Vehicle compaction line degree assessment method, device, storage medium and computer equipment

Abstract

The vehicle compaction line degree evaluation method, device, storage medium and computer equipment provided in the present application can obtain the simulated autonomous driving vehicle in the simulation test data and the solid line segment of the area where the simulated autonomous driving vehicle is located when evaluating the compaction line degree of the autonomous driving vehicle during the simulation test process. Then, a coordinate system can be established according to the vehicle contour of the simulated autonomous driving vehicle, and the target coordinates of each sampling point in the solid line segment in the coordinate system can be determined, thereby forming a target coordinate set. Each target coordinate in the target coordinate set can be used to calculate the signed distance with the vehicle contour, and the signed distance can be used to realize the evaluation of the compaction line degree of the simulated autonomous driving vehicle during the simulation test, thereby effectively improving the accuracy of the simulation test.

Description

Technical Field

[0001] The present application relates to the field of simulation test technology, and in particular to a method, device, storage medium and computer equipment for evaluating the degree of compaction line of a vehicle. Background Art

[0002] Changing lanes across a solid line is one of the common problems of autonomous vehicles and one of the issues that need to be paid attention to in simulation testing. At present, the common method to determine whether a vehicle crosses a solid line in simulation testing is to abstract the solid line into a line segment or a curve segment in a two-dimensional plane and the vehicle into a rectangle to determine whether the two intersect. However, there will be the following problems in actual use:

[0003] like Figure 1 As shown, Figure 1 This is a page schematic diagram of the degree of intersection between the solid line and the vehicle outline provided in the embodiment of the present application. Figure 1 (a) The solid line in the middle does not intersect the vehicle outline, and the test is passed; Figure 1 (b) The solid line in the middle just intersects the vehicle outline at one point, and the test fails; Figure 1 The vehicle in (c) clearly crossed the solid line and failed the test. Figure 1 It can be seen that Figure 1 (a) and Figure 1 The compaction line behaviors of the vehicles in (b) are very similar, but the final test results are different. Figure 1 (c) Ratio Figure 1 The vehicle in (b) has a more serious line compaction behavior, but the test results do not allow us to tell the difference in the degree of line compaction between the two.

[0004] Therefore, it is urgent to design a method that can evaluate the degree of vehicle compaction line in order to improve the accuracy of simulation testing. Summary of the invention

[0005] The purpose of the present application is to solve at least one of the above-mentioned technical deficiencies, especially the technical defect that the prior art lacks a method for evaluating the degree of compaction line of a vehicle.

[0006] The present application provides a method for evaluating the degree of compaction line of a vehicle, the method comprising:

[0007] Acquire simulation test data, the simulation test data comprising a plurality of continuous image frames, the image frames comprising a simulated autonomous driving vehicle and a solid line segment of an area where the simulated autonomous driving vehicle is located;

[0008] Establishing a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determining the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set;

[0009] Determine a signed distance between each target coordinate in the target coordinate set and the vehicle contour, and evaluate the degree of compaction line of the simulated autonomous driving vehicle during the simulation test according to the signed distance.

[0010] Optionally, before determining the target coordinates of each sampling point in the solid line segment in the coordinate system, the method further includes:

[0011] The solid line segment is sampled according to a set sampling method to obtain a plurality of sampling points.

[0012] Optionally, establishing a coordinate system according to a vehicle profile of the simulated autonomous driving vehicle comprises:

[0013] determining a vehicle profile corresponding to the simulated autonomous driving vehicle;

[0014] Taking the center point of the vehicle contour as the coordinate origin, constructing a coordinate axis passing through the coordinate origin according to the contour edge of the vehicle contour;

[0015] A coordinate system is established based on the coordinate origin and the coordinate axes.

[0016] Optionally, determining the target coordinates of each sampling point in the solid line segment in the coordinate system includes:

[0017] Convert the coordinates of each sampling point in the solid line segment in the corresponding image frame to the original coordinates in the coordinate system;

[0018] The original coordinates are mapped to the first quadrant of the coordinate system to obtain target coordinates of the original coordinates in the first quadrant.

