WO2021051361A1

WO2021051361A1 - High-precision map positioning method and system, platform and computer-readable storage medium

Info

Publication number: WO2021051361A1
Application number: PCT/CN2019/106792
Authority: WO
Inventors: 钟阳; 周游; 孙路; 江灿森
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2019-09-19
Filing date: 2019-09-19
Publication date: 2021-03-25
Also published as: CN112154355A; CN112154355B

Abstract

Provided are a high-precision map positioning method and system, a platform, and a computer-readable storage medium. The method comprises: acquiring an offline high-precision map, and establishing an online point cloud map; performing rasterization processing on the online point cloud map to obtain a plurality of online raster maps; and performing positioning on a mobile platform according to height intervals in the plurality of online raster maps and height intervals in the offline high-precision map. According to the method, the positioning accuracy is improved.

Description

High-precision map positioning method, system, platform and computer readable storage medium

Technical field

This application relates to the technical field of high-precision maps, and in particular to a high-precision map positioning method, system, platform, and computer-readable storage medium.

Background technique

With the development of map technology, high-precision maps have begun to be used in more and more fields. Generally, high-precision map positioning is to obtain the surrounding environment and some characteristic information of the surrounding environment through the sensors mounted on the mobile platform, and then match these characteristic information with the characteristic information in the high-precision map, so as to obtain the mobile platform at high altitude. Positioning in the accuracy map.

However, because this feature matching is more dependent on the richness of the surrounding environment, it may not be able to locate in some scenes with sparse features or lack of obvious features; and for some environments where there are repetitive features, errors may occur. The matching result. Therefore, how to improve the accuracy and stability of the high-precision map positioning result is an urgent problem to be solved at present.

Summary of the invention

Based on this, this application provides a high-precision map positioning method, system, platform, and computer-readable storage medium, aiming to improve the accuracy and stability of the high-precision map positioning result.

In the first aspect, this application provides a high-precision map positioning method, including:

Acquiring an offline high-precision map and establishing an online point cloud map, where the offline high-precision map includes a plurality of first height intervals;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result, wherein, The online grid map includes a plurality of second height intervals;

According to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, the movable platform is positioned to obtain the The first positioning result of the mobile platform.

In the second aspect, this application also provides a high-precision map positioning method, including:

Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result. Online raster map includes online complete height layer and online non-ground height layer;

Positioning the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result; and

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result;

According to the first positioning result and the second positioning result, the target positioning result of the movable platform is determined.

In a third aspect, the present application also provides a driving system, the driving system includes a lidar, a memory, and a processor; the memory is used to store a computer program;

The processor is configured to execute the computer program and, when executing the computer program, implement the following steps:

Acquiring an offline high-precision map, and establishing an online point cloud map through the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes a plurality of first height intervals;

According to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, the movable platform is positioned to obtain the The first positioning result of the mobile platform.

In a fourth aspect, the present application also provides a driving system, the driving system includes a lidar, a memory, and a processor; the memory is used to store a computer program;

Acquiring an offline high-precision map, and establishing an online point cloud map from the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer;

In a fifth aspect, the present application also provides a movable platform, the movable platform includes a lidar, a memory, and a processor; the memory is used to store a computer program;

In a sixth aspect, the present application also provides a movable platform, the movable platform includes a lidar, a memory, and a processor; the memory is used to store a computer program;

In a seventh aspect, the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor achieves the above-mentioned high precision Map positioning method.

The embodiments of the application provide a high-precision map positioning method, system, platform, and computer-readable storage medium. The online point cloud map is rasterized through each candidate positioning result in the candidate positioning result set to obtain each The online raster map corresponding to the candidate positioning results, through the multiple height intervals in the offline high-precision map and the multiple height intervals in each online raster map, to locate the movable platform, so that some features are sparse or lacking. The mobile platform can also be positioned in the scene with obvious characteristics, which can improve the accuracy and stability of the high-precision map positioning result.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the application.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of the steps of a high-precision map positioning method provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of sub-steps of the high-precision map positioning method in FIG. 1;

3 is a schematic flowchart of steps of another high-precision map positioning method provided by an embodiment of the present application;

4 is a schematic flowchart of sub-steps of the high-precision map positioning method in FIG. 3;

5 is a schematic flowchart of steps of another high-precision map positioning method provided by an embodiment of the present application;

FIG. 6 is a schematic flowchart of the steps of another high-precision map positioning method provided by an embodiment of the present application;

FIG. 7 is a schematic block diagram of the structure of a driving system provided by an embodiment of the present application;

FIG. 8 is a schematic block diagram of the structure of a movable platform provided by an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The flowchart shown in the drawings is only an example, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of steps of a high-precision map positioning method according to an embodiment of the present application. The high-precision map positioning method can be applied to a movable platform or a driving system. Among them, movable platforms include vehicles and aircraft. Aircraft include unmanned aerial vehicles and manned aerial vehicles. Vehicles include manned and unmanned vehicles. Unmanned aerial vehicles include rotary-wing unmanned aerial vehicles, such as four-rotor unmanned aerial vehicles and six-rotor unmanned aerial vehicles. A human aircraft, an eight-rotor unmanned aerial vehicle, or a fixed-wing unmanned aerial vehicle, or a combination of a rotor-type and a fixed-wing unmanned aerial vehicle, is not limited here.

Specifically, as shown in FIG. 1, the high-precision map positioning method includes steps S101 to S103.

S101. Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes a plurality of first height intervals.

Among them, the mobile platform uses high-precision lidar to collect three-dimensional point cloud data from the traveled area, and uses high-precision inertial navigation system and point cloud registration algorithm to process the collected three-dimensional point cloud data to generate offline high Accuracy map. Or, use high-precision lidar to collect three-dimensional point cloud data from the traveled area, use the Inertial Measurement Unit (IMU) to collect the attitude data of the movable platform, and use the Global Positioning System (GPS) Collect the position data of the movable platform, then correct the collected 3D point cloud data based on the posture data and the position data, and generate an offline high-precision map based on the corrected 3D point cloud data.

The mobile platform acquires offline high-precision maps during the movement process, collects real-time 3D point cloud data of objects around the mobile platform through lidar, and establishes an online point cloud map based on the real-time collected 3D point cloud data. Among them, the lidar can determine the three-dimensional point cloud data of the object based on the distance between the laser emission point and the reflection point of the emitted laser light on the object, and the emission direction of the laser at the laser emission point. The three-dimensional point cloud data of objects around the movable platform includes the distance between the object and the movable platform, the angle between the object and the movable platform, and the three-dimensional coordinates of the object.

Wherein, the offline high-precision map includes a plurality of first height intervals, the height of each grid in the offline high-precision map is located in the corresponding first height interval, and the first height interval is performed according to the height of the three-dimensional point cloud. According to the division, the height interval value of each first height interval may be the same or different, and the height interval value is the height difference between the two end points of the height interval. It should be noted that the height interval value and the number of height intervals can be set based on actual conditions, which is not specifically limited in this application. For example, if the height is 26 meters, the divided first height intervals are [0, 1), [1, 5), [5, 9), [9, 14), [14, 18), [18, 22) and [22, 26] total 7 first height intervals.

S102. Determine a candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set to obtain an online raster map corresponding to each candidate positioning result. Wherein, the online grid map includes a plurality of second height intervals.

The mobile platform determines the candidate positioning result set, and performs rasterization processing on the online point cloud map according to each candidate positioning result, and obtains the online grid map corresponding to each candidate positioning result, that is, in the online point cloud map Mark each candidate positioning result in the candidate positioning result set, and perform rasterization processing on the map area around each marked candidate positioning result, so that a grid map corresponding to each candidate positioning result can be obtained.

Wherein, the online grid map includes a plurality of second height intervals, the height of each grid in the online grid map is located in the corresponding second height interval, and the second height interval is divided according to the height of the three-dimensional point cloud Obtained, the height interval value of each second height interval may be the same or different, and the height interval value is the height difference value between the two end points of the height interval. It should be noted that the height interval value and the number of height intervals can be set based on actual conditions, which is not specifically limited in this application. For example, if the height is 26 meters, the divided second height intervals are [0, 1), [1, 5), [5, 9), [9, 14), [14, 18), [18, 22) and [22, 26] total 7 second height intervals.

It should be noted that the number of the first height interval and the second height interval may be the same or different. The first height interval and the second height interval have a corresponding relationship, and there is a corresponding relationship between the first height interval and the second height interval. The two ends of the interval are the same, which is not specifically limited in this application.

In an embodiment, the method for determining the candidate positioning result set is specifically: obtaining the current position data and current attitude data of the movable platform; determining the candidate position set according to the current position data; determining the candidate position set according to the current attitude data and the preset attitude error value Pose set: Determine the candidate positioning result set according to the candidate position set and the candidate pose set. Among them, the current position data of the movable platform is the position data output by the positioning system of the movable platform at the current moment, and the current posture data of the movable platform is the posture data output by the inertial measurement unit of the movable platform at the current moment. The position data includes the geographic coordinates of the movable platform, and the attitude data includes the pitch angle, roll angle, and yaw angle of the movable platform.

In an embodiment, the method of determining the candidate location set according to the current location data is specifically as follows: the movable platform determines the change trend of the current location data, and determines the candidate location set according to the change trend of the current location data. Specifically, the change trend can be characterized by the gradient value and gradient direction of the current position data, that is, a preset unit gradient is used to obtain a preset number of candidate gradient values along the gradient direction based on the gradient value, and determine The position information corresponding to each candidate gradient value is used to determine the candidate position set. It should be noted that the preset unit gradient and the preset number can be set based on actual conditions, which is not specifically limited in this application.

In an embodiment, the method for determining the candidate pose set may be: calculating the difference between the pose angle in the current pose data and the preset pose error value, and calculating the sum of the pose angle in the current pose data and the preset pose error value , And then based on the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value, determine the candidate attitude set, that is, the attitude angle and the preset attitude error The difference of is one end point, and the sum of the attitude angle and the preset attitude error value is the other end point to obtain the candidate attitude angle range, and obtain multiple candidate attitude angles from the candidate attitude angle range in the preset unit attitude angle , So as to form a set of candidate poses. It should be noted that the above-mentioned preset attitude error value and unit attitude angle can be set based on actual conditions, which is not specifically limited in this application. The current pose data and preset pose error values can quickly and accurately determine the candidate pose set.

In an embodiment, the method for determining the candidate pose set may also be: the movable platform determines the position coordinates of the movable platform in the offline high-precision map according to the current position data, that is, obtains the position coordinates of the movable platform from the current position data. Geographic location coordinates, and mark the geographic location coordinates in the offline high-precision map, and then obtain the location coordinates of objects around the geographic location coordinates in the offline high-precision map, and based on the location coordinates of surrounding objects in the offline high-precision map, Determine the position coordinates of the movable platform in the offline high-precision map; determine the candidate position set according to the position coordinates and the preset position error value. The candidate position set can be quickly and accurately determined through the current position data and the preset position error value.

In an embodiment, according to the candidate position set and the candidate pose set, the method for determining the candidate positioning result set is specifically as follows: the movable platform selects one candidate position from the candidate position set each time to combine with each candidate pose in the candidate pose set, Until the candidate positions in the candidate position set are selected once, each candidate positioning result obtained by the collection and combination is used as the candidate positioning result set.

In an embodiment, the method for determining the candidate positioning result set may also be: obtaining the historical positioning result of the movable platform, and determining the candidate positioning result set according to the historical positioning result. Wherein, the historical positioning result is the positioning result determined by the movable platform at the last moment, and the last moment and the current moment are separated by a preset time. It should be noted that the aforementioned preset time can be set based on actual conditions, which is not specifically limited in this application.

Specifically, obtain the historical position coordinates and historical attitude angle from the historical positioning results; perform derivative processing on the historical position coordinates to determine the gradient value and the gradient direction of the historical position coordinates, and determine the candidate according to the gradient value and the gradient direction Position set, that is, a preset number of candidate gradient values are obtained along the gradient direction based on the gradient value based on the preset unit gradient, and the position information corresponding to each candidate gradient value is determined, thereby determining the candidate position set ；

Calculate the difference between the historical attitude angle and the preset attitude error value, and calculate the sum of the historical attitude angle and the preset attitude error value; take the difference between the historical attitude angle and the preset attitude error value as an endpoint, and use the historical attitude angle and The sum of the preset attitude error values is the other end point to obtain the candidate attitude angle range, and obtain multiple candidate attitude angles from the candidate attitude angle range in the preset unit attitude angle, thereby forming a candidate pose set;

According to the candidate position set and the candidate pose set, determine the candidate positioning result set, that is, each candidate position is selected from the candidate position set and combined with each candidate pose in the candidate pose set until the candidate positions in the candidate position set are selected once At this time, each candidate positioning result obtained by the collection and combination is used as a candidate positioning result set. It should be noted that the aforementioned preset unit gradient, preset number, preset attitude error value, and preset unit attitude angle can be set based on actual conditions, and this application does not specifically limit this.

S103. Position the movable platform according to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, to obtain all The first positioning result of the movable platform is described.

After the mobile platform determines the online grid map corresponding to each candidate positioning result, according to the multiple first height intervals in the offline high-precision map and the multiple second online grid maps corresponding to each candidate positioning result In the height interval, the movable platform is positioned, and the first positioning result of the movable platform is obtained. By positioning the movable platform through multiple first height intervals in the offline high-precision map and multiple second height intervals in each online raster map, accurate positioning results can be obtained, and the high-precision map positioning results can be improved Accuracy and stability.

In an embodiment, as shown in FIG. 2, step S103 specifically includes: sub-steps S1031 to S1032.

S1031, according to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, determine the corresponding position of each candidate positioning result Matching degree.

Specifically, determine the status comparison result between each second height interval in each online raster map and the corresponding first height interval in the offline high-precision map; statistics of the status comparison results in each online raster map are expected Set the number of the second height interval of the status comparison result, and use the status comparison result in each online grid map as the number of the second height interval of the preset status comparison result as the corresponding match of each candidate positioning result degree. Among them, the state of the first height interval and the second height interval includes an occupied state and an unoccupied state. There is a three-dimensional point cloud in the first height interval or the second height interval in the occupied state, and the first height interval in the unoccupied state Or there is no three-dimensional point cloud in the second height interval. Among them, the state comparison results include different states, all occupied states, and all non-occupied states. Optionally, the preset state comparison result is "all occupied states".

