Vehicle end navigation path generation method and device, vehicle and storage medium

Abstract

The application discloses a vehicle-end navigation path 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: obtaining driving track data and initial navigation information; performing data cleaning processing on the initial navigation information based on the driving track data, to obtain intermediate navigation information; performing interval sampling on the driving track data by using the intermediate navigation information, to obtain a sampling result; and performing splicing processing on the intermediate navigation information and the sampling result, to obtain a vehicle-end navigation path. The application solves the technical problems that the navigation path of the vehicle navigation scheme in the related art is difficult to adapt to the personalized driving track demand and the automatic driving user experience is poor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle-end navigation path generation method and device, a vehicle and a storage medium. BACKGROUND

[0002] In automatic driving, a vehicle usually travels in real time following navigation data (such as V2 navigation path) issued by a navigation system. The navigation data contains a large amount of navigation position information and road structure information, so that the vehicle can intelligently select a reasonable travel route.

[0003] In the Artificial Intelligence (AI) driving scenario of automatic driving, the vehicle records the personalized driving route of the driver in the path learning stage. The personalized driving route will affect the navigation data issued by the navigation system, and in this process, the vehicle will generate and record multiple fragmented navigation data. However, it is difficult to generate a complete navigation path that matches the personalized driving route based on fragmented navigation data, which not only reduces user experience because the navigation cannot meet the personalized driving needs, but also reduces the safety of AI driving.

[0004] At present, there is no effective solution to the above problems. SUMMARY

[0005] Embodiments of the present application provide a vehicle-end navigation path generation method and device, a vehicle and a storage medium, to at least solve the technical problems that the navigation path of the vehicle navigation scheme in the related art is difficult to adapt to the personalized driving trajectory demand and the user experience of automatic driving is poor.

[0006] According to an aspect of an embodiment of the present application, a vehicle navigation method is provided, comprising: obtaining driving trajectory data and initial navigation information, wherein the driving trajectory data is used to represent a target driving trajectory recorded by a target vehicle in a path learning stage, and the initial navigation information includes road segment navigation data corresponding to multiple segments of yaw path in the path learning stage; performing data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; performing interval sampling on the driving trajectory data using the intermediate navigation information to obtain a sampling result; and performing splicing processing on the intermediate navigation information and the sampling result to obtain a vehicle-end navigation path.

[0007] Optionally, the road segment navigation data at least includes road structure data and vehicle navigation data.

[0008] Optionally, based on the driving trajectory data, the initial navigation information is subjected to data cleaning processing to obtain intermediate navigation information, including: for any target yaw path in the plurality of yaw paths, based on the driving trajectory data and the initial navigation information, the target driving trajectory and the target yaw path are subjected to distance matching to obtain a matching result; based on the matching result, part of the navigation information in the initial navigation information corresponding to the target yaw path is subjected to data segmentation and data pruning to obtain the intermediate navigation information.

[0009] Optionally, based on the driving trajectory data and the initial navigation information, the target driving trajectory and the target yaw path are subjected to distance matching to obtain a matching result, including: the trajectory points on the target driving trajectory and the navigation points on the target yaw path are traversed, and based on the driving trajectory data and the initial navigation information, the distance between the current trajectory point and the current navigation point in the traversal is calculated; a matching relationship between the trajectory points and the navigation points is established according to the distance to obtain the matching result.

[0010] Optionally, the matching relationship between the trajectory points and the navigation points is established according to the distance, including: in response to the distance between the current trajectory point and the current navigation point in the continuous target quantity in the traversal satisfying the target condition, the matching relationship between the trajectory points and the corresponding navigation points is sequentially established from the first trajectory point in the continuous target quantity of the current trajectory points.

[0011] Optionally, based on the matching result, part of the navigation information in the initial navigation information corresponding to the target yaw path is subjected to data segmentation and data pruning to obtain the intermediate navigation information, including: based on the matching result and the part of the navigation information, a data segmentation point is determined, wherein the distance between the navigation point corresponding to the data segmentation point and the matched trajectory point is greater than a preset threshold, or the navigation point corresponding to the data segmentation point is not within the road range corresponding to the matched trajectory point; the part of the navigation information is subjected to data segmentation according to the data segmentation point to obtain a segmentation result; based on the matching result and the segmentation result, a data pruning point is determined, wherein the navigation point corresponding to the data pruning point is at the target yaw path and the target driving trajectory is separated; the segmentation result is subjected to data pruning according to the data pruning point to obtain the intermediate navigation information.

[0012] Optionally, the driving trajectory data is subjected to interval sampling based on the intermediate navigation information to obtain a sampling result, including: the intermediate navigation information and the driving trajectory data are subjected to route comparison to obtain a road section interval to be sampled; the driving trajectory data is subjected to interval sampling based on the road section interval to obtain the sampling result.

[0013] Optionally, the intermediate navigation information and the driving trajectory data are subjected to route comparison to obtain a road section interval to be sampled, including: the intermediate navigation information is subjected to route analysis to determine a navigation road section; based on the part of the target driving trajectory corresponding to the driving trajectory data that is not covered by the navigation road section, a road section interval is determined.

[0014] Optionally, the interval sampling of the driving trajectory data based on the road section interval comprises: determining a target sampling strategy based on a road type corresponding to the road section interval; and performing interval sampling on the driving trajectory data based on the road section interval and the target sampling strategy to obtain the sampling result.

[0015] Optionally, the sampling result comprises a plurality of trajectory sampling points on the vehicle driving trajectory; and the splicing of the intermediate navigation information and the sampling result to obtain the target navigation information comprises: obtaining road structure data and vehicle navigation data matched with the plurality of trajectory sampling points; generating to-be-spliced navigation information based on the road structure data and the vehicle navigation data; and performing navigation semantic splicing on the intermediate navigation information and the to-be-spliced navigation information to obtain a vehicle-side navigation path.

[0016] According to another aspect of the embodiments of the present application, a vehicle navigation device is further provided, comprising: an acquisition module configured to acquire driving trajectory data and initial navigation information, wherein the driving trajectory data is used to represent a target driving trajectory recorded by a target vehicle in a path learning stage, and the initial navigation information comprises road section navigation data corresponding to a plurality of yaw paths in the path learning stage; a data processing module configured to perform data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; a sampling module configured to perform interval sampling on the driving trajectory data by using the intermediate navigation information to obtain a sampling result; a splicing module configured to perform splicing processing on the intermediate navigation information and the sampling result to obtain target navigation information; and a navigation module configured to generate a navigation instruction according to the target navigation information, wherein the navigation instruction is used to control the target vehicle to travel along the target driving trajectory.

[0017] According to another aspect of the embodiments of the present application, a vehicle is further provided, comprising a vehicle-mounted storage and a vehicle-mounted processor, the vehicle-mounted storage stores a computer program, and the vehicle-mounted processor is configured to run the computer program to execute the vehicle navigation method of any one of the above.

