Parking path optimization method, device, vehicle and storage medium

Abstract

The present application provides a parking path optimization method, device, vehicle, and storage medium, relating to the field of vehicle technology. The method is capable of correcting and optimizing a parking path, improving the practicality of the parking path and enhancing the stability of automatic parking. The method comprises: obtaining an original parking path, the original parking path comprising multiple path points; identifying abnormal path points from the original parking path based on a first road boundary and a second road boundary, the first road boundary and the second road boundary being the two side boundaries of the road on which the original parking path is located; correcting the abnormal path point based on adjacent path points to obtain a corrected path point; and optimizing the original parking path based on the corrected path point to obtain an optimized parking path.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a parking path optimization method, device, vehicle and storage medium. Background Art

[0002] Memory Parking is a type of autonomous parking technology that enables fully autonomous parking without user interaction. The user simply drives the vehicle manually, activates the learning map function in the garage, begins normal driving, selects a parking space, and parks. The built-in memory parking algorithm then records the vehicle's driving trajectory, environmental information collected by sensors, and other data, ultimately constructing a parking path and semantic map. The vehicle will then park autonomously based on this path.

[0003] While memory parking technology can bring convenience to users, it does require certain driving skills during the mapping phase. The steering wheel and vehicle must be kept stable during the mapping process, and obstacles within the parking path can also affect the mapping. Therefore, how to ensure that the parking path formed after mapping is not affected by the user's driving ability and obstacles, and how to lower the threshold for using memory parking technology, is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a parking path optimization method, device, vehicle, and storage medium for optimizing a parking path generated by a user while driving a car, thereby better implementing autonomous parking. The technical solutions provided in this application are as follows:

[0005] According to a first aspect of the present application, a parking path optimization method is provided, comprising: obtaining an original parking path, the original parking path including a plurality of path points; identifying abnormal path points from the original parking path based on a first road boundary and a second road boundary, the first road boundary and the second road boundary being two side boundaries of a road on which the original parking path is located; correcting the abnormal path point based on path points adjacent to the abnormal path point to obtain a corrected path point; and optimizing the original parking path based on the corrected path point to obtain an optimized parking path.

[0006] According to the above technical means, abnormal path points in the parking path are found according to the road boundaries on both sides of the parking path, and the abnormal path points are corrected according to the path points adjacent to the abnormal path points, and then the parking path is optimized. Finally, the optimized parking path is obtained, which can lower the usage threshold of memory parking technology and improve the user experience of automatic parking.

[0007] In one possible embodiment, the above method includes: for the multiple path points, performing the following identical steps: obtaining a first distance between the path point and a first road boundary and a second distance between the path point and a second road boundary; determining the larger distance between the first distance and the second distance as the judgment distance; and identifying the path point as an abnormal path point when the judgment distance is greater than a preset distance threshold.

[0008] According to the above technical means, it is possible to find abnormal path points at multiple path points, and then correct the abnormal path points, thereby improving the practicality of the parking path.

[0009] In a possible implementation, the method further includes: obtaining a road boundary point set, the road boundary point set including a plurality of road boundary points; dividing the road boundary point set into a first road boundary point subset and a second road boundary point subset based on distances between the road boundary points in the road boundary point set and the original parking path; fitting a first road boundary based on the first road boundary point subset, and fitting a second road boundary based on the second road boundary point subset.

[0010] According to the above technical means, the road boundary points are divided into a first road boundary point subset and a second road boundary point subset according to the distance between the road boundary points and the original parking path, preparing for the next step of finding abnormal path points and improving the work efficiency of optimizing the parking path.

[0011] In one possible implementation, the method includes: determining a distance between a road boundary point in a road boundary point set and the original parking path; dividing the road boundary points having a distance greater than 0 into a first road boundary point subset, and dividing the road boundary points having a distance less than 0 into a second road boundary point subset.

