Lane line fitting smoothing method, system and device and storage medium

Abstract

The invention discloses a lane line fitting smoothing method, system and device and a storage medium. The method comprises the steps that multiple pieces of geometry node information in a planView field corresponding to a target road ID are read from a simulation high-precision map opendrive file; determining a plurality of simulation lane line coordinate points and a plurality of simulation yaw angles corresponding to the target road ID according to the plurality of pieces of geometer node information; processing the plurality of simulated lane line coordinate points and the plurality of simulated yaw angles through a fitting function to obtain a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles; and realizing lane line fitting smoothness corresponding to the target road ID according to the plurality of lane line fitting coordinate points and the plurality of fitting yaw angles. According to the method, the purpose of smoothing the coordinate points of the lane lines of the high-precision map is achieved through the fitting function, and the problem of snakelike vehicles in the automatic driving simulation test process is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving simulation, and particularly to a lane line fitting and smoothing method, system, device, and storage medium. Background Technique

[0002] With the development of autonomous driving technology, there are more and more tests for autonomous vehicles. Autonomous driving simulation is an extremely important part of this process. It converts a large amount of development and test costs of autonomous vehicles into computer simulation development and testing, saving a large amount of time, labor, and material costs.

[0003] Autonomous driving simulation is carried out based on simulation software. Currently, autonomous driving simulation tests are based on simulation high-precision maps, which are drawn by mapping companies through road surveys. Generally, simulation high-precision maps are in the opendrive format. Currently, the simulation high-precision maps provided by mapping companies are not smoothed, and there is generally a problem that the road coordinate points are not smooth, which will cause the autonomous vehicle to snake severely during the autonomous driving simulation test, affecting the effect of the simulation test. Therefore, how to avoid vehicle snake shape during autonomous driving simulation tests has become an urgent problem to be solved.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a lane line fitting and smoothing method, system, device, and storage medium, aiming to solve the technical problem of how to avoid vehicle snake shape during autonomous driving simulation tests.

[0006] To achieve the above object, the present invention provides a lane line fitting and smoothing method, which includes:

[0007] Determine the target road ID under the road field according to the opendrive file of the simulation high-precision map;

[0008] Read multiple geometry node information in the planView field corresponding to the target road ID from the opendrive file of the simulation high-precision map;

[0009] Determine multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID according to the multiple geometry node information;

[0010] Process the multiple simulation lane line coordinate points and multiple simulation yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles;

[0011] Implement the lane line fitting smoothing corresponding to the target road ID based on multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0012] Optionally, the step of respectively reading multiple geometry node information in the planView field corresponding to the target road ID from the simulation high-precision map opendrive file includes:

[0013] Perform format conversion on the simulation high-precision map opendrive file to obtain a dictionary simulation map file;

[0014] Read multiple geometry node information in the planView field corresponding to the target road ID under the road field from the dictionary simulation map file.

[0015] Optionally, the step of processing multiple simulation lane line coordinate points and multiple simulation yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles includes:

[0016] Determine the fitting function through the polyfit method and polyld method in the matplotlib library in python;

[0017] Obtain the fitting equation coefficients according to multiple simulation lane line coordinate points through the fitting function;

[0018] Based on the fitting equation coefficients, process multiple simulation lane line coordinate points and multiple simulation yaw angles respectively through the fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0019] Optionally, the step of processing multiple simulation yaw angles through the fitting function based on the fitting equation coefficients to obtain multiple fitting yaw angles includes:

[0020] Derive the fitting function based on the fitting equation coefficients according to multiple lane line fitting coordinate points to obtain the coordinate slope values corresponding to each lane line fitting coordinate point;

[0021] Obtain the fitting yaw angles corresponding to each simulation yaw angle respectively through the yaw angle formula according to the coordinate slope values corresponding to each lane line fitting coordinate point.

[0022] Optionally, the step of implementing the lane line fitting smoothing corresponding to the target road ID based on multiple lane line fitting coordinate points and multiple fitting yaw angles includes:

[0023] Update multiple geometry node information corresponding to the target road ID in the dictionary simulation map file according to multiple lane line fitting coordinate points and multiple fitting yaw angles to obtain an updated dictionary simulation map file;

[0024] Convert the format of the updated dictionary simulation map file to obtain an updated opendrive file;

[0025] Based on the updated opendrive file, smooth the lane line fitting corresponding to the target road ID.

