Vehicle end navigation path generation method and device, vehicle and storage medium
By obtaining and processing the driving trajectory data of autonomous driving vehicles in the path learning stage, and generating navigation paths that match personalized driving trajectory, the problem of incomplete navigation paths is solved and user experience and security are improved.
Patent Information
- Application Number
- CN202411288402.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-13
AI Technical Summary
The personalized driving routes recorded by autonomous driving vehicles during the path learning stage are difficult to be effectively matched by the navigation system, resulting in incomplete navigation paths and reducing user experience and safety.
By obtaining driving trajectory data and initial navigation information, data cleaning, interval sampling and splicing are performed to generate a vehicle-side navigation path that matches the personalized driving trajectory, including detailed road section navigation data.
It realizes a vehicle-side navigation path with comprehensive and complete data generation and customized routes, improves the adaptability of user experience and the navigation path of autonomous vehicles to personalized needs, and enhances user experience and security.
Smart Images

Figure CN119085685A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a vehicle-side navigation path generation method, device, vehicle, and storage medium. Background Art
[0002] During autonomous driving, vehicles usually follow the navigation data (such as V2 navigation path) sent by the navigation system in real time. The navigation data contains a large amount of navigation location information and road structure information, allowing the vehicle to intelligently select a reasonable route.
[0003] In the scenario of artificial intelligence (AI) driving for autonomous driving, the vehicle will record the driver's personalized driving route during the path learning stage. The personalized driving route will affect the navigation data sent by the navigation system. During 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. This not only reduces the user experience because the navigation cannot meet personalized driving needs, but also reduces the safety of AI driving.
[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0005] The embodiments of the present application provide a vehicle-side navigation path generation method, device, vehicle and storage medium to at least solve the technical problems in the related art that the navigation path of the vehicle navigation solution is difficult to adapt to the personalized driving trajectory requirements and the autonomous driving user experience is poor.
[0006] According to one aspect of an embodiment of the present application, a vehicle navigation method is provided, including: acquiring driving trajectory data and initial navigation information, wherein the driving trajectory data is used to characterize a target driving trajectory recorded by a target vehicle in a path learning phase, and the initial navigation information includes segment navigation data corresponding to multiple segments of yaw paths in the path learning phase; 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 sampling results; and splicing the intermediate navigation information and the sampling results to obtain a vehicle-side 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 cleaned to obtain intermediate navigation information, including: for any target yaw path in the multiple yaw paths, 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 a matching result; based on the matching result, data segmentation and data pruning are performed on part of the navigation information corresponding to the target yaw path in the initial navigation information to obtain intermediate navigation information.
[0009] Optionally, 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 a matching result, including: traversing the trajectory points on the target driving trajectory and the navigation points on the target yaw path, and calculating the distance between the current trajectory point and the current navigation point in the traversal based on the driving trajectory data and the initial navigation information; establishing a matching relationship between the trajectory point and the navigation point according to the distance to obtain a matching result.
[0010] Optionally, establishing a matching relationship between trajectory points and navigation line points based on distance includes: in response to the distances between a current trajectory point of a continuous target number and a current navigation line point in the traversal all satisfying the target condition, starting from the first trajectory point in the continuous target number of current trajectory points, sequentially establishing a matching relationship between the trajectory points and the corresponding navigation line points.
[0011] Optionally, based on the matching result, data segmentation and data pruning are performed on part of the navigation information corresponding to the target yaw path in the initial navigation information to obtain intermediate navigation information, including: determining a data segmentation point based on the matching result and the part of the navigation information, 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; performing data segmentation on part of the navigation information according to the data segmentation point to obtain a segmentation result; determining a data pruning point based on the matching result and the segmentation result, wherein the target yaw path is separated from the target driving trajectory at the navigation line point corresponding to the data pruning point; and pruning the segmentation result according to the data pruning point to obtain intermediate navigation information.
[0012] Optionally, the driving trajectory data is interval sampled using the intermediate navigation information to obtain the sampling result, including: performing route comparison on the intermediate navigation information and the driving trajectory data to obtain the road section interval to be sampled; and performing interval sampling on the driving trajectory data based on the road section interval to obtain the sampling result.
[0013] Optionally, performing route comparison on the intermediate navigation information and the driving trajectory data to obtain the road section interval to be sampled includes: performing route analysis on the intermediate navigation information to determine the navigation section; and determining the road section interval based on a portion of the driving trajectory not covered by the navigation section in the target driving trajectory corresponding to the driving trajectory data.
[0014] Optionally, performing interval sampling on the driving trajectory data based on the road section interval to obtain the sampling result includes: determining a target sampling strategy based on the road type corresponding to the road section interval; performing interval sampling on the driving trajectory data using the road section interval and the target sampling strategy to obtain the sampling result.
[0015] Optionally, the sampling result includes multiple trajectory sampling points on the vehicle's driving trajectory; the intermediate navigation information and the sampling result are spliced to obtain target navigation information including: obtaining road structure data and vehicle navigation data that match multiple trajectory sampling points; generating navigation information to be spliced based on the road structure data and the vehicle navigation data; performing navigation semantic splicing on the intermediate navigation information and the navigation information to be spliced to obtain a vehicle-side navigation path.
[0016] According to another aspect of an embodiment of the present application, a vehicle navigation device is also provided, including: an acquisition module, 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 in the path learning stage, and the initial navigation information includes section navigation data corresponding to multiple sections of yaw paths in the path learning stage; a data processing module, used to perform data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; a sampling module, used to use the intermediate navigation information to perform interval sampling on the driving trajectory data to obtain sampling results; a splicing module, used to splice the intermediate navigation information and the sampling results to obtain target navigation information; a navigation module, used to generate navigation instructions according to the target navigation information, wherein the navigation instructions are used to control the target vehicle to travel along the target driving trajectory.
[0017] According to another aspect of an embodiment of the present application, a vehicle is also provided, including an on-board memory and an on-board processor, wherein a computer program is stored in the on-board memory, and the on-board processor is configured to run the computer program to execute any one of the above-mentioned vehicle navigation methods.
