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:2504.07623

プラトゥーニングのための共同走行経路最適化フレームワーク

Joint Travel Route Optimization Framework for Platooning

シェア:XThreadsFacebookLINEはてブBluesky

車両群(プラトゥーン)の集中管理による経路計画最適化を提案し、燃料消費・疲労・時間のコスト指標で評価した結果、個別経路計画より平均14%改善した。

著者: Akif Adas, Stefano Arrigoni, Mattia Brambilla, Monica Barbara Nicoli, Edoardo Sabbioni

分類: cs.ET, cs.RO, cs.SY, eess.SY

原文アブストラクト

Platooning represents an advanced driving technology designed to assist drivers in traffic convoys of varying lengths, enhancing road safety, reducing driver fatigue, and improving fuel efficiency. Sophisticated automated driving assistance systems have facilitated this innovation. Recent advancements in platooning emphasize cooperative mechanisms within both centralized and decentralized architectures enabled by vehicular communication technologies. This study introduces a cooperative route planning optimization framework aimed at promoting the adoption of platooning through a centralized platoon formation strategy at the system level. This approach is envisioned as a transitional phase from individual (ego) driving to fully collaborative driving. Additionally, this research formulates and incorporates travel cost metrics related to fuel consumption, driver fatigue, and travel time, considering regulatory constraints on consecutive driving durations. The performance of these cost metrics has been evaluated using Dijkstra's and A* shortest path algorithms within a network graph framework. The results indicate that the proposed architecture achieves an average cost improvement of 14 % compared to individual route planning for long road trips.

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. 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

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