安全な行動だけでは不十分:視覚言語行動ポリシーのための実行可能未来デコーディング
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
凍結したVLAポリシーにおいて、局所的に安全な行動でも将来の安全なタスク完了が不可能になる「実現可能性-尤度ギャップ」を定式化し、再学習やオンラインロールアウトなしで安全な候補を選び直す訓練不要のリランカーを提案した。
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: Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang, Jannik Hammel Nielsen, Xuebing Zhou, Haitham Bou Ammar
分類: cs.AI, cs.RO
原文アブストラクト
A safe action is not necessarily a viable one. Under a frozen vision-language-action (VLA) policy, an action can be likely and locally admissible yet leave no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the current action, whereas feasibility depends on the futures that remain after it. We derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation exposes a candidate-dependent feasible-future mass with two roles: its support records whether safe completion remains possible under the frozen continuation process, and its magnitude measures how much weighted safe-completion mass is preserved. Exact evaluation is impractical online, so we develop a selective finite-candidate approximation, derive conditions for recovering the best retained viable candidate, and instantiate it as an alarm-triggered, training-free reranker. On Safety-CHORES, VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. The resulting decoder is tied to an exact policy-relative safe-completion target, yet requires neither retraining of the base policy nor online trajectory rollouts.