[0018] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned vehicle navigation methods.
[0019] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the vehicle navigation method according to any one of the above items is implemented.
[0020] In the embodiment of the present application, firstly, the driving trajectory data and the initial navigation information are obtained; based on the driving trajectory data, the initial navigation information is cleaned to obtain the 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 spliced to obtain the vehicle-side navigation path. In the present application, the driving trajectory data is used to characterize the target driving trajectory recorded by the target vehicle in the path learning stage, and the initial navigation information includes the segment navigation data corresponding to the multiple segments of the yaw path in the path learning stage, and the multiple segments of the yaw path can characterize the personalized needs of the user in driving. The above-mentioned target driving trajectory can be regarded as the driving trajectory that the user prefers more. Therefore, the generated vehicle-side navigation path not only includes more detailed segment navigation data on part of the navigation path, but also can make the final target navigation path consistent with the vehicle driving trajectory route, so as to achieve the purpose of generating a vehicle-side navigation path with comprehensive and complete data and customized route, thereby achieving the technical effect of improving the adaptability of the vehicle navigation path to the personalized needs of the user and enhancing the user experience, thereby solving the technical problems that the navigation path of the vehicle navigation solution in the related technology is difficult to adapt to the personalized driving trajectory needs and the user experience of the autonomous driving is poor. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and the related descriptions of the embodiments are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0022] Figure 1 is a hardware structure block diagram of an optional computing terminal for implementing a vehicle navigation method according to an embodiment of the present application;
[0023] Figure 2 is a flow chart of a vehicle navigation method according to an embodiment of the present application;
[0024] Figure 3 is a schematic diagram of an optional navigation path and driving trajectory according to an embodiment of the present application;
[0025] Figure 4 It is a structural block diagram of a vehicle navigation device according to an embodiment of the present application. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments only include a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.
[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0028] According to an embodiment 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 accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0029] First, the operating environment of the above 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 an embodiment of the present application, such as Figure 1 As shown, a computing terminal 10 (for example, a computer terminal, a mobile smart terminal, a vehicle terminal, or a cloud computing virtual terminal, etc.) may include: one or more processors 102, a memory 104 for storing data, and a transmission device 106 for implementing a communication function, wherein each processor 102 may include but is not limited to a processing component such as a microprocessor (Microcontroller Unit, referred to as MCU) or a programmable logic device (Field Programmable Gate Array, referred to as FPGA).
[0030] The computing terminal 10 may further include: a display device 110, an input / output device 108, a Universal Serial Bus (USB) port (the USB port may be used as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure) and a camera (not shown in the figure). A person skilled in the art may understand that Figure 1 The structure of the computing terminal 10 shown is only for illustration and does not impose a strict limitation on the structure of the computing terminal 10. For example, the computing terminal 10 may also include Figure 1 More or fewer components than those shown in FIG. 1 , or computing terminal 10 may have the same components as those shown in FIG. Figure 1 Different categories of components are shown.
[0031] It should be noted that the one or more processors 102 and / or other data processing circuits in the computing terminal 10 may be embodied in whole or in part as software, hardware, firmware or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the vehicle terminal 10 (or mobile device).
[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle navigation method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned vehicle navigation method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the vehicle terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.
[0033] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the vehicle terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
[0034] Under the above operating environment, the embodiment of the present application provides the following Figure 2 The vehicle navigation method shown, Figure 2 is a flow chart of a vehicle navigation method according to an embodiment of the present application, such as Figure 2 As shown, the method includes the following implementation steps:
[0035] Step S201, 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 the segment navigation data corresponding to the multiple segments of the yaw path in the path learning stage;
[0036] Step S202, based on the driving trajectory data, the initial navigation information is cleaned to obtain intermediate navigation information;
[0037] Step S203, using the intermediate navigation information, performing interval sampling on the driving trajectory data to obtain a sampling result;
[0038] Step S204, concatenating the intermediate navigation information and the sampling result to obtain the vehicle-side navigation path.
[0039] The above implementation steps provided in the embodiment of the present application can be used to realize cloud mapping in the artificial intelligence (AI) driving scene in the field of autonomous driving technology, that is, to obtain a navigation map stored in the cloud, which can be used to determine multiple candidate vehicle-side navigation paths corresponding to the personalized driving route requirements of multiple users. In the path learning stage in the AI driving scene, the trajectory data corresponding to the actual driving trajectory of the vehicle after the user's manual intervention operation (such as turning on manual driving, changing the preferred route, changing the waypoint, etc.) is recorded, and the navigation data (including detailed information such as turns, lanes, and forks) given by the navigation system to the vehicle side for multiple sections of the road where the user's manual intervention causes deviation are spliced to generate a candidate vehicle-side navigation path stored in the cloud, which can keep the route consistent with the actual driving trajectory of the vehicle, meet the personalized needs of the user, and contain as much detailed navigation data as possible. After the path learning is completed, when the vehicle needs to navigate along the driving trajectory again (which can be manual driving or automatic driving), the cloud sends the spliced vehicle-side navigation path to the vehicle to help the vehicle correctly and safely drive according to the personalized driving trajectory of the user.
[0040] In the application scenario, the actual driving trajectory can be considered as a driving route that can represent the user's personalized driving needs. In this case, the actual driving trajectory is used as the target driving trajectory, and the recorded trajectory data is used as the driving trajectory data. Furthermore, the user's manual intervention operation will trigger multiple deviation events. The vehicle will update the navigation of the deviation section for each deviation event. At the same time, the vehicle will record the navigation data of the sections corresponding to the multiple deviation paths when multiple deviation events occur, and obtain the initial navigation information.
[0041] During the automatic driving process, when the vehicle is performing the target trip, the above-mentioned driving trajectory data and initial navigation information can be obtained, and the vehicle-side navigation path can be generated according to the method steps provided in the embodiment of the present application, and the target vehicle can be further controlled to travel along the target driving trajectory according to the waiting vehicle-side navigation path to complete the target trip. The starting point and end point of the above-mentioned target trip are the same as or close to the starting point and end point of the above-mentioned target driving trajectory.
