Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios

Accurate and seamless vehicle positioning is fundamental for autonomous driving tasks in urban environments, requiring the provision of high-end measuring devices. Light Detection and Ranging (lidar) sensors, together with Global Navigation Satellite Systems (GNSS) receivers, are therefore commonly...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Junjie Zhang, Kourosh Khoshelham, Amir Khodabandeh
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	autonomous driving Extended Kalman-Filter GNSS lidar sensor fusion vehicle positioning Science Q
Acceso en línea:	https://doaj.org/article/56c182ec63cb400d80423ef13d4f0c99
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:56c182ec63cb400d80423ef13d4f0c99
record_format	dspace
spelling	oai:doaj.org-article:56c182ec63cb400d80423ef13d4f0c992021-11-25T18:53:57ZSeamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios10.3390/rs132245252072-4292https://doaj.org/article/56c182ec63cb400d80423ef13d4f0c992021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4525https://doaj.org/toc/2072-4292Accurate and seamless vehicle positioning is fundamental for autonomous driving tasks in urban environments, requiring the provision of high-end measuring devices. Light Detection and Ranging (lidar) sensors, together with Global Navigation Satellite Systems (GNSS) receivers, are therefore commonly found onboard modern vehicles. In this paper, we propose an integration of lidar and GNSS code measurements at the <i>observation level</i> via a mixed measurement model. An Extended Kalman-Filter (EKF) is implemented to capture the dynamic of the vehicle movement, and thus, to incorporate the vehicle velocity parameters into the measurement model. The lidar positioning component is realized using point cloud registration through a deep neural network, which is aided by a high definition (HD) map comprising accurately georeferenced scans of the road environments. Experiments conducted in a densely built-up environment show that, by exploiting the abundant measurements of GNSS and high accuracy of lidar, the proposed vehicle positioning approach can maintain centimeter-to meter-level accuracy for the entirety of the driving duration in urban canyons.Junjie ZhangKourosh KhoshelhamAmir KhodabandehMDPI AGarticleautonomous drivingExtended Kalman-FilterGNSSlidarsensor fusionvehicle positioningScienceQENRemote Sensing, Vol 13, Iss 4525, p 4525 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autonomous driving Extended Kalman-Filter GNSS lidar sensor fusion vehicle positioning Science Q
spellingShingle	autonomous driving Extended Kalman-Filter GNSS lidar sensor fusion vehicle positioning Science Q Junjie Zhang Kourosh Khoshelham Amir Khodabandeh Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
description	Accurate and seamless vehicle positioning is fundamental for autonomous driving tasks in urban environments, requiring the provision of high-end measuring devices. Light Detection and Ranging (lidar) sensors, together with Global Navigation Satellite Systems (GNSS) receivers, are therefore commonly found onboard modern vehicles. In this paper, we propose an integration of lidar and GNSS code measurements at the <i>observation level</i> via a mixed measurement model. An Extended Kalman-Filter (EKF) is implemented to capture the dynamic of the vehicle movement, and thus, to incorporate the vehicle velocity parameters into the measurement model. The lidar positioning component is realized using point cloud registration through a deep neural network, which is aided by a high definition (HD) map comprising accurately georeferenced scans of the road environments. Experiments conducted in a densely built-up environment show that, by exploiting the abundant measurements of GNSS and high accuracy of lidar, the proposed vehicle positioning approach can maintain centimeter-to meter-level accuracy for the entirety of the driving duration in urban canyons.
format	article
author	Junjie Zhang Kourosh Khoshelham Amir Khodabandeh
author_facet	Junjie Zhang Kourosh Khoshelham Amir Khodabandeh
author_sort	Junjie Zhang
title	Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
title_short	Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
title_full	Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
title_fullStr	Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
title_full_unstemmed	Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios
title_sort	seamless vehicle positioning by lidar-gnss integration: standalone and multi-epoch scenarios
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/56c182ec63cb400d80423ef13d4f0c99
work_keys_str_mv	AT junjiezhang seamlessvehiclepositioningbylidargnssintegrationstandaloneandmultiepochscenarios AT kouroshkhoshelham seamlessvehiclepositioningbylidargnssintegrationstandaloneandmultiepochscenarios AT amirkhodabandeh seamlessvehiclepositioningbylidargnssintegrationstandaloneandmultiepochscenarios
_version_	1718410587506999296

Seamless Vehicle Positioning by Lidar-GNSS Integration: Standalone and Multi-Epoch Scenarios

Ejemplares similares