[0018] According to another aspect of the embodiments of the present application, a computer readable storage medium is further provided, comprising a stored executable program, wherein the executable program controls a device where the storage medium is located to execute the vehicle navigation method of any one of the above when the executable program is running.

[0019] According to another aspect of the embodiments of the present application, a computer program product is further provided, comprising a computer program, the computer program is executed by a processor to implement the vehicle navigation method according to any one of the above.

[0020] In the embodiment of the present application, first, the driving track data and the initial navigation information are acquired; based on the driving track data, the initial navigation information is subjected to data cleaning processing to obtain intermediate navigation information; the intermediate navigation information is used to perform interval sampling on the driving track data to obtain a sampling result; the intermediate navigation information and the sampling result are subjected to splicing processing to obtain a vehicle-end navigation path. In the present application, the driving track data is used to represent a target driving track recorded by a target vehicle in a path learning stage, and the initial navigation information includes road section navigation data corresponding to a plurality of sections of yaw path in the path learning stage, which can represent the individualized needs of the user in driving. The above target driving track can be regarded as a more preferred driving track of the user. Therefore, the generated vehicle-end navigation path not only contains more detailed road section navigation data on part of the navigation path, but also makes the final target navigation path consistent with the vehicle driving track route, thereby achieving the purpose of generating a vehicle-end navigation path with comprehensive and complete data and route customization, thereby realizing the technical effects of improving the adaptability of the vehicle navigation path to the individualized needs of the user and enhancing the user experience, and further solving the technical problems of the related art that the navigation path of the vehicle navigation scheme is difficult to adapt to the individualized driving track needs and the user experience of automatic driving is poor. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate certain illustrative embodiments of the present application and related descriptions of the embodiments, and do not constitute improper limitations on the present application. In the drawings:

[0022] Figure 1 is a hardware structure block diagram of a computing terminal for implementing a vehicle navigation method according to an embodiment of the present application;

[0023] Figure 2 is a flowchart of a vehicle navigation method according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a navigation path and a driving track according to an embodiment of the present application;

[0025] Figure 4 is a structure block diagram of a vehicle navigation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments only include part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should belong to the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] According to the embodiments of the present application, a method embodiment of a vehicle navigation method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0029] First, the running environment of the above-mentioned method embodiment is exemplarily described. Figure 1 is a hardware structure block diagram of an optional computing terminal for implementing a vehicle navigation method according to the embodiments of the present application, as Figure 1 shown, the computing terminal 10 (for example, a computer terminal, a mobile intelligent terminal, a vehicle terminal or a cloud computing virtual terminal, etc.) can include one or more processors 102, a memory 104 for storing data and a transmission device 106 for implementing communication functions, wherein each processor 102 can include but not limited to a processing component such as a microcontroller unit (MCU) or a field programmable gate array (FPGA) and the like.

[0030] The computing terminal 10 can further include a display device 110, an input / output device 108, a Universal Serial Bus (USB) port (which can be one of the ports of a computer bus, not shown), a network interface (not shown), a power supply (not shown), and a camera (not shown). Those skilled in the art will appreciate that Figure 1 The structure of the computing terminal 10 shown is merely illustrative and does not impose strict limitations on the structure of the computing terminal 10. For example, the computing terminal 10 can include more or fewer components than those shown in FIG. 1, or the computing terminal 10 can have different classes of components than those shown in FIG. 1. Figure 1 For example, the computing terminal 10 can include more or fewer components than those shown in FIG. 1, or the computing terminal 10 can have different classes of components than those shown in FIG. 1. Figure 1 For example, the computing terminal 10 can include more or fewer components than those shown in FIG. 1, or the computing terminal 10 can have different classes of components than those shown in FIG. 1.

[0031] It should be noted that one or more processors 102 and / or other data processing circuits in the computing terminal 10 can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuits can be a single independent processing module or can be incorporated in whole or in part into any one of the other elements in the computing terminal 10 (or mobile device).

[0032] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage means corresponding to the vehicle navigation method in the embodiments of the present application. The processor 102 can execute various functional applications and data processing by running the software programs and modules stored in the memory 104, i.e., implement the vehicle navigation method described above. The memory 104 can include a high-speed random access memory and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely disposed relative to the processor 102, which can be connected to the computing terminal 10 through a network. Examples of the network can include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0033] The transmission device 106 is configured to receive or send data via a network. Examples of the network can include a wireless network provided by a communication provider of the computing terminal 10. In one example, the transmission device 106 includes a network adapter (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module configured to communicate with the Internet in a wireless manner.

[0034] In the above operating environment, the embodiment of the present application provides a vehicle navigation method as shown in Figure 2 Figure 2 The flow chart of a vehicle navigation method according to the embodiment of the present application is shown in Figure 2

[0035] Step S201, obtaining driving track data and initial navigation information, wherein the driving track data is used to represent the target driving track recorded by the target vehicle in the path learning stage, and the initial navigation information includes the road segment navigation data corresponding to the multiple yaw paths in the path learning stage.

[0036] Step S202, based on the driving track data, performing data cleaning processing on the initial navigation information to obtain intermediate navigation information.

[0037] Step S203, using the intermediate navigation information to perform interval sampling on the driving track data to obtain a sampling result.

[0038] Step S204, performing splicing processing on the intermediate navigation information and the sampling result to obtain a vehicle-end navigation path.

[0039] The above implementation steps provided by the embodiment of the present application can be used to realize cloud mapping in the artificial intelligence (AI) driving scene in the field of automatic driving technology, that is, to obtain a navigation map stored in the cloud, which can be used to determine multiple candidate vehicle-end navigation paths corresponding to multiple user personalized driving route requirements. In the path learning stage in the AI driving scene, the track data corresponding to the actual driving track of the vehicle after the user's manual intervention operation (such as starting manual driving, changing the preferred route, changing the way points, etc.) is recorded, and the navigation data (containing detailed information such as turns, lanes, and forks) given by the navigation system for the multiple road segments deviated by the user's manual intervention is spliced for the vehicle end to generate the candidate vehicle-end navigation path stored in the cloud. The vehicle-end navigation path can not only keep the route consistent with the actual driving track of the vehicle and meet the user's personalized requirements, but also contain as much detailed navigation data as possible. After the path learning is completed, when the vehicle needs to navigate along the driving track again (which can be manual driving or automatic driving), the cloud will download the spliced vehicle-end navigation path to the vehicle to help the vehicle correctly and safely travel according to the user's personalized driving track.

[0040] ​​In an application scenario, the actual driving trajectory can be considered as a driving route that can represent the personalized driving demand of a user, and in this case, the actual driving trajectory is taken as a target driving trajectory, and the recorded trajectory data is taken as the driving trajectory data. Further, the user's manual intervention operation will trigger multiple yaw events, and the vehicle will update the navigation of the yaw section for each yaw event. At the same time, the vehicle will record the section navigation data corresponding to the multiple yaw path sections when the multiple yaw events occur, and obtain initial navigation information.

