Abstract
Masking By Moving (MByM), provides robust and accurate radar odometry measurements through an exhaustive correlative search across discretised pose candidates. However, this dense search creates a significant computational bottleneck which hinders real-time performance when high-end GPUs are not available. Utilising the translational invariance of the Fourier Transform, in our approach, f-MByM, we decouple the search for angle and translation. By maintaining end-to-end differentiability a neural network is used to mask scans and trained by supervising pose prediction directly. Training faster and with less memory, utilising a decoupled search allows f-MByM to achieve significant run-time performance improvements on a CPU (168%) and to run in real-time on embedded devices, in stark contrast to MByM. Throughout, our approach remains accurate and competitive with the best radar odometry variants available in the literature – achieving an end-point drift of 2.01% in translation and 6.3deg/km on the Oxford Radar RobotCar Dataset.
Useful links
Paper: https://doi.org/10.1109/icra46639.2022.9812063
Preprint: https://arxiv.org/abs/2203.00459
Bibtex
@inproceedings{fastmbym2022,
author={Weston, Rob and Gadd, Matthew and De Martini, Daniele and Newman, Paul and Posner, Ingmar},
title={Fast-MbyM: Leveraging Translational Invariance of the Fourier Transform for Efficient and Accurate Radar Odometry},
year={2022},
booktitle={2022 International Conference on Robotics and Automation (ICRA)},
pages={2186--2192},
doi={10.1109/icra46639.2022.9812063},
url={https://doi.org/10.1109/icra46639.2022.9812063},
}