Memory route mapping method and apparatus, vehicle machine controller, and vehicle

Abstract

A memory route mapping method and apparatus, a vehicle machine controller, a vehicle, a computer-readable storage medium, and a program product, relating to the technical field of electronic maps. The method comprises: acquiring road vector information and driving trajectory information collected in real time during the driving of a user vehicle on a preset route, and acquiring navigation information provided by a vehicle-end navigation map application (S101); performing graph optimization processing on the driving trajectory information, and generating high-precision trajectory information (S102); on the basis of the high-precision trajectory information and the road vector information, aggregating a plurality of road vector elements, and generating N segments of lightweight road information on the preset route (S103); and on the basis of the N segments of lightweight road information and the navigation information, creating a memory map of the preset route (S104). According to the described method, real-time mapping data collected and reported by a mass-produced user vehicle is used, so that sampling costs can be reduced, sampling data can be conveniently and flexibly obtained, and mapping content covers an entire road. In addition, graph optimization processing is performed on sampled driving trajectory information, thereby improving the accuracy and reliability of a memory map.

Description

Route mapping method, device, vehicle controller and vehicle

[0001] This application claims priority to Chinese Patent Application No. 2024112160467, filed with the State Intellectual Property Office of China on August 30, 2024, entitled "A Lightweight Memory Route Mapping Method, Apparatus, Vehicle Controller and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of electronic map technology, specifically to a method, apparatus, vehicle controller, and vehicle for creating maps with memory routes. Background Technology

[0003] The AI ​​(Artificial Intelligence) chauffeur service relies on offline maps that remember routes and needs to support a large number of users without large-scale testing. Simultaneously, it needs to ensure a lightweight mapping process while maintaining mapping quality to reduce costs and improve efficiency.

[0004] Currently, traditional route mapping relies on expensive specialized surveying equipment, such as lidar and mapping-grade GNSS (Global Navigation Satellite System), to improve sampling accuracy. This method is costly and has limited practicality. Furthermore, post-processing of lidar and mapping-grade GNSS data requires significant computational resources to generate usable high-precision maps, and cost constraints limit the coverage of these maps, preventing them from achieving full coverage of driving routes.

[0005] Summary of the Invention

[0006] To address or partially address the problems existing in related technologies, this application provides a memory route mapping method, apparatus, vehicle controller, and vehicle, which can solve the problems of high cost, large consumption of computing resources, and inability to fully cover driving roads caused by traditional memory map creation.

[0007] Firstly, this application provides a method for creating a memory route map, which can be applied to a vehicle control system, the method comprising:

[0008] The system acquires real-time road vector information and driving trajectory information collected during the user's vehicle's journey along a preset route, as well as navigation information provided by the vehicle-side navigation map application; wherein the road vector information includes multiple road vector elements.

[0009] The driving trajectory information is subjected to image optimization processing to generate high-precision trajectory information;

[0010] Based on the high-precision trajectory information and the road vector information, the multiple road vector elements are aggregated to generate N lightweight road information segments on the preset route, where N≥1;

[0011] Based on the N segments of lightweight road information and the navigation information, a memory map of the preset route is created.

[0012] In conjunction with the first aspect, in one possible implementation, the vehicle trajectory information includes: recursive DR (Range Direct Regression) information and GPS information along the vehicle trajectory; the step of performing graphical optimization processing on the vehicle trajectory information to generate high-precision trajectory information includes:

[0013] The recursive DR information and the GPS information are fused together, and after graph optimization processing, the high-precision trajectory information is generated.

[0014] In conjunction with the first aspect, in another possible implementation, the step of aggregating the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N segments of lightweight road information on the preset route includes:

[0015] Obtain at least two sampled data points recorded at different sampling times for the multiple road vector elements; aggregate the at least two sampled data points using a spatial distance algorithm to generate N segments of lightweight road information.

[0016] The spatial distance algorithm is as follows: points of continuous elements in at least two sampled data are aggregated into a segment in space, and points of non-continuous elements are represented by discrete endpoints in space.

[0017] In conjunction with the first aspect, in another possible implementation, the navigation information consists of at least one navigation segment information; before creating a memory map of the preset route based on the N segments of lightweight road information and the navigation information, the method further includes:

[0018] The segments corresponding to the current navigation segment in the N segments of lightweight road information are spliced ​​together, and the at least one navigation segment information is verified and repaired to generate navigation information consistent with the driving trajectory.

[0019] The step of creating a memory map of the preset route based on the N segments of lightweight road information and the navigation information includes:

[0020] The memory map is created based on the N segments of lightweight road information and the navigation information that matches the driving trajectory.

