Enhancing automated vehicle safety through testing with realistic driver models (06-009)

Project Description: Improving safety during interactions between human drivers and automated vehicles requires an environment where autonomous vehicle software can interact with realistic human driving behavior. Generating this behavior has been challenging due a lack of driver models that accurately reflect both vehicle kinematics and driver cognition. In this project we propose to develop an active inference model of car following behavior that will resolve these limitations. We use the publicly available INTERACTION dataset to fit and estimate the parameters of the proposed driver model. We assess our model’s ability to replicates human driving behavior in the dataset and handle conflict scenarios compared to established driver modeling paradigms. Data Scope: We use the publicly available INTERACTION dataset. The INTERACTION dataset is collected using drones on fixed road segments in the USA, Germany, and China. The dataset provides a lanelet2 format map and a set of time-indexed trajectories of the positions, velocities, and headings of each vehicle in the scene in the map's coordinate system at a sampling frequency of 10 Hz, and the vehicle's length and width for each road segment. Data Specification: Complete description of the INTERACTION dataset can be found on the official website: https://interaction-dataset.com/