Map updating method and device, electronic equipment and readable storage medium
By determining the target driving trajectory from the lane line information collected from the vehicle end and calculating the confidence, generating vector data update maps, the problem of low accuracy of lane line data in the prior art is solved, and the accuracy of map update is improved.
Patent Information
- Application Number
- CN202410016412.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-04
- Publication Date
- 2025-07-04
AI Technical Summary
In the prior art, the lane line data after the map is updated has low accuracy, and it is easy to cause inaccurate updates due to incorrect data.
By determining the first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle end, its confidence is calculated, and parsing it when the confidence reaches the threshold, vector data is generated to update the map.
Improve the accuracy of map update data and ensure the correspondence between lane line information and the actual traffic environment.
Smart Images
Figure CN120256440A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of maps, and particularly to a map update method, apparatus, electronic device, and readable storage medium. Background Art
[0002] With the continuous development of artificial intelligence and autonomous driving technologies, high-precision maps have become an important part of intelligent transportation systems. The geographical information contained in high-precision maps has high accuracy. Moreover, the lane line information and traffic environment are changing more and more frequently. In order to ensure the accuracy of high-precision maps, it is necessary to continuously update the lane line information in high-precision maps to correspond to the actual traffic environment and road information.
[0003] In related map update technologies, road information to be updated can be collected by map acquisition vehicles, then new lane line information can be generated based on the road information, and finally the lane line information in the map can be overwritten and updated to obtain updated map data.
[0004] However, in this method, if incorrect data is collected, incorrect updates will occur, and the accuracy of the updated lane line data is relatively low. Summary of the Invention
[0005] One of the purposes of the present application is to provide a map update method to solve the problem of relatively low accuracy of lane line data after map update in the prior art; the second purpose is to provide an apparatus; the third purpose is to provide an electronic device; the fourth purpose is to provide a storage medium.
[0006] To achieve the above purposes, the technical solutions adopted in the present application are as follows:
[0007] A map update method, the method includes:
[0008] Determine first lane line information corresponding to a target driving trajectory from the lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map;
[0009] Calculate a first confidence level of the first lane line information based on the number of acquisitions of the first lane line information;
[0010] When the first confidence level is greater than or equal to a first threshold, parse the first lane line information to obtain first vector data of the first lane line information;
[0011] Update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
[0012] Optionally, calculating a first confidence level of the first lane line information based on the number of acquisitions of the first lane line information includes:
[0013] Performing data segmentation on the first vector data to obtain first topological information;
[0014] Calculating a second confidence level of the first topological information based on the number of acquisitions of the first lane line information to obtain the first confidence level of the first lane line information.
[0015] Optionally, calculating the second confidence level of the first topological information based on the number of acquisitions of the first lane line information includes:
[0016] Obtaining an initial confidence level of the first topological information; wherein, the initial confidence level is generated by a trained deep learning model when each vehicle terminal acquires the first lane line information;
[0017] Using the topological information corresponding to the lane line information to be updated as a clustering center to cluster the first topological information, obtaining second topological information with successful clustering and third topological information with failed clustering;
[0018] Calculating a third confidence level of the third topological information based on the number of acquisitions of the lane line information and the initial confidence level to obtain the second confidence level of the first topological information.
[0019] Optionally, updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes:
[0020] Determining second vector data of the lane line information to be updated from the first map;
[0021] Comparing the second vector data with the first vector data to obtain first difference data corresponding to the first vector data and second difference data corresponding to the second vector data;
[0022] Deleting the second difference data from the second vector data and adding the first difference data to update the lane line information to be updated in the first map to obtain the second map.
[0023] Optionally, updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes:
[0024] Determining the relative positions between the lane lines included in the first lane line information from the first vector data;
[0025] Update the lane line information to be updated in the first map based on the relative position and the lane lines corresponding to the relative position to obtain a second map.
[0026] Optionally, determining the first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle terminal includes:
[0027] Obtain the trajectory length of the target driving trajectory;
[0028] In the case where the trajectory length is less than or equal to a second threshold, determine the first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle terminal.
[0029] Optionally, updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes:
[0030] In the case where there is no lane line information to be updated corresponding to the target driving trajectory in the first map, based on the position information corresponding to the target driving trajectory in the first map, add the first lane line information corresponding to the first vector data into the first map to obtain the second map.
