A Credible and Robust approach to Ego-Motion Estimation using an Automotive Radar

TL;DR

This paper presents a probabilistic method for ego-motion estimation using automotive radar data, offering robustness against environmental challenges and outliers without relying on explicit feature correspondence.

Contribution

The authors introduce a novel credible and robust probabilistic approach for radar-based ego-motion estimation that does not depend on explicit correspondence calculation.

Findings

Outperforms existing methods on nuScenes dataset

More credible and robust to outliers

Does not require explicit feature matching

Abstract

Consistent motion estimation is fundamental for all mobile autonomous systems. While this sounds like an easy task, often, it is not the case because of changing environmental conditions affecting odometry obtained from vision, Lidar, or the wheels themselves. Unsusceptible to challenging lighting and weather conditions, radar sensors are an obvious alternative. Usually, automotive radars return a sparse point cloud, representing the surroundings. Utilizing this information to motion estimation is challenging due to unstable and phantom measurements, which result in a high rate of outliers. We introduce a credible and robust probabilistic approach to estimate the ego-motion based on these challenging radar measurements; intended to be used within a loosely-coupled sensor fusion framework. Compared to existing solutions, evaluated on the popular nuScenes dataset and others, we show that our proposed algorithm is more credible while not depending on explicit correspondence calculation.