Analysing inequity in land use and transportation models by genetic algorithm for realistically quantified penetration rate of Advanced Driving System Equipped Vehicles

The continued evolutions in automated driving technologies and their rapid testing on common roads make it necessary to evaluate their impacts on land use and transportation models. It is crucial to quantify the number of advanced driving system-equipped vehicles that are going to be part of transportation networks. On the other hand, the intuitive property of these vehicles to create an induced demand can bring both positive and negative effects on the travel equilibrium costs that create inequity. To cater for the gap of realistic quantification of penetration rate and inequity evaluation on the inclusion of such vehicles; this research crafts a detailed and effective methodology. This research formulates a convex minimization problem as a lower-level part of the bi-level optimization model intending to minimize the travel equilibrium cost for all OD pairs. Also, acts as an assignment of demand to the network following the stochastic user equilibrium approach by using the Frank-Wolfe algorithm. Whereas, the upper level of the model maximizes the production of newly generated demand incorporating inequity constraints. A genetic algorithm is used to solve the multi-objective fitness function yielded from the bi-level optimization model by application of the model on a real transportation network of the city of Genoa, Italy.