发表机构
Institute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Xinjiang University; Beijing Zhongke Huiling Robot Technology Co., LTD.（中国科学院自动化研究所; 中国科学院大学; 新疆大学; 北京中科慧灵机器人技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ProxiDex提出动力学引导的近距策略，利用手-物近距表示和动作条件动力学，在视觉反馈不可靠时稳定灵巧操作，提升成功率与鲁棒性。
AI 中文摘要
多指灵巧操作依赖于稳定的手-物交互，然而在实践中这些交互是部分可观测的。视觉观测常被手部遮挡，触觉传感器引入特定于硬件的模态和标定负担，且现有策略很少建模这些线索在动作作用下的演变，导致其在接触不确定性下表现脆弱。为解决这些问题，我们提出了ProxiDex，一种动力学引导的近距策略框架，将手-物近距视为灵巧操作的交互状态。ProxiDex重建交互点云并将几何距离转换为近距线索，形成一种与硬件无关的接触表示，在VR遥操作期间提供沉浸式反馈。基于该表示，ProxiDex通过耦合的前向-逆向设计学习动作条件下的近距动力学：从动作预测未来观测潜在变量，同时从潜在变量变化解码近距变化。利用这些动力学，ProxiDex在操作阶段自适应地重新加权近距标记，并使用动力学一致性监督来引导策略推理，在不可靠的视觉反馈下稳定动作生成。仿真和真实世界实验表明，在标准物体、未见物体和扰动场景中，与代表性基线相比，成功率与鲁棒性均有提升。更多可视化结果可访问此https URL。
英文摘要
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/.
CommentsAccepted at the 10th Conference on Robot Learning (CoRL 2026). Project page: https://proxidex.github.io/
