An intelligent driving function complex test scene construction method, device and medium

Abstract

The application relates to a kind of intelligent driving function complex test scene construction method, equipment and medium, the method comprises the following steps: determining complex test scene type, including weather test scene and traffic test scene;The weather test scene is characterized using quantitative natural weather factors, and weather test scene is constructed in combination with natural driving behavior characteristics;The traffic test scene is characterized using driving behavior interaction feature parameters, and traffic test scene is constructed in combination with minimum safety distance and information entropy theory method.Compared with the prior art, the application has the advantages of helping to improve the authenticity of test scene construction and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, in particular to an intelligent driving function complex test scene construction method, device and medium. BACKGROUND

[0002] At present, the automobile industry is developing rapidly, the automobile ownership is rising, and the road traffic problem is increasingly prominent. Intelligent driving function has great potential in solving traffic safety problems and improving traffic efficiency, and has become one of the technology hotspots. Under the trend of global automobile industry accelerating the application of intelligent driving function, intelligent driving function mass production is an important stage of the development of high-level intelligent driving function. However, the test and evaluation method of intelligent driving function at home and abroad is still in the initial exploration stage, and the existing mature L2 level advanced driving assistance system test and evaluation regulations only focus on safety performance, which cannot meet the functional completion evaluation demand of high-level automatic driving system, and the test and evaluation of safety performance is relatively basic; the L3 level ECE R157 uniform provisions on certification of vehicles equipped with automatic lane keeping system is still in the exploration stage, the evaluation method is relatively general, and there is no detailed specification of specific working condition parameters under each scene type, and a systematic evaluation method has not been constructed, which cannot be directly applied to navigation intelligent driving function. Therefore, it is urgent to study the evaluation method of navigation intelligent driving and perfect the relative blank field of existing regulations and standards.

[0003] At present, the intelligent function test and evaluation standard is mostly carried out under good environmental conditions, for example, the test road surface is dry, and there is no visible wet place; the test road should be flat, and there is no obvious pit, crack and other adverse conditions; the weather is good and the light is normal. Good driving environment cannot meet the test demand of intelligent driving function under real traffic complex environment, and it is necessary to construct intelligent driving function test scene which can represent the complexity of real traffic environment. SUMMARY

[0004] The purpose of the present application is to provide an intelligent driving function complex test scene construction method, device and medium which can obtain a test scene that can more accurately represent the complexity of real traffic environment.

[0005] The purpose of the present application can be realized by the following technical solutions:

[0006] An intelligent driving function complex test scene construction method, comprising the following steps:

[0007] Determine the complex test scene type, including weather test scene and traffic test scene;

[0008] The weather test scene is represented by quantitative natural weather factors, and the weather test scene is constructed in combination with natural driving behavior characteristics;

[0009] The traffic test scenario is characterized using driving behavior interaction feature parameters, and constructed by combining minimum safe distance and information entropy theory methods.

[0010] Furthermore, the natural weather factors include sunlight, rainfall, and fog.

[0011] Furthermore, the quantification process of the natural weather factors includes:

[0012] The light factors are divided into four time periods according to the driving time: night, early morning and dusk, morning and afternoon, and noon. They are quantified in lux to complete the quantification process of light factors.

[0013] Based on the aforementioned rainfall factors, rainfall is categorized into four levels: no rain, light rain, moderate rain, and heavy rain. The rainfall is quantified using the amount of rainfall within a set time period as the unit, thus completing the quantification process of rainfall factors.

[0014] Based on the aforementioned fog factors, visibility is used as the unit for quantification, thus completing the quantification process of fog factors.

[0015] Furthermore, the steps for constructing the weather test scenario include:

[0016] The characteristics of natural driving behavior under quantified natural weather factors are characterized by the vehicle's headway at the moment of braking, where the representation expression is:

[0017] THW = d / v

[0018] In the formula, THW is the headway at the moment of braking, d represents the distance between the rear of the preceding vehicle and the front of this vehicle at the moment of braking, i.e., the relative distance, and v represents the speed of this vehicle.

[0019] Under different quantified natural weather factors, and combined with the median headway of the vehicle, an impact index of natural weather factors is constructed. The impact index of natural weather factors includes the impact index of sunlight, the impact index of rainfall, and the impact index of fog.

