A method and apparatus for checking a highway adas map
By using greedy algorithms and simulated annealing algorithms to generate optimized high-speed paths, the problems of high workload and low efficiency in ADAS map inspection methods are solved, achieving more efficient and accurate ADAS map generation and inspection, and improving the performance of autonomous driving systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHERY AUTOMOBILE CO LTD
- Filing Date
- 2025-01-02
- Publication Date
- 2026-08-04
AI Technical Summary
Existing ADAS map inspection methods are labor-intensive, inefficient, and costly, and cannot effectively handle the diversity and path duplication issues of national map data.
The algorithm employs a greedy algorithm and a simulated annealing algorithm to generate optimized high-speed paths. By generating a minimum spanning tree and iteratively optimizing the navigation path, combined with an automated inspection method, the algorithm reduces path duplication and generates more accurate ADAS maps.
It improves the efficiency of ADAS map inspection, reduces workload and cost, generates more accurate ADAS maps, reduces data duplication, and enhances the safety and reliability of autonomous driving systems.
Smart Images
Figure CN119915301B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving technology, and in particular to a method and device for inspecting highway ADAS maps. Background Technology
[0002] ADAS (Advanced Driver Assistance Systems) maps are map data specifically designed for advanced driver assistance systems. ADAS maps fall between in-vehicle maps and high-precision maps, with an accuracy typically ranging from 1 to 5 meters. They primarily provide the environmental information needed for vehicle perception and driving decisions, thereby improving driving safety and experience. ADAS maps not only include traditional road location information but also add data on the road itself, such as slope, curvature, and heading angle, as well as road-related data such as detailed information on highway exits, road-related points of interest, speed limits, and traffic signs.
[0003] Currently, in the field of autonomous driving, the data quality of ADAS maps is closely related to the driver assistance functions.
[0004] Due to the large volume of national map data and the diverse map attributes, duplicate paths are easily encountered when planning routes. Since ADAS maps are related to the location points in the path in real time, traditional ADAS map inspection methods are labor-intensive, complex, inefficient, and costly. Summary of the Invention
[0005] In view of this, this application provides a method for inspecting highway ADAS maps, which can reduce the workload of automating the inspection of ADAS maps. The method includes:
[0006] Obtain national highway network data.
[0007] Based on national highway network data, an optimized highway path is generated using a greedy algorithm and a simulated annealing algorithm. The optimized highway path includes multiple navigation paths, each corresponding to the optimal solution obtained iteratively by the simulated annealing algorithm. The union of these multiple navigation paths covers all highways in the national highway network data.
[0008] ADAS maps are generated based on optimized high-speed paths.
[0009] Static map is obtained by staticizing the ADAS map.
[0010] Perform automated checks on static maps.
[0011] Alternatively, based on national highway network data, optimized highway paths can be generated using greedy algorithms and simulated annealing algorithms, including:
[0012] Transform the national expressway network data into a graph structure.
[0013] Generate the minimum spanning tree of the graph structure.
[0014] A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data.
[0015] The simulated annealing algorithm is used to iterate over the covered data to obtain the optimal solution, and the multiple navigation paths corresponding to the optimal solution are used as optimized high-speed paths.
[0016] Optionally, generating ADAS maps based on optimized high-speed paths includes:
[0017] Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized highway route.
[0018] Optionally, the ADAS map can be staticized to obtain a static map, including:
[0019] The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
[0020] Optional automated checks on static maps include:
[0021] Perform at least one of the following checks on static maps: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
[0022] This application also provides a highway ADAS map inspection device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. The feature is that when the computer program is executed by the processor, it implements an automated highway ADAS map inspection method, the method comprising:
[0023] Obtain national highway network data.
[0024] Based on national highway network data, an optimized highway path is generated using a greedy algorithm and a simulated annealing algorithm. The optimized highway path includes multiple navigation paths, each corresponding to the optimal solution obtained iteratively by the simulated annealing algorithm. The union of these multiple navigation paths covers all highways in the national highway network data.