[0012] According to the above technical means, road boundary points with a distance greater than 0 from the original parking path are divided into a first road boundary point subset, and road boundary points with a distance less than 0 are divided into a second road boundary point subset. This can more clearly distinguish the road boundaries on both sides of the original parking path, thereby improving the accuracy of the original parking path.

[0013] In one possible implementation, the method includes: searching for a jumping point in a first road boundary point subset; dividing the first road boundary point subset into a plurality of first subsets using the jumping point as a dividing point; fitting a plurality of first road sub-boundaries based on the plurality of first subsets; and combining the plurality of first road sub-boundaries into a first road boundary.

[0014] According to the above technical means, the first road boundary point subsets are divided according to the jump points, and then multiple segments of the first road sub-boundaries are fitted, and finally a complete and accurate first road boundary is synthesized, which can improve the accuracy of optimizing the parking path.

[0015] In one possible implementation, the method includes: searching for a jump point in a second road boundary point subset; dividing the second road boundary point subset into a plurality of second subsets using the jump point as a dividing point; fitting a plurality of second road sub-boundaries based on the plurality of second subsets; and synthesizing the plurality of second road sub-boundaries into a second road boundary.

[0016] According to the above technical means, the second road boundary point subsets are divided according to the jump points, and then multiple segments of the second road sub-boundaries are fitted, and finally a complete and accurate second road boundary is synthesized, which can improve the accuracy of optimizing the parking path.

[0017] According to a second aspect of the present application, a parking path optimization device is provided, comprising: an acquisition module for acquiring an original parking path, the original parking path including a plurality of path points; an identification module for identifying abnormal path points from the original parking path based on a first road boundary and a second road boundary, the first road boundary and the second road boundary being two side boundaries of a road on which the original parking path is located; an optimization module for correcting the abnormal path point based on adjacent path points to obtain a corrected path point; and the optimization module for optimizing the original parking path based on the corrected path points to obtain an optimized parking path.

[0018] In one possible embodiment, the identification module is specifically used to: for the multiple path points, perform the following identical steps: obtain a first distance between the path point and the first road boundary and a second distance between the path point and the second road boundary; determine the larger distance between the first distance and the second distance as the judgment distance; and identify the path point as an abnormal path point when the judgment distance is greater than a preset distance threshold.

[0019] In one possible implementation, the apparatus further includes a partitioning module and a fitting module; the acquisition module is further configured to acquire a road boundary point set, the road boundary point set including a plurality of road boundary points; the partitioning module is configured to partition the road boundary point set into a first road boundary point subset and a second road boundary point subset based on distances between the road boundary points in the road boundary point set and the original parking path; and the fitting module is configured to fit a first road boundary based on the first road boundary point subset, and to fit a second road boundary based on the second road boundary point subset.

[0020] In one possible implementation, the partitioning module is specifically configured to: determine the distance between a road boundary point in the road boundary point set and the original parking path; partition the road boundary points having a distance greater than 0 into a first road boundary point subset, and partition the road boundary points having a distance less than 0 into a second road boundary point subset.

[0021] In one possible implementation, the fitting module is specifically configured to: search for a transition point in a first road boundary point subset; divide the first road boundary point subset into a plurality of first subsets using the transition point as a dividing point; fit a plurality of first road sub-boundaries based on the plurality of first subsets; and synthesize the plurality of first road sub-boundaries into a first road boundary.

[0022] In one possible implementation, the fitting module is specifically configured to: search for a transition point in the second road boundary point subset; divide the second road boundary point subset into a plurality of second subsets using the transition point as a dividing point; fit a plurality of second road sub-boundaries based on the plurality of second subsets; and synthesize the plurality of second road sub-boundaries into a second road boundary.

[0023] According to the third aspect provided by the present application, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation method thereof.

[0024] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of the vehicle, the vehicle is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fifth aspect provided by the present application, a computer program product is provided, which includes computer instructions. When the computer instructions are run on a vehicle, the vehicle executes the method of the above-mentioned first aspect and any possible implementation method thereof.