[0026] Optionally, after the step of smoothing the lane line fitting corresponding to the target road ID based on the updated opendrive file, the method further includes:

[0027] Based on the updated opendrive file, determine the left distance signal curve and the right distance signal curve corresponding to the test vehicle and the left and right lane lines respectively;

[0028] Determine the offset distance between the test vehicle and the road center line according to the left distance signal curve and the right distance signal curve;

[0029] When the offset distance is greater than a preset threshold, process multiple lane line fitting coordinate points and multiple fitting yaw angles through the fitting function.

[0030] In addition, to achieve the above object, the present invention also proposes a lane line fitting smoothing system, the lane line fitting smoothing system includes:

[0031] A determination module, configured to determine a target road ID under the road field according to the simulation high-precision map opendrive file;

[0032] A reading module, configured to respectively read multiple geometry node information in the planView field corresponding to the target road ID from the simulation high-precision map opendrive file;

[0033] The determination module is further configured to determine multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID according to the multiple geometry node information;

[0034] A calculation module, configured to process multiple simulation lane line coordinate points and multiple simulation yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles;

[0035] A fitting module, configured to smooth the lane line fitting corresponding to the target road ID according to multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0036] In addition, to achieve the above object, the present invention also provides a lane line fitting and smoothing device, which includes: a memory, a processor, and a lane line fitting and smoothing program stored on the memory and executable on the processor. The lane line fitting and smoothing program is configured to implement the steps of the lane line fitting and smoothing method as described above.

[0037] In addition, to achieve the above object, the present invention also provides a storage medium with a lane line fitting and smoothing program stored thereon. When the lane line fitting and smoothing program is executed by a processor, it implements the steps of the lane line fitting and smoothing method as described above.

[0038] The present invention first determines the target road ID under the road field according to the simulation high-precision map opendrive file, and reads the information of multiple geometry nodes in the planView field corresponding to the target road ID from the simulation high-precision map opendrive file. Then, according to the information of multiple geometry nodes, it determines multiple simulated lane line coordinate points and multiple simulated yaw angles corresponding to the target road ID. After that, it processes the multiple simulated lane line coordinate points and multiple simulated yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles. Finally, it realizes the lane line fitting and smoothing of the target road ID according to the multiple lane line fitting coordinate points and multiple fitting yaw angles. Compared with the prior art where the simulation high-precision map is not smoothed, there is generally a problem of uneven road coordinate points, resulting in serious serpentine movement of the autonomous driving vehicle during the autonomous driving simulation test, which affects the effect of the simulation test. In the present invention, the multiple simulated lane line coordinate points and multiple simulated yaw angles are subjected to fitting and smoothing processing through a fitting function, and this information is updated to the simulation high-precision map opendrive file, thus solving the problem of vehicle serpentine movement during the autonomous driving simulation test. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a schematic structural diagram of a lane line fitting and smoothing device in the hardware operating environment related to the embodiment of the present invention;

[0040] Figure 2 is a schematic flowchart of the first embodiment of the lane line fitting and smoothing method of the present invention;

[0041] Figure 3 is a curve graph of lane line coordinate points without smoothing processing in the first embodiment of the lane line fitting and smoothing method of the present invention;

[0042] Figure 4 is a curve graph of lane line coordinate point fitting in the first embodiment of the lane line fitting and smoothing method of the present invention;

[0043] Figure 5 This is a structural block diagram of the first embodiment of the lane line fitting and smoothing system of the present invention.

[0044] The realization, functional characteristics, and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific Embodiments

[0045] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] Refer to Figure 1 , Figure 1 This is a schematic structural diagram of a lane line fitting and smoothing device for the hardware operating environment involved in the embodiment solution of the present invention.

[0047] As Figure 1 shown, the lane line fitting and smoothing device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless-fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1 the structure shown in

[0049] does not constitute a limitation on the lane line fitting and smoothing device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Figure 1 shown, the memory 1005, as a storage medium, may include an operating system, a network communication module, a user interface module, and a lane line fitting and smoothing program.

[0050] In Figure 1In the lane line fitting and smoothing device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the lane line fitting and smoothing device of the present invention can be arranged in the lane line fitting and smoothing device. The lane line fitting and smoothing device calls the lane line fitting and smoothing program stored in the memory 1005 through the processor 1001 and executes the lane line fitting and smoothing method provided by the embodiment of the present invention.

