[go: up one dir, main page]

CN114662967B - Unmanned driving collision risk assessment method and system based on dynamic Bayesian network - Google Patents

Unmanned driving collision risk assessment method and system based on dynamic Bayesian network Download PDF

Info

Publication number
CN114662967B
CN114662967B CN202210363894.5A CN202210363894A CN114662967B CN 114662967 B CN114662967 B CN 114662967B CN 202210363894 A CN202210363894 A CN 202210363894A CN 114662967 B CN114662967 B CN 114662967B
Authority
CN
China
Prior art keywords
collision risk
network
vehicle
road traffic
risk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN202210363894.5A
Other languages
Chinese (zh)
Other versions
CN114662967A (en
Inventor
黄文成
张寅�
于耀程
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN202210363894.5A priority Critical patent/CN114662967B/en
Publication of CN114662967A publication Critical patent/CN114662967A/en
Application granted granted Critical
Publication of CN114662967B publication Critical patent/CN114662967B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

本发明公开了一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法及系统，通过采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况，并构建网络碰撞风险评估模型利用划分性能指标得到网络碰撞风险；构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；构建动态贝叶斯网络模型，对多时段的车辆碰撞风险概率进行无人驾驶碰撞风险评估；本发明通过构建交互感知‑动态贝叶斯模型结合网络级风险的影响对自动驾驶车辆碰撞风险进行评估，可根据评估风险进行预警，为推进自动驾驶在安全性方面的发展提供一定参考，解决了车辆驾驶过程中对车辆碰撞风险的预估未考虑道路交通环境影响即安全性不够高的问题。

Figure 202210363894

The invention discloses an unmanned driving collision risk assessment method and system based on a dynamic Bayesian network. By collecting the current road traffic conditions and performing preprocessing, the divided performance indicators and the divided road traffic conditions are obtained, and constructed The network collision risk assessment model uses the partition performance index to obtain the network collision risk; constructs the vehicle collision risk estimation model, and evaluates the vehicle collision risk probability according to the network collision risk; constructs a dynamic Bayesian network model, and performs an infinite analysis of the multi-period vehicle collision risk probability. Collision risk assessment of human driving; the present invention evaluates the collision risk of autonomous driving vehicles by constructing an interactive perception-dynamic Bayesian model combined with the influence of network-level risks, and can carry out early warning according to the assessed risk, in order to promote the development of automatic driving in terms of safety Provide a certain reference, and solve the problem that the estimation of vehicle collision risk during driving does not consider the impact of road traffic environment, that is, the safety is not high enough.

Figure 202210363894

Description

基于动态贝叶斯网络的无人驾驶碰撞风险评估方法及系统Unmanned driving collision risk assessment method and system based on dynamic Bayesian network

技术领域Technical Field

本发明涉及驾驶碰撞风险评估技术领域，具体涉及一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法及系统。The present invention relates to the technical field of driving collision risk assessment, and in particular to an unmanned driving collision risk assessment method and system based on a dynamic Bayesian network.

背景技术Background Art

自动驾驶技术不断发展，其安全性也倍受公众关注，对自动驾驶环境下的风险评估技术的要求越来越高，其考虑的方面也更加复杂全面，作为道路行车事故形式之一的碰撞事故时常发生，且其也是作为道路行车安全最先考虑的风险情况之一。因此为了保证对自动驾驶碰撞风险的评估更具安全性，提示驾驶人或车辆采取措施，减少发生碰撞威胁的可能，影响车辆发生碰撞事故概率的因素繁多，现目前主要考虑从自动驾驶的车辆层、运动学层、传感器测量层来建立影响车辆发生碰撞事故概率的体系，然而道路交通环境的不同也会对行车碰撞事故的发生造成影响，具有不同交通流属性的道路环境发生碰撞事故的概率也不尽相同。As autonomous driving technology continues to develop, its safety has also attracted much public attention. The requirements for risk assessment technology in the autonomous driving environment are getting higher and higher, and the aspects considered are becoming more complex and comprehensive. Collision accidents, as one of the forms of road accidents, often occur, and they are also one of the first risk situations to be considered for road driving safety. Therefore, in order to ensure that the assessment of autonomous driving collision risks is safer, the driver or vehicle is prompted to take measures to reduce the possibility of collision threats. There are many factors that affect the probability of vehicle collision accidents. At present, the main consideration is to establish a system that affects the probability of vehicle collision accidents from the vehicle layer, kinematic layer, and sensor measurement layer of autonomous driving. However, different road traffic environments will also affect the occurrence of driving collision accidents. The probability of collision accidents in road environments with different traffic flow attributes is also different.

发明内容Summary of the invention

针对现有技术中的上述不足，本发明提供一种基于交互感知-动态贝叶斯的无人驾驶碰撞风险评估方法，通过构建交互感知-动态贝叶斯模型结合网络级风险的影响对自动驾驶车辆碰撞风险进行评估，可根据评估风险进行预警，为推进自动驾驶在安全性方面的发展提供一定参考。In view of the above-mentioned deficiencies in the prior art, the present invention provides an unmanned driving collision risk assessment method based on interactive perception-dynamic Bayesian. By constructing an interactive perception-dynamic Bayesian model and combining the influence of network-level risks, the collision risk of autonomous driving vehicles is assessed. Early warnings can be issued based on the assessed risks, providing a certain reference for promoting the development of autonomous driving in terms of safety.

