Method, device and system for generating high-precision map and vehicle

Abstract

The invention relates to the field of vehicle navigation, and relates to a high-precision map generation method, device and system and a vehicle, and the method comprises the steps: obtaining a target navigation path of a target object from navigation data; according to a target navigation point in the target navigation path, obtaining a sub high-precision map matched with the target navigation point from a total high-precision map; and splicing the sub-high-precision maps into a target high-precision map according to the sequence of the target navigation points. According to the method, the navigation point in the target navigation path of the target object in the navigation data is acquired, so that the sub-high-precision maps matched with the target navigation point are acquired from the total high-precision map according to the navigation point, and the sub-high-precision maps are spliced into the target high-precision map; since the matched sub-high-precision map can be directly obtained from the total high-precision map through the navigation points, the efficiency of obtaining the sub-high-precision map can be improved, and the efficiency of generating the target high-precision map is further improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle navigation technology, and specifically to a method, device, system and vehicle for generating a high-precision map. Background Art

[0002] The autonomous driving process is strongly dependent on high-precision maps. It is necessary to accurately judge the current lane based on high-precision maps and choose the appropriate position to change lanes in advance to avoid the vehicle missing the best position for road diversion and being unable to get off the road.

[0003] In the prior art, a high-precision map can be generated based on the navigation data on the vehicle. However, the steps for generating a high-precision map from navigation data in the prior art are complicated, and it is not possible to quickly and efficiently generate a high-precision map for autonomous driving, and the efficiency of generating a high-precision map is low. Summary of the invention

[0004] The present application provides a method, device, system and vehicle for generating a high-precision map to solve the problem of low efficiency in generating high-precision maps.

[0005] In a first aspect, the present application provides a method for generating a high-precision map, comprising: obtaining a target navigation path of a target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; according to the target navigation point in the target navigation path, obtaining a sub-high-precision map matching the target navigation point from the total high-precision map; splicing the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0006] In the second aspect, the present application provides a device for generating a high-precision map, comprising: a first acquisition module, used to obtain a target navigation path of a target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; a second acquisition module, used to obtain a sub-high-precision map matching the target navigation point in the target navigation path from the total high-precision map; a splicing module, used to splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0007] In the third aspect, the present application provides a high-precision map generation system, comprising: a first acquisition module, used to obtain a target navigation path of a target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; a second acquisition module, used to obtain a sub-high-precision map matching the target navigation point in the target navigation path from the total high-precision map; a splicing module, used to splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0008] In a fourth aspect, the present application provides a vehicle, comprising: a processing module, used to obtain a target navigation path of a target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; according to the target navigation point in the target navigation path, obtaining a sub-high-precision map matching the target navigation point from the total high-precision map; splicing the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0009] In the fifth aspect, the present application provides a high-precision map generation device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: obtain a target navigation path of the target object from the navigation data, wherein the target navigation path is a path for navigating the target object; according to the target navigation point in the target navigation path, obtain a sub-high-precision map matching the target navigation point from the total high-precision map; splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0010] In a sixth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the method for generating a high-precision map as described in any one of the above items of the present application.

[0011] Beneficial effects of this application:

[0012] The present application obtains the navigation points in the target navigation path of the target object in the navigation data, and then obtains the sub-high-precision map that matches the target navigation point from the total high-precision map according to the navigation point, and splices them into a target high-precision map. Since the matching sub-high-precision map can be directly obtained from the total high-precision map through the navigation point, the efficiency of obtaining the sub-high-precision map can be improved, and the efficiency of generating the target high-precision map can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart of a method for generating a high-precision map of the present application;

[0014] Figure 2 A flowchart of obtaining a target navigation path for the method for generating a high-precision map of the present application;

[0015] Figure 3 A schematic diagram of determining a target navigation path for the method for generating a high-precision map of the present application;

[0016] Figure 4 A flowchart of obtaining a sub-high-precision map in the method for generating a high-precision map of the present application;

[0017] Figure 5 Another flowchart of obtaining a sub-high-precision map of the method for generating a high-precision map of the present application;

[0018] Figure 6 A schematic diagram of obtaining a sub-high-precision map in the method for generating a high-precision map of the present application;

[0019] Figure 7 A flowchart of determining a target high-precision map in the method for generating a high-precision map of the present application;

[0020] Figure 8 A schematic diagram of determining a heading angle in a method for generating a high-precision map of the present application;

[0021] Fig. 9 A schematic diagram of splicing sub-high-precision map segments in the method for generating a high-precision map of the present application;

[0022] Fig.10 A flowchart of a method for generating a high-precision map of the present application;

[0023] Fig.11 A schematic diagram of traversing available navigation points for the method for generating a high-precision map of the present application;

[0024] Fig.12 A schematic diagram of the loop phenomenon of the method for generating a high-precision map of the present application;

[0025] Fig.13A schematic diagram of a device for generating a high-precision map for the present application. DETAILED DESCRIPTION

[0026] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0027] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0028] For ease of description, spatial relative terms may be used herein to describe the relative positional relationship or movement of one element or feature relative to another element or feature as shown in the figure, such as "inside", "outside", "inner side", "outer side", "below", "below", "above", "above", "front", "back", etc. Such spatial relative terms are intended to include different orientations of the device in use or operation in addition to the orientation depicted in the figure. For example, if the device in the figure undergoes a position flip or a change in posture or a change in motion state, then these directional indications will also change accordingly, for example: an element described as "below other elements or features" or "below other elements or features" will subsequently be oriented as "above other elements or features" or "above other elements or features". Therefore, the example term "below..." can include both upper and lower orientations. The device can be oriented otherwise (rotated 90 degrees or in other directions) and the spatial relative descriptors used herein are interpreted accordingly.

[0029] In order to solve the technical problem of low efficiency in generating high-precision maps in the prior art, the present application provides a method, device, system and vehicle for generating high-precision maps, which improve the efficiency in generating high-precision maps.

