Thesis supervisor: Bálint Molnár
Location of studies (in Hungarian): Faculty of Informatics, Eötvös Loránd University Abbreviation of location of studies: ELTE
Description of the research topic:
Description of traffic situations and analysis of the relevant characteristics of the situations
The comprehension of a traffic situation plays a major role in driving a vehicle. It transforms perceived raw information into interpretable information. This forms a basis for future projection, decision making and action performing, such as navigating, maneuvering and driving control, within the driving control loop.
The aim of this research is to provide a generic traffic situation description capable of supplying various ADAS (Autonomic Driver Assistance System) with relevant information about the current driving and traffic situation of the ego vehicle („our” car) and its environment. With this information ADAS should be able to perform reasonable functions and actions and approach visionary goals such as injury and accident free driving, substantial assistance in arbitrary situations up to even autonomous driving.
Knowledge-based Traffic Situation Description
Most complex traffic situations seem to be those at intersections. Their understanding is influenced by a variety of object and relation types such as intersecting roads with lanes and markings, allowed and forbidden paths, vehicles coming from different directions and different kinds of road signs (see figure on the top left). Ontologies are well suited for modeling these multi-object traffic situations and for performing logic reasoning to check consistency of its knowledge and to reason about object types, relations and to e.g. apply traffic rules. Description logic (DL) is a language for building such ontologies
Description Logic Based Traffic Situation Description for ADAS
This research is widely concerned with the investigation and validation of applicability and capability of ontology based traffic situation description.
The interpretation and use of the complex networks originated out of the analyses of Big Data (traffic data) should exploit the ontological approach as a model-driven environment for understanding.
Required language skills: English Recommended language skills (in Hungarian): German Number of students who can be accepted: 1
Deadline for application: 2018-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).