In an embodiment, the method for determining the matching degree corresponding to each candidate positioning result is specifically: determining each second height interval in each online non-ground height layer, and the corresponding second height interval in the offline non-ground height layer The state comparison result between a height interval; count the number of the state comparison results in each online non-ground height layer as the preset state comparison result in the second height interval; according to each online non-ground height layer The status comparison result is the number of the second height interval of the preset status comparison result, and the matching degree of each candidate positioning result is determined, that is, the status comparison result in each online non-ground height layer is the preset status comparison result The number of the second height interval is used as the matching degree of each candidate positioning result.

Wherein, the offline high-precision map includes an offline non-ground height layer, a plurality of first height intervals are located in an offline non-ground height layer, the online raster map includes an online non-ground height layer, and the plurality of second height intervals are located in an online non-ground height layer. Height layer. Wherein, the end point heights of the first height interval located in the offline non-ground height layer and the second height interval located in the online non-ground height layer are greater than or equal to the set height threshold, and the height threshold can be set based on actual conditions. This is not specifically limited. Optionally, if the height threshold is 1 meter, the height of 26 meters is divided, and the first height interval obtained is [1, 5), [5, 9), [9, 14), [14, 18), [18, 22) and [22, 26] total 6 second height intervals, then the height of 26 meters is divided, and the second height intervals obtained are [1, 5), [5, 9), [9, 14), [14, 18), [18, 22) and [22, 26] total 6 second height intervals.

In an embodiment, the method for determining the state comparison result between the first height interval and the corresponding second height interval is specifically: acquiring the first state identification information of each first height interval in the offline non-ground height layer and acquiring The second state identification information of each second height interval of each online non-ground height layer; according to the first state identification information and each second state identification information, each second state identification information in each online non-ground height layer is determined The height interval is the state comparison result with the corresponding first height interval in the offline non-ground height layer. Wherein, the first state identification information includes the state identifier corresponding to each first altitude interval, and the second state identification information includes the state identifier corresponding to each second altitude interval, the state identifier, and the state represented by the state identifier. It can be set based on actual conditions, which is not specifically limited in this application. Optionally, the height interval with a state identifier of 0 is in a non-occupied state, and the height interval with a state identifier of 1 is in an occupied state.

Specifically, the state identifier corresponding to each first altitude interval in the first state identification information is logically ANDed with the state identifier corresponding to the second altitude interval in the second state identification information, so as to obtain each online The state comparison result between each second height interval in the non-ground height layer and the corresponding first height interval in the offline non-ground height layer. For example, if the first height interval and the second height interval are both 7, and the first state identification information is 1010101, and the second state identification information is 0111101, then the logical AND processing of 1010101 and 0111101 is performed bitwise, and the result is 0010100. Then the state comparison results between the 7 second height intervals and the corresponding first height intervals are different states, different states, different states, all occupied states, different states, all occupied states, and different states.

S1032, according to the matching degree of each candidate positioning result, select one candidate positioning result from the candidate positioning result set as the first positioning result of the movable platform.

After determining the matching degree of each candidate positioning result, the movable platform determines the first positioning result of the movable platform from the candidate positioning result set according to the corresponding matching degree of each candidate positioning result, that is, the one with the highest matching degree. The candidate positioning result is used as the first positioning result of the movable platform.

In the high-precision map positioning method provided by the above-mentioned embodiment, the online point cloud map is rasterized through each candidate positioning result in the candidate positioning result set, and the raster map corresponding to each candidate positioning result is obtained. The multiple height intervals in the accuracy map and the multiple height intervals in each online raster map are used to locate the movable platform, so that the movable platform can also be located in some scenes with sparse features or lack of obvious features. It can improve the accuracy and stability of high-precision map positioning results.

Please refer to FIG. 3, which is a schematic flowchart of the steps of another high-precision map positioning method provided by an embodiment of the present application.

Specifically, as shown in FIG. 3, the high-precision map positioning method includes steps S201 to S205.

S201. Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes a plurality of first height intervals.

S202. Determine a candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online raster map corresponding to each candidate positioning result. Wherein, the online grid map includes a plurality of second height intervals.

S203. Position the movable platform according to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, to obtain all The first positioning result of the movable platform is described.

S204: Position the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, to obtain a second positioning result of the movable platform.

The movable platform positions the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, and obtains the second positioning result of the movable platform. Among them, the online raster map also includes an online complete height layer, the height of each raster in the online complete height layer is the average height of the three-dimensional point cloud in the raster; the offline high-precision map also includes the offline complete height Layer, the height of each grid in this offline complete height layer is the average height of the 3D point cloud in the grid.

In an embodiment, as shown in FIG. 4, step S204 specifically includes: sub-steps S2041 to S2042.

S2041, according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, determine the matching degree corresponding to each candidate positioning result.

Specifically, the mobile platform obtains the corresponding partial offline complete height layer of each online complete height layer from the offline complete height layer; according to the height of each grid in each online complete height layer and the corresponding partial offline The height of each grid in the complete height layer, determine the loss cost between each online complete height layer and the corresponding partial offline complete height layer, and compare each online complete height layer with the corresponding partial offline complete height The loss cost between layers is used as the matching degree of each candidate positioning result.

S2042, according to the matching degree of each candidate positioning result, select one candidate positioning result from the candidate positioning result set as the second positioning result of the movable platform.

After determining the respective matching degree of each candidate positioning result, according to the respective matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the second positioning result of the movable platform.

The method for determining the second positioning result is specifically as follows: the movable platform verifies the candidate positioning results in the candidate positioning result set according to the matching degree of each candidate positioning result; obtains each candidate positioning result that passes the verification Each corresponding degree of matching, and the candidate positioning result that passes the verification corresponding to the smallest degree of matching is used as the second positioning result of the movable platform. Among them, the verification method of the candidate positioning result is specifically: determining whether the matching degree of the candidate positioning result is less than or equal to the preset matching degree threshold; if the matching degree of the candidate positioning result is less than or equal to the preset matching degree threshold, then determining the The candidate positioning result passes the verification, and if the matching degree of the candidate positioning result is greater than the preset matching degree threshold, it is determined that the candidate positioning result fails the verification. It should be noted that the above-mentioned matching degree threshold can be set based on actual conditions, which is not specifically limited in this application. Using the candidate positioning result that has passed the verification corresponding to the smallest matching degree as the second positioning result of the movable platform can further improve the accuracy of the positioning result.

S205. Fusion of the first positioning result and the second positioning result to obtain a target positioning result of the movable platform.

After obtaining the first positioning result and the second positioning result of the movable platform, the movable platform merges the first positioning result and the second positioning result to obtain the target positioning result of the movable platform. By fusing the two positioning results, the accuracy and stability of the positioning results can be further improved.

In one embodiment, the movable platform obtains the degree of matching of the first positioning result and the degree of matching of the second positioning result; according to the degree of matching of the first positioning result and the degree of matching of the second positioning result, the degree of matching of the first positioning result is determined The first weight coefficient and the second weight coefficient of the second positioning result; the target positioning result of the movable platform is determined according to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient.

