Map updating method and device, cloud equipment, vehicle and storage medium
By generating detection routes and acquisition routes in the cloud, screening and collecting road field data, the problem of map update methods in the prior art has been solved, and more efficient and accurate map data updates have been achieved.
Patent Information
- Application Number
- CN202311776340.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-21
- Publication Date
- 2025-06-24
AI Technical Summary
The prior art map update method results in a decrease in the freshness of map data, and the changes in road data cannot be collected in a timely and accurate manner.
By generating detection routes in the cloud, filtering out detection vehicles, and generating acquisition routes based on the differences between the road reference data collected by the detection vehicles and map data. The vehicles located on the acquisition route then collect the road field data and update the map.
It improves the freshness of map data, ensures that the data on the map can be updated in a timely and accurate manner, covering more differential data, thereby improving the efficiency and accuracy of map updates.
Smart Images
Figure CN120196690A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of map updating, and specifically relates to a map updating method, device, cloud device, vehicle and storage medium. Background Art
[0002] The map stores road data and the locations where the roads are located. Since the road data may change due to construction or other reasons, it is necessary to update the changed road data on the map. In the prior art, personnel use the perception system on a specific collection vehicle to sense the road change data. However, before the collection vehicle starts collecting data, it does not know which road or which section of the road has changed, and the collection work has a certain degree of blindness. As a result, the changed road data cannot be collected in a timely manner, and the collected road data has a certain lag. Using the lagged road data to update the map will reduce the freshness of the map, where freshness refers to the freshness of the data on the map.
[0003] In summary, the map updating method in the prior art reduces the freshness of map data.
[0004] Therefore, the prior art still needs to be improved. Summary of the Invention
[0005] The present application provides a map updating method, device, cloud device, vehicle and storage medium to solve the technical problem that the map updating method in the related art reduces the freshness of map data.
[0006] To achieve the above object, the present application adopts the following technical solutions:
[0007] The first aspect embodiment of the present application provides a map updating method, including the following steps:
[0008] Generate a detection route, and determine a detection vehicle according to the detection route;
[0009] Obtain the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map;
[0010] When there is difference data between the road reference data and the road map data, generate a collection route according to the difference data and the detection route;
[0011] Obtain the road field data collected by each collection vehicle located on the collection route, and update the map according to the road field data.
[0012] According to the above technical means, in the embodiment of the present application, a detection route is first generated on the cloud, and based on the real-time position relationship between each vehicle and the detection route on the cloud, that is, according to whether the vehicle is on the detection route, the detection vehicles are screened out. Then, according to the road reference data collected by the detection vehicles, the data with differences in the road data on the map is determined. According to the position of the difference data and the detection route, a collection route is generated. Finally, the road data collected by the vehicles located on the collection route is used to update the map. From the above analysis, it can be seen that in the present application, a detection route is roughly generated first, and then the road reference data is collected by the vehicles located on the detection route. If there are differences between the collected road reference data and the map data, it means that the map data deviates from the actual situation, that is, the data on the map needs to be updated. Therefore, a collection route is generated based on the position of the difference data, and then the road data is collected by the vehicles on the collection route to update the map. The present application generates a collection route with difference data based on the detection route. Therefore, by collecting road data through the vehicles driving on the collection route, more difference data can be accurately and timely collected, that is, more data that needs to be updated can be collected, thereby improving the freshness of the map data after updating.
[0013] Optionally, in an embodiment of the present application, the generating the detection route includes:
[0014] Sending the map data to be detected to each of all the driving vehicles;
[0015] Receiving the driving trajectory routes of each preselected vehicle, where the preselected vehicle is a vehicle among all the driving vehicles used to collect data different from the map data to be detected;
[0016] Aggregating all the received driving trajectory routes to generate a detection route.
[0017] According to the above technical means, in the embodiment of the present application, the detection route is generated from the driving trajectory routes of the vehicles that have collected different data, so that the collection route generated subsequently by the detection route can cover more different data, and the different data is the data that needs to be updated. Thus, the vehicles located on the collection route can collect more different data or difference data, and updating the map with this difference data can further improve the freshness of the map data.
