Vehicle departure pattern and queue length prediction at an isolated intersection with automatic vehicle identity detection

Abstract

Queue length is more likely to be affected by inefficient departure behaviour near the stop line at an intersection because of the prohibition of lane changes. The inefficient departure behaviour and its influence on the evolution of queue discharging in specific lanes have significant research value. In the past few years, the deployment of automatic vehicle identification (AVI) systems has made it possible to acquire information on vehicles' passing through an intersection. Researchers can obtain individual driving information more accurately and effectively based on an analysis of AVI data. These high-resolution data have enabled the reconstruction and quantitative analysis of the influence of microscopic traffic behaviour. This study aims to model the departure of vehicle platoon and predict the queue length at isolated intersections. They propose a multi-layer gated recurrent unit (GRU) network to understand the mechanism of queue length evolution. A case study of vehicle departure pattern and queue length prediction is presented with AVI data obtained from an isolated intersection in Xuancheng, Anhui province, China for the first quarter of 2018. The results of the case study indicate that their work has good application prospects. The proposed multi-layer GRU network has potential to guide the signal scheme optimisation.