A method and device for automatically detecting road surface unevenness of OpenDRIVE

Abstract

The present invention provides a method and device for automatically detecting road surface unevenness of OpenDRIVE. The method includes: reading road information in OpenDRIVE data; determining an automatic detection scheme for the road surface based on the slope of the road reference line; wherein the automatic detection scheme for the road surface includes a concave surface detection scheme and a convex surface detection scheme; and automatically detecting the unevenness of the road surface through the concave surface detection scheme and the convex surface detection scheme respectively. The present invention can comprehensively detect the road surface unevenness caused by abnormal elevation in the OpenDRIVE map data, quickly locate the defect points of the data, avoid the situation of subsequent vehicle autonomous driving simulation failures, and meet the basic quality requirements of autonomous driving vehicles for high-precision maps.

Description

Technical Field

[0001] The present invention relates to the field of high-precision map data, and particularly to a method and device for automatically detecting road surface unevenness of OpenDRIVE. Background Art

[0002] OpenDRIVE is mainly applied to the production of high-precision map data. As the basis for in-vehicle reference and the testing and application of autonomous driving simulators, its main purpose is to provide a road network description that can be used for simulation.

[0003] The high-precision map simulation data serves autonomous driving technology. Autonomous vehicles can perform technical applications such as road simulation driving, path planning, vehicle obstacle recognition or positioning in a simulation scenario. Therefore, autonomous driving technology usually has certain quality requirements for high-precision map simulation data. For example, the road in the map data needs to be flat without wrinkles, the lane lines cannot be displayed in the middle of the road surface, the elevation of the road surface is normal, and there are no holes or gaps in the road surface. If there are quality defect problems in the road data, various abnormal problems will occur during the simulation driving process of the vehicle, and the normal simulation driving process cannot be carried out, affecting the feasibility of the autonomous driving solution. In view of the above description, before the vehicle simulation autonomous driving of the map data, high-precision map providers need to quickly detect the defects in the quality of high-precision map data and perform corresponding repairs.

[0004] Currently, to check the quality problems of OpenDRIVE road data, it can only be visually displayed through simulation software, that is, after importing the data into the simulation software, check whether there are unevenness on the road surface. Through simulation visualization detection, on the one hand, it will consume a lot of time in the case of a large data range, and on the other hand, it is limited by the professional technology of the testers to accurately discover road defects. If an automated detection tool can be used to first detect the road quality defect problems and solve the unevenness of the road surface before the simulation of vehicle driving, it can not only find data quality problems as comprehensively as possible without omission without being affected by personnel, but also reduce the input time of manual visual inspection, improve the test efficiency, and reduce a series of steps of data import and export.

[0005] In view of this, overcoming the defects of the existing technology is an urgent problem to be solved in this technical field. Summary of the Invention

[0006] The present invention provides a solution to the technical problems of long input time, low test efficiency, and the risk of missed detection and missed inspection existing in the current road surface unevenness detection scheme.

[0007] To solve the above technical problems, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for automatically detecting road surface unevenness of OpenDRIVE, including:

[0009] Reading road information in OpenDRIVE data;

[0010] Determining an automatic detection scheme for the road surface according to the slope of the road reference line; wherein, the automatic detection scheme for the road surface includes a concave surface detection scheme and a convex surface detection scheme;

[0011] Automatically detecting the unevenness of the road surface through the concave surface detection scheme and the convex surface detection scheme respectively.

[0012] Preferably, the determining of the automatic detection scheme for the road surface according to the slope of the road reference line includes:

[0013] Traversing all roads and sequentially selecting reference points from the road reference line;

[0014] Traversing all reference points and sequentially calculating the slopes of each reference point;

[0015] Traversing the slopes of all reference points and respectively calculating the relative change amounts of the slopes of each reference point within a preset road reference line length width;

[0016] Comparing the relative change amounts of the slopes of each reference point with a preset slope threshold respectively, and sequentially finding a trigger point and an end point through the comparison results.

[0017] Preferably, the sequentially finding a trigger point and an end point through the comparison results specifically includes:

[0018] When the relative change amount of the slope of each reference point is greater than or equal to the preset slope threshold, taking the midpoint of each reference point as the trigger point or the end point; wherein, the slope positive and negative situations of the trigger point and the end point are opposite.

