Survey of Deep Learning-Based Methods for FMCW Radar Odometry and Ego-Localization

M Brune, T Meisen, A Pomp - Applied Sciences, 2024 - mdpi.com
This paper provides an in-depth review of deep learning techniques to address the
challenges of odometry and global ego-localization using frequency modulated continuous …

Prepared for the Worst: A Learning-Based Adversarial Attack for Resilience Analysis of the ICP Algorithm

Z Zhang, J Laconte, D Lisus, TD Barfoot - arXiv preprint arXiv:2403.05666, 2024 - arxiv.org
This paper presents a novel method to assess the resilience of the Iterative Closest Point
(ICP) algorithm via deep-learning-based attacks on lidar point clouds. For safety-critical …

The Finer Points: A Systematic Comparison of Point-Cloud Extractors for Radar Odometry

E Preston-Krebs, D Lisus, TD Barfoot - arXiv preprint arXiv:2409.12256, 2024 - arxiv.org
A key element of many odometry pipelines using spinning frequency-modulated continuous-
wave (FMCW) radar is the extraction of a point-cloud from the raw signal. This extraction …