[0025] ADAS maps are generated based on optimized high-speed paths.
[0026] Static map is obtained by staticizing the ADAS map.
[0027] Perform automated checks on static maps.
[0028] Alternatively, based on national highway network data, optimized highway paths can be generated using greedy algorithms and simulated annealing algorithms, including:
[0029] Transform the national expressway network data into a graph structure.
[0030] Generate the minimum spanning tree of the graph structure.
[0031] A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data.
[0032] The simulated annealing algorithm is used to iterate over the covered data to obtain the optimal solution, and the multiple navigation paths corresponding to the optimal solution are used as optimized high-speed paths.
[0033] Optionally, generating ADAS maps based on optimized high-speed paths includes:
[0034] Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized high-speed route.
[0035] Optionally, the ADAS map can be staticized to obtain a static map, including:
[0036] The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
[0037] Optional automated checks on static maps include:
[0038] Perform at least one of the following checks on static maps: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
[0039] The method for inspecting highway ADAS maps provided in this application uses simulated annealing algorithm to iterate based on national highway network data to determine the optimal solution and generate multiple navigation routes that are more accurate and cover all highways in the country with minimal path duplication. Based on this, the ADAS map generated based on the navigation routes is also more accurate and avoids map data duplication. This reduces workload, improves inspection efficiency, and lowers inspection costs in the final automated inspection of ADAS maps. Attached Figure Description
[0040] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0041] Figure 1A flowchart illustrating the method for checking highway ADAS maps provided in this application embodiment;
[0042] Figure 2 Another flowchart of the method for checking highway ADAS maps provided in the embodiments of this application;
[0043] Figure 3 This is an architecture diagram of a highway ADAS map inspection device provided in an embodiment of this application. Detailed Implementation
[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0045] Currently, in the field of autonomous driving, the quality of ADAS map data is closely related to assisted driving functions. In the industry today, traditional map data inspection methods mainly rely on manual verification by operators. Due to the large volume of national map data and its diverse attributes, this method is labor-intensive, complex, inefficient in updating, and costly in terms of labor. Furthermore, ADAS map data is dynamically transmitted based on the current location, and its inspection differs from that of traditional static maps. Therefore, there is an urgent need to establish an efficient and reliable automated inspection method for ADAS map data to ensure its quality and reduce the workload of automated inspection.
[0046] This application provides a method for checking highway ADAS maps, such as... Figure 1 As shown, the method includes steps S101, S102, S103, S104, and S105:
[0047] In step S101, data on the national expressway network is obtained.
[0048] In step S102, based on the national highway network data, an optimized highway path is generated using a greedy algorithm and a simulated annealing algorithm.
[0049] The optimized high-speed path includes multiple navigation paths, each corresponding to the optimal solution obtained iteratively using the simulated annealing algorithm. The union of these multiple navigation paths covers all expressways in the national expressway network data.
[0050] In step S103, an ADAS map is generated based on the optimized high-speed path.
[0051] In step S104, the ADAS map is staticized to obtain a static map.
[0052] In step S105, the static map is automatically checked.
[0053] In some optional embodiments, generating optimized highway paths based on national highway network data using greedy algorithms and simulated annealing algorithms includes:
[0054] Transform the national expressway network data into a graph structure.
[0055] Generate the minimum spanning tree of the graph structure.
[0056] A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data.
[0057] The simulated annealing algorithm is used to iterate over the covered data to obtain the optimal solution, and the multiple navigation paths corresponding to the optimal solution are used as optimized high-speed paths.
[0058] In some optional embodiments, generating an ADAS map based on an optimized high-speed path includes:
[0059] Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized highway route.
