Trajectory prediction (TP) of surrounding vehicles (SVs) is crucial for autonomous vehicles (AVs) to understand traffic situations and achieve safe-efficient decision-making and motion planning. However, different drivers’ personalized driving preferences will bring uncertainties for long-term TP in the mixed traffic environment. To this end, this paper proposes a TP model with interaction awareness and driving style awareness for long-term TP of heterogeneous SVs. Firstly, the driving conditions in the highD dataset are distinguished, and three different driving styles of the vehicle in the car-following condition are obtained based on an unsupervised clustering algorithm. Then, an encoder-decoder architecture based on novel lane attention and multi-head attention mechanisms is proposed, where the encoder analyzes historical trajectory patterns and the decoder generates future trajectory sequences. The lane attention mechanism enhances the spatial perception capability of vehicles towards the target lane, and the multi-head attention mechanism extracts high-dimensional global interaction information about the heterogeneous vehicle group (HVG) surrounding the target vehicle (TV). Experimental results show that the proposed model outperforms state-of-the-art models in root-mean-square-error (RMSE) for long-term TP and exhibits excellent adaptability to diverse driving tasks. Moreover, this paper verifies that the driving style topology within the HVG has multiple impacts on the TP accuracy of the TV.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Interaction-Aware and Driving Style-Aware Trajectory Prediction for Heterogeneous Vehicles in Mixed Traffic Environment


    Beteiligte:
    Zhang, Qixiang (Autor:in) / Xing, Yang (Autor:in) / Wang, Jinxiang (Autor:in) / Fang, Zhenwu (Autor:in) / Liu, Yahui (Autor:in) / Yin, Guodong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.07.2025


    Format / Umfang :

    2837739 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Safety-Balanced Driving-Style Aware Trajectory Planning in Intersection Scenarios With Uncertain Environment

    Wang, Xiao / Tang, Ke / Dai, Xingyuan et al. | IEEE | 2023

    Freier Zugriff

    Context-Aware Intention and Trajectory Prediction for Urban Driving Environment

    Meghjani, Malika / Verma, Shashwat / Eng, You Hong et al. | Springer Verlag | 2020


    Context-Aware Intention and Trajectory Prediction for Urban Driving Environment

    Meghjani, Malika / Verma, Shashwat / Eng, You Hong et al. | TIBKAT | 2020


    Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehicles

    Zhou, Weitao / Cao, Zhong / Xu, Yunkang et al. | IEEE | 2022


    Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks

    Mo, Xiaoyu / Xing, Yang / Lv, Chen | ArXiv | 2020

    Freier Zugriff