[0021] In conjunction with the first aspect, in another possible implementation, the step of splicing together the segments corresponding to the current navigation segment from the N segments of lightweight road information, and verifying and repairing the at least one navigation segment information, includes:

[0022] For each navigation segment in the at least one navigation segment information, navigation route splicing and navigation information repair are performed; wherein, the navigation route splicing is to splice multiple navigation routes generated during the navigation reset process into a complete navigation route; the navigation information repair is to attach one or more of the following information, such as slope, curvature, and speed limit, to the correct position of the spliced ​​navigation route, and / or to complete the navigation information through semantic information extracted from the trajectory.

[0023] In conjunction with the first aspect, in yet another possible implementation, after creating the memory map of the preset route, the method further includes:

[0024] Based on the real-time location of the user's vehicle, at least one nearby electronic map is loaded, and the at least one electronic map includes the created memory map;

[0025] Based on the current route of the user vehicle, a target map is searched in at least one electronic map, and the target map contains a route that matches the current route of the user vehicle.

[0026] The target map is loaded and provided to the vehicle for display, and also provides support for the subsequent positioning and planning module.

[0027] Secondly, this application provides a memory route mapping device, the device comprising:

[0028] The acquisition module is used to acquire real-time road vector information and driving trajectory information collected by the user's vehicle while it is driving on a preset route, as well as navigation information provided by the vehicle-side navigation map application; wherein the road vector information includes multiple road vector elements.

[0029] The optimization module is used to perform graphical optimization processing on the driving trajectory information to generate high-precision trajectory information;

[0030] The fusion module is used to aggregate the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route, where N≥1;

[0031] A creation module is used to create a memory map of the preset route based on the N segments of lightweight road information and the navigation information.

[0032] In conjunction with the second aspect, in one possible implementation, the driving trajectory information includes: trajectory recursion (DR) information and GPS information on the driving trajectory;

[0033] The optimization module fuses the recursive DR information and the GPS information, and after graph optimization processing, generates the high-precision trajectory information.

[0034] In conjunction with the second aspect, in another possible implementation, the fusion module acquires at least two sampled data points recorded at different sampling times for the plurality of road vector elements; and aggregates the at least two sampled data points using a spatial distance algorithm to generate the N segments of lightweight road information.

[0035] In conjunction with the second aspect, in yet another possible implementation, the device further includes:

[0036] The stitching and repair module is used to stitch together the segments corresponding to the current navigation segment in the N segments of lightweight road information before the creation module creates the memory map of the preset route, to verify and repair the at least one navigation segment information, and to generate navigation information consistent with the driving trajectory.

[0037] In conjunction with the second aspect, in yet another possible implementation, the device further includes:

[0038] A loading module is used to load at least one nearby electronic map based on the real-time location of the user's vehicle, wherein the at least one electronic map includes the created memory map;

[0039] The search module is used to search for a target map in at least one electronic map based on the current route of the user's vehicle, the target map containing routes that match the current route of the user's vehicle.

[0040] Thirdly, this application provides a vehicle controller, including: a memory and a processor, the memory and the processor being connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the lightweight memory route mapping method of the first aspect or any corresponding embodiment described above.

[0041] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the lightweight memory route mapping method described in the first aspect or any corresponding embodiment thereof.

[0042] In addition, this application provides a computer program product, including computer instructions for causing a computer to execute the lightweight memory route mapping method of the first aspect or any corresponding embodiment described above.

[0043] Fifthly, this application also provides a vehicle, including a vehicle controller and a data acquisition device, wherein the data acquisition device is used to collect road vector information and driving trajectory information of a user vehicle in real time during the driving process on a preset route, and to report the road vector information and the driving trajectory information to the vehicle controller;

[0044] The vehicle controller is used to acquire the road vector information and driving trajectory information reported by the acquisition device, as well as the navigation information provided by the vehicle-side navigation map application; to perform image optimization processing on the driving trajectory information to generate high-precision trajectory information; to aggregate the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route, where N≥1; and to create a memory map of the preset route based on the N lightweight road information segments and the navigation information.

[0045] In addition, the vehicle controller is also used to execute the lightweight memory route mapping method described in other embodiments corresponding to the first aspect above.

[0046] The lightweight memory route mapping method, device, vehicle controller, and vehicle provided in this embodiment utilize real-time mapping data collected and reported by mass-produced user vehicles, including road vector information, driving trajectory information, and other road vector elements. Compared with relying on expensive professional surveying equipment, such as lidar and surveying-grade GNSS, it saves sampling costs. Moreover, as long as it is a route on the user vehicle's driving trajectory, the sampling data for mapping can be obtained, which is convenient and flexible. Furthermore, the mapping content can achieve full coverage of roads within the driving range.