[0060] In some optional embodiments, the ADAS map is staticized to obtain a static map, including:
[0061] The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
[0062] In some optional embodiments, automated inspection of static maps includes:
[0063] Perform at least one of the following checks on static maps: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
[0064] The method for inspecting highway ADAS maps provided in this application uses simulated annealing algorithm to iterate based on national highway network data. The optimal solution obtained from the iteration is used as the navigation path to generate multiple navigation paths that are more accurate and cover all highways in the country with minimal path repetition. Based on this, the ADAS map generated based on the navigation path is also more accurate and avoids map data duplication. This reduces workload, improves inspection efficiency, and lowers inspection costs in the final automated inspection of ADAS maps.
[0065] This application also provides a method for checking highway ADAS maps, such as... Figure 2As shown, the method includes steps S201, S202, S203, S204, S205, S206, S207, and S208:
[0066] In step S201, data on the national expressway network is obtained.
[0067] It is understandable that the national highway network data can be pre-stored or retrieved from servers.
[0068] In step S202, the national expressway network data is converted into a graph structure.
[0069] Understandably, the national highway network is first represented by a graph structure, with nodes representing highway intersections (such as exits, entrances, toll stations, etc., and entrances and exits can be found by the connection between ramps and highways), edges representing highway segments, and distance representing the weight of the edges.
[0070] In step S203, a minimum spanning tree of the graph structure is generated based on the graph structure.
[0071] Understandably, after representing the national highway network using a graph structure, the minimum spanning tree of that graph structure is generated. The minimum spanning tree is the tree that covers all nodes in the graph structure and has the minimum total weight of its edges. This yields a planning path that covers all entrances and exits using the shortest distance. This path can serve as the basic route for traversing the national highway network because it inherently has no repeated road segments.
[0072] In step S204, a greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data.
[0073] Understandably, after generating the minimum spanning tree of the national highway network graph structure, some road segments may not be covered because the minimum spanning tree has no repeated edges. To cover all highway segments, a greedy algorithm can be used to supplement the coverage. Specifically, starting from any node in the graph, among all the uncovered road segments of the current node, select the shortest road segment, add this road segment to the path, and mark it as covered. Repeat the above process until all road segments are covered, and finally process the remaining isolated road segments individually. This can temporarily obtain a locally optimal solution that covers all edges.
[0074] In step S205, the simulated annealing algorithm is used to iterate the coverage data to obtain the optimal solution, and the multiple navigation paths corresponding to the optimal solution are used as optimized high-speed paths.
[0075] The optimized high-speed path includes multiple navigation paths, each corresponding to the optimal solution obtained iteratively using the simulated annealing algorithm. The union of these multiple navigation paths covers all expressways in the national expressway network data.
[0076] Understandably, the simulated annealing algorithm was ultimately chosen to further optimize the path. It is an algorithm for global problem optimization, aiming to find the globally optimal solution (i.e., the optimal solution in step S205) starting from an initial solution. Its core is the "temperature" parameter T, which gradually decreases over time. When the temperature is high, the algorithm can accept worse solutions, increasing the randomness and diversity of the search; as the temperature gradually decreases, the algorithm tends to choose better solutions. The acceptance probability formula is shown in formula (1):
[0077]
[0078] Where P is the probability, e represents the base of the natural logarithm (i.e., the natural constant), ΔE is the difference in the objective function between the current solution and the new solution, and T is the temperature. During the search process, the algorithm starts from an initial point and then adjusts according to the temperature, randomly selecting a neighborhood solution. If the solution is better than the current solution, it is accepted directly; if it is worse, the decision to accept it is based on probability P. As the temperature gradually decreases, the algorithm's exploration pace gradually slows down, eventually performing a refined search in a local region and gradually converging to the global optimum.