[0020] Weather complexity is constructed based on the influence indicators of the aforementioned natural weather factors, and used as a weather test scenario. The weather complexity is expressed as follows:

[0021] f weather =θ light *θ rain *θ fog

[0022] In the formula, f weather Let θ be the weather complexity parameter. light θ represents the light impact index. rain θ represents the value of the rainfall impact index. fog Indicators related to the impact of fog.

[0023] Further, the driving behavior interaction feature parameters include a meeting angle, a relative distance, and a relative speed.

[0024] Further, the step of constructing the traffic test scene includes:

[0025] According to a relationship between the meeting angle and the traffic complexity, a meeting angle complexity is calculated in combination with a minimum safety distance method, wherein the meeting angle complexity is calculated as:

[0026]

[0027] wherein f angle is the meeting angle complexity, θ i is a meeting angle of the test vehicle and a target vehicle i;

[0028] According to a relationship between the relative distance and the traffic complexity, a relative distance complexity is calculated in combination with an information entropy theory method, wherein the relative distance complexity is calculated as:

[0029]

[0030] wherein f distance is the relative distance complexity, d ij is a relative distance of the test vehicle and the target vehicle i, d max is a maximum relative distance of the test vehicle and the target vehicle;

[0031] According to a principle that the greater the relative speed is, the more dangerous it is, a relative speed complexity is calculated in combination with the information entropy theory method, wherein the relative speed complexity is calculated as:

[0032]

[0033] wherein f velocity is the relative speed complexity, v i is a relative speed of the test vehicle and the target vehicle i, v max is a maximum relative speed of the test vehicle and the target vehicle;

[0034] Traffic complexity is constructed based on the meeting angle complexity, the relative distance complexity, and the relative speed complexity, as a traffic test scene, wherein the traffic complexity is expressed as:

[0035]

[0036] wherein f is the traffic complexity.

[0037] Further, the maximum relative distance dmax The calculation process of d

[0038] Based on the distribution characteristics of the headway at the braking moment of the vehicle in the dangerous driving behavior and the normal driving behavior in the natural driving data, a support vector machine method is used to fit a demarcation curve representing the vehicle safety, wherein the demarcation curve of the vehicle safety is expressed as:

[0039]

[0040] In the formula, THE is the headway at the braking moment, represents the vehicle safety, and v represents the speed of the vehicle;

[0041] Based on the demarcation curve of the vehicle safety and the speed of the test vehicle, the maximum relative distance d max between the test vehicle and the target vehicle is obtained. max The calculation expression of d

[0042]

[0043] In the formula, v host represents the speed of the test vehicle.

[0044] Further, the calculation process of the maximum relative speed v max between the test vehicle and the target vehicle includes:

[0045] According to the distance collision time at the braking moment of the vehicle, a support vector machine method and a K-fold cross-validation method are combined to construct a demarcation curve of a non-collision condition and a collision condition in the dangerous working condition of the natural driving, wherein the calculation expression of the distance collision time is:

[0046] TTC=d / (v host -v target )

[0047] In the formula, TTC is the distance collision time at the braking moment of the vehicle, d represents the distance between the tail of the vehicle and the head of the vehicle at the braking moment, i.e., the relative distance; v host represents the speed of the vehicle; and v target represents the speed of the target vehicle.

[0048] Based on the demarcation curve of the non-collision condition and the collision condition, the speed of the test vehicle, and the maximum relative distance d max between the test vehicle and the target vehicle, the maximum relative speed v max between the test vehicle and the target vehicle is obtained. max The calculation expression of v

[0049]

[0050] In the formula, vhost Indicates the test vehicle speed.

[0051] The application also provides an electronic device, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs comprising instructions for performing the intelligent driving function complex test scene construction method as described above.

[0052] The application also provides a computer-readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs comprising instructions for performing the intelligent driving function complex test scene construction method as described above.

