The invention discloses a multi-mode vehicle speed prediction method based on driving data, and the method comprises the steps: firstly collecting standard condition data, extracting a driving mode, and carrying out the training of a classifier through the data of a standard condition for real-time condition recognition in order to determine the composition of a vehicle speed mode in a current driving environment; acquiring and preprocessing driving data, identifying real-time road working conditions by utilizing the acquired and processed data, determining basic modal composition of a vehiclespeed prediction model, updating parameters of the model by utilizing the acquired driving data, and finally predicting by utilizing the vehicle speed prediction model which is updated on line. The vehicle speed can be predicted in real time according to the difference between the driving environment and the driver characteristics, the prediction duration is prolonged on the premise that the prediction precision is guaranteed, and therefore the safety performance of an automobile system is improved; for a hybrid electric vehicle and an electric vehicle, the energy recovery efficiency during braking can be improved.

    本发明公开了一种基于驾驶数据的多模态车速预测方法,首先收集标准工况数据,提取驾驶模态,为确定当前驾驶环境下车速模态的组成,需要利用标准工况的数据进行分类器的训练以用于实时的工况识别;然后对驾驶数据进行采集及预处理,接着利用采集处理后的数据进行实时道路工况的识别并确定车速预测模型的基本模态组成,同时利用采集的驾驶数据对模型的参数进行更新,最后利用在线更新的车速预测模型进行预测。本发明能够根据驾驶环境和驾驶员特性的差异实时预测车速,在保证预测精度的前提下增加预测时长,从而提高汽车系统的安全性能;对于混合动力汽车和电动汽车,能够提高制动时的能量回收效率。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multi-modal vehicle speed prediction method based on driving data


    Weitere Titelangaben:

    一种基于驾驶数据的多模态车速预测方法


    Beteiligte:
    WU GANG (Autor:in) / YU BOYANG (Autor:in) / WANG CHUNYAN (Autor:in) / ZHOU QINGHUA (Autor:in) / SHI SHUAIPENG (Autor:in) / FENG JIAN (Autor:in) / YAN SHENXIANG (Autor:in) / ZHANG ZIYU (Autor:in) / WU ZIHAN (Autor:in) / HE PENG (Autor:in)

    Erscheinungsdatum :

    2020-07-28


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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 / G06K Erkennen von Daten , RECOGNITION OF DATA / G07C TIME OR ATTENDANCE REGISTERS , Zeit- oder Anwesenheitskontrollgeräte



    BiGRU based online multi-modal driving maneuvers and trajectory prediction

    Zhi, Yongshuai / Bao, Zhipeng / Zhang, Sumin et al. | SAGE Publications | 2021


    MULTI-MODAL DRIVING DANGER PREDICTION SYSTEM FOR AUTOMOBILES

    COSATTO ERIC / MELVIN IAIN / GRAF HANS PETER | Europäisches Patentamt | 2017

    Freier Zugriff

    Electric vehicle charging power prediction system based on multi-modal data perception

    WANG SHUANGXIAN / MU LINGBO / PENG LONGFENG | Europäisches Patentamt | 2022

    Freier Zugriff

    Multi-modal vehicle trajectory prediction method based on hierarchical order network

    WANG JUNSHENG / XU WEIXIANG | Europäisches Patentamt | 2023

    Freier Zugriff

    MULTI-MODAL MOVEMENT PLAN FRAMEWORK FOR AUTOMATIC DRIVING VEHICLE

    ZHANG YAJIA / LI DONG / ZHANG RANRAN et al. | Europäisches Patentamt | 2020

    Freier Zugriff