Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.05310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917249414070272 |
|---|---|
| author | Kong, Jipeng Liu, Xinzhe Lin, Yuhang Han, Jinrui Schwertfeger, Sören Bai, Chenjia Li, Xuelong |
| author_facet | Kong, Jipeng Liu, Xinzhe Lin, Yuhang Han, Jinrui Schwertfeger, Sören Bai, Chenjia Li, Xuelong |
| contents | Soccer presents a significant challenge for humanoid robots, demanding tightly integrated perception-action capabilities for tasks like perception-guided kicking and whole-body balance control. Existing approaches suffer from inter-module instability in modular pipelines or conflicting training objectives in end-to-end frameworks. We propose Perception-Action integrated Decision-making (PAiD), a progressive architecture that decomposes soccer skill acquisition into three stages: motion-skill acquisition via human motion tracking, lightweight perception-action integration for positional generalization, and physics-aware sim-to-real transfer. This staged decomposition establishes stable foundational skills, avoids reward conflicts during perception integration, and minimizes sim-to-real gaps. Experiments on the Unitree G1 demonstrate high-fidelity human-like kicking with robust performance under diverse conditions-including static or rolling balls, various positions, and disturbances-while maintaining consistent execution across indoor and outdoor scenarios. Our divide-and-conquer strategy advances robust humanoid soccer capabilities and offers a scalable framework for complex embodied skill acquisition. The project page is available at https://soccer-humanoid.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05310 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework Kong, Jipeng Liu, Xinzhe Lin, Yuhang Han, Jinrui Schwertfeger, Sören Bai, Chenjia Li, Xuelong Robotics Soccer presents a significant challenge for humanoid robots, demanding tightly integrated perception-action capabilities for tasks like perception-guided kicking and whole-body balance control. Existing approaches suffer from inter-module instability in modular pipelines or conflicting training objectives in end-to-end frameworks. We propose Perception-Action integrated Decision-making (PAiD), a progressive architecture that decomposes soccer skill acquisition into three stages: motion-skill acquisition via human motion tracking, lightweight perception-action integration for positional generalization, and physics-aware sim-to-real transfer. This staged decomposition establishes stable foundational skills, avoids reward conflicts during perception integration, and minimizes sim-to-real gaps. Experiments on the Unitree G1 demonstrate high-fidelity human-like kicking with robust performance under diverse conditions-including static or rolling balls, various positions, and disturbances-while maintaining consistent execution across indoor and outdoor scenarios. Our divide-and-conquer strategy advances robust humanoid soccer capabilities and offers a scalable framework for complex embodied skill acquisition. The project page is available at https://soccer-humanoid.github.io/. |
| title | Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.05310 |