Positioning method, positioning system, vehicle and computer-readable storage medium

Abstract

The present application provides a positioning method, a positioning system, a vehicle, and a computer-readable storage medium. The positioning method includes: obtaining a point cloud of the area where the positioning system is located at the current moment; matching the point cloud with the map to determine the target area that matches the point cloud in the map; determining the map point set of the target area in the map; for each data point in the point cloud, searching the map point set for the nearest map point and establishing a corresponding relationship; based on the corresponding relationship, determining the target location point that matches the point cloud in the map point set. In the above manner, the positioning method of the present application uses point clouds to match maps, determine the target area, search for the nearest target location point based on the target area, and combine the two-layer matching process to achieve stable and accurate initialization position positioning at the current moment.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving positioning technology, and in particular to a positioning method, a positioning system, a vehicle, and a computer-readable storage medium. Background Art

[0002] For the autonomous driving positioning system, an accurate initialization position is crucial, which directly affects the stability of the subsequent positioning system and whether the positioning may drift. For the current autonomous driving positioning system, the general initialization method is to directly initialize the positioning using the position received by RTK (Real Time Kinematic, i.e. carrier phase differential technology). This method is relatively simple, but the problems are also obvious. For some places with poor RTK signals, such as closed scenes such as tunnels, directly using the initialization position provided by RTK will be very inaccurate, which will directly affect the start of positioning. Summary of the invention

[0003] The present application provides a positioning method, a positioning system, a vehicle and a computer-readable storage medium.

[0004] The present application provides a positioning method, which includes:

[0005] Get the point cloud of the area where the positioning system is located at the current moment;

[0006] Matching the point cloud with a map to determine a target area in the map that matches the point cloud;

[0007] determining a set of map points of the target area in the map;

[0008] For each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship;

[0009] Based on the corresponding relationship, a target location point matching the point cloud is determined in the map point set.

[0010] The step of matching the point cloud with a map to determine a target area in the map that matches the point cloud includes:

[0011] Determine the search step size;

[0012] According to the search step length, searching in the map for an area that meets a preset matching requirement with the point cloud as a target area;

[0013] For each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship includes:

[0014] determining a set of map points of the target area in the map;

[0015] For each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship;

[0016] Based on the corresponding relationship, a target location point matching the point cloud is determined in the map point set.

[0017] Wherein, searching, according to the search step length, for an area in the map that meets a preset matching requirement with the point cloud as a target area includes:

[0018] Reducing the search step size to update the search step size;

[0019] Based on the updated search step length, the target area and the neighboring areas of the target area are searched for an area that meets a preset matching requirement with the point cloud, so as to update the target area.

[0020] Wherein, based on the updated search step length, searching for an area in the target area and an adjacent area of ​​the target area that meets a preset matching requirement with the point cloud to update the target area includes:

[0021] Determining whether the updated search step size is a preset minimum step size;

[0022] If yes, the target area corresponding to the current search step is confirmed as the final target area.

[0023] Wherein, determining the search step size includes:

[0024] Determine the pyramid level and determine the minimum step size;

[0025] An initial search step size is determined according to the pyramid level and the minimum step size.

[0026] Wherein, the positioning method further includes:

[0027] Obtaining the position based on real-time dynamic measurement technology;

[0028] Determining a tolerance range based on the position and the accuracy of the real-time dynamic measurement technology;

[0029] The initial search step is smaller than the tolerance range.

[0030] Wherein, searching, according to the search step length, for an area in the map that meets a preset matching requirement with the point cloud as a target area includes:

[0031] Based on the search step size, dividing the map into a plurality of search areas;

[0032] Determining the number of matching points in each of the search areas that match the point cloud;

[0033] The degree of matching between the search area and the point cloud is determined according to the ratio of the number of matching points to the total number of points in the search area.

[0034] Wherein, for each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship includes:

[0035] Establishing a binary tree with a set of map points within a preset range centered at the target location point in the map;

[0036] For each data point in the point cloud, the nearest map point is searched in the binary tree and a corresponding relationship is established.