[0030] Figure 1 This is a flow chart of a method for generating a high-precision map provided in an embodiment of the present application. It includes:

[0031] S101, obtaining a target navigation path of a target object from navigation data, wherein the target navigation path is a path for navigating the target object;

[0032] S102, according to the target navigation point in the target navigation path, obtaining a sub-high-precision map matching the target navigation point from the total high-precision map;

[0033] S103, stitching the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0034] The above-mentioned high-precision map generation method can be applied during the driving process. During the driving process, a target high-precision map of the target navigation path in the navigation data is generated, so as to use the target high-precision map to assist the user in driving or automatic driving.

[0035] The high-precision map in this embodiment may be a high-precision map used in the process of autonomous driving, assisted driving or manual driving navigation. The navigation information in the high-precision map may be detailed to the lane level, thereby assisting the vehicle in lane-level navigation or lane changing, etc.

[0036] The navigation data in this embodiment may be data of a navigation system that comes with the vehicle, such as SD navigation data, and a digital card navigation (Secure Digital, SD) navigation may be a navigation method that uses an SD card to store navigation data. A navigation system or navigation software may be installed on the vehicle, and the navigation system or navigation software performs navigation according to the path data in the SD card. The path data stored in the SD card may be updated and deleted, and the SD card may be a pluggable card or a virtual card integrated into a circuit board of the navigation system.

[0037] The total high-precision map in this embodiment can be a high-precision map within a specific area or a specific range. The total meaning is that the coverage is large, and all high-precision maps involved in the user's navigation process are covered. For example, a high-precision map of roads across the country, a high-precision map of roads within a province, a high-precision map of a certain highway, a high-precision map of a certain ring road, etc. In this embodiment, the total high-precision map can be understood as a general map of high-precision maps covering some areas and routes. When high-precision maps of certain areas and routes are needed, they can be obtained from the total high-precision map.

[0038] In this embodiment, taking the driving scene as an example, during the driving process, the vehicle is on the road, and the vehicle can navigate to the user through the navigation data and navigation system in the SD card. The user enters the end point, which constitutes the user's current position or the navigation path from the starting point to the end point selected by the user. In the driving process, the path from the starting point to the end point of the user can be determined from the navigation data, that is, the path for navigating the user. And in this path, the target navigation path can be determined. The target navigation path can be a path from the starting point to the end point, or it can be a section of the path from the starting point to the end point. For example, the target navigation path can be a path two kilometers forward from the current position of the user's vehicle. Since the vehicle is driving forward, the path two kilometers forward is used as the target navigation path, and a high-precision map of the target two kilometers forward can be generated for the vehicle to assist the vehicle in driving. The choice of two kilometers forward is because the calculation amount of choosing a path that is too far away is large, and the vehicle has not yet driven to such a far position, so there is no need to process data that is too far away. As the driving process approaches, it can be processed again. Alternatively, the user can anticipate entering autonomous driving mode in two minutes and need to use a high-precision map. In this case, the user can estimate that the vehicle will reach a point four kilometers behind the current location in two minutes (the value is only an estimated distance and does not constitute a limitation). In this case, the navigation path from the fourth to sixth kilometers behind the current location can be determined as the target navigation path, and the target high-precision map of the target navigation path can be calculated.

[0039] For the determined target navigation path, navigation data also carries navigation points, which are marking points in the target navigation path and are used to mark different locations. For example, if the target navigation path is two kilometers long, starting from the starting point, there is a navigation point every 100 meters (the navigation point may be used to measure distance, and may be a position corresponding to a road sign on the side of the road, and the function is not limited).

[0040] For the navigation points in the target navigation path, each navigation point corresponds to a position in the target navigation path. Based on the navigation point, the corresponding position is searched in the total high-precision map, and when the corresponding position is found from the total high-precision map, a high-precision map in the vicinity of the corresponding position is obtained as a sub-high-precision map. In other words, for each navigation point in the target navigation path, the corresponding position is determined from the total high-precision map, and a high-precision map nearby is obtained. Then for the target navigation path, multiple corresponding sub-high-precision maps are obtained, and the target high-precision map can be obtained by splicing multiple sub-high-precision maps.

[0041] Take an example to illustrate that when a user is driving on the road, the automatic driving or assisted driving function can be turned on. At this time, the system can determine from the user's navigation data that the user is navigating from position 1 to position 2, and the path from position 1 to position 2 is the navigation path. From the navigation path, the two-kilometer path from the user's current position is determined as the target navigation path, and a target high-precision map of the target navigation path is generated to assist the user in driving or automatic driving. For the target navigation path, multiple navigation points are obtained, and each navigation point determines the corresponding position from the total high-precision map, and a high-precision map near the corresponding position is obtained as a sub-high-precision map. Then, after splicing the sub-high-precision maps, a target high-precision map corresponding to the target navigation path is generated, and the target high-precision map is used to assist the user in driving or automatic driving. When the user drives a specific distance, such as one kilometer, the vehicle continues to determine the target navigation path and generate a target high-precision map. At this time, the two-kilometer path after the current position of the user when he has traveled one kilometer can be used as the target navigation path, or the two-kilometer path after the last determined target navigation path can be used as the target navigation path, so that as the user moves forward, the target high-precision map of the subsequent road section is continuously generated.

[0042] In one example, if Figure 2 As shown, the above step S101 of acquiring the target navigation path of the target object from the navigation data may include:

[0043] S201, determining a navigation path with the location of the target object in the navigation data as a starting point and the destination of the target object as an end point;

[0044] S202, starting from the starting point, traversing the target distance along the navigation path toward the end point;

[0045] S203: Determine a path corresponding to the target distance in the navigation path as the target navigation path.

[0046] In this embodiment, the above-mentioned target distance can be two kilometers in the above example, or other values. The larger the value, the greater the amount of calculation, and the smaller the value, the smaller the amount of calculation. This value can be determined according to the vehicle speed. Because if the vehicle speed is fast and the value is small, the user has already driven through the road section before obtaining the target high-precision map, and it will not play an auxiliary role. Therefore, a suitable value can be determined according to the vehicle speed. For example, after determination, the value is two kilometers in the above example. When determining the target navigation path, you can start from the current position of the vehicle and traverse backward for two kilometers, and use the two kilometers backward from the current position on the navigation path as the target navigation path.

[0047] In addition, you can also traverse a certain distance from the current position of the vehicle to the path that the vehicle has traveled, such as traversing 100 meters, and then traverse two kilometers backward from the current position of the vehicle, recording a total distance of 2100 meters. The purpose of traversing 100 meters forward is to compare the path calculated this time with the last 100 meters of the path calculated last time to see whether they are on the same path.

[0048] In addition, you can also traverse two kilometers backward from the vehicle's future position as the target navigation path. Traversing backward from a certain position in the future is to consider that the vehicle does not currently use the target high-precision map, but estimates that it will use the target high-precision map at some point in the future, so preparation is made in advance.

[0049] like Figure 3 As shown, arrows represent roads and directions of roads (roads are abstracted as arrows), the solid car represents the current position of the vehicle, and the dotted car represents the destination of the vehicle. When determining the target navigation path, the entire navigation path 303 can be determined as the target navigation path, or two kilometers 301 after the current position of the vehicle can be determined as the target navigation path, or two kilometers 302 at a future time can be determined as the target navigation path.

[0050] Through this embodiment, since a suitable target navigation path can be determined according to the vehicle speed or according to the scene requirements, the flexibility and accuracy of determining the target navigation path are improved.

[0051] In one example, if Figure 4 As shown, the above step S102 obtains a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path, including:

[0052] S401, obtaining an original navigation point in a target navigation path;

[0053] S402: When the distance between two adjacent original navigation points is greater than a distance threshold, insert a first navigation point between the two adjacent original navigation points;

[0054] S403, determining the original navigation point and the first navigation point as target navigation points;

[0055] S404, obtaining a sub-high-precision map that matches the target navigation point from the total high-precision map.

[0056] In this embodiment, the target navigation point can be an original navigation point on the target navigation path, or a navigation point obtained by adding or subtracting the original navigation point. If the target navigation point is an original navigation point, the number of original navigation points included in the target navigation path is the number of original navigation points used to obtain the sub-high-precision map. If the original navigation points are to be added or subtracted, the distance between two navigation points in the original navigation points can be checked. The distance may be a fixed value or a variable value. For two original navigation points whose distance exceeds the distance threshold, the first navigation point is inserted in the middle so that the distance between the two navigation points is less than the distance threshold.

[0057] For example, there are three navigation points on the target navigation path, the distance between the first and second navigation points is 50 meters, the distance between the second and third navigation points is 20 meters, and the distance threshold is 25 meters. Then, you need to insert the first navigation point between the first and second navigation points so that the distance between two adjacent navigation points is less than 25 meters. Insert navigation points as evenly as possible.

[0058] If the distance between two original navigation points is too close, some of the navigation points can be deleted. For example, if there are 5 navigation points on the target navigation path, located at 10 meters, 50 meters, 60 meters, 65 meters, and 75 meters respectively, it can be found that the distance between the first and second navigation points is too far, and the first navigation point needs to be added, while the distance between the second to fifth navigation points is relatively close, so they can be deleted, such as deleting the third and fourth navigation points.

[0059] In this embodiment, whether deleting navigation points or adding navigation points, the purpose is to make the distance between target navigation points on the target navigation path less than the distance threshold and as large as possible. The distance threshold is less than the distance threshold because if the distance between two adjacent navigation points is too large, a complete sub-high-precision map may not be obtained. If the distance between the navigation points is too dense, a large number of repeated sub-high-precision maps will be obtained.

[0060] The method in this embodiment can be used to reasonably set the number and spacing of target navigation points, so that the obtained sub-high-precision map can be more reasonable, reduce repeated parts and cover the entire target navigation path.

[0061] In one example, if Figure 5 As shown, the above step S102 obtains a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path, including:

[0062] S501, performing the following processing on each of the target navigation points:

[0063] S502, taking the target navigation point as the center, obtaining a high-precision map within a preset range around the target navigation point from the total high-precision map;

[0064] S503: Determine the acquired high-precision map as a sub-high-precision map of the target navigation point.

[0065] In this embodiment, for navigation points on the target navigation path, the corresponding points can be found in the total high-precision map. If the corresponding point cannot be found, the corresponding sub-high-precision map may not be obtained. If the corresponding point can be found, the specific high-precision map around the corresponding point is determined as the sub-high-precision map corresponding to the point.

[0066] In this embodiment, for each navigation point, when a sub-high-precision map is obtained on the total high-precision map, a sub-high-precision map within a preset range is obtained. The shape of the range can be square, circular, or even irregular. For example, the surrounding sub-high-precision map is obtained based on the terrain of the map, and the terrain is irregular, so the range of the obtained sub-high-precision map is also irregular. Taking the circular range as an example, a map of a circle with a radius of 25 meters near the navigation point on the total high-precision map can be obtained as a sub-high-precision map.

[0067] like Figure 6 As shown, Figure 6 The left side of the figure is the target navigation path, which includes two target navigation points. Figure 6 The right side is the total high-precision map, in which the map 602 near the point corresponding to the target navigation point is obtained, and each circle 602 is a sub-high-precision map of a target navigation point.

[0068] In this embodiment, the range of obtaining the sub-high-precision map can be different for navigation points in different terrain locations, and the more complex the terrain, the larger the range can be. By obtaining the sub-high-precision map in a preset range near the navigation point, a sub-high-precision map matching the target navigation point is obtained, and by flexibly setting the range of obtaining the sub-high-precision map, the generated target high-precision map can be made more accurate.

