Map generation method and device

Abstract

The invention discloses a map generation method and device, and relates to the field of automatic driving. The method comprises the steps that topographic data of a target range and a driving track of a preset vehicle are acquired, the target range comprises a plurality of areas and a plurality of roads connected with the areas, and the driving track is used for representing a track generated when the preset vehicle runs in the target range; based on the topographic data and the driving track, performing structured processing on the target range to generate topological information of the target range, the topological information of the target range including connection relationships between the plurality of regions and the plurality of roads and road center lines of the plurality of roads; and based on the topological information of the target range, generating topological information of a plurality of lanes in the target range so as to generate a map of the target range. The technical problems of low map generation efficiency and low precision in the strip mine scene are solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a map generation method and device. Background Art

[0002] High-precision maps refer to electronic maps with high precision, high freshness, and high richness, with absolute and relative precision within 1 meter. Compared with open-pit high-precision maps of roads, open-pit mines only have some natural topography and retaining walls in the operation scenes (such as mining and loading areas, roads, intersections, unloading areas, parking lots, etc.), and roads, intersections, and boundaries of the operation areas need to be manually marked, resulting in low efficiency and low accuracy in map generation.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a map generation method and device to at least solve the technical problems of low efficiency and low accuracy of map generation in an open-pit mine scenario.

[0005] According to one aspect of an embodiment of the present invention, a map generation method is provided, comprising: acquiring terrain data of a target range and a driving trajectory of a preset vehicle, wherein the target range includes multiple areas and multiple roads connected to the multiple areas, and the driving trajectory is used to characterize the trajectory generated by the preset vehicle driving within the target range; based on the terrain data and the driving trajectory, performing structured processing on the target range to generate topological information of the target range, wherein the topological information of the target range includes connection relationships between the multiple areas and the multiple roads, and road center lines of the multiple roads; based on the topological information of the target range, generating topological information of multiple lanes within the target range to generate a map of the target range.

[0006] According to another aspect of an embodiment of the present invention, a map generating device is also provided, including: an acquisition module, used to acquire terrain data of a target range and a driving trajectory of a preset vehicle, wherein the target range includes multiple areas and multiple roads connected to the multiple areas, and the driving trajectory is used to characterize the trajectory generated by the preset vehicle driving within the target range; a first generating module, used to perform structured processing on the target range based on the terrain data and the driving trajectory to generate topological information of the target range, wherein the topological information of the target range includes the connection relationship between the multiple areas and the multiple roads, and the road center lines of the multiple roads; a second generating module, used to generate topological information of multiple lanes within the target range based on the topological information of the target range to generate a map of the target range.

[0007] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0008] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0009] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0010] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0011] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0012] In an embodiment of the present invention, terrain data of a target range and a preset driving trajectory of a vehicle are obtained; based on the terrain data and the driving trajectory, the target range is structured to generate topological information of the target range; based on the topological information of the target range, topological information of multiple lanes within the target range is generated to generate a map of the target range. It is easy to notice that after the terrain data and the driving trajectory are obtained, the terrain data and the driving trajectory can be automatically analyzed and processed to sequentially generate topological information of the entire target range and topological information of all lanes within the entire target range, thereby generating a lane-level high-precision map. The entire processing process is completed automatically, does not require user participation, does not introduce errors caused by human processing, and map generation comprehensively considers a variety of data, thereby improving map generation efficiency and accuracy, thereby solving the technical problems of low map generation efficiency and low accuracy in open-pit mine scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0014] Figure 1 is a flow chart of a map generation method according to an embodiment of the present invention;

[0015] Figure 2 is a schematic diagram of an optional scenario-based processing according to an embodiment of the present invention;

[0016] Figure 3 is a schematic diagram of an optional map topology according to an embodiment of the present invention;

[0017] Figure 4 is a schematic diagram of an optional method for generating a road boundary according to an embodiment of the present invention;

[0018] Figure 5 is a schematic diagram of an optional single lane according to an embodiment of the present invention;

[0019] Figure 6 is a schematic diagram of generating lanes in an optional intersection area according to an embodiment of the present invention;

[0020] Figure 7 is a flow chart of an optional map generation method according to an embodiment of the present invention;

[0021] Figure 8 is a schematic diagram of a map generating device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a map generation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a map generation method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining terrain data of a target range and a preset driving trajectory of a vehicle, wherein the target range includes multiple areas and multiple roads connected to the multiple areas, and the driving trajectory is used to characterize the trajectory generated by the preset vehicle driving within the target range.

[0027] The target range in the above steps can be a geographical range that the user wants to generate a high-precision map. In different scenarios, the size of the target range can be different. For example, in the engineering operation scenario, the target range can be a larger operating area. For example, in the embodiment of the present application, the target range is an open-pit mine range as an example for explanation, but it is not limited to this. For the target range, it often includes different types of areas at different positions in the target range, and in order to facilitate users to go to different areas, different areas are connected with different roads. For example, for an open-pit mine, it not only includes operating areas such as mining and loading areas, unloading areas, and parking lots, but also includes intersections to different operating areas, and roads connecting different operating areas and intersections. For two specific areas, in order to facilitate vehicle driving, two sub-roads (heading in two directions respectively) can be connected as a road, or they can be directly connected by a one-way road. For example, in the open-pit mine scenario, the road where unloaded vehicles drive can be used as a road, the road where heavy-loaded vehicles drive can be used as a road, and the road where unloaded vehicles and heavy-loaded vehicles drive can also be used as a road. In addition, for each road, one or more lanes can also be included, and the number and width of the lanes can be determined according to the actual terrain.