[0019] Preferably, the concave surface detection scheme includes:

[0020] Presetting a road reference line length width1; wherein, width1 is greater than width;

[0021] Within any preset road reference line length width, if the slope of the trigger point is negative, the slope of the end point is positive, and the distance between the trigger point and the end point is less than width1, the concave surface detection is successful.

[0022] Preferably, the concave surface detection scheme specifically further includes:

[0023] If the distance between the trigger point and the end point is greater than or equal to width1, after canceling the trigger point, continue to find the next trigger point.

[0024] Preferably, the convex surface detection scheme specifically includes:

[0025] Preset the length width1 of the road reference line; where width1 is greater than width.

[0026] Within any preset road reference line length width, if the slope of the trigger point is positive, the slope of the end point is negative, and the distance between the trigger point and the end point is less than width1, the convex surface detection is successful.

[0027] Preferably, the convex surface detection scheme specifically further includes:

[0028] If the distance between the trigger point and the end point is greater than or equal to width1, after canceling the trigger point, continue to search for the next trigger point.

[0029] In a second aspect, the present invention provides a device for automatically detecting the unevenness of the road surface of OpenDRIVE, including:

[0030] At least one processor; and,

[0031] A memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor for performing the method for automatically detecting the unevenness of the road surface of OpenDRIVE as described in the first aspect.

[0032] Regarding the deficiencies in the prior art, the beneficial effects that the present invention can achieve are:

[0033] The present invention automatically detects the unevenness of the OpenDRIVE road surface, achieves the purpose of quickly detecting the unevenness of the road surface in the OpenDRIVE data, greatly reduces the test time for testers to visually check whether the road surface is uneven, improves the data detection coverage at the same time, avoids being missed in a certain area due to human objective factors, and to a certain extent speeds up the process of OpenDRIVE data testing and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0035] Figure 1 It is a schematic flowchart of a method for automatically detecting the unevenness of the road surface of OpenDRIVE;

[0036] Figure 2 is another schematic diagram of the method flow for automatic detection of road surface unevenness in OpenDRIVE;

[0037] Figure 3 is a schematic diagram of concave surface detection for the method of automatic detection of road surface unevenness in OpenDRIVE;

[0038] Figure 4 is Figure 3 a schematic diagram of the implementation process flow;

[0039] Figure 5 is a schematic diagram of convex surface application for the method of automatic detection of road surface unevenness in OpenDRIVE;

[0040] Figure 6 is Figure 5 a schematic diagram of the implementation process flow;

[0041] Figure 7 is a schematic diagram of the device structure for automatic detection of road surface unevenness in OpenDRIVE. Specific implementation manner

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. In addition, the technical features in each embodiment or a single embodiment provided by the present invention can be combined with each other arbitrarily to form a feasible technical solution. This combination is not restricted by the order of steps and / or the pattern of structural composition, but must be based on what can be achieved by those of ordinary skill in the art. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0043] Embodiment 1:

[0044] To solve the technical problems of long input time, low test efficiency, and the risk of missed detection and inspection existing in the current road surface unevenness detection scheme, Embodiment 1 of the present invention provides a method for automatic detection of road surface unevenness in OpenDRIVE, as Figure 1 shown, including:

[0045] Step 100, read the road information in the OpenDRIVE data.

[0046] Since OpenDRIVE data is written in XML format, in this step, the OpenDRIVE data is taken as input, and the input OpenDRIVE data is read through the readxml function in the C++ language to obtain the parsed map data. By traversing each Road tag in the OpenDRIVE data and obtaining the ID number of each road node, all the road information in the OpenDRIVE data can be obtained.

[0047] Step 200, determine the automated detection scheme for the road surface based on the slope of the road reference line; among them, the automated detection scheme for the road surface includes a concave surface detection scheme and a convex surface detection scheme.

[0048] In OpenDRIVE, the road reference line is a specific expression of the corresponding road (surface), and the road (surface) can be obtained by extending the road reference line. That is to say, to a certain extent, the change of the road reference line can reflect the change of the road (surface).

[0049] In this step, as one of the implementation methods, the automated detection scheme for the road surface determined based on the slope of the road reference line is as Figure 2 shown, and includes:

[0050] Step 201, traverse all roads and sequentially select reference points from the road reference line.

