Cargando…

Evaluating Localization Accuracy of Automated Driving Systems

Automated driving systems are in need of accurate localization, i.e., achieving accuracies below 0.1 m at confidence levels above 95%. Although during the last decade numerous localization techniques have been proposed, a common methodology to validate their accuracies in relation to a ground-truth...

Descripción completa

Detalles Bibliográficos
Autores principales: Rehrl, Karl, Gröchenig, Simon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8433815/
https://www.ncbi.nlm.nih.gov/pubmed/34502746
http://dx.doi.org/10.3390/s21175855
_version_ 1783751448560926720
author Rehrl, Karl
Gröchenig, Simon
author_facet Rehrl, Karl
Gröchenig, Simon
author_sort Rehrl, Karl
collection PubMed
description Automated driving systems are in need of accurate localization, i.e., achieving accuracies below 0.1 m at confidence levels above 95%. Although during the last decade numerous localization techniques have been proposed, a common methodology to validate their accuracies in relation to a ground-truth dataset is missing so far. This work aims at closing this gap by evaluating four different methods for validating localization accuracies of a vehicle’s position trajectory to different ground truths: (1) a static driving-path, (2) the lane-centerline of a high-definition (HD) map with validated accuracy, (3) localized vehicle body overlaps of the lane-boundaries of a HD map, and (4) longitudinal accuracy at stop points. The methods are evaluated using two localization test datasets, one acquired by an automated vehicle following a static driving path, being additionally equipped with roof-mounted localization systems, and a second dataset acquired from manually-driven connected vehicles. Results show the broad applicability of the approach for evaluating localization accuracy and reveal the pros and cons of the different methods and ground truths. Results also show the feasibility of achieving localization accuracies below 0.1 m at confidence levels up to 99.9% for high-quality localization systems, while at the same time demonstrate that such accuracies are still challenging to achieve.
format Online
Article
Text
id pubmed-8433815
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84338152021-09-12 Evaluating Localization Accuracy of Automated Driving Systems Rehrl, Karl Gröchenig, Simon Sensors (Basel) Article Automated driving systems are in need of accurate localization, i.e., achieving accuracies below 0.1 m at confidence levels above 95%. Although during the last decade numerous localization techniques have been proposed, a common methodology to validate their accuracies in relation to a ground-truth dataset is missing so far. This work aims at closing this gap by evaluating four different methods for validating localization accuracies of a vehicle’s position trajectory to different ground truths: (1) a static driving-path, (2) the lane-centerline of a high-definition (HD) map with validated accuracy, (3) localized vehicle body overlaps of the lane-boundaries of a HD map, and (4) longitudinal accuracy at stop points. The methods are evaluated using two localization test datasets, one acquired by an automated vehicle following a static driving path, being additionally equipped with roof-mounted localization systems, and a second dataset acquired from manually-driven connected vehicles. Results show the broad applicability of the approach for evaluating localization accuracy and reveal the pros and cons of the different methods and ground truths. Results also show the feasibility of achieving localization accuracies below 0.1 m at confidence levels up to 99.9% for high-quality localization systems, while at the same time demonstrate that such accuracies are still challenging to achieve. MDPI 2021-08-30 /pmc/articles/PMC8433815/ /pubmed/34502746 http://dx.doi.org/10.3390/s21175855 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Rehrl, Karl
Gröchenig, Simon
Evaluating Localization Accuracy of Automated Driving Systems
title Evaluating Localization Accuracy of Automated Driving Systems
title_full Evaluating Localization Accuracy of Automated Driving Systems
title_fullStr Evaluating Localization Accuracy of Automated Driving Systems
title_full_unstemmed Evaluating Localization Accuracy of Automated Driving Systems
title_short Evaluating Localization Accuracy of Automated Driving Systems
title_sort evaluating localization accuracy of automated driving systems
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8433815/
https://www.ncbi.nlm.nih.gov/pubmed/34502746
http://dx.doi.org/10.3390/s21175855
work_keys_str_mv AT rehrlkarl evaluatinglocalizationaccuracyofautomateddrivingsystems
AT grochenigsimon evaluatinglocalizationaccuracyofautomateddrivingsystems