为了达到上述发明目的，本发明采用的技术方案为：In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

一方面，一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法，包括以下步骤：On the one hand, a method for assessing collision risk of unmanned driving based on a dynamic Bayesian network comprises the following steps:

S1、采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况；S1. Collect the current road traffic conditions and perform preprocessing to obtain the division performance index and the road traffic conditions after division;

S2、构建网络碰撞风险评估模型，根据划分性能指标得到网络碰撞风险；S2. Construct a network collision risk assessment model and obtain the network collision risk according to the divided performance indicators;

S3、构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；S3. Construct a vehicle collision risk estimation model and evaluate the vehicle collision risk probability based on the network collision risk;

S4、基于不少于一个时段的车辆碰撞风险概率，通过动态贝叶斯网络模型进行评估。S4. The vehicle collision risk probability is evaluated based on no less than one period of time using a dynamic Bayesian network model.

优选地，步骤S1具体为：Preferably, step S1 specifically includes:

采集当前道路交通状况，并将当前道路交通状况进行分类，得到危险状态下的道路交通状况与安全状态下的道路交通状况，及划分性能指标；其中，划分性能指标分别表示为：The current road traffic conditions are collected and classified to obtain the road traffic conditions in dangerous state and safe state, and the classification performance indicators; wherein the classification performance indicators are respectively expressed as:

Figure BDA0003585065770000021
Figure BDA0003585065770000021

Figure BDA0003585065770000022
Figure BDA0003585065770000022

Figure BDA0003585065770000023
Figure BDA0003585065770000023

其中，W为分类的整体准确性，D为判断为危险状态的准确性，S为判断为安全状态的准确性，Tpz为正确判断为危险状态的数量，Taq为正确判断为安全状态的数量，Fpz为错误判断为危险状态的数量，Faq为错误判断为安全状态的数量。Among them, W is the overall accuracy of classification, D is the accuracy of judging as dangerous state, S is the accuracy of judging as safe state, T pz is the number of correctly judged as dangerous state, T aq is the number of correctly judged as safe state, F pz is the number of incorrectly judged as dangerous state, and F aq is the number of incorrectly judged as safe state.

优选地，步骤S2具体为：Preferably, step S2 is specifically:

构建网络碰撞风险评估模型，并根据划分性能指标评估当前道路交通状况中路段存在易发生碰撞的交通状况的概率，得到网络碰撞风险，其中，网络碰撞风险评估模型中碰撞风险计算式表示为：A network collision risk assessment model is constructed, and the probability of a traffic condition prone to collision in the current road traffic condition is evaluated according to the divided performance index, and the network collision risk is obtained. The collision risk calculation formula in the network collision risk assessment model is expressed as:

Figure BDA0003585065770000031
Figure BDA0003585065770000031

Figure BDA0003585065770000032
Figure BDA0003585065770000032

其中，TC为道路交通状况，取值为0和1分别对应安全状态与危险状态两种情况，NIR为网络级风险状况，P(NLR＝"danger")为危险状态下的网络级风险状况的概率，P(NLR＝"safe")为安全状态下的网络级风险状况的概率。Among them, TC is the road traffic condition, and the values 0 and 1 correspond to the safe state and dangerous state respectively. NIR is the network-level risk condition, P(NLR = "danger") is the probability of the network-level risk condition in the dangerous state, and P(NLR = "safe") is the probability of the network-level risk condition in the safe state.

优选地，步骤S3具体为：Preferably, step S3 specifically includes:

构建车辆碰撞风险估计模型，其模型表示为：Construct a vehicle collision risk estimation model, which is expressed as:

Figure BDA0003585065770000033
Figure BDA0003585065770000033

其中，

Figure BDA0003585065770000034
为t时刻下当前车辆处于危险状况下的车辆碰撞风险概率，N为当前车辆能感知到周围车辆的总数，VLRt为t时刻下当前车辆状况，
Figure BDA0003585065770000035
为(t-1)时刻下周围车辆总状况，
Figure BDA0003585065770000036
为(t-1)时刻周围车辆运动风险总状况，
Figure BDA0003585065770000037
为t时刻网络碰撞风险状况，
Figure BDA0003585065770000038
和
Figure BDA0003585065770000039
分别为车辆运动风险、周围车辆风险和网络碰撞风险的参数；in,
Figure BDA0003585065770000034
is the vehicle collision risk probability when the current vehicle is in a dangerous state at time t, N is the total number of surrounding vehicles that the current vehicle can perceive, VLR t is the current vehicle status at time t,
Figure BDA0003585065770000035
is the total status of surrounding vehicles at time (t-1),
Figure BDA0003585065770000036
is the total risk of surrounding vehicle movement at time (t-1),
Figure BDA0003585065770000037
is the network collision risk status at time t,
Figure BDA0003585065770000038
and
Figure BDA0003585065770000039
are the parameters for vehicle motion risk, surrounding vehicle risk, and network collision risk, respectively;

并利用网络碰撞风险结合车辆碰撞风险估计模型计算车辆碰撞风险概率。The network collision risk is combined with the vehicle collision risk estimation model to calculate the vehicle collision risk probability.

优选地，步骤S3中网络碰撞风险参数计算式表示为：Preferably, the network collision risk parameter calculation formula in step S3 is expressed as:

Figure BDA0003585065770000041
Figure BDA0003585065770000041

其中，W为分类的整体准确性，D为判断为危险状态的准确性，S为判断为安全状态的准确性，

Figure BDA0003585065770000042
为0时为周围没有对当前车辆构成威胁的车辆，
Figure BDA0003585065770000043
大于0时为周围存在对当前车辆构成威胁的车辆，
Figure BDA0003585065770000044
为t时刻处于安全状况下的网络碰撞风险；
Figure BDA0003585065770000045
为t时刻当前车辆处于危险状况下的网络碰撞风险。Among them, W is the overall accuracy of classification, D is the accuracy of judging as dangerous state, S is the accuracy of judging as safe state,
Figure BDA0003585065770000042
When it is 0, there are no vehicles around that pose a threat to the current vehicle.
Figure BDA0003585065770000043
When it is greater than 0, there are vehicles around that pose a threat to the current vehicle.
Figure BDA0003585065770000044
is the network collision risk in a safe state at time t;
Figure BDA0003585065770000045
is the network collision risk when the current vehicle is in a dangerous condition at time t.

