Abstract In cooperative automated driving, the task of lateral and longitudinal vehicle control can be shared by driver and automation. However, conflicting action intentions of the two partners could arise, which need to be resolved within limited time. This can be achieved through structured multimodal negotiation, called arbitration. In order to explore intuitive interaction patterns for arbitration situations, insights from human-human interaction might be transferred. Accordingly, in a field study, couples holding hands or walking arm in arm were videotaped and interviewed when a conflict concerning motion control has been observed. The analysis of the data shows that conflict situations concerning velocity and/or direction of movement occur in natural human-human interaction and that these types of conflict can be dependent on each other. Furthermore, partners use different interaction resources to successfully solve these situations. Results are transferred to cooperative automated driving and an example of an interaction pattern is presented.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning from the Best – Naturalistic Arbitration for Cooperative Driving


    Beteiligte:


    Erscheinungsdatum :

    24.06.2017


    Format / Umfang :

    12 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Cooperative Safety Based on Naturalistic Driving Data

    Li, Yingfeng “Eric” / Gibbons, Ronald B. / Kim, Bumsik | ASCE | 2022


    Naturalistic Driving Study

    Raphael Grzebieta | DOAJ | 2015

    Freier Zugriff

    Learning From Naturalistic Driving Data for Human-Like Autonomous Highway Driving

    Xu, Donghao / Ding, Zhezhang / He, Xu et al. | IEEE | 2021


    Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving

    Xu, Donghao / Ding, Zhezhang / He, Xu et al. | ArXiv | 2020

    Freier Zugriff

    Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning

    Li, Sisi / Wang, Wenshuo / Mo, Zhaobin et al. | IEEE | 2018