[0041] In the process of automatic driving, the vehicle can obtain the driving trajectory data and the initial navigation information when performing a target trip, generate a vehicle-end navigation path according to the method steps provided in the embodiments of the present application, and further control the target vehicle to travel along the target driving trajectory according to the vehicle-end navigation path to complete the target trip. The starting point and the ending point of the target trip are the same as or close to the starting point and the ending point of the target driving trajectory.

[0042] In particular, the section navigation data is V2 navigation data that is updated in real time by the vehicle when the yaw event is triggered and is issued through the vehicle central control screen. The V2 navigation data can contain more comprehensive navigation-related data, and in particular, the V2 navigation data can record more detailed road structure information so that the vehicle automatic driving system can make more accurate driving decisions based on the road structure information.

[0043] In order to obtain V2 navigation data that is consistent with the target driving trajectory route and has complete and comprehensive navigation information, the initial navigation information is subjected to data cleaning processing based on the driving trajectory data, and the part of data in the initial navigation information that is inconsistent with the target driving trajectory route is removed, to obtain intermediate navigation information.

[0044] Further, the intermediate navigation information includes V2 navigation data corresponding to the part of the navigation path that is consistent with the target driving trajectory route, and based on this, the driving trajectory data is subjected to data sampling in an interval that is not covered by the part of the navigation path on the target driving trajectory, to obtain a sampling result, which at least includes trajectory position data corresponding to multiple trajectory sampling points.

[0045] Further, the trajectory position data corresponding to the plurality of trajectory sampling points in the sampling result is converted into V2 navigation data corresponding to the plurality of trajectory sampling points, specifically, based on the trajectory position data, the V2 navigation data corresponding to the plurality of trajectory sampling points is queried from a historical navigation database, at this time, the trajectory position data and the V2 navigation data of each trajectory sampling point can also be combined and processed to update the V2 navigation data. The intermediate navigation information and the V2 navigation data corresponding to the plurality of trajectory sampling points are spliced to obtain a vehicle-end navigation path. The target navigation path corresponding to the vehicle-end navigation path is consistent with the target driving trajectory route, and the vehicle-end navigation path includes V2 navigation data corresponding to the entire target navigation path.

[0046] It is easy to note that the above method provided by the embodiments of the present application can effectively fuse the actual driving data of the vehicle and the basic information of the navigation system, improve the accuracy of path planning and navigation control of the autonomous vehicle, and is suitable for complex driving environments such as urban roads and highways, and can provide more accurate navigation guidance when dealing with road branches, roundabouts, complex intersections and the like.

[0047] Through the technical solutions provided by the above steps S201 to S205, the present application first acquires driving trajectory data and initial navigation information; based on the driving trajectory data, the initial navigation information is subjected to data cleaning processing to obtain intermediate navigation information; the intermediate navigation information is used to sample the driving trajectory data in intervals to obtain a sampling result; the intermediate navigation information and the sampling result are subjected to splicing processing to obtain a vehicle-end navigation path; and the target vehicle is controlled to drive along a target driving trajectory according to the vehicle-end navigation path. In the present application, the driving trajectory data is used to represent the target driving trajectory recorded by the target vehicle in the path learning stage, the initial navigation information includes road segment navigation data corresponding to a plurality of segments of yaw path in the path learning stage, the plurality of segments of yaw path can represent the individualized needs in user driving, and the above target driving trajectory can be regarded as a driving trajectory preferred by the user. Therefore, the generated vehicle-end navigation path not only contains more detailed road segment navigation data on part of the navigation path, but also enables the final target navigation path to be consistent with the driving trajectory route of the vehicle, thereby achieving the purpose of generating a vehicle-end navigation path with comprehensive and complete data and customized route, and realizing the technical effects of improving the adaptability of the vehicle navigation path to the individualized needs of the user and enhancing the user experience, and further solving the technical problems of the related art that the navigation path of the vehicle navigation scheme is difficult to adapt to the individualized driving trajectory needs and the user experience of autonomous driving is poor.

[0048] The vehicle-end navigation path generation scheme provided by the embodiments of the present application is mainly suitable for scenarios involving generating real-time and detailed navigation paths for the vehicle end in the field of intelligent driving technology, and can exhibit significant advantages in the following application scenarios (only examples, not limited thereto).

[0049] In the artificial intelligence chauffeur service, the vehicle needs to learn and adapt to the personalized driving habits and route preferences of the driver. The above-mentioned vehicle-end navigation path generation method generates a complete navigation path that adapts to personalized needs by fusing actual driving trajectory data and initial navigation information, significantly improving the user experience and safety of the automatic driving chauffeur service.

[0050] In the urban road driving scenario, the urban road environment is relatively complex, such as roads including intersections, roundabouts, bifurcated roads, etc. The above-mentioned vehicle-end navigation path generation method can provide more accurate navigation guidance for roads that handle these complex scenarios, especially when the driver temporarily changes the route or there are sudden situations such as road construction, it can quickly adjust and generate a navigation path that matches the actual driving trajectory.

[0051] In the highway driving scenario, the speed and safety requirements of the vehicle are higher, and the above-mentioned vehicle-end navigation path generation method ensures the accuracy of the navigation path through interval sampling and splicing of navigation information, especially when handling key decision points such as highway exits and service area entrances, providing more detailed road structure data and vehicle navigation data.

[0052] The above-mentioned vehicle-end navigation path generation method can also be integrated into an intelligent transportation system to optimize traffic flow and improve road utilization efficiency. By collecting and processing the actual driving trajectory data of vehicles, more reasonable route planning can be generated to reduce traffic congestion and improve the overall efficiency of the transportation network.

[0053] In the special vehicle navigation scenario, for special vehicles such as rescue vehicles, fire vehicles, military vehicles, etc., the above-mentioned vehicle-end navigation path generation method can generate navigation paths that adapt to special driving needs, especially in emergency situations, it can quickly plan and execute the best route to improve task execution efficiency and safety.

[0054] In summary, the above-mentioned vehicle-end navigation path generation method provided by the present application not only applies to the general driving needs of autonomous vehicles, but also provides more accurate, safer, and more personalized navigation services in various complex scenarios, with wide application prospects.

[0055] The following takes the artificial intelligence chauffeur application scenario as an example to further introduce other optional implementation modes of the above-mentioned vehicle-end navigation path generation method provided by the embodiments of the present application.

[0056] As an optional implementation mode, the above-mentioned road segment navigation data at least includes road structure data and vehicle navigation data.