[0026] Therefore, the above technical features of this application have the following beneficial effects:

[0027] (1) According to the road boundaries on both sides of the parking path, the abnormal path points in the parking path are found, and the abnormal path points are corrected according to the path points adjacent to the abnormal path points, and then the parking path is optimized. Finally, the optimized parking path is obtained, which can lower the threshold for using memory parking technology and improve the user experience of automatic parking.

[0028] (2) It can find abnormal path points at multiple path points and then correct them, thereby improving the practicality of the parking path.

[0029] (3) According to the distance between the road boundary points and the original parking path, the road boundary points are divided into the first road boundary point subset and the second road boundary point subset, which prepares for the next step of finding abnormal path points and improves the work efficiency of optimizing the parking path.

[0030] (4) The road boundary points whose distance to the original parking path is greater than 0 are divided into the first road boundary point subset, and the road boundary points whose distance is less than 0 are divided into the second road boundary point subset. This can more clearly distinguish the road boundaries on both sides of the original parking path, thereby improving the accuracy of the original parking path.

[0031] (5) According to the jump points, the first road boundary point subsets are divided, and then multiple segments of the first road sub-boundaries are fitted, and finally a complete and accurate first road boundary is synthesized, which can improve the accuracy of optimizing the parking path.

[0032] (6) The second road boundary point subsets are divided according to the jump points, and then multiple segments of the second road sub-boundaries are fitted, and finally a complete and accurate second road boundary is synthesized, which can improve the accuracy of optimizing the parking path.

[0033] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a parking path optimization method provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of an original parking path provided in an embodiment of this application;

[0037] Figure 3 A schematic diagram of another original parking path provided in an embodiment of the present application;

[0038] Figure 4 A schematic diagram of an optimized parking path provided in an embodiment of the present application;

[0039] Figure 5 An overall flow chart of a parking path optimization method provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of a parking path optimization method provided in an embodiment of the present application;

[0041] Figure 7 A schematic structural diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to enable ordinary people in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0043] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0044] For ease of understanding, a parking path optimization method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0045] Figure 1 FIG. 1 is a flow chart showing a method for optimizing a parking path according to an exemplary embodiment. Figure 1 As shown, the parking path optimization method includes the following steps:

[0046] S101: Obtain an original parking path.

[0047] The original parking path includes multiple path points, and each path point has horizontal and vertical coordinates and navigation attributes.

[0048] In some embodiments, after the original parking path is obtained, the original parking path is processed to have equal spacing, and the multiple path points are sorted in chronological order, and each path point is assigned a sequence number.

[0049] For example, Figure 1 As shown, the original parking path can be the driving trajectory of the vehicle when the user drives the car during the learning and mapping process.

[0050] It is understandable that during the learning and mapping process, the user's driving ability and the lane conditions in the parking path at the time will affect the generation of the parking path. Therefore, the original parking path cannot be directly used as the parking path in the actual automatic parking process for automatic parking.

[0051] S102: Identify abnormal path points from the original parking path according to the first road boundary and the second road boundary.

[0052] The first road boundary and the second road boundary are boundaries on both sides of the road where the original parking path is located.

[0053] In some embodiments, the first road boundary and the second road boundary are obtained according to the following method: obtaining a road boundary point set, the road boundary point set including a plurality of road boundary points; dividing the road boundary point set into a first road boundary point subset and a second road boundary point subset based on the distance between the road boundary points in the road boundary point set and the original parking path; fitting the first road boundary according to the first road boundary point subset, and fitting the second road boundary according to the second road boundary point subset.

[0054] It should be noted that during the learning and mapping process, when the user drives the car, the vehicle sensors will collect relevant data such as environmental information to construct a road boundary point set, which includes multiple road boundary points.