[0051] An embodiment of the present invention provides a lane line fitting and smoothing method. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of the lane line fitting and smoothing method of the present invention.

[0052] In this embodiment, the lane line fitting and smoothing method includes the following steps:

[0053] Step S10: Determine the target road ID under the road field according to the simulation high-precision map opendrive file.

[0054] It is easy to understand that the execution subject of this embodiment can be a lane line fitting and smoothing system with functions such as data processing, network communication, and program running, or other computer devices with similar functions. This embodiment does not impose any restrictions.

[0055] It should be noted that the simulation high-precision map opendrive file is a road file with a suffix of.xodr, which is used to describe information such as the coordinate points, length, width, yaw angle, curvature, and number of lanes of the simulation road. The target road ID is stored in the road field of the.xodr file.

[0056] It should also be understood that since the simulation high-precision map is composed of multiple roads, each road is represented by a road ID. When reading the road coordinate points and yaw angle information, the coordinate points and yaw angles of multiple lane lines of each road are read according to different road IDs respectively. The road field contains multiple road IDs, that is, road IDs, and the target road ID is the road ID corresponding to the lane line to be processed.

[0057] Step S20: Read multiple geometry node information in the planView field corresponding to the target road ID from the simulation high-precision map opendrive file.

[0058] Further, perform format conversion on the opendrive file of the simulation high-precision map to obtain a dictionary simulation map file; read the information of multiple geometry nodes in the planView field corresponding to the target road ID under the road field from the dictionary simulation map file.

[0059] Step S30: Determine multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID according to the information of multiple geometry nodes.

[0060] It should be understood that the.xodr is essentially an xml file. The reading of lane line coordinate points and yaw angles can be converted using the xml-to-dictionary conversion package in python to convert the.xodr file into a dictionary data structure, and then read multiple geometry nodes in the planView field corresponding to the target road ID under the road field in the dictionary simulation map file. Among them, each lane line coordinate point and yaw angle corresponds to a geometry node, and then the lane line coordinate points and the x, y, and hdg values of the yaw angles are read one by one according to multiple geometry nodes.

[0061] It should also be noted that multiple simulation lane line coordinate points and multiple simulation yaw angles of the target road ID can be saved to an excel or csv file.

[0062] Step S40: Process multiple simulation lane line coordinate points and multiple simulation yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0063] Further, determine the fitting function through the polyfit method and the polyld method in the matplotlib library in python; obtain the fitting equation coefficients through the fitting function according to multiple simulation lane line coordinate points; process multiple simulation lane line coordinate points and multiple simulation yaw angles through the fitting function based on the fitting equation coefficients to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0064] In a specific implementation, refer to Figure 3 , Figure 3 is the curve graph of the lane line coordinate points without smoothing processing in the first embodiment of the lane line fitting and smoothing method of the present invention. According to multiple simulation lane line coordinate points, a simulation curve graph can be generated. The lane line coordinate points without fitting are not smooth and oscillating. When an autonomous vehicle travels on such a serrated simulation road, it will show a snake-like shape.

[0065] In this embodiment, the lane line coordinate points without smoothing are multiple simulated lane line coordinate points. The least squares method is used for curve fitting of the lane line coordinates. The least squares method realizes that the sum of the squares of the errors between the generated data and the actual data is minimized. Curve fitting is to find a curve such that the data points are all not far above or below this curve, which can not only reflect the overall distribution of the data but also avoid large local fluctuations, thus realizing the smoothing of the lane line.

[0066] It should also be noted that the polyfit method and polyld method in the matplotlib library in python are used to determine the variables, order, and coefficients in the fitting function. The fitting function is y = ax3 + bx2 + cx + d, where x and y are the simulated lane line coordinate points, and a, b, and c are the fitting equation coefficients.

[0067] In specific implementation, multiple simulated lane line coordinate points saved in an excel or csv file are read. By solving the equations, the coefficients of the least squares fitting curve equation can be obtained. The least squares fitting curve equation y = f(x) is completed. Then, the x values of the above-read coordinate points are input into the least squares fitting curve equation y = f(x) to obtain the corresponding y values, thereby obtaining multiple lane line fitting coordinate points. Based on the multiple lane line fitting coordinate points, a lane line coordinate point fitting curve graph can be generated. Refer to Figure 4 , Figure 4 which is the lane line coordinate point fitting curve graph of the first embodiment of the lane line fitting and smoothing method of the present invention. Figure 4 It can be seen that the originally discrete and oscillating lane line coordinate points are smoothed through the least squares curve fitting.

