Analysis and Modeling of Vehicle Following Behavior in Mixed Traffic Conditions

Abstract

Abstract Car following models replicate the behaviour of a car following another car. In mixed traffic conditions, leader-follower vehicle types are not only car-car cases but also there are different combinations of vehicles (e.g., car-two wheeler and heavy vehicle-auto-rickshaw). Due to weak lane discipline, the follower is unable to strictly follow the lead vehicle. The other types of following behaviour like staggered following, following between vehicles, etc. are also observed under mixed traffic conditions. Depending on speed and position of vehicles in front, the subject vehicle may follow a leading vehicle with varying levels of lateral separation or stagger. The nature, extent and impact of such interactions need to be investigated for characterizing following behaviour under mixed traffic conditions. Hence, the present study focuses on analysis and modelling of vehicle following behaviour under mixed traffic conditions. The current study uses an open access mixed traffic trajectory data collected on an urban arterial road in Chennai city, India. The collected dataset includes 3005 vehicle trajectories with a total of 111,629 observations. To identify the different types of following behaviour, the extent of overlap (%) between leader-follower pair was used. The vehicle following behaviour was classified into three types: 1) Car Following 2) Staggered following and 3) Following between two vehicles. The vehicle following behaviour were analysed for different categories of vehicles and also, for different types of follower-leader pair. When the follower is a smaller size vehicle compared to a leader, it generally follows the leader. It was observed that when the vehicle size increases, staggered following behaviour of vehicle also increases. Subject vehicle chooses a following behaviour based on size of follower and leader, speeds of follower and leader, longitudinal gap between follower and leader, types of follower and leader. Multinomial Logistic Regression model was used to model the choices of vehicle following behaviour. This study has interesting implications in identifying vehicle-specific and vehicle following parameters for car following models to be adopted under mixed traffic and non-lane discipline traffic conditions.