Navigation map generation method, device, equipment and storage medium

Abstract

The application relates to the field of automatic driving vehicle positioning, and discloses a navigation map generation method, device and equipment and a storage medium. The method comprises the following steps: acquiring a first global map of a target area, extracting a first key element of a static road lane line from the first global map, and constructing a road network graph; acquiring a second global map of the target area, extracting a second key element of a dynamically changed road from the second global map, and determining position information of the second key element; when a navigation request is received, updating the road network graph according to the position information to obtain an updated road network graph; and according to the navigation request, performing optimal path planning on the updated road network graph to generate a corresponding navigation map. The application improves the loading efficiency of a navigation semantic map in the automatic driving process of a vehicle.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle positioning, and more particularly to a method, apparatus, device, and storage medium for generating navigation maps. Background Technology

[0002] With the development of autonomous vehicle positioning technology, related technologies have also advanced rapidly. Autonomous driving is gradually being applied in daily vehicle driving and commercial operations, such as driverless cars used in daily traffic and the taxi industry. As the area covered by autonomous driving expands, the coverage area of ​​driving navigation maps is also gradually increasing. Because map information includes data on roads, lanes, intersections, signs, traffic lights, etc., the amount of map file information required for autonomous driving is becoming increasingly larger.

[0003] Currently, autonomous vehicles load semantic maps using a full-load mode, loading all necessary data into the running memory at once to enable route planning and navigation. However, this full-load mode requires loading all semantic maps for autonomous driving into memory, which can lead to insufficient vehicle memory. Furthermore, the massive amount of map data results in slow data loading speeds and significant startup time. In short, the loading efficiency of navigation semantic maps during current autonomous driving processes is relatively low. Summary of the Invention

[0004] The main objective of this invention is to solve the problem of low loading efficiency of navigation semantic maps during the autonomous driving process of existing vehicles.

[0005] The first aspect of this invention provides a method for generating a navigation map, the method comprising: acquiring a first global map of a target area, and extracting a first key element of static road lane lines from the first global map to construct a road network map; acquiring a second global map of the target area, and extracting a second key element of dynamically changing roads from the second global map, and determining the location information of the second key element; when a navigation request is received, updating the road network map according to the location information to obtain an updated road network map; and performing optimal path planning on the updated road network map according to the navigation request to generate a corresponding navigation map.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of extracting the first key element of static road lane lines from the first global map to construct a road network map includes: identifying each intersection in the first global map and the lane lines connected to each intersection; using the lane lines connected to each intersection to determine the intersection center point of the corresponding intersection, and using the lane lines to connect the corresponding intersection center points to obtain multiple first key elements; and dividing and combining each first key element into blocks according to a preset size to obtain the final road network map.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of extracting the second key element of dynamically changed roads from the second global map and determining the location information of the second key element includes: identifying road change information of the second global map relative to the first global map according to a preset period; extracting the road change area in the road change information as the second key element; and extracting the location information of the second key element in the road change information.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the step of identifying road change information of the second global map relative to the first global map according to a preset period includes: identifying road construction areas in the first global map and road construction areas in the second global map according to a preset period; comparing the road construction areas in the first global map and the road construction areas in the second global map, and generating road change information based on the comparison result.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, updating the road network map according to the location information to obtain an updated road network map includes: matching the block area where the second key element is located in the road network map according to the location information; detecting whether the first key element and the second key element in the block area overlap; if they overlap, adjusting the traffic status of the corresponding first key element based on the traffic status of the overlapping second key element; and generating an updated road network map based on the adjusted traffic status of the first key element.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of performing optimal path planning on the updated road network map according to the navigation request and generating a corresponding navigation map includes: determining multiple navigation start points and multiple navigation end points on the updated road network map according to the navigation request; searching for each navigation planning path between each navigation start point and each navigation end point on the updated road network map and calculating the path cost of each navigation planning path; selecting the navigation planning path with the minimum path cost from the navigation planning paths and using it as the optimal navigation path; and generating a corresponding navigation map based on the optimal navigation path.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, determining multiple navigation starting points and multiple navigation ending points on the updated road network map according to the navigation request includes: extracting the navigation request and determining the corresponding initial navigation starting point and initial navigation ending point; matching multiple intersection center points directly connected to the initial navigation starting point on the updated road network map and using them as the corresponding navigation starting points; and matching multiple intersection center points directly connected to the initial navigation ending point on the updated road network map and using them as the corresponding navigation ending points.

