# 机器人时空编辑：通过掩码动作重建实现可控动作生成的统一接口

> 原文链接：https://robotics.hellobike.com/papers/2026-10-16-2610-23002
> 频道：papers | 更新日期：2026-10-16 | 标签：arxiv, cs.RO
> 核心摘要：该工作面向多样时空参考下的可控机器人行为生成，提出MAP接口与补全策略，并在ManiSkill、LIBERO-10及真实实验验证。

# 机器人时空编辑：通过掩码动作重建实现可控动作生成的统一接口

::: v-pre
> 原文链接：[Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction](https://arxiv.org/abs/2610.23002)（arXiv 2610.23002 · 发布日期：2026-10-16）

**Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction**

该工作面向多样时空参考下的可控机器人行为生成，提出MAP接口与补全策略，并在ManiSkill、LIBERO-10及真实实验验证。

## 核心要点

- 动机是生成式策略虽能合成机器人行为，但难以通过多样时空参考进行控制和编辑。
- 方法将关键点、流、姿态和关键位姿统一为时间笛卡尔动作空间的部分规格。
- Inpainting Policy重建末端执行器缺失动作维度，并结合进度引导对齐和多掩码训练。
- 在ManiSkill和LIBERO-10上平均成功率为92.67%和64.67%，真实实验展示位置和旋转误差。

**验证范围与局限**：验证范围包括ManiSkill、LIBERO-10以及真实世界时空控制实验。

## 英文摘要 (Abstract)

Generative policies can synthesize robot behaviors, yet controlling and editing them through diverse spatiotemporal references remains challenging. In the real world, human intent requires robot behaviors that satisfy constraints on where, when, and how actions are executed. Our key insight is that spatiotemporal control references, such as keypoints, flows, orientations, and keyposes, can be viewed as partial specifications of the same temporal Cartesian action space. We introduce the MAP (Masked Action Space) interface to unify these action references and formulate controllable manipulation as an action inpainting problem. Our Inpainting Policy (IP) reconstructs missing action dimensions of the end-effector, combining progress-guided alignment with multi-mask training to support unseen action-constraint combinations. We further adopt a training-free RePaint variant that iteratively inpaints the action during denoising to reduce control error. On ManiSkill and LIBERO-10, our policy achieves average task success rates of 92.67% and 64.67%, respectively.Real-world experiments demonstrate spatiotemporal control with average positional and rotational errors of 44.3 mm and 7°, respectively, showing that our policy can use diverse references to guide executable robot behaviors.

作者：Yanbang Li, Bu He, Yi Tian, Yu-Chiao Huang, Chenyu Zhang, Ruoqu Chen, Yuanzhe Liu, Yuxiang Gao, Mengdi Xu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.23002：Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction](https://arxiv.org/abs/2610.23002)