另一方面，一种基于动态贝叶斯网络的无人驾驶碰撞风险评估系统，包括：On the other hand, an unmanned driving collision risk assessment system based on a dynamic Bayesian network includes:

道路交通预处理模块，用于采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况；The road traffic preprocessing module is used to collect the current road traffic conditions and perform preprocessing to obtain the division performance index and the road traffic conditions after division;

网络碰撞风险评估模块，用于构建网络碰撞风险评估模型，根据划分性能指标得到网络碰撞风险；The network collision risk assessment module is used to build a network collision risk assessment model and obtain the network collision risk according to the divided performance indicators;

车辆碰撞风险估计模块，用于构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；The vehicle collision risk estimation module is used to build a vehicle collision risk estimation model and evaluate the vehicle collision risk probability based on the network collision risk;

动态贝叶斯网络模块，用于构建动态贝叶斯网络模型，对多时段内车辆碰撞风险概率进行评估。The dynamic Bayesian network module is used to construct a dynamic Bayesian network model to evaluate the probability of vehicle collision risk in multiple time periods.

本发明具有以下有益效果：The present invention has the following beneficial effects:

采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况，并构建网络碰撞风险评估模型利用划分性能指标得到网络碰撞风险；构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；构建动态贝叶斯网络模型，对多时段的车辆碰撞风险概率进行无人驾驶碰撞风险评估；可通过构建交互感知-动态贝叶斯模型结合网络级风险的影响对自动驾驶车辆碰撞风险进行评估，可根据评估风险进行预警，为推进自动驾驶在安全性方面的发展提供一定参考，解决了车辆驾驶过程中对车辆碰撞风险的预估未考虑道路交通环境影响即安全性不够高的问题。The current road traffic conditions are collected and preprocessed to obtain the division performance indicators and the road traffic conditions after division, and a network collision risk assessment model is constructed to obtain the network collision risk using the division performance indicators; a vehicle collision risk estimation model is constructed, and the vehicle collision risk probability is evaluated based on the network collision risk; a dynamic Bayesian network model is constructed to conduct unmanned driving collision risk assessment on the vehicle collision risk probability in multiple time periods; the collision risk of autonomous driving vehicles can be assessed by constructing an interactive perception-dynamic Bayesian model combined with the impact of network-level risks, and early warnings can be issued based on the assessed risks, providing a certain reference for promoting the development of autonomous driving in terms of safety, and solving the problem that the estimation of vehicle collision risk during vehicle driving does not take into account the impact of the road traffic environment, that is, the safety is not high enough.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

图1为本发明提供的一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法的步骤流程图；FIG1 is a flowchart of a method for assessing collision risk of an unmanned vehicle based on a dynamic Bayesian network provided by the present invention;

图2为本发明实施例提供的动态贝叶斯网络模型的结构示意图。FIG. 2 is a schematic diagram of the structure of a dynamic Bayesian network model provided by an embodiment of the present invention.

具体实施方式DETAILED DESCRIPTION

下面对本发明的具体实施方式进行描述，以便于本技术领域的技术人员理解本发明，但应该清楚，本发明不限于具体实施方式的范围，对本技术领域的普通技术人员来讲，只要各种变化在所附的权利要求限定和确定的本发明的精神和范围内，这些变化是显而易见的，一切利用本发明构思的发明创造均在保护之列。The specific implementation modes of the present invention are described below to facilitate those skilled in the art to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

一方面，如图1所示，本发明实施例提供一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法，包括以下步骤：On the one hand, as shown in FIG1 , an embodiment of the present invention provides an unmanned driving collision risk assessment method based on a dynamic Bayesian network, comprising the following steps:

S1、采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况；S1. Collect the current road traffic conditions and perform preprocessing to obtain the division performance index and the road traffic conditions after division;

本发明实施例中，道路交通状况可以分为易发生碰撞和安全两种状况，通过机器学习分类器得到，常用方法一般有k近邻，神经网络，支持向量机等，选取适宜的道路交通状况评价指标，使用一定的交通数据通过机器学习分类过程，将交通状况划分为两类，即为：危险状态下的道路交通状况与安全状态下的道路交通状况。In an embodiment of the present invention, road traffic conditions can be divided into two conditions: prone to collision and safe. The conditions are obtained through a machine learning classifier. Commonly used methods generally include k-nearest neighbor, neural network, support vector machine, etc., and appropriate road traffic condition evaluation indicators are selected. Certain traffic data is used through a machine learning classification process to divide the traffic conditions into two categories, namely: road traffic conditions in a dangerous state and road traffic conditions in a safe state.

优选地，步骤S1具体为：Preferably, step S1 specifically includes:

采集当前道路交通状况，并将当前道路交通状况进行分类，得到危险状态下的道路交通状况与安全状态下的道路交通状况，及划分性能指标；其中，划分性能指标分别表示为：The current road traffic conditions are collected and classified to obtain the road traffic conditions in dangerous state and safe state, and the classification performance indicators; wherein the classification performance indicators are respectively expressed as:

Figure BDA0003585065770000061
Figure BDA0003585065770000061

Figure BDA0003585065770000062
Figure BDA0003585065770000062

Figure BDA0003585065770000063
Figure BDA0003585065770000063

其中，W为分类的整体准确性，D为判断为危险状态的准确性，S为判断为安全状态的准确性，Tpz为正确判断为危险状态的数量，Taq为正确判断为安全状态的数量，Fpz为错误判断为危险状态的数量，Faq为错误判断为安全状态的数量。Among them, W is the overall accuracy of classification, D is the accuracy of judging as dangerous state, S is the accuracy of judging as safe state, T pz is the number of correctly judged as dangerous state, T aq is the number of correctly judged as safe state, F pz is the number of incorrectly judged as dangerous state, and F aq is the number of incorrectly judged as safe state.