[0079] Specifically, the algorithm first sets an initial temperature T0 and a cooling coefficient c (0.8-0.99). After obtaining an initial path using a greedy algorithm, it continuously attempts to locally optimize the current solution (e.g., node swapping, reversing parts of the path, reconnecting paths, etc.). The objective function is the sum of the weights E of the solution. Based on the calculated probability value P, it determines whether to accept a new solution. If accepted, the path is updated. Regardless of acceptance, the temperature T is multiplied by the cooling coefficient c after each iteration. The search stops when the convergence condition is met (the temperature drops to a certain threshold or the maximum number of iterations is reached).
[0080] This allows for the automatic generation of a near-global optimal set of routes, which can be used as optimized highway routes to effectively cover highways nationwide and minimize repeated route travel.
[0081] More specifically, the solution obtained by the greedy algorithm is the input of the simulated annealing algorithm, specifically obtained through DFS (Depth-First Search). The solution obtained by the greedy algorithm is an array containing different paths, and each array is a set of edges. The edges of the directed graph generated by the greedy algorithm have weights, and the weight value is the length of the corresponding edge. By calculation, the weight sum of an initial solution can be obtained. Then, a feedback function is added to the total length of the generated path and the number of special points (road merge, split point). That is, the closer the length is to the median and the closer the number of special points is to 2, the closer the path is to the desired path. The neighborhood solution is a new solution after local optimization, which is also a path. According to the probability P calculated by formula (1), if the probability P of the old solution obtained by the greedy algorithm is greater than a specified threshold, the old solution is used as the new solution; otherwise, the old solution is not used as the new solution.
[0082] In step S206, an ADAS map is generated based on the optimized high-speed path.
[0083] In some optional embodiments, generating an ADAS map based on an optimized high-speed path includes:
[0084] Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized highway route.
[0085] In step S207, the ADAS map is staticized to obtain a static map.
[0086] In some optional embodiments, the ADAS map is staticized to obtain a static map, including:
[0087] The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
[0088] Understandably, an ADAS map can be converted into a traditional static map by using a pre-stored ADAS map data visualization method based on QGIS design.
[0089] A method for visualizing ADAS map data based on QGIS design specifically includes:
[0090] 1. Record the GPS coordinates of the vehicle's driving trajectory and ADAS map data.
[0091] 2. Segment the GPS data, aggregate the GPS points in the same segment to form the coordinate points of that segment, use these coordinate points as line geometry in geojson, and use the map information in the segment as properties in geojson, and generate the corresponding segment.geojson file.
[0092] 3. The stub is point data. The GPS point at the segmentation point of each segment is the location point of the stub. The coordinate point is used as the point geometry in geojson, and the map information in the stub is used as the properties in geojson, generating the corresponding stub.geojson file.
[0093] 4. The short profile is point data. Based on the offset in the ADAS map, the nearest GPS point in the corresponding segment is found and used as the location of the data. That is, the coordinate point is used as the point geometry in geojson, and the map information in the short profile is used as the properties in geojson, thus generating the short.geojson file.
[0094] 5. The long profile process is similar to the short profile process, generating the corresponding long.geojson file.
[0095] 6. QGIS loads the processed geojson file and satellite imagery to visualize the ADAS map data, which is essentially converting the ADAS map into a traditional static map.
[0096] In step S208, the static map is automatically checked.
[0097] In some optional embodiments, automated inspection of static maps includes:
[0098] Perform at least one of the following checks on static maps: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
[0099] Understandably, to ensure the integrity and accuracy of the generated map data, some quantitative indicators and check items can be defined to perform an automated check on the data in advance, and then manual verification can be performed on the abnormal indicators. This can greatly reduce the amount of manual verification and thus improve efficiency.
[0100] Automated checks include, but are not limited to, the following aspects:
[0101] I. Data integrity checks, including:
[0102] Missing data detection: Use graph algorithms to traverse the map network to check for isolated nodes or unconnected road segments, and verify whether there is missing key data in the map, such as roads, intersections, traffic signs, extended lanes, etc.
[0103] Redundant data detection: Check for duplicate road segments, nodes, or other redundant data.
