異種ロボットのための校正済み予測安全:行動条件付きJEPAフレームワークとモデルベース安全シールド
Calibrated Predictive Safety for Heterogeneous Robots: An Action-Conditioned JEPA Framework with Model-Based Safety Shields
視覚言語行動ポリシーに実行時保証を追加するため、行動条件付きJEPA世界モデルで候補行動のタスク進捗と物理リスクを予測し、モデルベース安全シールドでフィルタリングするパイプラインを提案した。
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: Kaiming Zhong, Tianhua Liu, Yue Wang
分類: cs.RO
原文アブストラクト
Vision-language-action policies generalize broadly but provide no execution-time guarantees; classical model-based planners respect kinematic and geometric constraints but generalize poorly. We study whether an action-conditioned Joint-Embedding Predictive Architecture (JEPA) world model can predict, before execution, both task progress and physical risk for candidate action chunks, and whether coupling these predictions to an embodiment-specific model-based safety shield yields a deployable pipeline for heterogeneous robots. We propose a receding-horizon decision pipeline: (1) a proposer produces K candidate action chunks; (2) an action-conditioned JEPA rolls each candidate forward in a frozen-encoder latent space conditioned on an embodiment embedding; (3) calibrated risk and progress heads score each rollout and report uncertainty; (4) a deterministic per-embodiment safety shield filters inadmissible candidates; (5) a fallback ladder handles empty-admissible-set cases. The learned ranking only reorders admissible candidates; enforcement guarantees come from the deterministic shield and fallback ladder. We evaluate with a pre-registered protocol in simulation (LIBERO-Long). In 600-episode configurations the full framework improved success over a shield-only baseline and reduced collision false negatives at matched recall. Deployment-efficiency measurements on target on-robot and edge accelerators are included. Real-robot experiments and an offline reranking significance test remain future work; see the paper for disclosures.