S2、构建网络碰撞风险评估模型，根据划分性能指标得到网络碰撞风险；S2. Construct a network collision risk assessment model and obtain the network collision risk according to the divided performance indicators;

优选地，步骤S2具体为：Preferably, step S2 is specifically:

构建网络碰撞风险评估模型，并根据划分性能指标评估当前道路交通状况中路段存在易发生碰撞的交通状况的概率，得到网络碰撞风险，其中，网络碰撞风险评估模型中碰撞风险计算式表示为：A network collision risk assessment model is constructed, and the probability of a traffic condition prone to collision in the current road traffic condition is evaluated according to the divided performance index, and the network collision risk is obtained. The collision risk calculation formula in the network collision risk assessment model is expressed as:

Figure BDA0003585065770000071
Figure BDA0003585065770000071

Figure BDA0003585065770000072
Figure BDA0003585065770000072

其中，TC为道路交通状况，取值为0和1分别对应安全状态与危险状态两种情况，NIR为网络级风险状况，P(NLR＝"danger")为危险状态下的网络级风险状况的概率，P(NLR＝"safe")为安全状态下的网络级风险状况的概率。Among them, TC is the road traffic condition, and the values 0 and 1 correspond to the safe state and dangerous state respectively. NIR is the network-level risk condition, P(NLR = "danger") is the probability of the network-level risk condition in the dangerous state, and P(NLR = "safe") is the probability of the network-level risk condition in the safe state.

本发明实施例中，TC＝1时，表示当道路交通状况分类结果为易发生碰撞，网络级发生碰撞的概率即为整体准确性与判断危险准确性的折中值，TC＝0时，表示当前道路交通状况分类结果为安全；In the embodiment of the present invention, when TC=1, it means that when the road traffic condition classification result is prone to collision, the probability of collision at the network level is the compromise value between the overall accuracy and the accuracy of judging danger. When TC=0, it means that the current road traffic condition classification result is safe.

通过将道路交通网络进行安全和危险的二分类，并利用划分性能指标来表征道路网络碰撞风险，可以对网络级碰撞风险进行评估，并掌握道路交通的碰撞风险情况，即在行车过程中从道路网络层面了解碰撞风险，并将其作为碰撞风险估计的一部分，有利于行车碰撞风险评估的综合性、全面性。By classifying the road traffic network into safe and dangerous types and using the classification performance indicators to characterize the road network collision risk, the network-level collision risk can be evaluated and the collision risk situation of road traffic can be understood. That is, the collision risk can be understood from the road network level during driving and used as part of the collision risk estimation, which is conducive to the comprehensiveness of driving collision risk assessment.

S3、构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；S3. Construct a vehicle collision risk estimation model and evaluate the vehicle collision risk probability based on the network collision risk;

优选地，步骤S3具体为：Preferably, step S3 specifically includes:

构建车辆碰撞风险估计模型，其模型表示为：Construct a vehicle collision risk estimation model, which is expressed as:

Figure BDA0003585065770000073
Figure BDA0003585065770000073

其中，

Figure BDA0003585065770000074
为t时刻下当前车辆处于危险状况下的车辆碰撞风险概率，即在掌握(t-1)时刻周围车辆总状况、(t-1)时刻周围车辆运动风险总状况及t时刻网络碰撞风险状况的情况下，t时刻当前车辆处于危险状况的概率，N为当前车辆能感知到周围车辆的总数，VLRt为t时刻下当前车辆状况，
Figure BDA0003585065770000081
为(t-1)时刻下周围车辆总状况，
Figure BDA0003585065770000082
为(t-1)时刻周围车辆运动风险总状况，
Figure BDA0003585065770000083
为t时刻网络碰撞风险状况，
Figure BDA0003585065770000084
和
Figure BDA0003585065770000085
分别为车辆运动风险、周围车辆风险和网络碰撞风险的参数；in,
Figure BDA0003585065770000074
is the probability of vehicle collision risk when the current vehicle is in a dangerous state at time t, that is, the probability that the current vehicle is in a dangerous state at time t, given the total state of surrounding vehicles at time (t-1), the total state of motion risk of surrounding vehicles at time (t-1), and the network collision risk state at time t. N is the total number of surrounding vehicles that the current vehicle can sense. VLR t is the current vehicle state at time t.
Figure BDA0003585065770000081
is the total status of surrounding vehicles at time (t-1),
Figure BDA0003585065770000082
is the total risk of surrounding vehicle movement at time (t-1),
Figure BDA0003585065770000083
is the network collision risk status at time t,
Figure BDA0003585065770000084
and
Figure BDA0003585065770000085
are the parameters for vehicle motion risk, surrounding vehicle risk, and network collision risk, respectively;

并利用网络碰撞风险结合车辆碰撞风险估计模型计算车辆碰撞风险概率。The network collision risk is combined with the vehicle collision risk estimation model to calculate the vehicle collision risk probability.