[0104] II. Geographic consistency check, including:
[0105] Topological consistency: Ensure the map data has the correct topological structure. For example, check whether all road segments are correctly connected, and whether the angles, distribution, and locations of intersections are reasonable.
[0106] Geometric consistency: Verifying the accuracy of geometry, such as checking whether the geometry of roads and lanes meets expectations through geometric analysis algorithms (such as Bézier curves), or restoring geometry through lane curvature, etc.
[0107] III. Attribute accuracy check, including:
[0108] Rule-based range checks: These checks verify the reasonableness of map data attributes based on a predefined set of rules (such as speed limit ranges, road segment types, etc.). For example, they verify the accuracy of road types (highways, urban roads, etc.), speed limit information, and road directions (one-way streets, two-way streets).
[0109] Based on truth value comparison: If there is truth data from other map sources, attributes at the same location can be compared to determine whether the current map data attributes are correct. For example, verifying traffic signs (location, type), special roads (location, type, number of lanes, lane number), etc.
[0110] IV. Version difference check, including comparing map data for the same path in different versions to ensure that the differences are due to version changes rather than data changes.
[0111] V. Simulation and Scene Coverage Check: This includes testing the performance of the autonomous driving system under various map scenarios through simulation, such as different road types, weather conditions, and traffic densities. By outputting the coverage and accuracy of map data in different scenarios, the robustness and reliability of the map data are verified.
[0112] The method for inspecting highway ADAS maps provided in this application uses simulated annealing algorithm to iterate based on national highway network data. The optimal solution obtained from the iteration is used as the navigation path to generate multiple navigation paths that are more accurate and cover all highways in the country with minimal path repetition. Based on this, the ADAS map generated based on the navigation path is also more accurate and avoids map data duplication. This reduces workload, improves inspection efficiency, and lowers inspection costs in the final automated inspection of ADAS maps.
[0113] like Figure 3 As shown, this application embodiment also provides a highway ADAS map inspection device 30, including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the computer program is executed by the processor 301, it implements a highway ADAS map inspection method, the method including:
[0114] Obtain national highway network data.
[0115] Based on national highway network data, an optimized highway path is generated using a greedy algorithm and a simulated annealing algorithm.
[0116] The optimized high-speed path includes multiple navigation paths, each corresponding to the optimal solution obtained iteratively using the simulated annealing algorithm. The union of these multiple navigation paths covers all expressways in the national expressway network data.
[0117] ADAS maps are generated based on optimized high-speed paths.
[0118] Static map is obtained by staticizing the ADAS map.
[0119] Perform automated checks on static maps.
[0120] In some optional embodiments, generating optimized highway paths based on national highway network data using greedy algorithms and simulated annealing algorithms includes:
[0121] Transform the national expressway network data into a graph structure.
[0122] Generate the minimum spanning tree of the graph structure.
[0123] A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data.
[0124] The simulated annealing algorithm is used to iterate over the covered data to obtain the optimal solution, and the multiple navigation paths corresponding to the optimal solution are used as optimized high-speed paths.
[0125] In some optional embodiments, generating an ADAS map based on an optimized high-speed path includes:
[0126] Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized highway route.
[0127] In some optional embodiments, the ADAS map is staticized to obtain a static map, including:
[0128] The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
[0129] In some optional embodiments, automated inspection of static maps includes:
[0130] Perform at least one of the following checks on static maps: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
[0131] The inspection equipment for highway ADAS maps provided in this application uses simulated annealing algorithm to iterate based on national highway network data. The optimal solution obtained by iteration is used as the navigation path to generate multiple navigation paths that are more accurate and cover all highways in the country with minimal path repetition. Based on this, the ADAS map generated based on the navigation path is also more accurate and avoids map data duplication. This reduces workload, improves inspection efficiency, and lowers inspection costs in the final automated inspection of ADAS maps.