[0047] In addition, the accuracy and reliability of the mapping data are further improved by optimizing the sampled driving trajectory information and merging the processed high-precision trajectory information with N lightweight road information on the preset route to generate a memory map.

[0048] Furthermore, the method provided in this embodiment can achieve route matching and loading of correct memory map data on the vehicle side, avoiding the consumption of a large amount of network and computing resources in the backend, such as the server side. The memory map generated by this method provides reliable map support for the AI-assisted driving function.

[0049] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0050] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0051] Figure 1 is a flowchart illustrating a lightweight memory route mapping method according to an embodiment of this application;

[0052] Figure 2 is a flowchart illustrating another lightweight memory route mapping method according to an embodiment of this application;

[0053] Figure 3 is a flowchart illustrating another lightweight memory route mapping method according to an embodiment of this application;

[0054] Figure 4 is a flowchart illustrating another lightweight memory route mapping method according to an embodiment of this application;

[0055] Figure 5 is a structural block diagram of a lightweight memory route mapping device according to an embodiment of this application;

[0056] Figure 6 is a hardware structure diagram of a vehicle controller according to an embodiment of this application;

[0057] Figure 7 is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0058] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0059] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0060] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0061] Electronic maps integrate advanced Geographic Information System (GIS), remote sensing technology, Global Positioning System (GPS), and Internet technology, transforming traditional paper maps into a highly interactive, information-rich, and real-time updated digital platform.

[0062] During the creation of electronic maps, issues arise on the vehicle side, including low real-time mapping accuracy, discontinuous and incomplete navigation information due to navigation resets, and loopback matching problems. The loopback matching issue, in particular, is caused by environmental changes and accumulated geometric errors, making it difficult to guarantee a successful loopback matching rate based on low-precision real-time mapping data. Therefore, this application aims to address these problems by using algorithm optimization and data-driven intelligent matching methods to achieve high-precision route mapping based on lightweight, real-time mapping data, thereby meeting the demand for high-quality, lightweight maps in scenarios such as AI-powered assisted driving.

[0063] It should be noted that the lightweight memory route mapping method provided in this application can be executed by a mapping device or equipment. This mapping device or equipment can be implemented as part or all of an electronic device through software, hardware, or a combination of both. The electronic device can be a vehicle-side control device, such as a vehicle controller, or it can be a terminal device or a cloud device, such as a cloud server or other network device. This application does not specifically limit the electronic device. In the following method embodiments, the vehicle controller is used as the executing entity for illustration.

[0064] According to an embodiment of this application, a lightweight memory route mapping method is provided. It should be noted that the steps shown in the flowcharts 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 flowcharts, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0065] This embodiment provides a lightweight memory route mapping method, which can be used in the aforementioned vehicle controller. Figure 1 is a flowchart of the lightweight memory route mapping method according to an embodiment of this application, the method including:

[0066] Step S101: Obtain real-time road vector information and driving trajectory information collected by the user's vehicle while it is driving on the preset route, as well as navigation information provided by the vehicle-side navigation map application.

[0067] The user's vehicle is equipped with at least one sensor, such as a speed sensor, GPS sensor, or gyroscope sensor, to measure road vector information and driving trajectory information during driving.

[0068] The road vector information includes multiple road vector elements. A road vector element is a mapping element for a road, used to describe information such as the road and its surrounding routes and signs. Road vector elements include, but are not limited to, lane lines, dashed lines, lane boundary lines, road boundary lines, road surface arrows, stop lines, pedestrian crossings or crosswalks, etc., and these road vector elements can be represented by coordinate points.

[0069] The driving trajectory information refers to the trajectory route taken by the user's vehicle when traveling on a preset route. This driving trajectory information may include DR (Dead Reckoning) information and GPS information.

[0070] The DR (Depth Recording) information mainly includes the user vehicle's initial position, heading, speed, and travel time. Based on this information, the DR system can calculate the user vehicle's current position in real time using a mathematical model. This calculated position is a dynamically updated value that changes continuously over time. DR information is unaffected by external environmental factors, but errors accumulate over time.

[0071] GPS information includes three-dimensional position, velocity, and time information. For example, three-dimensional position refers to the GPS system's ability to determine a vehicle's three-dimensional location (longitude, latitude, and altitude) in real time by receiving signals from Global Positioning Satellites, accurately pinpointing the vehicle's current geographical location. Velocity information refers to the vehicle's three-dimensional velocity information, including speed magnitude and direction, in addition to position information. Time information: The GPS system provides accurate time information, which can be used for time synchronization. GPS signals can be affected by environmental factors such as multipath effects, building obstructions, and tunnels, leading to a decrease in positioning accuracy.

[0072] The navigation information provided by the vehicle navigation map application refers to the navigation information provided by the navigation map application APP on the vehicle controller for the user's vehicle's preset route. This navigation information can be displayed on the vehicle's display screen in the form of a navigation map.