优选地，步骤S3中网络碰撞风险参数

Figure BDA0003585065770000086
计算式表示为：Preferably, the network collision risk parameter in step S3 is
Figure BDA0003585065770000086
The calculation formula is:

Figure BDA0003585065770000087
Figure BDA0003585065770000087

其中，W为分类的整体准确性，D为判断为危险状态的准确性，S为判断为安全状态的准确性，

Figure BDA0003585065770000088
为0时为周围没有对当前车辆构成威胁的车辆，
Figure BDA0003585065770000089
大于0时为周围存在对当前车辆构成威胁的车辆，
Figure BDA00035850657700000810
为t时刻处于安全状况下的网络碰撞风险；
Figure BDA00035850657700000811
为t时刻当前车辆处于危险状况下的网络碰撞风险；Among them, W is the overall accuracy of classification, D is the accuracy of judging as dangerous state, S is the accuracy of judging as safe state,
Figure BDA0003585065770000088
When it is 0, there are no vehicles around that pose a threat to the current vehicle.
Figure BDA0003585065770000089
When it is greater than 0, there are vehicles around that pose a threat to the current vehicle.
Figure BDA00035850657700000810
is the network collision risk in a safe state at time t;
Figure BDA00035850657700000811
is the network collision risk when the current vehicle is in a dangerous condition at time t;

本发明实施例中，其中

Figure BDA00035850657700000812
有四种计算式，分别对应网络碰撞风险状况为危险和安全、周围车辆是否构成威胁相组合的四种情况,
Figure BDA00035850657700000813
为0时表示周围没有对当前车辆构成威胁的车辆，,
Figure BDA00035850657700000814
大于0时表示周围存在对当前车辆构成威胁的车辆；车辆运动风险
Figure BDA00035850657700000815
主要由当前车辆利用传感器感知周围第n个车的速度、与其之间的距离等属性得到其碰撞时间，并通过判断该碰撞时间是否小于临界碰撞时间，来判断该车辆是否对当前车辆构成威胁，并相应得到
Figure BDA0003585065770000091
的取值；周围车辆风险
Figure BDA0003585065770000092
主要根据当前车辆与周围第n个车之间的数据交互，掌握周围车辆是否存在危险驾驶情况后得到其取值；网络碰撞风险的参数
Figure BDA0003585065770000093
主要由道路交通网络状况的划分性能指标进行计算得到。In the embodiment of the present invention,
Figure BDA00035850657700000812
There are four calculation formulas, corresponding to the four situations where the network collision risk status is dangerous or safe, and whether the surrounding vehicles pose a threat.
Figure BDA00035850657700000813
When it is 0, it means there is no vehicle around that poses a threat to the current vehicle.
Figure BDA00035850657700000814
When it is greater than 0, it means there are vehicles around that pose a threat to the current vehicle; vehicle movement risk
Figure BDA00035850657700000815
The current vehicle mainly uses sensors to sense the speed of the nth vehicle around it, the distance between it and other attributes to obtain its collision time, and by judging whether the collision time is less than the critical collision time, it is judged whether the vehicle poses a threat to the current vehicle, and the corresponding
Figure BDA0003585065770000091
The value of surrounding vehicle risk
Figure BDA0003585065770000092
The value is obtained mainly based on the data interaction between the current vehicle and the nth vehicle around it, and whether there are dangerous driving situations of surrounding vehicles; the parameters of network collision risk
Figure BDA0003585065770000093
It is mainly calculated based on the performance indicators of the road traffic network conditions.

本发明实施例中，车辆运动风险参数

Figure BDA0003585065770000094
的计算式表征为：In the embodiment of the present invention, the vehicle motion risk parameter
Figure BDA0003585065770000094
The calculation formula is represented as:

Figure BDA0003585065770000095
Figure BDA0003585065770000095

其中，TTC为碰撞时间，TTCC为临界碰撞时间，当碰撞时间小于临界碰撞时间时，为危险状况，此时fK取1；当碰撞时间不小于临界碰撞时间时，为安全状况，此时fK取0。Among them, TTC is the collision time, TTC C is the critical collision time. When the collision time is less than the critical collision time, it is a dangerous situation, and f K is 1 at this time; when the collision time is not less than the critical collision time, it is a safe situation, and f K is 0 at this time.

本发明实施例中，周围车辆风险参数

Figure BDA0003585065770000096
表示为：In the embodiment of the present invention, the surrounding vehicle risk parameter
Figure BDA0003585065770000096
It is expressed as:

Figure BDA0003585065770000097
Figure BDA0003585065770000097

其中，周围车辆出现危险驾驶行为时，为危险状态，即：

Figure BDA0003585065770000098
当周围车辆未出现危险驾驶行为时，为安全状态，即：
Figure BDA0003585065770000099
Among them, when the surrounding vehicles have dangerous driving behaviors, it is a dangerous state, that is:
Figure BDA0003585065770000098
When there is no dangerous driving behavior by the surrounding vehicles, it is a safe state, that is:
Figure BDA0003585065770000099

本发明实施例中，通过数据交互、传感器感知的方式，并结合步骤S2对网络级风险的评估指标，从周围车辆级碰撞风险、车辆运动风险、网络级碰撞风险三方面来综合估计当前车辆所面临的碰撞风险情况，该对车辆碰撞风险的估计方法综合考虑了道路交通网络条件、周围车辆驾驶状态、车辆运动情况，相较于仅考虑单一因素等的碰撞风险估计方法更为综合，在当前车辆感知到周围车辆级碰撞风险、车辆运动风险仅处于一个较低水平，但道路交通条件较差时，由于考虑了网络级碰撞风险，对当前车辆的碰撞风险估计所得到的概率结果会处于一个相对更高水平，以此来提醒驾驶员保持警觉，使得行车过程更具安全性。In an embodiment of the present invention, through data interaction and sensor perception, and combined with the evaluation index of the network-level risk in step S2, the collision risk faced by the current vehicle is comprehensively estimated from three aspects: the surrounding vehicle-level collision risk, the vehicle motion risk, and the network-level collision risk. The method for estimating the vehicle collision risk comprehensively considers the road traffic network conditions, the driving status of the surrounding vehicles, and the vehicle motion conditions. Compared with the collision risk estimation method that only considers a single factor, it is more comprehensive. When the current vehicle perceives that the surrounding vehicle-level collision risk and the vehicle motion risk are only at a low level, but the road traffic conditions are poor, due to the consideration of the network-level collision risk, the probability result obtained by estimating the collision risk of the current vehicle will be at a relatively higher level, thereby reminding the driver to stay alert and make the driving process safer.

