The demand-oriented road improvement may cause inconsistency between roads of same type in terms of traffic channelization and control, and thus may reduce self-explainability of the roads. In this study, situation awareness is employed as theoretical foundation to evaluate the self-explainability of demand-oriented road improvement. Ten drivers were recruited to conduct a naturalistic study and performed a verbal commentary while driving on two roads of same type in Beijing. The one, which kept the initial design, acted as a control condition. Another one, which was channelized and controlled according to traffic demand, acted as the experimental condition. Then the drivers’ situation awareness was modeled using semantic networks. The content and structure analysis of these networks were analyzed. The results show that the former road is richer in situation awareness and has a higher self-explainability. The findings suggest that the demand-oriented road improvement is not beneficial to road safety due to poor self-explainability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    The Self-Explainability of Demand-Oriented Road Improvement


    Contributors:
    Yang, Yichi (author) / Ma, Jun (author) / Gao, Chun (author) / Huang, Jingbo (author) / Zhao, Yongqiang (author)

    Conference:

    International Conference on Transportation and Development 2018 ; 2018 ; Pittsburgh, Pennsylvania



    Publication date :

    2018-07-12




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Explainability of autonomous vehicle decision making

    WRAY KYLE HOLLINS / BENTAHAR OMAR / VAGADIA ASTHA et al. | European Patent Office | 2023

    Free access

    Explainability of Autonomous Vehicle Decision Making

    WRAY KYLE HOLLINS / BENTAHAR OMAR / VAGADIA ASTHA et al. | European Patent Office | 2021

    Free access

    Towards Explainability in Modular Autonomous System Software

    Zheng, Hongrui / Zang, Zirui / Yang, Shuo et al. | IEEE | 2023


    Enhancing Neural Network Explainability with Variational Autoencoders

    Tran, Loc / Dolph, Chester / Zhao, Derek | AIAA | 2021


    ENHANCING NEURAL NETWORK EXPLAINABILITY WITH VARIATIONAL AUTOENCODERS

    Tran, Loc / Dolph, Chester / Zhao, Derek | TIBKAT | 2021