[0031] A map update device, the device includes:
[0032] A determination module, configured to determine the first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle terminal; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map;
[0033] A calculation module, configured to calculate a first confidence level of the first lane line information based on the number of times of collection of the first lane line information;
[0034] An analysis module, configured to analyze the first lane line information to obtain first vector data of the first lane line information in the case where the first confidence level is greater than or equal to a first threshold;
[0035] An update module, configured to update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
[0036] Optionally, the calculation module includes:
[0037] A segmentation sub-module, configured to perform data segmentation on the first vector data to obtain first topological information;
[0038] A calculation sub-module, configured to calculate a second confidence level of the first topological information based on the number of times of collection of the first lane line information to obtain the first confidence level of the first lane line information.
[0039] Optionally, the calculation sub-module includes:
[0040] A first acquisition unit, configured to acquire an initial confidence level of the first topology information; wherein, the initial confidence level is generated by a trained deep learning model when each vehicle end collects the first lane line information;
[0041] A clustering unit, configured to cluster the first topology information with the topology information corresponding to the lane line information to be updated as a clustering center, and obtain a second topology information with successful clustering and a third topology information with failed clustering;
[0042] A calculation unit, configured to calculate a third confidence level of the third topology information based on the number of times of collecting the lane line information and the initial confidence level, and obtain a second confidence level of the first topology information.
[0043] Optionally, the update module includes:
[0044] A first determination sub-module, configured to determine second vector data of the lane line information to be updated from a first map;
[0045] A comparison sub-module, configured to compare the second vector data with the first vector data, and obtain first difference data corresponding to the first vector data and second difference data corresponding to the second vector data;
[0046] A first update sub-module, configured to delete the second difference data from the second vector data and add the first difference data, so as to update the lane line information to be updated in the first map, and obtain the second map.
[0047] Optionally, the update module includes:
[0048] A second determination sub-module, configured to determine the relative positions between the lane lines included in the first lane line information from the first vector data;
[0049] A second update sub-module, configured to update the lane line information to be updated in the first map based on the relative positions and the lane lines corresponding to the relative positions, and obtain a second map.
[0050] Optionally, the determination module includes:
[0051] A second acquisition sub-module, configured to acquire the trajectory length of the target driving trajectory;
[0052] A third determination sub-module, configured to determine first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle end when the length of the trajectory is less than or equal to a second threshold.
[0053] Optionally, the update module includes:
[0054] A third update sub-module, configured to add the first lane line information corresponding to the first vector data into the first map based on the position information corresponding to the target driving trajectory in the first map to obtain the second map when there is no lane line information to be updated corresponding to the target driving trajectory in the first map.
[0055] An electronic device includes the map update device as described above to implement any of the map update methods as described above.
[0056] A storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, cause the electronic device to execute any of the map update methods as described above.
[0057] Advantages of the present application:
[0058] In the embodiments of the present application, first lane line information corresponding to a target driving trajectory is determined from the lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map; a first confidence level of the first lane line information is calculated based on the number of times the first lane line information is collected; when the first confidence level is greater than or equal to a first threshold, the first lane line information is parsed to obtain first vector data of the first lane line information; and the lane line information to be updated in the first map is updated based on the first vector data to obtain a second map, so that the lane line information in the first map can be updated when the confidence level of the lane line information collected from the vehicle end is greater than the first threshold, improving the accuracy of the map update data. Description of the Drawings
[0059] Figure 1 It is a schematic flowchart of a map update method provided by an embodiment of the present application;
[0060] Figure 2 It is a schematic flowchart of another map update method provided by an embodiment of the present application;
[0061] Figure 3 It is a flowchart of a specific implementation manner of a map update method provided by an embodiment of the present application;
[0062] Figure 4 It is a schematic flowchart of a lane line topology generation method provided by an embodiment of the present application;
[0063] Figure 5 A logic block diagram of a map update device provided by an embodiment of the present application;
[0064] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners
[0065] The following will describe the implementation manners of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application and not for limiting the protection scope of the present application.
[0066] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.
[0067] Refer to Figure 1 , Figure 1 A schematic flowchart of a map update method provided by an embodiment of the present application. The method may include:
[0068] Step 101, determining first lane line information corresponding to a target driving trajectory from the lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to the lane line information to be updated in a first map.
