Transferring human motion skills to humanoid robots remains a significant challenge. In this study, we introduce a Wasserstein adversarial imitation learning system, allowing humanoid robots to replicate natural whole-body locomotion patterns and execute seamless transitions by mimicking human motions. First, we present a unified primitive-skeleton motion retargeting to mitigate morphological differences between arbitrary human demonstrators and humanoid robots. An adversarial critic component is integrated with Reinforcement Learning (RL) to guide the control policy to produce behaviors aligned with the data distribution of mixed reference motions. Additionally, we employ a specific Integral Probabilistic Metric (IPM), namely the Wasserstein-1 distance with a novel soft boundary constraint to stabilize the training process and prevent mode collapse. Our system is evaluated on a full-sized humanoid JAXON in the simulator. The resulting control policy demonstrates a wide range of locomotion patterns, including standing, push-recovery, squat walking, human-like straight-leg walking, and dynamic running. Notably, even in the absence of transition motions in the demonstration dataset, robots showcase an emerging ability to transit naturally between distinct locomotion patterns as desired speed changes.

翻译：将人类运动技能迁移至人形机器人仍是一项重大挑战。本研究提出一种Wasserstein对抗模仿学习系统，使机器人能够通过模仿人类动作复现全身自然运动模式并实现无缝过渡。首先，我们引入一种统一的原始骨架运动重定向方法，以消除任意人类演示者与人形机器人之间的形态差异。通过将对抗评判器与强化学习（RL）集成，引导控制策略生成与混合参考运动数据分布一致的行为。此外，我们采用特定积分概率度量（IPM），即带有新型软边界约束的Wasserstein-1距离，以稳定训练过程并防止模式崩塌。在仿真环境中，该策略在全尺寸人形机器人JAXON上完成评估。最终控制策略展现出丰富运动模式，包括站立、推挤恢复、蹲走、类人直腿行走及动态奔跑。值得注意的是，即使演示数据集缺失过渡动作，机器人仍能按期望速度变化，自发呈现出在不同运动模式间自然过渡的能力。