[0073] Optionally, the navigation information includes ADASIS V2 navigation information. ADASIS V2 (Advanced Driver Assistance Systems Interface Specifications Version 2) is a widely used communication protocol and data format specification in the automotive industry, providing various information about the road ahead, including lane geometry, slope, curvature, speed limits, traffic signs, etc. This data can be used by ADAS applications such as adaptive cruise control, lane keeping assist, and traffic sign recognition. This protocol enables the transmission of key data such as map data, real-time traffic information, and location information between vehicles through standardized data formats and interfaces.

[0074] Step S102: Perform image optimization processing on the driving trajectory information to generate high-precision trajectory information.

[0075] In one implementation, as shown in Figure 2, when the vehicle trajectory information includes DR information and GPS information, step S102 above, which optimizes the vehicle trajectory information to generate high-precision trajectory information, may include:

[0076] Step S102-1: The recursive DR information and GPS information are fused together, and after graph optimization processing, the high-precision trajectory information is generated.

[0077] The main purpose of Pose Graph processing is to globally optimize the pose (position and orientation) of a robot or camera at different time points through graph optimization methods, so as to improve the accuracy and consistency of the entire trajectory.

[0078] This step mainly involves data fusion, trajectory construction, and graph optimization of DR and GPS information. For example, filtering and denoising are performed on GPS and DR data to improve accuracy and reliability, and the timestamps of the two data sources are synchronized to ensure temporal alignment. Then, the data is processed by a data fusion algorithm, such as Kalman filtering or its variants (e.g., Extended Kalman Filter, Unscented Kalman Filter, UKF), to optimally fuse the GPS and DR data. Next, updated GPS and DR data are received in real time, and the latest vehicle position and attitude are calculated using the data fusion algorithm. The newly calculated position points are added to the trajectory to form a continuous trajectory line.

[0079] Finally, each pose point in the trajectory is considered a node in the graph, and the relative positions between nodes are considered edges. Based on the calculations from the DR system and the observations from GPS, edges are established between nodes and assigned corresponding weights (representing measurement errors). Pose graph optimization algorithms (such as Gauss-Newton's method, Levenberg-Marquardt algorithm, and LM optimization) are used to optimize the pose graph. The algorithm iteratively adjusts the positions of the nodes to minimize the edge weights (i.e., measurement errors), thereby obtaining a globally consistent trajectory. Finally, a high-precision trajectory is output. After processing with a Pose Graph, the resulting high-precision trajectory information enables high-precision vehicle localization and navigation.

[0080] Step S103: Based on the high-precision trajectory information and the road vector information, aggregate multiple road vector elements to generate N lightweight road information segments on the preset route, where N≥1.

[0081] In this step, the preset route is divided into several segments (e.g., N segments, where N is a positive integer) based on the lightweight road information. Each segment can contain a relatively independent road with similar geographical features or navigation points.

[0082] For example, based on real-time data such as vehicle latitude and longitude coordinates, speed, and direction from high-precision trajectory information, and road vector information including road geometry (e.g., lines, curves), attributes (e.g., number of lanes, speed limits, direction), and relationships with other roads (e.g., intersections, ramps), road vector elements are aggregated. This aggregation process includes road element aggregation, such as segmenting a preset route: dividing the preset route into N segments according to certain rules (e.g., distance, time, road type changes). The length and number of each segment can be adjusted according to actual needs, and key attribute information of each road segment is extracted, such as segment length, average speed limit, number of lanes, and road type.

[0083] The road vector elements are simplified by removing unnecessary details and retaining information crucial for navigation and route planning, generating N lightweight road information segments. This information maintains high accuracy while reducing data redundancy and storage requirements, thus improving system response speed and efficiency.

[0084] Step S104: Create a memory map of the preset route based on N segments of lightweight road information and navigation information.

[0085] For example, based on the N lightweight road information generated in step S103 and the navigation information obtained in step S101, such as ADASIS V2 navigation information, the two are combined and visualized to generate a memory map of a preset route composed of N lightweight roads.

[0086] Methods for creating memory maps include, but are not limited to: SLAM (Simultaneous Localization and Mapping), comprehensive use of map visualization, such as using Geographic Information System (GIS) software, segmented memorization, associative memorization, digital memorization, and multiple reviews and exercises.

[0087] The method provided in this embodiment utilizes real-time mapping data collected and reported by mass-produced user vehicles, such as road vector information and driving trajectory information. Compared with relying on expensive professional surveying equipment, such as lidar and surveying-grade GNSS, it saves sampling costs. Moreover, as long as the user vehicle's driving trajectory is on the route, the sampling data for mapping can be obtained, which is convenient and flexible. Furthermore, the mapping content can achieve full coverage of roads within the driving range.

