Car-Following-Response-Based Vehicle Classification via Deep Learning

Abstract

The driving characteristics of individual vehicles in the flow have been shown to influence the aggregate traffic flow characteristics. This is true both for individual human drivers as well as vehicles with some level of automation, such as adaptive cruise control (ACC). Knowledge of the individual constituents of the traffic flow will allow for more advanced traffic control strategies that are tailored to the individual vehicles and their respective driving characteristics. Therefore, there is a need to rapidly assess the car-following dynamics of individual vehicles and identify their level of automation based on their car-following trajectory. This study proposed a time-series based deep learning classification method to classify and identify human-driven and driver-assist vehicles in real-time from driving data. Powered by the recent advances in deep learning, we are able to identify individual vehicles in the flow using only car-following trajectory data and identify both ACC vehicles and human drivers. This article represents the first step toward assessing vehicle characteristics in real time. Furthermore, the proposed method can classify vehicles within a couple of seconds with high accuracy. Comparison with existing state-of-the-art methods shows the superior performance of the proposed method.