日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

自動運転arXiv:2403.20116

LeGo-Drive: 言語強化型ゴール指向閉ループ自律運転

LeGo-Drive: Language-enhanced Goal-oriented Closed-Loop End-to-End Autonomous Driving

シェア:XThreadsFacebookLINEはてブBluesky

言語指示からゴール位置を推定し、ゴールと軌道を反復的に改善する閉ループ自律運転フレームワークを提案。シミュレーションで成功率81%を達成。

著者: Pranjal Paul, Anant Garg, Tushar Choudhary, Arun Kumar Singh, K. Madhava Krishna

分類: cs.RO

原文アブストラクト

Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a set of control actions as a reactive solution for closed-loop planning based on their rich scene comprehension. However, these estimations are coarse and are subjective to their "world understanding" which may generate sub-optimal decisions due to perception errors. In this paper, we introduce LeGo-Drive, which aims to address this issue by estimating a goal location based on the given language command as an intermediate representation in an end-to-end setting. The estimated goal might fall in a non-desirable region, like on top of a car for a parking-like command, leading to inadequate planning. Hence, we propose to train the architecture in an end-to-end manner, resulting in iterative refinement of both the goal and the trajectory collectively. We validate the effectiveness of our method through comprehensive experiments conducted in diverse simulated environments. We report significant improvements in standard autonomous driving metrics, with a goal reaching Success Rate of 81%. We further showcase the versatility of LeGo-Drive across different driving scenarios and linguistic inputs, underscoring its potential for practical deployment in autonomous vehicles and intelligent transportation systems.

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

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