ReFeree

[IEEE RA-L] This repository is the official code for ReFeree: Radar-Based Lightweight and Robust Localization Using Feature and Free space.

Hogyun Kim*, Byunghee Choi*, Euncheol Choi, Younggun Cho^†

(* represents equal contribution.)

Spatial AI and Robotics Lab (SPARO)

News

• [September, 2024] Now, Cpp version's ReFeree code is released!!
• [September, 2024] Now, ReFeree-Radar-SLAM is released!!
• [September, 2024] Now, Python version's ReFeree code is released!!
• [September, 2024] ReFeree is accepted in RA-L!!

Note

• ReFeree can be integrated with various Radar odometry.
  • Integrated with Yeti-Odometry: ReFeree-Radar-SLAM

What is the ReFeree?

• ReFeree is a radar-based lightweight and robust global descriptor utilizing features and free space.
• ReFeree achieves rotational invariance and lightweight by selecting a one-dimensional ring-shaped description and robustness by mitigating the impact of false detection utilizing opposite noise characteristics between free space and feature.

  

How to use the ReFeree?

• Python version

  $ git clone https://github.com/sparolab/ReFeree.git
  $ cd python
  $ python3 test.py
  

• Cpp version

   $ git clone https://github.com/sparolab/ReFeree.git
   $ cd cpp
   $ mkdir build
   $ cd build
   $ cmake ..
   $ make
   $ ./test_referee
  

Supplementary

• Arxiv
• Paper
• Video
• Project page

Main Contribution

• Hogyun Kim
• Byunghee Choi
• Euncheol Choi
• Younggun Cho

Special Thanks

• SARAH H. CEN
• Keenan Burnett

Citation

@article{kim2024referee,
  title={ReFeree: Radar-Based Lightweight and Robust Localization using Feature and Free space},
  author={Kim, Hogyun and Choi, Byunghee and Choi, Euncheol and Cho, Younggun},
  journal={IEEE Robotics and Automation Letters},
  year={2024},
  publisher={IEEE}
}

Contact

• Hogyun Kim (hg.kim@inha.edu)
• Byunghee Choi (bhbhchoi@inha.edu)

License

• For academic usage, the code is released under the BSD 3.0 license. For any commercial purpose, please contact the authors.