[0053] Compared with the prior art, the application has the following beneficial effects:

[0054] (1) Based on the intelligent driving function scene test requirements, the scene complexity is split into weather complexity and traffic complexity, considering the intelligent driving function test environment influencing factors, which helps to improve the authenticity of the test scene construction, the weather complexity is represented by quantified natural weather factors, and the natural driving behavior under the natural weather factors is considered to construct the weather complexity, the traffic complexity is represented by driving behavior interaction characteristic parameters, and the minimum safety distance and information entropy theory method are considered to construct the traffic complexity, which helps to get more accurate test scene complexity in a more realistic test scene.

[0055] (2) The application represents and constructs the test scene meteorological environment based on weather influencing factors such as light, rainfall, and fog, fills the gap in intelligent driving function complex scene testing, provides a basis for subsequent development of related test evaluation standards, and helps the test certification of intelligent driving function.

[0056] (3) The application represents and constructs the test scene traffic complexity through traffic influencing factors such as meeting angle, relative distance, and relative distance, which together with the weather complexity represents the intelligent driving function complex test scene, accelerates the intelligent driving function test evaluation related research, and promotes the research and development and landing application of intelligent driving function. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a method flowchart of the application;

[0058] Figure 2 is a test scene element level in the embodiment of the application;

[0059] Figure 3Figures (a), (b) and (c) are diagrams of the distribution of the natural driving behavior feature THW under the influence of the weather complexity factors of illumination, rainfall and fog in the embodiments of the present application, wherein figure (a) is a diagram of the distribution of THW under different illumination environments, figure (b) is a diagram of the distribution of THW under different rainfall environments, and figure (c) is a diagram of the distribution of THW under different fog environments;

[0060] Figure 4 Figures (a), (b) and (c) are diagrams of the complexity of the meeting angle, relative distance and relative speed of the traffic complexity influencing factor corresponding to the embodiments of the present application, wherein figure (a) is a diagram of the complexity of the meeting angle, figure (b) is a diagram of the complexity of the relative distance, and figure (c) is a diagram of the complexity of the relative speed.

[0061] Figure 5 Figures (a) and (b) are diagrams of the safety boundary curves of the natural driving behavior feature THW and TTC in the embodiments of the present application, wherein figure (a) is a diagram of the safety boundary curve of THW, and figure (b) is a diagram of the safety boundary curve of TTC. DETAILED DESCRIPTION

[0062] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. The present embodiments are implemented on the premise of the technical solutions of the present application, and detailed implementation manners and specific operation processes are given, but the protection scope of the present application is not limited to the following embodiments.

[0063] Embodiment 1

[0064] The present embodiment provides a method for constructing an intelligent driving function complexity test scene, as shown in Figure 1 The method comprises the following steps:

[0065] S1, the type of the complex test scene is determined.

[0066] The present embodiment is based on the ASAM OpenScenario standard. The test scene elements can be divided into six levels according to the standard: road structure, traffic facilities, quasi-static road conditions, entity objects, environmental conditions and digital information. The road structure layer describes the structural parameters (such as topology, grade, curvature, slope, etc.) and design parameters (such as the number of lanes, lane line types, etc.) of the road; the traffic facilities layer describes traffic facilities (such as traffic lights, gantries, etc.) and isolation facilities (such as soundproof walls, green belts, etc.); the quasi-static road condition layer describes temporary changes in the topological structure (such as road maintenance, road closure, etc.) and short-time changes in the road surface state (such as road coverings, etc.); the entity object layer describes static or dynamic movable objects (such as motor vehicles, non-motor vehicles, pedestrians, etc.); the environmental condition layer describes natural factors that do not physically interact with the vehicle (such as weather, illumination, etc.); and the digital information layer describes interactive information such as V2X and high-precision maps, Figure 2The test requirements of intelligent driving function complex scenarios, considering the limited area of closed test area, fixed road structure, simple signs and markings, etc. The environmental condition layer and the entity object layer are selected as the weather complexity and traffic complexity to represent the complexity of the test scene.

[0067] S2, the quantified natural weather factors are used to represent the weather complexity, and the weather test scene is constructed by the natural driving behavior characteristics.