S4、基于不少于一个时段的车辆碰撞风险概率，通过动态贝叶斯网络模型进行评估。S4. The vehicle collision risk probability is evaluated based on no less than one period of time using a dynamic Bayesian network model.

本发明实施例中，通过采集时间间隔取了30秒、1分钟、3分钟、5分钟的交通状况数据，并结合整个行车过程中利用所建立的动态贝叶斯网络模型，对车辆碰撞风险进行动态估计以掌握当前车辆行驶过程中出现的碰撞风险情况，并对所出现的碰撞风险情况进行相应的预警；In the embodiment of the present invention, traffic condition data at time intervals of 30 seconds, 1 minute, 3 minutes, and 5 minutes are collected, and the dynamic Bayesian network model established during the entire driving process is used to dynamically estimate the vehicle collision risk to grasp the collision risk situation that occurs during the current vehicle driving process, and to give a corresponding early warning for the collision risk situation that occurs;

利用当前的车辆级碰撞风险情况、运动风险情况和下一时刻所估计的网络级碰撞风险情况，可对下一时刻车辆的碰撞风险进行估计。如附图2所示，t时刻当前车辆的碰撞风险由t-1时刻周围车辆的碰撞风险、t-1时刻周围车辆运动风险和t时刻的网络级风险作为输入，并通过步骤S3构建的车辆碰撞风险估计模型计算得到；t+1时刻当前车辆的碰撞风险由t时刻周围车辆的碰撞风险、t时刻周围车辆运动风险和t+1时刻的网络级风险作为输入，并通过步骤S3构建的车辆碰撞风险估计模型计算得到，其中t-1时刻、t时刻、t+1时刻的周围车辆运动学风险都分别由t-1时刻、t时刻、t+1时刻的传感器测量与模型计算得到。在设置一定的时间间隔后，每经过固定时间间隔进行一次网络、车辆、传感器等方面的数据交互，并由此动态贝叶斯网络模型可对当前车辆的碰撞风险进行估计，以此方式，在整个车辆行驶过程中进行车辆碰撞风险的动态估计，并将实时的车辆碰撞风险情况告知给驾驶员，使得驾驶员能更清楚地了解车辆碰撞风险情况，利于采取更加安全、合理的驾驶措施，减少碰撞事故发生的可能性，提高车辆行驶的安全性，为保障行车安全通过技术参考。The collision risk of the vehicle at the next moment can be estimated by using the current vehicle-level collision risk situation, motion risk situation and the estimated network-level collision risk situation at the next moment. As shown in Figure 2, the collision risk of the current vehicle at time t is calculated by the collision risk of the surrounding vehicles at time t-1, the motion risk of the surrounding vehicles at time t-1 and the network-level risk at time t as inputs, and is obtained by the vehicle collision risk estimation model constructed in step S3; the collision risk of the current vehicle at time t+1 is calculated by the collision risk of the surrounding vehicles at time t, the motion risk of the surrounding vehicles at time t and the network-level risk at time t+1 as inputs, and is obtained by the vehicle collision risk estimation model constructed in step S3, wherein the kinematic risks of the surrounding vehicles at time t-1, time t and time t+1 are respectively obtained by the sensor measurements and model calculations at time t-1, time t and time t+1. After setting a certain time interval, data interaction between the network, vehicle, sensor, etc. is performed once every fixed time interval, and the dynamic Bayesian network model can estimate the collision risk of the current vehicle. In this way, the vehicle collision risk is dynamically estimated during the entire vehicle driving process, and the real-time vehicle collision risk situation is informed to the driver, so that the driver can understand the vehicle collision risk situation more clearly, which is conducive to taking safer and more reasonable driving measures, reducing the possibility of collision accidents, improving the safety of vehicle driving, and providing technical reference for ensuring driving safety.

一种基于动态贝叶斯网络的无人驾驶碰撞风险评估系统，包括：An unmanned driving collision risk assessment system based on a dynamic Bayesian network, comprising:

道路交通预处理模块，用于采集当前道路交通状况，并进行预处理，得到划分性能指标，及划分后的道路交通状况；The road traffic preprocessing module is used to collect the current road traffic conditions and perform preprocessing to obtain the division performance index and the road traffic conditions after division;

网络碰撞风险评估模块，用于构建网络碰撞风险评估模型，根据划分性能指标得到网络碰撞风险；The network collision risk assessment module is used to build a network collision risk assessment model and obtain the network collision risk according to the divided performance indicators;

车辆碰撞风险估计模块，用于构建车辆碰撞风险估计模型，并根据网络碰撞风险评估车辆碰撞风险概率；The vehicle collision risk estimation module is used to build a vehicle collision risk estimation model and evaluate the vehicle collision risk probability based on the network collision risk;

动态贝叶斯网络模块，用于构建动态贝叶斯网络模型，对多时段内车辆碰撞风险概率进行评估。The dynamic Bayesian network module is used to construct a dynamic Bayesian network model to evaluate the probability of vehicle collision risk in multiple time periods.

