Road 4D risk occupancy assessment method and device based on vehicle-road-cloud collaborative framework

Abstract

The present application relates to the field of intelligent transportation technology, and in particular to a method and device for assessing 4D road risk occupancy based on a vehicle-road-cloud collaborative framework, wherein the method comprises: dynamically retrieving different sampling point sets; obtaining risk factors that affect the driving safety of ICVs; converting dynamic and static factors into geometric objects to obtain multiple dynamic and static factors within a preset perception range of each sampling point; performing risk quantification calculations on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, accumulating the corresponding risk values, and normalizing them to obtain the final risk values ​​of all sampling points in the sampling point set, and generating a 4D road risk occupancy map. This solves the problem in related technologies that, due to the lack of unified and efficient environmental perception and risk assessment standards, intelligent connected vehicles have difficulty making timely and accurate decisions in complex and changing traffic environments, increasing the computational burden, and reducing operational efficiency.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method and device for assessing road 4D risk occupancy based on a vehicle-road-cloud collaborative framework. Background Art

[0002] Intelligent connected vehicles (ICVs) integrate advanced sensors, powerful computing capabilities, real-time communication systems, and precise actuators to achieve highly automated driving. These capabilities rely on data collected by vehicle sensors to understand the surrounding environment and achieve environmental awareness. However, current environmental awareness and risk assessment methods lack unified standards and typically rely on basic information such as an object's position and velocity.

[0003] In related technologies, multiple factors and spatiotemporal indicators such as vehicles, drivers, road conditions, other traffic participants, traffic flow, potential collision losses, and behavior prediction are mainly incorporated into the theoretical framework of risk assessment to construct a new risk assessment method.

[0004] However, related technologies use parameters that are difficult to measure or subjectively evaluated, which may increase the complexity and uncertainty of the model and reduce the efficiency and accuracy of practical applications; the inclusion of human psychological and behavioral models may affect the generalization ability and credibility of the model; and the neglect of the impact of the road itself on risk affects the comprehensiveness and effectiveness of the assessment, which urgently needs to be improved. Summary of the Invention

[0005] This application provides a road 4D risk occupancy assessment method and device based on a vehicle-road-cloud collaborative framework to address the problems in related technologies such as the lack of unified and efficient environmental perception and risk assessment standards, which makes it difficult for intelligent connected vehicles to make timely and accurate decisions in complex and changing traffic environments, increases the computing burden, and reduces operating efficiency.

[0006] The first aspect of the present application provides a method for assessing road 4D risk occupancy based on a vehicle-road-cloud collaborative framework, comprising the following steps: dynamically retrieving different sampling point sets according to changes in the position and driving direction of an intelligent connected vehicle (ICV); obtaining risk factors that affect the driving safety of the ICV, wherein the risk factors are dynamic and static factors; converting the dynamic and static factors into geometric objects, so as to obtain multiple dynamic and static factors within a preset perception range of each sampling point based on the geometric objects and each sampling point in the sampling point set; performing risk quantification calculation on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, respectively, accumulating the corresponding risk values, and normalizing them to obtain final risk values ​​for all sampling points in the sampling point set, so as to generate a road 4D risk occupancy map based on the final risk values.

[0007] Optionally, in one embodiment of the present application, obtaining multiple dynamic and static factors within the preset perception range of each sampling point includes: adopting a preset perception range radius strategy to set differentiated perception ranges for static factors and dynamic factors, wherein the radius of the static perception range is smaller than the radius of the dynamic perception range.

[0008] Optionally, in one embodiment of the present application, the risk quantification calculation of the multiple dynamic and static factors and each sampling point includes: using the static factor risk quantification formula to quantify the static factors within the static perception range, and assigning fixed risk constant values ​​and corresponding weights to different types of static factors; using the dynamic factor risk quantification model to quantify the dynamic factors within the dynamic perception range to calculate the risk size of different types of dynamic factors.

