PMG: Parameterized Motion Generator for Human-like Locomotion Control

TL;DR

This paper introduces PMG, a real-time, parameterized motion generator for humanoid robots that produces natural, human-like locomotion and responds accurately to high-dimensional control inputs, facilitating practical deployment and sim-to-real transfer.

Contribution

The paper presents a novel parameterized motion generator that synthesizes reference trajectories from compact data and high-dimensional commands, improving adaptability and robustness in humanoid locomotion control.

Findings

PMG produces natural, human-like locomotion.

PMG responds precisely to high-dimensional control inputs.

PMG enables efficient sim-to-real transfer.

Abstract

Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In particular, while low-level motion tracking and trajectory-following controllers are mature, whole-body reference-guided methods are difficult to adapt to higher-level command interfaces and diverse task contexts: they require large, high-quality datasets, are brittle across speed and pose regimes, and are sensitive to robot-specific calibration. To address these limitations, we propose the Parameterized Motion Generator (PMG), a real-time motion generator grounded in an analysis of human motion structure that synthesizes reference trajectories using only a compact set of parameterized motion data together with high-dimensional control commands. Combined with an imitation-learning pipeline and an optimization-based sim-to-real motor parameter identification module, we validate the complete approach on our humanoid prototype ZERITH Z1 and show that, within a single integrated system, PMG produces natural, human-like locomotion, responds precisely to high-dimensional control inputs-including VR-based teleoperation-and enables efficient, verifiable sim-to-real transfer. Together, these results establish a practical, experimentally validated pathway toward natural and deployable humanoid control. Website: https://pmg-icra26.github.io/