HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914361463799808 |
|---|---|
| author | Chen, Yizhi Zhang, Zheng Cao, Zhanxiang Chen, Yihe Fu, Shengcheng Yan, Liyun Zhang, Yang Liu, Jiali Li, Haoyang Gao, Yue |
| author_facet | Chen, Yizhi Zhang, Zheng Cao, Zhanxiang Chen, Yihe Fu, Shengcheng Yan, Liyun Zhang, Yang Liu, Jiali Li, Haoyang Gao, Yue |
| contents | Controlling soccer robots involves multi-time-scale decision-making, which requires balancing long-term tactical planning and short-term motion execution. Traditional end-to-end reinforcement learning (RL) methods face challenges in complex dynamic environments. This paper proposes HierKick, a vision-guided soccer robot control framework based on dual-frequency hierarchical RL. The framework adopts a hierarchical control architecture featuring a 5 Hz high-level policy that integrates YOLOv8 for real-time detection and selects tasks via a coach model, and a pre-trained 50 Hz low-level controller for precise joint control. Through this architecture, the framework achieves the four steps of approaching, aligning, dribbling, and kicking. Experimental results show that the success rates of this framework are 95.2\% in IsaacGym, 89.8\% in Mujoco, and 80\% in the real world. HierKick provides an effective hierarchical paradigm for robot control in complex environments, extendable to multi-time-scale tasks, with its modular design and skill reuse offering a new path for intelligent robot control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00948 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control Chen, Yizhi Zhang, Zheng Cao, Zhanxiang Chen, Yihe Fu, Shengcheng Yan, Liyun Zhang, Yang Liu, Jiali Li, Haoyang Gao, Yue Robotics Controlling soccer robots involves multi-time-scale decision-making, which requires balancing long-term tactical planning and short-term motion execution. Traditional end-to-end reinforcement learning (RL) methods face challenges in complex dynamic environments. This paper proposes HierKick, a vision-guided soccer robot control framework based on dual-frequency hierarchical RL. The framework adopts a hierarchical control architecture featuring a 5 Hz high-level policy that integrates YOLOv8 for real-time detection and selects tasks via a coach model, and a pre-trained 50 Hz low-level controller for precise joint control. Through this architecture, the framework achieves the four steps of approaching, aligning, dribbling, and kicking. Experimental results show that the success rates of this framework are 95.2\% in IsaacGym, 89.8\% in Mujoco, and 80\% in the real world. HierKick provides an effective hierarchical paradigm for robot control in complex environments, extendable to multi-time-scale tasks, with its modular design and skill reuse offering a new path for intelligent robot control. |
| title | HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.00948 |