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:2401.11792

潜在深層強化学習とデモンストレーションを用いた効率的で汎用性の高いエンドツーエンド自動運転システム

Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations

シェア:XThreadsFacebookLINEはてブBluesky

正規化フローと変分推論を組み合わせた強化学習と専門家デモンストレーションを統合し、複雑な都市環境でのサンプル効率、安全性、汎化性能を向上させたエンドツーエンド自動運転システムを提案。

著者: Zuojin Tang, Xiaoyu Chen, Yongqiang Li, Jianyu Chen

分類: cs.RO, cs.AI, cs.LG

原文アブストラクト

An intelligent driving system should dynamically formulate appropriate driving strategies based on the current environment and vehicle status while ensuring system security and reliability. However, methods based on reinforcement learning and imitation learning often suffer from high sample complexity, poor generalization, and low safety. To address these challenges, this paper introduces an efficient and generalized end-to-end autonomous driving system (EGADS) for complex and varied scenarios. The RL agent in our EGADS combines variational inference with normalizing flows, which are independent of distribution assumptions. This combination allows the agent to capture historical information relevant to driving in latent space effectively, thereby significantly reducing sample complexity. Additionally, we enhance safety by formulating robust safety constraints and improve generalization and performance by integrating RL with expert demonstrations. Experimental results demonstrate that, compared to existing methods, EGADS significantly reduces sample complexity, greatly improves safety performance, and exhibits strong generalization capabilities in complex urban scenarios. Particularly, we contributed an expert dataset collected through human expert steering wheel control, specifically using the G29 steering wheel.

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