A ROUTE ADVICE AGENT THAT MODELS DRIVER PREFERENCES
Seth Rogers, Claude-Nicolas Fiechter, Pat Langley · 1999
Generating satisfactory routes for driving is a challenging task because the desirability of a particular route depends on many factors and varies from driver to driver. Current route advice systems present a single route to the driver based on static evaluation criteria, with little or no recourse if the driver finds this solution unsatisfactory. In this paper, we propose a more flexible approach, the Adaptive Route Advisor. Our route advice agent creates a model of the driver's route preferences and generates routes that satisfy these preferences. The driver interacts with the system to improve the suggested route and refine the user model. As the preference model becomes more accurate, the initial route suggestions become more satisfactory to the driver, resulting in better driving routes with less driver effort. We also present a pilot study on using route selections to construct a personalized model of driver preferences. Keywords: Machine learning for user modeling, interface ada...