The method for determining the first weighting coefficient and the second weighting coefficient is specifically: normalizing the matching degree of the first positioning result and the matching degree of the second positioning result; according to the matching degree of the processed first positioning result Determine the total matching degree according to the degree of matching with the processed second positioning result; determine the first weight coefficient of the first positioning result according to the processed first positioning result’s matching degree and the total matching degree; according to the processed second The matching degree of the positioning result and the total matching degree determine the second weight coefficient of the second positioning result.

The method for determining the weight coefficient is specifically: calculating the percentage of the matching degree of the processed first positioning result to the total matching degree, and using this percentage as the first weighting coefficient of the first positioning result; calculating the processed second positioning result The matching degree of the result is the percentage of the total matching degree, and this percentage is used as the second weighting coefficient of the second positioning result.

The method for determining the target positioning result is specifically: calculating the product of the first positioning result and the first weight coefficient to obtain the first weighted positioning result; calculating the product of the second positioning result and the second weighting coefficient to obtain the second weighted positioning result ; Calculate the sum of the first weight positioning result and the second weight positioning result, and use the sum of the first weight positioning result and the second weight positioning result as the target positioning result of the movable platform.

In the high-precision map positioning method provided by the above-mentioned embodiment, the online point cloud map is rasterized through each candidate positioning result in the candidate positioning result set, and the raster map corresponding to each candidate positioning result is obtained. Multiple height intervals in the accuracy map and multiple height intervals in each online raster map are used to locate the movable platform, and at the same time through each candidate positioning result corresponding online full height layer and offline full height layer Positioning the movable platform and finally fusing the two positioning results can further improve the accuracy and stability of the positioning results.

Please refer to FIG. 5, which is a schematic flowchart of the steps of another high-precision map positioning method according to an embodiment of the present application.

Specifically, as shown in FIG. 5, the high-precision map positioning method includes steps S301 to S305.

S301. Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer.

Among them, the mobile platform uses high-precision lidar to collect three-dimensional point cloud data from the traveled area, and uses high-precision inertial navigation system and point cloud registration algorithm to process the collected three-dimensional point cloud data to generate offline high Accuracy map.

Among them, the offline high-precision map includes an offline complete height layer and an offline non-ground height layer. The height of each grid in the offline complete height layer is the average height of the three-dimensional point cloud in the grid. The offline non-ground height map The layer includes multiple height intervals, which are divided according to the height of the three-dimensional point cloud. The height interval value of each height interval can be the same or different. The height interval value is the height difference between the two ends of the height interval. . It should be noted that the height interval value and the number of height intervals can be set based on actual conditions, which is not specifically limited in this application. For example, if the height is 26 meters, the height intervals divided in the offline non-ground height layer are [1, 5), [5, 9), [9, 14), [14, 18), [18, 22 ) And [22,26] total 6 first height intervals.

S302. Determine a candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set to obtain an online raster map corresponding to each candidate positioning result. The online raster map includes an online complete height layer and an online non-ground height layer.

Among them, the online raster map includes the online full height layer and the online non-ground height layer. The height of each grid in the online full height layer is the average height of the three-dimensional point cloud in the grid. This online non-ground height layer It includes multiple height intervals, which are divided according to the height of the three-dimensional point cloud. The height interval value of each height interval may be the same or different. The height interval value is the height difference between the two end points of the height interval. It should be noted that the height interval value and the number of height intervals can be set based on actual conditions, which is not specifically limited in this application.

In an embodiment, the method for determining the candidate location set is specifically as follows: the movable platform determines the change trend of the current location data, and determines the candidate location set according to the change trend of the current location data. Specifically, the change trend can be characterized by the gradient value and gradient direction of the current position data, that is, a preset unit gradient is used to obtain a preset number of candidate gradient values along the gradient direction based on the gradient value, and determine The position information corresponding to each candidate gradient value is used to determine the candidate position set. It should be noted that the preset unit gradient and the preset number can be set based on actual conditions, which is not specifically limited in this application.

S303. Position the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result.

The movable platform locates the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain the first positioning result. Specifically, determine the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result; according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result For the matching degree between the height layers, the first positioning result is determined from the candidate positioning result set, that is, the candidate positioning result with the highest matching degree is used as the first positioning result of the movable platform. By matching the corresponding online non-ground height layer and offline non-ground height layer of each candidate positioning result to the point cloud, and according to the matching result, the positioning result of the movable platform can be obtained, which improves the accuracy and stability of the positioning result Sex.

Among them, the height interval in the offline non-ground height layer is recorded as the first height interval, and the height interval in the online non-ground height layer is recorded as the second height interval, and the first height interval is the same as the corresponding second height interval .

In an embodiment, the movable platform determines the status comparison results between each second height interval in each online non-ground height layer and the corresponding first height interval in the offline non-ground height layer; The state comparison result in the online non-ground height layer is the number of the second height interval of the preset state comparison result; the state comparison result in each online non-ground height layer is the second height interval of the preset state comparison result The number is used as the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result. Among them, the state of the first height interval and the second height interval includes an occupied state and an unoccupied state. There is a three-dimensional point cloud in the first height interval or the second height interval in the occupied state, and the first height interval in the unoccupied state Or there is no three-dimensional point cloud in the second height interval. Among them, the state comparison results include different states, all occupied states, and all non-occupied states. Optionally, the preset state comparison result is "all occupied states".

S304. Position the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result.

The movable platform positions the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, and obtains the second positioning result of the movable platform. Specifically, according to the online complete height layer and offline complete height layer corresponding to each candidate positioning result, the corresponding matching degree of each candidate positioning result is determined; according to the matching degree of each candidate positioning result, from the candidate The positioning result centrally determines the second positioning result.

In one embodiment, the mobile platform obtains the local offline complete height layer corresponding to each online complete height layer from the offline complete height layer; according to the height and correspondence of each grid in each online complete height layer The height of each grid in the local offline complete height layer, determine the loss cost between each online complete height layer and the corresponding local offline complete height layer, and compare each online complete height layer with the corresponding local The loss cost between offline complete height layers is used as the matching degree of each candidate positioning result.

S305. Determine a target positioning result of the movable platform according to the first positioning result and the second positioning result.

After determining the first positioning result and the second positioning result of the movable platform, the target positioning result of the movable platform is determined according to the first positioning result and the second positioning result. By fusing the two positioning results, the accuracy and stability of the positioning results can be further improved.

In the high-precision map positioning method provided by the above-mentioned embodiment, the online point cloud map is rasterized through each candidate positioning result in the candidate positioning result set, and the raster map corresponding to each candidate positioning result is obtained. The ground height layer and the online non-ground height layer in each raster map are used to locate the movable platform to obtain a positioning result. At the same time, through the offline complete height layer and the online complete height map in each raster map Layer, the movable platform is positioned, and another positioning result is obtained. Finally, the final positioning result of the movable platform is jointly determined by the two positioning results, so that the movable platform can also be tested in some scenes with sparse features or lack of obvious features. Positioning can improve the accuracy and stability of high-precision map positioning results.

Please refer to FIG. 6, which is a schematic flowchart of the steps of yet another high-precision map positioning method according to an embodiment of the present application.

