From few to many: Using copulas and Monte Carlo simulation to estimate safety consequences

Abstract

With the introduction of more advanced vehicle technology, it is paramount to assess its safety benefit. Advanced driver assistance systems (ADAS) can reduce crashes and mitigate crash severity, if designed appropriately. Driver behavior models are integral to the ADAS design process, complementing time and resource intensive human participant experiments. The authors introduce a method to model driver responses to forward collision events by quantifying multivariate behavior with copulas and Monte Carlo simulation. This approach capitalizes on the data from small samples of crash events observed in naturalistic or simulator studies. Copulas summarize data by capturing the underlying joint distribution of variables, and Monte Carlo methods can be used to repeatedly sample from these distributions. A driver model can be parameterized with these samples, and run on a desktop driving simulation environment.