[0132] This application also provides a computer-readable storage medium, such as a memory including program code, which can be executed by the processor of a highway ADAS map checking device to complete the highway ADAS map checking method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.
[0133] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program or program code related to hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.
[0134] In this application, it should be understood that the terms “first”, “second”, etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated.
[0135] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only.
[0136] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.
[0137] The above description is only for the purpose of enabling those skilled in the art to understand the technical solution of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A method of inspection of a highway ADAS map, characterized in that, The method includes: Obtain national expressway network data; The national expressway network data is transformed into a graph structure, where nodes represent expressway intersections, edges represent expressway segments, and the weight of an edge is represented by the distance between the segments. Based on the national expressway network data, an optimized expressway path is generated using a greedy algorithm and a simulated annealing algorithm. The optimized expressway path includes multiple navigation paths, which correspond to the optimal solution obtained iteratively according to the simulated annealing algorithm. The union of the multiple navigation paths covers all expressways in the national expressway network data. ADAS map is generated based on the optimized high-speed path; The ADAS map is staticized to obtain a static map; Perform automated checks on the static map. The method of generating optimized high-speed paths using greedy algorithms and simulated annealing algorithms includes: Generate the minimum spanning tree of the graph structure; A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data; Using the coverage data as input to the simulated annealing algorithm, a neighborhood solution is generated by performing node swapping, path segment reversal, or path reconnection operations. The algorithm then performs iterative optimization with the goal of minimizing the total path length and reducing path duplication to obtain the optimal solution.
2. The method of checking a high-speed road ADAS map according to claim 1, characterized in that, The process of generating an ADAS map based on the optimized high-speed path includes: Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized high-speed path.
3. The method of inspection of a high-speed road ADAS map according to claim 1, characterized in that, The process of staticizing the ADAS map to obtain a static map includes: The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
4. The method of inspection of a high-speed road ADAS map according to claim 1, characterized in that, The automated inspection of the static map includes: Perform at least one of the following checks on the static map: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.
5. An inspection device for a highway ADAS map, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it implements a method for checking a highway ADAS map, the method comprising: Obtain national expressway network data; The national expressway network data is transformed into a graph structure, where nodes represent expressway intersections, edges represent expressway segments, and the weight of an edge is represented by the distance between the segments. Based on the national expressway network data, an optimized expressway path is generated using a greedy algorithm and a simulated annealing algorithm. The optimized expressway path includes multiple navigation paths, which correspond to the optimal solution obtained iteratively according to the simulated annealing algorithm. The union of the multiple navigation paths covers all expressways in the national expressway network data. ADAS map is generated based on the optimized high-speed path; The ADAS map is staticized to obtain a static map; Perform automated checks on the static map. The method of generating optimized high-speed paths using greedy algorithms and simulated annealing algorithms includes: Generate the minimum spanning tree of the graph structure; A greedy algorithm is used to supplement and cover the minimum spanning tree to obtain the covered data; Using the coverage data as input to the simulated annealing algorithm, a neighborhood solution is generated by performing node swapping, path segment reversal, or path reconnection operations. The algorithm then performs iterative optimization with the goal of minimizing the total path length and reducing path duplication to obtain the optimal solution.
6. The high-speed road ADAS map checking device according to claim 5, characterized in that, The process of generating an ADAS map based on the optimized high-speed path includes: Generate a corresponding ADAS map based on at least one GPS point corresponding to the optimized high-speed path.
7. The high-speed road ADAS map checking device according to claim 5, characterized in that, The process of staticizing the ADAS map to obtain a static map includes: The ADAS map is statically generated by using a pre-stored ADAS map data visualization algorithm.
8. The high-speed road ADAS map checking device according to claim 5, characterized in that, The automated inspection of the static map includes: Perform at least one of the following checks on the static map: data integrity check, geographic consistency check, attribute accuracy check, version difference check, and simulation and scene coverage check.