[0019] Optionally, evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the signed distance includes:

[0020] Selecting the minimum distance among the signed distances between each target coordinate and the vehicle contour as the target distance between the simulated autonomous driving vehicle and the solid line segment;

[0021] The degree of compaction of the simulated autonomous driving vehicle during the simulation test is evaluated according to the target distance.

[0022] Optionally, evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance includes:

[0023] Mapping the target distance to a target score within a set score interval;

[0024] The degree of compaction of the simulated autonomous driving vehicle during the simulation test is evaluated according to the target score.

[0025] Optionally, evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target score includes:

[0026] Comparing the target score with a preset compaction line degree threshold to obtain a comparison result;

[0027] The degree of compaction line of the simulated autonomous driving vehicle during the simulation test is determined according to the comparison result.

[0028] The present application also provides a vehicle compaction line degree assessment device, comprising:

[0029] A data acquisition module, used to acquire simulation test data, wherein the simulation test data includes a plurality of continuous image frames, wherein the image frames include a simulated autonomous driving vehicle and a solid line segment of an area where the simulated autonomous driving vehicle is located;

[0030] a coordinate determination module, configured to establish a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determine the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set;

[0031] A compaction line degree evaluation module is used to determine the signed distance between each target coordinate in the target coordinate set and the vehicle contour, and evaluate the compaction line degree of the simulated autonomous driving vehicle during the simulation test according to the signed distance.

[0032] The present application also provides a storage medium, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle compaction line degree assessment method as described in any of the above embodiments.

[0033] The present application also provides a computer device, comprising: one or more processors, and a memory;

[0034] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the vehicle compaction line degree assessment method as described in any one of the above embodiments are performed.

[0035] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0036] The vehicle compaction line degree evaluation method, device, storage medium and computer equipment provided in the present application can obtain the simulated autonomous driving vehicle in the simulation test data and the solid line segment of the area where the simulated autonomous driving vehicle is located when evaluating the compaction line degree of the autonomous driving vehicle during the simulation test process. Then, a coordinate system can be established according to the vehicle contour of the simulated autonomous driving vehicle, and the target coordinates of each sampling point in the solid line segment in the coordinate system can be determined, thereby forming a target coordinate set. Each target coordinate in the target coordinate set can be used to calculate the signed distance with the vehicle contour, and the signed distance can be used to realize the evaluation of the compaction line degree of the simulated autonomous driving vehicle during the simulation test, thereby effectively improving the accuracy of the simulation test. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A schematic diagram of a page showing the degree of intersection between a solid line and a vehicle outline provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a process flow of a method for evaluating the degree of compaction line of a vehicle provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of a coordinate system established according to a vehicle profile of a simulated autonomous driving vehicle provided in an embodiment of the present application;

[0041] Figure 4 A schematic diagram of the structure of a vehicle compaction line degree assessment device provided in an embodiment of the present application;

[0042] Figure 5 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] In one embodiment, Figure 2 As shown, Figure 2 A schematic flow chart of a method for evaluating the degree of compaction line of a vehicle provided in an embodiment of the present application; the present application provides a method for evaluating the degree of compaction line of a vehicle, the method may include:

[0045] S110: Acquire simulation test data.

[0046] In this step, when evaluating the degree of compaction of the autonomous driving vehicle, simulation test data can be obtained from the simulation test platform. The simulation test data can include multiple continuous image frames, and the image frames can include a simulated autonomous driving vehicle and a solid line segment of the area where the simulated autonomous driving vehicle is located.

[0047] It is understandable that some vehicle information and road condition information are generally collected during the road test of the autonomous driving vehicle, such as the real-time position and speed of the autonomous driving vehicle, whether there are obstacles on the road surface on which the autonomous driving vehicle is traveling, how the autonomous driving vehicle avoids obstacles when there are obstacles, and whether there are any behaviors that violate traffic rules during the avoidance process, such as solid line behavior, etc. The solid lines here can include the edge line of the road, the solid line of the lane boundary, the solid center line, the stop line, etc. In order to judge the solid line behavior of the autonomous driving vehicle and effectively manage the driving behavior of the autonomous driving vehicle based on the judgment results, the collected vehicle information and the road condition information of the road section can usually be input into the pre-built simulation test platform, and the autonomous driving vehicle can be simulated and tested through the simulation test platform, and the autonomous driving vehicle can be improved based on the simulation test results, thereby improving the driving ability of the autonomous driving vehicle.

