推論-想像-実行: 自動運転のためのワールドモデルを用いたクローズドループLLM意思決定
Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
LLMの意味的な意思決定と物理的な安全性のギャップを埋めるため、LLM推論器とアクション条件付きワールドモデルを組み合わせたクローズドループフレームワークRIAを提案。各ステップでLLMがアクション候補を生成し、ワールドモデルが短期的なロールアウトで安全性を検証して最適なアクションを選択する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Zhengqi Sun, Yiwen Sun, Boxuan Liu, Tailai Chen, Tianxu Guo, Jiabin Liu
分類: cs.AI, cs.CV, cs.LG, cs.RO
原文アブストラクト
Large language models (LLMs) are promising for autonomous driving, but semantics-only decision policies can yield physically unsafe behavior in dynamic traffic. Existing methods either perform online language reasoning without explicit dynamics verification or use world models mainly in offline pipelines, leaving a gap between semantic intent and physical feasibility at decision time. We propose Reason--Imagine--Act (RIA), a closed-loop framework that couples an LLM reasoner with an action-conditioned world model for online safety verification. At each step, the LLM proposes an action template and candidate sub-actions, the world model performs short-horizon rollouts, and a safety scorer selects the safest executable action with feedback to the next reasoning step. Under a unified CARLA point-goal protocol (1000 episodes), RIA achieves 80.05% route completion, 51.10% arrival rate, and 0.20% collision rate. Under the same closed-loop interface, RIA consistently outperforms training-free baselines, including CARLA TM and MADA, on core closed-loop metrics. For reproducibility, code is available at https://github.com/pku-smart-city/source_code/tree/main/RIA.