[0057] The road structure data can specifically include the following data: road name, such as the formal name or number of the road; road type, such as expressway, urban road, rural road, etc.; number of lanes, such as the number of lanes of the road (to help the autonomous driving system select the appropriate lane to travel); lane type, such as ordinary lane, left turn lane, right turn lane, etc.; lane speed limit, such as speed limit information of each lane; lane direction, such as the driving direction of each lane; intersection information, such as the location and turning indication of the intersection, including left turn, right turn, straight, etc.; road level, such as expressway, main road, secondary road, etc.; road length; road width, such as total road width, lane width, etc.; road marking, such as traffic signs and markings on the road, including lane dividers, speed limit signs, intersection signs, etc.; road conditions, such as road surface conditions, slope, etc.

[0058] The vehicle navigation data can specifically include the following data: map data, such as road, intersection, landmark, etc.; positioning data, such as real-time position, speed, direction, etc. of the vehicle; route planning data, such as optimal path, traffic conditions, estimated arrival time, etc.; voice navigation data, such as voice guidance, prompt, warning, etc.; traffic information data, such as real-time traffic conditions, accidents, construction, etc.; point of interest data, such as gas station, restaurant, scenic spot, etc.; vehicle information data, such as vehicle model, speed, fuel level, etc.; driving behavior data, such as sudden braking, speeding, etc.; warning data, such as dangerous sections, speed limit warnings, etc.; user preference data, such as user-set preferences, frequently used routes, etc.

[0059] The road segment navigation data in the present application can be V2 navigation data including more granular road structure data and vehicle navigation data. By subdividing the navigation data, the present application can more accurately match the actual driving trajectory of the vehicle, enhance the execution effect of the navigation instructions, and especially in complex road structure and variable vehicle navigation demand scenarios, provide more detailed and comprehensive navigation information, and improve the driving safety and user experience of the autonomous vehicle.

[0060] As an optional implementation, in step S202, based on the driving trajectory data, the initial navigation information is subjected to data cleaning processing to obtain intermediate navigation information, which can further include the following execution steps:

[0061] In step S221, for any one of the target yaw paths in the plurality of yaw paths, based on the driving trajectory data and the initial navigation information, the target driving trajectory and the target yaw path are subjected to distance matching to obtain a matching result.

[0062] Step S222, based on the matching result, data segmentation and data pruning are performed on the part of the initial navigation information corresponding to the target yaw path to obtain intermediate navigation information.

[0063] The data cleaning includes data segmentation and data pruning based on the matching result. Specifically, according to the route consistency matching result between the target driving trajectory and the target yaw path, the data segmentation manner of the part of the navigation information is determined, and the data to be pruned in the part of the navigation information is determined.

[0064] The route consistency matching result between the target driving trajectory and the target yaw path can be determined by the distance between the trajectory point on the target driving trajectory and the navigation point on the target yaw path. For example, if the distance is greater than a preset threshold, it is determined that the route consistency between the target driving trajectory and the target yaw path at the position corresponding to the trajectory point and the navigation point is not consistent.

[0065] The road structure data in the initial navigation information at least includes a road width. In the embodiment of the application, whether the distance between the trajectory point and the navigation point is greater than the road width can also be used to determine the data segmentation manner.

[0066] Through the technical solutions provided by steps S221 to S222, the application can accurately identify the navigation information inconsistent with the target driving trajectory through the data cleaning step, and through distance matching and targeted data segmentation and pruning, it is ensured that the personalized driving needs of the user embodied by the target yaw path are fully considered, and the accuracy and practicality of the intermediate navigation information are further ensured, providing a clean and optimized data basis for subsequent generation of personalized navigation paths.

[0067] As an optional implementation, in step S221, based on the driving trajectory data and the initial navigation information, distance matching is performed on the target driving trajectory and the target yaw path to obtain the matching result, which can further include the following execution steps:

[0068] Step S2211, the trajectory points on the target driving trajectory and the navigation points on the target yaw path are traversed, and the distance between the current trajectory point and the current navigation point in the traversal is calculated based on the driving trajectory data and the initial navigation information.

[0069] Step S2212, a matching relationship between the trajectory points and the navigation points is established according to the distance to obtain the matching result.

[0070] In the AI chauffeur application scenario, an optional navigation path and driving trajectory are as shown in Figure 3 Figure 3 ​In the specific embodiment, the target driving trajectory 301 is a segment of actual driving trajectory recorded by the vehicle after the user's manual intervention in the route learning stage, and the target driving trajectory corresponds to driving trajectory data; the navigation path 302a, the navigation path 302b and the navigation path 302c are navigation paths corresponding to the V2 navigation data recorded by the vehicle in the route learning stage. It can be found that the target driving trajectory is a relatively long complete driving route of the vehicle, and the navigation paths are a plurality of driving segments in the target driving trajectory, in which the vehicle records the V2 navigation data re-planned by the vehicle.

[0071] The target driving trajectory 301 includes a plurality of trajectory points, and each of the navigation path 302a, the navigation path 302b and the navigation path 302c includes a plurality of navigation points. When the target driving trajectory 301 and each navigation path (for example, the navigation path 302b) are matched in distance, the trajectory points on the target driving trajectory 301 and the navigation points on the navigation path 302b are traversed, and the distance between the current trajectory point and the current navigation point in the traversal is calculated. When it is detected that the distance between the current trajectory point and the current navigation point is less than a preset threshold, it is considered that the target driving trajectory 301 and the navigation path 302b are consistent in route at the positions corresponding to the current trajectory point and the current navigation point, a matching relationship is established between the current trajectory point and the current navigation point, that is, the current trajectory point and the current navigation point are regarded as a matching point pair. After the matching relationship is established between the target driving trajectory 301 and each of the navigation path 302a, the navigation path 302b and the navigation path 302c, a matching result is obtained. The matching result can be used to determine a plurality of matching point pairs corresponding to the target driving trajectory and the plurality of navigation paths.

[0072] Through the technical solutions provided in steps S2211 to S2212, the matching relationship between the trajectory points and the navigation points is established by accurately calculating the distance, which can ensure the high consistency between the navigation information and the actual driving trajectory. In particular, in the case of changes in the driving speed of the vehicle and complex road conditions, the personalized needs of the user can be accurately captured through the deviation segment, and more stable and reliable navigation services can be provided, thereby improving the driving safety and efficiency of the autonomous vehicle.

[0073] As an optional implementation, in step S2212, the matching relationship between the trajectory points and the navigation points is established according to the distance, and the step can further include the following execution steps:

[0074] In step S2213, in response to the distance between the current trajectory points and the current navigation points in the continuous target quantity in the traversal satisfying the target condition, the matching relationship between the trajectory points and the corresponding navigation points is sequentially established from the first trajectory point in the continuous target quantity of the current trajectory points.

