The invention discloses a pedestrian-vehicle collision risk degree analysis method based on an autonomous vehicle, and the method comprises the steps: dividing the street crossing behaviors into different habit types through Gaussian clustering according to the street crossing features in a pedestrian street crossing historical data set, and employing a joint probability distribution function to obtain a pedestrian-vehicle collision risk degree; an automatic driving vehicle is helped to obtain a future possible state set according to the current motion state of a pedestrian, a pedestrian-vehicle dynamic space-time relation is considered through a GCN graph convolutional neural network, a future possible trajectory set of the pedestrian is obtained, finally, the trajectory collision probability and the minimum encounter distance are considered, feature dimension reduction is performed by using a matter element extension theory, and the pedestrian collision probability is reduced. And establishing a risk degree function to realize real-time judgment of the human-vehicle collision risk degree. The method focuses on the characteristic that the pedestrian motion state has sudden change, more specifically considers the influence of the pedestrian-vehicle space-time relationship on the trajectory, improves the accuracy and credibility of the pedestrian-vehicle collision judgment result through the fusion of multiple indexes, further improves the intelligence of automatic driving, and improves the riding comfort and safety.

    本发明公开了一种基于自动驾驶汽车的人车碰撞危险度分析方法,首先根据行人过街历史数据集中的过街特征,通过高斯聚类将过街行为分为不同的习惯类型,利用联合概率分布函数,帮助自动驾驶车辆根据行人当前运动状态获取其未来可能状态集合,并通过GCN图卷积神经网络考虑人车动态时空关系,得到行人未来可能的轨迹集合,最后考虑轨迹碰撞概率与最小会遇距离,利用物元可拓理论进行特征降维,建立危险度函数,实现人车碰撞危险度实时判断。本方法聚焦行人运动状态存在突变的特征,更具体地考虑了人车时空关系对轨迹的影响,通过多指标的融合提升了人车碰撞判断结果的准确性与可信度,进一步提高自动驾驶的智能度、提升乘坐舒适性与安全性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Human-vehicle collision risk degree analysis method based on autonomous vehicle


    Weitere Titelangaben:

    一种基于自动驾驶汽车的人车碰撞危险度分析方法


    Beteiligte:
    ZHOU ZHUPING (Autor:in) / LIU BOWEN (Autor:in) / TANG RUIYAO (Autor:in) / LUAN PORONG (Autor:in) / OUYANG MOLAN (Autor:in) / LIU YANG (Autor:in) / LI WEI (Autor:in) / HU CHUNGANG (Autor:in) / OU WANQING (Autor:in)

    Erscheinungsdatum :

    2022-04-08


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06V / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    METHOD FOR AUTONOMOUS VEHICLE OF DETERMINING RISK OF COLLISION

    PARK KYUN SANG / LEE SANG HYUP / LEE JOUNG HEE | Europäisches Patentamt | 2020

    Freier Zugriff

    METHOD FOR AUTONOMOUS VEHICLE OF DETERMINING RISK OF COLLISION

    Europäisches Patentamt | 2023

    Freier Zugriff


    Concerted autonomous vehicle collision avoidance

    LOPEZ LOGAN A | Europäisches Patentamt | 2022

    Freier Zugriff

    CONCERTED AUTONOMOUS VEHICLE COLLISION AVOIDANCE

    LOPEZ LOGAN A | Europäisches Patentamt | 2021

    Freier Zugriff