HierKick: Hierarchical Reinforcement Learning for Vision-Guided Soccer Robot Control

TL;DR

HierKick introduces a hierarchical reinforcement learning framework for vision-guided soccer robots, effectively managing multi-time-scale decisions and demonstrating high success rates in simulation and real-world tests.

Contribution

The paper presents a novel dual-frequency hierarchical RL architecture integrating real-time vision detection and task-specific control for soccer robots.

Findings

Achieved over 95% success in IsaacGym simulation.

Attained nearly 90% success in Mujoco simulation.

Reached 80% success rate in real-world experiments.

Abstract

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.