Incremental hopping-window pose-graph fusion for real-time vehicle localization

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

In this work, we research and evaluate incremental hopping-window pose-graph fusion strategies for vehicle localization. Pose-graphs can model multiple absolute and relative vehicle localization sensors, and can be optimized using non-linear techniques. We focus on the performance of incremental hopping-window optimization for on-line usage in vehicles and compare it with global off-line optimization. Our evaluation is based on 180 Km long vehicle trajectories that are recorded in highway, urban, and rural areas, and that are accompanied with post-processed Real Time Kinematic GNSS as ground truth. The results exhibit a 17% reduction in the error's standard deviation and a significant reduction in GNSS outliers when compared with automotive-grade GNSS receivers. The incremental hopping-window pose-graph optimization bounds the computation cost, when compared to global pose-graph fusion, which increases linearly with the size of the pose-graph, whereas the difference in accuracy is only 1%. This allows real-time usage of non-linear pose-graph fusion for vehicle localization.
Original languageEnglish
Title of host publication2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring)
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Number of pages7
ISBN (Electronic)978-1-7281-1216-9
ISBN (Print)978-1-7281-1217-6
DOIs
Publication statusPublished - 27 Jun 2019
Event89th IEEE Vehicular Technology Conference, VTC Spring 2019 - Kuala Lumpur, Malaysia
Duration: 28 Apr 20191 May 2019

Conference

Conference89th IEEE Vehicular Technology Conference, VTC Spring 2019
Abbreviated title VTC Spring 2019
CountryMalaysia
CityKuala Lumpur
Period28/04/191/05/19

Fingerprint

Fusion reactions
Kinematics
Trajectories
Sensors
Costs

Cite this

Das, A., & Dubbelman, G. (2019). Incremental hopping-window pose-graph fusion for real-time vehicle localization. In 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring) [8746464] Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/VTCSpring.2019.8746464
Das, Anweshan ; Dubbelman, Gijs. / Incremental hopping-window pose-graph fusion for real-time vehicle localization. 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring). Piscataway : Institute of Electrical and Electronics Engineers, 2019.
@inproceedings{457e02c315d04155b7ae51f30f9391c9,
title = "Incremental hopping-window pose-graph fusion for real-time vehicle localization",
abstract = "In this work, we research and evaluate incremental hopping-window pose-graph fusion strategies for vehicle localization. Pose-graphs can model multiple absolute and relative vehicle localization sensors, and can be optimized using non-linear techniques. We focus on the performance of incremental hopping-window optimization for on-line usage in vehicles and compare it with global off-line optimization. Our evaluation is based on 180 Km long vehicle trajectories that are recorded in highway, urban, and rural areas, and that are accompanied with post-processed Real Time Kinematic GNSS as ground truth. The results exhibit a 17{\%} reduction in the error's standard deviation and a significant reduction in GNSS outliers when compared with automotive-grade GNSS receivers. The incremental hopping-window pose-graph optimization bounds the computation cost, when compared to global pose-graph fusion, which increases linearly with the size of the pose-graph, whereas the difference in accuracy is only 1{\%}. This allows real-time usage of non-linear pose-graph fusion for vehicle localization.",
author = "Anweshan Das and Gijs Dubbelman",
year = "2019",
month = "6",
day = "27",
doi = "10.1109/VTCSpring.2019.8746464",
language = "English",
isbn = "978-1-7281-1217-6",
booktitle = "2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring)",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Das, A & Dubbelman, G 2019, Incremental hopping-window pose-graph fusion for real-time vehicle localization. in 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring)., 8746464, Institute of Electrical and Electronics Engineers, Piscataway, 89th IEEE Vehicular Technology Conference, VTC Spring 2019, Kuala Lumpur, Malaysia, 28/04/19. https://doi.org/10.1109/VTCSpring.2019.8746464

Incremental hopping-window pose-graph fusion for real-time vehicle localization. / Das, Anweshan; Dubbelman, Gijs.

2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring). Piscataway : Institute of Electrical and Electronics Engineers, 2019. 8746464.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Incremental hopping-window pose-graph fusion for real-time vehicle localization

AU - Das, Anweshan

AU - Dubbelman, Gijs

PY - 2019/6/27

Y1 - 2019/6/27

N2 - In this work, we research and evaluate incremental hopping-window pose-graph fusion strategies for vehicle localization. Pose-graphs can model multiple absolute and relative vehicle localization sensors, and can be optimized using non-linear techniques. We focus on the performance of incremental hopping-window optimization for on-line usage in vehicles and compare it with global off-line optimization. Our evaluation is based on 180 Km long vehicle trajectories that are recorded in highway, urban, and rural areas, and that are accompanied with post-processed Real Time Kinematic GNSS as ground truth. The results exhibit a 17% reduction in the error's standard deviation and a significant reduction in GNSS outliers when compared with automotive-grade GNSS receivers. The incremental hopping-window pose-graph optimization bounds the computation cost, when compared to global pose-graph fusion, which increases linearly with the size of the pose-graph, whereas the difference in accuracy is only 1%. This allows real-time usage of non-linear pose-graph fusion for vehicle localization.

AB - In this work, we research and evaluate incremental hopping-window pose-graph fusion strategies for vehicle localization. Pose-graphs can model multiple absolute and relative vehicle localization sensors, and can be optimized using non-linear techniques. We focus on the performance of incremental hopping-window optimization for on-line usage in vehicles and compare it with global off-line optimization. Our evaluation is based on 180 Km long vehicle trajectories that are recorded in highway, urban, and rural areas, and that are accompanied with post-processed Real Time Kinematic GNSS as ground truth. The results exhibit a 17% reduction in the error's standard deviation and a significant reduction in GNSS outliers when compared with automotive-grade GNSS receivers. The incremental hopping-window pose-graph optimization bounds the computation cost, when compared to global pose-graph fusion, which increases linearly with the size of the pose-graph, whereas the difference in accuracy is only 1%. This allows real-time usage of non-linear pose-graph fusion for vehicle localization.

UR - http://www.scopus.com/inward/record.url?scp=85068961799&partnerID=8YFLogxK

U2 - 10.1109/VTCSpring.2019.8746464

DO - 10.1109/VTCSpring.2019.8746464

M3 - Conference contribution

AN - SCOPUS:85068961799

SN - 978-1-7281-1217-6

BT - 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Das A, Dubbelman G. Incremental hopping-window pose-graph fusion for real-time vehicle localization. In 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring). Piscataway: Institute of Electrical and Electronics Engineers. 2019. 8746464 https://doi.org/10.1109/VTCSpring.2019.8746464