[0068] According to the description of the environmental condition layer in ASAM Openscenario, the weather factors such as light, rain and fog that do not interact with the test vehicle are quantified to represent the weather complexity of the test scene. The light factor is divided into four time periods according to the driving time, namely night (18:30-7:00), morning and evening (7:00-8:30, 17:00-18:30), morning and afternoon (8:30-11:30, 14:00-17:00), and noon (11:30-14:00), and is quantified in units of lux. The rain factor is quantified in units of 24-hour rainfall in millimeters (mm) according to the GB-T 28592-2012 Rainfall Standard

[24] , which is divided into four levels: no rain, light rain, moderate rain, and heavy rain. The fog factor is quantified in units of visibility in meters (m) according to the GB / T 31444-2015 Foggy Road Traveling Condition Warning Classification, as shown in Table 1.

[0069] Table 1 Quantification of natural weather factors

[0070]

[0071] Based on the quantified weather factors, the light (θ light ), rain (θ rain ), and fog (θ fog ) influence indicators are constructed. The light intensity (5000-100000 lux), rainfall (0 mm), and fog visibility (500-1000 m) are set as the baseline indicators (value 1.0), and the non-good weather influence indicators are set based on the baseline indicators through the distribution of natural driving behavior characteristics.

[0072] The natural driving behavior characteristics under the quantified natural weather factors of light, rain, and fog are represented by the time headway (THW) of the driver's braking time, which is defined as

[0073] THW=d / v (1)

[0074] where d represents the distance between the tail of the preceding vehicle and the head of the vehicle at the braking time, i.e. the relative distance, and v represents the speed of the vehicle.

[0075] For the light factor, the rainfall factor, and the fog factor, the THW driving behavior characteristic distribution of the China-FOT natural driving dangerous working condition is studied, and the results are shown in FIGS. (a), (b), and (c) of Figure 3 FIG. 1, the median of THW under different quantized weather factors is analyzed, and the specific influence index values of different light factors, rainfall factors, and fog factors are constructed according to the weather factor influence index interval (1.0-2.0), as shown in Table 2.

[0076] Table 2 Natural weather factor influence index

[0077]

[0078] Based on the influence indexes such as light, rainfall, and fog, the weather complexity (f weather ) is constructed as a weather test scene, and the formula is as follows:

[0079] f weather =θ light *θ rain *θ fog (2)

[0080] S3, the driving behavior interaction feature parameter is used to represent the traffic complexity, and the traffic test scene is constructed by analyzing the natural driving behavior and using the minimum safety distance and information entropy theory method.

[0081] In the intelligent networked vehicle test evaluation, the traffic complexity is a key index for evaluating the navigation intelligent driving function. In order to represent the traffic state complexity, based on the space-time interaction relationship of traffic participants, the meeting angle θ ij , the relative speed v ij , and the relative distance d ij are used to construct the complex traffic test scene.

[0082] The relationship between the meeting angle and the complexity in the traffic test scene is widely recognized in the field of navigation, and the minimum safety distance (Minimum Distance to Collision, MDTC) is considered. Considering the difference between ship collision in the field of navigation and vehicle collision in road traffic, the meeting angle-complexity parameter formula is optimized. As shown in FIG. (a) of Figure 4 , based on the consideration of segmented research of vehicle normal turning and vehicle U-turn process in intersection area, the vehicle meeting angle value interval is set as [0°, 90°], and the calculation formula is as follows:

[0083]

[0084] In the formula, f angle is the meeting angle complexity, θi It is the encounter angle between the test vehicle and the target vehicle i.

[0085] like Figure 4 As shown in Figure (b), referring to the information entropy theory formula, the formula for relative distance and complexity is constructed as follows:

[0086]

[0087] In the formula, f distance It is the relative distance complexity, d ij d is the relative distance between the test vehicle and the target vehicle i. max It is the maximum relative distance between the test vehicle and the target vehicle.

[0088] Based on the principle that higher relative speeds lead to greater dangers, the relationship between relative speed and complexity is as follows: Figure 4 As shown in (c), referring to the information entropy theory formula, the formula for relative speed and complexity is constructed as follows:

[0089]

[0090] In the formula, f velocity It is the relative speed complexity, v i It measures the relative speed between the test vehicle and the target vehicle i, v. max It is the maximum relative speed between the test vehicle and the target vehicle.

[0091] Maximum relative distance d max and maximum relative velocity v max The relationship with test speed will be obtained through natural driving behavior characteristic analysis.

