01472382

Component

https://doi.org/10.3141/2383-01

http://scholar.google.com...kawa&publication_year=2013

This paper presents a method to model a driver’s en route learning process and changes in route choice at each decision node. A model based on Bayesian networks is proposed to describe the en route updating of the driver’s knowledge of the traffic state. A random utility–based model is developed to predict en route choices. A case study based on probe data is carried out to illustrate the development of the model and analyze the dynamic route choice problem. The results show that the model in which a driver’s choice of making decisions en route is taken into account has a better goodness of fit. The probability of making a choice en route is related to the distance from the origin and the spatial scale of the intersection at the decision node.

01506426

13-0646

English

pp 1–9

2013

Transportation Research Record: Journal of the Transportation Research Board

9780309287128

Print

Figures (6) ; References (19) ; Tables (3)

Bayes' theorem; Choice models; Drivers; Learning; Route choice; Travel behavior

Highways; Planning and Forecasting; I70: Traffic and Transport

TRIS, TRB, ATRI

Feb 5 2013 12:15PM

• Analysis of Effects of Activities While Traveling on Travelers’ Sentiment
• Drivers’ Perception of Route Alternatives as Indicator for the Indifference Band
• Geographic Distribution of E-Shopping: Application of Structural Equation Models in the Twin Cities of Minnesota
• Semantic Annotation of Global Positioning System Traces: Activity Type Inference
• Using Smartphones and Sensor Technologies to Automate Collection of Travel Data
• Who Are the Drivers of Peak Car Use? A Decomposition of Recent Car Travel Trends for Six Industrialized Countries