外观
论文arXiv 2609.219091 个月前
超越运动学：面向肌肉驱动模仿学习的仿真保真度基准测试
原文链接：Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning（arXiv 2609.21909 · 发布日期：2026-09-18）
Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning
比较SCONE/HyFyDy与MuJoCo/MyoSim两条MIRL流水线，在人类动捕和EMG上评估运动学与肌肉激活保真度。
核心要点
- 问题在于两类流水线虽能高保真复现运动学，但神经肌肉行为准确性仍不清楚。
- 方法是在同一组人类运动捕捉和EMG测量上，系统比较HyFyDy与MuJoCo流水线。
- 结果显示二者运动学相近；HyFyDy肌肉激活更贴近实验EMG，RMSE/r为0.164/0.4。
- MuJoCo对应RMSE/r为0.344/0.11；两者仍需发展GPU并行仿真中的生理真实感。
验证范围与局限：验证范围为两条MIRL流水线在人类运动捕捉与EMG测量上的比较。
英文摘要 (Abstract)
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.
作者：Ayah G. Ahmad, Claire E. Borden, Maegan Tucker
来源
本页事实对应的公开页面，以原文为准。