[0048] The simulation test platform in the present application may include a simulator, which can receive vehicle information and road condition information collected by the autonomous driving vehicle during the road test, and perform simulation tests based on the collected information. In addition, the simulation test platform may also include a display, which can be used to display the simulation test process and simulation test results of the autonomous driving vehicle.

[0049] When evaluating the degree of compaction line of an autonomous driving vehicle, a simulation test result can be obtained from a simulation test platform. The simulation test result includes multiple continuous image frames. The present application can filter out multiple image frames that include a simulated autonomous driving vehicle in the simulation test process, and image frames of solid line segments in the area where the simulated autonomous driving vehicle is located, so as to evaluate the degree of compaction line of the simulated autonomous driving vehicle in the corresponding image frames.

[0050] Among them, the solid line segment of the area where the simulated autonomous driving vehicle is located can be a solid line segment contained in the road surface within a radius of 20 meters with the center of the rear axle of the autonomous driving vehicle as the center in actual road conditions. The specific setting can be based on actual conditions and is not restricted here.

[0051] S120: Establishing a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determining the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set.

[0052] In this step, after obtaining the simulation test data through S110, a coordinate system can be established according to the vehicle contour of the simulated autonomous driving vehicle in the simulation test data, and the target coordinates of each sampling point in the solid line segment of the area where the simulated autonomous driving vehicle is located in the coordinate system can be determined, thereby obtaining a target coordinate set.

[0053] Among them, the vehicle contour of the simulated autonomous driving vehicle can be obtained by calculating the vehicle positioning position (rear axle center coordinates) provided by the on-vehicle positioning module and the vehicle contour model data stored in the system. The present application can regard the vehicle contour of the simulated autonomous driving vehicle as a rectangle, and establish a coordinate system based on the four sides of the rectangle. Then, the solid line segments of the area where the simulated autonomous driving vehicle is located are sampled, and the target coordinates of each sampling point in the coordinate system are determined to obtain a target coordinate set.

[0054] S130: Determine the signed distance between each target coordinate in the target coordinate set and the vehicle contour, and evaluate the degree of compaction line of the simulated autonomous driving vehicle during the simulation test according to the signed distance.

[0055] In this step, after obtaining the target coordinate set through S120, the signed distance between each target coordinate in the target coordinate set and the vehicle contour can be determined, and the degree of compaction line of the simulated autonomous driving vehicle during the simulation test can be evaluated based on the signed distance.

[0056] Specifically, when evaluating the degree of compaction of a simulated autonomous driving vehicle during a simulation test, the present application mainly utilizes the concept of a signed distance field to calculate the signed distance from each sampling point in a solid line segment in 2D space to the vehicle contour, and uses the signed distance to characterize the degree of intersection between the vehicle contour and the solid line, thereby quantitatively evaluating the degree of compaction of the simulated autonomous driving vehicle.

[0057] It should be noted that the signed distance function (SDF) used in the signed distance in this application can also be called an oriented distance function. This function is used to determine the distance from a point to the boundary of a region in a finite area in space and define the sign of the distance at the same time. For example, the point is positive inside the region boundary, negative outside, and 0 when it is on the boundary.

[0058] Furthermore, after applying the signed distance function to the present application, if the target coordinates corresponding to a certain sampling point are outside the vehicle contour, it means that its signed distance is positive; if the target coordinates corresponding to a certain sampling point are inside the vehicle contour, it means that its signed distance is negative; if the target coordinates corresponding to a certain sampling point are on the vehicle contour, it means that its signed distance is 0.