[0042] In particular, the above-mentioned road section navigation data is the V2 navigation data that is updated in real time by the vehicle and sent through the vehicle's central control screen when the above-mentioned deviation event is triggered. 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's 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 and has complete and comprehensive navigation information, the initial navigation information is cleaned based on the driving trajectory data to remove some data in the initial navigation information whose navigation path is inconsistent with the target driving trajectory to obtain intermediate navigation information.
[0044] Furthermore, the intermediate navigation information includes V2 navigation data corresponding to a partial navigation path consistent with the target driving trajectory route. Based on this, the driving trajectory data is sampled within the interval not covered by the above partial navigation path on the target driving trajectory to obtain a sampling result, which includes at least trajectory position data corresponding to multiple trajectory sampling points.
[0045] Furthermore, the trajectory position data corresponding to the multiple trajectory sampling points in the above sampling results are converted into V2 navigation data corresponding to the multiple trajectory sampling points. Specifically, based on the trajectory position data, the V2 navigation data corresponding to the multiple trajectory sampling points are queried from the historical navigation database. At this time, the trajectory position data and the V2 navigation data of each trajectory sampling point can also be merged and processed to update the V2 navigation data. The intermediate navigation information and the V2 navigation data corresponding to the multiple trajectory sampling points are spliced to obtain the vehicle-side navigation path. The target navigation path corresponding to the vehicle-side navigation path is consistent with the above target driving trajectory route, and the vehicle-side navigation path includes the V2 navigation data corresponding to the entire target navigation path.
[0046] It is easy to notice that the above method provided in the embodiment of the present application can effectively integrate the actual driving data of the vehicle and the basic information of the navigation system, improve the accuracy of the path planning and navigation control of the autonomous driving vehicle, and is suitable for complex driving environments such as urban roads and highways. In particular, when dealing with scenes such as road forks, roundabouts, and complex intersections, it can provide more accurate navigation guidance.
[0047] Through the technical solution provided by the above steps S201 to S205, the present application first obtains driving trajectory data and initial navigation information; 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 interval sampled to obtain sampling results; the intermediate navigation information and the sampling results are spliced to obtain a vehicle-side navigation path; and the target vehicle is controlled to travel along the target driving trajectory according to the vehicle-side navigation path. In the present application, the driving trajectory data is used to characterize the target driving trajectory recorded by the target vehicle during the path learning stage. The initial navigation information includes the segment navigation data corresponding to the multiple yaw paths in the path learning stage. The multiple yaw paths can characterize the personalized needs of the user in driving. The above target driving trajectory can be regarded as the driving trajectory that the user prefers more. Therefore, the generated vehicle-side navigation path not only includes more detailed segment navigation data on some navigation paths, but also can make the final target navigation path consistent with the vehicle driving trajectory route, thereby achieving the purpose of generating a vehicle-side navigation path with comprehensive and complete data and customized routes, thereby achieving the technical effect of improving the adaptability of the vehicle navigation path to the personalized needs of users and enhancing the user experience, thereby solving the technical problems in the related technology that the navigation path of the vehicle navigation solution is difficult to adapt to the personalized driving trajectory needs and the user experience of autonomous driving is poor.
[0048] The vehicle-side navigation path generation solution provided in the embodiments of the present application is mainly applicable to scenarios in the field of intelligent driving technology involving generating real-time and detailed navigation paths for the vehicle-side, and can especially show significant advantages in the following application scenarios (only examples, not limited to these).
[0049] In AI driving services, vehicles need to learn and adapt to the driver's personalized driving habits and route preferences. The above vehicle-side navigation path generation method generates a complete navigation path that adapts to personalized needs by integrating actual driving trajectory data and initial navigation information, significantly improving the user experience and safety of autonomous driving driving services.
[0050] In urban road driving scenarios, the urban road environment is relatively complex. For example, roads include intersections, roundabouts, forked roads and other types. The above-mentioned vehicle-side 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 emergencies such as road construction. It can quickly adjust and generate a navigation path that matches the actual driving trajectory.
[0051] In highway driving scenarios, higher speed and safety requirements are placed on vehicles. The above-mentioned vehicle-side navigation path generation method ensures the accuracy of the navigation path through interval sampling and splicing of navigation information, especially when dealing with key decision points such as highway exits and service area entrances, providing more detailed road structure data and vehicle navigation data.
[0052] The above vehicle-side navigation path generation method can also be integrated into the intelligent transportation system to optimize traffic flow and improve road utilization efficiency. By collecting and processing the actual driving trajectory data of the vehicle, a more reasonable route planning can be generated, traffic congestion can be reduced, and the operating efficiency of the entire transportation network can be improved.
[0053] In special vehicle navigation scenarios, for special vehicles such as rescue vehicles, fire trucks, military vehicles, etc., the above-mentioned vehicle-side navigation path generation method can generate navigation paths that meet special driving needs, especially in emergency situations. It can quickly plan and execute the best route to improve mission execution efficiency and safety.
[0054] From the above, the above-mentioned vehicle-side navigation path generation method provided in this application is not only suitable for the general driving needs of autonomous driving vehicles, but also can provide more accurate, safer and more personalized navigation services in various complex scenarios, and has broad application prospects.
[0055] The following takes the application scenario of artificial intelligence driving as an example to further introduce other optional implementation methods of the above-mentioned vehicle-side navigation path generation method provided in the embodiment of the present application.
[0056] As an optional implementation manner, the above-mentioned road section navigation data at least includes: road structure data and vehicle navigation data.
[0057] The above-mentioned road structure data may specifically include the following data: road name, such as the official 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 on the road (used to help the autonomous driving system select the appropriate lane for driving); lane type, such as ordinary lane, left turn lane, right turn lane, etc.; lane speed limit, such as speed limit information for each lane; lane direction, such as the driving direction of each lane; intersection information, such as the location and turning instructions of the intersection, including left turn, right turn, straight ahead, etc.; road grade, such as expressway, main road, secondary road, etc.; road length; road width, such as the total width of the road, lane width, etc.; road signs, such as traffic signs and markings on the road, including lane dividers, speed limit signs, intersection signs, etc.; road conditions, such as the road surface condition, slope and other information.
