# 迈向采用 Self-Recursive Pruning 的高效机器人操作模型

> 原文链接：https://robotics.hellobike.com/papers/2026-10-06-2610-08555
> 频道：papers | 更新日期：2026-10-06 | 标签：arxiv, cs.RO
> 核心摘要：提出免训练的LCAM非结构化剪枝，通过自递归粗到细校准，在LIBERO、OpenVLA和真实乒乓中验证机器人操作策略压缩。

# 迈向采用 Self-Recursive Pruning 的高效机器人操作模型

::: v-pre
> 原文链接：[Towards Efficient Robotic Manipulation Models with Self-Recursive Pruning](https://arxiv.org/abs/2610.08555)（arXiv 2610.08555 · 发布日期：2026-10-06）

**Towards Efficient Robotic Manipulation Models with Self-Recursive Pruning**

提出免训练的LCAM非结构化剪枝，通过自递归粗到细校准，在LIBERO、OpenVLA和真实乒乓中验证机器人操作策略压缩。

## 核心要点

- 通用剪枝准则偏向图像识别或语言模型，直接用于机器人闭环动作表现不佳。
- LCAM结合行归一化权重贡献、演示激活矩和动作预测损失敏感性排序连接。
- 自递归粗到细流程在嵌套剪枝后重校准重要性，并用离线动作失真分配细粒度预算。
- 在LIBERO-Object的OpenVLA上，50%非结构化剪枝成功率84.0%，保留密集策略逾90%。

**验证范围与局限**：验证范围包括三套LIBERO套件、OpenVLA评估和真实机器人乒乓任务。

## 英文摘要 (Abstract)

Network pruning can reduce parameter redundancy in robotic policies. However, generic pruning criteria are tailored for image recognition tasks and commonly designed to preserve weight magnitude, local reconstruction, or language-model likelihood rather than closed-loop action behavior. Directly applying these pruning algorithms to robotic tasks yields unsatisfactory performance. In this paper, we propose Loss-Conditioned Activation-Moment (LCAM) pruning, a training-free method for unstructured pruning of pre-trained robotic manipulation policies. Specifically, we first rank connections using row-normalized weight contribution, activation moments measured on calibration demonstrations, and the sensitivity of output directions to the action-prediction loss. We further design a self-recursive coarse-to-fine procedure: importance is recalibrated after each nested coarse pruning stage, while held-out offline action distortion guides fine-grained budget allocation after a sparsity knee. Our algorithm is free from costly recovery training and simulator rollouts after pruning. Experiments on three LIBERO suites with competitive robotic policies, together with evaluations on OpenVLA, show that LCAM attains competitive performance across a broad range of pruning ratios. Notably, on LIBERO-Object with OpenVLA, our LCAM achieves 84.0% success at 50% unstructured pruning, retaining over 90% of the dense policy's success rate. Promising results on real-world robotic ping pong further demonstrate the effectiveness of our pruning algorithm.

作者：Zijia Chen, Yuenan Hou, Yu Li, Weijie Li, Li Liu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.08555：Towards Efficient Robotic Manipulation Models with Self-Recursive Pruning](https://arxiv.org/abs/2610.08555)