an open-source mapping database from OpenStreetMap. To demonstrate its efficacy, we present performance results using Microsoft's AirSim and a low-cost commercial UAV platform in a real-world urban environment.

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2Google DeepMind、ロボット向けAIを発表新製品・発表
  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. 4SoftBank主導、Agile Robotsが5億ドル調達 NVIDIAと日立も参加資金調達
  5. 5NTT、ロボットの行動前に荷崩れを予測研究・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