The invention discloses a safety assessment method for an expected functional architecture of an automatic driving system, and the method comprises the following four steps: 1, dividing all components in a design architecture according to the design architecture of the to-be-assessed automatic driving system, abstracting the components into graph nodes, and forming a Bayesian risk graph; 2, injecting test data, collected and recorded by a DBC file, of a natural driving test of the automatic driving system into the Bayesian risk graph in the step 1, recording a node activation state in the Bayesian risk graph, and calculating a prior probability table and a conditional probability table; 3, introducing an unknown risk into the Bayesian risk map, calculating the occurrence probability of an unknown trigger event in combination with a Noisy-OR model, and perfecting an event occurrence probability table in the Bayesian risk map model; and 4, carrying out hazard assessment and grading on the unknown risk to obtain a hazard score corresponding to each grade, and taking a product of the obtained hazard score and the occurrence probability of the unknown risk obtained in the step 3 as a final safety score.

    本发明公开了一种面向自动驾驶系统预期功能架构的安全评估方法,包括以下四个步骤:步骤一:根据待评估的自动驾驶系统的设计架构,划分设计架构中的各个组成部件,抽象成图节点,形成贝叶斯风险图;步骤二:将DBC文件收集记录的自动驾驶系统自然行驶测试的测试数据注入到步骤一中的贝叶斯风险图中,记录贝叶斯风险图中节点激活状态,计算先验概率表和条件概率表;步骤三:在贝叶斯风险图中,引入未知风险,结合Noisy‑OR模型计算未知触发事件的发生概率,完善贝叶斯风险图模型中事件发生的概率表;步骤四:对未知风险进行危害评估并分级,获得各级别对应的危害分数,将获得的危害分数和步骤三中获得的未知风险发生概率的乘积作为最终的安全评分。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Safety assessment method for expected functional architecture of automatic driving system


    Weitere Titelangaben:

    一种面向自动驾驶系统预期功能架构的安全评估方法


    Beteiligte:
    FU YONGLE (Autor:in) / HUANG HUIBIN (Autor:in) / HU HENG (Autor:in) / HU HONGXING (Autor:in) / CHENG WENDONG (Autor:in) / LIU HONG (Autor:in)

    Erscheinungsdatum :

    2023-10-10


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    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 / 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



    Safety architecture for automatic driving, automatic driving system and vehicle

    HUANG JIPING / SUN XIAOWU / LI YUQIANG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Performance-limited expected function safety optimization method for automatic driving decision-making system

    DONG HAO / MOU KANGWEI / WU HAOTIAN | Europäisches Patentamt | 2022

    Freier Zugriff

    Automatic driving vehicle test method and test field based on expected function safety

    KONG LINGJIE / WANG MIN / ZHANG RENSHAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Automatic driving vehicle test method and test field based on expected function safety

    JIANG WEI / LI CHAOBIN / KONG LINGJIE et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    AUTOMATIC DRIVING SAFETY ASSESSMENT METHOD, DEVICE AND SYSTEM

    SHE XIAOLI / CAI JIANYONG / SHEN JUNQIANG et al. | Europäisches Patentamt | 2022

    Freier Zugriff