A mandatory lane changing decision model for self-driving vehicles is proposed for forced lane changing constrained by objective conditions. First, the NGSIM dataset is analysed to extract the trajectories of completed mandatory lane changing and the trajectories of uncompleted mandatory lane changing as the training data of the lane changing decisionmaking model, and for the problem that it is difficult to obtain the trajectory data of the trajectories that have the intention of mandatory lane changing but have not succeeded in changing lanes, this paper puts forward a method of extracting the target trajectories through the transverse acceleration thresholds, and the lateral acceleration thresholds are obtained from the vehicle's mandatory lane changing through the DBSCAN clustering. The transverse acceleration threshold is obtained by DBSCAN clustering, and the unsuccessful vehicle trajectory is extracted from the trajectory of the completed forced lane change according to this threshold. Finally, based on the Transformer encoder unit, the decision-making model of forced lane changing for self-driving vehicles is constructed. The model is verified to be able to achieve accurate decision-making for forced lane changing, which illustrates the reasonableness of filtering the unfinished trajectories of forced lane changing based on the transverse acceleration threshold, and the accuracy of the forced lane changing model reaches 95.6%, which is better than that of the long and short-term memory LSTM network model and the gated recurrent unit GRU model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on vehicle mandatory lane change decision model based on trajectory analysis


    Beteiligte:
    Wu, Jinsong (Herausgeber:in) / Ma'aram, Azanizawati (Herausgeber:in) / Zhu, Fang (Autor:in) / Xia, Hanqing (Autor:in) / Ma, Zechao (Autor:in) / Zhang, Lin (Autor:in) / Zhao, Yingjie (Autor:in) / Wang, Yuanrong (Autor:in)

    Kongress:

    Ninth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2024) ; 2024 ; Guilin, China


    Erschienen in:

    Proc. SPIE ; 13251


    Erscheinungsdatum :

    28.08.2024





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Hazard-Based Model of Mandatory Lane Change Duration

    Wu, Jiangling / Zhang, Shengrui / Singh, Amit Kumar et al. | ASCE | 2018


    An optimal mandatory lane change decision model for autonomous vehicles in urban arterials

    Cao, Peng / Hu, Yubai / Miwa, Tomio et al. | Taylor & Francis Verlag | 2017


    Analysing driving efficiency of mandatory lane change decision for autonomous vehicles

    Cao, Peng / Xu, Zhandong / Fan, Qiaochu et al. | IET | 2018

    Freier Zugriff

    Analysing driving efficiency of mandatory lane change decision for autonomous vehicles

    Cao, Peng / Xu, Zhandong / Fan, Qiaochu et al. | Wiley | 2019

    Freier Zugriff