# EgoPhys：从自我中心操作视频估计峰值接触力和机械功

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-11347
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：EgoPhys用RGB-only的CASA与TMTR，从自我中心操作视频估计峰值接触力和机械功，并在Hoi!测试集验证。

# EgoPhys：从自我中心操作视频估计峰值接触力和机械功

::: v-pre
> 原文链接：[EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video](https://arxiv.org/abs/2610.11347)（arXiv 2610.11347 · 发布日期：2026-10-08）

**EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video**

EgoPhys用RGB-only的CASA与TMTR，从自我中心操作视频估计峰值接触力和机械功，并在Hoi!测试集验证。

## 核心要点

- 物理扎根的铰接物体操作需要理解接触最大力与部件运动产生的功。
- 自我中心视频中的物理交互线索局部且间接，且峰值力与机械功依赖的时序特征不同。
- EgoPhys结合CASA聚合外观与几何线索，并用TMTR按语义、事件、运动专家分别路由预测。
- 在Hoi!数据集测试划分上，EgoPhys显著提升峰值力和机械功预测，MAE分别为5.205 N和0.894 J。

**验证范围与局限**：验证范围为Hoi!数据集测试划分上的自我中心操作视频。

## 英文摘要 (Abstract)

Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed as their parts move. Peak contact force and mechanical work quantify these complementary aspects, but estimating them from egocentric video is challenging because physical interaction cues are local and indirect. Moreover, peak force is associated with brief contact events, whereas mechanical work depends on force-motion coupling throughout the contact duration. To address these challenges, we propose EgoPhys, an RGB-only framework comprising Contact-Aware Spatial Aggregation (CASA) and Target-Specific Multi-Expert Temporal Routing (TMTR). CASA integrates appearance and geometry features to emphasize interaction-relevant cues, while TMTR models semantic, event, and motion cues with specialized temporal experts and routes them separately for force and work prediction. On the test split from Hoi! dataset, EgoPhys substantially improves predictions of peak force and mechanical work, achieving MAEs of \(5.205 \pm 0.584\) $N$ and $0.894 \pm 0.081$ $J$, respectively.

作者：Zhuo Dong, Jianhua Yang, Haohao Li, Yumeng Zhao, Keji He, Yan Huang, Liang Wang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.11347：EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video](https://arxiv.org/abs/2610.11347)