CFEAR-Teach-and-Repeat: Fast and Accurate Radar-only Localization

TL;DR

CFEAR-TR is a radar-based localization method that achieves high accuracy and robustness in adverse weather, using a teach-and-repeat approach with a single spinning radar for autonomous navigation.

Contribution

This work introduces a novel radar-only localization pipeline that combines map alignment with recent live frames, achieving lidar-level accuracy in challenging conditions.

Findings

Localization accuracy as low as 0.117 m and 0.096°

Up to 63% improvement over previous methods

Operates at 29 Hz in real-time

Abstract

Reliable localization in prior maps is essential for autonomous navigation, particularly under adverse weather, where optical sensors may fail. We present CFEAR-TR, a teach-and-repeat localization pipeline using a single spinning radar, which is designed for easily deployable, lightweight, and robust navigation in adverse conditions. Our method localizes by jointly aligning live scans to both stored scans from the teach mapping pass, and to a sliding window of recent live keyframes. This ensures accurate and robust pose estimation across different seasons and weather phenomena. Radar scans are represented using a sparse set of oriented surface points, computed from Doppler-compensated measurements. The map is stored in a pose graph that is traversed during localization. Experiments on the held-out test sequences from the Boreas dataset show that CFEAR-TR can localize with an accuracy as low as 0.117 m and 0.096{\deg}, corresponding to improvements of up to 63% over the previous state of the art, while running efficiently at 29 Hz. These results substantially narrow the gap to lidar-level localization, particularly in heading estimation. We make the C++ implementation of our work available to the community.