Intelligent driving function complex test scene construction method, equipment and medium

Abstract

The invention relates to an intelligent driving function complex test scene construction method and device and a medium, and the method comprises the following steps: determining the type of a complex test scene, including a weather test scene and a traffic test scene; representing the weather test scene by adopting quantized natural weather factors, and constructing the weather test scene in combination with natural driving behavior characteristics; and representing the traffic test scene by adopting driving behavior interaction characteristic parameters, and constructing the traffic test scene in combination with a minimum safety distance and information entropy theory method. Compared with the prior art, the method has the advantages of being beneficial to improving the authenticity of test scene construction and the like.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method, device and medium for constructing a complex test scenario for an intelligent driving function. Background Art

[0002] At present, the automobile industry is developing rapidly, the number of cars is constantly increasing, and road traffic problems are becoming increasingly prominent. Intelligent driving functions have great potential in solving traffic safety problems and improving traffic efficiency, and have become one of the hot technologies. Under the trend of accelerating the mass production and application of intelligent driving functions in the global automobile industry, the mass production of intelligent driving functions is an important stage in the development of high-level intelligent driving functions. However, the test and evaluation methods for intelligent driving functions at home and abroad are still in the early exploration stage. The existing mature L2 advanced driving assistance system test and evaluation regulations only focus on safety performance, which cannot meet the functional completion evaluation needs of high-level automatic driving systems, and the test and evaluation of safety performance are also relatively basic; while the L3 level "ECE R157 Uniform Provisions for Certification of Vehicles Equipped with Automatic Lane Keeping Systems" which is still in the exploration field is relatively general, and does not specify the specific working condition parameters under each scenario type in detail. It has not established a systematic evaluation method and cannot be directly applied to navigation intelligent driving functions. Therefore, it is urgent to study the evaluation methods of navigation intelligent driving and improve the relatively blank areas of existing regulations and standards.

[0003] At present, the intelligent function test evaluation standards are mostly carried out under good environmental conditions, such as the test road surface is dry and there is no visible moisture; the test road should be flat, without obvious potholes, cracks and other unfavorable conditions; the weather is good and the lighting is normal. A good driving environment cannot meet the test requirements of intelligent driving functions in a complex real traffic environment. It is necessary to build an intelligent driving function test scenario that can represent the complexity of the real traffic environment. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device and medium for constructing a complex test scenario for an intelligent driving function that can obtain a test scenario that more accurately represents the complexity of a real traffic environment.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for constructing a complex test scenario for an intelligent driving function comprises the following steps:

[0007] Determine the types of complex test scenarios, including weather test scenarios and traffic test scenarios;

[0008] The weather test scenario is characterized by using quantified natural weather factors, and the weather test scenario is constructed in combination with natural driving behavior characteristics;

[0009] The traffic test scenario is characterized by using driving behavior interaction characteristic parameters, and is constructed by combining the minimum safety distance and information entropy theoretical methods.

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

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

[0012] The illumination factor is divided into four time periods according to the driving time: night, early morning and dusk, morning and afternoon, and noon, and quantified in lux to complete the quantification process of the illumination factor;

[0013] Based on the rainfall factors, the rainfall is divided into four levels: no rain, light rain, moderate rain, and heavy rain, and the rainfall in a set time period is used as a unit for quantification, thereby completing the quantification process of the rainfall factors;

[0014] Based on the fog factor, quantification is performed with visibility as the bit, thereby completing the quantification process of the fog factor.

[0015] Furthermore, the step of constructing a weather test scenario includes:

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

[0017] THW=d / v

[0018] In the formula, THW is the headway time at the braking moment, d is the distance between the rear of the previous vehicle and the head of the vehicle at the braking moment, that is, the relative vehicle distance, and v is the speed of the vehicle;

[0019] Under different quantified natural weather factors, combined with the median of the headway time, an impact index of the natural weather factor is constructed, wherein the impact index of the natural weather factor includes a light impact index, a rainfall impact index and a fog impact index;

[0020] Based on the influencing index of the natural weather factors, the weather complexity is constructed as a weather test scenario. The weather complexity is expressed as:

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

[0022] In the formula, f weather is the weather complexity parameter, θ light is the illumination impact index value, θ rain is the rainfall impact index value, θ fog It is the fog impact index.

