Doppler-aware Odometry from FMCW Scanning Radar

TL;DR

This paper introduces a Doppler-aware odometry method using FMCW radar, combining Doppler-enhanced scan matching and neural network velocity regression to improve robustness and accuracy in challenging environments.

Contribution

It presents a novel approach integrating Doppler information into radar odometry and trains a neural network for velocity estimation, enhancing robustness over traditional methods.

Findings

Improved odometry accuracy in challenging environments.

Enhanced robustness to geometric ambiguities.

Validated on a new, publicly available dataset.

Abstract

This work explores Doppler information from a millimetre-Wave (mm-W) Frequency-Modulated Continuous-Wave (FMCW) scanning radar to make odometry estimation more robust and accurate. Firstly, doppler information is added to the scan masking process to enhance correlative scan matching. Secondly, we train a Neural Network (NN) for regressing forward velocity directly from a single radar scan; we fuse this estimate with the correlative scan matching estimate and show improved robustness to bad estimates caused by challenging environment geometries, e.g. narrow tunnels. We test our method with a novel custom dataset which is released with this work at https://ori.ox.ac.uk/publications/datasets.