Fuzzy Logic for Improved Dilemma Zone Identification: A Driving Simulator Study

This is an author's peer-reviewed final manuscript, as accepted by the publisher. The published article is copyrighted by the Transportation Research Board of the National Academies and can be found at: http://www.trb.org/Publications/PubsTRRJournal.aspx.Type-II dilemma zones are the segment of roadway approaching an intersection where drivers have difficulty deciding to stop or proceed at the onset of the circular yellow (CY) indication. Signalized intersection safety is improved when dilemma zones are correctly identified and steps are taken to reduce the likelihood that vehicles are caught in such zones. This research purports that using driving simulators as a means to collect driver response data at the onset of the CY indication is a valid methodology to augment our analysis of decisions and reactions made within the dilemma zone. The data obtained was compared against that from previous experiments documented in the literature and the evidence suggests that driving simulation is valid for describing driver behavior under the given conditions. After validating the data, fuzzy logic was proposed as a tool to model driver behavior in the dilemma zone, and three models were developed to describe driver behavior as it relates to the speed and position of the vehicle. These models were shown to be consistent with previous research on this subject and were able to predict driver behavior with up to 90% accuracy