The invention belongs to the technical field of active safety of electric vehicles, and particularly relates to a driving intention reasoning method for LSTM network optimization based on complete transfer learning. Comprising the following steps of 1, establishing a driving intention multivariable fractional order grey model; 2, judging whether the source domain and the target domain have similarity or not; step 3, designing and completely migrating the LSTM network; and 4, performing optimization calculation on the fractional order to determine the driving intention. The driving intention is inferred directly according to the road condition, the interference information is little, and the precision is high; due to the introduction of the grey absolute correlation degree, probability calculation of a large amount of data is omitted, and the calculation burden is greatly reduced.

    本发明属于电动汽车主动安全技术领域,具体的说是一种基于完全迁移学习的LSTM网络优化的驾驶意图推理方法。包括以下步骤:步骤一、建立驾驶意图多变量分数阶灰色模型;步骤二、判断源域与目标域是否具有相似性;步骤三、对LSTM网络进行设计与完全迁移;步骤四、对分数阶进行优化计算,从而确定驾驶意图。本发明直接由路面工况推理驾驶意图,干扰信息少,精度较高;灰色绝对关联度的引入省去了大量的数据的概率计算,计算负担大大减小。


    Access

    Download


    Export, share and cite



    Title :

    Driving intention reasoning method for LSTM network optimization based on complete transfer learning


    Additional title:

    一种基于完全迁移学习的LSTM网络优化的驾驶意图推理方法


    Contributors:
    LIAN YUFENG (author) / LI BINGLIN (author) / LI YAN (author) / LIU SHUAISHI (author) / SUN ZHONGBO (author) / LIU YANPING (author) / LIU KEPING (author)

    Publication date :

    2023-09-12


    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




    Computer assisted driving support based on intention reasoning

    Takagi, T. / Nishi, T. / Yasuda, D. | IEEE | 2000


    Driving intention prediction algorithm based on TPA-LSTM for autonomous vehicles

    Wu, Yanhong / Gao, Jianbo / Wu, Huateng et al. | SAGE Publications | 2024


    Vehicle lane changing intention recognition method based on TCN-LSTM network

    XIANG QIAOJUN / ZHOU WEI / YUAN RENTENG et al. | European Patent Office | 2024

    Free access

    Lane changing intention prediction method based on LSTM

    WANG WEIDA / YANG CHAO / QIE TIANQI et al. | European Patent Office | 2020

    Free access