rhaeus/ufomap

UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown

UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown

UFOMap is an efficient probabilistic 3D mapping framework with an explicit representation of unknown space.

UFOMap with occupied space as colored voxels and unknown space as white transparent voxels. The free space is not visualized here.

Using UFOMap you will be able to create 3D volumetric maps, containing unknown/free/occupied space, similar to the one below in real-time. The UFOMap maps you create can be used for efficient path/trajectory planning, obstacle avoidance, reconstruction, and more.

Colored UFOMap constructed in real-time (2 Hz) at 2 mm voxel size.

Table of Contents

Please see the Wiki for how to install and use UFOMap.

1. Setup
2. Tutorials
3. ROS Tutorials
4. Advanced ROS Tutorials
5. Performance
6. Example Outputs
7. Data Repository
8. API

Credits

Paper

• IEEE
• ArXiv

Cite

If you use UFOMap in a scientific publication, please cite the following paper:

• Daniel Duberg and Patric Jensfelt, "UFOMap: An Efficient Probabilistic 3D Mapping Framework That Embraces the Unknown," in IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6411-6418, Oct. 2020, doi: 10.1109/LRA.2020.3013861.

@article{duberg2020ufomap,
  author={Daniel Duberg and Patric Jensfelt},
  journal={IEEE Robotics and Automation Letters}, 
  title={{UFOMap}: An Efficient Probabilistic {3D} Mapping Framework That Embraces the Unknown}, 
  year={2020},
  volume={5},
  number={4},
  pages={6411-6418},
  doi={10.1109/LRA.2020.3013861}
}

Videos

• YouTube Playlist