[0075] In order to further improve the accuracy of route matching, the matching of a section of v2 and the corresponding trajectory point is checked according to multiple constraints when there are multiple near points on the target driving trajectory. After the first correct matching relationship is found, the subsequent v2 and trajectory point are constrained by the accumulated offset, direction and other information, and the corresponding relationship between the trajectory point and the navigation point is matched.

[0076] Through the technical solution provided by the above step S2213, the matching strategy of the continuous target quantity in the application can effectively reduce the matching error and ensure the accurate correspondence of the continuous trajectory starting from the first matching point and the navigation information. This is particularly effective for processing long-distance driving and multi-segment yaw path, and can provide continuous and smooth navigation experience.

[0077] As an optional implementation, in the step S222, based on the matching result, the part of the navigation information corresponding to the target yaw path in the initial navigation information is segmented and pruned to obtain the intermediate navigation information, which can further include the following execution steps:

[0078] In step S2221, based on the matching result and the part of the navigation information, a data segmentation point is determined, wherein the distance between the navigation point corresponding to the data segmentation point and the matched trajectory point is greater than a preset threshold, or the navigation point corresponding to the data segmentation point is not in the road range corresponding to the matched trajectory point.

[0079] In step S2222, the part of the navigation information is segmented according to the data segmentation point to obtain a segmentation result.

[0080] In step S2223, based on the matching result and the segmentation result, a data pruning point is determined, wherein the navigation point corresponding to the data pruning point is separated from the target yaw path and the target driving trajectory.

[0081] In step S2224, the segmentation result is pruned according to the data pruning point to obtain the intermediate navigation information.

[0082] When selecting the data segmentation point of the navigation information, two cases are considered. In the first case, when the distance between the trajectory point and the navigation point is greater than the preset threshold, it is considered that the target driving trajectory and the target yaw path are separated, and the position corresponding to the trajectory point and the navigation point is determined as the position of a data segmentation point. In the second case, when the distance between the trajectory point and the navigation point is greater than the road width, it is considered that the navigation point is not in the road range, and the position corresponding to the trajectory point and the navigation point can also be determined as the position of a data segmentation point. Based on this, the V2 navigation data is segmented into multiple segments according to the determined multiple data segmentation points, that is, the segmentation result includes the multiple segments of V2 navigation data obtained after segmentation.

[0083] For each piece of V2 navigation data, the data near the beginning and end may be separated from the track. Therefore, based on the matching result and the segmentation result, starting from the starting navigation point corresponding to each piece of V2 navigation data (in the direction of the ending navigation point), each navigation point is checked to determine whether the navigation point and the corresponding track point satisfy the target constraint. The first navigation point that satisfies the target constraint starting from the starting navigation point is determined as the head data pruning point corresponding to the piece of V2 navigation data. Similarly, starting from the ending navigation point corresponding to each piece of V2 navigation data (in the direction of the starting navigation point), each navigation point is checked to determine whether the navigation point and the corresponding track point satisfy the target constraint. The first navigation point that satisfies the target constraint starting from the ending navigation point is determined as the tail data pruning point corresponding to the piece of V2 navigation data. The data before the head data pruning point and the data after the tail data pruning point in the piece of V2 navigation data are deleted to obtain a piece of pruned V2 navigation data. When the segmentation result is pruned, the intermediate navigation information is obtained. The intermediate navigation information includes the pruned V2 navigation data.

[0084] In an exemplary application scenario, the starting point of the V2 navigation data is found by checking the consistency of the road width information of the matched track point, the V2 navigation data, and the track direction. The incorrect points and road information before the starting point are deleted. Then, the tail point is detected in reverse order, and the width and direction are checked to determine whether they meet the requirements. In addition, based on the navigation points on the subpath, it is determined whether the navigation point is separated from the target driving track. If it is determined that the navigation point is separated from the target driving track, the V2 navigation data corresponding to the navigation point is deleted, and the pruned V2 navigation data is obtained.

[0085] Through the technical solutions provided in steps S2221 to S2224, the navigation information irrelevant to or not matching the actual driving track is removed through accurate data segmentation and pruning. In particular, in the case of road condition changes or user behavior changes, the navigation strategy can be quickly adjusted, more accurate and timely navigation services can be provided, and the driving safety and flexibility of the autonomous vehicle are improved.

[0086] It should be noted that in the process of data segmentation and pruning, the above method steps provided by the embodiments of the present application consider the user personalized driving demand embodied by the yaw path. In the yaw path, the yaw driving track is used as the reference, and in other paths, the system generated navigation path is used as the reference. Thus, a vehicle end navigation path that meets the user personalized driving demand (i.e., consistent with the yaw driving track) and contains rich navigation information is generated.

[0087] As an optional implementation, in the step S203, the interval sampling of the driving track data by using the intermediate navigation information to obtain the sampling result can further include the following execution steps:

[0088] The step S231 compares the route of the intermediate navigation information and the driving track data to obtain a road section interval to be sampled;

[0089] The step S232 performs interval sampling on the driving track data based on the road section interval to obtain a sampling result.

[0090] The road section interval to be sampled is a partial track interval in which V2 navigation data is missing on the target driving track. The interval sampling is performed on the driving track data in this interval to generate V2 navigation data based on the sampling result to complete the vehicle-end navigation path.

[0091] Through the technical solutions provided in the steps S231 to S232, the application can supplement the detailed driving data missing in the original navigation information on the driving track by interval sampling, and ensure that the generated vehicle-end navigation path covers all driving intervals to provide more complete and detailed path guidance.

[0092] As an optional implementation, in the step S231, the route comparison of the intermediate navigation information and the driving track data to obtain the road section interval to be sampled can further include the following execution steps:

[0093] The step S2311 performs route analysis on the intermediate navigation information to determine a navigation road section;

[0094] The step S2312 determines a road section interval based on a part of the driving track not covered by the navigation road section in the target driving track corresponding to the driving track data.

[0095] The navigation road section is a navigation road section corresponding to the pruned V2 navigation data. The intermediate navigation information contains detailed and comprehensive V2 navigation data corresponding to the navigation road section. The part of the driving track not covered by the navigation road section in the target driving track is a road section interval in which V2 navigation data is missing. In this road section interval, the driving track data needs to be sampled to complete the complete V2 navigation information consistent with the route of the target driving track.

[0096] Through the technical solutions provided in the steps S2311 to S2312, the application can ensure that the sampling points cover all driving intervals not completely described by the navigation information, and can provide more comprehensive and detailed driving data, especially when processing non-standard road information such as new roads and small roads, to improve the driving safety and user experience of the autonomous vehicle.

[0097] As an optional implementation, in the step S232, the interval sampling of the driving trajectory data based on the road section interval to obtain the sampling result can further include the following execution steps:

[0098] In step S2321, a target sampling strategy is determined based on a road type corresponding to the road section interval.

[0099] In step S2322, the driving trajectory data is interval sampled based on the road section interval and the target sampling strategy to obtain the sampling result.

