Method, apparatus, and autonomous driving system for updating a navigation map

Abstract

The method, device and autonomous driving system for updating a navigation map provided by this application first obtain the trajectory point data of each floating vehicle and the road network data; then, based on grids and direction angle intervals, perform correlation statistics on the trajectory point data and the road network data to obtain road trajectory heat; wherein, the road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road and the passing ratio of the road in each road direction; finally, update the road direction and road construction status of the roads in the navigation map according to the road trajectory heat, thereby realizing the determination of road attributes including road direction and road construction status by using trajectory point data and road network data, and thus updating the navigation map using the obtained road attributes, effectively improving the timeliness of road attributes in the navigation map and also being beneficial to improving the navigation quality of the navigation map.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of autonomous driving technology, and in particular, to a method and device for updating a navigation map and an autonomous driving system. Background Art

[0002] A navigation map is an electronic map used to guide the travel routes of vehicles and pedestrians. For a navigation map, the accuracy of road attributes including road directions and road construction status will seriously affect the route guidance quality of the navigation map.

[0003] In the prior art, for obtaining information on changes in road attributes, such as a road being in a closed construction state due to construction, or information such as a road changing from one-way to two-way due to a change in traffic policies, generally comes from public information, such as news messages.

[0004] However, such a method is difficult to meet the timeliness requirements for changes in road attributes such as road directions and road construction status in the navigation map, and it is easy to have problems such as poor navigation quality of the navigation map due to delays in updating road attributes. Summary of the Invention

[0005] In view of the above problems, the present application provides a method and device for updating a navigation map and an autonomous driving system to solve the above problems.

[0006] In a first aspect, the present application provides a method for updating a navigation map, including:

[0007] Obtaining trajectory point data of each floating car and road network data;

[0008] Based on grids and direction angle intervals, performing correlation statistics on the trajectory point data and the road network data to obtain road trajectory heat; wherein, the road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road, and the traffic ratio of the road in each road direction;

[0009] Updating the road direction and road construction status of the road in the navigation map according to the road trajectory heat.

[0010] In a second aspect, the present application provides a device for updating a navigation map, including:

[0011] A data acquisition module, configured to obtain trajectory point data of each floating car and road network data;

[0012] A road trajectory heat acquisition module, configured to perform correlation statistics on the trajectory point data and the road network data based on grids and direction angle intervals to obtain road trajectory heat; wherein, the road trajectory heat includes the number of trajectory point data corresponding to different road directions of a road, and the traffic ratio of the road in each road direction.

[0013] An update module, configured to update the road direction and road construction status of a road in a navigation map according to the road trajectory heat.

[0014] In a third aspect, the present application provides an autonomous driving system, including: an update device for a navigation map and an autonomous driving vehicle;

[0015] Wherein, the update device for the navigation map updates the navigation map according to the navigation map update method described in any one of the foregoing first aspects, and sends the updated navigation map to the autonomous driving vehicle; the autonomous driving vehicle performs an autonomous driving task according to the received navigation map.

[0016] In a fourth aspect, the present application provides an electronic device, including: at least one processor and a memory;

[0017] The memory stores computer execution instructions;

[0018] The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method described in the first aspect.

[0019] In a fifth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored, and when a processor executes the computer execution instructions, the method described in the first aspect is implemented.

[0020] In a sixth aspect, the present application provides a computer program product, including computer instructions, characterized in that when the computer instructions are executed by a processor, the method described in the first aspect is implemented.

[0021] The method, device, and autonomous driving system for updating a navigation map provided in this application first obtain the trajectory point data of each floating vehicle and the road network data, and then perform correlation statistics on the trajectory point data and the road network data based on grids and angular range intervals to obtain the road trajectory heat. The road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road and the passing ratio of the road in each road direction. Finally, the road direction and road construction status of the roads in the navigation map are updated according to the road trajectory heat, thereby realizing the determination of road attributes including road direction and road construction status using the trajectory point data and the road network data, and then updating the navigation map using the obtained road attributes, effectively improving the timeliness of road attributes in the navigation map and also facilitating the improvement of the navigation quality of the navigation map. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic diagram of the network architecture on which this application is based;

[0024] Figure 2 It is a schematic flowchart of a method for updating a navigation map provided in an embodiment of the present application;

[0025] Figure 3 It is a schematic diagram of an angular range interval provided by this application;

[0026] Figure 4 It is a schematic diagram of the conversion processing process of a road provided by an implementation manner of this application;

[0027] Figure 5 It is a block diagram of the structure of a device for updating a navigation map provided in an embodiment of the present application;

[0028] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0030] A navigation map is an electronic map used to guide the driving routes of vehicles and pedestrians. For a navigation map, the accuracy of road attributes including road directions and road construction status will seriously affect the route guidance quality of the navigation map.