[0088] In addition, the accuracy and reliability of the mapping data are further improved by optimizing the sampled driving trajectory information and merging the processed high-precision trajectory information with N lightweight road information on the preset route to generate a memory map.

[0089] Furthermore, the method provided in this embodiment can achieve route matching and loading of correct memory map data on the vehicle side, avoiding the consumption of a large amount of network and computing resources in the backend, such as the server side. The memory map generated by this method provides reliable map support for the AI-assisted driving function.

[0090] Referring to Figure 3, in one possible implementation of this embodiment, step S103, which involves aggregating multiple road vector elements to generate N lightweight road information segments on a preset route, may include:

[0091] Step S103-1: Obtain at least two sampled data points of multiple road vector elements recorded at different sampling times.

[0092] Step S103-2: Aggregate at least two sampled data points using a spatial distance algorithm to generate N segments of lightweight road information.

[0093] The spatial distance algorithm is as follows: points of continuous elements in at least two sampled data sets are aggregated into a segment in space. Points of non-continuous elements can be represented by discrete endpoints in space, for example, by M endpoints. For example, a straight arrow on the ground can be represented by two points, endpoint A and vertex B. M ≥ 2 and is a positive integer.

[0094] The fusion method for continuous elements (e.g., long solid lines, road edges) uses a series of points to represent continuous elements, such as lane boundaries and road boundaries. For continuous elements, all elements are first spatially overlaid. If the lateral distance is less than or equal to a preset distance, the two lines are considered two observations of the same continuous element. If the distance is greater than the preset distance, the two lines are considered two observations of two different continuous elements. Then, geometric position averaging and attribute voting are performed on the two or more observations of the same continuous element after clustering to obtain continuous elements with better spatial position accuracy and more accurate attributes.

[0095] For discontinuous features, one possible approach is to first split the endpoints of the elements and then construct geometric constraints (position, direction), attribute constraints, and prior constraints between the point elements. Taking a ground arrow as an example, attribute constraints can be divided into arrow tail points and arrow vertices. Arrow vertices can be further divided into straight arrow vertices, left-turning arrow vertices, etc.

[0096] Taking road surface arrows as an example of prior constraints, associated arrows must be in the same lane, and lanes are separated by lane lines. Therefore, the line connecting associated arrows is not allowed to cross the lane lines.

[0097] In this step, point elements are associated and fused based on the above constraints. During the fusion process, the data is weighted according to its freshness, and new point elements are generated. Finally, the newly generated point elements are assembled to restore new road sign elements, generating lightweight road information for each segment of the route.

[0098] The navigation information consists of at least one navigation segment; the navigation information is visualized as navigation information in segments, each segment representing a distance. Prior to step S104, the method of this embodiment further includes:

[0099] Step S104-1: Segment corresponding to the current navigation segment in the N segments of lightweight road information are spliced ​​together, and the at least one navigation segment information is verified and repaired to generate navigation information consistent with the driving trajectory.

[0100] For example, since the navigation information in each segment may include incorrect or missing navigation information, and occasionally there may be information about deviation from the route, at least one navigation segment information needs to be verified and repaired before splicing the N segments of lightweight road information with the navigation information of each segment in order to correct the errors.

[0101] A specific implementation method for performing navigation route splicing and navigation information repair on each navigation segment information in at least one navigation segment information includes: splicing multiple navigation routes generated during the navigation reset process into a complete navigation route, which is called navigation route splicing.

[0102] For example, the implementation process of a navigation route splicing method includes: First, collecting all navigation route segments to be spliced, including information such as the start point, end point, waypoints, and direction of each segment. Then, matching and sorting the segments based on the coordinates of the start and end points to ensure they can be connected in the correct order. This involves spatial location algorithms such as nearest neighbor search and geometric matching. Finally, after confirming the correct order of the segments, connecting them sequentially to form a complete navigation route. During the splicing process, the connection points between segments need to be handled to ensure smooth, unbroken connections. Optionally, the spliced ​​route may also be optimized by removing redundant points and adjusting the path to reduce travel distance or time.

[0103] The navigation information repair involves attaching one or more of the following information—slope, curvature, and speed limit—to the correct location on the stitched navigation route, and / or supplementing the navigation information using semantic information extracted from the trajectory. A specific implementation process includes: using map data or real-time sensor data (such as GPS, gyroscopes, etc.), adding slope, curvature, speed limit, and other information point-by-point or segment-by-segment to the stitched navigation route. Then, using trajectory extraction techniques (such as machine learning, deep learning, etc.), semantic information such as road type (e.g., highway, urban road, rural road, etc.) and traffic signs (e.g., speed limit signs, no-turn signs, etc.) is extracted from the existing driving trajectory and attached to the corresponding navigation route segments.

