EWAM: 具身知能における閉ループオンライン適応のための拡張世界行動モデル
EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence
事前学習済みの凍結Cosmos3バックボーン上に、推論時に挿入する4つの軽量ニューラル層(記憶・異常検知・ポリシールーティング・行動修正)を組み合わせた閉ループオンライン適応アーキテクチャEWAMを提案。ゼロショット評価で追加データなしに新タスクレイアウトへ適応する。
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。
分類: cs.RO, cs.AI
原文アブストラクト
In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network. Evaluated entirely under a zero-shot task protocol, EWAM is centrally focused on reducing the amount of additional deployment data required to adapt to new task layouts. Notably, no extra task-specific demonstration sets were introduced in any of the evaluations, and no fine-tuning was performed on the backbone network. Its performance gains stem entirely from an inference-time co-reasoning mechanism composed of four inserted lightweight neural layers: the Neural Experience Memory Layer located in the intermediate layers of the Diffusion Transformer (DiT) provides task-relevant execution context; the Neural Anomaly Detection Layer after the state prediction head monitors the divergence between predicted and actual states in real time; the Neural Policy Routing Layer dynamically selects direct execution, conservative replanning, or rollback recovery based on the anomaly severity; and the Neural Action Correction Layer refines the generated action chunks using execution diagnostics. Unlike naive feature fusion, the memory, anomaly detection, and correction modules are deeply integrated into the Cosmos3 forward path in a differentiable manner, with only the final routing decision being a discrete supervised one.