Specifically, as shown in FIG. 6, the high-precision map positioning method includes steps S401 to S407.

S401. Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer.

The mobile platform acquires offline high-precision maps during the movement process, collects real-time 3D point cloud data of objects around the mobile platform through lidar, and establishes an online point cloud map based on the real-time collected 3D point cloud data.

Among them, the offline high-precision map includes an offline complete height layer and an offline non-ground height layer. The height of each grid in the offline complete height layer is the average height of the three-dimensional point cloud in the grid. The offline non-ground height map The layer includes multiple height intervals, which are divided according to the height of the three-dimensional point cloud. The height interval value of each height interval can be the same or different. The height interval value is the height difference between the two ends of the height interval. .

S402. Obtain a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time is separated from the current time by a preset time.

Specifically, the historical positioning result of the movable platform is acquired, and the historical positioning result is the positioning result determined by the movable platform at the previous time, and the previous time and the current time are separated by a preset time. It should be noted that the aforementioned preset time can be set based on actual conditions, which is not specifically limited in this application.

S403: Determine a candidate positioning result set according to the historical positioning result.

According to the candidate position set and the candidate pose set, determine the candidate positioning result set, that is, each candidate position is selected from the candidate position set and combined with each candidate pose in the candidate pose set until the candidate positions in the candidate position set are selected once At this time, each candidate positioning result obtained by the collection and combination is used as a candidate positioning result set.

It should be noted that the aforementioned preset unit gradient, preset number, preset attitude error value, and preset unit attitude angle can be set based on actual conditions, and this application does not specifically limit this.

In an embodiment, the method for determining the candidate positioning result set may be: obtaining historical position coordinates and historical attitude angles from the historical positioning results, and calculating the differences between the historical position coordinates and historical attitude angles and the preset positioning error values. And calculate the sum of the historical position coordinates and the historical attitude angle respectively with the preset positioning error value, and then determine the candidate coordinate set based on the difference and the sum of the historical position coordinates and the preset positioning error value, and based on the historical attitude angle and the preset positioning error The difference and the sum of the values determine the candidate pose set, and finally based on the candidate coordinate set and the candidate pose set, determine the candidate positioning result set. It should be noted that the above-mentioned preset positioning error value can be set based on actual conditions, which is not specifically limited in this application.

S404. Perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set to obtain an online raster map corresponding to each candidate positioning result, where the online raster map includes Online full height layer and online non-ground height layer.

The mobile platform rasterizes the online point cloud map according to each candidate positioning result, and obtains the online grid map corresponding to each candidate positioning result, that is, mark the candidate positioning result set in the online point cloud map For each candidate positioning result, rasterize the map area around each marked candidate positioning result to obtain a grid map corresponding to each candidate positioning result.

Among them, the online raster map includes the online full height layer and the online non-ground height layer. The height of each grid in the online full height layer is the average height of the three-dimensional point cloud in the grid. This online non-ground height layer It includes multiple height intervals, which are divided according to the height of the three-dimensional point cloud. The height interval value of each height interval may be the same or different. The height interval value is the height difference between the two end points of the height interval.

S405. Position the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result.

S406: Position the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result.

S407: Determine a target positioning result of the movable platform according to the first positioning result and the second positioning result.

The high-precision map positioning method provided in the foregoing embodiment can accurately determine the candidate positioning result set through historical positioning results and positioning error values, and perform an online point cloud map based on each candidate positioning result in the accurate candidate positioning result set. Rasterization process, get the raster map corresponding to each candidate positioning result, use the offline non-ground height layer and the online non-ground height layer in each raster map to locate the movable platform to obtain a positioning As a result, the mobile platform is positioned through the offline complete height layer and the online complete height layer in each raster map at the same time, and another positioning result is obtained. Finally, the final position of the movable platform is determined by the two positioning results. The positioning result makes it possible to locate the movable platform in some scenes with sparse features or lack of obvious features, which can improve the accuracy and stability of the high-precision map positioning result.

Please refer to FIG. 7, which is a schematic block diagram of a driving system provided by an embodiment of the present application. In one embodiment, the driving system includes an unmanned driving system and a manned driving system. Further, the driving system 500 includes a processor 501, a memory 502, and a lidar 503. The processor 501, the memory 502, and the lidar 503 are connected by a bus 504, such as an I2C (Inter-integrated Circuit) bus.

Specifically, the processor 501 may be a micro-controller unit (MCU), a central processing unit (CPU), a digital signal processor (Digital Signal Processor, DSP), or the like.

Specifically, the memory 502 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) disk, an optical disk, a U disk, or a mobile hard disk.

Specifically, the processor 501 and the memory 502 are the computing platform of the driving system, and the lidar 303 may be an external device of the driving system or an internal component of the driving system, which is not specifically limited in this application.

Wherein, the processor 501 is configured to run a computer program stored in the memory 502, and implement the steps of the high-precision map positioning method as described above when the computer program is executed.

It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the driving system described above can refer to the corresponding process in the above-mentioned high-precision map positioning method embodiment. No longer.

Please refer to FIG. 8, which is a schematic block diagram of a movable platform provided by an embodiment of the present application. The mobile platform 800 includes a processor 601, a memory 602, and a lidar 603. The processor 801, the memory 602, and the lidar 603 are connected by a bus 604, which is, for example, an I2C (Inter-integrated Circuit) bus. Among them, movable platforms include vehicles and aircraft, aircraft include unmanned aerial vehicles and manned aerial vehicles, vehicles include manned vehicles and unmanned vehicles, etc. Unmanned aerial vehicles include rotary-wing unmanned aerial vehicles, such as four-rotor unmanned aerial vehicles and hexarotors. An unmanned aerial vehicle, an eight-rotor unmanned aerial vehicle, or a fixed-wing unmanned aerial vehicle, or a combination of a rotor-type and a fixed-wing unmanned aerial vehicle, is not limited here.

Specifically, the processor 601 may be a micro-controller unit (MCU), a central processing unit (CPU), a digital signal processor (Digital Signal Processor, DSP), or the like.

Specifically, the memory 602 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) disk, an optical disk, a U disk, or a mobile hard disk.

Specifically, the processor 601 and the memory 602 are the computing platform of the driving system, and the lidar 603 may be an external device of the driving system or an internal component of the driving system, which is not specifically limited in this application.

Wherein, the processor 601 is configured to run a computer program stored in the memory 602, and implement the steps of the high-precision map positioning method as described above when the computer program is executed.

It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the mobile platform described above can refer to the corresponding process in the above-mentioned high-precision map positioning method embodiment. This will not be repeated here.

The embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement the foregoing implementation The steps of the high-precision map positioning method provided in the example.

The computer-readable storage medium may be the internal storage unit of the driving system or the movable platform described in any of the foregoing embodiments, for example, the hard disk or memory of the driving system or the movable platform. The computer-readable storage medium may also be an external storage device of the driving system or a removable platform, for example, a plug-in hard disk or a smart memory card (Smart Media Card, SMC) equipped on the driving system or the removable platform. , Secure Digital (SD) card, Flash Card (Flash Card), etc.

