ABot-M0.5: 統合移動・操作世界行動モデル

要旨

移动操作是通用型机器人的关键能力，但对于当前的具身学习方法而言仍具挑战性。视觉-语言-动作（VLA）策略通常是被动的，缺乏显式的世界建模，而现有的世界动作模型（WAMs）在移动操作的结构上仍存在对齐不足的问题：它们以粗粒度的视频片段为单位进行运算，建模了纠缠的导航-操作动作，并在与自回归推理不匹配的监督条件下训练逆动力学。因此，这些模型常常忽略细粒度的接触动力学，遭受动作分布冲突，并在长时程任务执行中累积误差。我们提出ABot-M0.5，这是一种全新的WAM，其核心理念是：移动操作需要在三个层面实现对齐——时间粒度、动作空间以及训练-测试一致性。为对齐时间粒度，我们引入了中间潜在动作，用于捕获局部视觉状态转换，并作为视频潜在表示与具身特定控制之间的桥接动作空间。为对齐动作空间，我们设计了双层混合Transformer架构，以解耦模态表示与异构动作子空间（如基座移动与手臂操作）。为对齐推理条件，我们提出了梦境驱动训练策略，逐步在模型预测的视频上训练逆动力学，从而提升自回归预测中的训练-测试对齐度和鲁棒性。在具有挑战性的移动操作与细粒度操作基准上的实验表明，ABot-M0.5在长时程任务成功率与细粒度控制精度上均达到了最先进的性能。这些结果突显了粒度对齐、动作解耦与推理一致的世界-动作建模的关键重要性。

English

Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling, while existing World Action Models (WAMs) are still poorly aligned with the structure of mobile manipulation: they operate on coarse video chunks, model entangled navigation-manipulation actions, and train inverse dynamics under supervision that does not match autoregressive inference. As a result, they often miss fine-grained contact dynamics, suffer from action-distribution conflicts, and accumulate errors over long-horizon rollouts. We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls. To align action space, we design a dual-level Mixture-of-Transformers architecture that disentangles both modality representations and heterogeneous action subspaces such as base movement and arm manipulation. To align inference conditions, we propose the dream-forcing training strategy that progressively trains inverse dynamics on model-predicted videos, improving train-test alignment and robustness during autoregressive prediction. Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy. These results highlight the critical importance of granularity-aligned, action-disentangled, and inference-consistent world-action modeling.