[0012] A second aspect of the present invention provides a navigation map generation apparatus, comprising: a network construction module, configured to acquire a first global map of a target area and extract a first key element of static road lane lines from the first global map to construct a road network map; a location determination module, configured to acquire a second global map of the target area and extract a second key element of dynamically changing roads from the second global map, and determine the location information of the second key element; a network update module, configured to update the road network map according to the location information when a navigation request is received, to obtain an updated road network map; and a path planning module, configured to perform optimal path planning on the updated road network map according to the navigation request, to generate a corresponding navigation map.

[0013] Optionally, in a first implementation of the second aspect of the present invention, the network construction module includes: a map recognition unit, used to recognize each intersection in the first global map and the lane lines connected to each intersection; an element construction unit, used to determine the intersection center point of the corresponding intersection using the lane lines connected to each intersection, and to connect the corresponding intersection center points using the lane lines to obtain multiple first key elements; and a block combination unit, used to divide and combine each of the first key elements into blocks according to a preset size to obtain the final road network map.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the location determination module includes: a change identification unit, configured to identify road change information of the second global map relative to the first global map according to a preset period; and a location extraction unit, configured to extract the road change area in the road change information as a second key element, and extract the location information of the second key element in the road change information.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the change identification unit includes: identifying road construction areas in the first global map and road construction areas in the second global map according to a preset period; comparing the road construction areas in the first global map and the road construction areas in the second global map, and generating road change information based on the comparison result.

[0016] Optionally, in a fourth implementation of the second aspect of the present invention, the network update module includes: a block matching unit, configured to match the block area where the second key element is located in the road network map according to the location information; an overlap detection unit, configured to detect whether the first key element and the second key element overlap in the block area; a state adjustment unit, configured to adjust the passage state of the corresponding first key element based on the passage state of the overlapping second key element if there is an overlap; and a network update unit, configured to generate an updated road network map based on the adjusted passage state of the first key element.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the path planning module includes: a navigation determination unit, configured to determine multiple navigation starting points and multiple navigation ending points on an updated road network map according to the navigation request; a consumption calculation unit, configured to search for each navigation planning path between each navigation starting point and each navigation ending point on the updated road network map, and calculate the path consumption of each navigation planning path; and a route selection unit, configured to select the navigation planning path with the minimum path consumption from the navigation planning paths and use it as the optimal navigation path, and generate a corresponding navigation map based on the optimal navigation path.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the navigation determination unit includes: extracting the navigation request, determining the corresponding initial navigation start point and initial navigation end point; matching multiple intersection center points directly connected to the initial navigation start point on the updated road network map, and using them as the corresponding navigation start point; and matching multiple intersection center points directly connected to the initial navigation end point on the updated road network map, and using them as the corresponding navigation end point.

[0019] A third aspect of the present invention provides a navigation map generation device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the navigation map generation device to perform the various steps of the navigation map generation method described above.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the steps of the above-described method for generating a navigation map.

[0021] The technical solution provided by this invention involves acquiring a first global map of the target area and extracting a first key element of static road lane lines from the first global map to construct a road network map; acquiring a second global map of the target area and extracting a second key element of dynamically changing roads from the second global map, and determining the location information of the second key element; when a navigation request is received, updating the road network map according to the location information to obtain an updated road network map; and performing optimal path planning on the updated road network map according to the navigation request to generate a corresponding navigation map. Compared with the prior art, this application extracts the first key element of static roads from the acquired first global map to construct a road network map, then extracts the location information of the corresponding dynamic second key elements of roads from the acquired second global map, and then uses the second key elements to update the road network map for road connections. Based on the navigation request, the optimal route with the lowest consumption (i.e., the optimal road) is planned from the updated road network, and a corresponding navigation map is generated based on the road network map. This results in a final navigation map with less data loading, thereby improving the loading efficiency of navigation semantic maps during autonomous driving. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the first embodiment of the navigation map generation method in this invention;

[0023] Figure 2 This is a schematic diagram of a second embodiment of the navigation map generation method in this invention;

[0024] Figure 3 This is a schematic diagram of a third embodiment of the navigation map generation method in this invention;

[0025] Figure 4 This is a schematic diagram of one embodiment of the navigation map generation device in this invention;

[0026] Figure 5This is a schematic diagram of another embodiment of the navigation map generation device in this invention;

[0027] Figure 6 This is a schematic diagram of one embodiment of the navigation map generation device in this invention. Detailed Implementation

[0028] This invention provides a method, apparatus, device, and storage medium for generating navigation maps. The method includes: acquiring a first global map of a target area and extracting a first key element of static road lane lines from the first global map to construct a road network map; acquiring a second global map of the target area and extracting a second key element of dynamically changing roads from the second global map, and determining the location information of the second key element; when a navigation request is received, updating the road network map according to the location information to obtain an updated road network map; and performing optimal path planning on the updated road network map according to the navigation request to generate a corresponding navigation map. This application improves the loading efficiency of navigation semantic maps during autonomous driving.

