Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lu, Yidan, Zhong, Yichao, Zhao, Liu, Li, Wanyue, Lu, Peng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917508257153024
author Lu, Yidan
Zhong, Yichao
Zhao, Liu
Li, Wanyue
Lu, Peng
author_facet Lu, Yidan
Zhong, Yichao
Zhao, Liu
Li, Wanyue
Lu, Peng
contents We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 humanoid robot, validated on physical hardware without any explicit mode-switching command at deployment. The framework extends Adversarial Motion Priors (AMP) by replacing the conventional global reference distribution with a state-dependent gate that routes each training transition to one of two discriminators: a dedicated recovery discriminator and a velocity-conditioned locomotion discriminator that jointly covers walking and running. The gate is defined by a single fixed threshold on projected gravity: the recovery discriminator is activated when body tilt exceeds approximately $37^\circ$ from vertical ($|g_z+1|>0.6$); otherwise the locomotion discriminator is used, with the normalized commanded velocity serving as a condition that selects the appropriate reference trajectory between walk and run clips. Only three LAFAN1 reference clips are required to regularize the complete behavior set. At deployment, a single frozen ONNX policy executes at 50\,Hz with no runtime mode logic; hardware experiments demonstrate successful recovery from both prone and supine falls and smooth walk-to-run transitions under the same controller.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18611
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors
Lu, Yidan
Zhong, Yichao
Zhao, Liu
Li, Wanyue
Lu, Peng
Robotics
We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 humanoid robot, validated on physical hardware without any explicit mode-switching command at deployment. The framework extends Adversarial Motion Priors (AMP) by replacing the conventional global reference distribution with a state-dependent gate that routes each training transition to one of two discriminators: a dedicated recovery discriminator and a velocity-conditioned locomotion discriminator that jointly covers walking and running. The gate is defined by a single fixed threshold on projected gravity: the recovery discriminator is activated when body tilt exceeds approximately $37^\circ$ from vertical ($|g_z+1|>0.6$); otherwise the locomotion discriminator is used, with the normalized commanded velocity serving as a condition that selects the appropriate reference trajectory between walk and run clips. Only three LAFAN1 reference clips are required to regularize the complete behavior set. At deployment, a single frozen ONNX policy executes at 50\,Hz with no runtime mode logic; hardware experiments demonstrate successful recovery from both prone and supine falls and smooth walk-to-run transitions under the same controller.
title Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors
topic Robotics
url https://arxiv.org/abs/2605.18611