[0055] After obtaining the set of road boundary points, it is necessary to establish a correspondence between the road boundary points and the path points, that is, to match the road boundary points with the closest path points.

[0056] In some embodiments, dividing the road boundary point set into a first road boundary point subset and a second road boundary point subset based on the distance between the road boundary points in the road boundary point set and the original parking path can be specifically implemented by the following steps: determining the distance between the road boundary points in the road boundary point set and the original parking path; dividing the road boundary points with a distance greater than 0 into the first road boundary point subset, and dividing the road boundary points with a distance less than 0 into the second road boundary point subset.

[0057] For example, the first road boundary point subset may be a left road boundary point subset, and the second road boundary point subset may be a right road boundary point subset; or, the first road boundary point subset may be a right road boundary point subset, and the second road boundary point subset may be a left road boundary point subset.

[0058] It should be noted that when the distance between a road boundary point and the original parking path is 0, it proves that the vehicle trajectory is pressed on the boundary line during the learning and mapping process. The road boundary point has no reference value. During the parking path optimization process, the road boundary point is chosen to be deleted.

[0059] In some embodiments, fitting a first road boundary based on a first subset of road boundary points and fitting a second road boundary based on a second subset of road boundary points can be specifically implemented by the following steps: finding a transition point in the first subset of road boundary points; dividing the first subset of road boundary points into multiple first subsets using the transition point as a demarcation point; fitting multiple segments of first road sub-boundaries based on the multiple first subsets; and synthesizing the multiple segments of first road sub-boundaries into the first road boundary. The second road boundary can be obtained by the following method: finding a transition point in the second subset of road boundary points; dividing the second subset of road boundary points into multiple second subsets using the transition point as a demarcation point; fitting multiple segments of second road sub-boundaries based on the multiple second subsets; and synthesizing the multiple segments of second road sub-boundaries into the second road boundary.

[0060] The jump point is a point where a jump occurs in the X direction or the Y direction.

[0061] As a possible implementation manner, the transition points in the first road boundary point subset and the second road boundary point subset may be searched according to the curvature of the road boundary points.

[0062] Exemplarily, N consecutive road boundary points are selected, where N is a natural number greater than 2. For example, three consecutive road boundary points A, B, and C are selected from the first road boundary point subset. A curvature K1 can be calculated based on points A and B, and another curvature K2 can be calculated based on points B and C. If the absolute value of the difference between K1 and K2 is greater than a preset curvature threshold, it indicates that there is a jump point among the three road boundary points A, B, and C. At this time, it is possible that all three points are jump points, or it is also possible that one or two of the points are jump points.

[0063] Considering that this embodiment essentially performs curvature detection on each road boundary point, in order to improve the efficiency of finding the jump point, the common road boundary point is determined as the jump point, that is, B in the above example is the jump point.

[0064] It is understandable that after segmenting the first and second road boundary point subsets based on the jump points, they need to be corrected based on the environmental information collected by sensors during the learning and mapping process and the freespace in the drivable area to avoid missegmentation in scenarios such as intersections, or unreasonable segmentation when environmental information changes.

[0065] The drivable free space refers to the static obstacle information detected by the sensor during the learning screenshot process, such as walls and pillars.

[0066] In some embodiments, identifying abnormal path points from the original parking path based on the first road boundary and the second road boundary can be specifically implemented as the following steps: for the multiple path points, performing the following identical steps: obtaining a first distance between the path point and the first road boundary and a second distance between the path point and the second road boundary; determining the larger of the first distance and the second distance as the judgment distance; and identifying the path point as an abnormal path point when the judgment distance is greater than a preset distance threshold.

[0067] For example, an abnormal path point is a point with a large deviation in the horizontal or vertical direction, for example Figure 1 Point P in the figure has a large deviation in the longitudinal direction.

[0068] S103. Correct the abnormal path point based on the path points adjacent to the abnormal path point to obtain a corrected path point.