[0069] In an embodiment of the present application, the first map may be an image. Lanes may be included in the first map, and lane lines may be included in the lanes. Therefore, lane line information may be included in the first map, which is used to indicate the driving direction of a vehicle, regulate the traffic behavior of the vehicle, ensure the safe passage of the road, and so on. In current vehicles, lane line information is usually collected through the vehicle terminal during driving to generate a crowdsourced map. In this way, the lane line information collected by the vehicle terminal can correspond to the driving trajectory of the vehicle terminal. First, the lane line information to be updated can be determined in the first map, and then the target driving trajectory corresponding to the lane line information to be updated can be determined according to the corresponding relationship between the lane line information and the driving trajectory. After that, the first lane line information corresponding to the target driving trajectory can be determined from the lane line information collected by each vehicle terminal. In this way, the road section corresponding to the first lane line information and the road section corresponding to the lane line information to be updated can be the same road section. In addition, considering that the driving trajectory of the vehicle may not be exactly the same as the target driving trajectory, when determining the first lane line information, a fuzzy matching method can be used, as long as the starting point, ending point, and road section corresponding to the first lane line information are the same as the target driving trajectory. Among them, the first lane line information may also be image information.
[0070] Step 102: Calculate a first confidence level of the first lane line information based on the number of times the first lane line information is collected.
[0071] In an embodiment of the present application, the vehicle terminal may be equipped with a trained deep learning model for generating a collection confidence level of the first lane line information when collecting the first lane line information. After that, the first confidence level of the first lane line information can be calculated according to the number of times the first lane line information is collected and the collection confidence level of the first lane line information. If the lane line information to be updated in the first map includes historical lane line information, the historical lane line information and the first lane line information can be compared. If there is information missing in the first lane line information compared with the historical lane line information, the first confidence level can be calculated according to the following formula 1:
[0072] N k =N k-1 -(100 - N k-1 )×10% (Formula 1)
[0073] In Formula 1, k is the number of times the first lane line information is collected, and k≥1. N k is the first confidence level of the first lane line information collected k times, N0 is the collection confidence level of the first lane line information, and 10% is the reduction index of the collection confidence level.
[0074] For example, if the acquisition confidence of the lane line element for which the lane line information is to be updated is 99, the confidence of the first lane line data not acquired once is 98.9; the confidence of the first lane line data not acquired 10 times is 97.4; the confidence of the first lane line data not acquired 40 times is 54.7.
[0075] If the lane line information to be updated is empty, or there is no information loss in the first lane line information compared to the historical lane line information, the first confidence of the first lane line information can be calculated based on the acquisition times of the first lane line information according to the normal distribution method. Obviously, the first confidence can usually be lower than the acquisition confidence.
[0076] Step 103, when the first confidence is greater than or equal to the first threshold, parse the first lane line information to obtain the first vector data of the first lane line information.
[0077] In the embodiments of the present application, vector data is a data type that describes geographical space information through geometric shapes and attribute data. The first threshold can be set. When the first confidence of the first lane line information is greater than or equal to the first threshold, the first lane line information can be parsed according to some image processing methods, so as to obtain the first vector data of the first lane line information. For example, since lane lines are usually two-dimensional graphics in white or yellow, the method of threshold segmentation can be adopted to obtain the lane line shape information in the first lane line information; since the positions between lane lines can be fixed, the clustering method can be adopted to obtain the relative position information between each lane line, and so on. The lane line shape information and the relative position information between each lane line can be combined to form the first vector data of the first lane line information.
[0078] Step 104, update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
[0079] In the embodiments of the present application, the lane line information to be updated in the first map can be replaced and updated according to the lane line shape information and the relative position information between each lane line included in the first vector data. After the replacement and update are completed, the lane line information included in the first map is data-packed and integrated, so as to obtain a second map.
[0080] In an embodiment of the present application, first lane line information corresponding to a target driving trajectory is determined from lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map; based on the number of times the first lane line information is collected, a first confidence level of the first lane line information is calculated; in a case where the first confidence level is greater than or equal to a first threshold, the first lane line information is parsed to obtain first vector data of the first lane line information; and the lane line information to be updated in the first map is updated based on the first vector data to obtain a second map, so that the lane line information in the first map can be updated when the confidence level of the lane line information collected from the vehicle end is greater than the first threshold, improving the accuracy of the map update data.