[0069] In one example, if Figure 7 As shown, the above step S103 stitches the sub-high-precision maps into a target high-precision map in the order of the target navigation points, including:

[0070] S701, according to the relationship between the heading angle of the path in the sub-high-precision map and the heading angle of the target navigation point, the path in the sub-high-precision map is deleted to obtain a deleted sub-high-precision map;

[0071] S702, traversing the sub-high-precision maps in sequence according to the order of the target navigation points, and dividing the continuous sub-high-precision maps into a group of sub-high-precision map segments;

[0072] S703, splicing the sub-high-precision maps into segments to form a target high-precision map.

[0073] In this embodiment, when obtaining a sub-high-precision map, the sub-high-precision map can be deleted. The purpose of deletion is to delete the fork in the sub-high-precision map. There may be paths other than the user's navigation path in the sub-high-precision map, so deleting the redundant parts can make the remaining sub-high-precision map more accurate.

[0074] The above-mentioned heading angle can be the angle formed by the two directions by determining another direction, with the ground as a plane and one direction on the ground as the initial direction. For example, taking the north direction on the ground as the initial direction, when determining the heading angle of the path in the sub-high-precision map, the direction of the path is used as another direction to determine the angle between the two directions. When determining the heading angle of the target navigation point, the line connecting the two adjacent target navigation points is determined as another direction, thereby obtaining the heading angles of the two target navigation points (the obtained heading angle can also be used as the heading angle of the previous target navigation point, and the heading angle of the next target navigation point is determined by the direction of the line connecting the next target navigation point and the next next target navigation point).

[0075] By comparing the heading angle of the path in the sub-high-precision map with the heading angle of the target navigation point, the path with a large difference between the heading angle of the path and the heading angle of the target navigation point is deleted to obtain the remaining sub-high-precision map.

[0076] For the remaining sub-high-precision maps, they are traversed in order from front to back according to the target navigation points. The continuous sub-high-precision maps are divided into the same segment, while the non-continuous sub-high-precision maps are divided into different segments, so that the sub-high-precision maps are divided into multiple segments.

[0077] For example, Figure 8 Schematic diagram for determining the heading angle. Figure 8 In FIG. 8 , the line connecting the two target navigation points forms a direction 802, which forms an angle 803 with the initial direction 801. The angle 803 is the heading angle of the target navigation point.

[0078] Fig. 9 A schematic diagram of segmenting a sub-high-precision map. Fig. 9 In the figure, there is a fork in path 901. Taking the left fork as the target navigation path as an example, when obtaining the sub-high-precision map, the sub-high-precision map at position 902 is not obtained or is deleted, then the sub-high-precision map of the first part is divided into one segment, and the sub-high-precision maps of the latter part are each divided into one segment.

[0079] In one example, when splicing sub-high-precision maps after deleting part of the path, if there is only one next sub-high-precision map segment after the current sub-high-precision map segment, the next sub-high-precision map segment can be spliced ​​after the current sub-high-precision map segment; if there are multiple next sub-high-precision map segments after the current sub-high-precision map segment in parallel, the sub-high-precision map segment with the largest number of consecutive navigation points starting from the first navigation point in the sub-high-precision map segment is selected and spliced ​​after the current sub-high-precision map segment to obtain the target high-precision map.

[0080] In this embodiment, since the sub-high-precision map has been segmented in the above process, the relationship between different segments may be a sequential relationship or a parallel relationship. In this case, it is necessary to delete some of the segments in the parallel relationship and keep one segment to be spliced ​​after the previous segment. For example, Fig. 9 For the segments of the middle and rear two sub-high-precision maps, select the segment on the left and splice it after the previous sub-high-precision map segment.

[0081] In one example, after splicing the sub-high-precision map segments, in order to ensure the accuracy of the spliced ​​high-precision map, you can traverse a certain distance forward from the starting point of the spliced ​​high-precision map and traverse a certain distance backward from the end point of the spliced ​​high-precision map; when traversing forward to the end of the path, the end of the path is used as the new starting point; when traversing backward to the end of the path, the end of the path is used as the new end point; the high-precision map between the new starting point and the new end point is determined as the target high-precision map.

[0082] In this embodiment, if the sub-high-precision maps are spliced ​​into a high-precision map, the high-precision map contains the target navigation path. The target navigation path traverses forward a certain distance from the starting point, and if it traverses to the end of the path, the end of the path is used as the new starting point, and if it traverses backward from the end point to the end of the path, the end of the path is used as the new end point.

[0083] The path end point can be the intersection of two roads, a T-junction, or a turn, etc. Traversing forward and backward for a certain distance to see if there is a path end point is to allow a small section of the path to be incorporated into the target high-precision map, rather than leaving a small distance before or after the target high-precision map that is not covered after the target high-precision map is determined. If a new target navigation path is started, the accurate target high-precision map may not be determined because the path is too short. Therefore, using the path end points before and after as the new starting point and end point can cover a smaller path segment and improve the integrity and accuracy of the determined target high-precision map.

[0084] Fig.10is a flow chart of this embodiment. Fig.10 As shown, the following steps are included:

[0085] 1. Data preparation. According to the sequence of target navigation points in the target navigation path, determine a circle with the target navigation point as the center and 25M as the radius, and obtain all high-precision map data within the circle. If the distance between two navigation points is greater than 25M, interpolate points at a distance of 25M. Use the two navigation points before and after to generate a heading angle value, compare the heading angle of the acquired range map data with the heading angle of the navigation point, exclude map data with too large heading angle errors, and retain map data that meets the conditions. Then, the sub-high-precision map data is obtained after deleting the data that does not meet the requirements.

[0086] The target navigation point corresponds to the sub-high-precision map data. The 25M range data is segmented. The navigation path is divided into multiple segments based on the presence or absence of map data within the 25M range. At the same time, multiple sub-high-precision map segments are also obtained.

