# EgoReveal：从自我中心演示中学习部分遮挡下的主动视觉与物体操作

> 原文链接：https://robotics.hellobike.com/papers/2026-10-09-2610-12999
> 频道：papers | 更新日期：2026-10-09 | 标签：arxiv, cs.RO
> 核心摘要：EgoReveal从自我中心人类演示学习视点重定位与操作，并在初始部分遮挡的物体操作实验中验证。

# EgoReveal：从自我中心演示中学习部分遮挡下的主动视觉与物体操作

::: v-pre
> 原文链接：[EgoReveal: Learning Active Vision and Object Manipulation under Partial Occlusions from Egocentric Demonstrations](https://arxiv.org/abs/2610.12999)（arXiv 2610.12999 · 发布日期：2026-10-09）

**EgoReveal: Learning Active Vision and Object Manipulation under Partial Occlusions from Egocentric Demonstrations**

EgoReveal从自我中心人类演示学习视点重定位与操作，并在初始部分遮挡的物体操作实验中验证。

## 核心要点

- 自我中心演示易于收集，但既有无需机器人或专用设备的方法未显式处理遮挡。
- 框架联合学习视点重定位和操作动作，在遮挡下移动视角以获得目标可见性。
- 采用两种模仿策略，分别预测未来相机臂位姿序列和未来控制命令。
- 根据目标可见性切换策略，实验中比固定相机基线更可靠完成任务。

**验证范围与局限**：验证范围为被操作物体初始部分遮挡的实验，摘要未说明仿真或真机设置。

## 英文摘要 (Abstract)

Learning from Demonstrations (LfD) enables robots to learn object manipulation directly from human demonstrations. In contrast to resource-intensive and labor-intensive teleoperation, egocentric demonstrations are easy to collect, enabling scalable data collection. Manipulated objects are often partially occluded in everyday environments, yet prior egocentric demonstration-based methods that require no robots or specialized teaching devices do not explicitly address occlusions. To fill this gap, we propose EgoReveal, a framework that learns viewpoint-repositioning together with manipulation actions from egocentric human demonstrations to reposition the viewpoint and obtain target visibility under partial occlusions. EgoReveal instantiates this as two imitation policies: one predicts the future camera-arm pose sequence from the current view and camera-arm pose, and the other predicts the future control commands from object keypoints and a history of control commands. EgoReveal switches between the two based on target visibility. In experiments where the manipulated object is partially occluded initially, EgoReveal repositions the camera to obtain visibility and completes the task more reliably than fixed-camera baselines.

作者：Hiromu Kurihara, Kazutoshi Tanaka, Masashi Hatano, Tadashi Kozuno, Hideo Saito, Mariko Isogawa
:::

## 原始参考来源 (Sources)

- [arXiv 2610.12999：EgoReveal: Learning Active Vision and Object Manipulation under Partial Occlusions from Egocentric Demonstrations](https://arxiv.org/abs/2610.12999)