The use of microscopic simulators for safety assessment in automated and partially automated scenarios: a comparison

In the field of safety assessments, the use of simulators to predict unknown scenarios is becoming crucial, due to the ability of predicting conflict points. The microscopic simulators, accountable for modeling single-vehicle interactions, differ for the type of car-following and lane-changing model, hence for the number of definable parameters. The possibility of modifying all the parameters inside the model equations makes them suitable for simulating autonomous vehicles too. To evaluate the road safety of a site, the output of traffic simulators can become the input of the SSAM (Surrogate Safety Assessment Model), which relies on surrogate safety measures (SSMs). Thus, the choice of the simulator is fundamental. The focus of this dissertation concerns the comparison of the car-following and lane-changing models at the basis of the most used commercial microscopic simulators (VISSIM, AIMSUN, PARAMICS) and the related SSAM outputs in the automated and partially automated traffic environment. The Gipps Model, valid for the car-following and the lane-changing model, aims at always achieving the safety distance, intervening on kinematic parameters like the acceleration, speed, and distance. It is possible to intervene on a limited number of parameters of this model. The Wiedemann model belongs to the family of psycho-physical one and it is governed by several parameters, which makes it useful to remodel complex situations, simulating the human mental workload in driving. The Gipps model and the Wiedemann one (implemented respectively in AIMSUN and VISSIM) have already been used for safety purposes, while the Fritszche one (implemented in PARAMICS) has been currently used only for environmental issues related to automation. It is possible to modify up to 16 parameters in the Gipps and Wiedemann model to simulate the automated and partially autonomous vehicles, even if these models belong to different car-following model family. Based on the site variables, each simulator showed potential strengths. Scenarios involving automated vehicles, which do not account for human behaviors, might be better represented by the Gipps model, which aims at reproducing only the safety distance and not the human mental behavior. Thus, this model could also be the most suitable for the general purpose of crash analysis above mentioned.