[0058] The above-mentioned vehicle navigation data may specifically include the following data: map data, such as information on roads, intersections, landmarks, etc.; positioning data, such as real-time location, speed, direction, etc. of the vehicle; route planning data, such as the best path, traffic conditions, estimated arrival time, etc.; voice navigation data, such as voice guidance, prompts, warnings, etc.; traffic information data, such as real-time traffic conditions, accidents, construction, etc.; point of interest data, such as information on gas stations, restaurants, attractions, etc.; vehicle information data, such as vehicle model, speed, fuel level, etc.; driving behavior data, such as behavior data such as sudden braking and speeding; warning data, such as dangerous road sections, speed limit warnings, etc.; user preference data, such as user-set preferences, commonly used routes, etc.
[0059] The above-mentioned road section navigation data in this application can be V2 navigation data including more fine-grained road structure data and vehicle navigation data. By subdividing the navigation data, this application can more accurately match the actual driving trajectory of the vehicle and enhance the execution effect of the navigation instructions, especially in scenarios with complex road structures and changing vehicle navigation requirements. It can provide more detailed and comprehensive navigation information and improve the driving safety and user experience of autonomous driving vehicles.
[0060] As an optional implementation, in the above step S202, based on the driving trajectory data, the initial navigation information is cleaned to obtain the intermediate navigation information, which may also include the following execution steps:
[0061] Step S221, for any target yaw path among the multiple yaw paths, based on the driving trajectory data and the initial navigation information, distance matching is performed between the target driving trajectory and the target yaw path 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 deviation path to obtain intermediate navigation information.
[0063] The data cleaning process includes data segmentation and data pruning based on the matching results. Specifically, according to the route consistency matching result between the target driving trajectory and the target yaw path, the data segmentation method of part of the navigation information is determined, and the data to be pruned in 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 line point on the target yaw path. For example, if the distance is greater than a preset threshold, it is determined that the target driving trajectory and the target yaw path are inconsistent at the position corresponding to the trajectory point and the navigation line point.
[0065] The road structure data in the initial navigation information at least includes the road width. In the embodiment of the present application, the data segmentation method can also be determined by whether the distance between the track point and the navigation line point is greater than the road width.
[0066] Through the technical solutions provided by the above steps S221 to S222, the present application can accurately identify navigation information that is inconsistent with the target driving trajectory through the data cleaning step, and ensure that the personalized driving needs of the user reflected by the target yaw path are fully considered through distance matching and targeted data segmentation and pruning, further ensuring the accuracy and practicality of the intermediate navigation information, and providing a clean and optimized data foundation for the subsequent generation of personalized navigation paths.
[0067] As an optional implementation, in the above 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 a matching result, which may also include the following execution steps:
[0068] Step S2211, traversing the track points on the target driving track and the navigation points on the target yaw path, and calculating the distance between the current track point in the traversal and the current navigation point based on the driving track data and the initial navigation information;
[0069] Step S2212, establishing a matching relationship between the trajectory point and the navigation line point according to the distance to obtain a matching result.
[0070] In the AI driving application scenario, an optional navigation path and driving trajectory is as follows: Figure 3 shown. Figure 3In the figure, the target driving trajectory 301 is an actual driving trajectory recorded by the vehicle after the user manually intervenes in the route learning stage, and the target driving trajectory corresponds to the driving trajectory data; the navigation path 302a, the navigation path 302b and the navigation path 302c are the navigation paths corresponding to the multiple groups of V2 navigation data recorded by the vehicle during the route learning stage. It is easy to find that the above target driving trajectory is a relatively long and complete vehicle driving route, and the above multiple navigation paths are multiple driving sections in the target trip, and the vehicle records its re-planned V2 navigation data in these driving sections.
[0071] The target driving trajectory 301 includes a plurality of trajectory points, and the navigation paths 302a, 302b, and 302c all include a plurality of trajectory points. When the target driving trajectory 301 is distance matched with each navigation path (here, the navigation path 302b is taken as an example), 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 have the same route at the corresponding position of the current trajectory point and the current navigation point, and 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 between the target driving trajectory 301 and each of the above-mentioned navigation paths 302a, 302b, and 302c is established, 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 by the above steps S2211 to S2212, the present application can ensure a high degree of consistency between navigation information and the actual driving trajectory by accurately calculating the distance and establishing a matching relationship. Especially in cases where the vehicle's driving speed changes or road conditions are complex, the application can accurately capture the user's personalized needs through the off-course sections, provide a more stable and reliable navigation service, and improve the driving safety and efficiency of autonomous driving vehicles.
[0073] As an optional implementation, in the above step S2212, establishing a matching relationship between the track point and the navigation line point according to the distance may further include the following execution steps:
[0074] Step S2213, in response to the distances between the current track points of the continuous target number and the current navigation line points in the traversal all satisfying the target conditions, starting from the first track point among the continuous target number of current track points, a matching relationship between the track points and the corresponding navigation line points is sequentially established.
[0075] In the case where there are multiple close points on the target driving trajectory, in order to further improve the accuracy of route matching, a variety of constraints are verified and matched based on the matching section v2 and the corresponding trajectory points; after finding the first correct matching relationship, the subsequent v2 and trajectory points are constrained by the accumulated offset, direction and other information, and then the corresponding relationship between the trajectory points and the navigation points is matched.
[0076] Through the technical solution provided in the above step S2213, the matching strategy for the number of continuous targets in the present application can effectively reduce the matching error and ensure the accurate correspondence between the continuous trajectory starting from the first matching point and the navigation information. This is especially effective for processing long-distance driving and multi-segment yaw paths, and can provide a continuous and smooth navigation experience.