[0031] For obtaining information on changes in road attributes in a navigation map, such as information that a road is in a closed construction state due to construction, or a road changes from one-way to two-way due to changes in traffic policies, etc., generally comes from public information such as news messages. However, due to limited information acquisition channels, such a method is difficult to meet the timeliness requirements of the navigation map, and it is easy to have problems such as poor navigation quality of the navigation map due to delays in updating road attributes.

[0032] To address such problems, the prior art generally adopts the following two methods to update the navigation map:

[0033] One of them is a method of determining road attributes in a navigation map based on the heat of trajectory grids. In this method, by calculating the grid density of vehicle driving trajectories and road geographic data, the construction status of a certain road section is determined by monitoring the change in grid density, and this information is sent to other relevant in-vehicle terminals through a service for detouring.

[0034] Another method is to analyze the driving trajectory and the information of the construction road to determine whether the construction road meets the condition for lifting the construction, and when it is determined that the construction road has met the condition for lifting the construction, the relevant road information in the electronic map is correspondingly modified, and the construction attribute mark on the construction road is removed.

[0035] However, in the former method, on the one hand, since only the position information of trajectory points is used to calculate the trajectory density on the corresponding grid of the road, this will lead to incorrect matching of trajectory points at intersections or on roads with separated on- and off-ramps. On the other hand, due to the trajectory density on the corresponding grid, it can only confirm the presence and amount of trajectories occupying the grid range in units of "roads", but cannot distinguish and determine the presence and amount of trajectories on "the forward and reverse directions of the road", that is, the former method cannot identify changes in road directions.

[0036] In the latter method, since it is also based on undirected trajectory grid heat analysis, that is, it cannot identify road direction changes either; at the same time, the determination of the road construction status in this method is based on the satisfaction of preset conditions, so when there is no trajectory on a road, it is very difficult to distinguish whether the user's trajectory does not really cover the road or the user's trajectory does not cover the road due to changes in the road construction status. In other words, this method can only be used for the identification of the removal of road construction and cannot be applied to the identification of new road construction.

[0037] Based on the above problems, according to the embodiments of the present application, by using the trajectory point data of floating cars and road network data, and performing statistical processing on the data based on grids and direction angle intervals to obtain road trajectory heat, and then analyzing the road trajectory heat to determine the road direction and road construction status of the road. On the one hand, on the basis of rasterizing the trajectory point data and road network data, the present application also determines the corresponding direction angle interval of the data, so that it can be determined whether the trajectory driving direction belongs to the forward road or the reverse road according to the direction angle interval, which is convenient for identifying whether the road direction has changed. On the other hand, through the grid processing based on the direction angle region and data, the trajectory point data can be statistically processed according to the forward and reverse directions of the road to obtain the forward and reverse road trajectory heat, and the change of the road trajectory heat can be monitored to effectively identify different road construction status changes such as new road construction and removal of road construction. That is to say, in the present application, by comparing with the road direction and road construction status of the road in the navigation map, it can be confirmed which roads' road attributes have changed, so that the roads in the navigation map can be updated in time based on the change of the road attributes, effectively improving the timeliness of the navigation map.

[0038] Reference Figure 1 , Figure 1 is a schematic diagram of a network architecture on which the present application is based. The Figure 1 shown network architecture may specifically include a floating car 1 and a server 2.

[0039] Among them, the floating car 1 may specifically be a bus and a taxi equipped with an in-vehicle GPS positioning device and driving on the urban main road. During the driving of the floating car 1, the in-vehicle GPS positioning device installed on it will record information such as the vehicle position, heading, and speed to obtain the trajectory point data of the floating car. Through the network, the floating car 1 will upload its own trajectory point data to the server 2 for the server 2 to analyze and use.

[0040] The server 2 can specifically be an independent server or a server cluster set in the cloud, which can be used to provide application services and application support related to the navigation map. For the server 2, it can be used to store, process, and update data related to the navigation map to ensure that the application client of the navigation map can provide corresponding navigation services for users. Among them, in this application, an update device for the navigation map is also carried on the server 2. The update device will use the trajectory point data uploaded by the floating vehicle 1 received by the server 2, combine it with the road network data already stored in the server 2, and based on the update method provided in this application, process the relevant data to realize the update of the navigation map in the server 2.

