README.md

---
license: apache-2.0
tags:
- robotics
- humanoid
---

# Click-and-Traverse: Collision-Free Humanoid Traversal in Cluttered Indoor Scenes

<p style="font-size: 1.2em;">
  <a href="https://axian12138.github.io/CAT/"><strong>Project Page</strong></a> | 
  <a href="https://github.com/GalaxyGeneralRobotics/Click-and-Traverse/"><strong>Code</strong></a> |
  <a href="https://arxiv.org/abs/2601.16035"><strong>Paper</strong></a> |
  <a href="https://www.youtube.com/watch?v=blek__Qf0Vc"><strong>Video Demo</strong></a>|
  <a href="https://huggingface.co/Axian12138/Click-and-Traverse"><strong>Models</strong></a>|
  <a href="https://huggingface.co/datasets/Axian12138/Click-and-Traverse/"><strong>Datasets</strong></a>
</p>

The system is designed for **general humanoid traversal tasks** requiring coordinated whole-body motion planning and collision avoidance.

---

## Key Capabilities

<table width="100%">
  <tr>
    <th width="50%">Full-Spatial Constraints</th>
    <th width="50%">Intricate Geometry Handling</th>
  </tr>
  <tr>
    <td valign="top">
      Indoor environments impose constraints at multiple spatial levels. Obstacles can appear simultaneously at the <strong>ground, lateral, and overhead</strong> levels, restricting humanoid motion in all spatial dimensions and requiring coordinated whole-body movement.
    </td>
    <td valign="top">
      The method handles <strong>complex and irregular obstacle geometries</strong> that commonly appear in real-world environments, going beyond simplified primitives such as cubes or regular polyhedra used in many prior benchmarks.
    </td>
  </tr>
</table>


<div align="center">
  <img 
    src="https://img.youtube.com/vi/blek__Qf0Vc/maxresdefault.jpg"
    style="width:100%; max-width:1000px; height:auto;"
    alt="Collision-Free Humanoid Traversal Demo"
  />
</div>

---

## Citation

```bibtex
@misc{xue2026collisionfreehumanoidtraversalcluttered,
  title        = {Collision-Free Humanoid Traversal in Cluttered Indoor Scenes},
  author       = {Xue, Han and Liang, Sikai and Zhang, Zhikai and Zeng, Zicheng and Liu, Yun and Lian, Yunrui and Wang, Jilong and Liu, Qingtao and Shi, Xuesong and Li, Yi},
  year         = {2026},
  eprint       = {2601.16035},
  archivePrefix= {arXiv},
  primaryClass = {cs.RO},
  url          = {https://arxiv.org/abs/2601.16035}
}