[0059] Then, the present application can quantify the degree of intersection between the vehicle contour and the solid line according to the signed distance between each target coordinate and the vehicle contour, thereby realizing the evaluation of the degree of compaction of the simulated autonomous driving vehicle. For example, the present application can convert the signed distance between each target coordinate and the vehicle contour into a score within a certain interval, and predetermine the degree of intersection between the vehicle contour and the solid line represented by each score, so as to more intuitively judge the severity of the compaction behavior of the simulated autonomous driving vehicle.

[0060] In the above embodiment, when evaluating the degree of compaction of the autonomous driving vehicle during the simulation test, the simulated autonomous driving vehicle in the simulation test data and the solid line segment of the area where the simulated autonomous driving vehicle is located can be obtained, and then a coordinate system can be established according to the vehicle contour of the simulated autonomous driving vehicle, and the target coordinates of each sampling point in the solid line segment in the coordinate system can be determined, thereby forming a target coordinate set. Each target coordinate in the target coordinate set can be used to calculate the signed distance with the vehicle contour, and the signed distance can be used to realize the evaluation of the degree of compaction of the simulated autonomous driving vehicle during the simulation test, thereby effectively improving the accuracy of the simulation test.

[0061] In one embodiment, before determining the target coordinates of each sampling point in the solid line segment in the coordinate system in S120, the method may further include: sampling the solid line segment according to a set sampling method to obtain a plurality of sampling points.

[0062] In this embodiment, before determining the target coordinates of each sampling point in the solid line segment in the coordinate system, the solid line segment may be sampled according to a set sampling method to obtain a plurality of sampling points.

[0063] For example, the present application may perform dense and uniform sampling on solid line segments, or may perform segmented sampling on solid line segments. Of course, in order to approximately calculate the minimum value of the signed distance of all points on the solid line segments, the denser the sampling, the more accurate the approximation.

[0064] In one embodiment, establishing a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle in S120 may include:

[0065] S121: Determine a vehicle profile corresponding to the simulated autonomous driving vehicle.

[0066] S122: Taking the center point of the vehicle contour as the coordinate origin, constructing a coordinate axis passing through the coordinate origin according to the contour edge of the vehicle contour.

[0067] S123: Establishing a coordinate system based on the coordinate origin and the coordinate axes.

[0068] In this embodiment, when establishing a coordinate system based on the vehicle contour of the simulated autonomous driving vehicle, the vehicle contour corresponding to the current simulated autonomous driving vehicle can be obtained based on the vehicle positioning position (rear axle center coordinates) provided by the on-board positioning module and the vehicle contour model data stored in the system. The vehicle contour can usually be regarded as a rectangle, and the center point of the rectangle is used as the coordinate origin, and the axes that are perpendicular or parallel to the sides of the rectangle and pass through the coordinate origin are used as the x-axis and y-axis to establish a plane rectangular coordinate system.

[0069] Indicatively, if Figure 3 As shown, Figure 3 A schematic diagram of a structure of a coordinate system established according to a vehicle profile of a simulated autonomous driving vehicle provided in an embodiment of the present application; wherein the vehicle profile of the simulated autonomous driving vehicle is Figure 3 A coordinate system is constructed by taking the center point of the rectangle as the coordinate origin, the axis parallel to the left and right sides of the rectangle and passing through the coordinate origin as the Y axis, and the axis parallel to the upper and lower sides of the rectangle and passing through the coordinate origin as the X axis, so as to more accurately reflect the degree of intersection between the vehicle contour and the solid line segment.

[0070] In one embodiment, determining the target coordinates of each sampling point in the solid line segment in the coordinate system in S120 may include:

[0071] S210: Convert the coordinates of each sampling point in the solid line segment in the corresponding image frame to original coordinates in the coordinate system.

[0072] S220: Map the original coordinates to the first quadrant of the coordinate system to obtain target coordinates of the original coordinates in the first quadrant.

[0073] In this embodiment, when determining the target coordinates of each sampling point in the solid line segment in the coordinate system, the coordinates of each sampling point in the solid line segment in the corresponding image frame can be determined first, and then the coordinates in the image frame are converted to the original coordinates of the sampling point in the coordinate system, and then the original coordinates are mapped to the first quadrant of the coordinate system, thereby obtaining the target coordinates of the original coordinates in the first quadrant.