[0092] The maximum relative distance d between the test vehicle and the target vehicle max It is characterized by the THW at the moment of driver braking. Figure 5 As shown in Figure (a), based on the THW distribution characteristics of driver braking moments for dangerous and normal driving behaviors in China-FOT natural driving data, a support vector machine method is used to fit a boundary curve characterizing vehicle safety. The boundary curve formula is defined as:

[0093]

[0094] In the formula, v represents the speed of the vehicle.

[0095] Based on the THW safety boundary curve and the speed of the test vehicle, the maximum relative distance d between the test vehicle and the target vehicle is obtained. max The formula is as follows:

[0096]

[0097] wherein v host represents the test vehicle speed.

[0098] The maximum relative speed v max between the test vehicle and the target vehicle is characterized by the distance-time-to-collision (TTC) at the braking time of the driver, and the formula for calculating the TTC is as follows:

[0099] TTC = d / (v host -v target ) (8)

[0100] wherein d represents the distance between the tail of the preceding vehicle and the head of the subject vehicle before braking, i.e., the relative vehicle distance; v host represents the speed of the subject vehicle; and v target represents the speed of the target vehicle.

[0101] Figure 5 Figure (b) in the above table shows the construction of the dividing curve between the non-collision condition and the collision condition in the China-FOT natural driving dangerous condition using the support vector machine method and the K-fold cross-validation method, and the formula for defining the dividing curve is as follows:

[0102]

[0103] wherein v host represents the test vehicle speed.

[0104] Based on the TTC safety dividing curve, the test vehicle speed, and the maximum relative distance d max , the maximum relative speed v max between the test vehicle and the target vehicle is obtained, and the formula is as follows:

[0105]

[0106] wherein v host represents the test vehicle speed.

[0107] The traffic complexity of the test vehicle and the target object i is taken as the traffic test scene by comprehensively considering the encounter angle, the relative distance, the relative speed, and other parameters, and the formula is as follows:

[0108]

[0109] Embodiment 2

[0110] The embodiment provides an electronic device, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs comprising instructions for performing the intelligent driving function complexity test scene construction method as described in embodiment 1.

[0111] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or partially contribute to the prior art, or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0112] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0113] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, 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 that implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus with the specified functions of one or more flows and / or blocks.

[0114] These computer program instructions can also be stored in a computer readable storage medium that can direct the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction apparatus, which implements the flow Figure 1 one or more flows and / or blocks Figure 1 an apparatus with the specified functions of one or more flows and / or blocks.

[0115] These computer program instructions can also be loaded into computer or other programmable data processing devices, so that a series of operations steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable data processing devices provide the function of realizing the processes specified in the flowcharts Figure 1 one flowchart or multiple flowcharts and / or blocks Figure 1 one block or multiple blocks.

[0116] Although the preferred embodiments of the application have been described, those skilled in the art will be able to make additional modifications and variations to these embodiments without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims be construed to include all such modifications and variations as fall within the scope of the application.

[0117] Obviously, various modifications and changes are possible in the present application without departing from the spirit and scope of the application. It is to be understood that the application includes any such modifications and changes only insofar as they come within the scope of the appended claims and their equivalents.

