HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation

Abstract

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.

References in corpus (10)

• Learning agile and dynamic motor skills for legged robots
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
• Skeleton-Aware Networks for Deep Motion Retargeting
• Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
• Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
• Learning Bipedal Walking for Humanoids with Current Feedback
• Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running
• Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer
• Benchmarking Potential Based Rewards for Learning Humanoid Locomotion
• Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors

Cited by in corpus (3)

• Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey
• AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
• Humanoid Robot Running Through Random Stepping Stones and Jumping Over Obstacles: Step Adaptation Using Spring-Mass Trajectories