DreamAvoid: 臨界期テストタイムドリーミングによるVLAポリシーの失敗回避
DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
VLAモデルが微細な操作中に失敗する問題に対し、実行が臨界期に入ったかを検出し、複数の候補行動を評価して最適な行動を選択する「テストタイムドリーミング」フレームワークを提案した。
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: Xianzhe Fan, Yuxiang Lu, Shenyuan Gao, Xiaoyang Wu, Ruihua Han, Manling Li, Hengshuang Zhao
分類: cs.RO, cs.AI, cs.CL, cs.CV
原文アブストラクト
Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly escalate into irrecoverable failures. Since existing VLA models rely predominantly on successful demonstrations for training, they lack an explicit awareness of failure during these critical phases. To address this, we propose DreamAvoid, a critical-phase test-time dreaming framework that enables VLA models to anticipate and avoid failures. We also introduce an autonomous boundary learning paradigm to refine the system's understanding of the subtle boundary between success and failure. Specifically, we (1) utilize a Dream Trigger to determine whether the execution has entered a critical phase, (2) sample multiple candidate action chunks from the VLA via an Action Proposer, and (3) employ a Dream Evaluator, jointly trained on mixed data (success, failure, and boundary cases), to "dream" the short-horizon futures corresponding to the candidate actions, evaluate their values, and select the optimal action. We conduct extensive evaluations on real-world manipulation tasks and simulation benchmarks. The results demonstrate that DreamAvoid can effectively avoid failures, thereby improving the overall task success rate. Our code is available at https://github.com/XianzheFan/DreamAvoid.
