通过量化手状态学习灵巧操作
Learning Dexterous Manipulation with Quantized Hand State
AI总结：
本文提出DQ-RISE方法，通过量化手状态简化手部动作预测，同时允许手臂动作与紧凑手状态协同扩散，从而实现更平衡高效的灵巧操作学习。
摘要：
灵巧机械手使机器人能够执行需要精细控制和适应性的复杂操作。实现此类操作具有挑战性，因为高自由度的手臂和手部运动紧密耦合，使学习和控制困难。成功的灵巧操作不仅依赖于精确的手部动作，还依赖于准确的臂部空间定位和协调的臂手动态。然而，现有视觉-运动策略通常将手臂和手部动作表示为单一联合空间，导致高维手部动作主导耦合动作空间并影响臂部控制。为此，我们提出了DQ-RISE，通过量化手状态简化手部动作预测，同时保留关键模式，并应用连续松弛使手臂动作与这些紧凑手状态协同扩散。这种设计使策略能够从数据中学习臂手协调，同时防止手部动作淹没动作空间。实验表明，DQ-RISE实现了更平衡和高效的學習，为结构化和可推广的灵巧操作铺平了道路。项目网站：http://rise-policy.github.io/DQ-RISE/
英文摘要：
Dexterous robotic hands enable robots to perform complex manipulations that require fine-grained control and adaptability. Achieving such manipulation is challenging because the high degrees of freedom tightly couple hand and arm motions, making learning and control difficult. Successful dexterous manipulation relies not only on precise hand motions, but also on accurate spatial positioning of the arm and coordinated arm-hand dynamics. However, most existing visuomotor policies represent arm and hand actions in a single combined space, which often causes high-dimensional hand actions to dominate the coupled action space and compromise arm control. To address this, we propose DQ-RISE, which quantizes hand states to simplify hand motion prediction while preserving essential patterns, and applies a continuous relaxation that allows arm actions to diffuse jointly with these compact hand states. This design enables the policy to learn arm-hand coordination from data while preventing hand actions from overwhelming the action space. Experiments show that DQ-RISE achieves more balanced and efficient learning, paving the way toward structured and generalizable dexterous manipulation. Project website: http://rise-policy.github.io/DQ-RISE/
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。