[0081] Referring to Figure 2 , Figure 2 FIG. is a schematic flowchart of another map update method provided by an embodiment of the present application, and the method may include:
[0082] Step 201, obtain the trajectory length of the target driving trajectory.
[0083] In an embodiment of the present application, the length of the road section corresponding to the target driving trajectory in the first map may be obtained, and then, according to the scale of the first map, the length of the road section corresponding to the target driving trajectory may be converted, so as to obtain the trajectory length of the target driving trajectory.
[0084] For example, if the length of the road section corresponding to the target driving trajectory in the first map is 5 cm and the scale of the first map is 1:104, then the trajectory length of the target driving trajectory is 0.05×104 = 500 m.
[0085] Step 202, in a case where the trajectory length is less than or equal to a second threshold, determine the first lane line information corresponding to the target driving trajectory from the lane line information collected from each vehicle end.
[0086] In an embodiment of the present application, the trajectory length of the target driving trajectory may be compared with a second threshold set manually. In a case where the trajectory length of the target driving trajectory is less than or equal to the second threshold, the first lane line information corresponding to the target driving trajectory may be determined from the lane line information collected from each vehicle end, so as to avoid an excessive amount of data included in the first lane line information.
[0087] In an embodiment of the present application, if the track length of the target driving track is greater than the second threshold, the target driving track can be segmented to generate a new target driving track for subsequent processes. Specifically, if the track length of the target driving track is greater than the second threshold and less than twice the second threshold, the target driving track can be evenly divided into two segments; if the track length of the target driving track is greater than twice the second threshold and less than three times the second threshold, the target driving track can be evenly divided into three segments, and so on.
[0088] In a possible embodiment, the first lane line information can be segmented according to the historical segmentation information of the lane line information to be updated. The historical segmentation information may include segmentation feature points. The positions corresponding to the segmentation feature points included in the historical segmentation information can be found in the first lane line information as the segmentation feature points of the first lane line information, and then the first lane line information can be segmented according to the segmentation feature points of the first lane line information.
[0089] In an embodiment of the present application, by obtaining the track length of the target driving track, when the track length is less than or equal to the second threshold, the first lane line information corresponding to the target driving track is determined from the lane line information collected from each vehicle end, which can control the data volume of the first lane line information within a certain range, effectively reducing the data complexity of the first lane line information and improving the usability of the first lane line information.
[0090] Step 203, calculate the first confidence level of the first lane line information based on the number of acquisitions of the first lane line information.
[0091] In an embodiment of the present application, the implementation content of this step can refer to the embodiment content of step 102 and will not be elaborated here.
[0092] Optionally, step 203 may include the following sub-steps:
[0093] Sub-step 2031, perform data segmentation on the first vector data to obtain first topological information.
[0094] In an embodiment of the present application, since the lane line information is image information, the topological information may be the relative position information between the respective lane lines included in the lane line information. The first vector data may include the lane line shape information of the lane line information to be updated and the relative position information between the respective lane lines. The sum of the relative position information between the respective lane lines of the lane line information to be updated is the first topological information corresponding to the second vector data. It should be noted that the first topological information is an overall data and generally cannot be disassembled and segmented.
[0095] In an embodiment of the present application, the first vector data can be segmented into the relative position information between each lane line included in the first lane line information and the lane line shape information, and then the lane line shape information included in the first lane line can be discarded. Finally, the relative position information between each lane line included in the first lane line information can be used as the second topological information.
[0096] Sub-step 2032: Calculate the second confidence level of the first topological information based on the number of acquisitions of the first lane line information, and obtain the first confidence level of the first lane line information.
[0097] In an embodiment of the present application, the first topological information may have an initial confidence level, and the initial confidence level of the first topological information may be the same as the initial confidence level of the first lane line information. The calculation method of the second confidence level of the first topological information may be similar to the calculation method of the first confidence level of the first lane line information, and reference may be made to the content of the embodiment in step 102. After calculating the second confidence level of the first topological information, the second confidence level of the first topological information may be determined as the first confidence level of the first lane line information.
