VLA運転のためのマルチ軌道教師信号とポリシー最適化の整合
Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving
VLA運転モデルにおいて、マルチ軌道模倣学習とGRPOを整合させる新しいフレームワークを提案し、非実行可能な軌道による勾配バイアスをパレート最適性と動的蒸留で解消する。
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: Tian Zhang, Zhuo Huang, Hongrui Ye, Yu Wu, Zengmao Wang, Kaixuan Zhou
分類: cs.CV, cs.AI, cs.LG
原文アブストラクト
Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection critical to final performance. However, some high-scoring trajectories that improve imitation can degrade subsequent GRPO by inducing advantage estimates misaligned with the current policy's feasible behavior distribution, driving updates away from safe and compliant behaviors. To address this, we propose a novel framework that aligns multi-trajectory supervision with policy optimization. To address the policy gradient bias induced by infeasible noisy trajectories outside the feasible region, augmented trajectories are constrained to a neighboring manifold of the ground-truth feasible region, and a Pareto-optimality criterion is adopted in place of the conventional aggregate score, retaining only non-dominated candidates and thereby filtering out conflicting samples at the source. To ensure that expanded trajectory supervision is effectively absorbed during policy optimization, we introduce two complementary mechanisms: feasibility-first advantage assignment and dynamic distillation. The former adapts Pareto credit to the feasibility composition of each rollout group and guides fully infeasible groups toward safe references. The latter updates teacher trajectories across refinement rounds to continually transfer useful supervision. Together, they progressively translate the benefits of expanded supervision into policy improvement. On NAVSIM v1 and v2, our method achieves 91.4 PDMS and 89.1 EPDMS, respectively, under single-trajectory inference, and recovers 440 of 658 initially failed scenes, 11.1\% higher than the original GRPO baseline.
関連論文
- 言語の役割を再考する:自動運転のための効率的VLAへ向けてVLA/自動運転