In transportation studies, modeling human learning and decision-making processes plays a key role in developing realistic safety countermeasures and appropriate crash-mitigation strategies. In this study, a human learning model was created that captures the cognitive structure of human memory. The relationship between long-term and short-term memories was incorporated into a reinforcement learning technique to construct the human learning model. The model was then applied to dilemma zone data collected in a simulator study. Dilemma zone is an area of roadway ahead of the signalized intersection in which drivers have difficulty deciding whether to stop or proceed through at the onset of yellow. Driver choice behavior and learning process in dilemma zones was modeled, taking into account drivers’ experiences at the previous intersections, and was compared to a pure machine learning model. The results of the model revealed lower and faster-merging errors when human learning was considered in training agents. The human learning model for dilemma zones presented here could be used to evaluate dilemma zone mitigation algorithms by considering their effects on driver agents.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Modeling Human Learning and Cognition Structure: Application to Driver Behavior in Dilemma Zone


    Contributors:


    Publication date :

    2016-07-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown