Road topological graph generation method and device, vehicle and storage medium

Abstract

The invention provides a road topological graph generation method and device, a vehicle and a storage medium, and relates to the technical field of automatic driving. The method comprises the following steps: acquiring a historical driving track of a vehicle in a target area, intersection position information in the target area and boundary information; according to the historical driving track and the boundary information, determining a passable area boundary of a road through which the historical driving track passes; according to the passable area boundary and the historical driving track, determining a road center line of a road through which the historical driving track passes; and based on the intersection position information, updating the road center line to generate a road topological graph. Therefore, the road topological graph of the target area can be accurately constructed based on the historical driving track, and the road topological graph comprises the connection relationship between the intersection and the road and the connection relationship between the roads, so that path planning from any starting point to terminal point in the target area can be realized, and the flexibility and success rate of valet parking are improved.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a method, apparatus, vehicle, and storage medium for generating road topology maps. Background Technology

[0002] With the development of automatic parking technology, valet parking has gradually become a mainstream method of automatic parking. However, due to the weak positioning signal in underground parking lots, using map navigation directly for valet parking may result in parking failure.

[0003] In related technologies, a road topology for a parking lot can be generated based on the user's historical parking trajectory, and then valet parking can be performed based on the generated road topology. However, the road topology generated in this way can only realize valet parking between a fixed start and a fixed end point within the parking lot, which is inflexible and has a low parking success rate. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, vehicle, and storage medium for generating road topology maps.

[0005] According to a first aspect of the present disclosure, a method for generating a road topology map is provided, including the generation of the road topology map.

[0006] Obtain the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information;

[0007] Based on the historical driving trajectory and the boundary information, the traversable area boundary of the road traversed by the historical driving trajectory is determined;

[0008] Based on the boundaries of the passable area and the historical driving trajectory, determine the centerline of the road along the historical driving trajectory;

[0009] Based on the intersection location information, the road centerline is updated to generate a road topology map.

[0010] According to a second aspect of the present disclosure, a road topology map generation apparatus is provided, comprising: an acquisition module, configured to acquire historical driving trajectories of vehicles within a target area, intersection location information and boundary information within the target area;

[0011] The first determining module is used to determine the passable area boundary of the road traversed by the historical driving trajectory based on the historical driving trajectory and the boundary information.

[0012] The second determining module is used to determine the center line of the road along the historical driving trajectory based on the boundary of the passable area and the historical driving trajectory.

[0013] The generation module is used to update the road centerline based on the intersection location information and generate a road topology map.

[0014] According to a third aspect of the present disclosure, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: implement the steps of the method for generating a road topology map as proposed in the first aspect of the present disclosure.

[0015] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of a mobile terminal, the steps of the method for generating a road topology map as proposed in the first aspect of the present disclosure are implemented.

[0016] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0017] In this embodiment, the historical driving trajectory of the vehicle within the target area, the intersection location information, and boundary information within the target area are first obtained. Based on the historical driving trajectory and boundary information, the traversable area boundaries of the roads traversed by the historical driving trajectory are determined. Based on the traversable area boundaries and the historical driving trajectory, the road centerlines of the roads traversed by the historical driving trajectory are determined. Based on the intersection location information, the road centerlines are updated to generate a road topology map. Therefore, a road topology map of the target area can be accurately constructed based on the historical driving trajectory. This road topology map includes the connection relationships between intersections and roads, as well as the connection relationships between roads, enabling path planning from any starting point to the destination within the target area, thus improving the flexibility and success rate of valet parking.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure:

[0020] Figure 1 This is a schematic flowchart illustrating a method for generating a road topology map according to some embodiments of this disclosure;

[0021] Figure 2 This is a schematic diagram of a connecting line provided in one embodiment of the present disclosure;

[0022] Figure 3 This is a schematic flowchart illustrating a method for generating a road topology map according to some embodiments of this disclosure;

[0023] Figure 4 This is a schematic flowchart illustrating a method for generating a road topology map according to some embodiments of this disclosure;

[0024] Figure 5 This is a schematic diagram of the structure of a road topology map generation apparatus according to some embodiments of the present disclosure;

[0025] Figure 6 This is a functional block diagram of a vehicle illustrating an exemplary embodiment. Detailed Implementation

[0026] Some embodiments of this disclosure will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this disclosure, except for operations that must be performed in a particular order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.