[0087] 2. Find the starting point. Perform precise high-precision map data matching on the segmented data in turn, find the first sub-high-precision map data corresponding to the first navigation point of each segment, and verify the first sub-high-precision map data. The verification method is to see whether the map data cannot be obtained for the three consecutive navigation points within a radius of 5M after the first navigation point or whether the map data obtained by the subsequent three navigation points have no continuous relationship with the data obtained by the first navigation point. If the judgment result is yes, the navigation point will not be used. Continue to judge one navigation point after another, find the navigation point that can be used and the corresponding sub-high-precision map data segment, record the obtained sub-high-precision map data segment and the subscript of the navigation point that meets the conditions, the grouping ID of the sub-high-precision map data segment, and deduce to the target navigation point behind in turn, continue to find the navigation point that can be used and record the subscript.

[0088] 3. Group data chain derivation. Use the group (segment) continuation topological relationship of the sub-high-precision map to obtain the subsequent group ID of the current group ID, and deduce it one group at a time. If there are multiple groups following a group ID, deduce each group backward for a certain distance and select the group with more and continuous navigation points as the group to be matched. Fig.11 As shown in , starting from the first usable target navigation point, we deduce backwards to obtain multiple target navigation points connected into a line. Fig.11 The road marked in green.

[0089] The current group ID is found in the successfully matched data. If the current navigation loops, the current matching process is exited and the next navigation point is used for matching. After the matching is completed, the results of the two matches are connected. Fig.12As shown in the green road in the figure, if a loop occurs on the road, the matching process will be exited.

[0090] 4. Start and end point verification. Perform a secondary verification on the starting position of the high-precision map data generated by the match. Continue to deduce the map data at the start and end points forward and backward for a certain distance to find out whether the road is cut off. If there is a road cutoff point, extend the high-precision map data to the road cutoff point. Record the start and end points of the high-precision map data that are successfully matched in this navigation.

[0091] 5. Generate a complete data link for the entire navigation path. Group the matched high-precision map data, assemble the data again according to the custom data format, and save a complete map data link planned according to the navigation path. Provide it to the autonomous driving back-end module for use. The back-end performs advance lane changes, acceleration and deceleration, and on-ramp and off-ramp operations according to the planned complete high-precision map data.

[0092] 6. Real-time output of high-precision map data. Obtain the vehicle's position, find the position of the vehicle in the high-precision map data, and output high-precision map data 2 kilometers ahead of the vehicle and 200 meters behind the vehicle.

[0093] In this embodiment, according to the SD navigation path planning, the high-precision map data according to the SD navigation planning is accurately matched. The specific implementation includes: the starting point and end point of the high-precision map in the SD navigation path, according to the SD navigation planning, the navigation landing point of the SD navigation is used to match the diversion road, and the complex scene loop, interchange, and parallel road are accurately matched. A complete high-precision map data link is generated to provide basic data support for autonomous driving.

[0094] This embodiment also provides a high-precision map generation device, including:

[0095] A first acquisition module is used to acquire a target navigation path of the target object from the navigation data, wherein the target navigation path is a path for navigating the target object;

[0096] A second acquisition module is used to acquire a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path;

[0097] The splicing module is used to splice the sub-high-precision maps into a target high-precision map in the order of target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0098] The above-mentioned high-precision map generation device can be used in the driving process to generate a target high-precision map of the target navigation path in the navigation data, so as to use the target high-precision map to assist the user in driving or automatic driving. The device can be installed on the vehicle, or it can be a device that provides cloud services, and generates a target high-precision map for the vehicle to use through the cloud service.

[0099] The high-precision map in this embodiment may be a high-precision map used in the process of autonomous driving, assisted driving or manual driving navigation. The navigation information in the high-precision map may be detailed to the lane level, thereby assisting the vehicle in lane-level navigation or lane changing, etc.

[0100] The navigation data in this embodiment may be data of a navigation system that comes with the vehicle, such as SD navigation data, and a digital card navigation (Secure Digital, SD) navigation may be a navigation method that uses an SD card to store navigation data. A navigation system or navigation software may be installed on the vehicle, and the navigation system or navigation software performs navigation according to the path data in the SD card. The path data stored in the SD card may be updated and deleted, and the SD card may be a pluggable card or a virtual card integrated into a circuit board of the navigation system.

[0101] The total high-precision map in this embodiment can be a high-precision map within a specific area or a specific range. The total meaning is that the coverage is large, and all high-precision maps involved in the user's navigation process are covered. For example, a high-precision map of roads across the country, a high-precision map of roads within a province, a high-precision map of a certain highway, a high-precision map of a certain ring road, etc. In this embodiment, the total high-precision map can be understood as a general map of high-precision maps covering some areas and routes. When high-precision maps of certain areas and routes are needed, they can be obtained from the total high-precision map.

[0102] In this embodiment, taking the driving scene as an example, during the driving process, the vehicle is on the road, and the vehicle can navigate to the user through the navigation data and navigation system in the SD card. The user enters the end point, which constitutes the user's current position or the navigation path from the starting point to the end point selected by the user. In the driving process, the path from the starting point to the end point of the user can be determined from the navigation data, that is, the path for navigating the user. And in this path, the target navigation path can be determined. The target navigation path can be a path from the starting point to the end point, or it can be a section of the path from the starting point to the end point. For example, the target navigation path can be a path two kilometers forward from the current position of the user's vehicle. Since the vehicle is driving forward, the path two kilometers forward is used as the target navigation path, and a high-precision map of the target two kilometers forward can be generated for the vehicle to assist the vehicle in driving. The choice of two kilometers forward is because the calculation amount of choosing a path that is too far away is large, and the vehicle has not yet driven to such a far position, so there is no need to process data that is too far away. As the driving process approaches, it can be processed again. Alternatively, the user can anticipate entering autonomous driving mode in two minutes and need to use a high-precision map. In this case, the user can estimate that the vehicle will reach a point four kilometers behind the current location in two minutes (the value is only an estimated distance and does not constitute a limitation). In this case, the navigation path from the fourth to sixth kilometers behind the current location can be determined as the target navigation path, and the target high-precision map of the target navigation path can be calculated.