[0028] The terrain data in the above steps may refer to a data set describing the surface morphology and characteristics of the target range, which may include, but is not limited to, information such as the height, slope, aspect, terrain roughness, and type of surface cover. For example, in an open-pit mine scenario, the user is more concerned about the terrain undulations of the entire open-pit mine. Therefore, the terrain data may be the elevation data of the target range, so that a digital elevation model (DEM) can be created. The user can determine where there are retaining walls, roads, intersections, and the three-dimensional terrain of the work area within the target range through the terrain data. The accuracy of the terrain data can be determined based on the accuracy of the generated map by the user, or based on the accuracy of the equipment used to collect the terrain data, but is not limited to this. For example, in an embodiment of the present application, the accuracy of the terrain data may be 10 cm.

[0029] The preset vehicle in the above steps can be a special collection vehicle equipped with a laser radar, or an ordinary vehicle traveling within the target range. For example, in an open-pit mine scenario, the preset vehicle can also be an autonomous driving mining truck, autonomous driving excavator and other working vehicles, but not limited to this. The driving trajectory in the above steps can be the data of the movement path of the preset vehicle over a period of time, including the following information: location information, timestamp, speed, direction, acceleration, etc., but not limited to this. Considering that terrain data can be collected by the preset vehicle, the generation of the driving trajectory usually depends on the positioning service on the vehicle-mounted device or mobile device. Therefore, the preset vehicle can travel on the roads or areas where vehicles can travel in the entire area, and during the driving process of the preset vehicle, the positioning information of the preset vehicle at different times is uploaded to the server through the positioning service, and the server summarizes all the positioning information to generate the driving trajectory.

[0030] In an optional embodiment, the user can upload the terrain data of the target range by himself, and control the preset vehicle to travel within the target range, so as to determine the driving trajectory of the preset vehicle within the target range based on the real-time positioning information of the preset vehicle. In another optional embodiment, the terrain data of the target range can be collected by the preset vehicle, and in the process of the preset vehicle collecting data, the driving trajectory of the preset vehicle within the target range can be determined based on the real-time positioning information of the preset vehicle.

[0031] Step S104, based on the terrain data and the driving trajectory, the target range is structured to generate topological information of the target range, wherein the topological information of the target range includes connection relationships between multiple areas and multiple roads, and road center lines of multiple roads.

[0032] It should be noted that the structured processing here is not just the process of converting unstructured data into structured data, but the analysis and processing of terrain data and driving trajectories to determine the topological information used to generate the map and achieve the purpose of structuring.

[0033] In an optional embodiment, by analyzing the terrain data, the boundaries and positions of different areas can be identified, and then the connection relationship between different areas can be determined in combination with the driving trajectory, thereby generating the connection relationship between multiple areas and multiple roads. Further, the center line of each road can be determined by analyzing the terrain data and the driving trajectory.

[0034] Step S106: Based on the topological information of the target range, generate topological information of multiple lanes in the target range to generate a map of the target range.

[0035] The topological information of the multiple lanes in the above step may refer to the connection relationship between all lanes within the entire target range.

[0036] In an optional embodiment, by performing structured processing on terrain data and driving trajectories, road-level topological information can be obtained, and then a road-level high-precision map can be generated. However, considering that users in actual scenarios need lane-level high-precision maps, the connection relationship between multiple lanes in multiple roads can be determined based on the road centerline of each road and the driving direction of the preset vehicle on each road, and then a lane-level high-precision map can be generated.

[0037] Through the solution provided by the above-mentioned embodiment of the present application, the terrain data of the target range and the preset driving trajectory of the vehicle are obtained; based on the terrain data and the driving trajectory, the target range is structured to generate the topological information of the target range; based on the topological information of the target range, the topological information of multiple lanes in the target range is generated to generate a map of the target range. It is easy to notice that after the terrain data and the driving trajectory are obtained, the terrain data and the driving trajectory can be automatically analyzed and processed to generate the topological information of the entire target range and the topological information of all lanes in the entire target range in turn, so as to generate a lane-level high-precision map. The entire processing process is completed automatically, does not require user participation, does not cite errors caused by human processing, and the map generation comprehensively considers a variety of data, thereby improving the efficiency and accuracy of map generation, thereby solving the technical problems of low efficiency and low accuracy of map generation in open-pit mine scenarios.

[0038] In the above-mentioned embodiment of the present application, the target range is structured based on the terrain data and the driving trajectory to generate topological information of the target range, including: based on the terrain data and the driving trajectory, the target range is structured to obtain structured data of the target range, wherein the structured data includes regional boundaries of multiple areas and reference lines of multiple roads; based on the structured data of the target range, the topological information of the target range is generated, wherein the topological information of the target range includes the connection relationship between multiple areas and multiple roads, and the road center lines of multiple roads.

[0039] The above-mentioned reference line may be a reference line of a road manually marked or automatically extracted. In this case, the center line has a certain deviation, so it is only considered as a reference line of the center line.

[0040] In an optional embodiment, the terrain data includes different elevation data, so that the elevation points belonging to the ground can be determined by analyzing the terrain data, and then the regional boundaries of different areas can be determined by aggregating adjacent elevation points. Furthermore, considering that there is a certain deviation in the terrain data and the vehicle cannot travel in all locations, it is necessary to further determine the roads between different areas in combination with the driving trajectory, identify the road centerline of each road, and then generate the topological information of the entire target range.

[0041] In another optional embodiment, different areas within the target range have certain division criteria. Therefore, the regional boundaries of different areas can be determined based on the division criteria and terrain data of different areas. Further, the roads between different areas are determined in combination with the driving trajectory, and the center line of each road is identified, thereby generating topological information of the entire target range.