[0027] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0028] Figure 1 This is a flowchart illustrating a method for generating a road topology map according to some embodiments of the present disclosure, such as... Figure 1 As shown, it includes the following steps:

[0029] Step 101: Obtain the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information.

[0030] The target area can be a parking lot.

[0031] Among them, the vehicle's historical driving trajectory within the target area can be the trajectory of the driver controlling the vehicle's driving within the target area.

[0032] The location information of intersections within the target area can be the center of the intersection or the area where the intersection is located. This disclosure does not limit this.

[0033] In some embodiments, the boundary information includes road edge lines, wall edge lines, and storage location edge lines.

[0034] In some embodiments, while the vehicle is traveling in the target area along a historical driving trajectory, it can acquire images of the vehicle's surroundings captured by the vehicle's image acquisition device, and then identify intersection location information and boundary information based on the acquired images of the vehicle's surroundings.

[0035] Step 102: Based on the historical driving trajectory and boundary information, determine the passable area boundaries of the roads traversed by the historical driving trajectory.

[0036] It should be noted that, due to the complex road layout of parking lots, there may be a lack of clear road boundaries. Therefore, the boundaries of the passable areas along the roads traversed by historical driving trajectories can be determined by combining the road boundaries, wall boundaries, and parking space boundaries.

[0037] In this embodiment of the disclosure, after determining the historical driving trajectory, the edge line near the historical driving trajectory can be determined as the boundary of the passable area of ​​the road traversed by the historical driving trajectory.

[0038] Step 103: Determine the center line of the roads traversed by the historical driving trajectory based on the boundaries of the passable area and the historical driving trajectory.

[0039] It should be noted that the historical driving trajectory may be curved due to irregular driving by the driver (such as passing oncoming traffic, driving on curves, etc.). In order to eliminate the curve of the trajectory and the problem that the historical driving trajectory is not in the center of the road, the historical driving trajectory can be pulled towards the center of the road according to the boundary of the passable area to obtain the center line of the road along the historical driving trajectory.

[0040] In some embodiments, each trajectory point can be moved to the center of the road based on the distance between each trajectory point in the historical driving trajectory and the boundaries of the passable areas on the left and right sides of the trajectory, thereby obtaining the road centerline.

[0041] Step 104: Based on the intersection location information, update the road centerline and generate a road topology map.

[0042] For example, intersection 1 connects to roads 1, 2, and 3. Historical travel trajectories show that it's possible to travel from road 1 to road 2 and from road 1 to road 3, but not from road 2 to road 3. Therefore, it's necessary to update the road centerlines based on the intersection location information so that the road centerlines pass through the center of the intersection. This ensures that the generated road topology map shows the connections between intersections and roads, and between roads themselves.

[0043] In some embodiments, a first coordinate point on the road centerline with a distance of a first distance from the center of the intersection can be determined first. Based on the boundary of the passable area, a connecting line between the center of the intersection and the first coordinate point can be generated. Based on the connecting line, the line segment from the first coordinate point to the second coordinate point on the road centerline can be replaced to generate a road topology map, wherein the second coordinate point is the coordinate point on the road centerline that is closest to the center of the intersection.

[0044] The first distance can be 10 meters, 8 meters, etc. This disclosure does not limit it.

[0045] In some embodiments, a connection line between the intersection center and the first coordinate point can be generated based on a path planning strategy. For example, the Hybrid-A* algorithm can be used, with the boundary of the passable area as a constraint, to generate path points between the intersection center and the first coordinate point. Then, a smooth connection method (such as the Dubins-curve curve connection algorithm) can be used to connect each path point to obtain a smooth connection line.