[0077] As an optional implementation, in the above step S222, based on the matching result, data segmentation and data pruning are performed on the part of the navigation information corresponding to the target deviation path in the initial navigation information to obtain the intermediate navigation information, which may also include the following execution steps:
[0078] Step S2221, determining a data segmentation point based on the matching result and the partial navigation information, wherein the distance between the navigation line point corresponding to the data segmentation point and the matched track 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 track point;
[0079] Step S2222, performing data segmentation on part of the navigation information according to the data segmentation points to obtain a segmentation result;
[0080] Step S2223, determining a data trimming point based on the matching result and the segmentation result, wherein the target yaw path is separated from the target driving track at the navigation line point corresponding to the data trimming point;
[0081] Step S2224, performing data pruning on the segmentation result according to the data pruning points to obtain intermediate navigation information.
[0082] When selecting the data segmentation points of the navigation information, two situations are considered. In the first situation, when it is found that the distance between the trajectory point and the navigation line point is greater than the preset threshold, it is considered that a route separation occurs between the target driving trajectory and the target deviation path. At this time, the position corresponding to the trajectory point and the navigation line point is determined as the position of a data segmentation point. In the second situation, when it is found that the distance between the trajectory point and the navigation line point is greater than the road width, it is considered that the navigation line point is not within the road range. At this time, the position corresponding to the trajectory point and the navigation line 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 of data according to the determined multiple data segmentation points, that is, the segmentation result includes multiple segments of V2 navigation data obtained after segmentation.
[0083] For each segment of V2 navigation data, some data near the beginning and the end may be separated from the track. Therefore, based on the matching results and the segmentation results, starting from the starting navigation line point corresponding to each segment of V2 navigation data (towards the direction of the ending navigation line point), check one by one to determine whether the navigation line point and the corresponding track point meet the target constraint, and determine the navigation line point that first meets the target constraint from the starting navigation line point as the head data trimming point corresponding to this segment of V2 navigation data; similarly, starting from the ending navigation line point corresponding to each segment of V2 navigation data (towards the direction of the starting navigation line point), check one by one to determine whether the navigation line point and the corresponding track point meet the target constraint, and determine the navigation line point that first meets the target constraint from the ending navigation line point as the tail data trimming point corresponding to this segment of V2 navigation data; delete the data before the head data trimming point and the data after the tail data trimming point in this segment of V2 navigation data to obtain a trimmed segment of V2 navigation data. When multiple segments of V2 navigation data in the segmentation result are trimmed, intermediate navigation information is obtained. The above intermediate navigation information includes multiple segments of trimmed V2 navigation data.
[0084] In an exemplary application scenario, the road width information of the matched trajectory point, the consistency of the V2 navigation data and the trajectory direction are checked, and a point that meets the conditions is found as the starting point of the V2 navigation data. The incorrect line points and road information in the front are deleted. Then the tail points are detected in reverse order to check whether the width and direction meet the requirements. In addition, based on the navigation line points on the branching section (subpath), it is determined whether the navigation line point is separated from the target driving trajectory. If it is determined that the navigation line point is separated from the target driving trajectory, the V2 navigation data corresponding to the navigation line point is deleted, thereby obtaining multiple segments of trimmed V2 navigation data.
[0085] Through the technical solutions provided by the above steps S2221 to S2224, the present application eliminates navigation information that is irrelevant to or does not match the actual driving trajectory through precise data segmentation and pruning. Especially when road conditions change or user behavior changes, the navigation strategy can be quickly adjusted to provide more accurate and timely navigation services, thereby improving the driving safety and flexibility of autonomous driving vehicles.
[0086] It should be noted that, in the process of data segmentation and pruning, the above method steps provided in the embodiment of the present application take into account the personalized driving needs of the user reflected in the yaw path. In these yaw sections, the yawed driving trajectory is used as the basis, and in other sections, the navigation path generated by the system is used as the basis. In this way, a vehicle-side navigation path is generated that meets the personalized driving needs of the user (that is, consistent with the yawed driving trajectory route) and contains rich navigation information.
[0087] As an optional implementation, in the above step S203, the driving trajectory data is sampled by intervals using the intermediate navigation information to obtain the sampling result, which may also include the following execution steps:
[0088] Step S231, performing route comparison on the intermediate navigation information and the driving trajectory data to obtain a road section to be sampled;
[0089] Step S232, performing interval sampling on the driving trajectory data based on the road section interval to obtain a sampling result.
[0090] The road section to be sampled is a partial track section on the target driving track where the V2 navigation data is missing. The driving track data is sampled within this section so that the V2 navigation data is generated based on the sampling result to complete the vehicle-side navigation path.
[0091] Through the technical solutions provided by the above steps S231 to S232, the present application specifically supplements the detailed driving data on the driving trajectory that are missing in the original navigation information through interval sampling, ensuring that the generated vehicle-side navigation path covers all driving intervals and providing more complete and detailed path guidance.
[0092] As an optional implementation, in the above step S231, the intermediate navigation information and the driving trajectory data are compared to obtain the road section to be sampled, and the following execution steps may also be included:
[0093] Step S2311, performing route analysis on the intermediate navigation information to determine the navigation section;
[0094] Step S2312, determining the section interval based on the portion of the driving trajectory not covered by the navigation section in the target driving trajectory corresponding to the driving trajectory data.
[0095] The above navigation sections are the navigation sections corresponding to the pruned V2 navigation data. The intermediate navigation information contains detailed and comprehensive V2 navigation data corresponding to these navigation sections. The part of the driving trajectory that is not covered by the navigation section in the target driving trajectory is the section interval where the V2 navigation data is missing. In this section interval, the driving trajectory data needs to be sampled to complete the complete V2 navigation information that is consistent with the target driving trajectory route.
[0096] Through the technical solutions provided by the above steps S2311 to S2312, the present application can ensure that the sampling points cover all driving ranges that are not fully described by the navigation information, especially when processing non-standard road information such as new roads and small roads, and can provide more comprehensive and detailed driving data, thereby improving the driving safety and user experience of autonomous driving vehicles.
[0097] As an optional implementation, in the above step S232, the driving trajectory data is sampled based on the road section interval to obtain the sampling result, which may also include the following execution steps:
[0098] Step S2321, determining a target sampling strategy based on the road type corresponding to the road section;
[0099] Step S2322, using the road section interval and target sampling strategy, interval sampling is performed on the driving trajectory data to obtain a sampling result.
