PMG: Parameterized Motion Generator for Human-like Locomotion Control

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Han, Chenxi, Min, Yuheng, Huang, Zihao, Hong, Ao, Liu, Hang, Cheng, Yi, Liu, Houde
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917290128179200
author Han, Chenxi
Min, Yuheng
Huang, Zihao
Hong, Ao
Liu, Hang
Cheng, Yi
Liu, Houde
author_facet Han, Chenxi
Min, Yuheng
Huang, Zihao
Hong, Ao
Liu, Hang
Cheng, Yi
Liu, Houde
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2602_12656
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PMG: Parameterized Motion Generator for Human-like Locomotion Control
Han, Chenxi
Min, Yuheng
Huang, Zihao
Hong, Ao
Liu, Hang
Cheng, Yi
Liu, Houde
Robotics
Artificial Intelligence
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/
title PMG: Parameterized Motion Generator for Human-like Locomotion Control
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2602.12656