[0046] Figure 2 This is a schematic diagram of a connecting line provided in one embodiment of the present disclosure, such as... Figure 2 As shown, point A is the center of the intersection, points B and C are the first coordinate points, and point D is the second coordinate point. The dashed lines are the connecting lines between points A and B, and between points A and C, and the solid lines are the road center lines. Delete the road center lines between points D and B, and between points D and C, and add the connecting lines between points A and B, and between points A and C to the road center lines to obtain the road topology map.

[0047] In this embodiment, the historical driving trajectory of the vehicle within the target area, the intersection location information, and boundary information within the target area are first obtained. Based on the historical driving trajectory and boundary information, the traversable area boundaries of the roads traversed by the historical driving trajectory are determined. Based on the traversable area boundaries and the historical driving trajectory, the road centerlines of the roads traversed by the historical driving trajectory are determined. Based on the intersection location information, the road centerlines are updated to generate a road topology map. Therefore, a road topology map of the target area can be accurately constructed based on the historical driving trajectory. This road topology map includes the connection relationships between intersections and roads, as well as the connection relationships between roads, enabling path planning from any starting point to the destination within the target area, thus improving the flexibility and success rate of valet parking.

[0048] Figure 3 This is a flowchart illustrating a method for generating a road topology map according to some embodiments of the present disclosure, such as... Figure 3 As shown, it includes the following steps:

[0049] Step 301: Obtain the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information.

[0050] The specific implementation of step 301 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0051] Step 302: Determine the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, wherein the distance between each trajectory point and the corresponding candidate edge line is less than a first threshold.

[0052] In some embodiments, candidate edges can be determined based on the distance between the trajectory point and each edge in the boundary information.

[0053] The first threshold can be 5 meters, 6 meters, etc. This disclosure does not limit it.

[0054] The candidate edge line corresponding to any trajectory point on any side of the historical driving trajectory can include at least one of the following: road edge line, wall edge line, and parking space edge line.

[0055] Step 303: Based on the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, determine the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory.

[0056] In some embodiments, if there is only one candidate edge line corresponding to the trajectory point on either side of the historical driving trajectory, the candidate edge line is directly determined as the target edge line.

[0057] In some embodiments, when there are multiple candidate edges corresponding to any trajectory point on either side of the historical driving trajectory, the edge with the highest priority among the multiple candidate edges is determined as the target edge corresponding to any trajectory point on either side of the historical driving trajectory. Therefore, only one edge with the highest priority needs to be determined to define the passable area, thus obtaining a more complete and accurate boundary of the passable area.

[0058] Among them, the priority of road edge lines is higher than that of wall edge lines, and the priority of wall edge lines is higher than that of storage location edge lines.

[0059] For example, if a road edge exists among the candidate edges corresponding to one side of the historical driving trajectory, the road edge is determined as the target edge; or, if a wall edge exists among the candidate edges corresponding to one side of the historical driving trajectory, the wall edge is determined as the target edge; or, if neither a road edge nor a wall edge exists among the candidate edges corresponding to one side of the historical driving trajectory, but a parking space edge exists, the parking space edge is determined as the target edge.

[0060] Step 304: Determine the boundary of the passable area based on the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory.

[0061] It should be noted that the target edge line corresponding to two adjacent trajectory points may be the same, and some trajectory points may not have a target edge line. Therefore, in this embodiment, the target edge lines can be deduplicated first to obtain the initial boundary. If the initial boundary is discontinuous, the broken areas are filled to obtain the passable area boundary. Thus, a complete and continuous passable area boundary can be obtained.

[0062] Step 305: Determine the center line of the roads traversed by the historical driving trajectory based on the boundaries of the passable area and the historical driving trajectory.

[0063] Step 306: Based on the intersection location information, update the road centerline and generate a road topology map.

