We present PANDORA, a novel diffusion-based policy learning framework designed specifically for dexterous robotic piano performance. Our approach employs a conditional U-Net architecture enhanced with FiLM-based global conditioning, which iteratively denoises noisy action sequences into smooth, high-dimensional trajectories. To achieve precise key execution coupled with expressive musical performance, we design a composite reward function that integrates task-specific accuracy, audio fidelity, and high-level semantic feedback from a large language model (LLM) oracle. The LLM oracle assesses musical expressiveness and stylistic nuances, enabling dynamic, hand-specific reward adjustments. Further augmented by a residual inverse-kinematics refinement policy, PANDORA achieves state-of-the-art performance in the ROBOPIANIST environment, significantly outperforming baselines in both precision and expressiveness. Ablation studies validate the critical contributions of diffusion-based denoising and LLM-driven semantic feedback in enhancing robotic musicianship. Videos available at: https://taco-group.github.io/PANDORA

翻译：本文提出PANDORA——一种专为灵巧机器人钢琴演奏设计的新型扩散策略学习框架。该方法采用基于FiLM全局调节增强的条件U-Net架构，通过迭代去噪将含噪声的动作序列转化为平滑的高维轨迹。为实现精确琴键执行与富有表现力的音乐演奏相结合，我们设计了复合奖励函数，整合了任务特定精度、音频保真度以及来自大型语言模型（LLM）预言机的高层语义反馈。LLM预言机评估音乐表现力与风格细微差异，支持动态的、针对特定手部的奖励调整。通过残差逆运动学细化策略的进一步强化，PANDORA在ROBOPIANIST环境中实现了最先进的性能，在精确度与表现力方面均显著超越基线方法。消融实验验证了基于扩散的去噪机制与LLM驱动的语义反馈对提升机器人音乐演奏能力的关键贡献。演示视频见：https://taco-group.github.io/PANDORA