[0041] Based on the foregoing network architecture, in a first aspect, referring to Figure 2 , Figure 2 is a schematic flowchart of a method for updating a navigation map provided by an embodiment of this application.

[0042] The method for updating a navigation map provided by an embodiment of this application includes:

[0043] Step 201, obtain the trajectory point data and road network data of each floating vehicle.

[0044] Step 202, based on the grid and the direction angle interval, perform correlation statistics on the trajectory point data and the road network data to obtain the road trajectory heat; wherein, the road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road, and the passing ratio of the road in each road direction.

[0045] Step 203, update the road direction and road construction status of the roads in the navigation map according to the road trajectory heat.

[0046] It should be noted that the execution subject of the method for updating the navigation map provided in this example is the update device of the navigation map, and this update device is integrated or installed in Figure 1 the server 2 shown to realize the update of the navigation map carried on the server 2.

[0047] Among them, the trajectory point data of the floating vehicle will be uploaded to the server in real time or regularly through the network, and the update device will obtain this trajectory point data through the server. The trajectory point data can specifically be information such as the vehicle position, heading, timestamp, and speed regularly recorded by the GPS positioning device of the floating vehicle during driving. Table 1 shows an example of the trajectory point data of a floating vehicle.

[0048] Table 1

[0049]

[0050] As shown in Table 1, the trajectory point data may specifically include information such as floating car ID, vehicle position, heading, and timestamp.

[0051] Among them, the floating car ID is used to distinguish the floating car to which the trajectory point data belongs. Exemplarily, the floating car ID may specifically adopt identity information such as license plate information and / or engine identification. The vehicle position is used to represent the real geographical location of the floating car. Exemplarily, the vehicle position may specifically be represented by longitude and latitude coordinates composed of an X coordinate and a Y coordinate. Of course, other coordinate forms may also be used. The heading is used to represent the sailing direction of the floating car, and can also be understood as the forward direction of the floating car. The timestamp is used to represent the generation time of the trajectory point data.

[0052] The road network data is data used to represent the road position and identity after the navigation map is generated. This road network data is generally pre-collected and stored in the server. The update device can obtain this road network data through the server.

[0053] Among them, the road network data may specifically include the road ID of each road in the navigation map and the line geometry coordinates of the road. Generally speaking, the line geometry coordinates are represented by the geographical coordinates of the road, such as longitude and latitude coordinates, etc. There are a series of coordinate sequences in the line geometry coordinates of the road, and each coordinate in the coordinate sequence will be distributed along the road.

[0054] Exemplarily, the road network data can be expressed as: the road ID (LINK_PID) is 13348246; the line geometry coordinates (LINESTRING) are (109.25642 23.71986, 109.2563 23.71994, 109.25592 23.7202).

[0055] Subsequently, as described in step 202, in order to accurately identify the road direction and road construction status of the road, in the embodiment of the present application, the update device will use the grid and direction angle interval as the association parameters during data association statistics to determine the heat situation of the road in different road directions. The heat situation of the road can be represented by the number of trajectory point data distributed on the road and the traffic ratio of the road in different road directions.

[0056] Specifically, the realization of the association can be divided into the following steps:

[0057] Step 2021: Perform trajectory heat statistics processing on each trajectory point data to obtain a trajectory heat result, where the trajectory heat result includes the number of trajectory point data in different grids and different direction angle intervals.

[0058] Step 2022: Perform data conversion processing on the road network data of each road to obtain the road conversion data of each road. The road conversion data of each road includes the grid corresponding to the road and the angular range corresponding to the road in different road directions.

[0059] Step 2023: Use the trajectory heat result and the grids and angular ranges in the road conversion data of each road as correlation conditions to obtain the road trajectory heat.

[0060] Among them, between Step 2021 and Step 2022, synchronous processing or asynchronous processing can be adopted. When asynchronous processing is adopted between Step 2021 and Step 2022, the execution order between them can be to execute Step 2021 first and then Step 2022; or it can be to execute Step 2022 first and then Step 2021; this application will not impose any restrictions on this.

[0061] Furthermore, in Step 2021, in order to perform correlation statistics based on grids and angular ranges on the data, the update device will first preprocess each trajectory point data to facilitate the final statistical processing to obtain the trajectory heat result.

[0062] Among them, during the trajectory heat statistical processing, various data conversion processes will be first performed on the trajectory point data to facilitate subsequent statistics. This may include coordinate conversion processing of geographical coordinates and angular conversion processing of heading information.