[0064] The specific implementation of steps 305 and 306 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0065] In this embodiment, the historical driving trajectory of the vehicle within the target area, the intersection location information, and the boundary information within the target area are obtained. Then, candidate edges corresponding to each trajectory point on both sides of the historical driving trajectory are determined. Based on the candidate edges corresponding to each trajectory point on both sides of the historical driving trajectory, target edges corresponding to each trajectory point on both sides of the historical driving trajectory are determined. Based on the target edges corresponding to each trajectory point on both sides of the historical driving trajectory, the boundary of the passable area is determined. Finally, based on the boundary of the passable area and the historical driving trajectory, the road centerline of the roads traversed by the historical driving trajectory is determined. Based on the intersection location information, the road centerline is updated to generate a road topology map. Therefore, based on the boundary information within the target area, the boundary of the passable area can be accurately and completely determined, providing accurate data support for subsequent determination of the road centerline and the drivable area of ​​the vehicle during valet parking, thereby making the generated road topology map more accurate.

[0066] Figure 4 This is a flowchart illustrating a method for generating a road topology map according to some embodiments of the present disclosure, such as... Figure 4 As shown, it includes the following steps:

[0067] Step 401: Obtain the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information.

[0068] Step 402: Determine the passable area boundaries of the roads traversed by the historical driving trajectory based on the historical driving trajectory and boundary information.

[0069] The specific implementation of steps 401 and 402 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0070] Step 403: Determine the grid corresponding to the first region, wherein the distance between each coordinate point in the first region and the historical driving trajectory is less than the second threshold.

[0071] The second threshold can be 10 meters, 15 meters, etc. This disclosure does not limit it.

[0072] The size of each sub-grid in the grid corresponding to the first region can be 0.2 meters, 0.3 meters, etc. This disclosure does not limit this.

[0073] Step 404: Determine the second distance between each sub-grid in the grid and the boundary of the passable area.

[0074] In some embodiments, the distance from the center point of each sub-grid to the boundary of the passable area can be calculated according to the point-to-curve distance calculation method, thereby obtaining a second distance between each sub-grid and the boundary of the passable area.

[0075] In some embodiments, the boundaries of the traversable area can be sampled to obtain a boundary point cloud. Then, a k-dimensional tree (kd-tree) corresponding to the boundary point cloud is generated. Based on the nearest neighbor tree, the target point cloud closest to the center point of each sub-grid is determined from the boundary point cloud. The distance between the center point of each sub-grid and the corresponding target point cloud is determined as the second distance between each sub-grid and the traversable area boundary. Thus, based on the nearest neighbor tree, the second distance between each sub-grid in the grid and the traversable area boundary can be quickly determined, thereby improving the efficiency of generating the road topology map.

[0076] In some embodiments, the point cloud located in the middle position of the boundary point cloud can be determined as the root node of the nearest neighbor search tree, and the point clouds located on both sides of the line where the middle point cloud is located can be determined as the left subtree and right subtree of the root node, respectively. This process is recursively iterated until all point clouds are assigned to nodes in the nearest neighbor search tree.

[0077] In some embodiments, a hash table corresponding to the grid of the first region can be generated based on the second distance corresponding to each sub-grid and whether it is within the boundary of the passable area, so that the second distance between each sub-grid and the boundary of the passable area, and whether it is within the passable area can be quickly queried.

[0078] Step 405: If the second distance corresponding to the sub-grid where the trajectory point is located in the historical driving trajectory is less than the second distance corresponding to at least one adjacent sub-grid, the center point of the adjacent sub-grid with the largest second distance is determined as the updated trajectory point corresponding to the trajectory point, until the second distance corresponding to the sub-grid where the updated trajectory point is located is greater than or equal to the second distance corresponding to the adjacent sub-grid.