[0029] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” or “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the navigation map generation method in this invention includes:

[0031] 101. Obtain the first global map of the target area, and extract the first key element of the static road lane lines from the first global map to construct a road network map;

[0032] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0033] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0034] In this embodiment, the first global map refers to the regional traffic map of the area where the autonomous vehicle is located (the regional map can be a national map, a provincial map, a prefecture-level city map, etc.). The regional traffic map can be a standard route map of the initial traffic planning, or a regional road route map updated at the current or a certain historical stage (such as a map generated after the previous map processing stage). The first key element of the static road lane line refers to the relevant static road driving instruction signs of the road traffic lines in the first global map as the first key element. In this application, the connecting line between the center lines of the intersection and the road is used as the first key element. In addition, road instruction lines and other road traffic lines can also be used as the first key element, which is not limited here.

[0035] In practical applications, multiple daily driving areas of the autonomous vehicle are acquired and then combined to generate a traffic driving area with the maximum driving coverage. The corresponding map is used as the first global map of the target area. Then, each intersection in the first global map and the lane lines connected to each intersection are identified. Using the lane lines connected to each intersection, the center point of the corresponding intersection is determined. The lane lines are then used to connect the corresponding center points of the intersection to obtain multiple first key elements. Finally, according to a preset size, each first key element is divided into blocks and combined to obtain the final road network map.

[0036] 102. Obtain the second global map of the target area, extract the second key element of the dynamically changing road from the second global map, and determine the location information of the second key element;

[0037] In this embodiment, the second global map refers to the latest traffic and road map of the current target area. In addition to processing road traffic information, this traffic and road map also includes construction areas such as road damage, repair, and underground pipeline maintenance, as well as corresponding road construction, traffic accident, and other temporary closure areas and other road congestion and detour information. The second key element of dynamically changing roads refers to the situation where roads are congested and cannot be driven normally, such as construction areas, temporary closure areas, or other road congestion or detour scenarios. The location information refers to the road location coordinates of the second key element in the area of ​​the second global map, that is, the location information of which road is currently an abnormal road that cannot be driven normally.

[0038] In practical applications, the latest road traffic map of the target area is obtained through a corresponding road traffic update website and used as the latest second global map of the target area. Then, according to a preset period, road change information of the second global map relative to the first global map is identified, that is, road construction areas in the first global map and road construction areas in the second global map are identified according to the preset period. Then, the road construction areas in the first global map and the road construction areas in the second global map are compared, and road change information is generated based on the comparison results. Thus, the road change areas in the road change information are extracted as the second key element, and the location information of the second key element in the road change information is also extracted.

[0039] 103. When a navigation request is received, the road network map is updated based on the location information to obtain an updated road network map;

[0040] In this embodiment, the navigation request refers to the navigation requirements information such as the start and end points given by the user to the autonomous vehicle; the update refers to loading the latest road conditions such as congestion, construction, and temporary closures into the road network map, so that the corresponding impassable routes in the road network map are removed from the road network map, and the connections between each first key element are updated.

[0041] In practical applications, based on location information, the second key element is matched to the block area in the road network map; then, it is detected whether the first and second key elements in the block area overlap; if they overlap, the traffic status of the corresponding first key element is adjusted based on the traffic status of the overlapping second key element; thus, an updated road network map is generated based on the adjusted traffic status of the first key element.

[0042] 104. Based on the navigation request, perform optimal route planning on the updated road network map and generate the corresponding navigation map.

[0043] In this embodiment, optimal route planning refers to generating navigation route information with the lowest travel consumption from the starting point to the destination on the road network map based on the navigation request, and using this route information as the optimal route planning.

