The pursuit of humanoid athletic sprints is hindered by a scarcity of humanoid-viable kinematic reference data and the inability of existing frameworks to maintain stability during sprints. To overcome these limitations, we introduce SPRINT, a novel framework driven by efficient, frequency-adaptive spectral priors. By characterizing the fundamental periodicity of human locomotion in the frequency domain using a reference library of five discrete motion sequences, these priors generate kinematically feasible joint trajectories across a broad velocity spectrum, successfully extrapolating to speeds that exceed the reference distribution. Guided by these pretrained priors, the SPRINT policy achieves zero-shot sim-to-real transfer in field experiments on the Unitree G1 platform, reaching a peak sprinting velocity of 6 m/s and demonstrating seamless gait transitions while preserving biomimetic naturalness. Ultimately, this work establishes frequency-adaptive spectral priors as a highly data-efficient foundation for humanoid athletic sprints. The project page is available at https://anonymous.4open.science/w/SPRINT-138A/.
Cite
@article{arxiv.2605.28549,
title = {SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints},
author = {Yantong Wei and Kaihong Huang and Hainan Pan and Jiawei Luo and Jiawei Zhou and Ziyan Mai and Zhiwen Zeng and Yaonan Wang and Huimin Lu},
journal= {arXiv preprint arXiv:2605.28549},
year = {2026}
}