[0074] Indicatively, if Figure 3As shown, in the coordinate system, the vertex coordinates of the upper right corner of the rectangle can be taken as B (xb, yb) to ensure that point B is in the first quadrant, that is, x>0 and y>0. Then the original coordinates to be calculated can be converted to the coordinate system to obtain P1 origin, and then the P1 origin is mapped to the first quadrant to obtain P1. Since P1 is symmetrical with P1 origin, the signed distance from point P1 to the rectangle is consistent with the signed distance from point P1 origin to the rectangle. Figure 3 Point P2 in is also obtained through the above process.

[0075] In one embodiment, evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the signed distance in S130 may include:

[0076] S131: Select the minimum distance among the signed distances between each target coordinate and the vehicle contour as the target distance between the simulated autonomous driving vehicle and the solid line segment.

[0077] S132: Evaluate the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance.

[0078] In this embodiment, when evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test, the signed distance between each target coordinate and the vehicle contour can be determined first, and then the distance with the smallest signed distance is selected as the target distance between the simulated autonomous driving vehicle and the solid line segment, and the degree of compaction of the simulated autonomous driving vehicle during the simulation test is evaluated based on the target distance.

[0079] Among them, when determining the signed distance between the target coordinates and the vehicle contour, such as Figure 3 As shown, the vector between point P and point B can be calculated, and the signed distance between the target coordinates and the vehicle contour can be determined based on whether point P is within the rectangle. For example, the vector between point P and point B is D(xd, yd). If point P is within the rectangle, its signed distance is max(xd, yd); if point P is outside the rectangle, its signed distance is norm(D) = sqrt(max(xd, 0)^2+max(yd, 0)^2).

[0080] After calculating the signed distances between each target coordinate and the vehicle contour, the distance with the smallest signed distance can be selected as the target distance between the simulated autonomous driving vehicle and the solid line segment, and the degree of solid line compaction of the simulated autonomous driving vehicle during the simulation test can be evaluated based on the target distance.

[0081] In one embodiment, evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance in S132 may include:

[0082] S1321: Map the target distance to a target score within a set score range.

[0083] S1322: Evaluate the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target score.

[0084] In this embodiment, after the target distance between the simulated autonomous driving vehicle and the solid line segment is obtained, the target distance can be mapped to a target score within a set score range, and the degree of solid line compression of the simulated autonomous driving vehicle can be evaluated based on the target score.

[0085] For example, after obtaining the target distance d between the simulated autonomous driving vehicle and the solid line segment, the target distance d can be standardized to a score between 0 and 1. The score reflects the behavior of the simulated autonomous driving vehicle in compacting the solid line during the simulation test. The lower the score is, the more serious the compacting behavior is. For example, if d>0, the final score can be set to 1; if d<=0, according to the theoretical minimum value dmin of the signed distance of the rectangle, a linear mapping of [dmin, 0]->[0, 1] is established, and d is mapped to obtain the final score.

[0086] It is understandable that different vehicle models may have different dmin, and therefore different mapping relationships may be established according to different vehicle models. Assuming dmin=-2, the final score mapping relationship may be f(d)=d / 2+1.

[0087] In one embodiment, S1322 evaluates the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target score, which may include:

[0088] S3221: Compare the target score with a preset compaction line degree threshold to obtain a comparison result.

[0089] S3222: Determine the degree of compaction line of the simulated autonomous driving vehicle during the simulation test according to the comparison result.

[0090] In this embodiment, after obtaining the target score between the simulated autonomous driving vehicle and the solid line segment, the target score can be compared with a preset compaction line degree threshold, and the compaction line degree of the simulated autonomous driving vehicle during the simulation test can be determined based on the comparison result.

[0091] For example, the present application may set multiple compaction line degree thresholds, such as when the compaction line degree is severe, the corresponding compaction line degree threshold may be less than or equal to 0.2, when the compaction line degree is normal, the corresponding compaction line degree threshold may be greater than 0.2 and less than or equal to 0.5, and when the compaction line degree is light, the corresponding compaction line degree threshold may be greater than 0.5. After obtaining the target score between the simulated autonomous driving vehicle and the solid line segment, the target score may be compared with the preset compaction line degree threshold to determine the compaction line degree of the simulated autonomous driving vehicle during the simulation test.