[0044] In practical applications, based on the navigation request, multiple navigation start points and multiple navigation end points are determined on the updated road network map. Specifically, by extracting the navigation request, the corresponding initial navigation start point and initial navigation end point are determined. Then, multiple intersection center points directly connected to the initial navigation start points are matched on the updated road network map and used as the corresponding navigation start points. Similarly, multiple intersection center points directly connected to the initial navigation end points are matched on the updated road network map and used as the corresponding navigation end points. Next, various planned navigation paths from each navigation start point to each navigation end point are searched on the updated road network map, and the path cost of each planned navigation path is calculated. Finally, the navigation planned path with the minimum path cost is selected as the optimal navigation path, and based on the optimal navigation path, the corresponding navigation map is generated.

[0045] In this embodiment of the invention, a first global map of the target area is acquired, and a first key element of static road lane lines is extracted from the first global map to construct a road network map; a second global map of the target area is acquired, and a second key element of dynamically changing roads is extracted from the second global map, and the location information of the second key element is determined; when a navigation request is received, the road network map is updated according to the location information to obtain an updated road network map; according to the navigation request, optimal path planning is performed on the updated road network map to generate a corresponding navigation map. Compared with the prior art, this application extracts the first key element of static roads from the acquired first global map to construct a road network map, and then extracts the location information of the corresponding dynamic second key elements of roads from the acquired second global map, and then uses the second key elements to update the road network map for road connections. Therefore, according to the navigation request, the optimal route with the lowest consumption (i.e., the optimal road) is planned from the updated road network, and a corresponding navigation map is generated based on the road network map. This results in a final navigation map with less data loading, thereby improving the loading efficiency of the navigation semantic map during vehicle autonomous driving.

[0046] Please see Figure 2 A second embodiment of the navigation map generation method in this invention includes:

[0047] 201. Identify each intersection in the first global map and the lane lines connecting to each intersection;

[0048] In this embodiment, the intersection refers to the connecting intersection of various roads (such as crossroads, Y-shaped intersections, etc.), and the lane lines refer to the lane marking lines at various intersections.

[0049] In practical applications, multiple daily driving areas of the autonomous vehicle are obtained and then combined to generate a traffic driving area with the maximum driving coverage. The corresponding map is used as the first global map of the target area. Then, each intersection in the first global map is identified, and the lane line information corresponding to each intersection is determined.

[0050] 202. Using the lane lines that connect to each intersection, determine the center point of the corresponding intersection, and use the lane lines to connect the corresponding center points to obtain multiple first key elements.

[0051] In this embodiment, using the lane lines connected to each intersection, the center line points of each intersection are extracted, that is, for each road entering or exiting the intersection, a center point (represented here as an ap point) is taken; then, using the lane line information, the corresponding intersection center points are connected to obtain multiple first key elements, that is, between other ap points that each ap point can directly reach, a connection is established to obtain the corresponding first key element (represented here as aplink) aplink, where aplink contains the abstract distance information between two aps in the link, that is, the cost of a car traveling from one point to another, which can be used to select the optimal solution when planning the route. This distance can be calculated from the map between the two points.

[0052] 203. According to the preset dimensions, divide and combine each of the first key elements into blocks to obtain the final road network diagram;

[0053] In this embodiment, the preset size refers to the preset block area.

[0054] In practical applications, each first key element is divided into blocks according to a preset size to obtain the final road network map. For example, each first key element is divided into blocks according to a 1km×1km grid to obtain multiple tile maps (represented by tiles). Finally, all AP points and AP links on the tile maps are combined to form a road network map (represented by apgraphs) and the map file is stored.

[0055] 204. Identify road change information in the second global map relative to the first global map according to a preset cycle;

[0056] In this embodiment, the preset period refers to the time interval for comparing corresponding changes.

[0057] In practical applications, the latest road traffic map of the target area is obtained through the corresponding road traffic update website and used as the latest second global map of the target area. According to a preset cycle, the road change information of the second global map relative to the first global map is identified, that is, the road change segments in the road condition change information (construction area, temporary closure area, etc.) of the second global map relative to the first global map are identified. Then, the road construction areas in the first global map and the road construction areas in the second global map are compared, and the road change information is generated based on the comparison results.

[0058] 205. Extract the road change area from the road change information and use it as the second key element, and extract the location information of the second key element from the road change information;

[0059] In this embodiment, the road change areas (i.e., construction areas, temporary closure areas, etc.) in the above-mentioned road change information are extracted and used as the second key element, and the road location information of the second key element in the road change information is extracted. The corresponding second key element and its location information are packaged into separate files and stored independently, separate from the above-mentioned road network map file.

