dorsal/arxiv
View SchemaHiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids
| Authors | Shaoting Zhu, Ziwen Zhuang, Mengjie Zhao, Kun-Ying Lee, Hang Zhao |
|---|---|
| Categories | |
| ArXiv ID | 2601.07718vv1 |
| URL | https://arxiv.org/abs/2601.07718 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Achieving robust humanoid hiking in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception. However, integrating exteroception remains a significant challenge: mapping-based methods suffer from state estimation drift; for instance, LiDAR-based methods do not handle torso jitter well. Existing end-to-end approaches often struggle with scalability and training complexity; specifically, some previous works using virtual obstacles are implemented case-by-case. In this work, we present \textit{Hiking in the Wild}, a scalable, end-to-end parkour perceptive framework designed for robust humanoid hiking. To ensure safety and training stability, we introduce two key mechanisms: a foothold safety mechanism combining scalable \textit{Terrain Edge Detection} with \textit{Foot Volume Points} to prevent catastrophic slippage on edges, and a \textit{Flat Patch Sampling} strategy that mitigates reward hacking by generating feasible navigation targets. Our approach utilizes a single-stage reinforcement learning scheme, mapping raw depth inputs and proprioception directly to joint actions, without relying on external state estimation. Extensive field experiments on a full-size humanoid demonstrate that our policy enables robust traversal of complex terrains at speeds up to 2.5 m/s. The training and deployment code is open-sourced to facilitate reproducible research and deployment on real robots with minimal hardware modifications.
{
"annotation_id": "394905f4-5867-47f1-bc64-dd422f3f2fb7",
"date_created": "2026-02-17T05:53:12.529000Z",
"date_modified": "2026-02-17T05:53:12.529000Z",
"file_hash": "3e1d48773741952e5e20fb704ecf53d2e56ca44dfc96e62ea7fad1b4341902f4",
"private": false,
"record": {
"abstract": "Achieving robust humanoid hiking in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception. However, integrating exteroception remains a significant challenge: mapping-based methods suffer from state estimation drift; for instance, LiDAR-based methods do not handle torso jitter well. Existing end-to-end approaches often struggle with scalability and training complexity; specifically, some previous works using virtual obstacles are implemented case-by-case. In this work, we present \\textit{Hiking in the Wild}, a scalable, end-to-end parkour perceptive framework designed for robust humanoid hiking. To ensure safety and training stability, we introduce two key mechanisms: a foothold safety mechanism combining scalable \\textit{Terrain Edge Detection} with \\textit{Foot Volume Points} to prevent catastrophic slippage on edges, and a \\textit{Flat Patch Sampling} strategy that mitigates reward hacking by generating feasible navigation targets. Our approach utilizes a single-stage reinforcement learning scheme, mapping raw depth inputs and proprioception directly to joint actions, without relying on external state estimation. Extensive field experiments on a full-size humanoid demonstrate that our policy enables robust traversal of complex terrains at speeds up to 2.5 m/s. The training and deployment code is open-sourced to facilitate reproducible research and deployment on real robots with minimal hardware modifications.",
"arxiv_id": "2601.07718",
"authors": [
"Shaoting Zhu",
"Ziwen Zhuang",
"Mengjie Zhao",
"Kun-Ying Lee",
"Hang Zhao"
],
"categories": [
"cs.RO",
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids",
"url": "https://arxiv.org/abs/2601.07718",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "3292235c-b1f6-4ed5-87f5-1440679e5cac",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}