[0104] For missing or incorrect information, it is supplemented or corrected by comparing it with other reliable data sources (such as navigation records from other users, traffic information released by the government, etc.). Finally, the corrected navigation information is verified to ensure its accuracy and reliability.

[0105] In addition, optionally, this step also includes: trajectory pose optimization, reversing post-processing, and trajectory semantic information extraction (such as identifying turns, ramps, etc.), and after these processing steps, the final output is navigation information consistent with the driving trajectory.

[0106] Step S104 above, which involves creating a memory map of a preset route based on N segments of lightweight road information and the navigation information, may include:

[0107] Step S104-2: Create the memory map based on the N segments of lightweight road information and navigation information that are consistent with the driving trajectory.

[0108] The navigation information generated in step S104-1 that is consistent with the driving trajectory is merged with N segments of lightweight road information to create a memory map.

[0109] In this embodiment, by associating trajectory and navigation route information, multiple navigation routes are automatically spliced ​​together, and erroneous and missing navigation information is repaired. This effectively solves the problem of discontinuous and incomplete navigation information caused by navigation reset, and provides users with more accurate, complete, and real-time navigation guidance.

[0110] In another specific implementation of this embodiment, as shown in FIG4, step S104, after creating the memory map of the preset route, further includes:

[0111] Step S105: Load at least one nearby electronic map based on the real-time location of the user's vehicle.

[0112] At least one electronic map includes the created memory map. As the user vehicle's position changes in real time during its journey, a memory map of the user vehicle's journey on each road is created according to steps S101 to S104 described above. For example, the method for creating the memory map is described in the foregoing embodiments and will not be repeated here.

[0113] Step S106: Based on the current route of the user vehicle, search for a target map in at least one electronic map, wherein the route contained in the target map matches the current route of the user vehicle.

[0114] For example, a matching method for finding a target map includes searching for nearby possible routes in an electronic map around the vehicle's current location. These routes should be consistent with the user's current driving direction. Then, the shape of the current route (e.g., via a series of coordinate points or path identifiers) is compared with the shapes of routes stored in the electronic map. For example, similarity algorithms (such as Hausdorff distance, Dynamic Time Warping (DTW), etc.) can be used to evaluate the degree of matching. Optionally, other route attributes, such as road type (highway, city road, etc.), traffic flow, speed limits, etc., can also be considered during the search for matching routes to ensure the most suitable match is found.

[0115] Step S107: Load the target map and provide it to the vehicle for display, and provide support for the subsequent positioning and planning module.

[0116] For example, after loading the target map, it is displayed on the screen and provides support for the subsequent positioning and planning module. This planning module can be another module or device connected to the vehicle's infotainment system controller.

[0117] In this embodiment, map elements are associated with trajectory mileage information, using mileage data to solve the loop matching problem. Furthermore, map elements within a specific range can be quickly located and extracted based on mileage information, improving search and utilization efficiency. In addition, this method also enables the search for matching target maps in the electronic map based on the user's current driving route, providing the user with accurate navigation maps in real time on the vehicle.

[0118] This embodiment also provides a lightweight memory route mapping device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0119] This embodiment provides a lightweight memory route mapping device. As shown in Figure 5, the device includes: an acquisition module 510, an optimization module 520, a fusion module 530, and a creation module 540. In addition, the device may include other more or fewer units or modules, such as a storage unit, etc., which are not limited in this embodiment.

[0120] The acquisition module 510 is used to acquire road vector information and driving trajectory information collected in real time during the user's vehicle's journey on a preset route, as well as navigation information provided by the vehicle-side navigation map application; the road vector information includes multiple road vector elements.

[0121] The optimization module 520 is used to perform graphical optimization processing on the driving trajectory information to generate high-precision trajectory information.

[0122] The fusion module 530 is used to aggregate the multiple road vector elements according to the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route, where N≥1 and N is a positive integer.

[0123] The creation module 540 is used to create a memory map of the preset route based on the N segments of lightweight road information and the navigation information.

[0124] In some alternative implementations, the vehicle trajectory information includes: trajectory recursion (DR) information and GPS information on the vehicle trajectory.

[0125] The optimization module 520 can be used to fuse the recursive DR information and GPS information, and generate the high-precision trajectory information after graph optimization processing.

[0126] In some alternative implementations, the fusion module 530 can be used to acquire at least two sampled data points recorded at different sampling times for the plurality of road vector elements; and to aggregate the at least two sampled data points using a spatial distance algorithm to generate the N segments of lightweight road information.