[0037] Wherein, determining the target location point matching the point cloud in the map point set based on the corresponding relationship includes:

[0038] Using the least square method to calculate each of the corresponding relationships to correct the target position point;

[0039] A corrected target location point is determined in the map point set.

[0040] After obtaining the point cloud of the area where the positioning system is located at the current moment, the positioning method further includes:

[0041] identifying dynamic data points in the point cloud;

[0042] The dynamic data points are deleted from the point cloud, and the deleted point cloud is matched with the map.

[0043] Wherein, identifying the dynamic data points in the point cloud includes:

[0044] Input the point cloud into a preset recognition network model to obtain a label for each data point in the point cloud;

[0045] The data points labeled as dynamic objects are identified as dynamic data points.

[0046] The present application also provides a positioning system, which includes a processor and a memory, wherein program data is stored in the memory, and the processor is used to execute the program data to implement the above method.

[0047] The present application also provides a vehicle, which includes the positioning system as described above.

[0048] The present application also provides a computer-readable storage medium, which is used to store program data. When the program data is executed by a processor, it is used to implement the above-mentioned positioning method.

[0049] The beneficial effects of the present application are: the positioning system obtains the point cloud of the area where the positioning system is located at the current moment; the point cloud is matched with the map to determine the target area that matches the point cloud in the map; the map point set of the target area is determined in the map; for each data point in the point cloud, the map point set is searched for the nearest map point and a corresponding relationship is established; based on the corresponding relationship, the target location point that matches the point cloud is determined in the map point set. In the above manner, the positioning method of the present application uses point cloud to match the map, determine the target area, search for the nearest target location point based on the target area, and combine the two-layer matching process to achieve stable and accurate initialization position positioning at the current moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0051] Figure 1 It is a flowchart of an embodiment of a positioning method provided by the present application;

[0052] Figure 2 yes Figure 1 A schematic flow chart of the sub-steps of step S12 in the positioning method;

[0053] Figure 3 yes Figure 2 A schematic flow chart of the sub-steps of step S122 in the positioning method;

[0054] Figure 4 It is a structural schematic diagram of an embodiment of a positioning system provided by the present application;

[0055] Figure 5 is a structural schematic diagram of another embodiment of the positioning system provided by the present application;

[0056] Figure 6 It is a structural schematic diagram of an embodiment of a vehicle provided by the present application;

[0057] Figure 7 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] In view of the above problems that RTK itself receives very poor positions due to limitations of scenes and other issues, point cloud ICP (Iterative Closest Point) matching or image being affected by lighting, which leads to the inability to provide accurate initialization positions, which will have a great impact on the autonomous driving positioning system. This application proposes a stable and accurate positioning initialization method based on lidar point cloud and map in a coarse-to-fine manner.

[0060] See also Figure 1 , Figure 1 It is a flowchart of an embodiment of a positioning method provided by the present application.

[0061] The positioning method of the present application is applied to a positioning system, wherein the positioning system of the present application can be a server, or a system composed of a server and a terminal device. Accordingly, the various parts of the positioning system, such as various units, subunits, modules, and submodules, can all be set in the server, or can be set in the server and the terminal device respectively.

[0062] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here. In some possible implementations, the positioning method of the embodiment of the present application can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0063] Specifically, if Figure 1 As shown, the positioning method of the embodiment of the present application specifically includes the following steps:

[0064] Step S11: Obtain the point cloud of the area where the positioning system is located at the current moment.

[0065] In the embodiment of the present application, the positioning system obtains the point cloud at the current moment through the laser radar, and obtains the map through information collection technology such as GPS. Figure 1 It is generally a three-dimensional map that reflects the three-dimensional information of the target location and environment.

[0066] Step S12: Match the point cloud with the map to determine a target area in the map that matches the point cloud.

[0067] Among them, the ground in the embodiment of this application Figure 1 Generally refers to the high-precision map used in the field of autonomous driving. Specifically, high precision, on the one hand, means that the absolute coordinate accuracy of high-precision electronic maps is higher. Absolute coordinate accuracy refers to the accuracy between a certain target on the map and the real things in the outside world. On the other hand, the road traffic information elements contained in high-precision maps are richer and more detailed.