[0068] Furthermore, based on the fitting equation coefficients, the multiple simulated yaw angles are processed through the fitting function. The processing method for obtaining multiple fitted yaw angles is to take the derivative of the fitting function based on the multiple lane line fitting coordinate points according to the fitting equation coefficients to obtain the coordinate slope values corresponding to each lane line fitting coordinate point; and the fitted yaw angles corresponding to each simulated yaw angle are obtained respectively through the yaw angle formula based on the coordinate slope values corresponding to each lane line fitting coordinate point.

[0069] In specific implementation, the x values of the above-read coordinate points are input into the least squares fitting curve equation y = f(x), and the equation is differentiated. The obtained y value is the slope value corresponding to this coordinate point, that is, the coordinate slope value k. The unit of the yaw angle hdg is radians. Then, according to the yaw angle formula hdg = arctan(k) * π / 180, the fitted yaw angles corresponding to each simulated yaw angle are obtained.

[0070] Furthermore, the method for realizing the lane line fitting smoothing corresponding to the target road ID according to multiple lane line fitting coordinate points and multiple fitting yaw angles is to update the information of multiple geometry nodes corresponding to the target road ID in the dictionary simulation map file according to multiple lane line fitting coordinate points and multiple fitting yaw angles, so as to obtain an updated dictionary simulation map file; convert the format of the updated dictionary simulation map file to obtain an updated opendrive file; and realize the lane line fitting smoothing corresponding to the target road ID based on the updated opendrive file.

[0071] In this embodiment, the new coordinate points x, y, and hdg after being processed by the fitting function are saved into the data body of the dictionary structure, or saved into a csv or excel table, and so on. The coordinate points x, y, and yaw angles hdg of all roads in the entire high-precision map are calculated and saved into the data body of the dictionary structure, or saved into a csv or excel table.

[0072] Furthermore, use the xml-to-dictionary conversion package in python to convert the.xodr file into a dictionary data structure, then read the geometry nodes in the planView field under the road field in the dictionary, and re-save the above-mentioned lane line coordinate points x, y, and yaw angle hdg into the geometry nodes in the dictionary structure. Each coordinate point and yaw angle corresponds to a geometry node, and they are sequentially saved into the corresponding fields of the lane line coordinate points x, y, and yaw angle hdg in the geometry node. Then, the coordinate points and yaw angle information of each section of the high-precision map correspond to the x, y, and hdg fields in the road field structure corresponding to the lane line id. When all the point coordinates and yaw angle information are saved in the dictionary structure, the point coordinates and yaw information after the lane line curve fitting are updated. Then, use the python for converting from dictionary to xml structure for conversion, and finally save it as an opendrive file in the.xodr format, so that the entire simulation high-precision map completes the coordinate point fitting smoothing process.

[0073] It should also be noted that during the autonomous driving simulation process, VTD will send the high-precision map lane line coordinate point information to the autonomous driving control algorithm in real time. The autonomous driving algorithm will perform real-time path planning and control based on the lane line coordinate point information. Only the forwarding code for the part where VTD sends to the control algorithm needs to be modified. First, read the lane line point coordinates sent by VTD in real time, then use the least squares method to fit the lane lines to obtain a smoothed curve equation. Then, keep the x value of the coordinate points unchanged and input them into the curve equation to obtain new y values. These new x and y values are the lane line point coordinates after smoothing. Finally, send these processed coordinate points to the autonomous driving algorithm in real time. Then the autonomous driving algorithm receives the lane line point coordinates after smoothing, and the driving trajectory will be stable. The autonomous driving vehicle will keep driving in the center of the road, and the problem of snake-like driving is also solved.

[0074] Furthermore, based on the updated OpenDRIVE file, determine the left distance signal curve and the right distance signal curve corresponding to the test vehicle and the left and right lane lines respectively; determine the offset distance of the test vehicle from the road center line according to the left distance signal curve and the right distance signal curve; when the offset distance is greater than a preset threshold, it is necessary to reprocess multiple lane line fitting coordinate points and multiple fitting yaw angles through a fitting function. If it is less than the preset threshold, it means that the lane lines are smooth, and the problem of snake-like driving of the vehicle during the autonomous driving simulation test is solved. The preset threshold can be user-defined, and this embodiment does not impose any restrictions.