Claims

1. A method for constructing a complex test scene of intelligent driving functions, characterized in that, The method comprises the following steps: determining a complex test scene type, including a weather test scene and a traffic test scene; characterizing the weather test scene with quantified natural weather factors, and constructing the weather test scene in combination with natural driving behavior characteristics; the step of constructing the weather test scene comprises: characterizing the natural driving behavior characteristics under quantified natural weather factors with a vehicle headway at a braking time, wherein the characterization expression is: THW=d / v In the formula, THW is the vehicle headway at the braking time, d represents the distance between the tail of the preceding vehicle and the head of the subject vehicle at the braking time, i.e. the relative distance, and v represents the speed of the subject vehicle; under different quantified natural weather factors, an influence index of the natural weather factor is constructed in combination with the median of the vehicle headway, and the influence index of the natural weather factor includes an illumination influence index, a rainfall influence index, and a fog influence index; a weather complexity is constructed based on the influence index of the natural weather factor, as the weather test scene, and the weather complexity is expressed as: f weather = θ light * θ rain * θ fog In the formula, f weather is a weather complexity parameter, θ light is a light influence index value, θ rain is a rainfall influence index value, θ fog is a fog influence index; characterizing the traffic test scene with driving behavior interaction characteristic parameters, and constructing the traffic test scene in combination with a minimum safety distance and an information entropy theory method; the driving behavior interaction characteristic parameters include a meeting angle, a relative distance, and a relative speed; the step of constructing the traffic test scene comprises: according to the relationship between the meeting angle and the traffic complexity, a meeting angle complexity is calculated in combination with the minimum safety distance method, and the calculation expression of the meeting angle complexity is: where f angle is the encounter angle complexity, θ i is the encounter angle of the test vehicle with target vehicle i; according to the relationship between the relative distance and the traffic complexity, a relative distance complexity is calculated in combination with the information entropy theory method, and the calculation expression of the relative distance complexity is: where f distance is the relative distance complexity, d ij is the relative distance of the test vehicle to the target vehicle i, d max is the maximum relative distance of the test vehicle to the target vehicle; according to the principle that the greater the relative speed is, the more dangerous it is, a relative speed complexity is calculated in combination with the information entropy theory method, and the calculation expression of the relative speed complexity is: where f velocity is the relative speed complexity, v i is the relative speed of the test vehicle to the target vehicle i, v max is the maximum relative speed of the test vehicle to the target vehicle; a traffic complexity is constructed based on the meeting angle complexity, the relative distance complexity, and the relative speed complexity, as the traffic test scene, and the traffic complexity is expressed as: In the formula, is the traffic complexity. 2.The intelligent driving function complexity test scene construction method of claim 1, wherein, the natural weather factors include an illumination factor, a rainfall factor, and a fog factor. 3.The method of claim 2, wherein, the quantification process of the natural weather factors comprises: the illumination factor is quantified according to the driving time, and is divided into four time periods, i.e. night, dawn and dusk, morning and afternoon, and noon, and is quantified in units of lux, thereby completing the quantification process of the illumination factor; based on the rainfall factor, the rainfall is divided into four levels, i.e. no rain, light rain, moderate rain, and heavy rain, and is quantified in units of rainfall amount in a set time period, thereby completing the quantification process of the rainfall factor; based on the fog factor, the visibility is quantified, thereby completing the quantification process of the fog factor. 4.The method of claim 1, wherein, The maximum relative distance d of the test vehicle and the target vehicle max The calculation process includes: based on the vehicle headway distribution characteristics of dangerous driving behavior and normal driving behavior at the braking time in the natural driving data, a support vector machine method is used to fit a demarcation curve of vehicle safety, and the demarcation curve of vehicle safety is expressed as: In the formula, THW is the vehicle headway at the braking time, and v represents the speed of the subject vehicle. obtaining a maximum relative distance d between the test vehicle and the target vehicle based on the demarcation curve of the vehicle safety and the test vehicle speed max wherein the maximum relative distance d max is calculated by the expression: In the formula, v host represents the test vehicle speed. 5.The method of claim 1, wherein, the maximum relative speed v between the test vehicle and the target vehicle max The calculation process comprises: According to the distance collision time of the vehicle braking time, and combined with the support vector machine method and the K-fold cross-validation method, a natural driving dangerous working condition non-collision working condition and collision working condition dividing curve is constructed, wherein the distance collision time calculation expression is: TTC = d / (v host -v target ) In the formula, TTC is the distance collision time when the vehicle brakes, d represents the distance between the tail of the preceding vehicle and the head of the subject vehicle before braking, i.e., the relative vehicle distance; v host represents the speed of the subject vehicle; v target represents the speed of the target vehicle; Based on the boundary curve between the non-collision and collision conditions, the speed of the test vehicle, and the maximum relative distance d between the test vehicle and the target vehicle. max Obtain the maximum relative speed v between the test vehicle and the target vehicle. max The maximum relative velocity v max The calculation expression is: In the formula, v host represents the test vehicle speed.

6. An electronic device, comprising: Comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs including instructions for performing the intelligent driving function complex test scene construction method as claimed in any one of claims 1-5.

7. A computer readable storage medium characterized in that, Comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the intelligent driving function complex test scene construction method as claimed in any one of claims 1-5.

Images