[0068] By matching the high-precision map with the point cloud, that is, based on each data point in the point cloud, each map location point in the high-precision map can be traversed to select the point with the highest matching degree as the target location point that matches the data point, and the map area including many target location points can be determined as the target area. The embodiment of the present application can effectively improve the matching accuracy with the data points in the point cloud and improve the positioning accuracy by utilizing the high precision between the location points in the high-precision map and the objects in the real external world.

[0069] In an embodiment of the present application, the positioning system matches the point cloud with the map within the set tolerance search range to determine the target position point in the map that matches the point cloud. Among them, the target position point is the position point with the highest matching degree with the point cloud according to the matching rules, including the matching rules embodied in the following coarse matching and fine matching processes, and each data point in the point cloud is determined to have a matching target position point. Specifically, the setting process of the tolerance search range refers to the following process: the positioning system obtains the position and its three-dimensional coordinates received by the RTK placed on the autonomous driving vehicle, and then sets a tolerance value and tolerance range for the RTK accuracy. For example, the tolerance value can be set to 20m. Through the above setting method, the positioning system can set a tolerance search range of ±20m in the x-direction, y-direction, and z-direction of the position received by the RTK, which is much larger than the accuracy tolerance range of the RTK.

[0070] Furthermore, before matching the point cloud with the map, the positioning system can also remove dynamic objects and their dynamic points in the point cloud to improve the accuracy of the match. Specifically, the positioning system can identify dynamic data points in the point cloud; delete the dynamic data points from the point cloud, and match the deleted point cloud with the map. The dynamic data points can be identified by manual labeling or by automatic machine labeling, and the data points marked as dynamic data points can be deleted from the point cloud. For example, the positioning system can obtain a pre-trained recognition network model, which can identify the label of each data point in the input point cloud. The label can be a dynamic object label, a static object label, an environmental label, etc.

[0071] A 3D point cloud map is a superposition of laser scans obtained at different locations and times. Since laser scans capture snapshots of the surrounding environment, they often contain moving objects, and these moving objects may be observed indirectly. Dynamic objects in the point cloud map will reduce the quality of the map and affect the positioning accuracy, so it is very important to remove dynamic objects from the 3D point cloud map. The positioning system of an embodiment of the present application can sense dynamic objects in the 3D point cloud map, and then remove the dynamic points of the dynamic objects in the point cloud based on the perception results.

[0072] Specifically, the positioning system of the embodiment of the present application can construct an occupancy grid map, in which stereo pixels represent the occupancy state of the space quantity over an extended time period. After generating the occupancy grid map, we use it as a filter to remove dynamic target points in the lidar scan before adding them to the map. In addition, we use object detection and a new stereo pixel traversal method to speed up the process of building the occupancy grid map. After the occupancy grid map is built, dynamic object removal can be run in real time.

[0073] Step S13: Determine a map point set of the target area in the map.

[0074] Furthermore, the positioning system of the embodiment of the present application can also use a pyramid matching method to match the point cloud with the target area in the map. For details on the matching process of the target area, please continue to refer to Figure 2 , Figure 2 yes Figure 1 A schematic flow chart of the sub-steps of step S12 in the positioning method.

[0075] Specifically, if Figure 2 As shown, step S12 of the positioning method in the embodiment of the present application specifically includes the following sub-steps:

[0076] Step S121: Determine the search step length.

[0077] In the embodiment of the present application, the positioning system determines the pyramid level and the step length corresponding to each pyramid level, wherein, in order to ensure that the search results are within a reasonable range, it is necessary to ensure that the maximum step length in the pyramid level is within the tolerance search range. Specifically, the step length and tolerance search range of the embodiment of the present application should meet the following conditions:

[0078] min_step*2^n<range

[0079] Among them, min_step is the minimum step length of the search, n is the pyramid level, and range is the tolerance search range. Therefore, the maximum step length of the search can be reflected as: max_step = min_step*2^n.

