Robust Vehicle Localization and Tracking in Rain using Street Maps

TL;DR

This paper introduces Map-Fusion, a novel vehicle localization method that combines intermittent GPS, IMU, VO data, and street maps to improve accuracy in adverse weather and challenging environments.

Contribution

The paper presents a new fusion algorithm that enhances vehicle localization robustness by integrating map data with drifting odometry and GPS, especially in rain and tunnel conditions.

Findings

Map-Fusion reduces localization error compared to state-of-the-art VO and VIO methods.

Achieved 2.46m error in clear weather and 6.05m in rain over 150m routes.

Validated in diverse real-world environments and on a mobile robot in real-time.

Abstract

GPS-based vehicle localization and tracking suffers from unstable positional information commonly experienced in tunnel segments and in dense urban areas. Also, both Visual Odometry (VO) and Visual Inertial Odometry (VIO) are susceptible to adverse weather conditions that causes occlusions or blur on the visual input. In this paper, we propose a novel approach for vehicle localization that uses street network based map information to correct drifting odometry estimates and intermittent GPS measurements especially, in adversarial scenarios such as driving in rain and tunnels. Specifically, our approach is a flexible fusion algorithm that integrates intermittent GPS, drifting IMU and VO estimates together with 2D map information for robust vehicle localization and tracking. We refer to our approach as Map-Fusion. We robustly evaluate our proposed approach on four geographically diverse datasets from different countries ranging across clear and rain weather conditions. These datasets also include challenging visual segments in tunnels and underpasses. We show that with the integration of the map information, our Map-Fusion algorithm reduces the error of the state-of-the-art VO and VIO approaches across all datasets. We also validate our proposed algorithm in a real-world environment and in real-time on a hardware constrained mobile robot. Map-Fusion achieved 2.46m error in clear weather and 6.05m error in rain weather for a 150m route.