Modeling Lane-Changing Behaviors in Merging Areas of Urban Expressways in Nanjing, China

Abstract

Merging bottlenecks in urban expressways have attracted much attention in recent years. In this paper, vehicular mandatory lane-changing (MLC) data are collected from Yingtian Avenue in Nanjing, China using cameras. Based on a series of video processing algorithms, 656 MLC behaviors of 1,560 vehicles are extracted from videos. A logistic regression model is proposed to depict MLC at the merging bottleneck and estimate the possibility of accepting gaps for merging, which is validated by precision testing and simulation. During the simulation, a discretionary lane-changing (DLC) model is utilized and calibrated to describe vehicular DLC behaviors for the sake of consistency and completeness. Finally, by simulating different arrival rates of mainline and ramp, a linear regression model is built to predict breakdown at merging bottlenecks. According to data analysis, the MLC model represents high precision during the decision-making process. Besides, the breakdown prediction model implies strong correlation between traffic demand and breakdown occurrence.