[0092] It is understandable that the compaction line degree threshold value listed in the present application is only one example, and the specific value can be adjusted according to the actual situation and is not limited here.

[0093] The following is a description of a vehicle compaction line degree assessment device provided in an embodiment of the present application. The vehicle compaction line degree assessment device described below and the vehicle compaction line degree assessment method described above can be referenced to each other.

[0094] In one embodiment, Figure 4 As shown, Figure 4 A schematic diagram of the structure of a vehicle compaction line degree assessment device provided in an embodiment of the present application; the present application also provides a vehicle compaction line degree assessment device, which may include a data acquisition module 210, a coordinate determination module 220, and a compaction line degree assessment module 230, specifically including the following:

[0095] The data acquisition module 210 is used to acquire simulation test data, wherein the simulation test data includes a plurality of continuous image frames, each image frame including a simulated autonomous driving vehicle and a solid line segment of an area where the simulated autonomous driving vehicle is located.

[0096] The coordinate determination module 220 is used to establish a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determine the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set.

[0097] The compaction line degree evaluation module 230 is used to determine the signed distance between each target coordinate in the target coordinate set and the vehicle contour, and evaluate the compaction line degree of the simulated autonomous driving vehicle during the simulation test according to the signed distance.

[0098] In the above embodiment, when evaluating the degree of compaction of the autonomous driving vehicle during the simulation test, the simulated autonomous driving vehicle in the simulation test data and the solid line segment of the area where the simulated autonomous driving vehicle is located can be obtained, and then a coordinate system can be established according to the vehicle contour of the simulated autonomous driving vehicle, and the target coordinates of each sampling point in the solid line segment in the coordinate system can be determined, thereby forming a target coordinate set. Each target coordinate in the target coordinate set can be used to calculate the signed distance with the vehicle contour, and the signed distance can be used to realize the evaluation of the degree of compaction of the simulated autonomous driving vehicle during the simulation test, thereby effectively improving the accuracy of the simulation test.

[0099] In one embodiment, the device may further include:

[0100] The sampling module is used to sample the solid line segment according to a set sampling method to obtain multiple sampling points.

[0101] In one embodiment, the coordinate determination module 220 may include:

[0102] The vehicle profile determination module is used to determine a vehicle profile corresponding to the simulated autonomous driving vehicle.

[0103] The first construction module is used to take the center point of the vehicle contour as the coordinate origin and construct a coordinate axis passing through the coordinate origin according to the contour edge of the vehicle contour.

[0104] The second building module is used to establish a coordinate system based on the coordinate origin and the coordinate axis.

[0105] In one embodiment, the coordinate determination module 220 may include:

[0106] The original coordinate determination module is used to convert the coordinates of each sampling point in the solid line segment in the corresponding image frame into the original coordinates in the coordinate system.

[0107] The target coordinate determination module is used to map the original coordinates to the first quadrant of the coordinate system to obtain the target coordinates of the original coordinates in the first quadrant.

[0108] In one embodiment, the compaction line degree assessment module 230 may include:

[0109] The target distance determination module is used to select the minimum distance among the signed distances between each target coordinate and the vehicle contour as the target distance between the simulated autonomous driving vehicle and the solid line segment.

[0110] The degree assessment module is used to assess the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance.

[0111] In one embodiment, the degree assessment module may include:

[0112] The target score determination module is used to map the target distance to a target score within a set score interval.

[0113] The degree assessment submodule is used to assess the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target score.

[0114] In one embodiment, the degree assessment submodule may include:

[0115] The comparison module is used to compare the target score with a preset compaction line degree threshold to obtain a comparison result.

[0116] An evaluation module is used to determine the degree of compaction line of the simulated autonomous driving vehicle during the simulation test according to the comparison result.

[0117] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle compaction line degree assessment method as described in any of the above embodiments.

[0118] In one embodiment, the present application also provides a computer device, including: one or more processors, and a memory.

