Safety-Oriented Calibration and Evaluation of the Intelligent Driver Model (2310.04259v2)

Abstract: Many car-following models like the Intelligent Driver Model (IDM) incorporate important aspects of safety in their definitions, such as collision-free driving and keeping safe distances, implying that drivers are safety conscious when driving. Despite their safety-oriented nature, when calibrating and evaluating these models, the main objective of most studies is to find model parameters that minimize the error in observed measurements like spacing and speed while studies specifically focused on calibrating and evaluating unobserved safe behavior captured by the parameters of the model are scarce. Most studies on calibration and evaluation of the IDM do not check if the observed driving behavior (i.e. spacing) are within the model estimated unobserved safety thresholds (i.e. desired safety spacing) or what parameters are important for safety. This limits their application for safety driven traffic simulations. To fill this gap, this paper first proposes a simple metric to evaluate driver compliance with the safety thresholds of the IDM model. Specifically, we evaluate driver compliance to their desired safety spacing, speed and safe time gap. Next, a method to enforce compliance to the safety threshold during model calibration is proposed. The proposed compliance metric and the calibration approach is tested using Dutch highway trajectory data obtained from a driving simulator experiment and two drones. The results show that compliance to the IDM safety threshold greatly depends on braking capability with a median compliance between 38% and 90% of driving time, indicating that drivers can only partially follow the IDM safety threshold in reality.