通过统一手部动作空间实现跨实体机器人操作
Cross-Embodiment Robot Manipulation via a Unified Hand Action Space
AI总结：
提出统一手部动作空间（UHAS）用于跨实体灵巧操作，将手部动作表示为标准球体几何变形，用级联逆运动学算法映射，经强化学习训练策略，实现跨实体零样本转移等显著收益。
摘要：
机器人操作策略通常与特定机器人手部实体相关联，限制了跨运动学结构平台的行为转移。本文提出统一手部动作空间（Unified Hand Action Space，UHAS），用于跨实体灵巧操控，将机器人手部动作表示为标准球体的几何变形，并使用级联逆运动学（CIK）算法将共享表示映射到特定实体的关节配置。通过强化学习，我们直接在所提出的动作空间中训练灵巧操作策略，用于手部内立方体重新定向任务。我们在包括Allegro Hand、LEAP Hand、Shadow Hand和MANO Human Hand在内的多种机器人手部的模拟和真实世界实验中评估我们的方法。实验结果表明了有效的灵巧操作、对未见手部的零样本转移、跨实体的快速微调以及成功的真实世界部署。我们的实验表明，所提出的UHAS表示能够实现跨机器人手部的稳定灵巧控制和跨实体策略转移。
英文摘要：
Robot manipulation policies are typically tied to specific robotic hand embodiments, limiting the transfer of learned behaviors across platforms with different kinematic structures. In this work, we propose the Unified Hand Action Space (UHAS), a sphere-based unified action representation for cross-embodiment dexterous manipulation. UHAS represents robotic hand actions as geometric deformations of a canonical sphere and uses a Cascade Inverse Kinematics (CIK) algorithm to map the shared representation to embodiment-specific joint configurations. Using reinforcement learning, we train dexterous manipulation policies directly in the proposed action space for in-hand cube reorientation tasks. We evaluate our method in both simulation and real-world experiments across multiple robotic hands, including the Allegro Hand, LEAP Hand, Shadow Hand, and MANO Human Hand. Experimental results demonstrate effective dexterous manipulation, zero-shot transfer to unseen hands, rapid finetuning across embodiments, and successful real-world deployment. Our experiments show that the proposed UHAS representation enables stable dexterous control and cross-embodiment policy transfer across robotic hands.
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。
