EXPLORATION OF ROUTE CHOICE BEHAVIOR WITH ADVANCED TRAVELER INFORMATION USING NEURAL-NETWORK CONCEPTS

A model of driver's route choice behavior under advanced traveler info rmation system (ATIS) is developed based on data collected from learni ng experiments using interactive computer simulation. The experiment s ubjected drivers to 32 simulated days in which they were to choose bet ween the freeway or a side road. A neural network model is used as a c onvenient modeling technique in this initial phase of the analysis. Th e results indicated that most subjects made route choices based mainly on their recent experiences. It was also demonstrated that route choi ce behaviors are related to the personal characteristics as well as th e characteristics of the respective routes. Travel experiences have le ss effect on the choice of the side road compared to the freeway and t he results indicate that the prediction accuracy of the model, the acc eptance rate of advice, and the quality of advice are closely correlat ed. The model developed here was for advice consistently provided at a level of 75 percent accuracy. The paper concludes with a discussion o f experimental limitations and suggestions for future research.