[0042] In the above embodiments of the present application, the target range is structured based on the terrain data and the driving trajectory to obtain structured data of the target range, including: based on the terrain data and the division strategy of the multiple regions, multiple regions are structured to obtain regional boundaries of the multiple regions; based on the terrain data and the driving trajectory, multiple roads are structured to obtain reference lines of the multiple roads.

[0043] The division strategy of multiple areas in the above steps can be a division criterion pre-established for the target range. For example, for an open-pit mine scenario, the division strategy can be a layout strategy such as the mining face, unloading face, parking lot, and energy replenishment field specified in the mine's production operation plan. For example, where the excavator digs, which road the self-driving mining truck takes, and where it excretes.

[0044] In an optional embodiment, after obtaining the terrain data and driving trajectory, the terrain data can be imported into a mapping software and colored according to the terrain elevation. Then, different areas can be drawn on the terrain data based on a multiple area division strategy through manual annotation. Each area can be represented by a polygon, and reference lines of different roads can be drawn on the terrain data based on the driving trajectory.

[0045] In another optional embodiment, after obtaining the terrain data and driving trajectory, the terrain data can be imported into a mapping software and colored according to the terrain elevation. In order to improve the degree of automation, an algorithm for automatically extracting regional boundaries can be used to determine the regional boundaries of each region based on the terrain data, and an algorithm for automatically extracting reference lines can be used to determine the reference lines of each road based on the terrain data and driving trajectory.

[0046] For example, still taking the open-pit mine scene as an example, the terrain data of the open-pit mine can be imported into the mapping software and colored according to the terrain elevation. Based on the production operation plan of the mine, the corresponding operating space range can be drawn on the terrain data by manual annotation at the designated mining operation surface, unloading operation surface, parking lot, and energy replenishment field, and represented by polygons. And according to the terrain data and driving trajectory, the geometric reference line of the road can be drawn, such as Figure 2 As shown, it mainly includes the boundary of the loading area, the boundary of the unloading area, the boundary of the intersection and the reference line of the road.

[0047] In the above-mentioned embodiment of the present application, based on the terrain data and the division strategy of multiple regions, multiple regions are structuredly processed to obtain the regional boundaries of the multiple regions, including: based on the division strategy of multiple regions, multiple regions are marked in the terrain data to determine the data points of each region; based on the data points of each region, the region is drawn to generate the regional boundaries of the region.

[0048] In an optional embodiment, the regional boundaries of multiple areas can be manually drawn according to the division strategy of multiple areas, that is, the data points belonging to the regional boundaries of each area are manually marked on the terrain data, so that the entire regional boundary can be generated based on these data points, and subsequent manual and automatic updates are supported.

[0049] In the above embodiments of the present application, multiple roads are structured based on terrain data and driving trajectories to obtain reference lines of multiple roads, including one of the following: based on the driving trajectory, multiple roads are marked in the terrain data, the data points of each road are determined, and the road can be drawn based on the data points of each road to generate a reference line of the road; based on the driving trajectory, the reference lines of multiple roads are extracted from the terrain data.

[0050] In an optional embodiment, after the terrain data and the driving track are displayed on the interactive interface, the boundary of each road can be marked on the interactive interface by manual drawing, so that the reference line of each road can be determined according to the manually marked points. In another optional embodiment, the reference line of each road can be extracted from the terrain data by automatically extracting the reference line in combination with the driving track.

[0051] In the above embodiments of the present application, topological information of the target range is generated based on the structured data of the target range, including: generating a map topology of the target range based on the structured data, wherein the map topology is used to characterize the connection relationship between multiple areas and multiple roads; generating road boundaries of multiple roads based on reference lines and terrain data of multiple roads; and adjusting the reference lines of different roads based on the road boundaries to generate a road centerline of the road.

[0052] In an optional embodiment, after determining the regional boundaries of multiple regions and the reference lines of multiple roads, the connection relationship between different regions and different roads can be determined in combination with the specific positions of the reference lines of the multiple roads and the specific positions of the regional boundaries of each region, thereby generating a map topology of the entire target range. Then, based on the reference lines of the multiple roads, the road boundary of each road can be determined, and then the road centerline can be determined based on the road boundary. Specifically, the reference line of the initially determined centerline can be adjusted by the accurate road boundary, thereby obtaining a centerline with higher accuracy as the road centerline of the road.

[0053] In the above-mentioned embodiment of the present application, a map topology of a target range is generated based on structured data, including: based on the direction information of reference lines of different roads, searching for a first area located at the starting point of the road from multiple areas, and constructing a first connection relationship between the road and the first area; based on the direction information of the reference line of the road, searching for a second area located at the end point of the road from multiple areas, and constructing a second connection relationship between the road and the second area; based on the first connection relationship and the second connection relationship, generating a map topology.

[0054] The first connection relationship in the above step indicates that the first area is the predecessor of the road, and the road is the successor of the first area. The second connection relationship in the above step indicates that the road is the predecessor of the second area, and the second area is the successor of the road.

[0055] In an optional embodiment, based on the direction information of the reference lines of different roads, that is, the geometric direction, the area at the starting point can be searched as the predecessor of the road, that is, the road is the successor of the area. Similarly, the area at the end point can be searched as the successor of the road, that is, the road is the predecessor of the area, so as to generate a map topology based on the predecessor, successor and other relationships between roads and areas.

[0056] For example, still taking the open-pit mine scenario as an example, assuming that based on the terrain data and the mine's production operation plan, the open-pit mine is determined to include the boundaries of loading area 1, loading area 2, unloading area 1, unloading area 2, parking lot, energy field, intersection 1 and intersection 2, and the reference lines of the seven roads are determined. After being processed by the above method, the generated map topology is as follows: Figure 3 As shown, the lines connecting different areas represent roads connecting different areas, and the arrows on the lines represent the geometric directions of the roads.

[0057] In the above-mentioned embodiment of the present application, road boundaries of multiple roads are generated based on reference lines and terrain data of multiple roads, including: based on the reference line of each road, determining a target search range corresponding to the road, wherein the distance between the boundary of the target search range and the reference line of the road is a preset distance; searching in the terrain data according to the target search range to determine whether there is boundary data of the road; if there is boundary data of the road, determining the road boundary of the road based on the boundary data of the road; if there is no boundary data of the road, generating the road boundary of the road at a position that is a preset distance from the reference line of the road.

[0058] The above-mentioned preset distance can be a standard distance between the road centerline and the road boundary, or it can be an artificially set distance between the road centerline and the road boundary, but is not limited to this. For example, in an embodiment of the present application, the preset offset threshold can be 5.0m.

[0059] The boundary data in the above steps may be the elevation difference between the road boundary and other terrain, or may be retaining walls, obstacles, etc. set at the road boundary, but is not limited thereto.

[0060] In an optional embodiment, for each road, a target search range can be determined based on a preset distance, on both sides of the reference line of the road, expanding outward from the reference line, and the target search range is used to determine the road boundary of the road. At this time, it can be understood that the width of the road is twice the preset distance. Then, all data points belonging to the target search range can be determined from the terrain data. Based on the elevation values ​​of these data points, it can be determined whether there is boundary data for the road. If there is boundary data, it means that the road is not a road of standard width. Therefore, the road boundary can be determined directly based on the boundary data. At this time, the distance between the road boundary and the reference line is less than the preset distance; if there is no boundary data, then the road boundary can be determined directly based on the preset distance. At this time, the distance between the road boundary and the reference line is the preset distance.

[0061] For example, still taking the open-pit mine scenario as an example, for Figure 4 For the road shown in the figure, after determining the reference line of the road (as shown by the solid line in the figure), we can expand outward from the reference line. Assuming that the preset distance is 5.0m, we can determine that the target search range is the range of 1m on both sides of the reference line. As shown in the road on the left, since the distance between the retaining wall and the reference line C1 is 3.5m<5.0m, it can be determined that there is boundary data. Therefore, the retaining wall boundary can be directly used as the road boundary (as shown in the figure). Figure 4 As shown in the upper section of the road on the right, since the distance between the retaining wall and the reference line C2 is 7.5m>5.0m, the road boundary can be generated at a distance of 5.0m from the reference line C2 (as shown in the upper section of the road on the right). Figure 4 (shown by the dashed line).

[0062] In the above embodiment of the present application, a road boundary of the road is generated at a position that is a preset distance from a reference line of the road, including: generating a virtual boundary of the road at a position that is a preset distance from the reference line of the road; when the virtual boundary of the road does not exceed the preset boundary of the road, determining the virtual boundary of the road as the road boundary of the road; when the virtual boundary of the road exceeds the preset boundary of the road, offsetting the virtual boundary of the road toward the reference line of the road according to a preset offset threshold to obtain the road boundary of the road.

[0063] Considering that a road may contain lanes in two directions, that is, a road contains two sub-roads, the reference line of each sub-road can be determined at this time, but if the above method is used, it may appear that the road boundary of one sub-road is inside another road. Therefore, a preset boundary of a road can be set in advance for some special roads. For example, if the road is adjacent to other roads, the preset boundary can be the center line of the reference lines of the two roads, but is not limited to this. Preferably, when the road contains two sub-roads, the preset boundary is used to characterize the center line of the reference lines of the two sub-roads.

[0064] The preset offset threshold in the above steps may be a pre-set fixed value or a dynamically changing value determined according to different road conditions, which may be updated by the user. For example, in an embodiment of the present application, the preset offset threshold may be 0.1 m.

[0065] In an optional embodiment, when it is determined that there is no boundary data within the target search range, first, a virtual boundary of the road can be generated at a position at a preset distance from the reference line of the road, and then the virtual boundary is further judged to determine whether the virtual boundary exceeds the preset boundary of the road, that is, to determine whether the virtual boundary is in another road. If the virtual boundary of the road does not exceed the preset boundary of the road, that is, the virtual boundary is only in the current road and not in another road, the virtual boundary can be directly used as the road boundary of the road, that is, it can be determined that the determination of the road boundary is accurate and can be considered as a real boundary. If the virtual boundary of the road exceeds the preset boundary of the road, that is, the virtual boundary is in another road, it can be determined that the determination of the road boundary is inaccurate, and therefore, it is necessary to offset the virtual boundary to the reference line of the road to ensure that the road boundary is not in another road.

[0066] It should be noted that the offset here can be performed not only once, but also multiple times. That is, if after offsetting once according to the preset offset threshold, the offset boundary still exceeds the preset boundary of the road, it can be offset again according to the preset offset threshold until the offset edge no longer exceeds the preset boundary of the road.

[0067] For example, still taking the open-pit mine scenario as an example, for Figure 4For the road shown in FIG. 1 , a virtual boundary can be generated at a position 5.0 m away from the reference line C1 on the right side of the reference line C1. Similarly, a virtual boundary can be generated at a position 5.0 m away from the reference line C2 on the left side of the reference line C2. Since both virtual boundaries exceed the center line between the reference lines C1 and C2, the two virtual boundaries need to be demarcated. The virtual boundary on the right side of the reference line C1 can be offset toward the reference line C1, and the virtual boundary on the left side of the reference line C2 can be offset toward the reference line C2, thereby obtaining the following: Figure 4 Road boundaries shown by dotted lines.