[0060] 206. When a navigation request is received, the road network map is updated based on the location information to obtain an updated road network map;

[0061] 207. Based on the navigation request, perform optimal route planning on the updated road network map and generate the corresponding navigation map.

[0062] In this embodiment of the invention, each intersection and lane line connecting to each intersection in the first global map are identified; the center point of the corresponding intersection is determined using the lane lines connecting to each intersection, and the corresponding center points are connected using the lane lines to obtain multiple first key elements; the first key elements are divided into blocks and combined according to a preset size to obtain the final road network map; road change information of the second global map relative to the first global map is identified according to a preset period; the road change area in the road change information is extracted as the second key element, and the position information of the second key element in the road change information is also extracted. Compared with the prior art, this application uses the center point connection corresponding to the lane line as the first key information to construct road network information, and then uses the obtained road change situation of the second global map relative to the first global map as the second key element, thereby realizing the construction of a road network map with less data loading and the extraction of the current corresponding road change information, so that the final planned route is more in line with the actual traffic route.

[0063] Please see Figure 3A third embodiment of the navigation map generation method in this invention includes:

[0064] 301. Obtain the first global map of the target area, and extract the first key element of the static road lane lines from the first global map to construct a road network map;

[0065] 302. Obtain the second global map of the target area, extract the second key element of the dynamically changing road from the second global map, and determine the location information of the second key element;

[0066] 303. Based on the location information, match the block area where the second key element is located in the road network map;

[0067] In this embodiment, in order to keep the apgraph consistent with the actual road conditions as much as possible, it is necessary to calculate the impact of the construction area on the apgraph when the vehicle starts. That is, the road network map needs to be updated according to the actual situation. Based on the above location information, the block area where the second key element is located in the road network map is matched. Since an aplink is the distance between two adjacent ap points, calculating an aplink only requires loading the tile related to this aplink into memory. By traversing all construction areas, the block area tiles affected by the construction area are extracted according to the corresponding location information.

[0068] 304. Detect whether the first and second key elements in the segmented region overlap;

[0069] In this embodiment, "overlap" refers to the situation where the roads are identical.

[0070] In practical applications, by detecting whether the first and second key elements in the segmented area overlap, the aplinks affected by the construction area are recalculated. That is, if an aplink's route intersects with the construction area, then the two aplinks in that aplink are considered unreachable, indicating an overlapping area.

[0071] 305. If there is an overlap, the passage status of the corresponding first key element shall be adjusted based on the passage status of the overlapping second key element.

[0072] In this embodiment, if the first key element and the second key element in the corresponding block area overlap, the passage status of the corresponding first key element is adjusted based on the passage status of the overlapping second key element (impassable or poor passage, etc.). If it is impassable, the passage status of the first key element is changed to impassable.

[0073] 306. Based on the traffic status of the adjusted first key element, generate an updated road network map;

[0074] In this embodiment, based on the traffic status of the adjusted first key element, the corresponding element connection lines in the dynamic tile map corresponding to the first key element are deleted (that is, after the calculation is completed, the tile is deleted from memory to avoid loading too many tiles and filling up the memory), and the corresponding connection relationships of the map key elements in the deleted dynamic tile map are calculated to generate an updated road network map.

[0075] 307. Based on the navigation request, determine multiple navigation start points and multiple navigation destinations on the updated road network map;

[0076] In this embodiment, when calculating the path, since the maps near the vehicle and the destination are already loaded into memory, the corresponding initial navigation start point and initial navigation end point are determined by extracting the navigation request. Then, multiple intersection center points directly connected to the initial navigation start point are matched on the updated road network map and used as the corresponding navigation start points, that is, all access points (ap points) directly reachable from the initial navigation start point (set as start) (set as start1, start2, start3) are used as the corresponding navigation start points. Then, multiple intersection center points directly connected to the initial navigation end point are matched on the updated road network map and used as the corresponding navigation start points, that is, all access points (ap points) directly reachable from the initial navigation end point (set as end1, end2, end3) are used as the corresponding navigation end points. In addition, the paths and precise distances from start point to start, start2, start3, and end1, end2, end3 to end are calculated.

[0077] 308. Search for each navigation planning path from each navigation start point to each navigation end point in the updated road network graph, and calculate the path cost of each navigation planning path.

