一手统治他们全部：统一灵活操作的规范表示
One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation
AI总结：
本文提出统一灵活操作的规范表示，通过统一参数空间和规范URDF格式，解决固定手设计限制，实现跨手灵活操作学习。
摘要：
当今灵活操作策略大多假设固定手设计，严重限制其在新结构布局下的泛化能力。为克服这一限制，我们引入了一种参数化的规范表示，统一了广泛灵活手架构。它包含统一的参数空间和规范URDF格式，提供三个关键优势：1）参数空间捕捉本质形态和运动学变化，用于学习算法的有效条件；2）可以在我们的空间上学习结构化潜在流形，使不同结构之间的插值产生平滑且物理上意义的形态过渡；3）规范URDF标准化了动作空间，同时保持原始URDF的动力学和功能属性，使跨结构策略学习高效可靠。通过广泛的分析和实验验证这些优势，包括抓取策略回放、VAE潜在编码和跨结构零样本迁移。具体而言，我们训练了一个VAE在统一表示上，获得紧凑且语义丰富的潜在嵌入，并开发一个基于规范表示的抓取策略，跨灵活手泛化。通过模拟和未见过的形态任务（例如81.9%的零样本成功率在3指LEAP手），证明我们的框架统一了结构多样手的表示和动作空间，为跨手学习提供可扩展的基础，朝着通用灵活操作迈进。项目页面：https://zhenyuwei2003.github.io/OHRA/
英文摘要：
Dexterous manipulation policies today largely assume fixed hand designs, severely restricting their generalization to new embodiments with varied kinematic and structural layouts. To overcome this limitation, we introduce a parameterized canonical representation that unifies a broad spectrum of dexterous hand architectures. It comprises a unified parameter space and a canonical URDF format, offering three key advantages. 1) The parameter space captures essential morphological and kinematic variations for effective conditioning in learning algorithms. 2) A structured latent manifold can be learned over our space, where interpolations between embodiments yield smooth and physically meaningful morphology transitions. 3) The canonical URDF standardizes the action space while preserving dynamic and functional properties of the original URDFs, enabling efficient and reliable cross-embodiment policy learning. We validate these advantages through extensive analysis and experiments, including grasp policy replay, VAE latent encoding, and cross-embodiment zero-shot transfer. Specifically, we train a VAE on the unified representation to obtain a compact, semantically rich latent embedding, and develop a grasping policy conditioned on the canonical representation that generalizes across dexterous hands. We demonstrate, through simulation and real-world tasks on unseen morphologies (e.g., 81.9% zero-shot success rate on 3-finger LEAP Hand), that our framework unifies both the representational and action spaces of structurally diverse hands, providing a scalable foundation for cross-hand learning toward universal dexterous manipulation. Project Page: https://zhenyuwei2003.github.io/OHRA/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