[0100] The road type corresponding to the road section interval can be a turning section, a straight section, etc. According to the target sampling strategy, when the driving trajectory data is sampled in the turning section, denser trajectory sampling points (such as one trajectory sampling point every 2 meters) can be selected to accurately represent the road structure data and vehicle navigation data of the turning section. Since the road condition of the straight section is relatively simple, according to the target sampling strategy, when the driving trajectory data is sampled in the straight section, sparser trajectory sampling points (such as one trajectory sampling point every 20 meters) can be selected to reduce the sampling cost.

[0101] Further, according to the target sampling strategy, a plurality of trajectory sampling points are selected on the target driving trajectory, and trajectory data corresponding to the plurality of trajectory sampling points is obtained from the driving trajectory data to obtain the sampling result.

[0102] Through the technical solutions provided by the steps S2321 to S2322, the application can collect more accurate and effective driving data according to different road types and conditions, especially when dealing with different road types such as highways and urban roads, it can provide more targeted and efficient data support to improve the accuracy and real-time performance of path planning and navigation control of the autonomous vehicle.

[0103] As an optional implementation, in the step S204, the sampling result includes a plurality of trajectory sampling points on the vehicle driving trajectory; and the intermediate navigation information and the sampling result are spliced to obtain the target navigation information, which can further include the following execution steps:

[0104] In step S241, road structure data and vehicle navigation data matched with the plurality of trajectory sampling points are obtained.

[0105] In step S242, the road structure data and the vehicle navigation data are used to generate to-be-spliced navigation information.

[0106] In step S243, the intermediate navigation information and the to-be-spliced navigation information are spliced in navigation semantics to obtain a vehicle-end navigation path.

[0107] In an exemplary application scenario, the plurality of trajectory sampling points in the sampling result are processed by translation, rotation, stretching, etc. to connect the two V2 head-tail points, so that the two adjacent V2 navigation data in the intermediate navigation information can be connected by at least one trajectory sampling point. In addition, the application embodiment also considers the road structure and the distance between the navigation points and the trajectory points, and samples and breaks the target driving trajectory to generate a supplementary navigation point between the two V2 navigation paths with correct connection relationship and road structure.

[0108] In the above application scenario, when implementing navigation semantic splicing, a plurality of trajectory sampling points are used as a plurality of supplementary navigation points, V2 navigation data (which can be obtained from a historical V2 navigation database) is added to each supplementary navigation point, and a supplementary V2 navigation segment is generated. Further, according to the road structure information in the supplementary V2 navigation segment and the road structure information of the plurality of V2 navigation segments in the intermediate navigation information, the intermediate navigation information and the supplementary V2 navigation segment are spliced, and the offset information (i.e., offset) in the V2 navigation path in the splicing result and the target driving trajectory is updated to obtain target navigation information.

[0109] Through the technical solutions provided by the above steps S241 to S253, the application can seamlessly fuse data by splicing the actual driving data (sampling result) and the optimized navigation information (intermediate navigation information), and generate a personalized path that not only conforms to the actual driving trajectory but also contains detailed navigation information. This not only improves the planning quality of the path, but also enhances the driving safety and user experience of the autonomous vehicle.

[0110] In summary, the application embodiment saves the navigation path data generated by the real-time learning of the vehicle end, and generates a target navigation path for the entire route in combination with the actual driving trajectory of the vehicle and the navigation path data. Specifically, based on the actual driving trajectory, the navigation path data corresponding to the plurality of learning paths is spliced, and the repeated data, missing data and error data in the splicing result are adjusted (such as deleted, added or corrected, etc.), and then the target navigation path is obtained, so that the target navigation path is consistent or substantially consistent with the actual driving trajectory, and the target navigation path contains both the real-time learning navigation path data and the user personalized data corresponding to the actual driving trajectory, i.e., the obtained target navigation path is a customized information complete navigation path.

[0111] In the autonomous driving technology, the embodiment and satisfaction of user personalized driving demand is a key point to improve driving experience and safety. For this, the core of the application is how to fuse the personalized driving trajectory of the user on the deviation path with the basic navigation path generated by the system to generate a vehicle end navigation path that meets the user's personalized demand and provides rich navigation information.

[0112] Specifically, in the processing of the yaw path, the application gives priority to the actual driving trajectory data of the user on these paths, because these data can more accurately reflect the driving habits and preferences of the user. In the non-yaw section, that is, the section where the user does not show special driving preferences, the system defaults to using the navigation path planned by itself, so that in the case where the user has no special requirements, the vehicle can still follow an efficient and safe route.

[0113] In this way, the application can ensure that the vehicle-end navigation path is more accurate on the user's preferred path, while maintaining the optimization of the system path on other sections, so as to meet the personalized needs and maintain the efficiency and safety of the overall path planning. The generation of the vehicle-end navigation path not only considers the individualization of the driving trajectory, but also combines rich navigation information, including road structure data and vehicle navigation data, which enables the autonomous vehicle to better understand and adapt to the road environment when executing the vehicle-end navigation path, and make more accurate driving decisions.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0115] It should be noted that for the above method embodiments, in order to simply describe, the technical solutions in the method embodiments are described as a series of action combinations, but those skilled in the art should know that the application is not limited by the order of actions in the described action combination, because according to the application, some steps described above can be performed in other order or simultaneously. In addition, those skilled in the art should know that the embodiments described in the specification of the application are preferred embodiments, and the actions and modules involved are not necessarily essential to implement the technical solutions of the application.

[0116] According to the embodiments of the application, a device embodiment of a vehicle navigation device is also provided, which is used to implement the above method embodiments and various optional implementation manners of the method embodiments, and the technical contents described above will not be repeated here. It should be noted that in the following related description of the device embodiment, the "module" can be software, hardware or a combination of software and hardware for realizing the specified function.

[0117] Figure 4 is a structural block diagram of a vehicle navigation device according to an embodiment of the application, as shown in Figure 4As shown, the vehicle navigation device comprises:

[0118] The acquisition module 401 is configured to acquire travel trajectory data and initial navigation information, wherein the travel trajectory data is used to represent a target travel trajectory recorded by a target vehicle in a path learning stage, and the initial navigation information comprises road section navigation data corresponding to a plurality of yaw path sections in the path learning stage.

[0119] The data processing module 402 is configured to perform data cleaning processing on the initial navigation information based on the travel trajectory data to obtain intermediate navigation information.

[0120] The sampling module 403 is configured to perform interval sampling on the travel trajectory data by using the intermediate navigation information to obtain a sampling result.

[0121] The generation module 404 is configured to perform splicing processing on the intermediate navigation information and the sampling result to obtain a vehicle-end navigation path.

[0122] Optionally, in the vehicle navigation device, the road section navigation data at least comprises road structure data and vehicle navigation data.