[0127] The spatial distance algorithm is as follows: points of continuous elements in at least two sampled data are aggregated into a segment in space, and points of non-continuous elements are represented by discrete endpoints in space.

[0128] In some alternative implementations, the navigation information consists of at least one navigation segment information.

[0129] The device provided in this embodiment also includes a splicing and repair module. The splicing and repair module is used to splice the segments corresponding to the current navigation segment in the N segments of lightweight road information before the creation module 540 creates the memory map of the preset route, to verify and repair the at least one navigation segment information, and to generate navigation information consistent with the driving trajectory.

[0130] The creation module 540 is also used to create the memory map based on the N segments of lightweight road information and the navigation information that is consistent with the driving trajectory.

[0131] In some alternative implementations, the splicing and repair module can be used to splice navigation routes and repair navigation information for each navigation segment in the at least one navigation segment information.

[0132] Among them, navigation route splicing is to splice multiple navigation routes generated during the navigation reset process into a complete navigation route; navigation information repair is to attach one or more of the following information—slope, curvature, and speed limit—to the correct position of the spliced ​​navigation route, and / or to complete the navigation information through semantic information extracted from the trajectory.

[0133] Optionally, in some other embodiments, the lightweight memory route mapping device described above further includes a loading module, a search module, and a display module.

[0134] For example, the loading module is used to load at least one nearby electronic map based on the real-time location of the user's vehicle, the at least one electronic map including the created memory map.

[0135] The search module is used to search for a target map in at least one electronic map based on the current route of the user's vehicle, the target map containing routes that match the current route of the user's vehicle.

[0136] The loading module is also used to load the target map and provide it to the vehicle for display via the display module, and to provide support for the subsequent positioning and planning module. For example, it provides positioning, route planning and other services to users or downstream devices.

[0137] Optionally, the display module is a display screen or a monitor.

[0138] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0139] The lightweight memory route mapping device in this embodiment is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0140] This application also provides a vehicle controller having the lightweight memory route mapping device shown in FIG5 above.

[0141] Please refer to Figure 6, which is a schematic diagram of the structure of a vehicle infotainment controller provided in an optional embodiment of this application. As shown in Figure 6, the vehicle infotainment controller includes: one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within a computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface).

[0142] In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple storage devices, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 uses a single processor 10 as an example.

[0143] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0144] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0145] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories can be connected to the vehicle controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0146] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0147] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 20 can be connected via a bus or other means; Figure 6 shows an example of a connection via a bus.

[0148] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0149] In addition, the vehicle controller also includes at least one communication interface for communicating with other devices or communication networks, such as connecting at least one sensor and a display screen.

[0150] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory.

[0151] It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implement the lightweight memory route mapping method shown in the above embodiments.

[0152] This application provides a computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the lightweight memory route mapping method of any embodiment of this application.

[0153] In addition, referring to Figure 7, this application embodiment also provides a vehicle, which includes a vehicle controller and a data acquisition device.

[0154] The data acquisition device is used to collect road vector information and vehicle trajectory information of the user vehicle in real time as it travels along a preset route, and reports the road vector information and the vehicle trajectory information to the vehicle controller. Furthermore, the data acquisition device includes, but is not limited to, various sensors, such as cameras, millimeter-wave radar, and other devices or apparatuses; the number of data acquisition devices can be set according to actual needs.

[0155] The vehicle controller is used to acquire road vector information and driving trajectory information reported by at least one sensor, as well as navigation information provided by a vehicle-side navigation map application; to perform image optimization processing on the driving trajectory information to generate high-precision trajectory information; to aggregate multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on a preset route; and to create a memory map of the preset route based on the N lightweight road information segments and navigation information.

[0156] In addition, the vehicle controller is also used to execute all or part of the method steps shown in Figures 2, 3 and 4 above. For details, please refer to the description of the above embodiments. This embodiment will not be repeated here.

[0157] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for creating a map based on memorized routes, characterized in that, The method includes: The system acquires real-time road vector information and driving trajectory information collected during the user's vehicle's journey along a preset route, as well as navigation information provided by the vehicle-side navigation map application; wherein the road vector information includes multiple road vector elements. The driving trajectory information is subjected to image optimization processing to generate high-precision trajectory information; Based on the high-precision trajectory information and the road vector information, the multiple road vector elements are aggregated to generate N lightweight road information segments on the preset route, where N≥1; Based on the N segments of lightweight road information and the navigation information, a memory map of the preset route is created.

2. The method according to claim 1, characterized in that, The driving trajectory information includes: trajectory recursion DR information and GPS information on the driving trajectory; The step of performing graphical optimization processing on the driving trajectory information to generate high-precision trajectory information includes: The recursive DR information and the GPS information are fused together, and after graph optimization processing, the high-precision trajectory information is generated.

3. The method according to claim 1, characterized in that, The step of aggregating the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route includes: Obtain at least two sampled data points of the plurality of road vector elements recorded at different sampling times; The at least two sampled data are aggregated using a spatial distance algorithm to generate the N segments of lightweight road information; The spatial distance algorithm is as follows: points of continuous elements in at least two sampled data are aggregated into a segment in space, and points of non-continuous elements are represented by discrete endpoints in space.

4. The method according to any one of claims 1-3, characterized in that, The navigation information consists of at least one navigation segment information; Before creating the memory map of the preset route based on the N segments of lightweight road information and the navigation information, the method further includes: The segments corresponding to the current navigation segment in the N segments of lightweight road information are spliced ​​together, and the at least one navigation segment information is verified and repaired to generate navigation information consistent with the driving trajectory. The step of creating a memory map of the preset route based on the N segments of lightweight road information and the navigation information includes: The memory map is created based on the N segments of lightweight road information and the navigation information that matches the driving trajectory.

5. The method according to claim 4, characterized in that, The step of splicing together the segments corresponding to the current navigation segment from the N segments of lightweight road information, and verifying and repairing the at least one navigation segment information, includes: Perform navigation route splicing and navigation information repair on each of the at least one navigation segment information; The navigation route splicing involves combining multiple navigation routes generated during the navigation reset process into a complete navigation route; the navigation information repair involves attaching one or more of the following information—slope, curvature, and speed limit—to the correct position of the spliced ​​navigation route, and / or supplementing the navigation information using semantic information extracted from the trajectory.

6. The method according to claim 1, characterized in that, After creating the memory map of the preset route, the following is also included: Based on the real-time location of the user's vehicle, at least one nearby electronic map is loaded, and the at least one electronic map includes the created memory map; Based on the current route of the user vehicle, a target map is searched in at least one electronic map, and the target map contains a route that matches the current route of the user vehicle. The target map is loaded and provided to the vehicle for display, and also provides support for the positioning and planning module.

7. A memory route mapping device, characterized in that, The device includes: The acquisition module is used to acquire real-time road vector information and driving trajectory information collected by the user's vehicle while it is driving on a preset route, as well as navigation information provided by the vehicle-side navigation map application; wherein the road vector information includes multiple road vector elements. The optimization module is used to perform graphical optimization processing on the driving trajectory information to generate high-precision trajectory information; The fusion module is used to aggregate the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route, where N≥1; A creation module is used to create a memory map of the preset route based on the N segments of lightweight road information and the navigation information.

8. The apparatus according to claim 7, characterized in that: The driving trajectory information includes: trajectory recursion DR information and GPS information on the driving trajectory; The optimization module fuses the trajectory recursive DR information and the GPS information, and after graph optimization processing, generates the high-precision trajectory information.

9. The apparatus according to claim 7, characterized in that: The fusion module acquires at least two sampled data points recorded at different sampling times for the multiple road vector elements; it then aggregates the at least two sampled data points using a spatial distance algorithm to generate the N segments of lightweight road information.

10. The apparatus according to any one of claims 7 to 9, characterized in that, The device further includes: The stitching and repair module is used to stitch together the segments corresponding to the current navigation segment in the N segments of lightweight road information before the creation module creates the memory map of the preset route, to verify and repair the at least one navigation segment information, and to generate navigation information consistent with the driving trajectory.

11. The apparatus according to any one of claims 7 to 9, characterized in that, The device further includes: A loading module is used to load at least one nearby electronic map based on the real-time location of the user's vehicle, wherein the at least one electronic map includes the created memory map; The search module is used to search for a target map in at least one electronic map based on the current route of the user's vehicle, the target map containing routes that match the current route of the user's vehicle.

12. A vehicle infotainment controller, characterized in that, It includes a memory and a processor, wherein the memory and the processor are connected. The memory stores computer instructions, and the processor executes the computer instructions to perform the lightweight memory route mapping method according to any one of claims 1 to 6.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

14. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

15. A vehicle, characterized in that, Including vehicle-mounted controllers and data acquisition equipment, among which, The data acquisition device is used to collect road vector information and driving trajectory information of the user vehicle in real time during the driving process of the user vehicle on the preset route, and to report the road vector information and driving trajectory information to the vehicle controller. The vehicle controller is used to acquire the road vector information and driving trajectory information reported by the acquisition device, as well as the navigation information provided by the vehicle-side navigation map application; to perform image optimization processing on the driving trajectory information to generate high-precision trajectory information; to aggregate the multiple road vector elements based on the high-precision trajectory information and the road vector information to generate N lightweight road information segments on the preset route, where N≥1; and to create a memory map of the preset route based on the N lightweight road information segments and the navigation information.

Images