[0068] In the above-mentioned embodiment of the present application, the reference line of the road is adjusted based on the road boundaries of different roads to generate the road centerline of the road, including: based on the road boundaries of the road, the kinematic and dynamic requirements of the vehicle, and the preset distance between the vehicle and the road boundaries of the road, the reference line of the road is adjusted to generate the road centerline of the road.

[0069] In an optional embodiment, the road reference line can be automatically and smoothly adjusted based on the road boundaries on the left and right sides of the road to obtain the road centerline, ensuring that the curvature of the road reference line meets the vehicle kinematics and dynamics requirements, and ensuring that the distance between the vehicle and the boundary meets the safety distance requirements.

[0070] In the above embodiment of the present application, based on the topological information of the target range, topological information of multiple lanes within the target range is generated, including: based on the road centerline of each road and the lane generation requirement of the road, generating at least one first lane in the road; determining at least two target roads connected to the same intersection area in multiple areas; based on at least one target lane in each target road, generating at least one second lane in the intersection area; based on the connection relationship between at least one first lane and at least one second lane, generating topological information of multiple lanes, wherein the multiple lanes include at least one first lane and at least one second lane.

[0071] The lane generation requirements in the above steps may be the number of lanes that the user needs to set in the road, the width of each lane, etc., but are not limited thereto.

[0072] In an optional embodiment, the lane centerline and lane boundary of at least one first lane in the road may be generated based on the road centerline of each road and according to the number of lanes, lane width, etc. For example, the number of lanes is 1 and the lane width is 5.0 m. The generated first lane is as follows: Figure 5Then, considering that the intersection area is often connected to multiple roads, in order to ensure the driving safety of vehicles in the intersection area, it is necessary to further generate at least one second lane in the intersection area, match the second lane generated in the intersection area with the first vehicle generated in each road connected to the intersection area, determine the connection relationship between the first lane and the second lane, and thus determine the connection relationship between all lanes, that is, the topological information of multiple lanes.

[0073] In the above embodiment of the present application, based on at least one target lane in each target road, at least one second lane in the intersection area is generated, including: based on the direction information of the lane centerline of each target lane, determining the type of target position connecting the target lane and the intersection area, wherein the type includes one of the following: entry position, exit position; based on a preset turning radius requirement, generating a lane between different types of target positions corresponding to different target lanes to generate at least one second lane.

[0074] In an optional embodiment, the rules for entering or exiting the intersection can be determined based on the geometric direction of the center line of the lane in the road connected to the intersection area, that is, the direction information, that is, determine whether the type of the lane and intersection connection position is an entry position or an exit position, and then generate a second lane between all entry positions and exit positions, that is, generate a guide lane for guiding vehicles to travel in the intersection area. In order to ensure the driving safety of vehicles driving in the guide lane, it is necessary to determine that the guide vehicle meets the turning radius requirement of the vehicle.

[0075] For example, for Figure 6 The intersection area (as shown in the rectangular box in the figure) and the roads (as shown in the thick solid line in the figure) shown in the figure, each road contains two bidirectional lanes (as shown in the solid line in the figure), so the intersection contains a total of 6 target positions, namely position 1 to position 6. Among them, based on the direction information of lane 1 connected to position 1 (as shown by the dotted arrow in the figure), it can be determined that the type of position 1 is the entry position, and similarly, the types of positions 3 and 5 can be determined as the entry positions, and the types of positions 2, 4 and 6 are exit positions. Then, a lane can be generated between position 1 and position 4 (as shown by the solid line in the figure), a lane can be generated between position 1 and position 6 (as shown by the solid line in the figure), a lane can be generated between position 3 and position 2 (as shown by the solid line in the figure), and a lane can be generated between position 5 and position 2 (as shown by the solid line in the figure).

[0076] In the above embodiment of the present application, topological information of multiple lanes is generated based on the connection relationship between at least one first lane and at least one second lane, including: for each second lane, searching for a front-drive lane located at the starting point of the second lane from at least one first lane, and constructing a third connection relationship between the second lane and the front-drive lane; for each second lane, searching for a rear-drive lane located at the starting point of the second lane from at least one first lane, and constructing a fourth connection relationship between the second lane and the rear-drive lane; the third connection relationship and the fourth connection relationship are summarized to obtain topological information of multiple lanes.

[0077] In an optional embodiment, based on the geometric directions of the first lane and the second lane, the first lane at the starting point of the second lane can be searched as the predecessor of the second lane, and the second lane can be recorded as the successor of the first lane; similarly, the first lane at the end point of the second lane can be searched as the successor of the second lane, and the second lane can be recorded as the predecessor of the first lane, thereby generating a lane topology based on the predecessor, successor, etc. relationship between the first lane and the second lane.

[0078] In the above-mentioned embodiment of the present application, terrain data of a target range and a driving trajectory of a preset vehicle are obtained, including: controlling the preset vehicle to drive within the target range, and obtaining point cloud data collected by the preset vehicle, and positioning data of the preset vehicle; performing data mapping on the point cloud data to generate terrain data; and summarizing the positioning data to generate a driving trajectory.

[0079] In an optional embodiment, a preset vehicle equipped with a laser radar drives within the target range, collects point cloud data within the target range and uploads it to a server. The server receives the point cloud data and performs data mapping and post-processing to generate high-precision terrain data. While the preset vehicle collects point cloud data, the positioning information can be uploaded to the server synchronously, thereby forming a driving track formed by a series of coordinate points.