[0063] Specifically, for trajectory point data, as shown in Table 1, it generally uses longitude and latitude coordinates to represent geographical coordinates. And to facilitate subsequent statistics and analysis, in this embodiment, the longitude and latitude coordinates will be converted to obtain the grid corresponding to the trajectory point data. In the "12-level Mercator coordinate", the map is divided into large grids and small grids. One large grid is a square area approximately 10240m * 10240m, and each large grid is evenly divided into 1024 * 1024 small grids, and each small grid is approximately a square area of 10m * 10m.

[0064] By using the conversion relationship between longitude and latitude coordinates and the grids of 12-level Mercator coordinates, the geographical coordinates in the trajectory point data can be converted to determine the grid corresponding to the trajectory point data.

[0065] Exemplarily, the WGS84 longitude and latitude coordinates (109.27117, 23.69368) can be converted into 12-level Mercator coordinates (3291_1770#269_398), where 3291 corresponds to the large grid X, 1770 corresponds to the large grid Y, 269 corresponds to the small grid X, and 398 corresponds to the small grid Y.

[0066] Meanwhile, the updating device also needs to perform a direction angle conversion process on the heading information in the trajectory point data to determine the direction angle interval corresponding to the trajectory point data.

[0067] Specifically, the direction angle interval refers to eight intervals obtained by equally dividing a full circle angle (360°) into eight parts and then dividing them according to due north, northeast, due east, southeast, due south, southwest, due west, and northwest.

[0068] Among them, for each direction angle interval, there corresponds a certain range of heading angles, and the corresponding relationship is shown in Table 2 below.

[0069] Table 2

[0070]

[0071] Figure 3 For the schematic diagram of a direction angle interval provided by this application, in combination with Figure 3 and as shown in Table 2, after obtaining each piece of trajectory point data, based on the corresponding relationship between the direction angle intervals shown in Table 2 and Figure 4 the direction angle conversion of the heading information in the trajectory point data can be performed to obtain the direction angle interval corresponding to the trajectory point data.

[0072] Correspondingly, the updating device needs to perform the above-mentioned coordinate conversion process based on geographical coordinates and the direction angle conversion process based on the heading for each piece of trajectory point data to determine the grid and direction angle interval corresponding to each piece of trajectory point data.

[0073] Then, taking each type of grid and each type of direction angle interval as key information, the quantity of each piece of trajectory point data is counted to obtain the trajectory heat map result. Table 3 shows a kind of trajectory heat map result.

[0074] Table 3

[0075]

[0076] As shown in Table 3, the number of floating cars with a direction angle interval of 7 at the geographical location where the large grid is 3291_1770 and the small grid is 269_398 on September 20, 2019 is 2; the number of floating cars with a direction angle interval of 6 at the geographical location where the large grid is 3291_1770 and the small grid is 261_391 on September 20, 2019 is 1.

[0077] Through the above processing, the trajectory heat map result with each grid and each direction angle interval as statistical conditions can be obtained.

[0078] Synchronous or asynchronous, the updating device will also perform data conversion processing on the road network data of each road as described in step 2022 to obtain the road conversion data of each road.

[0079] Similar to the conversion of the aforementioned trajectory point data, for road network data, through data conversion processing, the road network data can be converted into data with grids and direction angle intervals as statistical conditions.

[0080] Specifically, the updating device will first determine the longitude and latitude point sequences of each road according to the road network data of each road. Then, similar to the conversion processing of the trajectory point data described above, the updating device needs to perform grid conversion processing and heading conversion processing on the longitude and latitude point sequences of each road to obtain the grids and direction angle intervals corresponding to each road.

[0081] It should be noted that since this application needs to confirm and identify the road directions of roads, therefore, in the conversion processing, it is necessary to perform a conversion processing in the forward road direction of the road and a conversion processing in the reverse road direction of the road, that is, perform grid conversion processing and heading conversion processing on the longitude and latitude point sequences of each road to obtain the grids and the direction angle intervals in the forward road direction corresponding to each road; and perform direction angle interval conversion processing on the direction angle intervals in the forward road direction of each road to obtain the direction angle intervals in the reverse road direction of each road.

[0082] Finally, the updating device will obtain the road conversion data of each road composed of the grids corresponding to each road, the direction angle intervals in the forward road direction, and the direction angle intervals in the reverse road direction.

[0083] Further, taking the aforementioned road as an example, the road label LINK_PID of a road in the map road network is 13348246, and the line geometry coordinates LINESTRING of the road are (109.25642 23.71986, 109.25632 23.71994, 109.25592 23.7202).

[0084] The line geometry coordinates of a road in the navigation map can be expressed as a sequence of longitude and latitude points (from the starting point to the ending point).