[0123] Optionally, the data processing module 402 is further configured to: for any target yaw path in the plurality of yaw path sections, perform distance matching on the target travel trajectory and the target yaw path based on the travel trajectory data and the initial navigation information to obtain a matching result; and perform data segmentation and data pruning on part of the navigation information corresponding to the target yaw path in the initial navigation information based on the matching result to obtain the intermediate navigation information.

[0124] Optionally, the data processing module 402 is further configured to: traverse a track point on the target travel trajectory and a navigation point on the target yaw path, calculate a distance between a current track point and a current navigation point in the traversal based on the travel trajectory data and the initial navigation information; and establish a matching relationship between the track point and the navigation point according to the distance to obtain the matching result.

[0125] Optionally, the data processing module 402 is further configured to: in response to the distance between the current track point and the current navigation point in the continuous target number of times satisfying a target condition, sequentially establish the matching relationship between the track point and the corresponding navigation point from a first track point in the continuous target number of track points.

[0126] Optionally, the data processing module 402 is further configured to: determine a data segmentation point based on the matching result and the partial navigation information, where the data segmentation point corresponds to a navigation point whose distance to the matched trajectory point is greater than a preset threshold, or the data segmentation point corresponds to a navigation point that is not within a road range corresponding to the matched trajectory point; segment the partial navigation information according to the data segmentation point to obtain a segmentation result; determine a data pruning point based on the matching result and the segmentation result, where the data pruning point corresponds to a navigation point at which a target yaw path and a target driving trajectory are separated; and prune the segmentation result according to the data pruning point to obtain intermediate navigation information.

[0127] Optionally, the sampling module 403 is further configured to: perform route comparison on the intermediate navigation information and the driving trajectory data to obtain a road section interval to be sampled; and sample the driving trajectory data based on the road section interval to obtain a sampling result.

[0128] Optionally, the sampling module 403 is further configured to: perform route analysis on the intermediate navigation information to determine a navigation road section; and determine a road section interval based on a portion of the driving trajectory that is not covered by the navigation road section in the target driving trajectory corresponding to the driving trajectory data.

[0129] Optionally, the sampling module 403 is further configured to: determine a target sampling strategy based on a road type corresponding to the road section interval; and sample the driving trajectory data based on the road section interval and the target sampling strategy to obtain a sampling result.

[0130] Optionally, the sampling result includes a plurality of trajectory sampling points on a vehicle driving trajectory; and the generation module 404 is further configured to: obtain road structure data and vehicle navigation data matched by the plurality of trajectory sampling points; generate to-be-spliced navigation information based on the road structure data and the vehicle navigation data; and perform navigation semantic splicing on the intermediate navigation information and the to-be-spliced navigation information to obtain a vehicle-side navigation path.

[0131] The vehicle navigation device in the embodiments of the present application can realize the automation and integration of the vehicle navigation method, and is particularly suitable for a navigation system of an autonomous vehicle, and can improve the safety, stability, and user satisfaction of vehicle driving, and is suitable for various driving environments and scenarios.

[0132] It should be noted that the acquisition module 401, the data processing module 402, the sampling module 403, and the generation module 404 correspond to steps S21 to S24 in the method embodiments, and the four modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above method embodiments.

[0133] It should be noted that the various modules mentioned in the above device embodiments can be implemented by software, hardware or a combination of software and hardware. For example, when the above modules are implemented by hardware, each module can be arranged in the same processor, or each module can be arranged in different processors in any combination. For another example, the above modules can be hardware components or software components stored in a memory and processed by one or more processors, and the above modules can also run in the computing terminal 10 as shown in Figure 1

[0134] According to the embodiments of the present application, a vehicle is also provided, which comprises an on-board memory and an on-board processor, the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to implement the above vehicle navigation method.

[0135] The vehicle in the embodiments of the present application can utilize the above method and device to achieve more accurate and real-time path planning and navigation control, and is particularly suitable for autonomous vehicles, which can provide safe, stable and efficient driving experience in various driving environments, and improve user satisfaction and vehicle performance.

[0136] According to the embodiments of the present application, a computer readable storage medium is also provided, which comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to implement the above vehicle navigation method when the program is running.

[0137] Optionally, the above computer storage medium can include but is not limited to: hard disk drive (HDD), solid state drive (SSD), USB flash drive, optical disc, memory card, cloud storage medium and network storage device (NAS) and the like.

[0138] Optionally, the above computer readable storage medium can be configured to store a computer program for performing the following steps: obtaining driving trajectory data and initial navigation information, wherein the driving trajectory data is used to represent the target driving trajectory recorded by the target vehicle in the path learning stage, and the initial navigation information comprises road segment navigation data corresponding to the multiple yaw paths in the path learning stage; performing data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; performing interval sampling on the driving trajectory data using the intermediate navigation information to obtain a sampling result; and performing splicing processing on the intermediate navigation information and the sampling result to obtain a vehicle-end navigation path.

[0139] ​The computer readable storage medium in the embodiments of the present application can be used to store and transmit the execution program of the method, is particularly suitable for the navigation system of the autonomous vehicle, can improve the safety, stability and user satisfaction of vehicle driving, is suitable for various driving environments and scenes, and provides strong data processing and navigation control capabilities for the development of autonomous driving technology.

[0140] According to the embodiments of the present application, a computer program product is also provided. The computer program product includes a computer program which, when executed by a processor, can implement the vehicle navigation method described above.

[0141] Optionally, the computer program product described above can provide vehicle navigation services based on the vehicle navigation method described above.

[0142] Optionally, in the present embodiment, the computer program product can be a set of instructions and codes pre-written according to the vehicle navigation method described above. The computer program product can run on various different computer platforms, including personal computers, servers, mobile devices, etc.

[0143] Optionally, in the present embodiment, the instructions and codes corresponding to the computer program product are used to implement the following method steps: obtaining driving trajectory data and initial navigation information, wherein the driving trajectory data is used to represent the target driving trajectory recorded by the target vehicle in the path learning stage, and the initial navigation information includes road segment navigation data corresponding to the multiple segments of the yaw path in the path learning stage; based on the driving trajectory data, performing data cleaning processing on the initial navigation information to obtain intermediate navigation information; using the intermediate navigation information, performing interval sampling on the driving trajectory data to obtain a sampling result; and performing splicing processing on the intermediate navigation information and the sampling result to obtain a vehicle-end navigation path.

[0144] The computer program product in the embodiments of the present application can provide more accurate and real-time path planning and navigation control for autonomous vehicles, is particularly suitable for handling complex road environments and unexpected situations, can improve the safety, stability and user satisfaction of vehicle driving, is suitable for various driving environments and scenes, and provides strong data processing and navigation control capabilities for the development of autonomous driving technology. At the same time, it can also be applied to intelligent transportation systems, vehicle safety monitoring and other fields, and provides strong support for future intelligent travel and traffic safety.