[0018] Optionally, in an embodiment of the present application, the determining the detection vehicles according to the detection route includes:
[0019] Receiving the real-time positions sensed by each vehicle;
[0020] Calculating the real-time distance between the real-time position and the detection route;
[0021] Select a set number of detection vehicles from each of the vehicles according to the real-time distance corresponding to each vehicle.
[0022] According to the above technical means, in the embodiment of the present application, the detection vehicles are selected according to the distance between the real-time positions of each vehicle and the detection route. Therefore, the present application can select the vehicles located on the detection route as the detection vehicles, so that the detection vehicles can collect the positions where the differential data for updating the map is located along the detection route, so as to generate the subsequent collection route according to the positions where the differential data is located.
[0023] Optionally, in an embodiment of the present application, when there is differential data between the road reference data and the road map data, generating a collection route according to the differential data and the detection route includes:
[0024] Analyze the road reference data to obtain road attribute reference data and the road positions corresponding to the road attribute reference data;
[0025] Extract the road map data at the road positions from the map;
[0026] When there is differential data between the road map data and the road attribute reference data, generate a collection route according to the position where the differential data is located and the detection route.
[0027] According to the above technical means, the differential data in the embodiment of the present application is road attribute differential data, that is, the positions where the attribute differential data is detected are found, and the collection route is jointly generated by these positions and the detection route. The collection route in the present application covers more attribute differential data for updating the map. Therefore, by collecting road attribute data by the vehicles on the collection route, more differential data different from the road map data, that is, attribute differential data, can be collected in a timely and accurate manner. Using this differential data to update the map can improve the freshness of the updated map data.
[0028] Optionally, in an embodiment of the present application, when there is differential data between the road map data and the road attribute reference data, generating a collection route according to the position where the differential data is located and the detection route includes:
[0029] When there is differential data between the road map data and the road attribute reference data, calculate the distances between each lane and the position where the differential data is located;
[0030] Select the nearest lane from each of the lanes according to the distances corresponding to each of the lanes;
[0031] When the detection route covers the nearest lane, the detection route is used as a collection route;
[0032] When the detection route does not cover the nearest lane, the nearest lane is used as the collection route.
[0033] According to the above technical means, the collection route of the embodiment of the present application is the lane closest to the location of the difference data, so that the vehicle located in the nearest lane can collect more difference data for updating the map more accurately and timely.
[0034] Optionally, in one embodiment of the present application, the acquiring of the road field data collected by each collection vehicle located on the collection route and updating the map according to the road field data includes:
[0035] For each sampling position in the acquisition route, reading reference road field data corresponding to the sampling position in each acquired road field data, wherein the road field data includes reference road field data of at least one sampling position in the acquisition route;
[0036] Selecting the target road field data at the sampling location from all the reference road field data read;
[0037] The target road field data is used to replace the road map data at the map position corresponding to the sampling position on the map, so as to update the map.
[0038] According to the above-mentioned technical means, each vehicle is limited by its own performance, resulting in certain errors in the road field data collected by each vehicle. Therefore, this embodiment compares the road field data collected by multiple vehicles together to eliminate the road field data with large differences, thereby retaining more accurate target road field data, so that the target road field data can update the map more accurately.
[0039] A second aspect of the present application provides a map updating method, comprising the following steps:
[0040] Collecting the real-time location and road data at the real-time location, and sending the real-time location to the cloud;
[0041] Receiving map data to be detected covering the real-time location on the map sent by the cloud;
[0042] When the map data to be detected is different from the road data, a driving trajectory route is collected. The driving trajectory route is used to be sent to the cloud to be aggregated into a detection route at the cloud, so that the cloud determines a detection vehicle based on the detection route; so that the cloud reads the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map; when there is difference data between the road reference data and the road map data, so that the cloud generates a collection route according to the difference data and the detection route; so that the cloud obtains the road field data collected by each collection vehicle located on the collection route, so that the cloud updates the map according to the road field data.
[0043] According to the above technical means, the embodiments of the present application aggregate the driving trajectory routes of each vehicle that has collected different data, so that the aggregated detection route can cover as much as possible the geographical area where the different data is located, so that the collection route generated from the detection route can cover as many different data as possible, and thus more different data or difference data can be collected to update the map.
