cs.RONov 4, 2026

Playing Soccer Like Humans Do: Learning Versatile and Agile Humanoid Soccer via Latent Motion Priors

Authors: Haoyu Shao, Yunshen Wang, Jingze Zhang, Shaohang Zhu, Yong-Lu Li, Tianzhu Zhang, Baoxiong Jia, Siyuan Huang

Organizations: University of Science and Technology of China · State Key Laboratory of General Artificial Intelligence, BIGAI · Shanghai Jiao Tong University · Peking University

Abstract

Humanoid soccer requires a robot to seamlessly combine agile locomotion, ball manipulation, and impact-rich contact dynamics across a continuous, dynamic behavioral spectrum. Yet existing approaches either cover only a limited set of skills, or forego motion priors entirely and produce unnatural behaviors, leaving the combination of a unified skill set and human-like motion quality unaddressed. We present soccerbot, a hierarchical reinforcement learning framework that resolves both limitations through a structured latent motion prior distilled from large-scale human soccer motion capture data. By constraining policy learning within this dynamically plausible motion manifold, a single skill-conditioned policy naturally learns to perform moving, dribbling, trapping, and kicking in a unified formulation, while inherently producing human-like motion and fluid transitions during commanded skill switching. Augmented by robustness-oriented simulation design, soccerbot transfers zero-shot to the Unitree G1 humanoid robot, demonstrating agile, natural, and robust execution of the full soccer skill repertoire under real-world conditions.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SkillX: Unified Multi-Skill Policy Learning for Humanoid Soccer

    Sep 6, 2026Zhangchen Ye, Enxuan Ruan, Yifei Bao +10Robot Skill LearningHumanoid Robot Control

  2. Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library

    Sep 30, 2026Abu Hanif Muhammad Syarubany, Jaehyun Jang, Hwanhee Kim +3Humanoid Robot LocomotionRobot Skill Learning

  3. DAVIS: A Depth-Only End-to-End Active-Vision Framework for Humanoid Soccer Skills

    Sep 23, 2026Jiakang Jin, Yixiao Huo, Pengyuan Wang +12Robot Skill LearningHumanoid Robot Control