[0098] Optionally, sub-step 2032 may include the following sub-steps:
[0099] Sub-step A1: Obtain the initial confidence level of the first topological information; wherein, the initial confidence level is generated by a trained deep learning model when each vehicle terminal acquires the first lane line information.
[0100] In an embodiment of the present application, the initial confidence level of the first lane line information may be used as the initial confidence level of the first topological information, which is generated by a trained deep learning model when each vehicle terminal acquires the first lane line information, and represents the acquisition accuracy of the first lane line information.
[0101] Sub-step A2: Use the topological information corresponding to the lane line information to be updated as the clustering center, and cluster the first topological information to obtain the second topological information with successful clustering and the third topological information with failed clustering.
[0102] In an embodiment of the present application, the lane line information to be updated can be parsed, so that the topological information corresponding to the lane line information to be updated can be obtained. Then, the topological information corresponding to the lane line information to be updated can be used as the clustering center to cluster the first topological information. Since the first topological information is the topological information corresponding to the actually acquired lane line information, the first topological information may include topological information different from the topological information corresponding to the lane line information to be updated. Therefore, after clustering, the second topological information with successful clustering and the third topological information with failed clustering can be obtained. It should be noted that if the lane line information to be updated is empty, all the first topological information may fail to cluster.
[0103] Sub-step A3: Calculate the third confidence level of the third topological information based on the number of acquisitions of the lane line information and the initial confidence level, to obtain the second confidence level of the first topological information.
[0104] In the embodiments of the present application, the second topological information with successful clustering is the same as the topological information corresponding to the lane line information to be updated. Therefore, there is no need to update the second topological information. At this time, the third confidence level of the third topological information can be calculated, and the calculation formula is shown in Equation 2 below:
[0105] P(A n ) = P(A n-1 ) + P(x n ) / K (Equation 2)
[0106] In Equation 2, A is the lane line element collected, n is the number of acquisitions of the lane line element, and n≥1. A n represents the lane line element A that has been collected n times. P(A n ) is the confidence level of the lane line element collected n times. P(x n ) is the average value of the initial confidence levels of the lane line information corresponding to the third topological information. K = 20, which is a preset constant. Among them, it can be set that P(A0) = 0, and the upper limit value of P(A n ) is set to 100.
[0107] After calculating the third confidence level of the third topological information, the third confidence level can be used as the first confidence level of the first lane line information.
[0108] In the embodiments of the present application, by obtaining the initial confidence level of the first topological information; wherein, the initial confidence level is generated by each vehicle terminal through a trained deep learning model when collecting the first lane line information. Using the topological information corresponding to the lane line information to be updated as the clustering center, clustering the first topological information to obtain the second topological information with successful clustering and the third topological information with failed clustering. Based on the number of acquisitions of the lane line information and the initial confidence level, calculating the third confidence level of the third topological information to obtain the second confidence level of the first topological information, the topological information that needs to be updated can be screened out according to the clustering method to update the first map, improving the accuracy and efficiency of map updating.
[0109] In the embodiments of the present application, by performing data segmentation on the first vector data to obtain the first topological information, and calculating the second confidence level of the first topological information based on the number of acquisitions of the first lane line information to obtain the first confidence level of the first lane line information, the first topological information of the first lane line information can be obtained and the first topological information can be used as the first confidence level of the first lane line information, improving the usability of the first confidence level.
[0110] Step 204: When the first confidence level is greater than or equal to the first threshold, parse the first lane line information to obtain first vector data of the first lane line information.
[0111] In the embodiments of the present application, the implementation content of this step can refer to the embodiment content of step 103, which will not be elaborated here.
[0112] Step 205: Update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
[0113] In the embodiments of the present application, the implementation content of this step can refer to the embodiment content of step 104, which will not be elaborated here.
[0114] Optionally, step 205 may include the following sub-steps:
[0115] Sub-step 2051: Determine second vector data of the lane line information to be updated from the first map.
[0116] In the embodiments of the present application, the second vector data of the lane line information to be updated can be determined from the first map by the same method as obtaining the first vector data. The relevant implementation content can refer to the embodiment content of step 103, which will not be elaborated here.
[0117] Sub-step 2052: Compare the second vector data with the first vector data to obtain first difference data corresponding to the first vector data and second difference data corresponding to the second vector data.