[0085] At this time, the updating device can perform grid conversion on the sequence of longitude and latitude points through two steps of "equidistant interpolation" and "calculating the heading between two points" to obtain the grid corresponding to the road. In this process, the grid distribution based on the aforementioned "12-level Mercator coordinates" can be used to determine the large grid and small grid corresponding to each sequence point in the sequence of longitude and latitude points.

[0086] Then, based on the angle between the line connecting two adjacent sequence points in the sequence of longitude and latitude points and the due north direction as the "heading angle" of the road, the direction angle interval of the road is determined. Among them, since the road is generally divided into the forward road direction and the reverse road direction, the direction from the starting point of the road to the end point is forward, and vice versa. For the same connection line, there is a certain correlation between its forward road direction and reverse road direction. The direction angle interval DRegion of the road in the forward road direction and the direction angle interval RRegion in the reverse road direction can be determined through the following formula.

[0087]

[0088] Through the above processing, road conversion data will be obtained. Figure 4 It is a schematic diagram of the conversion processing process of a road provided by an embodiment of the present application. As Figure 4 shown, it corresponds to the distribution of the road in each small grid under the large grid number 3291_1770. Combining Figure 4 the conversion results shown in Table 4 can be obtained.

[0089] Table 4

[0090]

[0091] As shown in Table 4, taking the road ID 13348246 as an example, the distribution of one of the sequence points on this road can represent that the large grid is 3291_1770 and the small grid is 91_61. Among them, the direction angle interval of the forward road direction is 7, and the direction angle interval of the reverse road direction is 3.

[0092] Through the method shown in Table 4, each piece of processed road data in the road network data can be represented to facilitate subsequent statistics.

[0093] After completing the processing of the trajectory point data and the road network data, the updating device will, as shown in step 2023, use the grid in the trajectory heat result and the grid and direction angle interval in the road conversion data of each road as the association condition to obtain the road trajectory heat.

[0094] Specifically, the updating device will first use the grid in the trajectory heat result and the grid in the road conversion data as the association condition to count the number of trajectory point data corresponding to each road in different direction angle intervals, and obtain the number of trajectory point data corresponding to different road directions of the road.

[0095] Then, according to the number of trajectory point data corresponding to different road directions of the road, determine the total number of trajectory point data corresponding to the entire road direction of the road.

[0096] Finally, according to the number of trajectory point data corresponding to different road directions of the road and the total number of trajectory point data corresponding to the whole road direction of the road, determine the traffic ratio of the road in each road direction.

[0097] For further illustration, Table 5 shows the road trajectory heat under a specified time dimension. Table 5 is only a schematic data table, and the data it is based on has nothing to do with the aforementioned Tables 1-4.

[0098] Table 5

[0099]

[0100] Regarding the number of trajectory point data corresponding to the forward road direction and the number of trajectory point data corresponding to the reverse road direction, it is first necessary to determine the trajectory point data that conforms to the grid and the forward direction angle interval or the reverse direction angle interval involved in the road from all the trajectory point data, and then count the number of these trajectory point data respectively to obtain the number of trajectory point data corresponding to the forward road direction and the number of trajectory point data corresponding to the reverse road direction.

[0101] The traffic ratio of the forward road direction can specifically be used to represent: on this road, when a floating car passes through this road, the ratio between the number of floating cars traveling in the forward road direction and the total number of floating cars traveling in both directions of the road.

[0102] That is, the traffic ratio of the forward road direction = the number of trajectory point data corresponding to the forward road direction / (the number of trajectory point data corresponding to the forward road direction + the number of trajectory point data corresponding to the reverse road direction).

[0103] Similarly, the traffic ratio of the reverse road direction can specifically be used to represent: on this road, when a floating car passes through this road, the ratio between the number of floating cars traveling in the reverse road direction and the total number of floating cars traveling in both directions of the road.

[0104] That is, the traffic ratio of the reverse road direction = the number of trajectory point data corresponding to the reverse road direction / (the number of trajectory point data corresponding to the forward road direction + the number of trajectory point data corresponding to the reverse road direction).

[0105] It should be particularly noted that when determining the road trajectory heat in this application, since the grid and the direction angle interval are used as the associated conditions at the same time to count the total number of trajectory point data, it can effectively and accurately count the total amount of data of the trajectory point data of the road that is prone to "ambiguity".

[0106] Among them, roads that are prone to "ambiguity" can be, for example, intersections. Generally, an intersection is an area formed by the intersection of multiple roads. When counting the total number of trajectory point data in this area, by using the direction angle interval in the trajectory heat result, it is possible to determine which road in the intersection the trajectory point is for.

