Marc Zofka

Abteilungsleiter

Werdegang

Marc Zofka studierte von 2007 bis 2010 Information Engineering an der Universität Konstanz mit dem Schwerpunkt Visual Analytics. Im Anschluss belegte er den Masterstudiengang Informatik am Karlsruher Institut für Technologie (KIT). Seine Schwerpunkte liegen in den Gebieten Kognitive Systeme, Robotik und Sensorfusion.

Seine Masterarbeit mit dem Titel "Regularisierung der Korrespondenzfindung von Unterwasseraufnahmen" legte er am Lehrstuhl für interaktive Echtzeitsysteme in Kooperation mit dem Fraunhofer IOSB ab.

Seit Mai 2013 ist er wissenschaftlicher Mitarbeiter in der Abteilung TKS. Er ist im Bereich des energieeffizienten Fahrens und der  Verifikation von Fahrassistenzsystemen tätig.

Publikationen

Zeitungs- oder Zeitschriftenartikel (1)

1. Consistent Test Method for Assistance SystemsDetails

   Sebastian Schwab, Tobias Leichsenring, Marc René Zofka, Tobias Bär, 2014

Konferenzbeitrag (5)

1. Data-­driven Simulation and Parametrization of Traffic Scenarios for the Development of Advanced Driver Assistance SystemsDetails

   Zofka, Marc René and Kuhnt, Florian and Rist, Christoph and Schamm, Thomas and Zöllner, J. Marius, 2015

2. Testing of advanced driver assistance towards automated driving: A survey and taxonomy on existing approaches and open questionsDetails

   Stellet, Jan Erik and Zofka, Marc René and Schumacher, Jan and Schamm, Thomas and Niewels, Frank and Zöllner, J. Marius, 2015

3. Robust, Marker-Based Head Tracking for Testing Cognitive Vehicles in the LoopInfoDetails

   Zofka, Marc René and Kohlhaas, Ralf and Bär, Tobias and Schwab, Sebastian and Schamm, Thomas and Zöllner, J Marius, Springer, 2014

   One of the great challenges for the release of automated vehicles is the verification and evaluation of their cognitive skills. Therefore, Vehicle-in-the-loop testing provides an adequate tool, combining real test drives with simulations. In this paper we present our innovative Vehicle-in-the-loop framework: First, a marker-based head tracking is presented, which is able to track the driver’s head in presence of vehicle’s movement and illumination influences. Second, we present our realization based on the Open-Source framework ROS with an exemplary coupling to the professional simulation tool CarMaker. Finally, we evaluate our approach in different driving scenarios.

4. Semivirtual simulations for the evaluation of vision-based ADASInfoDetails

   Zofka, Marc René and Kohlhaas, Ralf and Schamm, Thomas and Zöllner, J Marius, 2014

   The design and development process of advanced driver assistance systems (ADAS) is divided into different phases, where the algorithms are implemented as a model, then as software and finally as hardware. Since it is unfeasable to simulate all possible driving situations for environmental perception and interpretation algorithms, there is still a need for expensive and time-consuming real test drives of thousands of kilometers. Therefore we present a novel approach for testing and evaluation of vision-based ADAS, where reliable simulations are fused with recorded data from test drives to provide a task-specific reference model. This approach provides ground truth with much higher reliability and reproducability than real test drives and authenticity than using pure simulations and can be applied already in early steps of the design process. We illustrate the effectiveness of our approach by testing a vision-based collision mitigation system on recordings of a german highway.

5. New test method for reproducible real-time tests of ADAS ECUs: “Vehicle-in-the-Loop” connects real-world vehicles with the virtual worldInfoDetails

   C. Miquet, S. Schwab, R. Pfeffer, M. R. Zofka, T. Bär, Dr. T. Schamm, Prof. Dr. J. M. Zöllner, 2014

   Modern vehicles act more and more autonomously. While in the early years of driver assistance systems parking aids were only available in premium-class vehicles and initially provided drivers only with acoustic help in maneuvering a vehicle into a parking space, the evolutionary automatic parking assistance system today is available even in medium-sized vehicles. The simple cruise control evolved into adaptive cruise control (ACC); the automatic emergency-brake-assist function is an extension of ACC. Lane change, intersection and emergency-steer-assist are additional electronic “co-drivers” intended to make driving safer.

Export Suchergebnis .bib

Kontakt

Telefon: +49 721 9654-366
Fax: +49 721 9654-367
E-Mail: zofka@dont-want-spam.fzi.de

Zurück