[0080] Combine the following Figure 7 Taking an open-pit mine scenario as an example, a preferred embodiment of the present application is described in detail. Figure 7 As shown, the method includes the following process:

[0081] Step S702, data input, including high-precision terrain and vehicle trajectory. High-precision point clouds are collected by special collection vehicles or unmanned mining trucks equipped with laser radars. After uploading to the cloud, the point clouds are mapped and post-processed to generate high-precision terrain data. After the collection vehicle or mining truck collects point cloud data, its real-time positioning information is synchronously uploaded to the cloud to form a vehicle driving trajectory formed by a series of coordinate points. The above two types of data are imported into the high-precision map production line for high-precision mapping of open-pit mines.

[0082] Step S704, the operation scene is structured, including the operation area structured and the road network structured. The high-precision terrain is imported into the map making software and colored according to the terrain slope. The following steps are performed to complete the operation scene structured: the operation area is structured, according to the production operation plan of the mine, the corresponding operation space range is drawn at the designated mining operation surface, unloading operation surface, parking lot, and energy replenishment field, and represented by polygons; the road network is structured, according to the high-precision terrain and the trajectory of the vehicle, the geometric reference lines of the empty and heavy-loaded roads are drawn.

[0083] Step S706, automatic topology mapping, including: constructing map topology, extracting road boundaries and automatically adjusting the center line of the road. Constructing map topology: According to the geometric direction of the empty and overloaded road reference lines, search for the work area or intersection at the starting point as the predecessor of the road, and this road record is the successor of the corresponding area; similarly, search for the work area or intersection at the end point as the successor of the road, and this road record is the predecessor of the area. Extracting road boundaries: According to the empty and overloaded road reference lines, automatically search for retaining wall boundaries within a certain threshold range (R). When there is a retaining wall boundary, take the retaining wall boundary as the road boundary. When there is no retaining wall boundary, generate a virtual boundary at a distance R from the reference line. If the generated virtual boundary exceeds the center line of the empty and overloaded reference lines, then take the center line as the reference line and offset a certain threshold (Offset) to one side of the road reference line to generate a new virtual boundary as the boundary. Automatically adjust the road centerline: Generate the left and right boundaries of the road (including retaining wall boundaries and virtual boundaries) according to the previous step, and automatically and smoothly adjust the road reference line to ensure that the curvature of the road reference line meets the vehicle kinematics and dynamics requirements, and that the distance between the vehicle and the boundary meets the safety distance requirements.

[0084] Step S708, automatic lane mapping, including: automatic generation of lanes within the road, automatic generation of guide lanes within the intersection, and automatic generation of lane topological relationships. Automatic generation of lanes within the road: Based on the road reference line generated in step S706, the lane centerline and boundary are generated according to the number of lanes and lane width offset. Automatic generation of guide lanes within the intersection: According to the geometric direction of the lane centerline in the road connected to the intersection, the rules for entering or exiting the intersection are determined, and a guide lane is generated between all entry and exit points to meet the vehicle turning radius requirements, thereby automatically generating all guide lanes within the intersection. Dynamic generation of lane topological relationships: Based on the intersection guide lanes generated in the previous step, the lane connected at the geometric starting point is automatically searched as the front drive lane of the current lane. Similarly, the lane connected at the geometric end point is automatically searched as the rear drive lane of the current lane, and the topological relationship construction of all lanes is completed in sequence.

[0085] Through the above steps, a semi-automatic mapping method for high-precision maps based on map topology is provided to assist in the production of high-precision maps for open-pit mines. Among them, the open-pit mine map topology structure (topological nodes, arcs) converts unstructured terrain into a structured map topology framework: roads are topological arcs, and independent open spaces such as mining and loading areas, intersections, unloading areas, parking lots, gas stations, and charging stations are topological nodes. All nodes are connected through arcs to construct the entire map topology framework and automatically generate lane-level high-precision maps. Automatically extract the boundaries of roads and work areas based on high-precision terrain data, greatly improving the efficiency and accuracy of map making.

[0086] According to an embodiment of the present invention, a map generating device is provided. It should be noted that the device can be used to execute the above-mentioned map generating method.

[0087] Figure 8 is a schematic diagram of a map generating device according to an embodiment of the present invention. Figure 8 As shown, the device method comprises:

[0088] The acquisition module 82 is used to obtain the terrain data of the target range and the driving trajectory of the preset vehicle, wherein the target range includes multiple areas and multiple roads connected to the multiple areas, and the driving trajectory is used to characterize the trajectory generated by the preset vehicle driving within the target range.

[0089] The first generating module 84 is used to perform structured processing on the target range based on the terrain data and the driving trajectory to generate topological information of the target range, wherein the topological information of the target range includes the connection relationship between multiple areas and multiple roads, and the road center lines of multiple roads.

[0090] The second generating module 86 is used to generate topological information of a plurality of lanes in the target range based on the topological information of the target range, so as to generate a map of the target range.

[0091] In the above embodiment of the present application, the first generation module includes: a first processing unit, used to perform structured processing on the target range based on terrain data and driving trajectory to obtain structured data of the target range, wherein the structured data includes regional boundaries of multiple areas and reference lines of multiple roads; a first generation unit, used to generate topological information of the target range based on the structured data of the target range, wherein the topological information of the target range includes the connection relationship between multiple areas and multiple roads, and the road center lines of multiple roads.

[0092] In the above-mentioned embodiment of the present application, the first processing unit includes: a first processing sub-unit, which is used to perform structured processing on multiple areas based on terrain data and the division strategy of multiple areas to obtain regional boundaries of multiple areas; a second processing sub-unit, which is used to perform structured processing on multiple roads based on terrain data and driving trajectories to obtain reference lines of multiple roads.

[0093] In the above embodiment of the present application, the first processing subunit is also used to mark multiple areas in the terrain data based on the division strategy of multiple areas, determine the data points of each area, and draw the area based on the data points of each area to generate the area boundary of the area.