[0009] Optionally, in one embodiment of the present application, the static factor risk quantification formula is:

[0010]

[0011] Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point;

[0012] The dynamic factor risk quantification model is:

[0013]

[0014] Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

[0015] The second aspect of the present application provides a road 4D risk occupancy assessment device based on a vehicle-road-cloud collaborative framework, including: a retrieval module, used to dynamically retrieve different sampling point sets according to changes in the position and driving direction of an intelligent connected vehicle (ICV); an acquisition module, used to obtain risk factors affecting the driving safety of the ICV, wherein the risk factors are dynamic and static factors; a determination module, used to convert the dynamic and static factors into geometric objects, so as to obtain multiple dynamic and static factors within a preset perception range of each sampling point based on the geometric objects and each sampling point in the sampling point set; an assessment module, used to perform risk quantification calculation on the multiple dynamic and static factors and each sampling point, to obtain risk values ​​corresponding to the multiple dynamic and static factors respectively, to accumulate the corresponding risk values, and to normalize them to obtain the final risk values ​​of all sampling points in the sampling point set, so as to generate a road 4D risk occupancy map based on the final risk values.

[0016] Optionally, in one embodiment of the present application, the determination module includes: adopting a preset perception range radius strategy to set differentiated perception ranges for static factors and dynamic factors, wherein the radius of the static perception range is smaller than the radius of the dynamic perception range.

[0017] Optionally, in one embodiment of the present application, the evaluation module includes: an allocation unit, which is used to quantify the static factors within the static perception range using a static factor risk quantification formula, and assign fixed risk constant values ​​and corresponding weights to different types of static factors; a calculation unit, which is used to quantify the dynamic factors within the dynamic perception range using a dynamic factor risk quantification model to calculate the risk size of different types of dynamic factors.

[0018] Optionally, in one embodiment of the present application, the static factor risk quantification formula is:

[0019]

[0020] Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point;

[0021] The dynamic factor risk quantification model is:

[0022]

[0023] Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

[0024] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework as described in the above embodiment.

[0025] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework.

[0026] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework.

[0027] The embodiments of the present application can dynamically retrieve different sampling point sets based on changes in the position and driving direction of the ICV and obtain risk factors that affect the driving safety of the ICV. Furthermore, the dynamic and static factors are converted into geometric objects. Based on the geometric objects and each sampling point in the sampling point set, multiple dynamic and static factors within the preset perception range of each sampling point are obtained. Risk quantification is then performed for the multiple dynamic and static factors and each sampling point, resulting in risk values ​​corresponding to the multiple dynamic and static factors. The corresponding risk values ​​are accumulated and normalized to obtain a 4D risk occupancy map consisting of the final risk values ​​of all sampling points in the sampling point set. This helps to promptly respond to dynamic changes and achieve quantitative risk assessment. Furthermore, the use of a vehicle-road-cloud collaborative framework helps optimize resource allocation, improve the accuracy and efficiency of assessments, and help ICVs obtain beyond-visual-range risk perception capabilities that individual vehicles do not possess, effectively avoiding risks in advance and enabling more reasonable and long-term planning. This solves the problems in related technologies that, due to the lack of unified and efficient environmental perception and risk assessment standards, make it difficult for ICVs to make timely and accurate decisions in complex and changing traffic environments, increase computational burdens, and reduce operational efficiency.

[0028] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0030] Figure 1 This is a flowchart of a road 4D risk occupancy assessment method based on a vehicle-road-cloud collaborative framework according to an embodiment of the present application;

[0031] Figure 2 Schematic diagram of the principle of a road 4D risk occupancy assessment method based on a vehicle-road-cloud collaborative framework according to one embodiment of the present application;

[0032] Figure 3 A schematic diagram of an arrangement of road sampling points according to an embodiment of the present application;

[0033] Figure 4 Schematic diagram of a curve showing the relationship between risk value and estimated arrival time according to one embodiment of the present application;

[0034] Figure 5 A schematic diagram of a vehicle-road-cloud collaboration framework according to an embodiment of the present application;

[0035] Figure 6 This is a schematic diagram of the structure of a road 4D risk occupancy assessment device based on a vehicle-road-cloud collaborative framework according to an embodiment of the present application;