本发明实施例中提供的一种基于动态贝叶斯网络的无人驾驶碰撞风险评估系统包括上述一种基于动态贝叶斯网络的无人驾驶碰撞风险评估方法的全部有益效果。An unmanned driving collision risk assessment system based on a dynamic Bayesian network provided in an embodiment of the present invention includes all the beneficial effects of the above-mentioned unmanned driving collision risk assessment method based on a dynamic Bayesian network.

本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to the flowchart and/or block diagram of the method, device (system), and computer program product according to the embodiment of the present invention. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the process and/or box in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

本发明中应用了具体实施例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

本领域的普通技术人员将会意识到，这里所述的实施例是为了帮助读者理解本发明的原理，应被理解为本发明的保护范围并不局限于这样的特别陈述和实施例。本领域的普通技术人员可以根据本发明公开的这些技术启示做出各种不脱离本发明实质的其它各种具体变形和组合，这些变形和组合仍然在本发明的保护范围内。Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims (3)

1. The unmanned driving collision risk assessment method based on the dynamic Bayesian network is characterized by comprising the following steps of:
s1, collecting current road traffic conditions, and preprocessing the current road traffic conditions to obtain dividing performance indexes and divided road traffic conditions; the method specifically comprises the following steps:
collecting current road traffic conditions, classifying the current road traffic conditions to obtain road traffic conditions in a dangerous state, road traffic conditions in a safe state and division performance indexes; wherein, the dividing performance indexes are respectively expressed as:
Figure FDA0004056225480000011
Figure FDA0004056225480000012
Figure FDA0004056225480000013
wherein W is the overall accuracy of classification, D is the accuracy of judgment as a dangerous state, S is the accuracy of judgment as a safe state, and T pz To correctly determine the number of dangerous states, T aq To correctly judge the number of safe states, F pz Number of misjudged dangerous states，F aq The number of false positives as a safety state;
s2, constructing a network collision risk evaluation model, and obtaining a network collision risk according to the division performance indexes; the method specifically comprises the following steps:
constructing a network collision risk evaluation model, and evaluating the probability of the traffic condition which is easy to collide in the road section in the current road traffic condition according to the division performance indexes to obtain the network collision risk, wherein a collision risk calculation formula in the network collision risk evaluation model is represented as follows:
Figure FDA0004056225480000021
Figure FDA0004056225480000022
the TC is a road traffic condition, values of 0 and 1 respectively correspond to two conditions of a safe state and a dangerous state, the NLR is a network level risk condition, the P (NLR = "danger") is the probability of the network level risk condition in the dangerous state, and the P (NLR = "safe") is the probability of the network level risk condition in the safe state;
s3, constructing a vehicle collision risk estimation model, and evaluating vehicle collision risk probability according to the network collision risk; the method specifically comprises the following steps:
constructing a vehicle collision risk estimation model, wherein the model is expressed as follows:
Figure FDA0004056225480000023
wherein,
Figure FDA0004056225480000024
the collision risk probability of the vehicle under the dangerous condition of the current vehicle at the moment t, N is the total number of the vehicles around the current vehicle, VLR t Is the current vehicle condition at time t,
Figure FDA0004056225480000025
is the total status of the surrounding vehicle at time (t-1), based on>
Figure FDA0004056225480000026
The total situation of the risk of movement of the vehicle around the time (t-1),
Figure FDA0004056225480000027
for the network collision risk situation at time t, device for selecting or keeping>
Figure FDA0004056225480000028
And &>
Figure FDA0004056225480000029
Parameters of vehicle motion risk, surrounding vehicle risk and network collision risk are respectively set;
calculating the probability of the vehicle collision risk by combining the network collision risk and a vehicle collision risk estimation model;
and S4, evaluating through a dynamic Bayesian network model based on the vehicle collision risk probability of not less than one time period.
2. The unmanned aerial vehicle collision risk assessment method based on dynamic Bayesian network as claimed in claim 1, wherein the network collision risk parameter calculation formula in step S3 is expressed as:
Figure FDA0004056225480000031
wherein W is the overall accuracy of classification, D is the accuracy of judgment as a dangerous state, S is the accuracy of judgment as a safe state,
Figure FDA0004056225480000032
a vehicle in the surroundings which does not pose a threat to the current vehicle, when 0>
Figure FDA0004056225480000033
Greater than 0 for a vehicle in the surroundings which poses a threat to the current vehicle, based on the vehicle status>
Figure FDA0004056225480000034
The network collision risk under the safety condition at the moment t;
Figure FDA0004056225480000035
and the network collision risk of the current vehicle in the dangerous condition at the moment t.
3. A system for unmanned collision risk assessment based on dynamic bayesian network using the method of claim 1, comprising:
the road traffic preprocessing module is used for acquiring the current road traffic condition and preprocessing the current road traffic condition to obtain a division performance index and divided road traffic conditions;
the network collision risk evaluation module is used for constructing a network collision risk evaluation model and obtaining a network collision risk according to the division performance indexes;
the vehicle collision risk estimation module is used for constructing a vehicle collision risk estimation model and evaluating the vehicle collision risk probability according to the network collision risk;
and the dynamic Bayesian network module is used for constructing a dynamic Bayesian network model and evaluating the vehicle collision risk probability in multiple periods.
CN202210363894.5A 2022-04-07 2022-04-07 Unmanned driving collision risk assessment method and system based on dynamic Bayesian network Expired - Fee Related CN114662967B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210363894.5A CN114662967B (en) 2022-04-07 2022-04-07 Unmanned driving collision risk assessment method and system based on dynamic Bayesian network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210363894.5A CN114662967B (en) 2022-04-07 2022-04-07 Unmanned driving collision risk assessment method and system based on dynamic Bayesian network

Publications (2)

Publication Number Publication Date
CN114662967A CN114662967A (en) 2022-06-24
CN114662967B true CN114662967B (en) 2023-04-07

