ハイブリッド身体性タスクにおける長期的進化のためのワールド・エゴモデリング
World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
本論文は、長期的なハイブリッド身体性タスク（ナビゲーションと操作の組み合わせ）において、世界と自己の進化を分離してモデル化する新しいパラダイム「ワールド・エゴモデリング」を提案し、その実装としてWEMモデルとベンチマークHTEWorldを構築した。
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: Zuyao Lin, Jianhui Zhang, Peidong Jia, Xiaoguang Zhao, Shanghang Zhang, Xingyu Chen
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
World models are widely explored in embodied intelligence, yet they typically predict distinct evolutions of the world and the ego within a single stream, where the world captures persistent instruction-agnostic scene regularities and the ego captures robot-centric instruction-conditioned dynamics. This world-ego entanglement leads to a degradation in long-horizon embodied scenarios, particularly in hybrid tasks with interleaved navigation and manipulation behaviors. In this paper, we introduce \emph{World-Ego Modeling}, a new conceptual paradigm that decomposes future evolution into world and ego components. We define the world-ego boundary from three perspectives, i.e., motion-, semantic-, and intention-based views, and analyze three disentanglement strategies with post-, pre-, and full disentanglement. Further, we instantiate this paradigm as the World-Ego Model (WEM), a unified embodied world model that couples an implicit separate world-ego planner with a cascade-parallel mixture-of-experts (CP-MoE) diffusion generator. To enable rigorous evaluation, we further construct HTEWorld, the first benchmark for long-horizon world modeling with hybrid navigation-manipulation tasks, providing 125K video clips (over 4.5M frames) with fine-grained action annotations and 300 multi-turn evaluation trajectories (over 2K instructions). Extensive experiments show that WEM achieves state-of-the-art performance on HTEWorld while remaining competitive on existing manipulation-only benchmarks.