[0036] Figure 7 A schematic structural diagram of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0038] The following describes the road 4D risk occupancy assessment method and device based on the vehicle-road-cloud collaborative framework of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that in the related technologies mentioned in the above background technology center, due to the lack of a unified and efficient environmental perception and risk assessment standard, it is difficult for intelligent connected vehicles to make timely and accurate decisions in complex and changeable traffic environments, which increases the computing burden and reduces operating efficiency, the present application provides a road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework. In this method, different sampling point sets can be dynamically retrieved according to the changes in the position and driving direction of the ICV, and the risk factors affecting the driving safety of the intelligent connected vehicle ICV can be obtained. Then, the dynamic and static factors are converted into geometric objects, so as to obtain the risk factors affecting the driving safety of the intelligent connected vehicle ICV based on the geometric objects and each sampling point set. The system uses a sampling point to obtain multiple dynamic and static factors within the preset perception range of each sampling point, thereby performing risk quantification calculations on the multiple dynamic and static factors and each sampling point, and obtaining the risk values ​​corresponding to the multiple dynamic and static factors. The corresponding risk values ​​are accumulated and normalized to obtain a 4D risk occupancy map composed of the final risk values ​​of all sampling points in the sampling point set. This helps to respond to dynamic changes in a timely manner and achieve quantitative assessment of risks. The use of the vehicle-road-cloud collaborative framework is conducive to optimizing resource allocation, improving the accuracy and efficiency of assessments, and can help ICVs obtain beyond-visual-range risk perception capabilities that a single vehicle does not have, effectively avoiding risks in advance, and making more reasonable and long-term plans. This solves the problem in related technologies that, due to the lack of unified and efficient environmental perception and risk assessment standards, intelligent connected vehicles have difficulty making timely and accurate decisions in complex and changing traffic environments, increasing the computing burden, and reducing operating efficiency.

[0039] Specifically, Figure 1 A flowchart of a road 4D risk occupancy assessment method based on a vehicle-road-cloud collaborative framework provided in an embodiment of the present application.

[0040] like Figure 1 As shown, the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework includes the following steps:

[0041] In step S101, different sampling point sets are dynamically retrieved according to changes in the position and driving direction of the intelligent connected vehicle (ICV).

[0042] During the actual implementation process, the embodiment of the present application can obtain the road area where the ICV is located and the driving direction requirements after entering the intersection in the future based on the instructions sent by the ICV from the edge cloud platform, and dynamically retrieve different road sampling point sets stored in advance based on prior information from the edge cloud platform.

[0043] It is worth noting that the road sampling point set is dynamic. When the ICV's location changes to a different road area, the road sampling point set is also dynamically updated. Sampling points can be dynamically selected based on the road sampling point set, which is conducive to improving the timeliness and flexibility of data collection and providing a basis for subsequent calculation and evaluation.

[0044] In step S102, risk factors affecting the driving safety of the ICV are obtained, wherein the risk factors are dynamic and static factors.

[0045] It can be understood that risk factors refer to any factors in the environment that may pose a threat to the driving safety of ICVs, including static factors and dynamic factors. Among them, static factors are relatively stationary in space and can be fixed obstacles on the road, such as road markings, railings, curbs, roadblocks, and potholes; dynamic factors are constantly changing in time and space, posing a direct and urgent threat to the driving safety of ICVs, including but not limited to human-driven vehicles (HDVs), non-motor vehicles, and pedestrians.

[0046] Specifically, combined Figure 2 As shown, the embodiments of the present application can utilize the edge cloud platform to obtain static factors that affect the driving safety of intelligent connected vehicles (ICVs) based on data stored in advance based on prior information, including fixed obstacles on the road, such as road markings, railings, curbs, roadblocks, and potholes. Dynamic factors can be perceived by multiple roadside sensing units, including human-driven vehicles (HDVs), non-motorized vehicles, pedestrians, etc.

[0047] The embodiment of the present application can obtain the BEV perception results (structured data) sent by the road-side perception unit, and obtain the static and dynamic factors that affect the driving safety of intelligent connected vehicles (ICVs), thereby helping to improve the accuracy of risk assessment, carry out targeted protection, and achieve efficient resource allocation, avoid unnecessary computing loads, and save energy.

