Advanced Assistance Driver Systems (ADAS) adaptation with respect to driver driving style is a research field of major interest, given the additional benefits that could be obtained in terms of comfort and safety perceived by the user. In this work, a personalized Adaptive Cruise Control (ACC) oriented driving style features extraction method is proposed, meant to be used to choose an ACC tuning which better fits the driver on road behaviour. The method exploits an Artificial Neural Network driver model, capable of capturing the driver behaviour in a car following scenario, trained and validated over real data. From a closed-loop model analysis in a simulation environment driving style features are then extracted, looking at the system response to variations of the preceding vehicle speed. Finally, the effectiveness of the extracted features for a non-trivial characterization of the driver behaviour is assessed, comparing the results obtained considering three different drivers.


    Access

    Download


    Export, share and cite



    Title :

    A personalized Adaptive Cruise Control driving style characterization based on a learning approach



    Publication date :

    2019-01-01



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    629



    A personalized Adaptive Cruise Control driving style characterization based on a learning approach

    Nava, Dario / Panzani, Giulio / Zampieri, Pierluigi et al. | IEEE | 2019


    Research on Adaptive Cruise Control Strategy Considering Driving Style

    Hou, Ruiyu / Hui, Fei / Kuang, Ruimin et al. | IEEE | 2023


    Multimodel Approach to Personalized Autonomous Adaptive Cruise Control

    Bolduc, Andrew Phillip / Guo, Longxiang / Jia, Yunyi | IEEE | 2019


    A learning model for personalized adaptive cruise control

    Chen, Xin / Zhai, Yong / Lu, Chao et al. | IEEE | 2017


    A Learning Model for Personalized Adaptive Cruise Control

    Chen, Xin / Zhai, Yong / Lu, Chao et al. | British Library Conference Proceedings | 2017