mlsanityData to 14 Oct 2026

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

arXiv 2603.00948 ↗First posted 1 Mar 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 32 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

15 of 32 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids27 Feb
  2. 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning29 Oct
  3. 2024RobocupGym: A challenging continuous control benchmark in Robocup3 Jul
  4. 2024Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning3 May

Other references · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 150
  3. 2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 48
  4. 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 33
  5. 2025Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewardscited by 32
  6. 2023Predictable MDP Abstraction for Unsupervised Model-Based RLcited by 8
  7. 2016Deep Reinforcement Learning for Tensegrity Robot Locomotioncited by 7
  8. 2023Designing a skilled soccer team for RoboCup: exploring skill-set-primitives through reinforcement learningcited by 6
  9. 2024Towards Equitable Agile Research and Development of AI and Roboticscited by 2
  10. 2024Mastering Agile Jumping Skills from Simple Practices with Iterative Learning Controlcited by 2
  11. 2021PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots
  2. 2025Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams
  3. 2026RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
  4. 2025SoccerDiffusion: Toward Learning End-to-End Humanoid Robot Soccer from Gameplay Recordings
  5. 2025Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments
  6. 2026Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning ↗
  7. 2025Dribble Master: Learning Agile Humanoid Dribbling through Legged Locomotion
  8. 2026Reinforcement Learning Enabled Adaptive Multi-Task Control for Bipedal Soccer Robots