[0048] In step S103, the dynamic and static factors are converted into geometric objects, so as to obtain a plurality of dynamic and static factors within a preset perception range of each sampling point based on the geometric object and each sampling point in the sampling point set.

[0049] It is understood that geometric objects can be expressed in four forms: single point, multiple points, line segments, and vectors. The preset perception range refers to the maximum range or area within which a target can be effectively detected, identified, and tracked at a sampling point. The specific setting can be determined by those skilled in the art based on actual circumstances and is not limited here.

[0050] Specifically, combined Figure 2 and Figure 3As shown, the embodiment of the present application can lay out road surface risk sampling points in a grid along the road direction according to an adjustable resolution, and present traffic risk factors in the form of geometric objects. Furthermore, the embodiment of the present application can calculate the Euclidean distance between two sampling points, and the vertical distance from a point to a line segment vector, so as to know whether the dynamic and static factors are within the perception range of the sampling point.

[0051] It is worth noting that the embodiment of the present application can lay out road risk sampling points in a grid pattern, and use the road space as a perspective to evaluate the risk occupancy of the entire traffic road, achieve comprehensive monitoring of the entire road section, enhance environmental perception capabilities, convert dynamic and static factors into geometric objects, and be able to understand the surrounding environment with more precise geometric forms, improve the accuracy and detail of perception, and provide data support for subsequent evaluations.

[0052] Optionally, in one embodiment of the present application, multiple dynamic and static factors within a preset perception range of each sampling point are obtained, including: adopting a preset perception range radius strategy to set differentiated perception ranges for static factors and dynamic factors, wherein the radius of the static perception range is smaller than the radius of the dynamic perception range.

[0053] Based on the characteristics of dynamic and static factors, this embodiment of the application sets the static factor perception range radius smaller than the dynamic factor perception range radius, enabling more accurate perception of the specific location of static factor risks. The larger dynamic factor perception range addresses the high uncertainty of dynamic factors' motion. Appropriately expanding the dynamic factor perception range helps improve road space safety redundancy. Using different perception range radii based on the characteristics of different factors improves the accuracy and safety of risk assessment.

[0054] In step S104, risk quantification calculations are performed on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, respectively. The corresponding risk values ​​are accumulated and normalized to obtain final risk values ​​for all sampling points in the sampling point set, and a road 4D risk occupancy map is generated based on the final risk values.

[0055] In the embodiment of the present application, multiple dynamic and static factors can be used to perform risk quantification calculations on each sampling point in a sampling point set of a partial road area that is called in real time. The risk values ​​corresponding to the multiple dynamic and static factors can be obtained. The corresponding risk values ​​are accumulated and normalized to obtain the final risk value of all sampling points in the sampling point set. Compared with 3D-Occupancy, only the risk value of each road surface unit needs to be calculated, and the computational complexity is much lower than traversing the occupancy of three-dimensional voxels.

[0056] It is worth noting that this application optimizes the driving risk field modeling in related technologies by removing the reliance on complex and difficult-to-quantify parameters, focusing on directly observable information and key risk factors, and using ETA as a key indicator to quantify the risk of dynamic factors, thereby achieving risk quantification. At the same time, this application can combine time prediction with risk valuation, using perception results to predict the risk of the road environment within the next few seconds, which can support ICVs to make plans and decisions in advance in dynamic mixed and dynamic traffic scenarios.

[0057] Optionally, in one embodiment of the present application, a risk quantification calculation is performed on multiple dynamic and static factors and each sampling point, including: using a static factor risk quantification formula to quantify the static factors within the static perception range, and assigning fixed risk constant values ​​and corresponding weights to different types of static factors; using a dynamic factor risk quantification model to quantify the dynamic factors within the dynamic perception range to calculate the risk size of different types of dynamic factors.

