发表机构
KAIST; DGIST（韩国科学技术院; 大邱庆北科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人钢琴演奏缺乏动态评估的问题，提出CANTABILE框架，通过速度感知策略与双重奖励提升表现力，在EXPRESSIVE-51上速度F1从0.06升至0.34，并支持运行时强度控制。
AI 中文摘要
机器人钢琴演奏已成为灵巧双手操作的标准基准，然而其进展几乎完全以音符准确性来衡量——即按下哪些键（音高）以及何时按下（起始时间）——而表现力演奏所必需的音乐动态既未得到奖励，也未得到评估。我们提出CANTABILE，一个面向机器人钢琴演奏的动态感知框架，其（i）通过将策略条件设定于即将到来的速度目标，并将每个键在起始时刻的角速度映射回MIDI速度，从而闭合乐谱到接触的回路；（ii）将速度保真奖励与起始时间覆盖奖励相结合，使得无法通过省略困难音符来改善动态表现；（iii）通过一个alpha缩放的、仅手指的残差策略来细化冻结的动态感知基础策略，将击键强度适应局部化于标称音符执行之外。在EXPRESSIVE-51（RoboPianist中一个动态丰富的51首歌曲子集）上，CANTABILE将速度F1分数——在±8 MIDI速度容差内联合衡量音高、起始时间和强度——从RoboPianist基线的0.06提升至0.34，改善了全部51首歌曲，将匹配音符的速度误差减半以上，并将与参考音频的log-mel距离降低了8%。强度随机化训练还实现了无需重新训练即可在运行时控制演奏强度。
英文摘要
Robotic piano playing has emerged as a standard benchmark for dexterous bimanual manipulation, yet progress on it has been measured almost entirely by note accuracy -- which keys are pressed (pitch) and when (onset) -- leaving the musical dynamics essential for expressive performance neither rewarded nor evaluated. We propose CANTABILE, a dynamics-aware framework for robotic piano performance that (i) closes the score-to-contact loop by conditioning the policy on upcoming velocity goals and mapping each key's angular velocity at onset back to MIDI velocity, (ii) couples a velocity-fidelity reward with an onset-coverage reward, so that dynamics cannot be improved by omitting difficult notes, and (iii) refines a frozen dynamics-aware base policy with an alpha-scaled, finger-only residual that localizes strike-intensity adaptation away from nominal note execution. On EXPRESSIVE-51, a dynamics-rich 51-song subset of RoboPianist, CANTABILE raises Velocity F1 -- jointly measuring pitch, onset, and intensity within a +/-8 MIDI-velocity tolerance -- from 0.06 to 0.34 over the RoboPianist baseline, improves all 51 songs, more than halves matched-note velocity error, and reduces log-mel distance to reference audio by 8%. Intensity-randomized training further enables runtime control of performance intensity without retraining.
Comments9 pages, 10 figures, 4 tables. Under review
