Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain

TL;DR

This paper introduces Free-T2M, a frequency-domain approach for text-to-motion generation in humanoid robots, significantly improving motion quality and robustness by separating semantic planning and detailed execution phases.

Contribution

It proposes a novel frequency-domain framework with stage-specific consistency alignment and a temporal-adaptive module, enhancing the stability and accuracy of robot motion synthesis from language.

Findings

Reduces FID from 0.152 to 0.060 on StableMoFusion baseline.

Improves semantic correctness and motion robustness.

Establishes a new state-of-the-art in diffusion-based T2M tasks.

Abstract

Enabling humanoid robots to synthesize complex, physically coherent motions from natural language commands is a cornerstone of autonomous robotics and human-robot interaction. While diffusion models have shown promise in this text-to-motion (T2M) task, they often generate semantically flawed or unstable motions, limiting their applicability to real-world robots. This paper reframes the T2M problem from a frequency-domain perspective, revealing that the generative process mirrors a hierarchical control paradigm. We identify two critical phases: a semantic planning stage, where low-frequency components establish the global motion trajectory, and a fine-grained execution stage, where high-frequency details refine the movement. To address the distinct challenges of each phase, we introduce Frequency enhanced text-to-motion (Free-T2M), a framework incorporating stage-specific frequency-domain consistency alignment. We design a frequency-domain temporal-adaptive module to modulate the alignment effects of different frequency bands. These designs enforce robustness in the foundational semantic plan and enhance the accuracy of detailed execution. Extensive experiments show our method dramatically improves motion quality and semantic correctness. Notably, when applied to the StableMoFusion baseline, Free-T2M reduces the FID from 0.152 to 0.060, establishing a new state-of-the-art within diffusion architectures. These findings underscore the critical role of frequency-domain insights for generating robust and reliable motions, paving the way for more intuitive natural language control of robots.