[0069] In some embodiments, a quadratic function is established based on the coordinates of two path points adjacent to the abnormal path point, and the direction coordinate values ​​of the abnormal path point without deviation are substituted into the quadratic function to obtain the coordinates of the corrected path point.

[0070] For example, Figure 2 Point P is an abnormal path point, and points M and N are adjacent path points to point P. According to the coordinates of points M and N, find the quadratic function corresponding to points M and N, and substitute the horizontal coordinate of point P into the quadratic function to obtain the coordinates of the corrected path point P1.

[0071] S104: Optimize the original parking path based on the corrected path points to obtain an optimized parking path.

[0072] like Figure 3 As shown, Figure 3 The original parking path after the abnormal path points are corrected is obtained. In some embodiments, the original parking path is smoothed by using quadratic programming. Figure 4 The optimized parking path is shown.

[0073] In this way, according to the road boundaries on both sides of the parking path, abnormal path points in the parking path are found, and the abnormal path points are corrected according to the path points adjacent to the abnormal path points, and then the parking path is optimized. Finally, the optimized parking path is obtained, which can lower the usage threshold of memory parking technology and improve the user experience of automatic parking.

[0074] Below, Figure 5 The content shown further illustrates the above method provided in the embodiment of the present application.

[0075] First, the original parking path is preprocessed, which includes equal spacing processing and sorting of path points.

[0076] Furthermore, the original parking path is corrected based on the road boundary point set and environmental information.

[0077] Furthermore, the corrected original parking path is optimized to obtain an optimized parking path.

[0078] Finally, path planning and following control are performed based on the optimized parking path to ensure that the vehicle can achieve autonomous parking.

[0079] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the parking path optimization device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0080] In the embodiments of the present application, the parking path optimization device can be divided into functional modules according to the above method. For example, the parking path optimization device can include functional modules corresponding to the respective functional divisions, or two or more functions can be integrated into a single processing module. The integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the module division in the embodiments of the present application is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used.

[0081] Figure 6 is a schematic structural diagram of a parking path optimization device according to an exemplary embodiment. Figure 6 The parking path optimization device includes: an acquisition module 601, an identification module 602 and an optimization module 603.

[0082] The acquisition module 601 is configured to acquire an original parking path, where the original parking path includes a plurality of path points.

[0083] The identification module 602 is configured to identify abnormal path points from the original parking path based on a first road boundary and a second road boundary, where the first road boundary and the second road boundary are boundaries on both sides of the road where the original parking path is located.

[0084] The optimization module 603 is used to correct the abnormal path point based on the path points adjacent to the abnormal path point to obtain a corrected path point.

[0085] The optimization module 603 is further configured to optimize the original parking path based on the corrected path points to obtain an optimized parking path.

[0086] In some embodiments, the identification module 602 is specifically used to: for the multiple path points, perform the following same steps: obtain a first distance between the path point and the first road boundary and a second distance between the path point and the second road boundary; determine the larger distance between the first distance and the second distance as the judgment distance; if the judgment distance is greater than a preset distance threshold, identify the path point as an abnormal path point.

[0087] In some embodiments, the apparatus further includes a division module 604 and a fitting module 605; the acquisition module 601 is further configured to obtain a road boundary point set, the road boundary point set including a plurality of road boundary points; the division module 604 is configured to divide the road boundary point set into a first road boundary point subset and a second road boundary point subset based on the distance between the road boundary points in the road boundary point set and the original parking path; and the fitting module 605 is configured to fit a first road boundary based on the first road boundary point subset, and to fit a second road boundary based on the second road boundary point subset.

[0088] In some embodiments, the partitioning module 604 is specifically configured to: determine the distance between a road boundary point in the road boundary point set and the original parking path; partition the road boundary points with a distance greater than 0 into a first road boundary point subset, and partition the road boundary points with a distance less than 0 into a second road boundary point subset.