[0044] An embodiment of the third aspect of the present application provides a map update device, including:
[0045] A detection vehicle generation module, configured to generate a detection route and determine a detection vehicle according to the detection route;
[0046] A data collection module, configured to obtain the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map;
[0047] A collection route generation module, configured to generate a collection route according to the difference data and the detection route when there is difference data between the road reference data and the road map data;
[0048] An update module, configured to obtain the road field data collected by each collection vehicle located on the collection route and update the map according to the road field data.
[0049] An embodiment of the fourth aspect of the present application provides a cloud device. The cloud device includes a memory, a processor, and a map update program stored in the memory and executable on the processor. When the processor executes the map update program, the steps of the above-mentioned map update method are implemented.
[0050] An embodiment of the fifth aspect of the present application provides a vehicle. The vehicle includes a memory, a processor, and a map update program stored in the memory and executable on the processor. When the processor executes the map update program, the steps of the above-mentioned map update method are implemented.
[0051] In the sixth aspect of the embodiments of the present application, a computer-readable storage medium is provided. A map update program is stored on the computer-readable storage medium. When the map update program is executed by a processor, the steps of the above-mentioned map update method are implemented;
[0052] Alternatively, a route collection program is stored on the computer-readable storage medium. When the route collection program is executed by a processor, the steps of the above-mentioned route collection method are implemented.
[0053] Advantages of the present application:
[0054] (1) In the embodiments of the present application, a detection route is first generated on the cloud, and based on the real-time position relationship between each vehicle and the detection route on the cloud, that is, according to whether the vehicle is on the detection route, the detection vehicles are screened out. Then, based on the road reference data collected by the detection vehicles, the data with differences in the road data on the map is determined. According to the location of the difference data and the detection route, a collection route is generated. Finally, the road data collected by the vehicles located on the collection route is used to update the map. From the above analysis, it can be seen that in the present application, a detection route is roughly generated first, and then the road reference data is collected by the vehicles located on the detection route. If there are differences between the collected road reference data and the map data, it means that the map data deviates from the actual situation, that is, the data on the map needs to be updated. Therefore, a collection route is generated based on the location of the difference data, and then the road data is collected by the vehicles on the collection route to update the map. The present application generates a collection route with difference data based on the detection route. Therefore, by collecting road data by the vehicles driving on the collection route, more difference data can be accurately and timely collected, that is, more data that needs to be updated can be collected, thereby improving the freshness of the map data after update.
[0055] (2) Due to the limitations of each vehicle's own performance, there are certain errors in the road field data collected by each vehicle. Therefore, in this embodiment, the road field data collected by multiple vehicles are compared together to eliminate the road field data with relatively large differences, so as to retain the relatively accurate target road field data, enabling the target road field data to more accurately update the map.
[0056] (3) In the embodiments of the present application, the driving track routes of each vehicle that has collected different data are aggregated, so that the aggregated detection route can cover as much as possible the geographical area where the different data is located, so that the collection route generated from the detection route can cover as much as possible more different data, and thus more different data or difference data can be collected to update the map.
[0057] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Brief Description of the Drawings
[0058] The above-mentioned and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, where:
[0059] Figure 1 is the overall flowchart of the present application;
[0060] Figure 2 is the map update flowchart in the embodiment of the present application;
[0061] Figure 3 is the schematic diagram of the interaction between the vehicle and the cloud in the embodiment of the present application;
[0062] Figure 4 is the schematic structural diagram of the map update device in the embodiment of the present application;
[0063] Figure 5 is the internal structure principle block diagram of the cloud device provided in the embodiment of the present application. Detailed Description of the Embodiments
[0064] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.
[0065] A map update method, device, cloud device, vehicle, and storage medium according to an embodiment of the present application will be described below with reference to the accompanying drawings. In view of the fact that the existing map update method in the above-mentioned background technology reduces the freshness of map data, the present application provides a map update method. In this method, a detection route is first generated; then, based on the detection route, a detection vehicle is determined; then, road reference data sensed by the detection vehicle and road map data corresponding to the road reference data on the map are obtained; when there is difference data between the road reference data and the road map data, an acquisition route is generated according to the difference data and the detection route; finally, road field data collected by each acquisition vehicle located on the acquisition route is obtained, and the map is updated according to the road field data. The present application can improve the freshness of the map data after update.