[0094] In the above-mentioned embodiment of the present application, the second processing subunit is also used to perform one of the following steps: based on the driving trajectory, marking multiple roads in the terrain data, determining the data points of each road, and drawing the road based on the data points of each road to generate a reference line of the road; based on the driving trajectory, extracting reference lines of multiple roads from the terrain data.

[0095] In the above embodiment of the present application, the first generation unit includes: a first generation subunit, used to generate a map topology of a target range based on structured data, wherein the map topology is used to characterize the connection relationship between multiple areas and multiple roads; a second generation subunit, used to generate road boundaries of multiple roads based on reference lines and terrain data of multiple roads; and a third generation subunit, used to adjust the reference line of the road based on the road boundaries of different roads to generate a road centerline of the road.

[0096] In the above-mentioned embodiments of the present application, the first generating subunit is also used for: based on the direction information of the reference lines of different roads, searching for a first area located at the starting point of the road from multiple areas, and constructing a first connection relationship between the road and the first area; based on the direction information of the reference lines of the road, searching for a second area located at the end point of the road from multiple areas, and constructing a second connection relationship between the road and the second area; and generating a map topology based on the first connection relationship and the second connection relationship.

[0097] In the above-mentioned embodiment of the present application, the second generating subunit is also used to: determine the target search range corresponding to each road based on the reference line of the road, wherein the distance between the boundary of the target search range and the reference line of the road is a preset distance; search in the terrain data according to the target search range to determine whether there is boundary data of the road; if there is boundary data of the road, determine the road boundary of the road based on the boundary data of the road; if there is no boundary data of the road, generate the road boundary of the road at a position that is a preset distance away from the reference line of the road.

[0098] In the above-mentioned embodiment of the present application, the second generating subunit is also used for: generating a virtual boundary of the road at a position which is a preset distance from a reference line of the road; determining the virtual boundary of the road as the road boundary of the road when the virtual boundary of the road does not exceed the preset boundary of the road; and offsetting the virtual boundary of the road toward the reference line of the road according to a preset offset threshold to obtain the road boundary of the road when the virtual boundary of the road exceeds the preset boundary of the road.

[0099] In the above embodiment of the present application, the third generating subunit is also used to adjust the reference line of the road based on the road boundary of the road, the vehicle kinematics and dynamics requirements, and the preset distance between the vehicle and the road boundary of the road to generate the road centerline of the road.

[0100] In the above embodiment of the present application, the second generation module includes: a second generation unit, used to generate at least one first lane in the road based on the road centerline of each road and the lane generation requirements of the road; a determination unit, used to determine at least two target roads connected to the same intersection area in multiple areas; a third generation unit, used to generate at least one second lane in the intersection area based on at least one target lane in each target road; a fourth generation unit, used to generate topological information of multiple lanes based on the connection relationship between at least one first lane and at least one second lane, wherein the multiple lanes include at least one first lane and at least one second lane.

[0101] In the above embodiment of the present application, the third generation unit includes: a determination subunit, which is used to determine the type of target position connecting the target lane and the intersection area based on the direction information of the lane centerline of each target lane, wherein the type includes one of the following: entry position, exit position; a fourth generation subunit, which is used to generate a lane between different types of target positions corresponding to different target lanes based on a preset turning radius requirement to generate at least one second lane.

[0102] In the above embodiment of the present application, the fourth generation unit includes: a first search subunit, which is used to search for a front-drive lane located at the starting point of each second lane from at least one first lane, and construct a third connection relationship between the second lane and the front-drive lane; a second search subunit, which is used to search for a rear-drive lane located at the starting point of each second lane from at least one first lane, and construct a fourth connection relationship between the second lane and the rear-drive lane; and a summary subunit, which is used to summarize the third connection relationship and the fourth connection relationship to obtain topological information of multiple lanes.

[0103] In the above-mentioned embodiment of the present application, the acquisition module includes: an acquisition unit, which is used to control the preset vehicle to travel within the target range, and obtain the point cloud data collected by the preset vehicle, and the positioning data of the preset vehicle; perform data mapping on the point cloud data to generate terrain data; and a summary unit, which is used to summarize the positioning data and generate a driving trajectory.

[0104] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0105] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0106] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0107] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0108] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0109] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0111] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0112] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0114] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A map generation method, characterized in that: include: Acquire terrain data of a target range and a driving trajectory of a preset vehicle, wherein the target range includes multiple areas and multiple roads connected to the multiple areas, and the driving trajectory is used to characterize the trajectory generated by the preset vehicle driving within the target range; Based on the terrain data and the driving trajectory, the target range is structured to generate topological information of the target range, wherein the topological information of the target range includes connection relationships between the multiple areas and the multiple roads, and road center lines of the multiple roads; Based on the topology information of the target range, topology information of a plurality of lanes within the target range is generated to generate a map of the target range.

2. The method according to claim 1, characterized in that The step of performing structural processing on the target range based on the terrain data and the driving trajectory to generate topological information of the target range includes: Based on the terrain data and the driving trajectory, the target range is structured to obtain structured data of the target range, wherein the structured data includes area boundaries of the multiple areas and reference lines of the multiple roads; Based on the structured data of the target range, topological information of the target range is generated, wherein the topological information of the target range includes connection relationships between the multiple areas and the multiple roads, and road center lines of the multiple roads.

3. The method according to claim 2, characterized in that The step of performing structured processing on the target range based on the terrain data and the driving trajectory to obtain structured data of the target range includes: Based on the terrain data and the division strategy of the multiple regions, the multiple regions are subjected to structured processing to obtain the regional boundaries of the multiple regions; Based on the terrain data and the driving trajectory, the multiple roads are structured to obtain reference lines of the multiple roads.

