Learning Soccer Skills for Humanoid Robots

A Progressive Perception-Action Framework (PAiD)

Authors:
Jipeng Kong, Xinzhe Liu, Yuhang Lin, Jinrui Han, Sören Schwertfeger, Chenjia Bai, Xuelong Li

📄 Project Page: https://soccer-humanoid.github.io/

---

Overview

This repository is for the paper Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework.

Soccer is a challenging task for humanoid robots, requiring tightly integrated perception and whole-body control. We propose PAiD (Perception-Action integrated Decision-making), a progressive framework with three stages: motion-skill acquisition via human motion tracking, lightweight perception-action integration for positional generalization, and physics-aware sim-to-real transfer. Experiments on the Unitree G1 show robust, human-like kicking across static/rolling balls, varied positions, disturbances, and indoor/outdoor scenarios.

---

Code Release

We are preparing the official release, and the code will be published in this repository.

---

Citation

If you find this work useful in your research, please consider citing:

@misc{kong2026learningsoccerskillshumanoid,
  title={Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework},
  author={Jipeng Kong and Xinzhe Liu and Yuhang Lin and Jinrui Han and Sören Schwertfeger and Chenjia Bai and Xuelong Li},
  year={2026},
  eprint={2602.05310},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2602.05310}
}

---

Contact

For questions or collaborations, please open an issue or contact the authors.