Reproduce “A Hierarchical, Model-Based System for High-Performance Humanoid Soccer” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Quanyou Wang, Mingzhang Zhu, Ruochen Hou, Kay Gillespie, Alvin Zhu, Shiqi Wang, Yicheng Wang, Gaberiel I. Fernandez and 11 more
Researchers from UCLA developed ARTEMIS, an integrated adult-sized humanoid robot system featuring novel hardware and a hierarchical, model-based software stack, which secured victory at the RoboCup 2024 Adult-Sized Humanoid Soccer Competition by enabling dynamic locomotion, powerful in-gait kicks, and robust autonomous gameplay.
Key insights
- A tightly coupled, hierarchical, model-based integration of hardware and software components is critical for achieving high-performance autonomous behavior in dynamic, adversarial environments.
- Powerful and accurate in-gait kicks can be achieved without interrupting locomotion by combining proprioceptive QDD actuators, a specialized foot design, and a mid-swing kicking module.
- Robust and stable pose estimation, perception, and collision-aware navigation in challenging, dynamic environments benefit from combining optimized deep learning with geometric clustering and model predictive control.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.