Eco-driving plays an increasingly important role in intelligent transportation systems, where the vehicle-following economy and safety are receiving increasing attention in recent years. In this context, this article proposes a novel deep deterministic policy gradient (DDPG)-based driving control strategy for connected electric vehicles (CEVs) under vehicle-following scenarios. Three original contributions make this article distinctive from existing studies. First, a multi-objective optimization problem including driving safety, passenger comfort, and the driving economy for the following vehicle is established, in which the battery capacity degradation cost is first considered in the vehicle-following problem. Second, a DDPG-based driving control strategy is proposed where a penalty is introduced into the multi-objective optimization reward function to accelerate the convergence process. Third, the coupling relationship of the three objectives is carefully studied. Different weighting factors are tested and analyzed to balance the three objectives. Detailed discussion and comparison under different driving cycles validate the superiority of the proposed method, e.g., a 16–31% reduction of battery capacity degradation cost with better safety and comfort, compared with existing vehicle-following strategies. This work makes a potential contribution to the artificial intelligence application of intelligent transportation systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-Objective Optimization of Vehicle-Following Control for Connected Electric Vehicles Based on Deep Deterministic Policy Gradient


    Weitere Titelangaben:

    Sae Int. J. Elec. Veh


    Beteiligte:
    Li , Heng (Autor:in) / Peng, Hui (Autor:in) / He, Wei (Autor:in) / Gao, Yang (Autor:in) / Wu, Yue (Autor:in) / Zhang, Yulin (Autor:in)


    Erscheinungsdatum :

    2023-07-17


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Multi-Task Vehicle Platoon Control: A Deep Deterministic Policy Gradient Approach

    Mehran Berahman / Majid Rostami-Shahrbabaki / Klaus Bogenberger | DOAJ | 2022

    Freier Zugriff

    Unmanned Aerial Vehicles Control Study Using Deep Deterministic Policy Gradient

    Sun, Dan / Gao, Dong / Zheng, Jianhua et al. | IEEE | 2018




    Developing Flight Control Policy Using Deep Deterministic Policy Gradient

    Tsourdos, Antonios / Dharma Permana, Ir. Adhi / Budiarti, Dewi H. et al. | IEEE | 2019