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

TL;DR

This study compares radar-only, lidar-only, and cross-modal radar-to-lidar localization systems across various weather conditions, finding lidar remains most accurate even in snowstorms, but radar offers advantages in map size and potential robustness.

Contribution

It provides an extensive empirical comparison of radar and lidar localization systems under diverse weather conditions, challenging assumptions about lidar sensitivity to precipitation.

Findings

Lidar-only system achieved the best accuracy even during snowstorms.

Radar-only system was competitive with smaller maps.

Radar sensors have potential for improvement and robustness in extreme weather.

Abstract

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