[0145] In the above-mentioned multiple embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other manners. For example, the above-described device embodiments are only illustrative, for example, the division of the plurality of modules can be a logical function division, and any possible division manner can be used in actual implementation in the application scenario; for example, the plurality of modules (or units or components in the module) can be combined with each other, and can be integrated into another system. For example, some features in the above-described method embodiments can be omitted or skipped.

[0147] It should be noted that in each of the above embodiments, the modules, components or units described as separate components can be physically separate, or can be integrated in physics. The components shown as modules or units can be physical modules or physical units, or virtual modules or virtual units, that is, a plurality of modules or a plurality of units can be in the same position, or can be distributed in a plurality of positions or a plurality of spaces. In the application scenario, according to the actual needs of the scene, some or all of the modules or units can be selected to implement the technical solutions of the embodiments of the present application, and then the corresponding technical purposes are achieved.

[0148] In particular, for the integrated functional modules or functional units, if implemented in the form of software functional units and sold or used as independent products, the modules or functional units can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application.

[0149] The above only describes the preferred embodiments of the present application, and it should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for generating vehicle-side navigation routes, characterized in that, include: Acquire driving trajectory data and initial navigation information, wherein the driving trajectory data is used to characterize the target driving trajectory recorded by the target vehicle during the path learning phase, and the initial navigation information includes road segment navigation data corresponding to multiple deviance paths in the path learning phase; Based on the driving trajectory data, the initial navigation information is cleaned to obtain intermediate navigation information; Using the intermediate navigation information, the driving trajectory data is sampled in intervals to obtain the sampling results; The intermediate navigation information and the sampling results are concatenated to obtain the vehicle-side navigation path; Based on the driving trajectory data, the initial navigation information is cleaned to obtain intermediate navigation information, including: for any target deviation path among the multiple deviation paths, distance matching is performed on the target driving trajectory and the target deviation path based on the driving trajectory data and the initial navigation information to obtain a matching result; based on the matching result, data segmentation and data trimming are performed on the portion of the initial navigation information corresponding to the target deviation path to obtain intermediate navigation information.

2. The vehicle-side navigation path generation method according to claim 1, characterized in that, The road segment navigation data includes at least: road structure data and vehicle navigation data.

3. The vehicle-side navigation route generation method according to claim 1, characterized in that, Based on the driving trajectory data and the initial navigation information, distance matching is performed on the target driving trajectory and the target deviation path to obtain the matching result, which includes: Traverse the trajectory points on the target driving trajectory and the navigation line points on the target deviation path, and calculate the distance between the current trajectory point and the current navigation line point during the traversal based on the driving trajectory data and the initial navigation information; Based on the distance, a matching relationship is established between the trajectory point and the navigation line point to obtain the matching result.

4. The vehicle-side navigation path generation method according to claim 3, characterized in that, Establishing a matching relationship between the trajectory points and the navigation line points based on the distance includes: In response to the fact that the distance between the current trajectory point and the current navigation line point of the consecutive target number in the traversal all meet the target condition, starting from the first trajectory point in the consecutive target number of current trajectory points, the matching relationship between the trajectory point and the corresponding navigation line point is established sequentially.

5. The vehicle-side navigation path generation method according to claim 1, characterized in that, Based on the matching results, the navigation information in the initial navigation information corresponding to the target deviation path is segmented and pruned to obtain the intermediate navigation information, which includes: Based on the matching results and the partial navigation information, a data segmentation point is determined, wherein the distance between the navigation line point corresponding to the data segmentation point and the matched trajectory point is greater than a preset threshold, or the navigation line point corresponding to the data segmentation point is not within the road range corresponding to the matched trajectory point; The navigation information is segmented according to the data segmentation points to obtain the segmentation result; Based on the matching result and the segmentation result, a data trimming point is determined, wherein the target yaw path and the target driving trajectory are separated at the navigation line point corresponding to the data trimming point; The segmentation results are pruned according to the data pruning points to obtain the intermediate navigation information.

6. The vehicle-side navigation path generation method according to claim 1, characterized in that, Using the intermediate navigation information, the driving trajectory data is sampled in intervals to obtain the sampling results, including: The intermediate navigation information and the driving trajectory data are compared to obtain the road segment interval to be sampled; The driving trajectory data is sampled from the road segment intervals to obtain the sampling results.

7. The vehicle-side navigation path generation method according to claim 6, characterized in that, By comparing the intermediate navigation information and the driving trajectory data, the road segment interval to be sampled is obtained, including: The intermediate navigation information is parsed to determine the navigation route. Based on the portion of the target driving trajectory not covered by the navigation segment corresponding to the driving trajectory data, the segment interval is determined.

8. The vehicle-side navigation path generation method according to claim 6, characterized in that, Based on the aforementioned road segment intervals, the driving trajectory data is sampled within intervals to obtain the sampling results, including: Based on the road type corresponding to the road segment interval, determine the target sampling strategy; Using the road segment intervals and the target sampling strategy, the driving trajectory data is sampled in intervals to obtain sampling results.

9. The vehicle-side navigation path generation method according to claim 1, characterized in that, The sampling results include multiple trajectory sampling points along the vehicle's driving trajectory; The intermediate navigation information and the sampling results are concatenated to obtain the vehicle-side navigation path, which includes: Obtain road structure data and vehicle navigation data matched by the multiple trajectory sampling points; Based on the road structure data and the vehicle navigation data, generate navigation information to be stitched together; The intermediate navigation information and the navigation information to be assembled are semantically concatenated to obtain the vehicle-side navigation path.

10. A vehicle-mounted navigation route generation device, characterized in that, include: The acquisition module is used to acquire driving trajectory data and initial navigation information, wherein the driving trajectory data is used to characterize the target driving trajectory recorded by the target vehicle during the path learning stage, and the initial navigation information includes road segment navigation data corresponding to multiple deviance paths in the path learning stage; The data processing module is used to perform data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; The sampling module is used to perform interval sampling on the driving trajectory data using the intermediate navigation information to obtain the sampling results; The generation module is used to concatenate the intermediate navigation information and the sampling results to obtain the vehicle-side navigation path; The data processing module is further configured to: for any segment of the target deviation path among the multiple deviation paths, perform distance matching between the target driving trajectory and the target deviation path based on the driving trajectory data and the initial navigation information to obtain a matching result; and based on the matching result, perform data segmentation and data trimming on the portion of the initial navigation information corresponding to the target deviation path to obtain intermediate navigation information.

11. A vehicle, characterized in that, The system includes an onboard memory and an onboard processor, wherein the onboard memory stores a computer program and the onboard processor is configured to run the computer program to execute the vehicle-side navigation path generation method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device where the storage medium is located to perform the vehicle navigation path generation method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the vehicle navigation path generation method according to any one of claims 1 to 9.

Images