[0058] In some embodiments, although static factors are relatively stationary in space, they may play a key role in traffic accidents. In embodiments of the present application, a static factor risk quantification formula may be used to quantify the static factors. Optionally, in one embodiment of the present application, the static factor risk quantification formula is:

[0059]

[0060] Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point;

[0061] In addition, each type of static obstacle is assigned a fixed risk value and a corresponding weight. The embodiment of the present application can evaluate the risk constants and risk weights of different types of static factors based on the degree of harm to ICV occupants or traffic participants. For example, the weights of railings and curbs will cause collision damage to ICVs and occupants, and the risk constants and weights will be higher. The solid lines are traffic rules issues, but will not cause direct harm like the first two, so the risk constants and weights will be smaller.

[0062] In other embodiments, dynamic factors are constantly changing in time and space, posing a direct and urgent threat to the driving safety of ICVs. In this embodiment, it is necessary to consider key information such as the position, speed, and heading angle of traffic participants, and quantify the risk of these dynamic factors by introducing the Estimated Time of Arrival (ETA) indicator and a dynamic factor risk quantification model obtained by polynomial regression fitting. Optionally, in one embodiment of this application, the dynamic factor risk quantification model is:

[0063]

[0064] Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

[0065] Specifically, for dynamic factors, the sampling point can calculate the ETA value with the traffic participant's location according to formula (1), and calculate the potential collision risk based on the ETA value and formula (2). For static factors, the sampling point can detect whether the vector and point enter the static perception range and assign a fixed risk value based on the static factor type.

[0066] In the actual execution process, the sampling point can calculate the corresponding ETA value according to its own position and the position of the dynamic factors, combined with the movement speed and direction, according to formula (1). Figure 4 As shown in the figure, for example, a vehicle B is traveling at a speed of 4m / s and is about 2m away from sampling point A. Using the ETA formula, it can be calculated that the ETA value between the two is about 0.5 seconds. According to the collision risk formula, the potential collision risk brought by this dynamic factor is calculated to be 0.95.

[0067] The embodiment of the present application utilizes a static factor risk quantification formula to quantify static factors, which can achieve a quantitative assessment of risk factors, making risk levels more intuitive and comparable, facilitating system priority sorting and resource allocation, and utilizes a dynamic factor risk quantification model to quantify dynamic factors, which can respond to changes in real time and help to take timely measures.

[0068] Further, combined with Figure 5 As shown, the embodiment of the present application designs and adopts a simple and normalized mathematical modeling. The data collected from the ICV, multiple road-side sensing units, and edge cloud storage can be integrated and split into independent data vectors. Then, the edge cloud platform retrieves the corresponding set of sampling points of the road section to be passed in the future and converts the dynamic and static factors into corresponding geometric objects to realize data collection and processing. The road sampling points with risk values ​​below the preset threshold, that is, collision-free points, can be screened out and stored in sequence for risk occupancy assessment. The results of the road risk occupancy situation can be transmitted back to the ICV from the cloud as reference information to provide real-time support for its decision-making. Utilizing the vehicle-road-cloud collaborative architecture, the algorithm is run on a high-computing server in the cloud, which helps to reduce the computing burden of the vehicle-side hardware and speed up the assessment of road risks.

[0069] According to the 4D road risk occupancy assessment method based on the vehicle-road-cloud collaborative framework proposed in the embodiment of the present application, different sampling point sets can be dynamically retrieved according to changes in the position and driving direction of the ICV, and risk factors affecting the driving safety of the intelligent connected vehicle (ICV) can be obtained. Then, the dynamic and static factors are converted into geometric objects. Based on the geometric objects and each sampling point in the sampling point set, multiple dynamic and static factors within a preset perception range of each sampling point are obtained, and risk quantification calculations are performed on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors. The corresponding risk values ​​are accumulated and normalized to obtain a 4D risk occupancy map consisting of the final risk values ​​of all sampling points in the sampling point set. This helps to respond to dynamic changes in a timely manner and realize quantitative risk assessment. In addition, the use of the vehicle-road-cloud collaborative framework is conducive to optimizing resource allocation and improving the accuracy and efficiency of assessment. It can help ICVs obtain beyond-visual-range risk perception capabilities that a single vehicle does not have, effectively avoid risks in advance, and make more reasonable and long-term plans. This solves the problem in related technologies that, due to the lack of unified and efficient environmental perception and risk assessment standards, smart connected vehicles find it difficult to make timely and accurate decisions in complex and changing traffic environments, which increases the computing burden and reduces operating efficiency.