[0089] In some embodiments, the fitting module 605 is specifically used to: find a jump point in the first road boundary point subset; divide the first road boundary point subset into multiple first subsets based on the jump point; fit multiple segments of the first road sub-boundary based on the multiple first subsets; and synthesize the multiple segments of the first road sub-boundary into a first road boundary.

[0090] In some embodiments, the fitting module 605 is specifically used to: find a jump point in the second road boundary point subset; divide the second road boundary point subset into multiple second subsets based on the jump point; fit multiple segments of second road sub-boundaries based on the multiple second subsets; and synthesize the multiple segments of second road sub-boundaries into a second road boundary.

[0091] Figure 7 FIG. 1 is a schematic diagram of a vehicle structure according to an exemplary embodiment. Figure 7 As shown, vehicle 70 includes, but is not limited to, a processor 701 and a memory 702 .

[0092] The memory 702 is configured to store executable instructions of the processor 701. It is understood that the processor 701 is configured to execute instructions to implement the parking path optimization method in the above embodiment.

[0093] It should be noted that those skilled in the art can understand that Figure 7 The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and the vehicle may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0094] Processor 701 is the vehicle's control center, connecting all parts of the vehicle using various interfaces and lines. By running or executing software programs and / or modules stored in memory 702 and accessing data stored in memory 702, it performs various vehicle functions and processes data, thereby providing overall vehicle monitoring. Processor 701 may include one or more processing units. Optionally, processor 701 may integrate an application processor and a modem processor, with the application processor primarily handling the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 701.

[0095] The memory 702 can be used to store software programs and various data. The memory 702 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and application programs required by at least one functional module (such as a determination unit, a processing unit, etc.). Furthermore, the memory 702 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0096] In an exemplary embodiment, a computer-readable storage medium including instructions is further provided, such as a memory 702 including instructions. The instructions can be executed by the processor 701 of the vehicle 70 to implement the parking path optimization method in the above embodiment.

[0097] In actual implementation, Figure 6 The functions of the acquisition module 601, the identification module 602, the optimization module 603, the division module 604 and the fitting module 605 can all be obtained by Figure 7 The processor 701 in the embodiment calls the computer program stored in the memory 702. The specific execution process can be referred to the description of the parking path optimization method in the above embodiment, which will not be repeated here.

[0098] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0101] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0103] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A parking path optimization method, characterized in that: The method comprises: Obtaining an original parking path, the original parking path including a plurality of path points; the original parking path is the driving trajectory of the vehicle when the user drives the vehicle during the learning and mapping process; For each of the plurality of waypoints, if a judgment distance corresponding to the waypoint is greater than a preset distance threshold, the waypoint is identified as an abnormal waypoint; the judgment distance is the larger of a first distance and a second distance; the first distance is the distance between the waypoint and a first road boundary; the second distance is the distance between the waypoint and a second road boundary; the first road boundary and the second road boundary are two side boundaries of the road where the original parking path is located; Correcting the abnormal path point based on path points adjacent to the abnormal path point to obtain a corrected path point, including: establishing a quadratic function based on the coordinates of two path points adjacent to the abnormal path point, and substituting the direction coordinate values ​​of the abnormal path point that do not deviate into the quadratic function to obtain the corrected path point; Optimizing the original parking path based on the corrected path points to obtain an optimized parking path includes: smoothing the original parking path using quadratic programming based on the corrected path points to obtain the optimized parking path.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a road boundary point set, where the road boundary point set includes a plurality of road boundary points; dividing the road boundary point set into a first road boundary point subset and a second road boundary point subset based on distances between road boundary points in the road boundary point set and the original parking path; A first road boundary is fitted based on the first subset of road boundary points, and a second road boundary is fitted based on the second subset of road boundary points.