[0051] The sequential selection of reference points from the road reference line adopts an equal-spacing point-taking method, which can take points at equal intervals in a certain direction or along the arc of the road reference line. Preferably, it takes points at equal intervals in the parallel direction when the road surface is flat. In the actual implementation process, the equal interval can be reasonably adapted. For example, the equal interval is 0.2 meters, that is, a point is taken on the road reference line every 0.2 meters.

[0052] Step 202, traverse all reference points and sequentially calculate the slopes of each reference point.

[0053] Traverse the elevations of each point on each road reference line. The traversal process starts from the starting point of the road reference line. Due to the unevenness of the road surface, the corresponding road reference line will also fluctuate to varying degrees. During the sequential calculation of the slopes of each reference point, the slopes of each reference point are positive and negative. It should be noted that if the slope of a certain reference point is 0, it means that the tangent passing through this reference point coincides with or is parallel to the road surface.

[0054] Step 203, traverse the slopes of all reference points and calculate the relative change amount of the slopes of each reference point respectively within the preset road reference line length width.

[0055] For each road, there may be multiple uneven sections. In this step, by presetting the length width of the road reference line, each road can be detected section by section; in the actual implementation process, the preset length width of the road reference line can also be reasonably adapted. For example, the preset length width of the road reference line width is 4 meters, that is, within each 4-meter range, the relative change in the slope of each reference point is calculated respectively.

[0056] Combined with the above example where the reference points are equally spaced at 0.2 meters, it can be known that within a 4-meter range, there are a1, a2,..., a 19 , a 20 A total of 20 reference points, where a1 is the starting point within a 4-meter range, and a 20 Is the end point within the same 4-meter range. When calculating the relative change in the slope of each reference point, the slopes of every two reference points are subtracted once, and the absolute value of the difference is taken to obtain the relative change in the slope of each reference point; taking the reference point a1 as an example, the relative change in the slope of the reference point a1 is respectively |Ka1 - Ka2|, |Ka1 - Ka3|,..., |Ka1 - Ka 19 |, |Ka1 - Ka 20 |; taking the reference point a2 as an example, the relative change in the slope of the reference point a2 is respectively |Ka2 - Ka3|, |Ka2 - Ka4|,..., |Ka2 - Ka 19 |, |Ka2 - Ka 20 |. Calculate the relative change in the slope of other reference points in a similar manner and calculate successively backward to finally obtain the relative change in the slope of each reference point, where K represents the slope.

[0057] Step 204: Compare the relative change in the slope of each reference point with the preset slope threshold respectively, and find the trigger point and the end point successively based on the comparison results.

[0058] The comparison of the relative change in the slope of each reference point with the preset slope threshold respectively means comparing the above calculation results such as |Ka1 - Ka2|, |Ka1 - Ka3|,..., |Ka1 - Ka 19 |, |Ka1 - Ka 20 | and |Ka2 - Ka3|, |Ka2 - Ka4|,..., |Ka2 - Ka 19 |, |Ka2 - Ka 20 | with the preset slope threshold. In the actual implementation process, the preset slope threshold can also be reasonably adapted. For example, the preset slope threshold is 0.8, and based on the comparison results, the search strategies for the trigger point and the end point are determined.

[0059] Further, based on the comparison results, trigger points and end points are sequentially found, which specifically includes:

[0060] When the relative change in slope of each reference point is greater than or equal to a preset slope threshold, the midpoint of each reference point is taken as a trigger point or an end point; among them, the signs of the slopes of the trigger point and the end point are opposite.

[0061] For any concave surface or any convex surface, the slopes of its reference points have a process of gradual conversion between a series of positive values and a series of negative values. Among them, the process in which the slopes of the reference points gradually change from a series of negative values to a series of positive values corresponds to a concave surface (as Figure 3 shown. At this time, the trigger point is located in the negative value area, and the end point is located in the positive value area), and the process in which the slopes of the reference points gradually change from a series of positive values to a series of negative values corresponds to a convex surface (as Figure 5 shown. At this time, the trigger point is located in the positive value area, and the end point is located in the negative value area).

[0062] For the sake of easy understanding, any concave surface or any convex surface can be divided into two sets according to the signs of the slopes of the reference points on the reference line, including a positive set and a negative set.