[0078] In this embodiment, based on the multiple navigation start points and navigation endpoints found above, the updated road network map searches for each navigation planning path between each navigation start point and each navigation endpoint. That is, using the road network map and algorithms such as Astar, multiple navigation planning paths between each navigation start point and each navigation endpoint are calculated, and then the path consumption of each navigation planning path is calculated, that is, the driving distance, traffic lights, and estimated travel time of each path are calculated, and the navigation planning path with the lowest time and the lowest overall vehicle energy consumption is calculated.

[0079] 309. Select the navigation planning path with the least path consumption from all navigation planning paths and use it as the optimal navigation path. Based on the optimal navigation path, generate the corresponding navigation map.

[0080] In this embodiment, based on the results of the path consumption calculation, the navigation planning path with the minimum path consumption is selected from all navigation planning paths and taken as the optimal navigation path. Then, based on the optimal navigation path, a corresponding navigation map is generated. That is, based on the global optimal navigation path and road block map information, dynamic navigation route information corresponding to the current location is generated and dynamically displayed, or the full set of optimal navigation paths is directly loaded for route navigation.

[0081] In this embodiment of the invention, based on location information, the second key element is matched to the block area of ​​the road network map; whether the first and second key elements in the block area overlap; if they overlap, the traffic status of the corresponding first key element is adjusted based on the traffic status of the overlapping second key element; an updated road network map is generated based on the adjusted traffic status of the first key element; multiple navigation start points and multiple navigation end points are determined on the updated road network map according to the navigation request; various navigation planning paths between each navigation start point and each navigation end point are searched in the updated road network map, and the path consumption of each navigation planning path is calculated; the navigation planning path with the minimum path consumption is selected from the navigation planning paths and taken as the optimal navigation path; based on the optimal navigation path, a corresponding navigation map is generated. Compared with the prior art, this application updates the road network map using the second key element, and plans the optimal navigation path with the minimum consumption based on multiple navigation start points and navigation end points using the updated road network map to generate the corresponding navigation map. This achieves efficient global route planning with only a small amount of map information and a small amount of memory, improving the loading efficiency of navigation semantic maps during vehicle autonomous driving.

[0082] The method for generating navigation maps in the embodiments of the present invention has been described above. The apparatus for generating navigation maps in the embodiments of the present invention will be described below. Please refer to [link / reference needed]. Figure 4 One embodiment of the navigation map generation device in this invention includes:

[0083] The network construction module 401 is used to obtain the first global map of the target area and extract the first key element of the static road lane lines from the first global map to construct a road network map.

[0084] The location determination module 402 is used to acquire a second global map of the target area, extract a second key element of dynamically changing roads from the second global map, and determine the location information of the second key element.

[0085] The network update module 403 is used to update the road network map according to the location information when a navigation request is received, so as to obtain an updated road network map.

[0086] The route planning module 404 is used to perform optimal route planning on the updated road network map based on the navigation request, and generate a corresponding navigation map.

[0087] In this embodiment of the invention, a first global map of the target area is acquired, and a first key element of static road lane lines is extracted from the first global map to construct a road network map; a second global map of the target area is acquired, and a second key element of dynamically changing roads is extracted from the second global map, and the location information of the second key element is determined; when a navigation request is received, the road network map is updated according to the location information to obtain an updated road network map; according to the navigation request, optimal path planning is performed on the updated road network map to generate a corresponding navigation map. Compared with the prior art, this application extracts the first key element of static roads from the acquired first global map to construct a road network map, and then extracts the location information of the corresponding dynamic second key elements of roads from the acquired second global map, and then uses the second key elements to update the road network map for road connections. Therefore, according to the navigation request, the optimal route with the lowest consumption (i.e., the optimal road) is planned from the updated road network, and a corresponding navigation map is generated based on the road network map. This results in a final navigation map with less data loading, thereby improving the loading efficiency of navigation semantic maps during vehicle autonomous driving.

[0088] Please see Figure 5 Another embodiment of the navigation map generation device in this invention includes:

[0089] The network construction module 401 is used to obtain the first global map of the target area and extract the first key element of the static road lane lines from the first global map to construct a road network map.

[0090] The location determination module 402 is used to acquire a second global map of the target area, extract a second key element of dynamically changing roads from the second global map, and determine the location information of the second key element.

[0091] The network update module 403 is used to update the road network map according to the location information when a navigation request is received, so as to obtain an updated road network map.

[0092] The route planning module 404 is used to perform optimal route planning on the updated road network map based on the navigation request, and generate a corresponding navigation map.

[0093] Furthermore, the network construction module 401 includes:

[0094] The map recognition unit 4011 is used to recognize each intersection in the first global map and the lane lines connected to each intersection;

[0095] The element construction unit 4012 is used to determine the intersection center point of the corresponding intersection using the lane lines connected to each of the intersections, and to connect the corresponding intersection center points using the lane lines to obtain multiple first key elements.

[0096] The block combination unit 4013 is used to divide and combine each of the first key elements according to a preset size to obtain the final road network map.

[0097] Furthermore, the position determination module 402 includes:

[0098] The change recognition unit 4021 is used to recognize road change information of the second global map relative to the first global map according to a preset period.

[0099] The location extraction unit 4022 is used to extract the road change area in the road change information and use it as the second key element, and to extract the location information of the second key element in the road change information.

[0100] Furthermore, the change identification unit 4021 includes:

[0101] According to a preset cycle, road construction areas in the first global map and road construction areas in the second global map are identified; the road construction areas in the first global map and road construction areas in the second global map are compared, and road change information is generated based on the comparison results.

[0102] Furthermore, the network update module 403 includes:

[0103] Block matching unit 4031 is used to match the block area where the second key element is located in the road network map according to the location information;

[0104] The overlap detection unit 4032 is used to detect whether the first key element and the second key element in the segmented region overlap.

[0105] The state adjustment unit 4033 is used to adjust the passage state of the corresponding first key element based on the passage state of the overlapping second key element if there is overlap.

[0106] Network update unit 4034 is used to generate an updated road network map based on the traffic status of the adjusted first key element.

[0107] Furthermore, the path planning module 404 includes:

[0108] The navigation determination unit 4041 is used to determine multiple navigation starting points and multiple navigation ending points on the updated road network map according to the navigation request;

[0109] The consumption calculation unit 4042 is used to search for each navigation planning path between each navigation starting point and each navigation ending point in the updated road network graph, and to calculate the path consumption of each navigation planning path.

[0110] The route selection unit 4043 is used to select the navigation planning path with the least path consumption from each of the navigation planning paths and use it as the optimal navigation path, and generate a corresponding navigation map based on the optimal navigation path.

[0111] Furthermore, the navigation determination unit 4041 includes:

[0112] Extract the navigation request and determine the corresponding initial navigation start point and initial navigation end point; match multiple intersection center points directly connected to the initial navigation start point on the updated road network map and use them as the corresponding navigation start points; match multiple intersection center points directly connected to the initial navigation end point on the updated road network map and use them as the corresponding navigation end points.

[0113] In this embodiment of the invention, a first global map of the target area is acquired, and a first key element of static road lane lines is extracted from the first global map to construct a road network map; a second global map of the target area is acquired, and a second key element of dynamically changing roads is extracted from the second global map, and the location information of the second key element is determined; when a navigation request is received, the road network map is updated according to the location information to obtain an updated road network map; according to the navigation request, optimal path planning is performed on the updated road network map to generate a corresponding navigation map. Compared with the prior art, this application extracts the first key element of static roads from the acquired first global map to construct a road network map, and then extracts the location information of the corresponding dynamic second key elements of roads from the acquired second global map, and then uses the second key elements to update the road network map for road connections. Therefore, according to the navigation request, the optimal route with the lowest consumption (i.e., the optimal road) is planned from the updated road network, and a corresponding navigation map is generated based on the road network map. This results in a final navigation map with less data loading, thereby improving the loading efficiency of navigation semantic maps during vehicle autonomous driving.

[0114] above Figure 4 and Figure 5The navigation map generation device in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The navigation map generation device in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0115] Figure 6 This is a schematic diagram of a navigation map generation device 600 provided in an embodiment of the present invention. The navigation map generation device 600 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) for storing application programs 633 or data 632. The memory 620 and storage media 630 can be temporary or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the navigation map generation device 600. Furthermore, the processor 610 may be configured to communicate with the storage media 630 and execute the series of instruction operations in the storage media 630 on the navigation map generation device 600.

[0116] The navigation map generating device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input / output interfaces 660, and / or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 6 The illustrated structure of the navigation map generation device does not constitute a limitation on the navigation map generation device, which may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0117] The present invention also provides a navigation map generation device, wherein the computer device includes a memory and a processor, the memory storing computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor performs each step of the navigation map generation method in the above embodiments.

[0118] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform various steps of the navigation map generation method.

