Radar Odometry for Autonomous Ground Vehicles: A Survey of Methods and Datasets

TL;DR

This survey reviews recent advancements in radar odometry for autonomous ground vehicles, emphasizing its robustness in adverse conditions, and discusses datasets, methods, and future challenges in the field.

Contribution

It provides a comprehensive overview and categorization of recent radar odometry methods, datasets, and metrics, highlighting challenges and future directions.

Findings

Radars are effective in adverse weather and lighting conditions.

Recent methods leverage Doppler information for improved accuracy.

The survey identifies key challenges and research gaps in radar odometry.

Abstract

Radar odometry has been gaining attention in the last decade. It stands as one of the best solutions for robotic state estimation in unfavorable conditions; conditions where other interoceptive and exteroceptive sensors may fall short. Radars are widely adopted, resilient to weather and illumination, and provide Doppler information which make them very attractive for such tasks. This article presents an extensive survey of the latest work on ground-based radar odometry for autonomous robots. It covers technologies, datasets, metrics, and approaches that have been developed in the last decade in addition to in-depth analysis and categorization of the various methods and techniques applied to tackle this problem. This article concludes with challenges and future recommendations to advance the field of radar odometry making it a great starting point for newcomers and a valuable reference for experienced researchers.