The aim of this paper is to explore route choice on road networks. The route choice model is divided into three levels: the generation of alternatives, the perception of alternatives and choice set, and finally the choice of alternatives belonging to the choice set. A deterministic, selective, multi-criteria approach is used to generate the routes. A covering measure is calculated by comparing observed and generated paths to take into account which routes are currently chosen. With regards to perception level, some simplifying hypotheses are assumed: one choice set is considered, the perception probability of the considered choice set is equal to one, and all the alternatives are characterized by the same probability to be perceived. Choice level is treated using two different approaches: a random utility model and a fuzzy utility model are specified, calibrated and validated. A new fuzzy utility model is specified in order to simulate route choice level. The specified models are compared in order to highlight their similarities, advantages and disadvantages. The database used for calibrations is obtained with a survey carried out in Catania (Italy), concerning dairy products delivery to local retailers. The models are calibrated. It is possible to open new lines of research by comparing the results obtained from consolidated logit models and from fuzzy models.