[0080] Step S122: Based on the search step length, search the map for an area that meets a preset matching requirement with the point cloud as a target area.

[0081] In the embodiment of the present application, after the positioning system determines the search step, it first starts to calculate the target area corresponding to the optimal matching score of the maximum pyramid level from the maximum pyramid level and the maximum step length max_step. The target area is the map area with the highest matching degree with the point cloud among the multiple search areas divided by the map.

[0082] Taking the maximum pyramid level and the maximum step length as an example, the search for the target area in the embodiment of the present application is detailed in detail. Figure 3 , Figure 3 yes Figure 2 A flowchart of the sub-steps of step S122 in the positioning method.

[0083] Specifically, if Figure 3 As shown, step S122 of the positioning method in the embodiment of the present application specifically includes the following sub-steps:

[0084] Step S1221: Based on the search step, divide the map into multiple search areas.

[0085] In an embodiment of the present application, the positioning system divides the map into multiple search areas based on the maximum search step.

[0086] Step S1222: Determine the number of matching points in each search area that match the point cloud.

[0087] In the embodiment of the present application, the positioning system traverses multiple search areas of the map according to the point cloud, and searches for matching points between the point cloud and each search area. If the positioning system successfully searches for matching points in the search area according to the point cloud, the matching score is recorded plus 1; if the positioning system cannot search for matching points in the search area according to the point cloud, the matching score does not increase.

[0088] After the positioning system traverses all the search areas in the map, it obtains the final matching score, which corresponds to the number of matching points between the map and the point cloud.

[0089] Step S1223: Determine the degree of match between the search area and the point cloud based on the ratio of the number of matching points to the total number of points in the search area.

[0090] In the embodiment of the present application, the positioning system uses the ratio of the number of matching points to the total number of points in the search area, that is, the total matching score is divided by the total number of points in the search area to obtain the final score of the search area, that is, the matching degree. The formula for calculating the matching degree is as follows:

[0091] score=total score / points number

[0092] Among them, score is the matching degree, total score is the number of matching points, and points number is the total number of points in the search area.

[0093] It should be noted that the search method for other step lengths is basically the same as the search method for the maximum step length, and will not be described in detail here.

[0094] Step S123: reduce the search step length to update the search step length.

[0095] In the embodiment of the present application, after the positioning system calculates the matching degree of all search areas corresponding to the maximum pyramid level according to the maximum step length, the search area with the largest matching degree is selected as the target area for the next pyramid level search, that is, the optimal position.

[0096] The positioning system reduces the maximum step size to half of the original one and obtains the next step size corresponding to the next pyramid level.

[0097] Step S124: Based on the search step length, search the target area and the neighboring areas of the target area in the map for an area that meets the preset matching requirements with the point cloud, so as to update the target area.

[0098] In the embodiment of the present application, the positioning system uses the next step size to search in the target area and its adjacent areas to obtain the target area of ​​the pyramid level to update the target area of ​​the maximum pyramid level.

[0099] The range of the neighboring area can be set to twice the step size of the next layer, that is, 2×current_step. Adding the neighboring area as the search area can optimize the search efficiency and improve the search accuracy.

[0100] The positioning system repeatedly performs the above steps S121 to S124 until the target area search of all pyramid levels is completed. When the positioning system iteratively searches the last level of the pyramid level, the search area with the largest matching degree in the search area of ​​the last level is the target area where the best initialization position is located.

[0101] The positioning method of the above steps S121 to S124 realizes a coarse match for the precise initialization position. The embodiment of the present application can further realize a precise match for the initialization position based on the coarse matching results of the positioning method of the above embodiment to further improve the accuracy of the initialization position. Please continue to refer to steps S14 to S15.

[0102] Step S14: For each data point in the point cloud, search for the nearest map point in the map point set and establish a corresponding relationship.

[0103] Affected by the accuracy of the minimum step length, the initialization position obtained by the coarse matching result of the positioning method in the above embodiment is not accurate enough. The positioning system in the embodiment of the present application adopts a fine alignment method to further refine the initialization position.