[0063] As Figure 3 shown, it is a schematic diagram of concave surface detection for an automatic detection method of road surface unevenness of OpenDRIVE. For any concave surface, {Ka1, Ka2... Ka n-1 , Ka n} is the negative set, {Kb1, Kb2... Kb n-1 , Kb n} is the positive set. Assuming |Ka1 - Ka2| ≥ 0.8, the midpoint a between a1 and a2 is taken as the trigger point. Assuming |Kb1 - Kb2| ≥ 0.8, the midpoint b between b1 and b2 is taken as the end point. If the relative change in slope of each reference point is less than 0.8, there is no trigger point a and end point b. It can be understood that the relative change in slope of each reference point is small, that is, the road surface is relatively flat.

[0064] As Figure 5 shown, it is a schematic diagram of convex surface detection for an automatic detection method of road surface unevenness of OpenDRIVE. For any convex surface, {Ka1, Ka2... Ka n-1 , Ka n} is the positive set, {Kb1, Kb2... Kb n-1 , Kb n} is a negative set. Assume |Ka1 - Ka2| ≥ 0.8, then take the midpoint a between a1 and a2 as the trigger point. Assume |Kb1 - Kb2| ≥ 0.8, then take the midpoint b between b1 and b2 as the end point. If the relative change in slope of each reference point is less than 0.8, there is no trigger point a and end point b. It can be understood that the relative change in slope of each reference point is small, that is, the road surface is relatively flat.

[0065] Step 300, automatically detect the unevenness of the road surface through the concave surface detection scheme and the convex surface detection scheme respectively.

[0066] For the automatic detection process of any concave surface, the concave surface detection scheme includes:

[0067] Preset the road reference line length width1; where width1 is greater than width.

[0068] Similarly, by presetting the road reference line length width1, each road can be detected section by section, and the preset road reference line length width1 can also be reasonably adapted. For example, the preset road reference line length width1 is 20 meters, that is, within a range of 20 meters, detect whether there is a concave surface.

[0069] Within any preset road reference line length width, if the slope of the trigger point is negative, the slope of the end point is positive, and the distance between the trigger point and the end point is less than width1, the concave surface detection is successful.

[0070] In specific implementation, the concave surface detection scheme specifically further includes:

[0071] If the distance between the trigger point and the end point is greater than or equal to width1, after canceling the trigger point, continue to find the next trigger point.

[0072] If the distance between the trigger point and the end point is greater than or equal to width1, the system determines that the distance between the trigger point and the end point is relatively far and is not sufficient to form a concave surface that will affect the automatic driving process of the vehicle. Further, after canceling the trigger point, continue to find the next trigger point. In this way, it can be understood that if no trigger point is finally found, it means that there is no concave surface on this road.

[0073] In the actual implementation process, as one of the stricter methods, the distance between the starting point a1 of the trigger point a and the ending point b2 of the end point b can also be compared with the preset road reference line length width1.

[0074] As Figure 4 shown, it is Figure 3 the flow schematic diagram of the specific implementation process.

[0075] For the automated detection process of any convex surface, the convex surface detection scheme includes:

[0076] Preset the road reference line length width1; where width1 is greater than width.

[0077] By the preset road reference line length width1, each road can be detected section by section, and the preset road reference line length width1 can also be reasonably adapted. For example, the preset road reference line length width1 is 20 meters, that is, within 20 meters, it is detected whether there is a convex surface.

[0078] Within any preset road reference line length width range, if the slope of the trigger point is positive, the slope of the end point is negative, and the distance between the trigger point and the end point is less than width1, the convex surface detection is successful.

[0079] In specific implementation, the convex surface detection scheme specifically further includes:

[0080] If the distance between the trigger point and the end point is greater than or equal to width1, after canceling the trigger point, continue to find the next trigger point.

[0081] If the distance between the trigger point and the end point is greater than or equal to width1, the system determines that the distance between the trigger point and the end point is relatively far and is not sufficient to form a convex surface that will affect the automatic driving process of the vehicle. Further, after canceling the trigger point, continue to find the next trigger point. In the above way, it can be understood that if no trigger point is finally found, it means that there is no convex surface on this road.

[0082] In the actual implementation process, as one of the ways to tighten, the distance between the starting point a1 of the trigger point a and the ending point b2 of the end point b can also be compared with the preset road reference line length width1.

[0083] As Figure 6 shown, it is Figure 5 the flow schematic diagram of the specific implementation process.