[0079] For example, the sub-grid where the trajectory point is located is sub-grid 1. The adjacent sub-grids of sub-grid 1 are sub-grid 2, sub-grid 3, sub-grid 4, sub-grid 5, sub-grid 6, sub-grid 7, sub-grid 8, and sub-grid 9. Among them, the second distances corresponding to sub-grids 7, sub-grid 8, and sub-grid 9 are greater than the second distances corresponding to sub-grid 1, and the second distance corresponding to sub-grid 9 is the largest. Therefore, the center point of sub-grid 9 is determined as the updated trajectory point corresponding to the trajectory point. Then, the target sub-grid with the largest second distance among the adjacent sub-grids of sub-grid 9 and greater than the second distance corresponding to sub-grid 9 is determined. The center point of the target sub-grid is determined as the updated trajectory point corresponding to the trajectory point. This process is iterated until the second distance of the target sub-grid is greater than the second distances corresponding to its adjacent sub-grids.

[0080] Step 406: Smooth the updated trajectory points corresponding to each trajectory point to obtain the road centerline.

[0081] In some embodiments, a trajectory smoothing algorithm can be used to smooth the updated trajectory points corresponding to each trajectory point to obtain the road centerline. The trajectory smoothing algorithm can be an S-curve algorithm, a polynomial curve algorithm, a moving average smoothing algorithm, a Kalman filter algorithm, etc. This disclosure does not limit the specific algorithm used.

[0082] Step 407: Based on the intersection location information, update the road centerline and generate a road topology map.

[0083] In this embodiment, the historical driving trajectory of a vehicle within a target area, intersection location information, and boundary information within the target area are obtained. Based on the historical driving trajectory and boundary information, the traversable area boundary of the road traversed by the historical driving trajectory is determined. Then, a grid corresponding to a first area is determined. Where the distance between each coordinate point in the first area and the historical driving trajectory is less than a second threshold, a second distance between each sub-grid in the grid and the traversable area boundary is determined. If the second distance corresponding to the sub-grid containing a trajectory point in the historical driving trajectory is less than the second distance corresponding to at least one adjacent sub-grid, the center point of the adjacent sub-grid with the largest second distance is determined as the updated trajectory point corresponding to the trajectory point. This process continues until the second distance corresponding to the sub-grid containing the updated trajectory point is greater than or equal to the second distance corresponding to the adjacent sub-grids. Finally, the updated trajectory points corresponding to each trajectory point are smoothed to obtain the road centerline. Therefore, based on the historical driving trajectory and the second distance between each sub-grid and the traversable area boundary, the road centerline of the road traversed by the historical driving trajectory can be determined quickly and accurately, thereby improving the efficiency of the generated road topology map.

[0084] To implement the above embodiments, this disclosure also proposes a road topology map generation apparatus.

[0085] Figure 5 This is a block diagram of a road topology map generation apparatus according to some embodiments of this disclosure. (Refer to...) Figure 5 The device includes:

[0086] The acquisition module 501 is used to acquire the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information;

[0087] The first determining module 502 is used to determine the passable area boundary of the road traversed by the historical driving trajectory based on the historical driving trajectory and boundary information.

[0088] The second determining module 503 is used to determine the center line of the road traversed by the historical driving trajectory based on the boundary of the passable area and the historical driving trajectory.

[0089] The generation module 504 is used to update the road centerline based on the intersection location information and generate a road topology map.

[0090] In some embodiments, the generation module 504 is configured to:

[0091] Determine the first coordinate point as the distance between the centerline of the road and the center of the intersection;

[0092] Based on the boundary of the passable area, generate a connection line between the center of the intersection and the first coordinate point;

[0093] Based on the connecting lines, the line segments between the first coordinate point and the second coordinate point in the road centerline are replaced to generate a road topology map, where the second coordinate point is the coordinate point on the road centerline that is closest to the center of the intersection.

[0094] In some embodiments, the first determining module 502 is configured to:

[0095] Determine the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, wherein the distance between each trajectory point and its corresponding candidate edge line is less than a first threshold.

[0096] Based on the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, determine the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory.

[0097] Based on the target edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, the boundary of the passable area is determined.

