ReFeree: Radar-based Lightweight and Robust Localization using Feature and Free space
IEEE Robotics and Automation Letters (RA-L)
Hogyun Kim*, Byunghee Choi*, Euncheol Choi, and Younggun Cho
(* means equally to this work)
Contribution
The proposed place recognition successfully identifies the correct loop in radar images abundant with multipath and speckle noise. In contrast, Radar Scan Context exhibits vulnerability to multipath, often leading to the identification of incorrect loops. Also, 42x1 shape of our lightweight descriptor enables us to perform the SLAM with Nvidia Jetson Nano in the Mulran dataset.
Video
Abstract
Place recognition plays an important role in achieving robust long-term autonomy. Real-world robots face a wide range of weather conditions (e.g. overcast, heavy rain, and snowing) and most sensors (i.e. camera, LiDAR) essentially functioning within or near-visible electromagnetic waves are sensitive to adverse weather conditions, making reliable localization difficult. In contrast, radar is gaining traction due to the electromagnetic waves, less affected by environmental changes and weather independence.
In this work, we propose a radar-based efficient, lightweight, and robust place recognition. We achieve 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. In addition, the initial heading can be estimated, which can assist in building a SLAM pipeline that combines odometry and registration, which takes into account onboard computing.
The proposed method was tested for rigorous validation across various scenarios (i.e. single session, multi-session, and different weather conditions). In particular, we validate our descriptor achieving reliable place recognition performance through the results of extreme environments that lacked structural information such as an OORD dataset.
Method
This figure represents our method's pipeline.
In the frontend, we perform feature extraction and generate descriptors: R-ReFeree for place recognition and A-ReFeree for initial heading estimation. In the backend, we obtain a radar map through place retrieval and pose graph optimization. The white square and blue squares on the radar image in the ReFeree module are range-wise block and angel-wise block respectively. And the white and blue squares that make up the range-wise block and angle-wise block represent feature and free space respectively, and the red square represents the farthest feature for a unit angle.
BibTex
@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}
}