Neural network based vehicle-following model for mixed traffic conditions

摘要

Car-following behaviour is well studied and analyzed in the last fifty years for homogeneous traffic.However in the mixed traffic, following behaviour is found to vary based on type of lead and followingvehicles. In this study, a neural network based model is proposed to predict the following behaviour fordifferent lead and following vehicle-type combinations. Performance of the model is studied using datacollected for six vehicle-type combinations. A multi-layer feed-forward back propagation network isused to predict vehicle-type dependent following behaviour by incorporating the vehicle- type as inputinto the model. The neural network model is then integrated into a simulation program to study themacroscopic behaviour of the model. Performance of the proposed neural network model is comparedwith the conventional Gipps‟ model at microscopic and macroscopic level. This study prompts the needfor considering vehicle-type dependent following behaviour and ability of neural networks to modelthis behaviour in mixed traffic conditions.