# 超越 State-as-Action：利用命令-状态差异进行机器人模仿学习

> 原文链接：https://robotics.hellobike.com/papers/2026-09-27-2609-33145
> 频道：papers | 更新日期：2026-09-27 | 标签：arxiv, cs.RO
> 核心摘要：针对受约束交互中运动难以反映控制需求的问题，提出CSDW利用命令-状态差异加权监督，并在三项真机任务上验证。

# 超越 State-as-Action：利用命令-状态差异进行机器人模仿学习

::: v-pre
> 原文链接：[Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning](https://arxiv.org/abs/2609.33145)（arXiv 2609.33145 · 发布日期：2026-09-27）

**Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning**

针对受约束交互中运动难以反映控制需求的问题，提出CSDW利用命令-状态差异加权监督，并在三项真机任务上验证。

## 核心要点

- 从测得运动构造动作目标很常见，但受约束交互下命令-状态差异可能包含额外控制需求。
- CSDW考虑机器人响应时间，将后续进展、持续未满足需求和需求变化合成为连续命令监督权重。
- 三项真机任务的任务与阶段分析显示，受约束交互中监督缺口更大，局部命令信息有用。
- CSDW在受约束任务上优于均匀命令监督，在较少受约束任务中各方法表现相近；项目页已提供。

**验证范围与局限**：验证范围为三项真实机器人任务，包括受约束任务和较少受约束任务。

## 英文摘要 (Abstract)

Constructing action targets from measured robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect control demands that motion alone does not capture. We investigate when this information matters and how to exploit it. Across three real-robot tasks, task and phase analyses reveal larger supervision gaps under constrained interaction, while selective command retention provides evidence of locally useful command information. Building on these findings, we propose Command-State Discrepancy Weighting (CSDW), which accounts for robot response times and combines subsequent progress, persistent unmet demand, and demand changes into continuous weights for command supervision. The method requires no task-phase annotations or changes to policy architecture or inference. CSDW improves over uniform command supervision on constrained tasks, while methods perform similarly in the less constrained task. Project page: https://seen-e.github.io/CSDW/.

作者：Peiyan Li, Yueran Tao, Enhao Zhang, Zhixuan Zhao, Chenghao Yue, Hao Wang, Lei Lv, Wentao Zhao, Jiahao Chen, Xin Liu
:::

## 原始参考来源 (Sources)

- [arXiv 2609.33145：Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning](https://arxiv.org/abs/2609.33145)