MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
This work addresses the challenge of enabling humanoid robots to perform diverse, human-like locomotion skills from example data, which is important for natural human-robot interaction.
MuGen introduces a data-driven framework for humanoid robots to learn and execute multi-skill locomotion from human motion data, achieving expressive and accurate motion tracking and mimicry.
This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perform expressive motions like humans under the guidance of example motion sequences. To achieve this, we employ vector-quantized autoencoders (VQ-VAEs) trained with model-based reinforcement learning, resulting in a generative representation of locomotion that captures key patterns of human motion from hours of heterogeneous human performance data. We employ a teacher-student learning framework and develop a new policy distillation strategy to enable a deployable student policy learning this efficient latent representation. This policy allows the robot to track and mimic unseen human motions and further enables the robot to reuse the learned latent space for other tasks. We demonstrate the effectiveness of our framework through a diverse set of motions and accurate execution.