Neuro - fuzzy model for car following behaviour in heterogeneous road traffic condition

Abstract

Since the past few decades, the car following theory has been a key element in the microscopic simulation models and has gained widespread attention. The theory aims to describe the way a vehicle follows a leading vehicle on a roadway. The road traffic situation of Bangladesh is heterogeneous in nature, where vehicles vary widely in static and dynamic characteristics and share the same width of carriageway. Therefore, the car following behaviour under this condition is expected to be quite different from that of homogeneous or car dominated traffic. This justifies the development of car following models for heterogeneous road traffic condition. However, in reality, the car following behaviour of a driver is influenced by a vague perception of the stimuli and his decision making mechanism is driven by fuzzy rules gained by knowledge and experience. Therefore, the deterministic models are unable to emulate the complex and multi ruled behaviour of the driver in an uncertain environment of the road. Considering these issues, this study aims to develop Neuro-Fuzzy models to depict car following behaviour in heterogeneous road traffic condition. In this study, car following data have been collected in the form of video footage of vehicular movements at one of the busiest roads of Dhaka city. From the video footage, car following parameters have been extracted by converting the two dimensional coordinates of vehicle trajectories of the video footage into real world positions along the road. From these positions, various car following parameters such as distance, speed and acceleration were calculated. A total of three models were developed by using the' Fuzzy Logic Toolbox' of MATLAB for three different types of motorised vehicles. The models were calibrated through the Adaptive Neuro-Fuzzy Inference System of the same toolbox, in order to alter the membership functions such that the models are able to replicate the real scenario of vehicular movement accurately. In order to validate the models, a simulation model was developed by using SIMULINK, which is capable to produce the time dependent response of the models pertaining to various car following parameters. The demonstration of local stability was performed through numerical examples, which performed satisfactorily.