[0119] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the vehicle compaction line degree assessment method as described in any one of the above embodiments are performed.

[0120] Indicatively, if Figure 5 As shown, Figure 5 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 may be provided as a server. Figure 5 The computer device 300 includes a processing component 302, which further includes one or more processors, and a memory resource represented by a memory 301 for storing instructions executable by the processing component 302, such as an application. The application stored in the memory 301 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the vehicle compaction line degree assessment method of any of the above embodiments.

[0121] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0122] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0124] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0125] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating the degree of compaction line of a vehicle, characterized in that: The method comprises: Acquire simulation test data, wherein the simulation test data includes a plurality of continuous image frames, wherein the image frames include a simulated autonomous driving vehicle and a solid line segment of an area where the simulated autonomous driving vehicle is located; Establishing a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determining the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set; determining a signed distance between each target coordinate in the target coordinate set and the vehicle profile, and evaluating a degree of compaction of the simulated autonomous driving vehicle during a simulation test according to the signed distance; The step of evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the signed distance includes: Selecting the minimum distance among the signed distances between each target coordinate and the vehicle contour as the target distance between the simulated autonomous driving vehicle and the solid line segment; The degree of compaction of the simulated autonomous driving vehicle during the simulation test is evaluated according to the target distance.

2. The method according to claim 1, characterized in that Before determining the target coordinates of each sampling point in the solid line segment in the coordinate system, the method further includes: The solid line segment is sampled according to a set sampling method to obtain a plurality of sampling points.

3. The method according to claim 1, characterized in that The establishing of a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle comprises: determining a vehicle profile corresponding to the simulated autonomous driving vehicle; Taking the center point of the vehicle contour as the coordinate origin, constructing a coordinate axis passing through the coordinate origin according to the contour edge of the vehicle contour; A coordinate system is established based on the coordinate origin and the coordinate axes.

4. The method according to claim 3, characterized in that The step of determining the target coordinates of each sampling point in the solid line segment in the coordinate system comprises: Convert the coordinates of each sampling point in the solid line segment in the corresponding image frame to the original coordinates in the coordinate system; The original coordinates are mapped to the first quadrant of the coordinate system to obtain target coordinates of the original coordinates in the first quadrant.

5. The method according to claim 1, characterized in that The step of evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance includes: Mapping the target distance to a target score within a set score interval; The degree of compaction of the simulated autonomous driving vehicle during the simulation test is evaluated according to the target score.

6. The method according to claim 5, characterized in that The step of evaluating the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target score includes: Comparing the target score with a preset compaction line degree threshold to obtain a comparison result; The degree of compaction line of the simulated autonomous driving vehicle during the simulation test is determined according to the comparison result.

7. A vehicle compaction line degree assessment device, characterized in that: include: A data acquisition module, used to acquire simulation test data, wherein the simulation test data includes a plurality of continuous image frames, wherein the image frames include a simulated autonomous driving vehicle and a solid line segment of an area where the simulated autonomous driving vehicle is located; a coordinate determination module, configured to establish a coordinate system according to the vehicle profile of the simulated autonomous driving vehicle, and determine the target coordinates of each sampling point in the solid line segment in the coordinate system to obtain a target coordinate set; a compaction line degree evaluation module, configured to determine a signed distance between each target coordinate in the target coordinate set and the vehicle contour, and to evaluate a compaction line degree of the simulated autonomous driving vehicle during a simulation test according to the signed distance; The compaction line degree evaluation module evaluates the compaction line degree of the simulated autonomous driving vehicle during the simulation test according to the signed distance, including: a target distance determination module, configured to select the minimum distance among the signed distances between each target coordinate and the vehicle contour as the target distance between the simulated autonomous driving vehicle and the solid line segment; The degree assessment module is used to assess the degree of compaction of the simulated autonomous driving vehicle during the simulation test according to the target distance.

8. A storage medium, characterized in that: The storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the vehicle compaction line degree assessment method as described in any one of claims 1 to 6.

9. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the vehicle compaction line degree assessment method as described in any one of claims 1 to 6 are performed.

Images