Dribble Master: Learning Agile Humanoid Dribbling through Legged Locomotion
Zhuoheng Wang, Jinyin Zhou, Qi Wu

TL;DR
This paper presents a two-stage curriculum learning approach for humanoid robots to learn agile soccer dribbling, combining simulation training with real-world transfer, and emphasizing active perception for effective ball control.
Contribution
Introduces a novel two-stage curriculum learning framework with a virtual camera model and heuristic rewards for realistic and adaptable humanoid dribbling skills.
Findings
Successful transfer of policies from simulation to real robot
Effective ball manipulation and agile dribbling behaviors achieved
Enhanced perception through active sensing strategies
Abstract
Humanoid soccer dribbling is a highly challenging task that demands dexterous ball manipulation while maintaining dynamic balance. Traditional rule-based methods often struggle to achieve accurate ball control due to their reliance on fixed walking patterns and limited adaptability to real-time ball dynamics. To address these challenges, we propose a two-stage curriculum learning framework that enables a humanoid robot to acquire dribbling skills without explicit dynamics or predefined trajectories. In the first stage, the robot learns basic locomotion skills; in the second stage, we fine-tune the policy for agile dribbling maneuvers. We further introduce a virtual camera model in simulation that simulates the field of view and perception constraints of the real robot, enabling realistic ball perception during training. We also design heuristic rewards to encourage active sensing,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobotic Locomotion and Control · Robot Manipulation and Learning · Human Motion and Animation
