Ontology-based traffic scene modeling, traffic regulations dependent situational awareness and decision-making for automated vehicles

Martin Buechel, Gereon Hinz, Frederik Ruehl, Hans Schroth, Csaba Gyoeri, Alois Knoll

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

33 Scopus citations

Abstract

This paper presents a modular framework for traffic regulations based decision-making of automated vehicles. It builds on a semantic traffic scene representation formulated as ontology and includes knowledge about traffic regulations. The semantic representation supports traffic situation classification by reasoning, providing improved situational awareness for the automated vehicle. Decision-making rules are directly derived from traffic regulations and concepts used in the ontology are harmonized with concepts used in traffic regulations. Due to the modular structure of the developed ontology, switching between different sets of national traffic regulations becomes a simple process. The methodology is evaluated for a variety of traffic scenarios, building up from basic to complex urban scenarios containing intersections, traffic regulating police officers and crossing street railways.

Original languageEnglish
Title of host publicationIV 2017 - 28th IEEE Intelligent Vehicles Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1471-1476
Number of pages6
ISBN (Electronic)9781509048045
DOIs
StatePublished - 28 Jul 2017
Event28th IEEE Intelligent Vehicles Symposium, IV 2017 - Redondo Beach, United States
Duration: 11 Jun 201714 Jun 2017

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings

Conference

Conference28th IEEE Intelligent Vehicles Symposium, IV 2017
Country/TerritoryUnited States
CityRedondo Beach
Period11/06/1714/06/17

Fingerprint

Dive into the research topics of 'Ontology-based traffic scene modeling, traffic regulations dependent situational awareness and decision-making for automated vehicles'. Together they form a unique fingerprint.

Cite this