The invention discloses an unmanned overtaking decision-making method based on DDPG and fused with time sequence information. According to the invention, states at a plurality of continuous moments, such as vehicle speed, wheel rotation speed, positions of adjacent vehicles, lane line distance detection and other state information, are obtained and processed to generate a multi-dimensional state input matrix. And inputting the state matrix into an overtaking decision control model, and directly outputting action control signals of the vehicle, such as an accelerator, a brake and a steering angle, so as to control the vehicle to complete an overtaking driving behavior. A neural network structure of the overtaking model is based on an Actor-Critic architecture, time sequence driving state information is fused into a multi-dimensional state matrix input by a neural network, and the proportions of state spaces at different moments are controlled through a time attenuation factor weight coefficient. Finally, a simulation experiment on a TORCS (ThOpenRacingCarrier) platform shows that the overtaking model fused with the time sequence information can control the unmanned vehicle to safely and accurately complete the overtaking task.

    本发明公开了融合时序信息的基于DDPG的无人驾驶超车决策方法。本发明通过获取多个连续时刻的状态,如车辆速度、车轮转速、距离邻近其它车辆位置和车道线距离检测等状态信息,处理生成一个多维状态输入矩阵。然后将该状态矩阵输入到超车决策控制模型中,直接输出车辆的动作控制信号,如油门、刹车和转向角度,从而控制车辆完成超车驾驶行为。超车模型的神经网络结构基于Actor‑Critic架构,其中神经网络输入的多维状态矩阵融入了时间序列驾驶状态信息,通过时间衰减因子权重系数来控制不同时刻的状态空间所占的比重。最后通过在TORCS(TheOpenRacingCarSimulator)平台上的仿真实验表明,融合时序信息的超车模型能够控制无人车安全、精准地完成超车任务。


    Access

    Download


    Export, share and cite



    Title :

    DDDPG-based unmanned overtaking decision-making method fusing time sequence information


    Additional title:

    融合时序信息的基于DDPG的无人驾驶超车决策方法


    Contributors:
    HUANG ZHIQING (author) / ZHANG CHENYANG (author) / WANG SHUQING (author) / ZHAO RUI (author)

    Publication date :

    2023-05-16


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Overtaking decision-making method based on game theory

    WANG PENGWEI / GUO DONG / XU YI et al. | European Patent Office | 2024

    Free access

    Automatic overtaking method for unmanned vehicle

    WANG FENGHUI / GAO YANHE / FANG XINGHONG et al. | European Patent Office | 2022

    Free access

    Automated Highway Overtaking: A Perspective from Decision-Making

    Tomar, Abhishek Singh / Forrai, Alexandru / Tillema, Frans | SAE Technical Papers | 2021



    Automated Highway Overtaking: A Perspective from Decision-Making

    Tomar, Abhishek Singh / Forrai, Alexandru / Tillema, Frans | British Library Conference Proceedings | 2021