Safety performance functions in a road environment with automated vehicles

The reduction of road fatalities can be achieved by intervening in various aspects, including infrastructure, transportation policy, vehicles, and driver behavior. One of the most promising solutions to solve this issue is to rely on Automated Vehicles (AVs), which can prevent human errors, which account for most crashes. However, the impact of AVs on road safety is still unquantifiable. The reason resides in a lack of observed data, as well as in the uncertainty about AV introduction on roads and their interaction with other vehicles and users. In this paper, a methodology to predict the impact of AVs is proposed, relying on Safety Performance Functions (SPFs). An ad hoc SPF for AVs has been developed just for multivehicle crashes, based on a set of market penetration rates, to propose a mathematical model that can include recent technological innovations in road traffic and be adapted to other contexts. Considering the area of the Province of Bari and three different time horizons, crashes were simulated with the presence of AVs in different traffic scenarios. The proposed scenarios were taken from extensive literature studies about the deployment of AVs. The SPF for the predicted crashes was developed by adding one coefficient that considers the presence of AVs to the baseline equation, controlling for the road geometry. The fitted models show a satisfactory goodness-of-fit, based on different metrics, including CuRe (Cumulative Residuals) plots.