[0023] Furthermore, the driving behavior interaction characteristic parameters include encounter angle, relative distance and relative speed.

[0024] Furthermore, the step of constructing a traffic test scenario includes:

[0025] According to the relationship between the encounter angle and traffic complexity, combined with the minimum safety distance method, the encounter angle complexity is calculated, wherein the calculation expression of the encounter angle complexity is:

[0026]

[0027] In the formula, f angle is the encounter angle complexity, θ i is the encounter angle between the test vehicle and the target vehicle i;

[0028] According to the relationship between the relative distance and traffic complexity, combined with the information entropy theory method, the relative distance complexity is calculated, wherein the calculation expression of the relative distance complexity is:

[0029]

[0030] In the formula, f distance is the relative distance complexity, d ij is the relative distance between the test vehicle and the target vehicle i, d max is the maximum relative distance between the test vehicle and the target vehicle;

[0031] According to the principle that the greater the relative speed, the more dangerous it is, combined with the information entropy theory method, the relative speed complexity is calculated, where the calculation expression of the relative speed complexity is:

[0032]

[0033] In the formula, f velocity is the relative speed complexity, v i is the relative speed between the test vehicle and the target vehicle i, v max is the maximum relative speed between the test vehicle and the target vehicle;

[0034] Based on the encounter angle complexity, relative distance complexity and relative speed complexity, traffic complexity is constructed as a traffic test scenario, wherein the traffic complexity is expressed as:

[0035]

[0036] In the formula, The traffic complexity.

[0037] Furthermore, the maximum relative distance d between the test vehicle and the target vehicle ismax The calculation process includes:

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

[0039]

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

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

[0042]

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

[0044] Furthermore, the maximum relative speed v between the test vehicle and the target vehicle is max The calculation process includes:

[0045] According to the distance-to-collision time at the moment of vehicle braking, the boundary curve between non-collision conditions and collision conditions in natural driving dangerous conditions is constructed by combining the support vector machine method and the K-fold intersection verification method, wherein the calculation expression of the distance-to-collision time is:

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

[0047] Where TTC is the distance to collision time at the moment of vehicle braking, d represents the distance between the rear of the preceding vehicle and the head of the vehicle at the moment of braking, i.e., the relative vehicle distance; v host Indicates the vehicle speed; v target Indicates the target vehicle speed;

[0048] Based on the boundary curve between the non-collision condition and the collision condition, the test vehicle speed, 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 , where the maximum relative speed v max The calculation expression is:

[0049]

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

[0051] The present invention also provides an electronic device, comprising: one or more processors; a memory; and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the method for constructing complex test scenarios for intelligent driving functions as described above.

[0052] The present invention also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the method for constructing complex test scenarios for intelligent driving functions as described above.

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

[0054] (1) Based on the requirements of intelligent driving function scenario testing, the present invention divides the scenario complexity into weather complexity and traffic complexity, takes into account the influencing factors of the intelligent driving function test environment, helps to improve the authenticity of the test scenario construction, characterizes the weather complexity by quantifying natural weather factors, and constructs the weather complexity by considering the natural driving behavior under natural weather factors, characterizes the traffic complexity by driving behavior interaction characteristic parameters, and constructs the traffic complexity by considering the minimum safety distance and information entropy theoretical method, which helps to obtain more accurate test scenario complexity in a more realistic test scenario.

[0055] (2) The present invention constructs the meteorological environment of the test scenario based on the characterization of weather influencing factors such as light, rainfall, and fog, filling the gap in complex scenario testing of intelligent driving functions, providing a basis for the subsequent formulation of relevant test evaluation standards, and facilitating the test and certification of intelligent driving functions.

[0056] (3) The present invention constructs the traffic complexity of the test scenario by characterizing traffic influencing factors such as encounter angle, relative distance, and relative distance, and jointly characterizes the complex test scenario of the intelligent driving function with the weather complexity, accelerates the research related to the test and evaluation of the intelligent driving function, and promotes the research, development and application of the intelligent driving function. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0058] Figure 2 It is the test scene element level in the embodiment of the present invention;

[0059] Figure 3The THW distribution diagram of the natural driving behavior characteristics under the lighting, rainfall and fog environment of the weather complexity influencing factors in the embodiment of the present invention, wherein (a) is the THW distribution diagram under different lighting environments, (b) is the THW distribution law diagram under different rainfall environments, and (c) is the THE distribution diagram under different fog environments;