[0070] Next, a road 4D risk occupancy assessment device based on a vehicle-road-cloud collaborative framework proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0071] Figure 6 It is a block diagram of a road 4D risk occupancy assessment device based on a vehicle-road-cloud collaborative framework according to an embodiment of the present application.

[0072] like Figure 6 As shown, the road 4D risk occupancy assessment device 10 based on the vehicle-road-cloud collaborative framework includes: a calling module 100, an acquisition module 200, a determination module 300 and an assessment module 400.

[0073] Specifically, the retrieval module 100 is used to dynamically retrieve different sampling point sets according to changes in the position and driving direction of the intelligent connected vehicle ICV;

[0074] An acquisition module 200 is configured to acquire risk factors that affect the driving safety of the ICV, wherein the risk factors are dynamic and static factors;

[0075] a determination module 300 for converting the dynamic and static factors into geometric objects, so as to obtain, based on the geometric objects and each sampling point in the sampling point set, a plurality of dynamic and static factors within a preset perception range of each sampling point;

[0076] Evaluation module 400 is configured to perform risk quantification calculations on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, accumulate the corresponding risk values, and normalize them to obtain a final risk value for all sampling points in the sampling point set, thereby generating a 4D road risk occupancy map based on the final risk values.

[0077] Optionally, in one embodiment of the present application, the determination module 300 includes: a setting unit.

[0078] The setting unit is configured to adopt a preset perception range radius strategy to set differentiated perception ranges for static factors and dynamic factors, wherein the radius of the static perception range is smaller than the radius of the dynamic perception range.

[0079] Optionally, in one embodiment of the present application, the evaluation module 400 includes: an allocation unit and a calculation unit.

[0080] The allocation unit is configured to quantify the static factors within the static perception range using a static factor risk quantification formula, and allocate fixed risk constant values ​​and corresponding weights to different types of static factors;

[0081] The calculation unit quantifies the dynamic factors within the dynamic perception range by using a dynamic factor risk quantification model to calculate the risk sizes of different types of the dynamic factors.

[0082] Optionally, in one embodiment of the present application, the static factor risk quantification formula is:

[0083]

[0084] Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point;

[0085] The dynamic factor risk quantification model is:

[0086]

[0087] Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

[0088] It should be noted that the above explanation of the embodiment of the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework is also applicable to the road 4D risk occupancy assessment device based on the vehicle-road-cloud collaborative framework of this embodiment, and will not be repeated here.

[0089] According to the 4D road risk occupancy assessment device based on the vehicle-road-cloud collaborative framework proposed in the embodiment of the present application, different sampling point sets can be dynamically retrieved according to changes in the position and driving direction of the ICV, and risk factors affecting the driving safety of the intelligent connected vehicle (ICV) can be obtained. Then, the dynamic and static factors are converted into geometric objects. Based on the geometric objects and each sampling point in the sampling point set, multiple dynamic and static factors within a preset perception range of each sampling point are obtained. Risk quantification calculations are then performed on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors. The corresponding risk values ​​are accumulated and normalized to obtain a 4D risk occupancy map consisting of the final risk values ​​of all sampling points in the sampling point set. This helps to respond to dynamic changes in a timely manner and achieve quantitative risk assessment. In addition, the use of the vehicle-road-cloud collaborative framework is conducive to optimizing resource allocation and improving the accuracy and efficiency of assessments. It can help ICVs obtain beyond-visual-range risk perception capabilities that a single vehicle does not have, effectively avoid risks in advance, and make more reasonable and long-term plans.

[0090] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0091] Memory 701 , processor 702 , and computer programs stored in the memory 701 and executable on the processor 702 .

[0092] When the processor 702 executes the program, the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework provided in the above embodiment is implemented.

[0093] Furthermore, the vehicle further comprises:

[0094] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0095] The memory 701 is used to store computer programs that can be run on the processor 702 .

[0096] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0097] If the memory 701, processor 702, and communication interface 703 are implemented independently, the communication interface 703, memory 701, and processor 702 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0098] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0099] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0100] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for assessing the road 4D risk occupancy based on the vehicle-road-cloud collaborative framework is implemented.

