# ProxiDex：学习用于灵巧操作的动力学引导接近性策略

> 原文链接：https://robotics.hellobike.com/papers/2026-09-15-2609-16586
> 频道：papers | 更新日期：2026-09-15 | 标签：arxiv, cs.RO
> 核心摘要：ProxiDex将手物接近性作为交互状态，通过动力学引导策略，在仿真和真实灵巧操作中提升成功率与鲁棒性。

# ProxiDex：学习用于灵巧操作的动力学引导接近性策略

::: v-pre
> 原文链接：[ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation](https://arxiv.org/abs/2609.16586)（arXiv 2609.16586 · 发布日期：2026-09-15）

**ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation**

ProxiDex将手物接近性作为交互状态，通过动力学引导策略，在仿真和真实灵巧操作中提升成功率与鲁棒性。

## 核心要点

- 多指操作依赖稳定手物交互，但视觉遮挡、触觉标定和接触不确定会使策略脆弱。
- 方法重建交互点云，将几何距离转为硬件无关的接近性线索，并支持VR遥操作反馈。
- 其学习动作条件接近性动力学，并在操作阶段间自适应重加权接近性token。
- 仿真和真实实验表明，其在标准、未见物体和扰动场景优于代表性基线，并提供额外可视化。

**验证范围与局限**：验证范围为仿真和真实实验中的标准、未见物体与扰动场景。

## 英文摘要 (Abstract)

Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and existing policies rarely model how these cues evolve under actions, making them brittle under contact uncertainty. To address these, we present ProxiDex, a dynamics-guided proximity policy framework that treats hand-object proximity as an interaction state for dexterous manipulation. ProxiDex reconstructs interaction point clouds and converts geometric distances into proximity cues, forming a hardware-agnostic contact representation that provides immersive feedback during VR teleoperation. Built on this representation, ProxiDex learns action-conditioned proximity dynamics with a coupled forward-inverse design: future observation latents are predicted from actions, while proximity variations are decoded from latent changes. Leveraging these dynamics, ProxiDex adaptively reweights proximity tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference, stabilizing action generation under unreliable visual feedback. Simulation and real-world experiments demonstrate improved success rates and robustness over representative baselines across standard, unseen objects, and perturbation scenarios. Additional visualizations are available at https://proxidex.github.io/.

作者：Yushan Bai, Boyu Zheng, Zhiyang Mao, Hongzheng Sun, Yuchuang Tong, En Li, Zhengtao Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2609.16586：ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation](https://arxiv.org/abs/2609.16586)