Reproduce “Terrain-Indexed Motion Priors and Geometric Support for Extreme Humanoid Parkour” 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
Chenghao Sun, Youhao Lyu, Zizheng Li, Shuting Zhang, Ziyang Dong, Wenhao Cui
The authors train a humanoid parkour policy through privileged imitation, terrain-indexed adversarial motion priors, and geometric hand–knee support guidance, reducing but retaining the prior’s weight. The policy adapts support placement without an external skill label. In simulation, hybrid success is 96.34% versus 79.65% for a local baseline; limited-surface and hardware results do not establish general safety or reliability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.