[0098] In some embodiments, the first determining module 502 is configured to:

[0099] When there are multiple candidate edges corresponding to any trajectory point on any side of the historical driving trajectory, the edge with the highest priority among the multiple candidate edges is determined as the target edge corresponding to any trajectory point on any side of the historical driving trajectory. Among them, the priority of road edges is higher than that of wall edges, and the priority of wall edges is higher than that of parking space edges.

[0100] In some embodiments, the first determining module 502 is configured to:

[0101] The target edge lines are deduplicated to obtain the initial boundary;

[0102] When the initial boundary is discontinuous, the broken areas are filled to obtain the boundary of the passable area.

[0103] In some embodiments, the second determining module 503 is configured to:

[0104] Determine the grid corresponding to the first region, wherein the distance between each coordinate point in the first region and the historical driving trajectory is less than a second threshold.

[0105] Determine a second distance between each sub-cell in the grid and the boundary of the passable area;

[0106] If the second distance corresponding to the sub-grid where the trajectory point is located in the historical driving trajectory is less than the second distance corresponding to at least one adjacent sub-grid, the center point of the adjacent sub-grid with the largest second distance is determined as the updated trajectory point corresponding to the trajectory point, until the second distance corresponding to the sub-grid where the updated trajectory point is located is greater than or equal to the second distance corresponding to the adjacent sub-grid.

[0107] The updated trajectory points corresponding to each trajectory point are smoothed to obtain the road centerline.

[0108] In some embodiments, the second determining module 503 is configured to:

[0109] The boundary of the passable area is sampled to obtain the boundary point cloud;

[0110] Generate the nearest neighbor search tree corresponding to the boundary point cloud;

[0111] Based on the nearest neighbor search tree, determine the target point cloud that is closest to the center point of each sub-grid from the boundary point cloud;

[0112] The distance between the center point of each sub-grid and the corresponding target point cloud is determined as the second distance between each sub-grid and the boundary of the passable area.

[0113] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0114] The road topology map generation apparatus of this disclosure first acquires the historical driving trajectory of a vehicle within a target area, intersection location information, and boundary information within the target area; based on the historical driving trajectory and boundary information, it determines the traversable area boundaries of the roads traversed by the historical driving trajectory; based on the traversable area boundaries and the historical driving trajectory, it determines the road centerlines of the roads traversed by the historical driving trajectory; and based on the intersection location information, it updates the road centerlines to generate a road topology map. Thus, a road topology map of the target area can be accurately constructed based on the historical driving trajectory, and the road topology map includes the connection relationships between intersections and roads, as well as the connection relationships between roads, thereby enabling path planning from any starting point to the destination within the target area, improving the flexibility and success rate of valet parking.

[0115] Figure 6 This is a block diagram illustrating a vehicle 600 according to an exemplary embodiment. For example, vehicle 600 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 600 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0116] Reference Figure 6The vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 600 can be interconnected via wired or wireless means.

[0117] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, and a navigation system. The perception system 620 may include various sensors for sensing information about the environment surrounding the vehicle 600. For example, the perception system 620 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0118] The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system. The drive system 640 may include components that provide power to the vehicle 600. In one embodiment, the drive system 640 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0119] Some or all of the functions of vehicle 600 are controlled by computing platform 650. Computing platform 650 may include at least one processor 651 and memory 652, processor 651 can execute instructions 653 stored in memory 652.

[0120] Processor 651 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0121] The memory 652 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0122] In addition to instruction 653, memory 652 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 652 can be used by computing platform 650. In this embodiment of the present disclosure, processor 651 can execute instruction 653 to complete all or part of the steps of the above-described method for generating a road topology map.

[0123] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the method for generating a road topology map provided in this disclosure.

[0124] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0125] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0126] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0127] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for generating a road topology map, characterized in that, The method includes: Obtain the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information; Based on the historical driving trajectory and the boundary information, determine the traversable area boundary of the road traversed by the historical driving trajectory; Based on the boundaries of the passable area and the historical driving trajectory, determine the centerline of the road along the historical driving trajectory; Based on the intersection location information, the road centerline is updated to generate a road topology map.