It should be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should also be understood that the term "and/or" used in the specification and appended claims of this application refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the scope of protection of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A high-precision map positioning method is characterized in that it includes:

Acquiring an offline high-precision map and establishing an online point cloud map, where the offline high-precision map includes a plurality of first height intervals;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result, wherein, The online grid map includes a plurality of second height intervals;

According to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, the movable platform is positioned to obtain the The first positioning result of the mobile platform.
The high-precision map positioning method according to claim 1, wherein the online grid map corresponding to each candidate positioning result according to the multiple first height intervals in the offline high-precision map Positioning the movable platform in a plurality of second height intervals to obtain the first positioning result of the movable platform includes:

According to the multiple first height intervals in the offline high-precision map and the multiple second height intervals in the online grid map corresponding to each candidate positioning result, the matching degree corresponding to each candidate positioning result is determined ；

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the first positioning result of the movable platform.
The high-precision map positioning method according to claim 2, wherein the offline high-precision map comprises an offline non-ground height layer, the plurality of first height intervals are located in the offline non-ground height layer, and the online The grid map includes an online non-ground height layer, and the plurality of second height intervals are located in the online non-ground height layer; according to the plurality of first height intervals in the offline high-precision map and each candidate positioning result The respective corresponding multiple second height intervals in the online grid map determine the matching degree corresponding to each candidate positioning result, including:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

According to the number of the second height intervals in each of the online non-ground height layers where the state comparison result is the preset state comparison result, the matching degree corresponding to each candidate positioning result is determined.
The high-precision map positioning method according to claim 3, wherein the determining each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layers The corresponding state comparison results between the first height intervals include:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to the first state identification information and each of the second state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layer. The state comparison result between the corresponding first height intervals.
The high-precision map positioning method according to any one of claims 1 to 4, wherein the online raster map further includes an online complete height layer, and the offline high-precision map further includes an offline complete height layer The positioning of the movable platform is performed according to the plurality of first height intervals in the offline high-precision map and the plurality of second height intervals in the online grid map corresponding to each candidate positioning result, to obtain After the first positioning result of the movable platform, it further includes:

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, to obtain a second positioning result of the movable platform;

The first positioning result and the second positioning result are merged to obtain the target positioning result of the movable platform.
The high-precision map positioning method according to claim 5, wherein the online complete height layer and the offline complete height layer corresponding to each candidate positioning result are performed on the movable platform Positioning to obtain the second positioning result of the movable platform includes:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the second positioning result of the movable platform.
The high-precision map positioning method according to claim 6, characterized in that, according to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the mobile platform The second positioning results include:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

A matching degree corresponding to each candidate positioning result that has passed the verification is acquired, and the candidate positioning result that has passed the verification corresponding to the smallest matching degree is taken as the second positioning result of the movable platform.
The high-precision map positioning method according to claim 5, wherein the fusing the first positioning result and the second positioning result to obtain the target positioning result of the movable platform comprises:

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The high-precision map positioning method according to claim 8, wherein the first positioning result of the first positioning result is determined according to the matching degree of the first positioning result and the matching degree of the second positioning result. The weight coefficient and the second weight coefficient of the second positioning result include:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The high-precision map positioning method according to any one of claims 1 to 4, wherein the determining a candidate positioning result set comprises:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The high-precision map positioning method according to claim 10, wherein the determining a candidate position set according to the current position data comprises:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The high-precision map positioning method according to claim 10, wherein the determining a candidate pose set according to the current pose data and a preset pose error value comprises:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The high-precision map positioning method according to any one of claims 1 to 4, wherein the determining a candidate positioning result set comprises:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A high-precision map positioning method is characterized in that it includes:

Obtain an offline high-precision map, and establish an online point cloud map, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result. Online raster map includes online complete height layer and online non-ground height layer;

Positioning the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result; and

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result;

According to the first positioning result and the second positioning result, the target positioning result of the movable platform is determined.
The high-precision map positioning method according to claim 14, wherein the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result are compared to the The mobile platform performs positioning and obtains the first positioning result, including:

Determining the degree of matching between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result;

According to the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, a first positioning result is determined from the candidate positioning result set.
The high-precision map positioning method according to claim 15, wherein the offline non-ground height layer includes a plurality of first height intervals, and the online non-ground height layer includes a plurality of second height intervals, so The first height interval is the same as the corresponding second height interval; the determining the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result includes:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

Use each of the numbers as the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result.
The high-precision map positioning method according to claim 16, wherein the determining each of the second height intervals in each of the online non-ground height layers differs from those in the offline non-ground height layers The corresponding state comparison results between the first height intervals include:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to each of the second state identification information and the first state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layers. The state comparison result between the corresponding first height intervals.
The high-precision map positioning method according to claim 14, wherein the mobile platform is positioned according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result To get the second positioning result, including:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree of each candidate positioning result, the second positioning result is determined from the candidate positioning result set.
The high-precision map positioning method according to claim 18, wherein the determining the second positioning result from the candidate positioning result set according to the corresponding matching degree of each candidate positioning result comprises:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

The matching degree corresponding to each candidate positioning result that passed the verification is acquired, and the candidate positioning result that passes the verification corresponding to the smallest matching degree is taken as the second positioning result.
The high-precision map positioning method according to any one of claims 14 to 19, wherein the target positioning result of the movable platform is determined according to the first positioning result and the second positioning result ,include:

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The high-precision map positioning method according to claim 20, wherein the first positioning result of the first positioning result is determined according to the matching degree of the first positioning result and the matching degree of the second positioning result. The weight coefficient and the second weight coefficient of the second positioning result include:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The high-precision map positioning method according to any one of claims 14 to 19, wherein the determining a candidate positioning result set comprises:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The high-precision map positioning method according to claim 22, wherein the determining a candidate position set according to the current position data comprises:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The high-precision map positioning method according to claim 22, wherein the determining a candidate pose set according to the current pose data and a preset pose error value comprises:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The high-precision map positioning method according to any one of claims 14 to 19, wherein the determining a candidate positioning result set comprises:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A driving system, characterized in that, the driving system includes a lidar, a memory, and a processor;

The memory is used to store a computer program;

The processor is configured to execute the computer program and, when executing the computer program, implement the following steps:

Acquiring an offline high-precision map, and establishing an online point cloud map through the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes a plurality of first height intervals;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result, wherein, The online grid map includes a plurality of second height intervals;

According to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, the movable platform is positioned to obtain the The first positioning result of the mobile platform.
The driving system according to claim 26, wherein the processor implements the multiple second height intervals in the online grid map corresponding to each candidate positioning result and the offline high-precision map. The multiple first height intervals of the mobile platform are positioned, and when the first positioning result of the mobile platform is obtained, it is used to realize:

According to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, the matching degree corresponding to each candidate positioning result is determined ；

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the first positioning result of the movable platform.
The driving system according to claim 27, wherein the offline high-precision map comprises an offline non-ground height layer, the plurality of first height intervals are located in the offline non-ground height layer, and the online grid map Including an online non-ground height layer, the multiple second height intervals are located in the online non-ground height layer; the processor implements multiple second height intervals in the online grid map corresponding to each candidate positioning result. The height interval and the multiple first height intervals in the offline high-precision map are used to determine the matching degree corresponding to each candidate positioning result to achieve:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

