2020/11/18 by Gurcan Comert, Comert, Gurcan, Mecit Cetin +1
Engineering · #Applications (stat.AP) #FOS: Computer and information sciences #FOS: Electrical engineering #Systems and Control (eess.SY) #Traffic Prediction and Management Techniques #Traffic control and management #Vehicular Ad Hoc Networks (VANETs) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2011.09397
openalex publication_date 2020/11/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Today vehicles are becoming a rich source of data as they are equipped with\nlocalization or tracking and with wireless communications technologies. With\nthe increasing interest in automated- or self- driving technologies, vehicles\nare also being equipped with range measuring sensors (e.g., LIDAR, stereo\ncameras, and ultrasonic) to detect other vehicles and objects in the\nsurrounding environment. It is possible to envision that such vehicles could\nshare their data with the transportation infrastructure elements (e.g., a\ntraffic signal controller) to enable different mobility and safety\napplications. Data from these connected vehicles could then be used to estimate\nthe system state in real-time. This paper develops queue length estimators from\nconnected vehicles equipped with range measurement sensors. Simple\nplug-and-play models are developed for queue length estimations without needing\nground truth queue lengths by extending the previous formulations. The proposed\nmethod is simple to implement and can be adopted to cyclic queues at traffic\nsignals with known phase lengths. The derived models are evaluated with data\nfrom microscopic traffic simulations. From numerical experiments, the QLE model\nwith range sensors improves the errors as much as 25% in variance-to-mean ratio\nand 5 % in coefficient of variation at low less than 20% market penetration\nrates.\n