Uncertainty-Driven Radar-Inertial Fusion for Instantaneous 3D Ego-Velocity Estimation

TL;DR

This paper introduces an uncertainty-aware radar-inertial fusion method for real-time 3D ego-velocity estimation, improving accuracy and robustness over existing techniques in autonomous navigation.

Contribution

It presents a neural network-based approach that estimates ego-velocity and its uncertainty from radar data, integrated with inertial measurements via an Extended Kalman Filter, enhancing ego-motion estimation.

Findings

Lower velocity estimation error compared to existing methods

Outperforms scan matching-based techniques in accuracy

Demonstrates robustness on publicly available dataset

Abstract

We present a method for estimating ego-velocity in autonomous navigation by integrating high-resolution imaging radar with an inertial measurement unit. The proposed approach addresses the limitations of traditional radar-based ego-motion estimation techniques by employing a neural network to process complex-valued raw radar data and estimate instantaneous linear ego-velocity along with its associated uncertainty. This uncertainty-aware velocity estimate is then integrated with inertial measurement unit data using an Extended Kalman Filter. The filter leverages the network-predicted uncertainty to refine the inertial sensor's noise and bias parameters, improving the overall robustness and accuracy of the ego-motion estimation. We evaluated the proposed method on the publicly available ColoRadar dataset. Our approach achieves significantly lower error compared to the closest publicly available method and also outperforms both instantaneous and scan matching-based techniques.