Vision-Language-Actionモデルは一歩の観測摂動に頑健か?
Are Vision-Language-Action Models Robust to One-Step Observation Perturbations?
VLAモデルに対する一時的な観測ノイズの影響を調査し、予測アクションの一貫性に基づいて実行長を動的に調整するCAREを提案した研究。
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: Shojiro Yamabe, Jun Sakuma
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
Understanding the safety risks of vision-language-action (VLA) models is essential for their deployment in the physical world. Existing safety research has mainly considered persistent perturbations that are applied continuously to observations throughout an episode. However, momentary observation corruption, in which observations are severely perturbed only briefly within an episode, remains an underexplored safety threat. To address this gap, this work investigates robustness to one-step perturbations applied at a single time step per episode. Our experiments reveal that these perturbations substantially degrade VLA performance and that their impact depends on the action chunk execution length. Based on them, we propose CARE, which dynamically selects the execution length based on consistency with the previously predicted action chunk. CARE improves robustness with low computational overhead while preserving clean performance by selecting shorter execution lengths only under perturbations.