[0060] Figure 4 The figures are corresponding diagrams of the complexity of the factors affecting traffic complexity, namely, the encounter angle, relative distance, and relative speed in the embodiment of the present invention; wherein (a) is the complexity diagram of the encounter angle, (b) is the complexity diagram of the relative distance, and (c) is the complexity diagram of the relative speed;

[0061] Figure 5 THW and TTC safety boundary curve diagrams of natural driving behavior characteristics in an embodiment of the present invention; wherein (a) is a THW safety boundary curve diagram, and (b) is a TTC safety boundary curve diagram. DETAILED DESCRIPTION

[0062] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0063] Example 1

[0064] This embodiment provides a method for constructing a complex test scenario for an intelligent driving function. Figure 1 As shown, the method comprises the following steps:

[0065] S1. Clarify the types of complex test scenarios.

[0066] This embodiment is based on the ASAM OpenScenario standard, which divides the test scenario elements into six levels: road structure, traffic facilities, quasi-static road conditions, physical 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 type, etc.) of the road; the traffic facility layer describes the traffic facilities (such as traffic lights, gantries, etc.) and isolation facilities (such as sound insulation walls, green belts, etc.); the quasi-static road condition layer describes temporary changes in topological structures (such as road maintenance, road closures, etc.) and short-term changes in road surface conditions (such as road surface coverings, etc.); the physical object layer describes static or dynamic movable objects (such as motor vehicles, non-motor vehicles, pedestrians, etc.); the environmental conditions layer describes natural factors that do not physically interact with the vehicle (such as weather, light, etc.); the digital information layer describes interactive information such as V2X and high-precision maps, such as Figure 2According to the test requirements of complex scenarios of intelligent driving functions, and considering the limited area of ​​the closed field test area, fixed road structure, simple signs and markings, the environmental condition layer and the entity object layer are selected as weather complexity and traffic complexity to characterize the complexity of the test scenario.

[0067] S2. Use quantified natural weather factors to characterize weather complexity and construct weather test scenarios based on natural driving behavior characteristics.

[0068] Referring to the description of the environmental condition layer in ASAM Openscenario, weather factors such as lighting, rainfall, and fog that do not physically interact with the test vehicle are quantified to characterize the weather complexity of the test scenario. The illumination factor is divided into four time periods according to the driving time: night (18:30-7:00), early morning and dusk (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 lux. The rainfall factor is divided into four levels: no rain, light rain, moderate rain, and heavy rain according to the standard "GB-T 28592-2012 Precipitation Level"

[24] , and is quantified in 24-hour rainfall millimeters (mm). The fog factor is quantified in meters (m) according to the standard "GB / T 31444-2015 Warning Classification of Highway Traffic Conditions in Fog Days", as shown in Table 1.

[0069] Table 1 Quantification of natural weather factors

[0070]

[0071] Based on the quantified weather factors, construct the light (θ light ), rainfall (θ rain ), fog(θ fog ) Impact indicators. Good weather factors such as light intensity (5000-100000 lux), rainfall (0 mm), and fog visibility (500-1000 m) are set as benchmark indicators (value 1.0). The impact indicators of bad weather will be set based on the benchmark indicators through the distribution of natural driving behavior elements.

[0072] The natural driving behavior characteristics under quantitative natural weather factors such as light, rainfall, and fog are characterized by the time headway (THW) at the driver's braking moment, and the formula is defined as

[0073] THW=d / v (1)

[0074] In the formula, d represents the distance between the rear of the preceding vehicle and the front of the vehicle at the moment of braking, that is, the relative vehicle distance; v represents the speed of the vehicle.

[0075] In view of the factors of light, rainfall and fog, the distribution of THW driving behavior characteristics in China-FOT natural driving dangerous conditions is studied. The results are as follows: Figure 3 As shown in Figures (a), (b) and (c) in the figure, the median THW under different quantitative weather factors is analyzed. According to the weather factor impact index range (1.0-2.0), the specific impact index values ​​of different lighting factors, rainfall factors and fog factors are constructed, as shown in Table 2.