[0066] For example, if a vehicle on the middle lane of this route senses a difference between the actual road data and the road data on the map, then the middle lane is taken as the detection route. Then, according to the positional relationship between other vehicles and the middle lane, vehicles that are relatively close to the middle lane are preferably selected as detection vehicles. After that, the road data (road reference data) sensed by the detection vehicles is collected, and the road data sensed by the detection vehicles at the same position is compared with the road map data. If there is a data A in the road reference data that is different from the road map data at the same position, then an acquisition route is generated based on the position of data A and the middle lane. For example, although the detection vehicle collects data A on the middle lane, since the sensing range of the vehicle's sensing system is not limited to the middle lane, data A may be located in the left lane, then the left lane is taken as the acquisition route. If data A is still on the middle lane, then the middle lane is taken as the acquisition route. If data A is on the right lane, then the right lane is taken as the acquisition route. Since there is already a data A on the acquisition route that is locally different from the road map data, that is, it indicates that the road data on the map does not match the actual road data, so the map needs to be updated. Also, since there is already a data A on the acquisition route that is different from the map data, due to the correlation between the data, there is a high probability that there are more data B, data C, etc. on the acquisition route that are different from the map data. Therefore, using the vehicles located on the acquisition route can more likely collect more differential data that is different from the map data, so that the differential data can be timely informed by the vehicle, so as to update the map in time with more differential road field data.
[0067] Specifically, Figure 1 is a schematic flowchart of a map update method provided by an embodiment of the present application.
[0068] As Figure 1 shown, the map update method includes the following steps:
[0069] S100, generate a detection route, and determine detection vehicles according to the detection route;
[0070] S200, obtain the road reference data sensed by the detection vehicles and the road map data corresponding to the road reference data on the map;
[0071] S300, when there is differential data between the road reference data and the road map data, generate an acquisition route according to the differential data and the detection route;
[0072] S400, obtain the road field data collected by each acquisition vehicle located on the acquisition route, and update the map according to the road field data.
[0073] The vehicle in steps S100 to S400 is a vehicle with autonomous driving function, and the vehicle also has the function of real-time data collection. The data can be video, image, radar, point cloud data, etc., and the road data is covered in these data.
[0074] In one embodiment, the generation of the detection route in step S100 includes the following specific steps S101, S102, and S103:
[0075] S101, send the map data to be detected to each of all the driving vehicles.
[0076] The map data to be detected is obtained in the following way:
[0077] The vehicle sends its location to the cloud, and the cloud extracts the map data packet covering this location from the map according to this location, that is, the crowdsourced map data. This map data packet is the map data to be detected, that is, Figure 2 the vehicle in sends the location to request the detection map data, and the cloud downloads the crowdsourced map data.
[0078] When the cloud receives requests sent by vehicles within the same location range and feeds back the map data to be detected covering this location range to the requesting vehicles, the cloud will count the number of vehicles fed back based on the same location range. When the total number of vehicles reaches a certain number, the number of vehicles at this time is sufficient to collect the actual road data to update the map. Even if the cloud receives requests from vehicles within the same location range again, it will no longer send the same map data to be detected to the subsequent requesting vehicles, thus saving the computing resources of the subsequent vehicles.
[0079] The map in this embodiment is a crowdsourced map. The crowdsourced map uses the crowdsourcing method to collect high-precision map data and makes a high-precision map based on the vehicle-end map data collected by crowdsourcing. The crowdsourced map has the advantages of low cost and fast update. The crowdsourced map improves the data accuracy and freshness by collecting a large amount of data.
[0080] If the vehicle sends its location to the cloud and the cloud cannot match the location of the vehicle on the map, it means that there is currently no road data established in this location area on the cloud map, and there is no premise for updating the map. Therefore, the road data collected by the vehicle is directly uploaded to the cloud to fill in the missing data on the cloud map.
