Raci-Net: Ego-vehicle Odometry Estimation in Adverse Weather Conditions

TL;DR

Raci-Net is a deep learning-based odometry estimation system that fuses visual, inertial, and radar data to maintain accurate vehicle positioning in adverse weather conditions like snow and rain.

Contribution

This paper introduces a novel sensor fusion approach that dynamically combines visual, inertial, and radar data for robust odometry in challenging weather.

Findings

Radar enhances odometry accuracy in poor visibility conditions.

The model outperforms existing methods in degraded environments.

Sensor fusion improves robustness across diverse weather scenarios.

Abstract

Autonomous driving systems are highly dependent on sensors like cameras, LiDAR, and inertial measurement units (IMU) to perceive the environment and estimate their motion. Among these sensors, perception-based sensors are not protected from harsh weather and technical failures. Although existing methods show robustness against common technical issues like rotational misalignment and disconnection, they often degrade when faced with dynamic environmental factors like weather conditions. To address these problems, this research introduces a novel deep learning-based motion estimator that integrates visual, inertial, and millimeter-wave radar data, utilizing each sensor strengths to improve odometry estimation accuracy and reliability under adverse environmental conditions such as snow, rain, and varying light. The proposed model uses advanced sensor fusion techniques that dynamically adjust the contributions of each sensor based on the current environmental condition, with radar compensating for visual sensor limitations in poor visibility. This work explores recent advancements in radar-based odometry and highlights that radar robustness in different weather conditions makes it a valuable component for pose estimation systems, specifically when visual sensors are degraded. Experimental results, conducted on the Boreas dataset, showcase the robustness and effectiveness of the model in both clear and degraded environments.