[0103] For the determined target navigation path, navigation data also carries navigation points, which are marking points in the target navigation path and are used to mark different locations. For example, if the target navigation path is two kilometers long, starting from the starting point, there is a navigation point every 100 meters (the navigation point may be used to measure distance, and may be a position corresponding to a road sign on the side of the road, and the function is not limited).

[0104] For the navigation points in the target navigation path, each navigation point corresponds to a position in the target navigation path. Based on the navigation point, the corresponding position is searched in the total high-precision map, and when the corresponding position is found from the total high-precision map, a high-precision map in the vicinity of the corresponding position is obtained as a sub-high-precision map. In other words, for each navigation point in the target navigation path, the corresponding position is determined from the total high-precision map, and a high-precision map nearby is obtained. Then for the target navigation path, multiple corresponding sub-high-precision maps are obtained, and the target high-precision map can be obtained by splicing multiple sub-high-precision maps.

[0105] Take an example to illustrate that when a user is driving on the road, the automatic driving or assisted driving function can be turned on. At this time, the system can determine from the user's navigation data that the user is navigating from position 1 to position 2, and the path from position 1 to position 2 is the navigation path. From the navigation path, the two-kilometer path from the user's current position is determined as the target navigation path, and a target high-precision map of the target navigation path is generated to assist the user in driving or automatic driving. For the target navigation path, multiple navigation points are obtained, and each navigation point determines the corresponding position from the total high-precision map, and a high-precision map near the corresponding position is obtained as a sub-high-precision map. Then, after splicing the sub-high-precision maps, a target high-precision map corresponding to the target navigation path is generated, and the target high-precision map is used to assist the user in driving or automatic driving. When the user drives a certain distance, such as one kilometer, the vehicle continues to determine the target navigation path and generate a target high-precision map. At this time, the two-kilometer path after the current position of the user when he has traveled one kilometer can be used as the target navigation path, or the two-kilometer path after the last determined target navigation path can be used as the target navigation path, so that as the user moves forward, the target high-precision map of the subsequent road section is continuously generated.

[0106] For other examples of this embodiment, please refer to the above method examples and are not limited here.

[0107] The present application also provides a system for generating a high-precision map, including:

[0108] A first acquisition module is used to acquire a target navigation path of the target object from the navigation data, wherein the target navigation path is a path for navigating the target object;

[0109] A second acquisition module is used to acquire a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path;

[0110] The splicing module is used to splice the sub-high-precision maps into a target high-precision map in the order of target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0111] The high-precision map generation system can be used in the driving process to generate a target high-precision map of the target navigation path in the navigation data, so as to use the target high-precision map to assist users in driving or automatic driving. The system can be installed on the vehicle, or it can be a cloud system to generate a target high-precision map for the vehicle through cloud services.

[0112] The high-precision map in this embodiment may be a high-precision map used in the process of autonomous driving, assisted driving or manual driving navigation. The navigation information in the high-precision map may be detailed to the lane level, thereby assisting the vehicle in lane-level navigation or lane changing, etc.

[0113] The navigation data in this embodiment may be data of a navigation system that comes with the vehicle, such as SD navigation data, and a digital card navigation (Secure Digital, SD) navigation may be a navigation method that uses an SD card to store navigation data. A navigation system or navigation software may be installed on the vehicle, and the navigation system or navigation software performs navigation according to the path data in the SD card. The path data stored in the SD card may be updated and deleted, and the SD card may be a pluggable card or a virtual card integrated into a circuit board of the navigation system.

[0114] The total high-precision map in this embodiment can be a high-precision map within a specific area or a specific range. The total meaning is that the coverage is large, and all high-precision maps involved in the user's navigation process are covered. For example, a high-precision map of roads across the country, a high-precision map of roads within a province, a high-precision map of a certain highway, a high-precision map of a certain ring road, etc. In this embodiment, the total high-precision map can be understood as a general map of high-precision maps covering some areas and routes. When high-precision maps of certain areas and routes are needed, they can be obtained from the total high-precision map.

[0115] In this embodiment, taking the driving scene as an example, during the driving process, the vehicle is on the road, and the vehicle can navigate to the user through the navigation data and navigation system in the SD card. The user enters the end point, which constitutes the user's current position or the navigation path from the starting point to the end point selected by the user. In the driving process, the path from the starting point to the end point of the user can be determined from the navigation data, that is, the path for navigating the user. And in this path, the target navigation path can be determined. The target navigation path can be a path from the starting point to the end point, or it can be a section of the path from the starting point to the end point. For example, the target navigation path can be a path two kilometers forward from the current position of the user's vehicle. Since the vehicle is driving forward, the path two kilometers forward is used as the target navigation path, and a high-precision map of the target two kilometers forward can be generated for the vehicle to assist the vehicle in driving. The choice of two kilometers forward is because the calculation amount of choosing a path that is too far away is large, and the vehicle has not yet driven to such a far position, so there is no need to process data that is too far away. As the driving process approaches, it can be processed again. Alternatively, the user can anticipate entering autonomous driving mode in two minutes and need to use a high-precision map. In this case, the user can estimate that the vehicle will reach a point four kilometers behind the current location in two minutes (the value is only an estimated distance and does not constitute a limitation). In this case, the navigation path from the fourth to sixth kilometers behind the current location can be determined as the target navigation path, and the target high-precision map of the target navigation path can be calculated.

[0116] For the determined target navigation path, navigation data also carries navigation points, which are marking points in the target navigation path and are used to mark different locations. For example, if the target navigation path is two kilometers long, starting from the starting point, there is a navigation point every 100 meters (the navigation point may be used to measure distance, and may be a position corresponding to a road sign on the side of the road, and the function is not limited).