[0107] For example, at a crossroads in the due east, south, west, and north directions (i.e., the direction angle intervals corresponding to the crossroads are 0, 2, 4, and 6 respectively), if the heading of a trajectory point is 89° (corresponding to the direction angle interval of 2), at this time, this trajectory point will be matched with the east-west road (i.e., the road with the direction angle intervals of 2 and 6), and the trajectory point will not be mis-matched to the north-south road (i.e., the road with the direction angle intervals of 0 and 4). That is to say, such a method will make the determined road trajectory heat more accurate.

[0108] After completing the above operations, the update device will execute step 203, that is, update the road direction and road construction status of the roads in the navigation map according to the road trajectory heat.

[0109] Among them, since the road trajectory heat already includes the number of trajectory point data corresponding to the road in different road directions, as well as information such as the passing ratio of the road in each road direction, by comparing this information with historical information, it is possible to determine whether the road direction and road construction status of the road have changed. Once the update device determines that the road direction and road construction status of the road are different from the historical road attributes, the road attributes in the navigation map can be updated accordingly to ensure the timeliness of the navigation map.

[0110] Of course, in an optional manner, only roads that meet a certain activity level will be counted into the road trajectory heat shown in Table 5, so as to avoid errors in trajectory heat statistics caused by too low road activity, and thus also avoid problems such as incorrect changes caused by changing the road attributes of roads with too low activity. Among them, the activity of the road can be specifically manifested as the number of trajectory point data corresponding to the grid where the road is located within a relatively long time period (and such roads with low activity can also be understood as remote roads with few floating cars passing by).

[0111] In order to determine whether the road direction and road construction status of the road have changed, in one method, a preset neural network model can be used to achieve this. Specifically, for step 203, it can specifically include:

[0112] Step 2031: Input the road trajectory heat into a preset road direction determination model and a preset road construction status determination model to obtain a road direction determination result and the road construction status determination result;

[0113] Step 2032: Update the road direction and road construction status of the roads in the navigation map according to the road direction determination result and the road construction status determination result.

[0114] In step 2031, a road direction determination model for determining the road direction and a road construction status determination model for determining the road construction status are set in the update device. Both of these two models can adopt existing neural network model architectures. By inputting each piece of information in the previously obtained road trajectory heat into these two models, the road direction determination result and the road construction status determination result as described in step 2032 can be obtained. And using these two results, the road attributes of the roads in the navigation map can be updated as described above.

[0115] Based on the above implementation manner, since the operation of the model generally consumes a large amount of resources, in this implementation manner, the road trajectory heat can also be initially screened to avoid the sharp increase in the amount of computation caused by inputting the road trajectory heat with unchanged road status into the model.

[0116] Specifically, before step 2031, it may further include:

[0117] Step 2030: Predict the road direction and road construction status of the road according to the road trajectory heat, and obtain the prediction result of the road direction and the prediction result of the road construction status;

[0118] If the prediction result of the road direction of the road is inconsistent with the road direction of the road in the navigation map, or if the road construction status of the road is inconsistent with the road construction status of the road in the navigation map, then execute step 2031, that is, the step of inputting the road trajectory heat into the preset road direction determination model and the preset road construction status determination model.

[0119] Specifically, the update device can predict the road direction of the road according to the passing ratio of each road direction in the road trajectory heat.

[0120] As described above, the passing ratio of the road direction is generally ratio data. Taking the passing ratio of the forward road direction as an example, when the ratio of the passing ratio of the forward road direction belongs to the interval (0.4, 0.6), the road direction of this road should be a two-way traffic state. In this state, the forward road direction activity shown by the number of trajectory point data in the forward road direction should be greater than the preset activity threshold, and at the same time, the reverse road direction activity shown by the number of trajectory point data in the reverse road direction should also be greater than the preset activity threshold.

[0121] When the ratio of the passing ratio in the forward road direction belongs to the interval of (0.9, 1], the road direction of the road is in the forward passing state. In this state, the forward road direction activity shown by the number of trajectory point data in the forward road direction should be greater than the preset activity threshold. At the same time, the reverse road direction activity shown by the number of trajectory point data in the reverse road direction should be less than the preset silent threshold.

[0122] When the ratio of the passing ratio in the forward road direction belongs to the interval of [0, 0.1), the road direction of the road is in the reverse passing state. In this state, the forward road direction activity shown by the number of trajectory point data in the forward road direction should be less than the preset silent threshold. At the same time, the reverse road direction activity shown by the number of trajectory point data in the reverse road direction should be greater than the preset activity threshold.

