仅靠运动模仿无法准确还原人体步态动力学，需加入力信息才可靠。
Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kinetics
- 用运动数据训练机器人步态，但缺少地面反作用力等动力学信息
- 不加力信息的模型在关节力矩上误差显著，与真实值偏差大
- 适合关注步态生物力学建模或康复应用的研究者参考
运动模仿学习（IL）在机器人和步态建模中日益广泛应用，但其在缺乏显式动力学信息的情况下能否恢复符合生物力学的关节力矩仍不明确。本研究对比了仅运动模仿（MOIL）与融合地面反作用力（GRF）和压力中心（CoP）的动力学感知模仿学习（KAIL）框架，并通过消融实验分析各动力学项贡献。实验使用一名非残疾参与者在0.9、1.2和1.5 m/s三个速度下的行走数据。尽管两者在运动学追踪精度上相当，但MOIL在GRF、CoP及关节力矩估计上相比逆向动力学参考值表现出明显更大的误差；而KAIL生成的动力学更符合生物力学实际。结果表明，仅依赖运动模仿的方法存在根本性局限，可能导致步态生物力学误判及其下游应用偏差。
原文摘要 · Abstract (English)
Motion imitation learning (IL) is increasingly used in robotics and human gait modeling, yet its ability to recover biomechanically consistent joint moments without explicit kinetic information remains unclear. In this study, we examined whether motion imitation alone can estimate reasonable biological joint moments. We compare motion-only IL (MOIL) against a kinetics-aware IL (KAIL) framework that incorporates ground reaction forces (GRF) and center of pressure (CoP) in imitation rewards, with an ablation study to examine the contribution of each kinetic term. Experiments were conducted using walking data from a non-disabled participant at three speeds (0.9, 1.2, and 1.5 m/s). While both MOIL and KAIL achieved comparable kinematic tracking accuracy, MOIL exhibited substantially larger errors in GRF, CoP, and joint moment estimates relative to inverse dynamics references. In contrast, KAIL produced kinetics more consistent with biomechanical values. These findings highlight a fundamental limitation of MOIL approaches, which may lead to erroneous interpretations of gait biomechanics and downstream applications by failing to estimate consistent human-like gait kinetics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。