[0075] In specific implementation, start the simulation test environment, open the VTD simulation software, import the above-mentioned updated high-precision map, that is, the updated OpenDRIVE file, place the test vehicle on the high-precision map, start the autonomous driving mode, and let the test vehicle drive in the autonomous driving mode on the high-precision map. Pull the distance l1 and l2 signal curves between the vehicle and the left and right lane lines. Then the offset distance of the vehicle from the road center line is d = (l1 + l2) / 2. By observing the magnitude of the d value, the severity of the snake-like driving of the vehicle can be judged. After comparison, for the lane lines without smoothing, the offset distance of the vehicle from the road center line is greater than 0.5m, while for the lane lines with smoothing, the offset distance of the vehicle from the road center line is less than 0.2m, and the problem of snake-like driving disappears. It can be seen that by fitting the lane line coordinate points through the least squares method, the lane lines are smoothed, and the problem of snake-like driving of the vehicle during the autonomous driving simulation test is solved, which is of great significance for the high-precision map data processing and the autonomous driving simulation test work.

[0076] In this embodiment, first, the target road ID under the road field is determined according to the opendrive file of the simulation high-precision map, and multiple geometry node information in the planView field corresponding to the target road ID is respectively read from the opendrive file of the simulation high-precision map. Then, multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID are determined according to the multiple geometry node information. After that, the multiple simulation lane line coordinate points and multiple simulation yaw angles are processed through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles. Finally, lane line fitting smoothing corresponding to the target road ID is realized according to the multiple lane line fitting coordinate points and multiple fitting yaw angles. Compared with the prior art where the simulation high-precision map is not smoothed, there is generally a problem of uneven road coordinate points, resulting in serious snake-like movement of the autonomous driving vehicle during the autonomous driving simulation test, which affects the effect of the simulation test. In this embodiment, the multiple simulation lane line coordinate points and multiple simulation yaw angles are subjected to fitting and smoothing processing through a fitting function, and this information is updated to the opendrive file of the simulation high-precision map, so as to solve the problem of snake-like movement of the vehicle during the autonomous driving simulation test.

[0077] Referring to Figure 5 , Figure 5 which is the structural block diagram of the first embodiment of the lane line fitting and smoothing system of the present invention.

[0078] As Figure 5 shown, the lane line fitting and smoothing system proposed in the embodiment of the present invention includes:

[0079] A determination module 5001, configured to determine the target road ID under the road field according to the opendrive file of the simulation high-precision map;

[0080] A reading module 5002, configured to respectively read multiple geometry node information in the planView field corresponding to the target road ID from the opendrive file of the simulation high-precision map;

[0081] The determination module 5001 is further configured to determine multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID according to the multiple geometry node information;

[0082] A calculation module 5003, configured to process multiple simulation lane line coordinate points and multiple simulation yaw angles through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles;

[0083] A fitting module 5004, configured to realize lane line fitting smoothing corresponding to the target road ID according to multiple lane line fitting coordinate points and multiple fitting yaw angles.

[0084] In this embodiment, first, the target road ID under the road field is determined according to the opendrive file of the simulation high-precision map, and multiple geometry node information in the planView field corresponding to the target road ID is read from the opendrive file of the simulation high-precision map. Then, multiple simulation lane line coordinate points and multiple simulation yaw angles corresponding to the target road ID are determined according to the multiple geometry node information. After that, the multiple simulation lane line coordinate points and multiple simulation yaw angles are processed through a fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles. Finally, the lane line fitting smoothing corresponding to the target road ID is realized according to the multiple lane line fitting coordinate points and multiple fitting yaw angles. Compared with the prior art where the simulation high-precision map is not smoothed, there is generally a problem of uneven road coordinate points, resulting in serious serpentine movement of the autonomous driving vehicle during the autonomous driving simulation test, which affects the effect of the simulation test. In this embodiment, the multiple simulation lane line coordinate points and multiple simulation yaw angles are subjected to fitting and smoothing processing through a fitting function, and this information is updated to the opendrive file of the simulation high-precision map, so as to solve the problem of vehicle serpentine movement during the autonomous driving simulation test.

[0085] Other embodiments or specific implementation manners of the lane line fitting smoothing system of the present invention can refer to the above method embodiments, and will not be elaborated here.