3. The method according to claim 2, characterized in that Dividing the road boundary point set into a first road boundary point subset and a second road boundary point subset based on distances between road boundary points in the road boundary point set and the original parking path, comprising: determining a distance between a road boundary point in the road boundary point set and the original parking path; The road boundary points with a distance greater than 0 are divided into the first road boundary point subset, and the road boundary points with a distance less than 0 are divided into the second road boundary point subset.

4. The method according to claim 2, characterized in that The step of fitting a first road boundary according to the first road boundary point subset includes: Finding a transition point in the first road boundary point subset; Taking the jump point as a dividing point, dividing the first road boundary point subset into a plurality of first subsets; Fitting a plurality of first road sub-boundaries according to the plurality of first subsets; Multiple segments of the first road sub-boundaries are synthesized into the first road boundary.

5. The method according to claim 2, characterized in that The step of fitting a second road boundary according to the second road boundary point subset includes: Finding a transition point in the second road boundary point subset; Taking the jump point as a dividing point, dividing the second road boundary point subset into a plurality of second subsets; Fitting a plurality of second road sub-boundaries according to the plurality of second subsets; The plurality of second road sub-boundaries are synthesized into the second road boundary.

6. A parking path optimization device, characterized in that: The device comprises: An acquisition module is configured to acquire an original parking path, wherein the original parking path includes a plurality of path points; the original parking path is the driving trajectory of the vehicle when the user drives the vehicle during the learning and mapping process; an identification module configured to identify, for each of the plurality of path points, a path point as an abnormal path point if a judgment distance corresponding to the path point is greater than a preset distance threshold; the judgment distance being the larger of a first distance and a second distance; the first distance being the distance between the path point and a first road boundary; the second distance being the distance between the path point and a second road boundary; the first road boundary and the second road boundary being two side boundaries of a road on which the original parking path is located; an optimization module, configured to correct the abnormal path point based on path points adjacent to the abnormal path point to obtain a corrected path point, comprising: establishing a quadratic function based on the coordinates of two path points adjacent to the abnormal path point, and substituting the direction coordinate values ​​of the abnormal path point that do not deviate into the quadratic function to obtain the corrected path point; The optimization module is further configured to optimize the original parking path based on the corrected path points to obtain an optimized parking path, including: smoothing the original parking path using quadratic programming based on the corrected path points to obtain the optimized parking path.

7. The device according to claim 6, characterized in that The device also includes a division module and a fitting module; The acquisition module is further configured to acquire a road boundary point set, wherein the road boundary point set includes a plurality of road boundary points; The dividing module is configured to divide the road boundary point set into a first road boundary point subset and a second road boundary point subset based on distances between road boundary points in the road boundary point set and the original parking path; The fitting module is configured to fit a first road boundary according to the first road boundary point subset, and to fit a second road boundary according to the second road boundary point subset.

8. The device according to claim 7, characterized in that The partitioning module is specifically used to: determining a distance between a road boundary point in the road boundary point set and the original parking path; The road boundary points with a distance greater than 0 are divided into the first road boundary point subset, and the road boundary points with a distance less than 0 are divided into the second road boundary point subset.

9. The device according to claim 7, characterized in that The fitting module is specifically used for: Finding a transition point in the first road boundary point subset; Taking the jump point as a dividing point, dividing the first road boundary point subset into a plurality of first subsets; Fitting a plurality of first road sub-boundaries according to the plurality of first subsets; Multiple segments of the first road sub-boundaries are synthesized into the first road boundary.

10. The device according to claim 7, characterized in that The fitting module is specifically used for: Finding a transition point in the second road boundary point subset; Taking the jump point as a dividing point, dividing the second road boundary point subset into a plurality of second subsets; Fitting a plurality of second road sub-boundaries according to the plurality of second subsets; The plurality of second road sub-boundaries are synthesized into the second road boundary.

11. A vehicle, characterized in that: include: processor; A memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a vehicle, the processor of the vehicle is capable of performing the method according to any one of claims 1 to 5.

Images