arXiv cs.AI· Qinxi Yu, Wenzhou Ding, Gloria X. Wang, Albert J. Zhai, Shenlong Wang·· 3 天前AI 评分27
Box-WAM：用框轨迹作为世界动作模型的紧凑状态表示
Box-WAM: Box Trajectories as Compact State Representations for World Action Models
AI 导读
Box-WAM 提出用任务相关物体的有向边界框轨迹替代全帧视频预测，作为世界动作模型（WAM）的紧凑未来状态表示。该方法在显著降低训练与推理计算成本的同时提升了动作预测性能，表明以物体为中心的紧凑状态可作为机器人操作中基于视频的世界动作建模的高效替代方案。
正文 · 原文
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 this https URL
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17526 [cs.RO] |
| (or arXiv:2610.17526v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17526 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qinxi Yu [view email]
[v1]
Tue, 13 Oct 2026 00:42:36 UTC (5,062 KB)
来源：arXiv cs.AI · arxiv.org