[0084] Embodiment 2:

[0085] Based on the same overall technical solution as in Embodiment 1, as Figure 7As shown in the figure, it is a schematic structural diagram of a device for automatically detecting the unevenness of the road surface of OpenDRIVE provided in Embodiment 2 of the present invention, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor for performing the method for automatically detecting the unevenness of the road surface of OpenDRIVE as described in Embodiment 1.

[0086] In summary, the present invention provides a method and a device for automatically detecting the unevenness of the road surface of OpenDRIVE. By automatically detecting the unevenness of the road surface of OpenDRIVE, the purpose of quickly detecting the unevenness of the road surface in OpenDRIVE data is achieved, greatly reducing the test time for testers to visually check whether the road surface is uneven. At the same time, the data detection coverage is improved, avoiding missed detection and inspection of a certain area due to human objective factors, and accelerating the process of OpenDRIVE data testing and development to a certain extent.

[0087] It should be noted that in the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, an electronic device, or a computer software program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention 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-ROM, optical storage, etc.) containing computer-usable program code.

[0089] The present invention is described with reference to the flowcharts and / or block diagrams of methods, systems, electronic devices, or computer software program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a system for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0090] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system that implements the functions specified in the flowchart(s) Figure 1 a flowchart or flowcharts and / or block(s) Figure 1 a block or blocks specified in the block(s).

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart(s) Figure 1 a flowchart or flowcharts and / or block(s) Figure 1 a block or blocks specified in the block(s).

[0092] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

Claims

1. A method for automatically detecting road surface unevenness of OpenDRIVE, characterized in that, Including: Reading road information from OpenDRIVE data; Determining an automated detection scheme for the road surface based on the slope of the road reference line; wherein, the automated detection scheme for the road surface includes a concave surface detection scheme and a convex surface detection scheme; Automatically detecting the unevenness of the road surface through the concave surface detection scheme and the convex surface detection scheme respectively; The determining of the automated detection scheme for the road surface based on the slope of the road reference line includes: Traversing all roads and sequentially selecting reference points from the road reference line; Traversing all reference points and sequentially calculating the slopes of each reference point; Traversing the slopes of all reference points, within the preset road reference line length width, respectively calculating the relative change amount of the slope of each reference point; when calculating the relative change amount of the slope of each reference point, subtracting the slopes of every two reference points once and taking the absolute value of the result of the subtraction, that is, the relative change amount of the slope of each reference point can be obtained; Comparing the relative change amount of the slope of each reference point with the preset slope threshold respectively, and successively finding the trigger point and the end point on the road reference line through the comparison result; The successively finding the trigger point and the end point through the comparison result specifically includes: When the relative change amount of the slope of each reference point is greater than or equal to the preset slope threshold, taking the midpoint of the first pair of reference points whose relative change amount is greater than or equal to the preset slope threshold as the trigger point or the end point; wherein, the slope positive and negative situations of the trigger point and the end point are opposite.

2. The method for automatically detecting road surface unevenness of OpenDRIVE according to claim 1, characterized in that, The concave surface detection scheme includes: Presetting the road reference line length width1; wherein, width1 is greater than width; If the slope of the trigger point is negative, the slope of the end point is positive, and the distance between the trigger point and the end point is less than width1, then the concave surface detection is successful.

3. The method for automatically detecting road surface unevenness of OpenDRIVE according to claim 2, wherein, The concave surface detection scheme specifically further includes: If the distance between the trigger point and the end point is greater than or equal to width1, after canceling this trigger point, continue to find the next trigger point.

4. The method for automatically detecting road surface unevenness of OpenDRIVE according to claim 1, characterized in that The convex surface detection scheme specifically includes: Presetting the road reference line length width1; wherein, width1 is greater than width; If the slope of the trigger point is positive, the slope of the end point is negative, and the distance between the trigger point and the end point is less than width1, then the convex surface detection is successful.

5. The method for automatically detecting road surface unevenness of OpenDRIVE according to claim 4, characterized in that, The convex surface detection scheme specifically further includes: If the distance between the trigger point and the end point is greater than or equal to width1, after canceling this trigger point, continue to find the next trigger point.

6. An apparatus for automatically detecting road surface unevenness of OpenDRIVE, characterized in that, Including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor for performing the method for automatically detecting the unevenness of the road surface of OpenDRIVE as described in any one of claims 1 - 5.

Images