[0123] The above interval range can be specifically set according to the actual situation. This embodiment is only an example.

[0124] Through the above method, the road direction of the road can be simply predicted according to the trajectory heat result. Then, based on the predicted road direction, it is compared with the road direction marked in the original data of the navigation map. If the comparison result is inconsistent, it means that the road direction may have changed at this time. Then, in order to further accurately determine the corresponding change, the trajectory heat result can be input into the road direction determination model mentioned above for further determination. After determining that the road direction has changed, the road direction of the corresponding road in the navigation map is updated.

[0125] In an alternative embodiment, similar to the road direction prediction mentioned above, the road construction state of the road can also be predicted by using the number of trajectory point data corresponding to the road in different road directions in the road trajectory heat.

[0126] Specifically, by tracking the number of trajectory point data corresponding to the same road in different road directions over time, it can be known that when it is found that the total number of trajectory point data in all road directions of a certain road decreases sharply, and even the road activity characterized by the total number of its trajectory point data is lower than the preset silent threshold, it can be considered that the road has entered a road construction state such as "construction / closed / under construction".

[0127] On the contrary, when it is found that the total number of trajectory point data in all road directions of a certain road increases sharply, and even the road activity characterized by the total number of its trajectory point data is higher than the preset activity threshold, it can be considered that the road has entered a road construction state such as "normal".

[0128] Through the above method, the road construction status of a road can be simply predicted based on the trajectory heat map results. Then, based on the predicted road construction status, a comparison is made with the road construction status marked in the original data of the navigation map. If the comparison results are inconsistent, it indicates that the road construction status may have changed at this time. Subsequently, in order to further accurately determine the corresponding changes, the trajectory heat map results can be input into the road construction status determination model mentioned above for further determination. After determining that the road construction status has changed, the road construction status of the corresponding road in the navigation map is updated.

[0129] In addition, the two models mentioned in step 2031 above can be obtained through pre-training. In an alternative embodiment, the training of the above models can also use the data statistics method mentioned in step 202 above. That is, a large amount of trajectory point data and road network data for training are collected, and these trajectory point data and road network data for training are processed respectively using the processing method described in step 202 to obtain a training data set.

[0130] Meanwhile, in order to be used for the training of the models, the training data set also needs to include the real road attributes of the road, that is, the real road direction and the real road construction status corresponding to the training data set. These real road attributes can be obtained from publicly published information or by using the method of crowdsourcing collection and annotation.

[0131] After obtaining the training data set including data (trajectory point data and road network data for training) and annotations (real road direction and real road construction status), the training data set is input into the two models to be trained respectively for the training of corresponding objectives.

[0132] During the training process, the model will extract feature vectors from data of different dimensions based on its own training objectives. For example, monitoring indicators such as "the number of positive and negative trajectories, the proportion of active cells" matched by the road are extracted as several-dimensional features, combined with attributes of the road itself such as "direction, road type, road, length" and time series features such as "whether the monitoring day before / after the change is a working day". For each road and different mining themes, different-dimensional feature vectors can be transformed to generate a machine learning model for the objective, and a road direction determination model for determining the road direction and a road construction status determination model for determining the road construction status are obtained respectively.

[0133] The method for updating a navigation map provided by this application first obtains the trajectory point data of each floating car and the road network data, and then, based on grids and direction angle intervals, performs correlation statistics on the trajectory point data and the road network data to obtain the road trajectory heat. The road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road and the traffic ratio of the road in each road direction. Finally, according to the road trajectory heat, the road direction and road construction status of the roads in the navigation map are updated, thereby realizing the determination of road attributes including road direction and road construction status by using trajectory point data and road network data, and then updating the navigation map by using the obtained road attributes, effectively improving the timeliness of road attributes in the navigation map and also being beneficial to improving the navigation quality of the navigation map.

[0134] In a second aspect, corresponding to the method for updating a navigation map in the above embodiment, Figure 5 is a structural block diagram of an updating device for a navigation map provided by an embodiment of this application. For ease of description, only parts related to the embodiment of this application are shown. Referring to Figure 5 The updating device for the navigation map includes:

[0135] A data acquisition module 510, configured to acquire the trajectory point data of each floating car and the road network data;

[0136] A road trajectory heat acquisition module 520, configured to perform correlation statistics on the trajectory point data and the road network data based on grids and direction angle intervals to obtain the road trajectory heat. The road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road and the traffic ratio of the road in each road direction;

[0137] An updating module 530, configured to update the road direction and road construction status of the roads in the navigation map according to the road trajectory heat.

