Ecole d'ingénieur et centre de recherche en Sciences du numérique

Semantic technologies for vehicle data

Klotz, Benjamin


Vehicles are evolving from purely mechanical entities to highly connected and autonomous ones that generate an enormous quantity of data. While accessing and processing this new rich data leads to new business and technical opportunities, making vehicle fleets interoperable is still highly challenging with competing standards, numerous vehicle signals and attributes, heterogeneous formats and vehicle architectures. In order to ensure replicability and interoperability we propose to use Semantic Web technologies in this thesis. In this thesis, we propose VSSo, a vehicle signal and attribute ontology that builds on the automotive standard VSS, and that follows the SSN/SOSA design pattern. VSSo is comprehensive while being extensible for OEMs, so that they can use additional private signals in an interoperable way. We describe a more general driving context ontology supporting the description of events and states of the various agents of driving situations: drivers, passengers, vehicles, roads, trajectories. We develop tools and demonstrators to highlight the benefit of the driving context ontology in predicting and contextualizing aggressive driving, and recommending POIs and safer routes. Finally, we contribute to the Web of Things specification by aligning our ontologies with it. We provide automotive-specific requirements and implementations, and highlight the benefit of the Web of Things for automotive application developers.


Titre:Semantic technologies for vehicle data
Département:Data Science
Eurecom ref:5968
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Thesis and is available at :
Bibtex: @phdthesis{EURECOM+5968, year = {2019}, title = {{S}emantic technologies for vehicle data}, author = {{K}lotz, {B}enjamin}, school = {{T}hesis}, month = {09}, url = {} }
Voir aussi: