The invention discloses a CAV speed guidance system based on deep reinforcement learning. The CAV speed guidance system comprises a vehicle-mounted system which detects vehicle driving data and vehicle state information data; the roadside monitoring system detects a driving environment, and vehicle information data and pedestrian information data on different roads, and matches the pedestrian and vehicle information data with a lane-level road link to obtain a data packet; the vehicle-road cooperative cloud computing center processes and stores the received data and sends the processed data to the mobile edge computing center; and the mobile edge calculation center performs comprehensive risk assessment on the road accident risk, constructs a Markov decision process and a speed guidance model of a multi-target additional reward function, constructs the multi-target additional reward function to calculate the optimal guidance speed for the CAV, and sends the optimal guidance speed of the CAV to the vehicle-mounted system. The problem of communication delay is solved; and a multi-target environment reward mechanism is comprehensively integrated, so that the CAV guide speed, the traffic safety, the traffic stability and the traffic efficiency are improved.

    本发明公开了一种基于深度强化学习的CAV速度引导系统,包括:车载系统检测车辆行驶数据和车辆状态信息数据;路侧监控系统检测行车环境、不同道路上的车辆信息数据和行人信息数据,将行人及车辆信息数据与车道级道路链路进行匹配,得到数据包;车路协同云计算中心对接收的数据进行处理和存储,将处理后的数据发送给移动边缘计算中心;移动边缘计算中心对道路事故风险进行综合风险评估,构建多目标附加奖励函数的马尔科夫决策过程和速度引导模型,构建多目标附加奖励函数为CAV计算最优引导速度,将CAV最优引导速度发送给车载系统。解决了通信延迟问题;全面综合多目标环境奖励机制,提升CAV引导速度对交通安全性、稳定性及通行效率。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    CAV speed guidance system and method based on deep reinforcement learning


    Weitere Titelangaben:

    一种基于深度强化学习的CAV速度引导系统及方法


    Beteiligte:
    ZHOU ZHONGQI (Autor:in) / JIN BIAO (Autor:in) / LIU NING (Autor:in) / YANG DONG (Autor:in)

    Erscheinungsdatum :

    2024-02-27


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / H04W WIRELESS COMMUNICATION NETWORKS , Drahtlose Kommunikationsnetze



    On Deep Reinforcement Learning for Spacecraft Guidance

    Hovell, Kirk / Ulrich, Steve | AIAA | 2020


    ON DEEP REINFORCEMENT LEARNING FOR SPACECRAFT GUIDANCE

    Hovell, Kirk / Ulrich, Steve | TIBKAT | 2020


    Intersection Signal Control Based on Speed Guidance and Reinforcement Learning

    Lu, Gaohui / Rehman, Hamza / Chen, Xiatong et al. | SAE Technical Papers | 2023


    Quadcopter Guidance Law Design using Deep Reinforcement Learning

    Aydinli, Sevket Utku / Kutay, Ali Turker | IEEE | 2023


    REAL-TIME OPTIMAL ENTRY GUIDANCE BASED ON DEEP REINFORCEMENT LEARNING

    Cheng, Lin / Wang, Zhenbo / Zeng, Haorang | TIBKAT | 2021