[0104] Specifically, the positioning system establishes a kd tree at the optimal initialization position obtained by the positioning method of the above embodiment, searches for the nearest map point in the kd tree for each point in the point cloud, and establishes a corresponding relationship. The corresponding relationship can be a mapping relationship, which reflects the one-to-one correspondence between a data point in the point cloud and the nearest map point in the map.

[0105] Step S15: Based on the corresponding relationship, determine the target location point that matches the point cloud in the map point set.

[0106] In the embodiment of the present application, the positioning system uses LM (Levenberg-Marquardt) least squares optimization to solve the matching relationship and calculate the cost function between the point cloud and the map. The lower the cost of the cost function, the better the corresponding matching result. Therefore, the positioning system can determine the optimal target position in the map point according to the cost value of the cost function.

[0107] Specifically, the cost function between point cloud and map matching is:

[0108]

[0109] Among them, R is the rotation matrix, T is the translation, P i is a point in the point cloud, Q i is the matching point on the map with the point cloud.

[0110] The positioning system locates the current moment according to the corrected target position point, that is, the optimal target position determined in step S15 is used as the positioning initialization position of the autonomous driving vehicle.

[0111] Furthermore, the positioning system can also calculate the optimal target position for several frames of lidar point clouds acquired continuously and construct an initialization position interpolator; then, the initialization position interpolator is used to interpolate the system time when the system is started at the next moment to provide a more accurate initialization position for the moving autonomous driving vehicle and solve the problem of poor RTK signal in some closed areas.

[0112] In the embodiment of the present application, the positioning system obtains the point cloud of the area where the positioning system is located at the current moment; matches the point cloud with the map to determine the target area that matches the point cloud in the map; determines the map point set of the target area in the map; for each data point in the point cloud, searches the map point set for the nearest map point and establishes a corresponding relationship; based on the corresponding relationship, determines the target location point that matches the point cloud in the map point set. In the above manner, the positioning method of the present application uses the point cloud to match the map, determines the target area, searches for the nearest target location point based on the target area, and combines the two-layer matching process to achieve stable and accurate initialization position positioning at the current moment.

[0113] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0114] In order to implement the positioning method of the above embodiment, the present application also proposes a positioning system, for details, please refer to Figure 4 , Figure 4 It is a structural diagram of an embodiment of a positioning system provided by the present application.

[0115] like Figure 4 As shown, the positioning system 400 provided in the present application includes a point cloud acquisition module 41 , a point cloud matching module 42 and a position positioning module 43 .

[0116] The point cloud acquisition module 41 is used to acquire the point cloud of the area where the positioning system is located at the current moment.

[0117] The point cloud matching module 42 is used to match the point cloud with the map to determine a target area in the map that matches the point cloud; determine a map point set of the target area in the map; for each data point in the point cloud, search for the nearest map point in the map point set and establish a corresponding relationship.

[0118] The position positioning module 43 is used to determine the target position point matching the point cloud in the map point set based on the corresponding relationship.

[0119] To implement the positioning method of the above embodiment, this application also proposes another positioning system, please refer to Figure 5 , Figure 5 It is a structural schematic diagram of another embodiment of the positioning system provided by the present application.

[0120] The positioning system 500 of the embodiment of the present application includes a memory 51 and a processor 52 , wherein the memory 51 and the processor 52 are coupled.

[0121] The memory 51 is used to store program data, and the processor 52 is used to execute the program data to implement the positioning method described in the above embodiment.

[0122] In this embodiment, the processor 52 may also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip having signal processing capabilities. The processor 52 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 52 may also be any conventional processor, etc.

[0123] Furthermore, the positioning system 500 of the embodiment of the present application also includes a laser radar 53, wherein the laser radar 53 is connected to the processor 52, and is used to collect point cloud data and transmit the point cloud data to the processor 52.

[0124] To implement the positioning method of the above embodiment, the present application also provides a vehicle 600, for details, please refer to Figure 6 , Figure 6 It is a structural schematic diagram of a vehicle embodiment provided by the present application.

