Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Are We Ready for Radar to Replace Lidar in All-Weather Mapping and Localization?

About

We present an extensive comparison between three topometric localization systems: radar-only, lidar-only, and a cross-modal radar-to-lidar system across varying seasonal and weather conditions using the Boreas dataset. Contrary to our expectations, our experiments showed that our lidar-only pipeline achieved the best localization accuracy even during a snowstorm. Our results seem to suggest that the sensitivity of lidar localization to moderate precipitation has been exaggerated in prior works. However, our radar-only pipeline was able to achieve competitive accuracy with a much smaller map. Furthermore, radar localization and radar sensors still have room to improve and may yet prove valuable in extreme weather or as a redundant backup system. Code for this project can be found at: https://github.com/utiasASRL/vtr3

Keenan Burnett, Yuchen Wu, David J. Yoon, Angela P. Schoellig, Timothy D. Barfoot• 2022

Related benchmarks

TaskDatasetResultRank
LocalizationBoreas (sequences)
Lateral RMSE (m)0.048
22
OdometryBoreas (test)
Translational Error (%)1.97
8
LiDAR LocalizationBoreas Road Trip (Suburban Route)
Lateral RMSE (m)0.024
4
LiDAR LocalizationBoreas Road Trip (Industrial Route)
Lateral RMSE (m)0.021
4
LiDAR LocalizationBoreas Road Trip (Regional Route)
Lateral RMSE (m)0.033
4
Radar LocalizationBoreas Industrial
Longitude Error (m)0.08
4
SE(3) OdometryBoreas-RT (suburbs)
Translation Error (%)29
4
SE(3) OdometryBoreas-RT (industrial)
Translation Error (%)25
4
SE(3) OdometryBoreas-RT (urban)
Translation Error (%)0.49
4
SE(3) OdometryBoreas-RT (farm)
Translation Error (%)44
4
Showing 10 of 25 rows

Other info

Follow for update