[0081] S102, receive the driving trajectory routes of each preselected vehicle, and the preselected vehicle is a vehicle among all the driving vehicles used to collect data different from the map data to be detected.
[0082] While each vehicle receives the map data to be detected sent by the cloud, each vehicle also starts to collect road data. If the road data collected by the vehicle is different from the map data to be detected, that is Figure 2 perform differential analysis on the vehicle collection data in Figure 3 (that is, perform differential analysis on the vehicle), then the vehicle is a preselected vehicle. The preselected vehicle sends its own driving trajectory route to the cloud.
[0083] The road data includes data information related to autonomous driving such as ground elements, intersection information, divergence and confluence, etc. Analyze whether the above data information within the same position range on the map data to be detected is consistent with the data collected by the vehicle. If not, then the vehicle that has collected inconsistent or different data is the preselected vehicle.
[0084] The road data also includes road data such as speed limit signs, solid and dashed lines on the road surface, traffic lights, number of lanes, etc. Similarly, analyze whether the above data information within the same position range on the map data to be detected is consistent with the above data collected by the vehicle. If not, then the vehicle that has collected inconsistent or different data is the preselected vehicle.
[0085] S103, Aggregate all the received driving trajectory routes to generate a detection route.
[0086] The cloud receives the respective driving trajectory routes sent by multiple preselected vehicles. As Figure 2 and Figure 3 shown, the cloud aggregates multiple driving trajectory routes to obtain a detection route. For example, the cloud receives eight driving trajectory routes of eight vehicles located on a certain highway section. This highway section is the area covered by the map data to be detected, among which three driving trajectory routes are in the middle lane, four driving trajectory routes are in the left lane, and one is in the right lane. Then the routes covered by the middle lane and the left lane are the detection routes.
[0087] In one embodiment, determining the detection vehicle according to the detection route in step S100 includes the following specific steps S104, S105, and S106:
[0088] S104, Receive the real-time positions sensed by each vehicle.
[0089] The vehicle in step S104 can be the preselected vehicle in step S102, that is, other vehicles. Each vehicle sends the real-time position it senses to the cloud. The cloud can also obtain the real-time positions of each vehicle through GNSS devices.
[0090] S105, Calculate the real-time distance between the real-time position and the detection route.
[0091] S106, screen out a set number of detection vehicles from each of the vehicles according to the real-time distance corresponding to each vehicle.
[0092] That is, try to select the vehicles close to the detection route as the detection vehicles. In this embodiment, the vehicles located within the detection route are used as the detection vehicles. A certain number of detection vehicles can complete the subsequent acquisition of road reference data. Therefore, only a set number of vehicles need to be selected as the detection vehicles.
[0093] In one embodiment, step S300 includes the following specific steps S301 to S305:
[0094] S301, analyze the road reference data to obtain road attribute reference data and the road position corresponding to the road attribute reference data.
[0095] That is, the road reference data collected by the detection vehicles includes road attribute reference data and the road position corresponding thereto. Among them, the road attribute reference data includes ground elements, intersection information, diverging and merging, speed limit signs, solid and dashed lines on the road surface, traffic lights, and the number of lanes collected on the spot by the vehicle.
[0096] S302, extract the road map data at the road position from the map.
[0097] That is, the road map data and the road attribute reference data are both data at the same road position. Only the former comes from the cloud map, and the latter comes from the data collected by the detection vehicles. The road map data also includes ground elements, intersection information, diverging and merging, speed limit signs, solid and dashed lines on the road surface, traffic lights, and the number of lanes on the map.
[0098] S303, when there are difference data between the road map data and the road attribute reference data, calculate the respective distances between each lane and the position where the difference data is located.
[0099] For example, if there is a difference in the speed limit signs between the road map data and the road attribute reference data, then the speed limit sign is the difference data, and the speed limit sign is at position X on the far right side of the road. Then calculate the distances between each lane on the road and position X. This distance is the distance along the side-by-side direction of each lane.
[0100] S304, screen out the nearest lane from each of the lanes according to the respective distances corresponding to each lane.
