Automated Vehicle Identification Based on Car-Following Data With Machine Learning

Vehicles with adaptive cruise control, i.e., SAE Levels 1 and 2 automated vehicles (AVs), have been operating on roads with a significant and rapidly growing penetration rate. Identifying these AVs is critical to understanding near-future mixed traffic characteristics and managing highway mobility and safety. This study identifies adaptive cruise control-equipped vehicles from human-driven vehicles (HVs) by constructing a set of learning-based models using car-following trajectories in a short time window. It is extendible to Level 3 and + AV identification when data is available. To compare model performance and draw physical insights, two physics-based models are proposed based on the premise that, in general, the car-following behavior of an AV is less volatile than an HV. Four car-following datasets, including AV makes from different manufacturers, are mixed to build a comprehensive identification model. Results show that physics-based approaches identify more than 80% AVs and 70% HVs. The identification accuracy of learning-based models is even higher. For example, the cluster-aware long short-term memory network identifies 98.79% of AVs and 95.45% of HVs. Learning-based identification models developed by this study can be integrated with the existing infrastructure (e.g., surveillance cameras), which have been used to extract car-following trajectories, to detect AVs in mixed traffic streams. This opens unparalleled data-driven opportunities to analyze and control mixed traffic to enhance safety (e.g., notifying surrounding traffic of the presence of AVs) and mobility (e.g., opening AV dedicated lanes when the percentage is great enough).