[0100] The road type corresponding to the above-mentioned road section interval may be a turning section, a straight section, etc. According to the above-mentioned target sampling strategy, when sampling the driving trajectory data on the turning section, a denser trajectory sampling point can be selected (for example, one trajectory sampling point is selected every 2 meters), so as to accurately characterize the road structure data and vehicle navigation data of the turning section. Since the road conditions of the straight section are relatively simple, according to the above-mentioned target sampling strategy, when sampling the driving trajectory data on the straight section, a sparser trajectory sampling point can be selected (for example, one trajectory sampling point is selected every 20 meters), so as to reduce the sampling cost.
[0101] Furthermore, according to the above 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 are obtained from the driving trajectory data to obtain a sampling result.
[0102] Through the technical solutions provided by the above steps S2321 to S2322, the present application can collect more accurate and effective driving data according to different road types and conditions through customized sampling strategies, especially when dealing with different road types such as highways and urban roads. It can provide more targeted and efficient data support, and improve the accuracy and real-time performance of the path planning and navigation control of autonomous driving vehicles.
[0103] As an optional implementation, in the above step S204, the sampling result includes multiple trajectory sampling points on the vehicle driving trajectory; the intermediate navigation information and the sampling result are spliced to obtain the target navigation information, and the following execution steps may also be included:
[0104] Step S241, obtaining road structure data and vehicle navigation data matched by multiple trajectory sampling points;
[0105] Step S242, generating navigation information to be spliced based on the road structure data and the vehicle navigation data;
[0106] Step S243, performing navigation semantic splicing on the intermediate navigation information and the navigation information to be spliced to obtain a vehicle-side navigation path.
[0107] In an exemplary application scenario, with the goal of connecting the two segments of V2 head and tail points, multiple trajectory sampling points in the sampling results are translated, rotated, stretched, etc., so that two adjacent segments of V2 navigation data in the intermediate navigation information can be connected by at least one trajectory sampling point. In addition, the embodiment of the present application also considers the road structure and the distance between the navigation line point and the trajectory point, and samples and interrupts the target driving trajectory to generate supplementary line points between the two segments of V2 navigation paths with a correct connection relationship and in accordance with the road structure.
[0108] In the above application scenario, when implementing navigation semantic splicing, multiple trajectory sampling points are used as multiple supplementary navigation points, and V2 navigation data (which can be obtained from the historical V2 navigation database) is added to each supplementary navigation point to generate a supplementary V2 navigation segment. Further, based on the road structure information in the supplementary V2 navigation segment and the road structure information of multiple V2 navigation sections 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 the target navigation information.
[0109] Through the technical solutions provided in the above steps S241 to S253, the present application can achieve seamless data fusion by splicing the actual driving data (sampling results) 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 driving vehicle.
[0110] In summary, the embodiment of the present application saves the navigation path data generated by real-time learning on the vehicle side, combines the actual driving trajectory of the vehicle and the navigation path data, and generates a target navigation path for the entire route. Specifically, based on the actual driving trajectory, the navigation path data corresponding to multiple learning paths are spliced, and the duplicate data, missing data, and erroneous data in the splicing results are adjusted (for example, 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 learned navigation path data and the user personalized data corresponding to the actual driving trajectory, that is, the obtained target navigation path is a customized information complete navigation path.
[0111] In autonomous driving technology, the embodiment and satisfaction of users' personalized driving needs is a key point to improve driving experience and safety. To this end, the core of this application is how to integrate the user's personalized driving trajectory on the yaw path with the basic navigation path generated by the system to generate a vehicle-side navigation path that meets the user's personalized needs and provides rich navigation information.
[0112] Specifically, when processing off-course paths, the present application gives priority to using the user's actual driving trajectory data on these paths, because these data can more accurately reflect the user's driving habits and preferences. On non-off-course sections, that is, sections where the user does not show any special driving preferences, the system defaults to using its own planned navigation path, which ensures that the vehicle can still follow an efficient and safe route without special requirements from the user.
[0113] In this way, the application can ensure that the vehicle-side navigation path is more accurate on the user's preferred path, while maintaining the optimization of the system path on other sections, which not only meets the personalized needs, but also maintains the efficiency and safety of the overall path planning. The generation of the vehicle-side navigation path not only takes into account the personalization of the driving trajectory, but also combines rich navigation information, including road structure data and vehicle navigation data, which enables the autonomous driving vehicle to better understand and adapt to the road environment when executing the vehicle-side 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 used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0115] It should be noted that, for the above method embodiments, for the sake of simplicity, the technical solutions in the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of actions in the described action combinations, because according to the present application, some of the above steps can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification of this application belong to preferred embodiments, and the actions and modules involved are not necessarily necessary to implement the technical solutions of the present application.
[0116] According to an embodiment of the present invention, a device embodiment of a vehicle navigation device is also provided, and the vehicle navigation device is used to implement the above method embodiment and multiple optional implementations of the method embodiment, and the technical content that has been described in the previous text is no longer repeated in the device embodiment. It should be noted that in the following related descriptions of the device embodiment, a "module" can be software, hardware, or a combination of software and hardware for implementing a specified function.
[0117] Figure 4 is a structural block diagram of a vehicle navigation device according to an embodiment of the present application, such as Figure 4As shown, the vehicle navigation device includes:
[0118] An acquisition module 401 is used to acquire 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 the segment navigation data corresponding to the multiple segments of the yaw path in the path learning stage;
[0119] The data processing module 402 is used to perform data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information;
[0120] The sampling module 403 is used to perform interval sampling on the driving trajectory data using the intermediate navigation information to obtain a sampling result;
[0121] The generation module 404 is used to splice the intermediate navigation information and the sampling results to obtain the vehicle-side navigation path.
[0122] Optionally, in the vehicle navigation device, the road section navigation data at least includes: road structure data and vehicle navigation data.
