soccerbot: Humanoid robot learns soccer skills zero-shot
What happened
Haoyu Shao and other authors published a paper proposing a hierarchical reinforcement learning framework called soccerbot: it distills a structured latent motion prior from large-scale human soccer motion capture data, constrains policy learning within a dynamically feasible motion manifold, enables a single skill-conditioned policy to uniformly learn moving, dribbling, trapping, and kicking, and maintains human-like motions and smooth transitions during skill switching. The authors state that, combined with a simulation design oriented toward robustness, the framework transfers zero-shot to the Unitree G1 humanoid robot and completes the full set of soccer skills in a real environment, exhibiting agile, natural, and robust execution. The above real-environment performance comes from the paper authors' description.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROsoccerbot: Learning Humanoid Soccer Skills with Latent Motion Priors
The authors propose soccerbot, a hierarchical reinforcement learning framework that distills a structured latent motion prior from large-scale human soccer motion capture data, constraining policy learning within a dynamically feasible motion manifold. A single skill-conditioned policy thereby learns moving, dribbling, trapping, and kicking in a unified way, while maintaining human-like motion and fluid transitions during skill switching. After robustness-oriented simulation design, the framework transfers zero-shot to the Unitree G1 humanoid robot, completing the full soccer skill set in real-world environments.
Activity for this event
- Current
- 3
- Peak
- 10Nov 5 14:00
- Past 24 hours
- -49%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.