The invention provides a target network training method, device and system for automatic driving, and the method comprises the steps: generating first state information and environment identification information corresponding to the first state information through a simulation environment processing module, and enabling the environment identification information to be used for representing the driving information of a target vehicle in a preset range; inputting the first state information into a hierarchical graph neural network to obtain a first coding feature and a first decoding feature corresponding to the first state information; inputting the first coding feature into a multi-layer perceptron to obtain decoding information corresponding to the first coding feature; determining a first loss value of the hierarchical graph neural network according to the environment identification information and the decoding information; and determining a second loss value of the first actor network; and updating parameters of the hierarchical graph neural network and the first actor network according to the second loss value. According to the technology of the application, the learning ability of the hierarchical graph neural network for the key information is improved, so that the decision performance of the target network is improved.

    本申请提出一种用于自动驾驶的目标网络的训练方法、设备以及系统,其中的方法包括:利用仿真环境处理模块生成第一状态信息和第一状态信息对应的环境标识信息,环境标识信息用于表征目标车辆的预设范围内的行车信息;将第一状态信息输入层次化图神经网络,得到第一状态信息对应的第一编码特征和第一解码特征;将第一编码特征输入多层感知机,得到第一编码特征对应的解码信息;根据环境标识信息和解码信息,确定层次化图神经网络的第一损失值;以及,确定第一演员网络的第二损失值;根据第二损失值更新层次化图神经网络和第一演员网络的参数。根据本申请的技术,提升了层次化图神经网络对于关键信息的学习能力,从而提升了目标网络的决策性能。


    Access

    Download


    Export, share and cite



    Title :

    Target network training method, device and system for automatic driving


    Additional title:

    用于自动驾驶的目标网络的训练方法、设备以及系统


    Contributors:

    Publication date :

    2023-07-11


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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



    Target network training method for automatic driving, electronic equipment and system

    ZHANG HENGZHANG / WANG TIANCHENG | European Patent Office | 2023

    Free access

    Training method of automatic driving algorithm model, automatic driving method and device

    WEI KAI / YIN PING / SUN XINGYAN | European Patent Office | 2024

    Free access

    Target monitoring method and automatic driving system

    LI JIYANG / YAN XUESHU / LIU BIN et al. | European Patent Office | 2021

    Free access

    Automatic driving dangerous target determination method and device

    CHEN RUI / GONG SHENGBO / ZOU WENTAO et al. | European Patent Office | 2021

    Free access

    METHOD AND SYSTEM FOR TRAINING AUTOMATIC DRIVING MODEL

    LEE CHIEH / KUO CHIN-PIN | European Patent Office | 2025

    Free access