[0118] In the embodiments of the present application, the data at the same positions of the second vector data and the first vector data can be compared, so that the same data and difference data between the second vector data and the first vector data can be obtained. Among the difference data, the first difference data corresponding to the first vector data and the second difference data corresponding to the second vector data can be included.
[0119] Sub-step 2053: Delete the second difference data from the second vector data and add the first difference data to update the lane line information to be updated in the first map to obtain the second map.
[0120] In the embodiments of the present application, the second difference data in the second vector data can be deleted, then the first difference data is added to the second vector data, and an association is established with the data in the second vector data that has not been deleted, so as to complete the update of the second vector data. After that, the lane line information to be updated in the first map can be updated according to the updated second vector data to obtain the second map.
[0121] In an embodiment of the present application, by determining second vector data of lane line information to be updated from a first map, comparing the second vector data with the first vector data, obtaining first difference data corresponding to the first vector data and second difference data corresponding to the second vector data, deleting the second difference data from the second vector data and adding the first difference data, so as to update the lane line information to be updated in the first map, and obtaining a second map, the second vector data corresponding to the lane line information to be updated can be updated by the first difference data of the first vector data, improving the accuracy of map update.
[0122] Sub-step 2054: Determine the relative positions between the lane lines included in the first lane line information from the first vector data.
[0123] In an embodiment of the present application, since the first vector data includes the lane line shape information of the first lane line information and the relative position information between each lane line, therefore, the relative positions between each lane line included in the first lane line information can be determined from the first vector data.
[0124] Sub-step 2055: Update the lane line information to be updated in the first map based on the relative positions and the lane lines corresponding to the relative positions, so as to obtain a second map.
[0125] In an embodiment of the present application, according to the relative positions between each lane line, the lane line information corresponding to the relative positions in the lane line information to be updated in the first map can be found, and then each lane line in the lane line information to be updated can be overwritten and updated according to each lane line information in the first lane line information corresponding to the relative positions. Among them, each lane line to be updated can be covered only by the lane line at the corresponding position. After the update is completed, the lane line information is integrated with other data of the first map to obtain the second map.
[0126] In an embodiment of the present application, by determining the relative positions between the lane lines included in the first lane line information from the first vector data, and updating the lane line information to be updated in the first map based on the relative positions and the lane lines corresponding to the relative positions, so as to obtain a second map, the lane line information to be updated in the first map can be updated according to the relative positions between the lane lines included in the first vector data and each lane line, avoiding separate updates for each lane line and improving the efficiency of map update.
[0127] Sub-step 2056: When there is no lane line information to be updated corresponding to the target driving trajectory in the first map, based on the position information corresponding to the target driving trajectory in the first map, add the lane line information corresponding to the first vector data into the first map to obtain the second map.
[0128] In the embodiments of the present application, when there is no lane line information to be updated corresponding to the target driving trajectory in the first map, that is, when the lane line information to be updated is empty, the lane line information corresponding to the first vector data can be added to the position corresponding to the target driving trajectory in the first map based on the position information corresponding to the target driving trajectory in the first map, so that the second map can be obtained.
[0129] In the embodiments of the present application, by adding the lane line information corresponding to the first vector data into the first map based on the position information corresponding to the target driving trajectory in the first map when there is no lane line information to be updated corresponding to the target driving trajectory in the first map to obtain the second map, the first map can be updated when there is no lane line information to be updated corresponding to the target driving trajectory in the first map, improving the usability of the map update method.
[0130] Refer to Figure 3 , Figure 3 It is a flowchart of a specific implementation manner of a map update method provided by an embodiment of the present application. In the figure, first, the confidence of the first lane line can be calculated. When the confidence is greater than or equal to the first threshold, the data is parsed to obtain vector data. Then, the vector data can be segmented according to the segmentation information of the historical map to obtain segmented data. Then, the segmented data can be clustered according to the clustering method of the historical map. After that, the data with clustering failure is aggregated with the historical map to update the historical map. After the update is completed, the map is published, and the updated map is added to the historical map database for the next data segmentation.
[0131] Refer to Figure 4 , Figure 4 It is a schematic flowchart of a lane line topology generation method provided by an embodiment of the present application. In the figure, first, the process can be started, then the historical map data is read. Then, the segmentation points of the historical map are fused with the segmentation points corresponding to the current data collected by the vehicle terminal. Then, the current data collected by the vehicle terminal can be segmented according to the segmentation points. After the segmentation is completed, the lane line topology of each segment of data can be generated. After the lane line topology is generated, the process can be ended.