2. The method according to claim 1, characterized in that, The intersection location information includes the intersection center location. The step of updating the road centerline based on the intersection location information and generating a road topology map includes: Determine the first coordinate point on the road centerline whose distance from the center position of the intersection is the first distance; Based on the boundary of the passable area, a connecting line is generated between the center of the intersection and the first coordinate point; Based on the connecting line, the line segment from the first coordinate point to the second coordinate point in the road centerline is replaced to generate the road topology map, wherein the second coordinate point is the coordinate point on the road centerline that is closest to the center position of the intersection.

3. The method according to claim 1, characterized in that, in, The boundary information includes road edge lines, wall edge lines, and parking space edge lines. Determining the passable area boundary of the roads traversed by the historical driving trajectory based on the historical driving trajectory and the boundary information includes: Determine the candidate edge lines corresponding to each trajectory point in the historical driving trajectory on both sides of the historical driving trajectory, wherein the distance between each trajectory point and the corresponding candidate edge line is less than a first threshold. Based on the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory, the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory is determined. The boundary of the passable area is determined based on the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory.

4. The method according to claim 3, characterized in that, The step of determining the target edge line corresponding to each trajectory point on both sides of the historical driving trajectory based on the candidate edge lines corresponding to each trajectory point on both sides of the historical driving trajectory includes: If there are multiple candidate edges corresponding to any trajectory point on any side of the historical driving trajectory, the edge with the highest priority among the multiple candidate edges is determined as the target edge corresponding to any trajectory point on any side of the historical driving trajectory. The priority of the road edge is higher than that of the wall edge, and the priority of the wall edge is higher than that of the parking space edge.

5. The method according to claim 3, characterized in that, The step of determining the boundary of the passable area based on the target edge lines corresponding to each trajectory point on both sides of the historical driving trajectory includes: The target edge lines are deduplicated to obtain the initial boundary; If the initial boundary is discontinuous, the broken areas are filled to obtain the passable area boundary.

6. The method according to claim 1, characterized in that, The step of determining the road centerline of the roads traversed by the historical driving trajectory based on the boundary of the passable area and the historical driving trajectory includes: Determine the grid corresponding to the first region, wherein the distance between each coordinate point in the first region and the historical driving trajectory is less than a second threshold. Determine a second distance between each sub-cell in the grid and the boundary of the passable area; If the second distance corresponding to the sub-grid where the trajectory point is located in the historical driving trajectory is less than the second distance corresponding to at least one adjacent sub-grid, the center point of the adjacent sub-grid with the largest second distance is determined as the updated trajectory point corresponding to the trajectory point, until the second distance corresponding to the sub-grid where the updated trajectory point is located is greater than or equal to the second distance corresponding to the adjacent sub-grid. The updated trajectory points corresponding to each trajectory point are smoothed to obtain the road centerline.

7. The method according to claim 6, characterized in that, Determining the second distance between each sub-cell in the grid and the boundary of the passable area includes: The boundary of the passable area is sampled to obtain a boundary point cloud; Generate the nearest neighbor search tree corresponding to the boundary point cloud; Based on the nearest neighbor search tree, the target point cloud that is closest to the center point of each sub-grid is determined from the boundary point cloud; The distance between the center point of each sub-grid and the corresponding target point cloud is determined as the second distance between each sub-grid and the boundary of the passable area.

8. A method and apparatus for generating a road topology map, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's historical driving trajectory within the target area, the intersection location information within the target area, and the boundary information; The first determining module is used to determine the passable area boundary of the road traversed by the historical driving trajectory based on the historical driving trajectory and the boundary information. The second determining module is used to determine the center line of the road along the historical driving trajectory based on the boundary of the passable area and the historical driving trajectory. The generation module is used to update the road centerline based on the intersection location information and generate a road topology map.

9. A vehicle, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to implement the steps of the method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of a mobile terminal, implement the steps of the method according to any one of claims 1-7.

Images