通过对抗姿态正则化在灵巧钢琴演奏中强制执行类人运动学
Enforcing Human-like Kinematics in Dexterous Piano Playing via Adversarial Posture Regularization
AI总结：
提出对抗姿态正则化（APR）方法，利用少量非对齐的人类演奏数据，通过对抗目标匹配策略姿态分布与人类先验，使高自由度灵巧手在物理仿真中弹钢琴时呈现更自然的姿势。
摘要：
强化学习可以训练双手灵巧手在物理仿真中弹钢琴，并具有高音符准确度，但对于高自由度灵巧手，仅依赖任务奖励或逆运动学往往导致不自然的姿势和关节过度伸展。我们提出\textit{对抗姿态正则化（APR）}。它避免了昂贵的、与歌曲对齐的专家演示数据，而是使用少量随意的人类演奏数据。通过对抗目标匹配策略的姿态分布与人类先验，APR鼓励更类人的手形。同时，我们使用消费级Meta Quest 3收集并发布了钢琴演奏的非结构化手部运动数据，并将关键运动信息重定向到Shadow Hand。最终，在所有三个类人度量（cPSI、BSE和FAC）以及视觉质量上，我们取得了比先前方法显著更好的性能。项目仓库：此 https URL。
英文摘要：
Reinforcement learning can train bimanual dexterous hands to play piano in physics simulation with high note accuracy, but for high-DoF dexterous hands, relying solely on task rewards or IK inversion often leads to unnatural postures and joint overextension. We propose \textit{Adversarial Posture Regularization (APR)}. It avoids expensive, song-aligned expert demonstration data and instead uses a small amount of casual human playing data. By matching the distribution of the posture of the policy with the human prior through an adversarial objective, APR encourages more human-like hand shapes. Meanwhile, we collect and release unstructured hand motion data of piano playing using a consumer-grade Meta Quest 3, and retarget the key motion information to the Shadow Hand. Finally, we achieve significantly better performance than prior methods on all three human-likeness metrics (cPSI, BSE, and FAC) as well as in visual quality. Project repository: https://github.com/APRProject/APRPianist.
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。