[0117] For the navigation points in the target navigation path, each navigation point corresponds to a position in the target navigation path. Based on the navigation point, the corresponding position is searched in the total high-precision map, and when the corresponding position is found from the total high-precision map, a high-precision map in the vicinity of the corresponding position is obtained as a sub-high-precision map. In other words, for each navigation point in the target navigation path, the corresponding position is determined from the total high-precision map, and a high-precision map nearby is obtained. Then for the target navigation path, multiple corresponding sub-high-precision maps are obtained, and the target high-precision map can be obtained by splicing multiple sub-high-precision maps.

[0118] Take an example to illustrate that when a user is driving on the road, the automatic driving or assisted driving function can be turned on. At this time, the system can determine from the user's navigation data that the user is navigating from position 1 to position 2, and the path from position 1 to position 2 is the navigation path. From the navigation path, the two-kilometer path from the user's current position is determined as the target navigation path, and a target high-precision map of the target navigation path is generated to assist the user in driving or automatic driving. For the target navigation path, multiple navigation points are obtained, and each navigation point determines the corresponding position from the total high-precision map, and a high-precision map near the corresponding position is obtained as a sub-high-precision map. Then, after splicing the sub-high-precision maps, a target high-precision map corresponding to the target navigation path is generated, and the target high-precision map is used to assist the user in driving or automatic driving. When the user drives a certain distance, such as one kilometer, the vehicle continues to determine the target navigation path and generate a target high-precision map. At this time, the two-kilometer path after the current position of the user when he has traveled one kilometer can be used as the target navigation path, or the two-kilometer path after the last determined target navigation path can be used as the target navigation path, so that as the user moves forward, the target high-precision map of the subsequent road section is continuously generated.

[0119] For other examples of this embodiment, please refer to the above method examples and are not limited here.

[0120] A vehicle is also provided in this embodiment, including: a processing module, used to obtain a target navigation path of the target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; according to the target navigation point in the target navigation path, obtaining a sub-high-precision map matching the target navigation point from the total high-precision map; splicing the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0121] During the driving process, the above-mentioned vehicle can generate a target high-precision map of the target navigation path in the navigation data, thereby using the target high-precision map to assist user driving or automatic driving.

[0122] The high-precision map in this embodiment may be a high-precision map used in the process of autonomous driving, assisted driving or manual driving navigation. The navigation information in the high-precision map may be detailed to the lane level, thereby assisting the vehicle in lane-level navigation or lane changing, etc.

[0123] The navigation data in this embodiment may be data of a navigation system that comes with the vehicle, such as SD navigation data, and a digital card navigation (Secure Digital, SD) navigation may be a navigation method that uses an SD card to store navigation data. A navigation system or navigation software may be installed on the vehicle, and the navigation system or navigation software performs navigation according to the path data in the SD card. The path data stored in the SD card may be updated and deleted, and the SD card may be a pluggable card or a virtual card integrated into a circuit board of the navigation system.

[0124] The total high-precision map in this embodiment can be a high-precision map within a specific area or a specific range. The total meaning is that the coverage is large, and all high-precision maps involved in the user's navigation process are covered. For example, a high-precision map of roads across the country, a high-precision map of roads within a province, a high-precision map of a certain highway, a high-precision map of a certain ring road, etc. In this embodiment, the total high-precision map can be understood as a general map of high-precision maps covering some areas and routes. When high-precision maps of certain areas and routes are needed, they can be obtained from the total high-precision map.

[0125] In this embodiment, taking the driving scene as an example, during the driving process, the vehicle is on the road, and the vehicle can navigate to the user through the navigation data and navigation system in the SD card. The user enters the end point, which constitutes the user's current position or the navigation path from the starting point to the end point selected by the user. In the driving process, the path from the starting point to the end point of the user can be determined from the navigation data, that is, the path for navigating the user. And in this path, the target navigation path can be determined. The target navigation path can be a path from the starting point to the end point, or it can be a section of the path from the starting point to the end point. For example, the target navigation path can be a path two kilometers forward from the current position of the user's vehicle. Since the vehicle is driving forward, the path two kilometers forward is used as the target navigation path, and a high-precision map of the target two kilometers forward can be generated for the vehicle to assist the vehicle in driving. The choice of two kilometers forward is because the calculation amount of choosing a path that is too far away is large, and the vehicle has not yet driven to such a far position, so there is no need to process data that is too far away. As the driving process approaches, it can be processed again. Alternatively, the user can anticipate entering autonomous driving mode in two minutes and need to use a high-precision map. In this case, the user can estimate that the vehicle will reach a point four kilometers behind the current location in two minutes (the value is only an estimated distance and does not constitute a limitation). In this case, the navigation path from the fourth to sixth kilometers behind the current location can be determined as the target navigation path, and the target high-precision map of the target navigation path can be calculated.

[0126] For the determined target navigation path, navigation data also carries navigation points, which are marking points in the target navigation path and are used to mark different locations. For example, if the target navigation path is two kilometers long, starting from the starting point, there is a navigation point every 100 meters (the navigation point may be used to measure distance, and may be a position corresponding to a road sign on the side of the road, and the function is not limited).

[0127] For the navigation points in the target navigation path, each navigation point corresponds to a position in the target navigation path. Based on the navigation point, the corresponding position is searched in the total high-precision map, and when the corresponding position is found from the total high-precision map, a high-precision map in the vicinity of the corresponding position is obtained as a sub-high-precision map. In other words, for each navigation point in the target navigation path, the corresponding position is determined from the total high-precision map, and a high-precision map nearby is obtained. Then for the target navigation path, multiple corresponding sub-high-precision maps are obtained, and the target high-precision map can be obtained by splicing multiple sub-high-precision maps.

