Align2Act: 人間の運転行動に整合する指示チューニング済み自動運転モデル
Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving
人間の運転推論パターンと交通ルールに基づく構造化指示でLLMを微調整し、解釈可能な軌道計画を生成する自動運転フレームワークを提案。nuPlanベンチマークで性能と人間らしさを向上。
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: Kanishkha Jaisankar, Sunidhi Tandel
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Motion planning in complex scenarios is a core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to generate trajectories, while recent approaches leverage large language models (LLMs) for decision-making. However, it remains unclear whether LLMs truly capture human driving logic. We propose Align2Act, a motion planning framework that transforms instruction-tuned LLMs into interpretable planners aligned with human behavior. We derive structured driving instructions based on human reasoning patterns (e.g., anticipate hazards, yield at intersections) and traffic rules (e.g., stop at red lights, maintain lane boundaries). Our Align2ActChain module guides step-by-step reasoning to produce both an interpretable rationale and a safe trajectory. By fine-tuning LLaMA-2-7B with LoRA on one million scenarios from the nuPlan dataset, our method achieves an open-loop score of 85.17 and closed-loop scores of 70.31 (non-reactive) and 66.96 (reactive) on Test14-random. Unlike prior work focused on synthetic or open-loop settings, we demonstrate improved planning quality and human-likeness on the real-world nuPlan closed-loop benchmark. Ablation studies confirm that structured reasoning significantly improves performance over baseline LLM planners.
