KIT | KIT-Bibliothek | Impressum | Datenschutz

A Data-driven Verification Framework for Active Safety Functions

Elgharbawy, M.; Scherhaufer, I.; Frey, M. ORCID iD icon; Gauterin, F. ORCID iD icon

Abstract (englisch):

This paper presents an innovative approach toward data-driven scenario synthesis for verification of active safety functions. Despite the recent rapid growth of active safety to consolidate road safety, they still have various challenges coping with dynamic traffic situations of daily life. Therefore, automotive systems Engineering has established data- and knowledge-driven test methods to assure the required software reliability in a highly safety-critical context. However, the reliance on Naturalistic-Field Operational Tests (N-FOT) is inadequate and, in particular, time and cost-intensive when applied to the next generation of automated driving functions, e.g. advanced emergency braking and truck platooning. The presented framework utilises an ontology-based test scenario synthesis to identify criticality margins using a Cluster-Hardware-in-the-Loop (Cluster-HiL) co-simulation platform. Additionally, we demonstrate a systematic process to complement virtual testing by extracting insights from N-FOT database using event-based time series analysis. To this end, data mining techniques are used to obtain representative scenarios witnessed in real-world traffic. ... mehr

Zugehörige Institution(en) am KIT Institut für Fahrzeugsystemtechnik (FAST)
Publikationstyp Vortrag
Publikationsdatum 07.09.2018
Sprache Englisch
Identifikator KITopen-ID: 1000132992
Veranstaltung 17th Driving Simulation and Virtual Reality Conference and Exhibition (DSC 2018), Antibes, Frankreich, 05.09.2018 – 07.09.2018
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page