# Box-WAM：边界框轨迹作为世界动作模型的紧凑状态表示

> 原文链接：https://robotics.hellobike.com/papers/2026-10-13-2610-17526
> 频道：papers | 更新日期：2026-10-13 | 标签：arxiv, cs.RO
> 核心摘要：BoxWAM用任务相关物体的有向边界框轨迹替代未来视频帧，在机器人操作任务上降低计算成本并提升动作预测。

# Box-WAM：边界框轨迹作为世界动作模型的紧凑状态表示

::: v-pre
> 原文链接：[Box-WAM: Box Trajectories as Compact State Representations for World Action Models](https://arxiv.org/abs/2610.17526)（arXiv 2610.17526 · 发布日期：2026-10-13）

**Box-WAM: Box Trajectories as Compact State Representations for World Action Models**

BoxWAM用任务相关物体的有向边界框轨迹替代未来视频帧，在机器人操作任务上降低计算成本并提升动作预测。

## 核心要点

- WAM显式预测动作和未来状态，但全帧视频预测在训练和推理中计算开销较高。
- BoxWAM以任务相关物体的有向边界框轨迹表示未来，捕捉动作引起的关键物理变化。
- 结果显示，框轨迹预测显著降低计算成本，同时改善动作预测性能。
- 摘要提供结果视频链接，未说明代码或模型是否开源。

**验证范围与局限**：仅说明在机器人操作任务上验证，摘要未注明仿真或真机范围。

## 英文摘要 (Abstract)

World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outperform action-only models across various robotic manipulation tasks. How- ever, representing the future with full-frame video prediction can be computation- ally expensive during both training and inference. This raises a central question: what compact state representation preserves the planning and supervision bene- fits of future prediction? In this paper, we propose BoxWAM, which replaces dense future frames with oriented bounding box trajectories of task-relevant ob- jects. By explicitly imagining object-centric future motion, our method provides a lightweight prediction target that captures the key physical changes induced by robot actions. We show that box trajectory prediction substantially reduces com- putational cost while improving action prediction performance, suggesting that object-centric compact states can serve as an efficient alternative to video-based world action modeling for robotic manipulation. Result videos can be found on https://box-wam.github.io

作者：Qinxi Yu, 丁文舟, Gloria X. Wang, Albert J. Zhai, Shenlong Wang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.17526：Box-WAM: Box Trajectories as Compact State Representations for World Action Models](https://arxiv.org/abs/2610.17526)