[0123] Optionally, the data processing module 402 is also used to: for any target yaw path among the multiple yaw paths, perform distance matching between the target driving trajectory and the target yaw path based on the driving trajectory data and the initial navigation information to obtain a matching result; based on the matching result, perform data segmentation and data pruning on part of the navigation information corresponding to the target yaw path in the initial navigation information to obtain intermediate navigation information.
[0124] Optionally, the data processing module 402 is also used to: traverse the trajectory points on the target driving trajectory and the navigation points on the target yaw path, calculate the distance between the current trajectory point in the traversal and the current navigation point based on the driving trajectory data and the initial navigation information; establish a matching relationship between the trajectory point and the navigation point based on the distance to obtain a matching result.
[0125] Optionally, the above-mentioned data processing module 402 is also used to: in response to the distances between the current trajectory points of the continuous target number and the current navigation line points in the traversal all satisfying the target conditions, starting from the first trajectory point among the current trajectory points of the continuous target number, sequentially establish a matching relationship between the trajectory points and the corresponding navigation line points.
[0126] Optionally, the data processing module 402 is further used to: determine a data segmentation point based on the matching results and part of the navigation information, 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; perform data segmentation on part of the navigation information according to the data segmentation point to obtain a segmentation result; determine a data pruning point based on the matching results and the segmentation results, wherein the target yaw path is separated from the target driving trajectory at the navigation line point corresponding to the data pruning point; perform data pruning on the segmentation result according to the data pruning point to obtain intermediate navigation information.
[0127] Optionally, the sampling module 403 is further used to: perform route comparison on the intermediate navigation information and the driving trajectory data to obtain a road section interval to be sampled; perform interval sampling on the driving trajectory data based on the road section interval to obtain a sampling result.
[0128] Optionally, the sampling module 403 is further used to: perform route analysis on the intermediate navigation information to determine the navigation section; and determine the section interval based on a portion of the target driving trajectory corresponding to the driving trajectory data that is not covered by the navigation section.
[0129] Optionally, the sampling module 403 is further used to: determine a target sampling strategy based on the road type corresponding to the road section interval; and perform interval sampling on the driving trajectory data using the road section interval and the target sampling strategy to obtain a sampling result.
[0130] Optionally, the sampling result includes multiple trajectory sampling points on the vehicle's driving trajectory; the above-mentioned generation module 404 is also used to: obtain road structure data and vehicle navigation data matching multiple trajectory sampling points; generate navigation information to be spliced based on the road structure data and vehicle navigation data; perform navigation semantic splicing on the intermediate navigation information and the navigation information to be spliced to obtain the vehicle-side navigation path.
[0131] The above-mentioned vehicle navigation device in the embodiment of the present application can realize the automation and integration of the above-mentioned vehicle navigation method, and is particularly suitable for the navigation system of an autonomous driving vehicle. It 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 above-mentioned acquisition module 401, data processing module 402, sampling module 403 and generation module 404 correspond to steps S21 to S24 in the method embodiment. The four modules are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned method embodiment.
[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 hardware is used to implement the above modules, the various modules can be set in the same processor, or the various modules can be set 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, or the above modules can also be run as part of the device on a processor such as a processor. Figure 1 In the computing terminal 10 shown.
[0134] According to an embodiment of the present invention, a vehicle embodiment is also provided. The vehicle includes 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-mentioned vehicle navigation method.
[0135] The above-mentioned vehicle in the embodiment of the present application can utilize the above-mentioned method and device to achieve more accurate and real-time path planning and navigation control, which is particularly suitable for autonomous driving vehicles, and can provide a safe, stable and efficient driving experience in various driving environments, thereby improving user satisfaction and vehicle performance.
[0136] According to an embodiment of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to implement the above-mentioned vehicle navigation method.
[0137] Optionally, the above-mentioned computer storage media may include but are not limited to: hard disk drive (HDD), solid state drive (SSD), USB flash drive, optical disk, memory card, cloud storage media and network storage device (NAS).
[0138] Optionally, the computer-readable storage medium may be configured to store a computer program for executing the following steps: obtaining 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 segment navigation data corresponding to multiple segments of yaw paths during the path learning phase; 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 sampling results; and splicing the intermediate navigation information and the sampling results to obtain a vehicle-side navigation path.
[0139] The above-mentioned computer-readable storage medium in the embodiment of the present application can be used to store and transmit the execution program of the above-mentioned method, and is particularly suitable for the navigation system of an autonomous driving vehicle. It can improve the safety, stability and user satisfaction of vehicle driving, and is suitable for various driving environments and scenarios. It provides powerful data processing and navigation control capabilities for the development of autonomous driving technology.
[0140] According to an embodiment of the present invention, a computer program product is also provided. The computer program product includes a computer program, and when the computer program is executed by a processor, the above vehicle navigation method can be implemented.
[0141] Optionally, the computer program product may provide vehicle navigation services based on the vehicle navigation method.
[0142] Optionally, in this embodiment, the computer program product may be a set of instructions and codes pre-written according to the vehicle navigation method. The computer program product may run on various computer platforms, including personal computers, servers, mobile devices, etc.
[0143] Optionally, in this 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 characterize the target driving trajectory recorded by the target vehicle in the path learning stage, and the initial navigation information includes segment navigation data corresponding to multiple segments of yaw paths 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 sampling results; and splicing the intermediate navigation information and the sampling results to obtain a vehicle-side navigation path.
[0144] The above-mentioned computer program product in the embodiment of the present application can provide more accurate and real-time path planning and navigation control for autonomous driving vehicles, and is particularly suitable for handling complex road environments and emergencies. It can improve the safety, stability and user satisfaction of vehicle driving, and is suitable for various driving environments and scenarios. It provides powerful data processing and navigation control capabilities for the development of autonomous driving technology. It can also be applied to intelligent transportation systems, vehicle safety monitoring and other fields, and provide strong support for future smart travel and traffic safety.
[0145] In the above-mentioned multiple embodiments of the present application, the description of each embodiment has different emphases. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0146] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of multiple modules can be a logical function division, and there can be any other possible division methods when actually implemented in the application scenario; for another example, multiple modules (or units or components in the modules) can be combined with each other and can be integrated into another system. For example, some features of the method embodiments described above can be ignored or skipped.
