# 按需细化动作：面向机器人操作的自适应动作块细化

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-19765
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：为兼顾操作成功率与推理延迟，RAIN预测不同细化级别动作误差以自适应细化提案，并在ManiSkill和真机任务验证。

# 按需细化动作：面向机器人操作的自适应动作块细化

::: v-pre
> 原文链接：[Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation](https://arxiv.org/abs/2610.19765)（arXiv 2610.19765 · 发布日期：2026-10-14）

**Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation**

为兼顾操作成功率与推理延迟，RAIN预测不同细化级别动作误差以自适应细化提案，并在ManiSkill和真机任务验证。

## 核心要点

- 轻量策略延迟低但误差影响成功率，迭代生成策略成功率高却增加推理延迟。
- RAIN在细化前预测各级动作误差，决定每个可执行提案是否以及细化多少。
- 在八个ManiSkill任务中成功率66.6%，以5.71倍更低延迟接近最佳扩散策略。
- 四个真机任务中成功率由ACT的55.0%升至72.5%，项目页已公开。

**验证范围与局限**：验证范围为八个ManiSkill仿真任务和四个真实机器人任务。

## 英文摘要 (Abstract)

Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. Iterative generative policies can achieve higher task success rates, but repeated network evaluations increase inference latency. Refining action proposals from computationally lightweight policies can combine these strengths, but the amount of refinement needed varies across states. We introduce RAIN (Refine Actions If Needed), a framework that predicts action errors at different refinement levels to decide whether and how much to refine each executable proposal, before performing any refinement. We train an ensemble to predict these errors by comparing action proposals and their refined versions with expert actions from offline demonstrations, without requiring explicit labels of refinement needs. Calibration balances uncertainty, computation, and temporal consistency. We evaluate RAIN on eight ManiSkill tasks and four real-robot tasks. In simulation, our policy achieves 66.6% success, approaching the best evaluated diffusion-policy success rate with 5.71 times lower policy latency. On the real robot, success increases from 55.0% with Action Chunking with Transformers (ACT) to 72.5%, with comparable average successful completion time. Matched controls show that dynamic routing maintains the strongest observed fixed-refinement success level with 26.6% fewer refiner evaluations. Project page: https://rain-policy.github.io/.

作者：Hanlin Liu, Zichen Zhou, Jiacheng Zhang, Liuyuan Na, Jin Jin, Guangyan Chen, Yufeng Yue, Gen Li, Fangqiang Ding
:::

## 原始参考来源 (Sources)

- [arXiv 2610.19765：Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation](https://arxiv.org/abs/2610.19765)