This paper proposes an end-to-end driving algorithm based on deep learning for the environmental perception problem of intelligent connected vehicles. The algorithm combines behavioral cloning technology and realizes real-time perception and decision-making of complex driving scenarios by learning from human driving data. This paper first designs a perception model based on convolutional neural networks and long short-term memory networks to process multimodal sensor data, extract environmental features, and ensure accurate judgment of vehicles under various road conditions. Then, the performance of the algorithm is evaluated and verified by building a virtual driving simulation environment. Compared with traditional methods, the proposed algorithm has significantly improved accuracy and efficiency, with an average error controlled within 0.1 meters and a decision time shortened to 0.05 seconds, showing good practicality and foresight. The research in this paper provides new ideas and methods for environmental perception and autonomous driving technology of intelligent connected vehicles, and lays the foundation for the development of more efficient and safer autonomous driving systems in the future.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Environmental Perception Algorithm of Intelligent Connected Vehicles Based on Deep Learning


    Contributors:
    Zhao, Kangqi (author) / Guan, Donghe (author)


    Publication date :

    2024-10-23


    Size :

    928476 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Cooperative Perception with Deep Reinforcement Learning for Connected Vehicles

    Aoki, Shunsuke / Higuchi, Takamasa / Altintas, Onur | IEEE | 2020


    COOPERATIVE PERCEPTION WITH DEEP REINFORCEMENT LEARNING FOR CONNECTED VEHICLES

    Aoki, Shunsuke / Higuchi, Takamasa / Altintas, Onur | British Library Conference Proceedings | 2020


    Environmental Perception for Intelligent Vehicles

    Tang, Xiaoliang / Li, Yuanxiang / Wei, Xian | Springer Verlag | 2022


    Evidential deep learning-based multi-modal environment perception for intelligent vehicles

    Geletu, Mihreteab Negash / Giurgi, Danut-Vasile / Josso-Laurain, Thomas et al. | IEEE | 2023


    Review on Uncertainty Estimation in Deep-Learning-Based Environment Perception of Intelligent Vehicles

    Yin, Huilin / Chen, Zhaoru / Yan, Jun et al. | British Library Conference Proceedings | 2022