自動運転車両の運動計画のための言語モデルのオンポリシー蒸留
On-Policy Distillation of Language Models for Autonomous Vehicle Motion Planning
大規模言語モデル(LLM)による自動運転の運動計画知識を、小型の学生モデルへ効果的に蒸留する手法を研究。オンポリシー蒸留(GKD)が強化学習ベースラインを上回り、モデルサイズを5倍削減しても教師モデルに匹敵する性能を達成した。
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: Amirhossein Afsharrad, Amirhesam Abedsoltan, Ahmadreza Moradipari, Sanjay Lall
分類: cs.RO, cs.AI, cs.SY, eess.SY
原文アブストラクト
Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction as a language generation problem. However, deploying capable LLMs in resource-constrained onboard systems remains a fundamental challenge. In this paper, we study how to effectively transfer motion planning knowledge from a large teacher LLM to a smaller, more deployable student model. We build on the GPT-Driver framework, which represents driving scenes as language prompts and generates waypoint trajectories with chain-of-thought reasoning, and investigate two student training paradigms: (i) on-policy generalized knowledge distillation (GKD), which trains the student on its own self-generated outputs using dense token-level feedback from the teacher, and (ii) a dense-feedback reinforcement learning (RL) baseline that uses the teacher's log-probabilities as per-token reward signals in a policy gradient framework. Experiments on the nuScenes benchmark show that GKD substantially outperforms the RL baseline and closely approaches teacher-level performance despite a 5$\times$ reduction in model size. These results highlight the practical value of on-policy distillation as a principled and effective approach to deploying LLM-based planners in autonomous driving systems.