[0132] Refer to Figure 5 , Figure 5The logic block diagram of a map update device provided by an embodiment of the present application. The map update device 500 may include:
[0133] A determination module 501, configured to determine first lane line information corresponding to a target driving trajectory from lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to lane line information to be updated in a first map;
[0134] A calculation module 502, configured to calculate a first confidence level of the first lane line information based on the number of times the first lane line information is collected;
[0135] An analysis module 503, configured to analyze the first lane line information to obtain first vector data of the first lane line information when the first confidence level is greater than or equal to a first threshold;
[0136] An update module 504, configured to update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
[0137] Optionally, the calculation module 502 includes:
[0138] A segmentation sub-module, configured to perform data segmentation on the first vector data to obtain first topology information;
[0139] A calculation sub-module, configured to calculate a second confidence level of the first topology information based on the number of times the first lane line information is collected, to obtain the first confidence level of the first lane line information.
[0140] Optionally, the calculation sub-module includes:
[0141] A first acquisition unit, configured to acquire an initial confidence level of the first topology information; wherein, the initial confidence level is generated by a trained deep learning model when each vehicle end collects the first lane line information;
[0142] A clustering unit, configured to cluster the first topology information with the topology information corresponding to the lane line information to be updated as a clustering center, to obtain second topology information with successful clustering and third topology information with failed clustering;
[0143] A calculation unit, configured to calculate a third confidence level of the third topology information based on the number of times the lane line information is collected and the initial confidence level, to obtain the second confidence level of the first topology information.
[0144] Optionally, the update module 504 includes:
[0145] A first determination sub-module, configured to determine second vector data of the lane line information to be updated from the first map;
[0146] A comparison sub-module, configured to compare the second vector data with the first vector data to obtain first difference data corresponding to the first vector data and second difference data corresponding to the second vector data;
[0147] A first update sub-module, configured to delete the second difference data from the second vector data and add the first difference data, so as to update the lane line information to be updated in the first map to obtain the second map.
[0148] Optionally, the update module 504 includes:
[0149] A second determination sub-module, configured to determine the relative positions between the lane lines included in the first lane line information from the first vector data;
[0150] A second update sub-module, configured to update the lane line information to be updated in the first map based on the relative positions and the lane lines corresponding to the relative positions to obtain a second map.
[0151] Optionally, the determination module 501 includes:
[0152] A second acquisition sub-module, configured to acquire the trajectory length of the target driving trajectory;
[0153] A third determination sub-module, configured to determine the first lane line information corresponding to the target driving trajectory from the lane line information collected by each vehicle end when the trajectory length is less than or equal to a second threshold.
[0154] Optionally, the update module 504 includes:
[0155] A third update sub-module, configured to add the first lane line information corresponding to the first vector data into the first map based on the position information corresponding to the target driving trajectory in the first map to obtain the second map when there is no lane line information to be updated corresponding to the target driving trajectory in the first map.
[0156] In summary, the embodiments of the present application provide a map data update device, including: a determination module, configured to determine first lane line information corresponding to a target driving trajectory from the lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map; a calculation module, configured to calculate a first confidence level of the first lane line information based on the number of times the first lane line information is collected; an analysis module, configured to analyze the first lane line information to obtain first vector data of the first lane line information when the first confidence level is greater than or equal to a first threshold; and an update module, configured to update the lane line information to be updated in the first map based on the first vector data to obtain a second map, which can update the lane line information in the first map when the confidence level of the lane line information collected from the vehicle end is greater than the first threshold, thereby improving the accuracy of the map update data.
[0157] As Figure 6 shown, the embodiments of the present application further provide an electronic device M00, including a processor M01 and a memory M02. A program or instruction that can run on the processor M01 is stored on the memory M02. When the program or instruction is executed by the processor M01, it implements each step of the above-mentioned map update method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.
[0158] In an embodiment of the present application, the memory M02 can be used to store software programs and various data. The memory M02 mainly includes a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area can store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory M02 can include a volatile memory or a non-volatile memory, or the memory M02 can include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory M02 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.