[0147] It should be noted that in the above-mentioned embodiments, the modules, components or units described as separate parts can be physically separated or physically integrated. The parts displayed as modules or units can be physical modules or physical units, or virtual modules or virtual units, that is, multiple modules or multiple units can be in the same position, or distributed in multiple positions or multiple spaces. In the application scenario, according to the actual needs of the scenario, some or all of the multiple modules or multiple units can be selected to implement the technical solutions of the embodiments of the present application, thereby achieving the corresponding technical objectives.
[0148] In particular, for an integrated functional module or functional unit, if it is implemented in the form of a software functional unit and sold or used as an independent product, the module or functional unit can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
[0149] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A vehicle-side navigation path generation method, characterized in that: include: Acquire 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 segment navigation data corresponding to multiple segments of off-course paths in the path learning stage; Based on the driving trajectory data, the initial navigation information is cleaned to obtain intermediate navigation information; Using the intermediate navigation information, performing interval sampling on the driving trajectory data to obtain a sampling result; The intermediate navigation information and the sampling result are spliced to obtain a vehicle-side navigation path.
2. The vehicle-side navigation path generation method according to claim 1, characterized in that: The road section navigation data at least includes: road structure data and vehicle navigation data.
3. The vehicle-side navigation path generation method according to claim 1, characterized in that: Based on the driving trajectory data, the initial navigation information is cleaned to obtain the intermediate navigation information, including: For any target yaw path among the multiple yaw paths, based on the driving trajectory data and the initial navigation information, distance matching is performed between the target driving trajectory and the target yaw path to obtain a matching result; Based on the matching result, data segmentation and data pruning are performed on a portion of the navigation information corresponding to the target yaw path in the initial navigation information to obtain the intermediate navigation information.
4. The vehicle-side navigation path generation method according to claim 3, 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 yaw path, and the matching result is obtained, including: Traversing the track points on the target driving track and the navigation points on the target yaw path, and calculating the distance between the current track point in the traversal and the current navigation point based on the driving track data and the initial navigation information; A matching relationship between the track point and the navigation line point is established according to the distance to obtain the matching result.
5. The vehicle-side navigation path generation method according to claim 4, characterized in that: Establishing a matching relationship between the track point and the navigation line point according to the distance includes: In response to the distances between the current track points of the continuous target number and the current navigation line points in the traversal all satisfying the target conditions, starting from the first track point among the current track points of the continuous target number, a matching relationship between the track points and the corresponding navigation line points is sequentially established.
6. The vehicle-side navigation path generation method according to claim 3, characterized in that: Based on the matching result, data segmentation and data pruning are performed on a portion of the navigation information corresponding to the target deviation path in the initial navigation information to obtain the intermediate navigation information, including: Determine a data segmentation point based on the matching result and the partial navigation information, wherein a distance between a navigation line point corresponding to the data segmentation point and a matched track point is greater than a preset threshold, or the navigation line point corresponding to the data segmentation point is not within a road range corresponding to the matched track point; According to the data segmentation points, data segmentation is performed on the part of the navigation information to obtain a segmentation result; Determine a data pruning point based on the matching result and the segmentation result, wherein the target yaw path is separated from the target driving track at a navigation line point corresponding to the data pruning point; According to the data pruning points, data pruning is performed on the segmentation result to obtain the intermediate navigation information.
7. The vehicle-side navigation path generation method according to claim 1, characterized in that: Using the intermediate navigation information, interval sampling is performed on the driving trajectory data, and the sampling results obtained include: Performing route comparison on the intermediate navigation information and the driving trajectory data to obtain a road section to be sampled; The driving trajectory data is sampled based on the road section interval to obtain the sampling result.
8. The vehicle-side navigation path generation method according to claim 7, characterized in that: Comparing the intermediate navigation information with the driving trajectory data to obtain the road section to be sampled includes: Performing route analysis on the intermediate navigation information to determine a navigation section; The section interval is determined based on a portion of the driving trajectory not covered by the navigation section in the target driving trajectory corresponding to the driving trajectory data.
9. The vehicle-side navigation path generation method according to claim 7, characterized in that: The driving trajectory data is sampled based on the road section interval, and the sampling result is obtained including: Determining a target sampling strategy based on the road type corresponding to the road section; The driving trajectory data is sampled by using the road section interval and the target sampling strategy to obtain a sampling result.
10. The vehicle-side navigation path generation method according to claim 1, characterized in that: The sampling result includes a plurality of trajectory sampling points on the vehicle driving trajectory; The intermediate navigation information and the sampling result are spliced to obtain the vehicle-side navigation path, including: Acquire road structure data and vehicle navigation data matched by the plurality of trajectory sampling points; Generate navigation information to be spliced based on the road structure data and the vehicle navigation data; The intermediate navigation information and the navigation information to be spliced are subjected to navigation semantic splicing to obtain the vehicle-side navigation path.
11. A vehicle-side navigation path generation device, characterized in that: include: An acquisition module, 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 in the path learning stage, and the initial navigation information includes the segment navigation data corresponding to the multiple segments of the yaw path in the path learning stage; A data processing module, used for performing data cleaning processing on the initial navigation information based on the driving trajectory data to obtain intermediate navigation information; A sampling module, used to perform interval sampling on the driving trajectory data using the intermediate navigation information to obtain a sampling result; A generation module is used to splice the intermediate navigation information and the sampling result to obtain a vehicle-side navigation path.
12. A vehicle, characterized in that: It includes an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the vehicle-side navigation path generation method described in any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the vehicle-side navigation path generation method described in any one of claims 1 to 10.
14. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the vehicle-side navigation path generation method according to any one of claims 1 to 10.
Citation Information
Patent Citations
Road fault detection method and device
CN106952473A
Method and device for acquiring actual driving track of vehicle, storage method of driving history and navigation method of driving history
CN108240813A
Navigation updating method and device, electronic equipment and storage medium
CN114252083A
Method and device for determining recommended route, electronic equipment and vehicle
CN114964279A
Map navigation method and device based on driving preference
CN117537834A