[0076] Table 2 Influence indexes of natural weather factors

[0077]

[0078] Based on the influencing indicators such as light, rainfall, fog, etc., the weather complexity (f weather ), as the weather test scenario, the formula is as follows:

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

[0080] S3. Use driving behavior interaction characteristic parameters to characterize traffic complexity. Through natural driving behavior analysis, use the minimum safety distance and information entropy theory methods to construct traffic test scenarios.

[0081] In the test and evaluation of intelligent connected vehicles, traffic complexity is a key indicator for evaluating navigation intelligent driving functions. In order to characterize the complexity of traffic conditions, based on the spatiotemporal interaction relationship between traffic participants, the encounter angle θ of the vehicles is calculated. ij , relative speed v ij and the relative distance d ij Build complex traffic test scenarios.

[0082] The relationship between the encounter angle and the complexity of the traffic test scenario is based on the widely recognized minimum distance to collision (MDTC) research in the navigation field. Considering the differences between ship collisions in the navigation field and vehicle collisions in road traffic, the encounter angle-complexity parameter formula is used for optimization. Figure 4 As shown in Figure (a), based on the consideration of the normal turning of vehicles at the intersection and the segmented study of the vehicle turning process, the vehicle encounter angle value interval is set to [0°, 90°], and the calculation formula is as follows:

[0083]

[0084] In the formula, f angle is the encounter angle complexity, θi 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 relative distance and complexity formula is constructed as follows:

[0086]

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

[0088] According to the principle that the greater the relative speed, the more dangerous it is, the relationship between relative speed and complexity is as follows: Figure 4 As shown in (c), referring to the information entropy theory formula, the relative speed and complexity formula is constructed as follows:

[0089]

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

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

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

[0093]

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

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

[0096]

[0097] In the formula, v host Indicates the test vehicle speed.

[0098] The maximum relative speed v between the test vehicle and the target vehicle max , characterized by the time to collision (TTC) at the moment of the driver's braking. The TTC calculation formula is as follows:

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

[0100] In the formula, d represents the distance between the rear of the preceding vehicle and the front of the vehicle at the moment of braking, i.e., the relative vehicle distance; v host Indicates the vehicle speed; v target Indicates the target vehicle speed.

[0101] Figure 5 Figure (b) shows the boundary curve between non-collision conditions and collision conditions in China-FOT natural driving dangerous conditions constructed by using the support vector machine method and K-fold intersection verification method. The boundary curve formula is defined as:

[0102]

[0103] In the formula, v host Indicates the test vehicle speed.

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

[0105]

[0106] In the formula, v host Indicates the test vehicle speed.

[0107] Taking into account parameters such as the encounter angle, relative distance, and relative speed, the traffic complexity between the test vehicle and the target object i is used as the traffic test scenario. The formula is:

[0108]

[0109] Example 2

[0110] This embodiment provides an electronic device, including: one or more processors; a memory; and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the method for constructing complex test scenarios for intelligent driving functions as described in Example 1.

[0111] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0112] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may 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-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0116] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0117] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for constructing complex test scenarios for intelligent driving functions, characterized in that: The following steps are involved: Determine the types of complex test scenarios, including weather test scenarios and traffic test scenarios; The weather test scenario is characterized by using quantified natural weather factors, and the weather test scenario is constructed in combination with natural driving behavior characteristics; The traffic test scenario is characterized by using driving behavior interaction characteristic parameters, and is constructed by combining the minimum safety distance and information entropy theoretical methods.

2. The method for constructing complex test scenarios for intelligent driving functions according to claim 1, characterized in that: The natural weather factors include light factors, rainfall factors and fog factors.

3. The method for constructing complex test scenarios for intelligent driving functions according to claim 2, characterized in that: The quantification process of the natural weather factors includes: The illumination factor is divided into four time periods according to the driving time: night, early morning and dusk, morning and afternoon, and noon, and quantified in lux to complete the quantification process of the illumination factor; Based on the rainfall factors, the rainfall is divided into four levels: no rain, light rain, moderate rain, and heavy rain, and the rainfall in a set time period is used as a unit for quantification, thereby completing the quantification process of the rainfall factors; Based on the fog factor, quantification is performed with visibility as the bit, thereby completing the quantification process of the fog factor.

