|
|
Digital
Library of the European Council for Modelling and Simulation |
|
Title: |
Ground Vehicle
Localization With Particle Filter Based On Simulated Road Marking Image |
|
Authors: |
Oleg
Shipitko, Anton Grigoryev |
|
Published in:
|
(2018). ECMS 2018
Proceedings Edited by: Lars Nolle, Alexandra
Burger, Christoph Tholen,
Jens Werner, Jens Wellhausen European Council for
Modeling and Simulation. doi:
10.7148/2018-0005 ISSN:
2522-2422 (ONLINE) ISSN:
2522-2414 (PRINT) ISSN:
2522-2430 (CD-ROM) 32nd European Conference on Modelling and Simulation, Wilhelmshaven, Germany, May 22nd
– May 265h, 2018 |
|
Citation
format: |
Oleg
Shipitko, Anton Grigoryev
(2018). A Ground
Vehicle Localization With Particle Filter Based On Simulated Road Marking
Image, ECMS 2018 Proceedings Edited by:
Lars Nolle, Alexandra Burger, Christoph
Tholen, Jens Werner, Jens Wellhausen
European Council for Modeling and Simulation. doi: 10.7148/2018-0341 |
|
DOI: |
https://doi.org/10.7148/2018-0341 |
|
Abstract: |
Precise localization is a prerequisite and a corner-stone for successful operation of any autonomous ve-hicle. In this paper, consideration is given to a lane
feature-based approach to a self-driving vehicle local-ization.
Proposed map-relative localization method is built upon a combination of
vision-based lane mark-ings detection and odometry data. Detected lane mark-ings
are aligned with a reference map in order to de-rive global pose estimate
while odometry provides path consistency. To
combine heterogeneous sensory data use is made of particle filter method. It
allows for non-Gaussian noise common for vision-based detectors as well as a
further extension of data sources. The ap-proach
described in this work was tested on a real vehi-cle
in urban environment and proved itself to be precise
and reliable enough for real-world applications. It was able to provide
lateral and longitudinal map-relative localization with a precision of 0.2 m. |
|
Full
text: |
|
