发表机构
Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究系统比较了基于HyFyDy和MuJoCo的两种肌肉驱动模仿学习流程，发现HyFyDy的肌肉激活更接近实验EMG数据，更适于肌肉骨骼建模，但两者均需提升生理真实性。
AI 中文摘要
在这项工作中，我们对两种最先进的运动模仿强化学习（MIRL）流程进行了系统比较，一种基于SCONE/HyFyDy构建，另一种基于MuJoCo/MyoSim构建。HyFyDy通过详细的肌肉肌腱建模强调生理真实性，而MuJoCo则优先考虑计算效率和可扩展的策略学习。尽管近期工作已证明这两种流程都能以高保真度再现人体运动学，但它们是否能准确捕捉产生该运动的潜在神经肌肉行为仍不清楚。这一局限性对于机器人辅助设备的设计和控制尤为重要，因为在这些应用中，肌肉激活模式和代谢成本等结果指标常被用作优化目标。为了进行系统比较，我们的工作使用一组共同的人体运动捕捉和肌电图（EMG）测量数据对两种流程进行了对比。结果显示，虽然两种流程产生的运动学结果具有相对准确性，但HyFyDy的肌肉激活与实验EMG更为一致，这由HyFyDy和MuJoCo的肌肉激活平均合并（RMSE，r）值（分别为（0.164，0.4）和（0.344，0.11））所支持。尽管我们得出结论，HyFyDy更先进的生理真实性使其目前更适合肌肉骨骼建模，但两者都需要进一步发展，以将生理真实性引入GPU可并行化的仿真环境，并推进机器人辅助设备的设计。
英文摘要
In this work, we conduct a systematic comparison of two state-of-the-art motion-imitation reinforcement learning (MIRL) pipelines, one built on SCONE/HyFyDy and one built on MuJoCo/MyoSim. HyFyDy emphasizes physiological realism through detailed musculotendon modeling, while MuJoCo prioritizes computational efficiency and scalable policy learning. While recent work has demonstrated that both pipelines reproduce human kinematics with high fidelity, it remains unclear if they accurately capture the underlying neuromuscular behavior that produced the movement. This limitation is particularly important for robotic assistive-device design and control, where outcome measures such as muscle activation patterns and metabolic cost are often used as optimization targets. To conduct a systematic comparison, our work compares both pipelines using a common set of human motion-capture and electromyography (EMG) measurements. The results find that while both pipelines produce similar kinematics with relative accuracy, the muscle activations from HyFyDy are more aligned with the experimental EMG, as supported by the average pooled (RMSE, r) values for muscle activations from HyFyDy and MuJoCo: (0.164, 0.4) and (0.344, 0.11), respectively. While we conclude that the more advanced physiological realism of HyFyDy currently makes it more suitable for musculoskeletal modeling, both require further development to bring physiological realism to GPU-parallelizable simulation environments and advance robotic assistive device design.
Comments8 pages, 5 figures, 2 tables, submitted to ICRA 2027
