DECOWAM: 脚式移動マニピュレーションのための分離型全身世界行動モデル
DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
移動マニピュレーションのための世界行動モデルを提案し、カメラの自己運動とベース・アーム動作を分離して予測する。実ロボットデータセットを用いて、将来の映像と行動の予測精度を向上させた。
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: Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu
分類: cs.AI, cs.RO
原文アブストラクト
Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly distinguish camera ego-motion from base and arm actions. Here we introduce DECOWAM, a whole-body world-action model that separates these factors through dedicated conditional interfaces. DECOWAM freezes an adapted FastWAM backbone and trains residual adapters, an action-equivalent future bottleneck distilled from privileged observations, adversarially separated base and arm latents, and base-velocity conditioning for video prediction. We further introduce ARMDOG, a real-robot dataset that synchronizes video, whole-body state and action, and language. On a fixed replay protocol, DECOWAM improved both future-video and action prediction over FastWAM, reducing action MSE by 21.7% with 25.95M trainable adaptation parameters. Across 79 closed-loop trials per method, it achieved the highest observed whole-body coordination and base-displacement robustness among the compared systems, while task completion remained comparable to the strongest baseline. These results show that embodiment-aware factorization can support parameter-efficient joint visual prediction and whole-body control under moving viewpoints.