[0119] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0120] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0121] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0122] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a navigation map, characterized in that, The method for generating the navigation map includes: Obtain the first global map of the target area, and extract the first key element of the static road lane lines from the first global map to construct a road network map; Obtain a second global map of the target area, extract a second key element of dynamically changing roads from the second global map, and determine the location information of the second key element; wherein, the second global map refers to the latest traffic road map of the target area, which includes road congestion and detour information; When a navigation request is received, the road network map is updated based on the location information to obtain an updated road network map; Based on the navigation request, optimal route planning is performed on the updated road network map to generate a corresponding navigation map; The step of extracting the first key element of static road lane lines from the first global map and constructing a road network map includes: Identify each intersection in the first global map and the lane lines connecting each intersection; Using the lane lines connected to each of the intersections, the center point of the corresponding intersection is determined, and the lane lines are used to connect the corresponding center points to obtain multiple first key elements. According to the preset size, each of the first key elements is divided into blocks and combined to obtain the final road network map.

2. The method for generating a navigation map according to claim 1, characterized in that, The step of extracting the second key element of dynamically changing roads from the second global map and determining the location information of the second key element includes: According to a preset period, road change information of the second global map relative to the first global map is identified, wherein the preset period refers to the corresponding change comparison time interval; The road change area in the road change information is extracted and used as the second key element, and the location information of the second key element in the road change information is extracted.

3. The method for generating a navigation map according to claim 2, characterized in that, The step of identifying road change information of the second global map relative to the first global map according to a preset period includes: Based on a preset cycle, identify road construction areas in the first global map and road construction areas in the second global map; The road construction areas in the first global map and the road construction areas in the second global map are compared, and road change information is generated based on the comparison results.

4. The method for generating a navigation map according to claim 2, characterized in that, The step of updating the road network map based on the location information to obtain an updated road network map includes: Based on the location information, match the block area where the second key element is located in the road network map; Detect whether the first key element and the second key element in the segmented region overlap; If they overlap, the passage status of the corresponding first key element is adjusted based on the passage status of the overlapping second key element. Based on the traffic status of the adjusted first key element, an updated road network map is generated.

5. The method for generating a navigation map according to claim 4, characterized in that, The step of performing optimal route planning on the updated road network map based on the navigation request and generating a corresponding navigation map includes: Based on the navigation request, multiple navigation start points and multiple navigation end points are determined on the updated road network map; Search for each navigation planning path between each navigation start point and each navigation end point in the updated road network graph, and calculate the path cost of each navigation planning path. The navigation path with the least path consumption is selected from all the navigation planning paths and taken as the optimal navigation path. Based on the optimal navigation path, the corresponding navigation map is generated.

6. The method for generating a navigation map according to claim 5, characterized in that, The step of determining multiple navigation start points and multiple navigation destinations on the updated road network map based on the navigation request includes: Extract the navigation request and determine the corresponding initial navigation start point and initial navigation end point; On the updated road network map, match the center points of multiple intersections that are directly connected to the initial navigation starting point, and use them as the corresponding navigation starting points; On the updated road network map, match the center points of multiple intersections that are directly connected to the initial navigation endpoint, and use them as the corresponding navigation endpoints.

7. A navigation map generation apparatus, characterized in that, The navigation map generation device includes: The network construction module is used to obtain the first global map of the target area and extract the first key element of the static road lane lines from the first global map to construct a road network map. The location determination module is used to acquire a second global map of the target area, extract a second key element of dynamically changing roads from the second global map, and determine the location information of the second key element; wherein, the second global map refers to the latest traffic road map of the target area, which includes road congestion and detour information; The network update module is used to update the road network map according to the location information when a navigation request is received, so as to obtain an updated road network map. The route planning module is used to perform optimal route planning on the updated road network map based on the navigation request and generate a corresponding navigation map. The network construction module includes: a map recognition unit, used to recognize each intersection in the first global map and the lane lines connected to each intersection; an element construction unit, used to determine the intersection center point of the corresponding intersection using the lane lines connected to each intersection, and to connect the corresponding intersection center points using the lane lines to obtain multiple first key elements; and a block combination unit, used to divide and combine each of the first key elements into blocks according to a preset size to obtain the final road network map.

8. A navigation map generation device, characterized in that, The navigation map generation device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the navigation map generating device to perform the steps of the navigation map generating method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the steps of the navigation map generation method as described in any one of claims 1-6.

Images