According to the number of the second height intervals in each of the online non-ground height layers where the state comparison result is the preset state comparison result, the matching degree corresponding to each candidate positioning result is determined.
The driving system according to claim 27, wherein the processor is configured to determine that each of the second height intervals in each of the online non-ground height layers is different from those in the offline non-ground height layers. When the corresponding state comparison results between the first height intervals are used to realize:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to the first state identification information and each of the second state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layer. The state comparison result between the corresponding first height intervals.
The driving system according to any one of claims 26 to 29, wherein the online raster map further includes an online complete height layer, and the offline high-precision map further includes an offline complete height layer; The processor realizes the positioning of the movable platform according to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, to obtain After the first positioning result of the movable platform, it is also used to achieve:

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, to obtain a second positioning result of the movable platform;

The first positioning result and the second positioning result are merged to obtain the target positioning result of the movable platform.
The driving system according to claim 30, wherein the processor realizes that the online complete height layer and the offline complete height layer corresponding to each candidate positioning result are performed on the movable platform. Positioning, when the second positioning result of the movable platform is obtained, it is used to realize:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the second positioning result of the movable platform.
The driving system according to claim 31, wherein the processor realizes that according to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the mobile platform's When the second positioning result is used, it is used to achieve:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

A matching degree corresponding to each candidate positioning result that has passed the verification is acquired, and the candidate positioning result that has passed the verification corresponding to the smallest matching degree is taken as the second positioning result of the movable platform.
The driving system according to claim 30, wherein the processor realizes the fusion of the first positioning result and the second positioning result to obtain the target positioning result of the movable platform, and is used to realize:

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The driving system according to claim 33, wherein the processor realizes that the first positioning result of the first positioning result is determined according to the matching degree of the first positioning result and the matching degree of the second positioning result. The weight coefficient and the second weight coefficient of the second positioning result are used to realize:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The driving system according to any one of claims 26 to 29, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The driving system according to claim 35, wherein the processor realizes the determination of a candidate position set according to the current position data to realize:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The driving system according to claim 35, wherein said determining a candidate posture set according to the current posture data and a preset posture error value is used to achieve:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The driving system according to any one of claims 26 to 29, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A driving system, characterized in that, the driving system includes a lidar, a memory, and a processor;

The memory is used to store a computer program;

The processor is configured to execute the computer program and, when executing the computer program, implement the following steps:

Acquiring an offline high-precision map, and establishing an online point cloud map from the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result. Online raster map includes online complete height layer and online non-ground height layer;

Positioning the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result; and

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result;

According to the first positioning result and the second positioning result, the target positioning result of the movable platform is determined.
The driving system according to claim 39, wherein the processor realizes that according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, the The mobile platform performs positioning and obtains the first positioning result, which is used to achieve:

Determining the degree of matching between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result;

According to the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, a first positioning result is determined from the candidate positioning result set.
The driving system according to claim 40, wherein the offline non-ground height layer includes a plurality of first height intervals, the online non-ground height layer includes a plurality of second height intervals, and the first The height interval is the same as the corresponding second height interval; the processor realizes the determination of the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, for achieve:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

Use each of the numbers as the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result.
The driving system according to claim 41, wherein the processor is configured to determine that each of the second height intervals in each of the online non-ground height layers is different from those in the offline non-ground height layers. The corresponding state comparison results between the first height intervals are used to achieve:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to each of the second state identification information and the first state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layers. The state comparison result between the corresponding first height intervals.
The driving system according to claim 39, wherein the processor implements the positioning of the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result. To obtain the second positioning result, which is used to achieve:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree corresponding to each candidate positioning result, the second positioning result is determined from the candidate positioning result set.
The driving system according to claim 43, wherein the processor realizes that the second positioning result is determined from the candidate positioning result set according to the matching degree corresponding to each candidate positioning result, so as to realize:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

The matching degree corresponding to each candidate positioning result that passed the verification is acquired, and the candidate positioning result that passes the verification corresponding to the smallest matching degree is taken as the second positioning result.
The driving system according to any one of claims 39 to 44, wherein the processor is configured to determine the target positioning result of the movable platform according to the first positioning result and the second positioning result To achieve:

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The driving system according to claim 45, wherein the processor determines the first position of the first positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result. The weight coefficient and the second weight coefficient of the second positioning result are used to achieve:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The driving system according to any one of claims 39 to 44, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The driving system according to claim 47, wherein the processor realizes the determination of a candidate position set according to the current position data to realize:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The driving system according to claim 47, wherein the processor implements the determination of a candidate posture set according to the current posture data and a preset posture error value, so as to realize:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The driving system according to any one of claims 39 to 44, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A movable platform, characterized in that the movable platform includes a lidar, a memory and a processor;

The memory is used to store a computer program;

The processor is configured to execute the computer program and, when executing the computer program, implement the following steps:

Acquiring an offline high-precision map, and establishing an online point cloud map through the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes a plurality of first height intervals;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result, wherein, The online grid map includes a plurality of second height intervals;

According to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, the movable platform is positioned to obtain the The first positioning result of the mobile platform.
The mobile platform according to claim 51, wherein the processor implements the multiple second height intervals in the online grid map corresponding to each candidate positioning result and the offline high-precision map A plurality of first height intervals in, positioning the movable platform, and when the first positioning result of the movable platform is obtained, it is used to realize:

According to the multiple second height intervals in the online grid map and the multiple first height intervals in the offline high-precision map corresponding to each candidate positioning result, the matching degree corresponding to each candidate positioning result is determined ；

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the first positioning result of the movable platform.
The mobile platform according to claim 52, wherein the offline high-precision map comprises an offline non-ground height layer, the plurality of first height intervals are located in the offline non-ground height layer, and the online grid The map includes an online non-ground height layer, and the plurality of second height intervals are located in the online non-ground height layer; the processor implements a plurality of second height intervals in the online grid map corresponding to each candidate positioning result. The second height interval and the multiple first height intervals in the offline high-precision map are used to determine the matching degree of each candidate positioning result to achieve:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

According to the number of the second height intervals in each of the online non-ground height layers where the state comparison result is the preset state comparison result, the matching degree corresponding to each candidate positioning result is determined.
The mobile platform according to claim 53, wherein the processor is configured to determine that each of the second height intervals in each of the online non-ground height layers is different from the offline non-ground height layers When the state comparison result between the corresponding first height intervals in, it is used to realize:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to the first state identification information and each of the second state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layer. The state comparison result between the corresponding first height intervals.
The mobile platform according to any one of claims 51 to 54, wherein the online raster map further includes an online complete height layer, and the offline high-precision map further includes an offline complete height layer; The processor realizes the positioning of the movable platform according to the plurality of second height intervals in the online grid map and the plurality of first height intervals in the offline high-precision map corresponding to each candidate positioning result, After obtaining the first positioning result of the movable platform, it is also used to achieve:

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result, to obtain a second positioning result of the movable platform;