Family

ID=82034413

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210363894.5A Expired - Fee Related CN114662967B (en) 2022-04-07 2022-04-07 Unmanned driving collision risk assessment method and system based on dynamic Bayesian network

Country Status (1)

Country Link
CN (1) CN114662967B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2869283A1 (en) * 2013-10-31 2015-05-06 Inria Institut National de Recherche en Informatique et en Automatique Method and system of driving assistance for collision avoidance
CN105761548A (en) * 2016-04-14 2016-07-13 西安电子科技大学 Intersection collision-avoiding method based on dynamic Bayes network
WO2018220418A1 (en) * 2017-06-02 2018-12-06 Toyota Motor Europe Driving assistance method and system
CN110834644A (en) * 2019-10-30 2020-02-25 中国第一汽车股份有限公司 Vehicle control method and device, vehicle to be controlled and storage medium
EP3706034A1 (en) * 2019-03-06 2020-09-09 Robert Bosch GmbH Movement prediction of pedestrians useful for autonomous driving
CN112015843A (en) * 2020-09-02 2020-12-01 中国科学技术大学 Driving risk situation assessment method and system based on multi-vehicle intention interaction result
CN113792655A (en) * 2021-09-14 2021-12-14 京东鲲鹏(江苏)科技有限公司 Intention identification method and device, electronic equipment and computer readable medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11577750B2 (en) * 2018-11-08 2023-02-14 Bayerische Motoren Werke Aktiengesellschaft Method and apparatus for determining a vehicle comfort metric for a prediction of a driving maneuver of a target vehicle

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2869283A1 (en) * 2013-10-31 2015-05-06 Inria Institut National de Recherche en Informatique et en Automatique Method and system of driving assistance for collision avoidance
CN105761548A (en) * 2016-04-14 2016-07-13 西安电子科技大学 Intersection collision-avoiding method based on dynamic Bayes network
WO2018220418A1 (en) * 2017-06-02 2018-12-06 Toyota Motor Europe Driving assistance method and system
EP3706034A1 (en) * 2019-03-06 2020-09-09 Robert Bosch GmbH Movement prediction of pedestrians useful for autonomous driving
CN110834644A (en) * 2019-10-30 2020-02-25 中国第一汽车股份有限公司 Vehicle control method and device, vehicle to be controlled and storage medium
CN112015843A (en) * 2020-09-02 2020-12-01 中国科学技术大学 Driving risk situation assessment method and system based on multi-vehicle intention interaction result
CN113792655A (en) * 2021-09-14 2021-12-14 京东鲲鹏(江苏)科技有限公司 Intention identification method and device, electronic equipment and computer readable medium

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Dongye Sun 等.A highway crash risk assessment method based on traffic safety state division.《plos one》.2020,第1-14页. *
Mohammad Bahram 等.A Combined Model- and Learning-Based Framework for Interaction-Aware Maneuver Prediction.《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》.2016,第17卷(第6期),第1538-1550页. *
Wencheng Huang 等.Railway dangerous goods transportation system risk analysis: An Interpretive Structural Modeling and Bayesian Network combining approach.《Reliability Engineering and System Safety》.2020,第204卷第1-10页. *
仝兆景 等.基于 DBN 的特种车辆前向防撞推理模型.《测控技术》.2019,第38卷(第10期),第56-60页. *

Also Published As

Publication number Publication date
CN114662967A (en) 2022-06-24

Similar Documents

Publication Publication Date Title
US11475770B2 (en) Electronic device, warning message providing method therefor, and non-transitory computer-readable recording medium
CN115179960B (en) A multi-source data acquisition system and method for comprehensive monitoring of human and vehicle status
CN110765980A (en) Abnormal driving detection method and device
Pech et al. Head tracking based glance area estimation for driver behaviour modelling during lane change execution
CN111222477B (en) Vision-based method and device for detecting departure of hands from steering wheel
CN107437147A (en) Reduce the vehicle travel risk dynamic assessment method and its system of freight logistics scene
CN110901385A (en) Active speed limiting method based on fatigue state of driver
CN116957345B (en) Data processing method for unmanned system
WO2016107876A1 (en) Vehicular motion monitoring method
CN119190018B (en) A V2X-based blind spot assisted driving method and system for intersections
CN114852088A (en) Driver assistance system and method for identifying and warning dangerous and fatigue driving behaviors
CN115782905B (en) Automatic driving safety degree quantification system for driving vehicle
Derbel Driving style assessment based on the GPS data and fuzzy inference systems
CN111563468B (en) Driver abnormal behavior detection method based on attention of neural network
CN114662967B (en) Unmanned driving collision risk assessment method and system based on dynamic Bayesian network
Srinivasan et al. Advanced Driver Assistance System (ADAS) in Autonomous Vehicles: A Complete Analysis
CN115865988B (en) Passenger ship passenger tread event monitoring system and method by utilizing mobile phone sensor network
CN117912295A (en) Vehicle data processing method and device, electronic equipment and storage medium
Shichkina et al. Analysis of driving style using self-organizing maps to analyze driver behavior.
CN115985137A (en) Risk assessment method for tunnel traffic operation, electronic equipment and storage medium
EP3654246B1 (en) Method, vehicle, system, and storage medium for indicating anomalous vehicle scenario using encoder network and replay buffer
CN114282776A (en) Method, device, equipment and medium for cooperatively evaluating automatic driving safety of vehicle and road
Fasanmade et al. Context-aware quantitative risk assessment machine learning model for drivers distraction
Dang et al. Comprehensive Evaluation of Regional Road Transport Safety Service Level
CN114333042B (en) Method and device for sensing controller working mode, electronic device, and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20230407