Research

Paper

AI LLM March 25, 2026

SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating

Authors

Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang, Donghan Koo

Abstract

Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physical hallucinations, producing motion trajectories that are physically infeasible to track with a downstream motion tracking controller or unsafe for real-world deployment. These failures often arise from the lack of explicit physics-aware objectives for real-robot execution and become more severe under out-of-distribution (OOD) user inputs. Hence, we propose SafeFlow, a text-driven humanoid whole-body control framework that combines physics-guided motion generation with a 3-Stage Safety Gate driven by explicit risk indicators. SafeFlow adopts a two-level architecture. At the high level, we generate motion trajectories using Physics-Guided Rectified Flow Matching in a VAE latent space to improve real-robot executability, and further accelerate sampling via Reflow to reduce the number of function evaluations (NFE) for real-time control. The 3-Stage Safety Gate enables selective execution by detecting semantic OOD prompts using a Mahalanobis score in text-embedding space, filtering unstable generations via a directional sensitivity discrepancy metric, and enforcing final hard kinematic constraints such as joint and velocity limits before passing the generated trajectory to a low-level motion tracking controller. Extensive experiments on the Unitree G1 demonstrate that SafeFlow outperforms prior diffusion-based methods in success rate, physical compliance, and inference speed, while maintaining diverse expressiveness.

Metadata

arXiv ID: 2603.23983
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23983v1</id>\n    <title>SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating</title>\n    <updated>2026-03-25T06:24:16Z</updated>\n    <link href='https://arxiv.org/abs/2603.23983v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23983v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physical hallucinations, producing motion trajectories that are physically infeasible to track with a downstream motion tracking controller or unsafe for real-world deployment. These failures often arise from the lack of explicit physics-aware objectives for real-robot execution and become more severe under out-of-distribution (OOD) user inputs. Hence, we propose SafeFlow, a text-driven humanoid whole-body control framework that combines physics-guided motion generation with a 3-Stage Safety Gate driven by explicit risk indicators. SafeFlow adopts a two-level architecture. At the high level, we generate motion trajectories using Physics-Guided Rectified Flow Matching in a VAE latent space to improve real-robot executability, and further accelerate sampling via Reflow to reduce the number of function evaluations (NFE) for real-time control. The 3-Stage Safety Gate enables selective execution by detecting semantic OOD prompts using a Mahalanobis score in text-embedding space, filtering unstable generations via a directional sensitivity discrepancy metric, and enforcing final hard kinematic constraints such as joint and velocity limits before passing the generated trajectory to a low-level motion tracking controller. Extensive experiments on the Unitree G1 demonstrate that SafeFlow outperforms prior diffusion-based methods in success rate, physical compliance, and inference speed, while maintaining diverse expressiveness.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-03-25T06:24:16Z</published>\n    <arxiv:comment>Project Page: https://hanbyelcho.info/safeflow/</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Hanbyel Cho</name>\n    </author>\n    <author>\n      <name>Sang-Hun Kim</name>\n    </author>\n    <author>\n      <name>Jeonguk Kang</name>\n    </author>\n    <author>\n      <name>Donghan Koo</name>\n    </author>\n  </entry>"
}