[0086] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0087] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0089] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A lane line fitting and smoothing method, characterized in that: The lane line fitting and smoothing method comprises the following steps: Determine the target road ID under the road field according to the simulated high-precision map opendrive file; Reading multiple geometry node information in the planView field corresponding to the target road ID from the simulated high-precision map opendrive file respectively; Determine multiple simulated lane line coordinate points and multiple simulated yaw angles corresponding to the target road ID according to multiple geometry node information; Processing a plurality of simulated lane line coordinate points and a plurality of simulated yaw angles through a fitting function to obtain a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles; The lane line fitting smoothing corresponding to the target road ID is achieved according to a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles.

2. The method according to claim 1, characterized in that The step of respectively reading the plurality of geometry node information in the planView field corresponding to the target road ID from the simulated high-precision map opendrive file comprises: Convert the format of the simulated high-precision map opendrive file to obtain a dictionary simulated map file; The plurality of geometry node information in the planView field corresponding to the target road ID under the road field is read from the dictionary simulation map file.

3. The method according to claim 2, characterized in that The step of processing a plurality of simulated lane line coordinate points and a plurality of simulated yaw angles by a fitting function to obtain a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles comprises: Determine the fitting function using the polyfit method and polyld method in the matplotlib library in Python; Obtaining fitting equation coefficients through the fitting function according to a plurality of simulated lane line coordinate points; Based on the fitting equation coefficients, the multiple simulated lane line coordinate points and the multiple simulated yaw angles are processed respectively by the fitting function to obtain multiple lane line fitting coordinate points and multiple fitting yaw angles.

4. The method according to claim 3, characterized in that The step of processing a plurality of simulated yaw angles by the fitting function based on the fitting equation coefficients to obtain a plurality of fitting yaw angles comprises: Based on the fitting equation coefficient, the fitting function is derived according to a plurality of lane line fitting coordinate points to obtain a coordinate slope value corresponding to each lane line fitting coordinate point; According to the coordinate slope values ​​corresponding to the fitting coordinate points of each lane line, the fitting yaw angle corresponding to each simulated yaw angle is obtained by using the yaw angle formula.

5. The method according to claim 4, characterized in that The step of achieving lane line fitting smoothing corresponding to the target road ID according to a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles comprises: Update multiple geometry node information corresponding to the target road ID in the dictionary simulation map file according to multiple lane line fitting coordinate points and multiple fitting yaw angles to obtain an updated dictionary simulation map file; Convert the updated dictionary simulation map file into a new format to obtain an updated opendrive file; The lane line fitting smoothing corresponding to the target road ID is achieved based on the updated opendrive file.

6. The method according to claim 5, characterized in that After the step of implementing lane line fitting smoothing corresponding to the target road ID based on the updated opendrive file, the method further includes: Determine the left distance signal curve and the right distance signal curve corresponding to the left lane line and the right lane line of the test vehicle respectively based on the updated opendrive file; Determine the offset distance between the test vehicle and the center line of the road according to the left distance signal curve and the right distance signal curve; When the offset distance is greater than a preset threshold, the multiple lane line fitting coordinate points and the multiple fitting yaw angles are processed by the fitting function.

7. A lane line fitting and smoothing system, characterized in that: The lane line fitting and smoothing system comprises: A determination module is used to determine the target road ID under the road field according to the simulated high-precision map opendrive file; A reading module, used for reading the multiple geometry node information in the planView field corresponding to the target road ID from the simulated high-precision map opendrive file; The determination module is further used to determine a plurality of simulated lane line coordinate points and a plurality of simulated yaw angles corresponding to the target road ID according to a plurality of geometry node information; A calculation module, used for processing a plurality of simulated lane line coordinate points and a plurality of simulated yaw angles through a fitting function to obtain a plurality of lane line fitting coordinate points and a plurality of fitting yaw angles; The fitting module is used to achieve lane line fitting smoothing corresponding to the target road ID according to multiple lane line fitting coordinate points and multiple fitting yaw angles.

8. A lane line fitting and smoothing device, characterized in that: The device comprises: a memory, a processor, and a lane line fitting and smoothing program stored in the memory and executable on the processor, wherein the lane line fitting and smoothing program is configured to implement the steps of the lane line fitting and smoothing method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a lane line fitting and smoothing program, and when the lane line fitting and smoothing program is executed by the processor, the steps of the lane line fitting and smoothing method according to any one of claims 1 to 6 are implemented.

Images