Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lisus, Daniil, Laconte, Johann, Burnett, Keenan, Zhang, Ziyu, Barfoot, Timothy D.
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908380382101504
author Lisus, Daniil
Laconte, Johann
Burnett, Keenan
Zhang, Ziyu
Barfoot, Timothy D.
author_facet Lisus, Daniil
Laconte, Johann
Burnett, Keenan
Zhang, Ziyu
Barfoot, Timothy D.
contents This paper presents a novel deep-learning-based approach to improve localizing radar measurements against lidar maps. This radar-lidar localization leverages the benefits of both sensors; radar is resilient against adverse weather, while lidar produces high-quality maps in clear conditions. However, owing in part to the unique artefacts present in radar measurements, radar-lidar localization has struggled to achieve comparable performance to lidar-lidar systems, preventing it from being viable for autonomous driving. This work builds on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information. To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library. The learned weights facilitate ICP by filtering out harmful radar points related to artefacts, noise, and even vehicles on the road. Combining an analytical approach with a learned weight reduces overall localization errors and improves convergence in radar-lidar ICP results run on real-world autonomous driving data. Our code base is publicly available to facilitate reproducibility and extensions.
format Preprint
id arxiv_https___arxiv_org_abs_2309_08731
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights
Lisus, Daniil
Laconte, Johann
Burnett, Keenan
Zhang, Ziyu
Barfoot, Timothy D.
Robotics
Machine Learning
This paper presents a novel deep-learning-based approach to improve localizing radar measurements against lidar maps. This radar-lidar localization leverages the benefits of both sensors; radar is resilient against adverse weather, while lidar produces high-quality maps in clear conditions. However, owing in part to the unique artefacts present in radar measurements, radar-lidar localization has struggled to achieve comparable performance to lidar-lidar systems, preventing it from being viable for autonomous driving. This work builds on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information. To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library. The learned weights facilitate ICP by filtering out harmful radar points related to artefacts, noise, and even vehicles on the road. Combining an analytical approach with a learned weight reduces overall localization errors and improves convergence in radar-lidar ICP results run on real-world autonomous driving data. Our code base is publicly available to facilitate reproducibility and extensions.
title Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights
topic Robotics
Machine Learning
url https://arxiv.org/abs/2309.08731