[0159] The processor M01 can include one or more processing units; optionally, the processor M01 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and applications, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor M01.
[0160] The embodiments of the present application further provide an electronic device, including the map update device as described above, for implementing each process of the above map update method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.
[0161] The embodiments of the present application further provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiment of the map update method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.
[0162] Wherein, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disc, etc.
[0163] The embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement each process of the above-mentioned embodiment of the map update method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.
[0164] It should be understood that the chip involved in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system or system-on-chip, etc.
[0165] The embodiments of the present application provide a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement each process of the above-mentioned embodiment of the map update method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.
[0166] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the methods and devices in the embodiments of the present application are not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.
[0167] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the related technology, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.
[0168] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.
Claims
1. A method for map updating, characterized in that, The method includes: Determining first lane line information corresponding to a target driving trajectory from lane line information collected from each vehicle end; wherein, the target driving trajectory corresponds to lane line information to be updated in a first map; Calculating a first confidence level of the first lane line information based on the number of times the first lane line information is collected; When the first confidence level is greater than or equal to a first threshold, parsing the first lane line information to obtain first vector data of the first lane line information; Updating the lane line information to be updated in the first map based on the first vector data to obtain a second map.
2. The method according to claim 1, wherein The calculating the first confidence level of the first lane line information based on the number of times the first lane line information is collected includes: Performing data segmentation on the first vector data to obtain first topological information; Calculating a second confidence level of the first topological information based on the number of times the first lane line information is collected to obtain the first confidence level of the first lane line information.
3. The method according to claim 2, characterized in that, The calculating the second confidence level of the first topological information based on the number of times the first lane line information is collected includes: Obtaining an initial confidence level of the first topological information; wherein, the initial confidence level is generated by a trained deep learning model when each vehicle end collects the first lane line information; Taking the topological information corresponding to the lane line information to be updated as a clustering center, clustering the first topological information to obtain second topological information with successful clustering and third topological information with failed clustering; Calculating a third confidence level of the third topological information based on the number of times the lane line information is collected and the initial confidence level to obtain the second confidence level of the first topological information.
4. The method according to claim 1, characterized in that, The updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes: Determining second vector data of the lane line information to be updated from the first map; Comparing the second vector data with the first vector data to obtain first difference data corresponding to the first vector data and second difference data corresponding to the second vector data; Deleting the second difference data from the second vector data and adding the first difference data to update the lane line information to be updated in the first map to obtain the second map.
5. The method according to claim 1, characterized in that, The updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes: Determining the relative positions between lane lines included in the first lane line information from the first vector data; Updating the lane line information to be updated in the first map based on the relative positions and the lane lines corresponding to the relative positions to obtain the second map.
6. The method according to claim 1, characterized in that, The determining first lane line information corresponding to a target driving trajectory from lane line information collected from each vehicle end includes: Obtaining the trajectory length of the target driving trajectory; When the trajectory length is less than or equal to a second threshold, determining the first lane line information corresponding to the target driving trajectory from lane line information collected from each vehicle end.
7. The method according to claim 1, wherein Updating the lane line information to be updated in the first map based on the first vector data to obtain a second map includes: In the case where there is no lane line information to be updated corresponding to the target driving trajectory in the first map, based on the position information corresponding to the target driving trajectory in the first map, adding the first lane line information corresponding to the first vector data into the first map to obtain the second map.
8. A map update device, characterized in that, The device includes: A determination module, configured to determine the first lane line information corresponding to the target driving trajectory from the lane line information collected by each vehicle terminal; wherein, the target driving trajectory corresponds to the lane line information to be updated in the first map; A calculation module, configured to calculate a first confidence level of the first lane line information based on the number of times the first lane line information is collected; An analysis module, configured to analyze the first lane line information to obtain first vector data of the first lane line information when the first confidence level is greater than or equal to a first threshold; An update module, configured to update the lane line information to be updated in the first map based on the first vector data to obtain a second map.
9. An electronic device, characterized in that, Including the map update device according to claim 8, for implementing the map update method according to any one of claims 1 to 7.
10. A readable storage medium, characterized in that, When the instructions in the readable storage medium are executed by a processor of an electronic device, the electronic device is caused to execute the map update method according to any one of claims 1 to 7.