[0101] If the difference data is at position X on the far right side of the road, then the right lane is the nearest lane.
[0102] S305. When the detection route covers the nearest lane, use the detection route as the acquisition route; when the detection route does not cover the nearest lane, use the nearest lane as the acquisition route.
[0103] In one embodiment, all the differential data detected by the detection vehicle is made into an update list, that is, all the differential data is saved in the update list. Since the detection vehicle is only a part of the vehicles, the road attribute reference data collected by the detection vehicle can only determine that there are differential data that need to be updated on the map. However, the road attribute reference data collected by each detection vehicle is not necessarily accurate. Therefore, the differential data on the map cannot be directly replaced with the road attribute reference data to update the map. More acquisition vehicles located on the acquisition route are needed to collect the on-site road attribute data to update the map. In this embodiment, step S400 includes the following specific steps S401, S402, and S403:
[0104] S401. For each sampling position in the acquisition route, read the reference on-site road data corresponding to the sampling position from the obtained on-site road data of each road, where the on-site road data includes the reference on-site road data of at least one sampling position in the acquisition route.
[0105] S402. Select the target on-site road data of the sampling position from all the read reference on-site road data.
[0106] For example, ten acquisition vehicles located on the acquisition route all collect the reference on-site road data at the same position (i.e., the sampling position). Remove the data with obvious differences among these ten reference on-site road data, and the remaining is the target on-site road data required to update the map.
[0107] S403. Use the target on-site road data to replace the road map data at the map position corresponding to the sampling position on the map to update the map.
[0108] That is, delete the original differential data on the map and store the target on-site road data on the map to complete the operation of updating the map. Since the differential data is in the above update list, after completing the operation of updating the map, the update list needs to be deleted.
[0109] In summary, in the present application, the vehicle detects road data in real time, and performs differential analysis on the real-time road data and the map data to filter out the data on the map that does not conform to the actual road. The vehicle that filters out the data that does not conform to the actual road uploads its own trajectory to the cloud, and a detection route is generated from the trajectory. Then, based on the analysis of the road data collected from the vehicles on the detection route, a collection route is generated. Finally, the cloud receives the road data collected by the vehicles on the collection route, and the cloud performs secondary detection on the road data to reduce the misjudgment rate of vehicle detection, accurately determine the data update range, achieve accurate data collection, reduce the upload of invalid data, and significantly reduce the consumption of resources such as traffic, bandwidth, and computing. It realizes dynamic scheduling of the cloud, improves the automation rate of collection tasks and data updates, and has an adaptive adjustment ability.
[0110] Next, a map update device according to an embodiment of the present application will be described with reference to the accompanying drawings.
[0111] As Figure 4 shown, the map update device 10 includes: a detection vehicle generation module 100, a data collection module 200, a collection route generation module 300, and an update module 400.
[0112] Specifically, the detection vehicle generation module 100 is configured to generate a detection route and determine a detection vehicle according to the detection route.
[0113] The data collection module 200 is configured to obtain the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map.
[0114] The collection route generation module 300 is configured to generate a collection route according to the difference data and the detection route when there is difference data between the road reference data and the road map data.
[0115] The update module 400 is configured to obtain the road field data collected by each collection vehicle located on the collection route and update the map according to the road field data.
[0116] It should be noted that the foregoing explanation of the embodiments of the map update method also applies to the map update device of this embodiment, and will not be repeated here.
[0117] Figure 5 It is a schematic structural diagram of a cloud device provided by an embodiment of the present application. The cloud device may include:
[0118] A memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.
[0119] When the processor 502 executes the program, it implements the map update method provided in the above embodiments.
[0120] Furthermore, the terminal device further includes:
[0121] A communication interface 503, which is used for communication between the memory 501 and the processor 502.
[0122] A memory 501, which is used to store a computer program that can run on the processor 502.
[0123] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.
[0124] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be interconnected through a bus and complete communication with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.
[0125] Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 can complete communication with each other through an internal interface.
[0126] The processor 502 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.
[0127] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the above map update method.
[0128] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0129] In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.
[0130] Any process or method description shown in a flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application belong.
[0131] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can read and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.