4. The method for constructing complex test scenarios for intelligent driving functions according to claim 1, characterized in that: The steps of constructing the weather test scenario include: The natural driving behavior characteristics under quantified natural weather factors are characterized by the headway time at the moment of vehicle braking, where the characterization expression is: THW=d / v In the formula, THW is the headway at the braking moment, d is the distance between the rear of the previous vehicle and the head of the vehicle at the braking moment, that is, the relative vehicle distance, and v is the speed of the vehicle; Under different quantified natural weather factors, combined with the median of the headway time, an impact index of the natural weather factor is constructed, wherein the impact index of the natural weather factor includes a light impact index, a rainfall impact index and a fog impact index; Based on the influencing index of the natural weather factors, the weather complexity is constructed as a weather test scenario. The weather complexity is expressed as: f weat h er =θ light *i rain *i fog In the formula, f weather is the weather complexity parameter, θ light is the illumination impact index value, θ rain is the rainfall impact index value, θ fog It is the fog impact index.

5. The method for constructing complex test scenarios for intelligent driving functions according to claim 1, characterized in that: The driving behavior interaction characteristic parameters include encounter angle, relative distance and relative speed.

6. The method for constructing complex test scenarios for intelligent driving functions according to claim 5, characterized in that: The steps of constructing the traffic test scenario include: According to the relationship between the encounter angle and traffic complexity, combined with the minimum safety distance method, the encounter angle complexity is calculated, wherein the calculation expression of the encounter angle complexity is: In the formula, f angle is the encounter angle complexity, θ i is the encounter angle between the test vehicle and the target vehicle i; According to the relationship between the relative distance and traffic complexity, combined with the information entropy theory method, the relative distance complexity is calculated, wherein the calculation expression of the relative distance complexity is: In the formula, f distance is the relative distance complexity, d ij is the relative distance between the test vehicle and the target vehicle i, d max is the maximum relative distance between the test vehicle and the target vehicle; According to the principle that the greater the relative speed, the more dangerous it is, combined with the information entropy theory method, the relative speed complexity is calculated, where the calculation expression of the relative speed complexity is: In the formula, f velocity is the relative speed complexity, v i is the relative speed between the test vehicle and the target vehicle i, v max is the maximum relative speed between the test vehicle and the target vehicle; Based on the encounter angle complexity, relative distance complexity and relative speed complexity, traffic complexity is constructed as a traffic test scenario, wherein the traffic complexity is expressed as: In the formula, The traffic complexity.

7. The method for constructing complex test scenarios for intelligent driving functions according to claim 6, characterized in that: The maximum relative distance d between the test vehicle and the target vehicle max The calculation process includes: Based on the headway distribution characteristics of the vehicle braking moment of dangerous driving behaviors and normal driving behaviors in natural driving data, the support vector machine method is used to fit the boundary curve representing vehicle safety, where the boundary curve of vehicle safety is expressed as: In the formula, THW is the headway time at the braking moment, indicating vehicle safety, and v is the vehicle speed; Based on the vehicle safety boundary curve and the test vehicle speed, the maximum relative distance d between the test vehicle and the target vehicle is obtained. max , where the maximum relative distance d max The calculation expression is: In the formula, v host Indicates the test vehicle speed.

8. The method for constructing complex test scenarios for intelligent driving functions according to claim 6, characterized in that: The maximum relative speed v between the test vehicle and the target vehicle max The calculation process includes: According to the distance-to-collision time at the moment of vehicle braking, the boundary curve between non-collision conditions and collision conditions in natural driving dangerous conditions is constructed by combining the support vector machine method and the K-fold intersection verification method, wherein the calculation expression of the distance-to-collision time is: TTC=d / (v host -v target ) Where TTC is the distance to collision time at the moment of vehicle braking, d represents the distance between the rear of the preceding vehicle and the head of the vehicle at the moment of braking, i.e., the relative vehicle distance; v host Indicates the vehicle speed; v target Indicates the target vehicle speed; Based on the boundary curve between the non-collision condition and the collision condition, the test vehicle speed, 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 , where the maximum relative speed v max The calculation expression is: In the formula, v host Indicates the test vehicle speed.

9. An electronic device, characterized in that: include: one or more processors; Memory; and One or more programs stored in a memory, wherein the one or more programs include instructions for executing the method for constructing a complex test scenario for an intelligent driving function as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: It includes one or more programs for execution by one or more processors of an electronic device, and the one or more programs include instructions for executing the method for constructing complex test scenarios for intelligent driving functions as described in any one of claims 1-8.

Images