The first positioning result and the second positioning result are merged to obtain the target positioning result of the movable platform.
The mobile platform according to claim 55, wherein the processor realizes that the online complete height layer and the offline complete height layer corresponding to each of the candidate positioning results can be compared to the mobile platform. When positioning is performed, when the second positioning result of the movable platform is obtained, it is used to achieve:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree of each candidate positioning result, one candidate positioning result is selected from the candidate positioning result set as the second positioning result of the movable platform.
The mobile platform according to claim 56, wherein the processor realizes that according to the matching degree of each candidate positioning result, one candidate positioning result is selected as the movable platform from the candidate positioning result set. When the second positioning result is used to achieve:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

A matching degree corresponding to each candidate positioning result that has passed the verification is acquired, and the candidate positioning result that has passed the verification corresponding to the smallest matching degree is taken as the second positioning result of the movable platform.
The movable platform according to claim 55, wherein the processor realizes the fusion of the first positioning result and the second positioning result, and when the target positioning result of the movable platform is obtained, it is used to realize :

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The movable platform according to claim 58, wherein the processor realizes that the first positioning result is determined according to the matching degree of the first positioning result and the matching degree of the second positioning result. A weight coefficient and a second weight coefficient of the second positioning result are used to realize:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The mobile platform according to any one of claims 51 to 54, characterized in that the processor realizes the determination of a candidate positioning result set for realizing:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The mobile platform according to claim 60, wherein the processor realizes the determination of a candidate position set according to the current position data for realizing:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The mobile platform according to claim 60, wherein the candidate pose set is determined according to the current pose data and a preset pose error value to achieve:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The mobile platform according to any one of claims 51 to 54, characterized in that the processor realizes the determination of a candidate positioning result set for realizing:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A movable platform, characterized in that the movable platform includes a lidar, a memory and a processor;

The memory is used to store a computer program;

The processor is configured to execute the computer program and, when executing the computer program, implement the following steps:

Acquiring an offline high-precision map, and establishing an online point cloud map from the three-dimensional point cloud data collected by the lidar, where the offline high-precision map includes an offline complete height layer and an offline non-ground height layer;

Determine the candidate positioning result set, and perform rasterization processing on the online point cloud map according to each candidate positioning result in the candidate positioning result set, to obtain an online grid map corresponding to each candidate positioning result. Online raster map includes online complete height layer and online non-ground height layer;

Positioning the movable platform according to the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result to obtain a first positioning result; and

Positioning the movable platform according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result to obtain a second positioning result;

According to the first positioning result and the second positioning result, the target positioning result of the movable platform is determined.
The mobile platform according to claim 64, wherein the processor realizes that the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result are processed for the The movable platform performs positioning and obtains the first positioning result, which is used to achieve:

Determining the degree of matching between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result;

According to the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, a first positioning result is determined from the candidate positioning result set.
The mobile platform of claim 65, wherein the offline non-ground height layer includes a plurality of first height intervals, the online non-ground height layer includes a plurality of second height intervals, and the first A height interval is the same as the corresponding second height interval; the processor realizes the determination of the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result, using To achieve:

Determining a state comparison result between each of the second height intervals in each of the online non-ground height layers and the corresponding first height intervals in the offline non-ground height layers;

Counting the number of the second height intervals in each of the online non-ground height layers where the state comparison result is a preset state comparison result;

Use each of the numbers as the matching degree between the online non-ground height layer and the offline non-ground height layer corresponding to each candidate positioning result.
The mobile platform according to claim 66, wherein the processor is configured to determine that each of the second height intervals in each of the online non-ground height layers is different from the offline non-ground height layer The state comparison result between the corresponding first height intervals in, is used to realize:

Acquiring first state identification information of each first height interval in the offline non-ground height layer and acquiring second state identification information of each second height interval in each of the online non-ground height layer;

According to each of the second state identification information and the first state identification information, it is determined that each of the second height intervals in each of the online non-ground height layers is different from that in the offline non-ground height layers. The state comparison result between the corresponding first height intervals.
The mobile platform according to claim 64, wherein the processor realizes that the online complete height layer and the offline complete height layer corresponding to each candidate positioning result are performed on the mobile platform. Positioning to obtain the second positioning result, which is used to achieve:

Determine the matching degree corresponding to each candidate positioning result according to the online complete height layer and the offline complete height layer corresponding to each candidate positioning result;

According to the matching degree of each candidate positioning result, the second positioning result is determined from the candidate positioning result set.
The mobile platform according to claim 68, wherein the processor realizes that the second positioning result is determined from the candidate positioning result set according to the matching degree corresponding to each candidate positioning result, and is used to realize:

Verifying the candidate positioning results in the candidate positioning result set according to the matching degree corresponding to each candidate positioning result;

The matching degree corresponding to each candidate positioning result that passed the verification is acquired, and the candidate positioning result that passes the verification corresponding to the smallest matching degree is taken as the second positioning result.
The movable platform according to any one of claims 64 to 69, wherein the processor is configured to determine the target location of the movable platform according to the first positioning result and the second positioning result As a result, used to achieve:

Acquiring the matching degree of the first positioning result and acquiring the matching degree of the second positioning result;

Determining the first weight coefficient of the first positioning result and the second weight coefficient of the second positioning result according to the degree of matching of the first positioning result and the degree of matching of the second positioning result;

According to the first positioning result, the second positioning result, the first weight coefficient and the second weight coefficient, the target positioning result of the movable platform is determined.
The movable platform according to claim 70, wherein the processor is configured to determine the first positioning result of the first positioning result according to the matching degree of the first positioning result and the matching degree of the second positioning result. A weight coefficient and the second weight coefficient of the second positioning result are used to achieve:

Normalizing the matching degree of the first positioning result and the matching degree of the second positioning result;

Determine the overall matching degree according to the matching degree of the processed first positioning result and the matching degree of the processed second positioning result;

Determining the first weight coefficient of the first positioning result according to the processed matching degree of the first positioning result and the total matching degree;

The second weight coefficient of the second positioning result is determined according to the matching degree of the second positioning result after processing and the total matching degree.
The movable platform according to any one of claims 64 to 69, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Obtain the current position data and current posture data of the movable platform;

Determining a candidate position set according to the current position data;

Determining a candidate pose set according to the current pose data and a preset pose error value;

According to the candidate position set and the candidate pose set, a candidate positioning result set is determined.
The mobile platform according to claim 72, wherein the processor realizes the determination of a candidate position set according to the current position data for realizing:

The change trend of the current position data is determined, and a candidate position set is determined according to the change trend of the current position data.
The mobile platform according to claim 72, wherein the processor implements the determination of a candidate pose set according to the current pose data and a preset pose error value, and is used to implement:

Calculating the difference between the attitude angle in the current attitude data and the preset attitude error value, and calculating the sum of the attitude angle in the current attitude data and the preset attitude error value;

The candidate pose set is determined according to the difference between the attitude angle in the current attitude data and the preset attitude error value and the sum of the attitude angle in the current attitude data and the preset attitude error value.
The movable platform according to any one of claims 64 to 69, wherein the processor realizes the determination of a candidate positioning result set for realizing:

Acquiring a historical positioning result of the movable platform, where the historical positioning result is a positioning result determined by the movable platform at a previous time, and the previous time and the current time are separated by a preset time;

A candidate positioning result set is determined according to the historical positioning result.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes as described in any one of claims 1 to 25. The high-precision map positioning method described.