[0128] Take an example to illustrate that when a user is driving on the road, the automatic driving or assisted driving function can be turned on. At this time, the system can determine from the user's navigation data that the user is navigating from position 1 to position 2, and the path from position 1 to position 2 is the navigation path. From the navigation path, the two-kilometer path from the user's current position is determined as the target navigation path, and a target high-precision map of the target navigation path is generated to assist the user in driving or automatic driving. For the target navigation path, multiple navigation points are obtained, and each navigation point determines the corresponding position from the total high-precision map, and a high-precision map near the corresponding position is obtained as a sub-high-precision map. Then, after splicing the sub-high-precision maps, a target high-precision map corresponding to the target navigation path is generated, and the target high-precision map is used to assist the user in driving or automatic driving. When the user drives a certain distance, such as one kilometer, the vehicle continues to determine the target navigation path and generate a target high-precision map. At this time, the two-kilometer path after the current position of the user when he has traveled one kilometer can be used as the target navigation path, or the two-kilometer path after the last determined target navigation path can be used as the target navigation path, so that as the user moves forward, the target high-precision map of the subsequent road section is continuously generated.

[0129] For other examples of this embodiment, please refer to the above method examples and are not limited here.

[0130] like Fig.13 As shown, in an embodiment of the present application, a high-precision map generation device is provided, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0131] Memory 113, used for storing computer programs;

[0132] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement the method for generating a high-precision map provided in any of the above method embodiments, including:

[0133] Acquire a target navigation path of the target object from the navigation data, wherein the target navigation path is a path for navigating the target object;

[0134] According to the target navigation point in the target navigation path, a sub-high-precision map matching the target navigation point is obtained from the total high-precision map;

[0135] The sub-high-precision maps are spliced ​​into a target high-precision map in the order of target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

[0136] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for generating a high-precision map provided in any of the aforementioned method embodiments are implemented.

[0137] The device embodiments described above are illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment, or some parts of the embodiments.

[0139] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0140] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for generating a high-precision map, characterized in that: include: Acquire a target navigation path of the target object from the navigation data, wherein the target navigation path is a path for navigating the target object; According to the target navigation point in the target navigation path, obtaining a sub-high-precision map matching the target navigation point from the total high-precision map; The sub-high-precision maps are spliced ​​into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

2. The method according to claim 1, characterized in that The step of acquiring the target navigation path of the target object from the navigation data comprises: Determine a navigation path with the location of the target object in the navigation data as a starting point and the destination of the target object as an end point; Starting from the starting point, traversing a target distance along the navigation path toward the end point; A path corresponding to the target distance in the navigation path is determined as the target navigation path.

3. The method according to claim 1, characterized in that The step of acquiring a sub-high-precision map matching the target navigation point in the target navigation path from the total high-precision map includes: Obtaining an original navigation point in the target navigation path; When the distance between two adjacent original navigation points is greater than a distance threshold, inserting a first navigation point between the two adjacent original navigation points; Determine the original navigation point and the first navigation point as the target navigation point; Obtain a sub-high-precision map that matches the target navigation point from the total high-precision map.

4. The method according to claim 1, characterized in that: The step of acquiring a sub-high-precision map matching the target navigation point in the target navigation path from the total high-precision map includes: Each of the target navigation points is processed as follows: Taking the target navigation point as the center, obtaining a high-precision map within a preset range around the target navigation point from the total high-precision map; The acquired high-precision map is determined as a sub-high-precision map of the target navigation point.

5. The method according to claim 1, characterized in that: The step of splicing the sub-high-precision maps into a target high-precision map in the order of the target navigation points comprises: According to the relationship between the heading angle of the path in the sub-high-precision map and the heading angle of the target navigation point, the path in the sub-high-precision map is deleted to obtain a deleted sub-high-precision map; Traversing the deleted sub-high-precision maps in sequence according to the order of the target navigation points, and dividing the continuous sub-high-precision maps into a group of sub-high-precision map segments; The sub-high-precision map segments are spliced ​​into the target high-precision map.

6. The method according to claim 5, characterized in that The step of segmenting the sub-high-precision maps into the target high-precision map comprises: When there is only one next high-precision sub-map segment after the current high-precision sub-map segment, splice the next high-precision sub-map segment after the current high-precision sub-map segment; When there are multiple parallel sub-high-precision map segments after the current sub-high-precision map segment, the sub-high-precision map segment with the largest number of consecutive navigation points starting from the first navigation point in the sub-high-precision map segment is selected and spliced ​​after the current sub-high-precision map segment to obtain the target high-precision map.

7. The method according to claim 6, characterized in that After stitching the sub-high-precision map segments, it also includes: Traverse a certain distance forward from the starting point of the spliced ​​high-precision map and traverse a certain distance backward from the end point of the spliced ​​high-precision map; When traversing forward to the end of the path, the end of the path is used as the new starting point; When traversing backward to the end of the path, the end of the path is taken as the new end point; The high-precision map between the new starting point and the new end point is determined as the target high-precision map.

8. A device for generating a high-precision map, characterized in that: include: A first acquisition module, used for acquiring a target navigation path of a target object from navigation data, wherein the target navigation path is a path for navigating the target object; A second acquisition module is used to acquire a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path; A splicing module is used to splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

9. A high-precision map generation system, characterized in that: include: A navigation path acquisition module, used to acquire a target navigation path of a target object from navigation data, wherein the target navigation path is a path for navigating the target object; A matching module, configured to obtain a sub-high-precision map matching the target navigation point from the total high-precision map according to the target navigation point in the target navigation path; A splicing module is used to splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

10. A vehicle, characterized in that: include: A processing module is used to obtain a target navigation path of a target object from navigation data, wherein the target navigation path is a section of a path used to navigate the target object; according to a target navigation point in the target navigation path, obtain a sub-high-precision map matching the target navigation point from a total high-precision map; and splice the sub-high-precision maps into a target high-precision map in the order of the target navigation points, wherein the target high-precision map is a high-precision map of the target navigation path.

Images