Augmenting Vision with Radar for All-weather Geo-localization without a Prior HD Map

Abstract

Accurate and robust geo-localization in all-weather conditions is essential for enabling autonomous vehicles and delivery robots to offer uninterrupted mobility services in the real world. In this paper, we propose the first camera and radar fusion based geo-localisation method that is robust to all-weather conditions. The core of the proposed method is to leverage the rich semantics information in images and sensing consistency in radars across all-weather. Our proposed method surpasses the state of the art camera-based and LiDAR-camera based methods in inclement weather conditions, shown by extensive comparative experiments. Notably, our approach requires only an open accessible map, eliminating the need for high-definition maps and offering a cost-effective solution for geo-localizing or globally localizing autonomous vehicles in any weather condition. Our code and trained model will be released publicly.