[0125] The vehicle 600 of the embodiment of the present application includes a positioning system 61, and the positioning method described in the above embodiment is implemented through the positioning system 61. The specific structure of the positioning system 61 is the same as that of the positioning system 500 described in the above embodiment, and will not be repeated here.

[0126] To implement the positioning method of the above embodiment, the present application also provides a computer-readable storage medium, such as Figure 7 As shown, the computer-readable storage medium 700 is used to store program data 71. When the program data 71 is executed by the processor, it is used to implement the positioning method described in the above embodiment.

[0127] The present application also provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to enable a computer to execute the positioning method as described in the embodiment of the present application. The computer program product may be a software installation package.

[0128] The positioning method described in the above embodiment of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0129] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A positioning method, It is characterized in that The positioning method comprises: Get the point cloud of the area where the positioning system is located at the current moment; Determine the pyramid level and determine the minimum step size; Determining an initial search step size according to the pyramid level and the minimum step size; According to the search step length, searching in the map for an area that meets a preset matching requirement with the point cloud as a target area; determining a set of map points of the target area in the map; For each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship; Based on the corresponding relationship, a target location point matching the point cloud is determined in the map point set.

2. The positioning method according to claim 1, It is characterized in that The step of searching, according to the search step, for an area in the map that meets a preset matching requirement with the point cloud as a target area comprises: Reducing the search step size to update the search step size; Based on the updated search step length, the target area and the neighboring areas of the target area are searched for an area that meets a preset matching requirement with the point cloud, so as to update the target area.

3. The positioning method according to claim 2, It is characterized in that The step of searching, based on the updated search step length, for an area in the target area and an area adjacent to the target area that meets a preset matching requirement with the point cloud to update the target area includes: Determining whether the updated search step size is a preset minimum step size; If yes, the target area corresponding to the current search step is confirmed as the final target area.

4. The positioning method according to claim 1, It is characterized in that The positioning method further includes: Obtaining the position based on real-time dynamic measurement technology; Determining a tolerance range based on the position and the accuracy of the real-time dynamic measurement technology; The initial search step is smaller than the tolerance range.

5. The positioning method according to claim 4, It is characterized in that The step of searching, according to the search step, for an area in the map that meets a preset matching requirement with the point cloud as a target area comprises: Based on the search step size, dividing the map into a plurality of search areas; Determining the number of matching points in each of the search areas that match the point cloud; The degree of matching between the search area and the point cloud is determined according to the ratio of the number of matching points to the total number of points in the search area.

6. The positioning method according to claim 1, It is characterized in that For each data point in the point cloud, searching for the nearest map point in the map point set and establishing a corresponding relationship includes: Establishing a binary tree with a set of map points within a preset range centered at the target location point in the map; For each data point in the point cloud, the nearest map point is searched in the binary tree and a corresponding relationship is established.

7. The positioning method according to claim 1 or 6, It is characterized in that Determining a target location point matching the point cloud in the map point set based on the corresponding relationship includes: Using the least square method to calculate each of the corresponding relationships to correct the target position point; A corrected target location point is determined in the map point set.

8. The positioning method according to claim 1, It is characterized in that After obtaining the point cloud of the area where the positioning system is located at the current moment, the positioning method further includes: identifying dynamic data points in the point cloud; The dynamic data points are deleted from the point cloud, and the deleted point cloud is matched with the map.

9. The positioning method according to claim 8, It is characterized in that The identifying the dynamic data points in the point cloud comprises: Input the point cloud into a preset recognition network model to obtain a label for each data point in the point cloud; The data points labeled as dynamic objects are identified as dynamic data points.

10. A positioning system, It is characterized in that The positioning system includes a processor and a memory, wherein program data is stored in the memory, and the processor is used to execute the program data to implement the method according to any one of claims 1-9.

11. A vehicle, It is characterized in that The vehicle comprises the positioning system of claim 10.

12. A computer-readable storage medium, It is characterized in that The computer-readable storage medium is used to store program data, and when the program data is executed by a processor, it is used to implement the method according to any one of claims 1 to 9.

Images