RAVE: A Framework for Radar Ego-Velocity Estimation

TL;DR

RAVE is a radar-based ego-velocity estimation framework that improves autonomous system accuracy by integrating radar data with outlier rejection and filtering, validated on multiple datasets.

Contribution

The paper introduces RAVE, a novel radar ego-velocity estimation framework that combines zero velocity detection, outlier rejection, and filtering, with a systematic analysis of existing techniques.

Findings

RAVE significantly improves odometry accuracy on open-source datasets.

The proposed filtering method effectively discards infeasible velocity estimates.

Systematic analysis reveals impact of outlier rejection techniques on estimation accuracy.

Abstract

State estimation is an essential component of autonomous systems, usually relying on sensor fusion that integrates data from cameras, LiDARs and IMUs. Recently, radars have shown the potential to improve the accuracy and robustness of state estimation and perception, especially in challenging environmental conditions such as adverse weather and low-light scenarios. In this paper, we present a framework for ego-velocity estimation, which we call RAVE, that relies on 3D automotive radar data and encompasses zero velocity detection, outlier rejection, and velocity estimation. In addition, we propose a simple filtering method to discard infeasible ego-velocity estimates. We also conduct a systematic analysis of how different existing outlier rejection techniques and optimization loss functions impact estimation accuracy. Our evaluation on three open-source datasets demonstrates the effectiveness of the proposed filter and a significant positive impact of RAVE on the odometry accuracy. Furthermore, we release an open-source implementation of the proposed framework for radar ego-velocity estimation accompanied with a ROS interface.