A Bayesian adaptive inference approach to estimating herterogeneous gap acceptance functions

Document Type

Conference Proceeding

Publication Date



Department of Civil, Environmental, and Geospatial Engineering; Center for Cyber-Physical Systems


This paper presents a Bayesian adaptive inference approach to estimating heterogeneous gap acceptance functions. The proposed approach models each individual driver behavior among gaps, which is an extension of the Mahmassani and Sheffi’s gap acceptance model for each individual driver. To estimate the heterogeneous gap acceptance parameters for each individual driver, the authors develop a Bayesian adaptive inference framework combing a trial-to-trial information gain strategy that can estimate multiple dimensional parameters to identify the heterogeneous driver’s behavior on gap acceptance. The authors implement the Bayesian adaptive inference framework and conduct experiment analysis to examine the convergence of the algorithm.

Publisher's Statement

This paper was sponsored by TRB committee AHB45 Traffic Flow Theory and Characteristics.

Publication Title

Transportation Research Board 94th Annual Meeting