An advanced traveler navigation system adapted to route choice preferences of the individual users

The majority of existing navigation systems only account for a single aspect of the route choice, like travel time or distance, in finding the optimal route for the trips of their users in the network. However, research shows there are a variety of different factors with different levels of importance that can affect the route choice behavior of users, while the relative importance of these factors also varies with trip purpose of the users. In this research, we first identify the different factors that travelers take into account in their route choice decision in the network. A stated preference survey is used to show the heterogeneity in preferences of the users regarding the relative importance of these factors. The results of the survey also indicate the partial inability of existing navigation systems in suggesting the routes that match the preferences of users. This shortcoming of navigation systems can be attributed to ignoring the diversity in influential factors and the heterogeneity in preferences of the users by these systems in the approximating the route choice behavior of travelers. To resolve the problem, we propose a dynamic mixed logit route choice model to include the effects of information and learning to estimate parameters of a multivariable general cost function for individual users based on their own historical route choice data over time. On this basis, we propose the concept of a smart navigation system that can gather the required information from real-time and online sources to suggest the routes that best match the users' own preferences.