[0132] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or combinations thereof. In the above-described embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0133] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.
[0134] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0135] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.
Claims
1. A method for map updating, characterized in that, Including the following steps: Generate a detection route, and determine a detection vehicle according to the detection route; Obtain the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map; When there is difference data between the road reference data and the road map data, generate a collection route according to the difference data and the detection route; Obtain the road field data collected by each collection vehicle located on the collection route, and update the map according to the road field data.
2. The map update method according to claim 1, wherein The generating the detection route includes: Send the map data to be detected to each driving vehicle among all driving vehicles; Receive the driving track routes of each preselected vehicle, where the preselected vehicle is a vehicle among all driving vehicles used to collect data different from the map data to be detected; Aggregate all the received driving track routes to generate a detection route.
3. The map update method according to claim 1, characterized in that, The determining the detection vehicle according to the detection route includes: Receive the real-time positions sensed by each vehicle; Calculate the real-time distance between the real-time position and the detection route; Select a set number of detection vehicles from each vehicle according to the real-time distance corresponding to each vehicle.
4. The map update method according to claim 1, wherein, The generating the collection route according to the difference data and the detection route when there is difference data between the road reference data and the road map data includes: Analyze the road reference data to obtain road attribute reference data and the road position corresponding to the road attribute reference data; Extract the road map data at the road position from the map; When there is difference data between the road map data and the road attribute reference data, generate a collection route according to the position where the difference data is located and the detection route.
5. The map update method according to claim 4, wherein The generating the collection route according to the position where the difference data is located and the detection route when there is difference data between the road map data and the road attribute reference data includes: When there is difference data between the road map data and the road attribute reference data, calculate the distance between each lane and the position where the difference data is located; Select the nearest lane from each lane according to the distance corresponding to each lane; When the detection route covers the nearest lane, use the detection route as the collection route; When the detection route does not cover the nearest lane, use the nearest lane as the collection route.
6. The map updating method according to claim 1, wherein The obtaining the road field data collected by each collection vehicle located on the collection route and updating the map according to the road field data includes: For each sampling position in the collection route, read the reference road field data corresponding to the sampling position from the obtained road field data, where the road field data includes the reference road field data of at least one sampling position in the collection route; Select the target road field data of the sampling position from all the read reference road field data; Use the target road field data to replace the road map data at the map position corresponding to the sampling position on the map to update the map.
7. A method for map update, characterized in that, Including the following steps: Collect the real-time position and road data at the real-time position, and send the real-time position to the cloud; Receive the map data to be detected covering the real-time position sent by the cloud; When the map data to be detected is different from the road data, collect the driving trajectory route, which is used to be sent to the cloud to aggregate and generate a detection route at the cloud, so that the cloud determines the detection vehicle based on the detection route; So that the cloud reads the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map; when there is difference data between the road reference data and the road map data, so that the cloud generates a collection route according to the difference data and the detection route; so that the cloud obtains the road field data collected by each collection vehicle located on the collection route, so that the cloud updates the map according to the road field data.
8. A map update device, characterized in that, It includes: A detection vehicle generation module, configured to generate a detection route and determine a detection vehicle according to the detection route; A data collection module, configured to obtain the road reference data sensed by the detection vehicle and the road map data corresponding to the road reference data on the map; A collection route generation module, configured to generate a collection route according to the difference data and the detection route when there is difference data between the road reference data and the road map data; An update module, configured to obtain the road field data collected by each collection vehicle located on the collection route and update the map according to the road field data.
9. A cloud device, characterized in that, The cloud device includes a memory, a processor, and a map update program stored in the memory and executable on the processor. When the processor executes the map update program, it implements the steps of the map update method according to any one of claims 1-6.
10. A vehicle, characterized in that, The vehicle includes a memory, a processor, and a map update program stored in the memory and executable on the processor. When the processor executes the map update program, it implements the steps of the map update method according to claim 7.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a map update program. When the map update program is executed by a processor, it implements the steps of the map update method according to any one of claims 1-6; Or, the computer-readable storage medium stores a map update program. When the map update is executed by a processor, it implements the steps of the map update method according to claim 7.