4. The method according to claim 3, characterized in that The step of performing structured processing on the multiple regions based on the terrain data and the division strategy of the multiple regions to obtain the region boundaries of the multiple regions includes: Based on the division strategy of the multiple regions, marking the multiple regions in the terrain data, and determining data points of each region; The region is drawn based on the data points of each region to generate a region boundary of the region.

5. The method according to claim 3, characterized in that: The performing structural processing on the plurality of roads based on the terrain data and the driving trajectory to obtain reference lines of the plurality of roads includes one of the following: Based on the driving trajectory, the plurality of roads are marked in the terrain data, data points of each road are determined, and the road can be drawn based on the data points of each road to generate a reference line of the road; Based on the driving trajectory, reference lines of the plurality of roads are extracted from the terrain data.

6. The method according to any one of claims 2 to 5, characterized in that The generating the topology information of the target range based on the structured data of the target range includes: Based on the structured data, generating a map topology of the target range, wherein the map topology is used to characterize a connection relationship between the multiple areas and the multiple roads; generating road boundaries of the plurality of roads based on reference lines of the plurality of roads and the terrain data; The reference line of the road is adjusted based on the road boundaries of different roads to generate the road centerline of the road.

7. The method according to claim 6, characterized in that The step of generating a map topology of the target range based on the structured data includes: Based on the direction information of the reference lines of different roads, searching for a first area located at the starting point of the road from the multiple areas, and establishing a first connection relationship between the road and the first area; Based on the direction information of the reference line of the road, searching for a second area located at the end of the road from the multiple areas, and establishing a second connection relationship between the road and the second area; The map topology is generated based on the first connection relationship and the second connection relationship.

8. The method according to claim 6 or 7, characterized in that: The generating road boundaries of the plurality of roads based on the reference lines of the plurality of roads and the terrain data comprises: Based on the reference line of each road, determining a target search range corresponding to the road, wherein the distance between the boundary of the target search range and the reference line of the road is a preset distance; Searching the terrain data according to the target search range to determine whether there is boundary data of the road; If boundary data of the road exists, determining a road boundary of the road based on the boundary data of the road; In the case where there is no boundary data of the road, a road boundary of the road is generated at a position that is the preset distance away from a reference line of the road.

9. The method according to claim 8, characterized in that Generating a road boundary of the road at a position that is the preset distance from a reference line of the road includes: Generating a virtual boundary of the road at a position that is the preset distance from a reference line of the road; If the virtual boundary of the road does not exceed the preset boundary of the road, determining the virtual boundary of the road as the road boundary of the road; When the virtual boundary of the road exceeds the preset boundary of the road, the virtual boundary of the road is offset toward the reference line of the road according to a preset offset threshold to obtain the road boundary of the road; Preferably, when the road includes two sub-roads, the preset boundary is used to characterize the center line of the reference lines of the two sub-roads.

10. The method according to any one of claims 6 to 9, characterized in that The step of adjusting the reference line of the road based on the road boundaries of different roads to generate the road centerline of the road includes: Based on the road boundary of the road, the kinematic and dynamic requirements of the vehicle, and the preset distance between the vehicle and the road boundary of the road, the reference line of the road is adjusted to generate the road centerline of the road.

11. The method according to any one of claims 1 to 10, characterized in that The generating, based on the topological information of the target range, topological information of a plurality of lanes within the target range comprises: Based on the road centerline of each road and the lane generation requirement of the road, generating at least one first lane in the road; determining at least two target roads connected to the same intersection area among the multiple areas; Based on at least one target lane in each target road, generating at least one second lane in the intersection area; Based on the connection relationship between the at least one first lane and the at least one second lane, topology information of the plurality of lanes is generated, wherein the plurality of lanes include the at least one first lane and the at least one second lane.

12. The method according to claim 11, characterized in that The generating at least one second lane in the intersection area based on at least one target lane in each target road includes: Based on the direction information of the lane centerline of each target lane, determining the type of the target position where the target lane is connected to the intersection area, wherein the type includes one of the following: an entry position and an exit position; Based on a preset turning radius requirement, a lane is generated between different types of target positions corresponding to different target lanes to generate the at least one second lane.

13. The method according to claim 11 or 12, characterized in that: The generating the topology information of the plurality of lanes based on the connection relationship between the at least one first lane and the at least one second lane comprises: For each second lane, searching for a front lane located at a starting point of the second lane from the at least one first lane, and constructing a third connection relationship between the second lane and the front lane; For each second lane, searching for a rear-drive lane located at a starting point of the second lane from the at least one first lane, and constructing a fourth connection relationship between the second lane and the rear-drive lane; The third connection relationship and the fourth connection relationship are summarized to obtain topological information of the multiple lanes.

14. The method according to any one of claims 1 to 13, characterized in that The obtaining of the terrain data of the target range and the preset driving trajectory of the vehicle include: Controlling the preset vehicle to travel within the target range, and acquiring point cloud data collected by the preset vehicle and positioning data of the preset vehicle; Performing data mapping on the point cloud data to generate the terrain data; The positioning data are aggregated to generate the driving trajectory.

15. A map generating device, characterized in that: include: An acquisition module, used to acquire terrain data of a target range and a driving trajectory of a preset vehicle, wherein the target range includes a plurality of areas and a plurality of roads connected to the plurality of areas, and the driving trajectory is used to characterize a trajectory generated by the preset vehicle driving within the target range; A first generating module is used to perform structured processing on the target range based on the terrain data and the driving trajectory to generate topological information of the target range, wherein the topological information of the target range includes connection relationships between the multiple areas and the multiple roads, and road center lines of the multiple roads; The second generating module is used to generate topological information of multiple lanes in the target range based on the topological information of the target range, so as to generate a map of the target range.

Images