[0101] An embodiment of the present application also provides a computer program product, which can run computer instructions. When the computer instructions are executed by a processor, the above-mentioned road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework is implemented.

[0102] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0104] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0105] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0106] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0107] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0108] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0109] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A road 4D risk occupancy assessment method based on a vehicle-road-cloud collaborative framework, characterized by: The following steps are involved: Dynamically retrieve different sampling point sets based on changes in the location and driving direction of the intelligent connected vehicle (ICV); Obtaining risk factors that affect the driving safety of the ICV, wherein the risk factors are dynamic and static factors; Converting the dynamic and static factors into a geometric object, so as to obtain a plurality of dynamic and static factors within a preset perception range of each sampling point based on the geometric object and each sampling point in the sampling point set; A risk quantification calculation is performed on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, and the corresponding risk values ​​are accumulated and normalized to obtain a final risk value for all sampling points in the sampling point set, so as to generate a road 4D risk occupancy map based on the final risk value.

2. The method according to claim 1, characterized in that The obtaining of multiple dynamic and static factors within a preset perception range of each sampling point includes: A preset perception range radius strategy is adopted to set differentiated perception ranges for static factors and dynamic factors, where the radius of the static perception range is smaller than that of the dynamic perception range.

3. The method according to claim 2, characterized in that The performing risk quantification calculation on the multiple dynamic and static factors and each sampling point includes: quantifying the static factors within the static perception range using a static factor risk quantification formula, and assigning fixed risk constant values ​​and corresponding weights to different types of static factors; The dynamic factors within the dynamic perception range are quantified using a dynamic factor risk quantification model to calculate the risk sizes of different types of the dynamic factors.

4. The method according to claim 3, characterized in that The static factor risk quantification formula is: Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point; The dynamic factor risk quantification model is: Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

5. A road 4D risk occupancy assessment device based on a vehicle-road-cloud collaborative framework, characterized in that: include: The retrieval module is used to dynamically retrieve different sampling point sets based on changes in the position and driving direction of the intelligent connected vehicle (ICV); an acquisition module, configured to acquire risk factors affecting the driving safety of the ICV, wherein the risk factors are dynamic and static factors; a determination module, configured to convert the dynamic and static factors into a geometric object, so as to obtain a plurality of dynamic and static factors within a preset perception range of each sampling point based on the geometric object and each sampling point in the sampling point set; An assessment module is configured to perform risk quantification calculations on the multiple dynamic and static factors and each sampling point to obtain risk values ​​corresponding to the multiple dynamic and static factors, accumulate the corresponding risk values, normalize them to obtain a final risk value for all sampling points in the sampling point set, and generate a 4D road risk occupancy map based on the final risk values.

6. The device according to claim 5, characterized in that The determination module includes: The setting unit is configured to set differentiated perception ranges for static factors and dynamic factors by adopting a preset perception range radius strategy, wherein the radius of the static perception range is smaller than the radius of the dynamic perception range.

7. The device according to claim 6, characterized in that The evaluation module includes: an allocating unit, configured to quantify the static factors within the static perception range using a static factor risk quantification formula, and allocate fixed risk constant values ​​and corresponding weights to different types of the static factors; The calculation unit quantifies the dynamic factors within the dynamic perception range by using a dynamic factor risk quantification model to calculate the risk sizes of different types of the dynamic factors.

8. The device according to claim 7, characterized in that The static factor risk quantification formula is: Among them, Risk sta is the static risk value, Constant is the risk constant value, Distance so is the distance between the factor and the sampling point; The dynamic factor risk quantification model is: Among them, ETA is the estimated arrival time, Distance so is the distance between the factor and the sampling point, Speed ​​is the driving speed of the dynamic factor, Risk dyn is the dynamic risk value.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework as described in any one of claims 1-4.

11. A computer program product comprising a computer program, characterized in that The computer program is executed to implement the road 4D risk occupancy assessment method based on the vehicle-road-cloud collaborative framework as described in any one of claims 1-4.

Images