Identification of critical cases of ADAS safety by FOT based parameterization of a catalogue
Sprache des Vortragstitels:
Englisch
Original Tagungtitel:
The 2017 Asian Control Conference
Sprache des Tagungstitel:
Englisch
Original Kurzfassung:
Safety Testing of Advanced Driver Assistance Systems(ADAS) and Automated Driving Functions(ADF) has paramount importance for the diffusion of these technologies, especially because the expectations of the public are very high. On the road testing alone would require an unaffordable testing time. Against this background, testing must include simulations, but this is no easy task, as the corresponding scenarios can be unrealistic or irrelevant or both, especially if they are produced by simulations alone. Using measurements alone, is also not better, as it would require a very large testing amount. This paper proposes a method to solve this problem relying on a catalogue of the test cases and using Field-Operational-Test (FOT) measurements to obtain a realistic parameterization. This method is presented at the example of the lane change scenario, one of the most relevant safety critical maneuvers. It shows that the last majority of measured cases can be covered with a rather simple parametrization and sensible estimate of the collision risk can be derived