[0138] Optionally, the road trajectory heat acquisition module 520 is specifically configured to:

[0139] Perform trajectory heat statistics processing on each trajectory point data to obtain a trajectory heat result, where the trajectory heat result includes the number of trajectory point data under different grids and different direction angle intervals;

[0140] Perform data conversion processing on the road network data of each road to obtain the road conversion data of each road. The road conversion data of each road includes the grids corresponding to the road and the direction angle intervals corresponding to the road in different road directions;

[0141] Using the grid and direction angle intervals in the trajectory heat result and the road conversion data of each road as the association conditions, the road trajectory heat is obtained.

[0142] Optionally, the road trajectory heat acquisition module 520 is specifically configured to:

[0143] Using the grid in the trajectory heat result and the grid in the road conversion data as the association conditions, count the number of trajectory point data corresponding to each road in different direction angle intervals, and obtain the number of trajectory point data corresponding to the road in different road directions;

[0144] According to the number of trajectory point data corresponding to the road in different road directions, determine the total number of trajectory point data corresponding to the road in all road directions;

[0145] According to the number of trajectory point data corresponding to the road in different road directions and the total number of trajectory point data corresponding to the road in all road directions, determine the traffic ratio of the road in each road direction.

[0146] Optionally, the road trajectory heat acquisition module 520 is specifically configured to:

[0147] Perform coordinate conversion on the geographical coordinates in the trajectory point data to obtain the grid corresponding to the trajectory point data;

[0148] Perform direction angle conversion on the heading information in the trajectory point data to obtain the direction angle interval corresponding to the trajectory point data;

[0149] Count the number of trajectory point data in each grid and each direction angle interval to obtain the trajectory heat result.

[0150] Optionally, the road trajectory heat acquisition module 520 is specifically configured to:

[0151] Determine the longitude and latitude point sequence of each road according to the road network data of each road;

[0152] Perform grid conversion processing and heading conversion processing on the longitude and latitude point sequences of the roads to obtain the grids corresponding to the roads and the direction angle intervals of the forward road directions;

[0153] Perform direction angle interval conversion processing on the direction angle intervals of the forward road directions of the roads to obtain the direction angle intervals of the reverse road directions of the roads;

[0154] The grids corresponding to the roads, the direction angle intervals of the forward road directions, and the direction angle intervals of the reverse road directions constitute the road conversion data of the roads.

[0155] Optionally, the update module 530 is specifically configured to:

[0156] Input the road trajectory heat into a preset road direction determination model and a preset road construction status determination model to obtain a road direction determination result and the road construction status determination result;

[0157] Update the road direction and road construction status of the road in the navigation map according to the road direction determination result and the road construction status determination result.

[0158] Optionally, before the update module 530 inputs the road trajectory heat into a preset road direction determination model and a preset road construction status determination model to obtain a road direction determination result and the road construction status determination result, it is further used for:

[0159] Predict the road direction and road construction status of the road according to the road trajectory heat to obtain a predicted result of the road direction and a predicted result of the road construction status;

[0160] If the predicted result of the road direction of the road is inconsistent with the road direction of the road in the navigation map, or if the road construction status of the road is inconsistent with the road construction status of the road in the navigation map, then execute the step of inputting the road trajectory heat into a preset road direction determination model and a preset road construction status determination model.

[0161] Optionally, the update module 530 is specifically used for:

[0162] Predict the road direction of the road according to the passing ratio of each road direction in the road trajectory heat;

[0163] Predict the road construction status of the road according to the number of trajectory point data corresponding to the road in different road directions in the road trajectory heat.

[0164] The navigation map update device provided by the present application first obtains the trajectory point data of each floating vehicle and road network data; then, based on grids and direction angle intervals, statistically correlates the trajectory point data and the road network data to obtain road trajectory heat, where the road trajectory heat includes the number of trajectory point data corresponding to the road in different road directions and the passing ratio of the road in each road direction; finally, updates the road direction and road construction status of the road in the navigation map according to the road trajectory heat, thereby realizing the determination of road attributes including road direction and road construction status by using trajectory point data and road network data, and updating the navigation map by using the obtained road attributes, effectively improving the timeliness of road attributes in the navigation map and also facilitating the improvement of the navigation quality of the navigation map.

[0165] An embodiment of the present application further provides an autonomous driving system, including: an updating device for a navigation map and an autonomous driving vehicle;

[0166] Wherein, the updating device for the navigation map updates the navigation map according to the method for updating the navigation map described in any one of the foregoing, and sends the updated navigation map to the autonomous driving vehicle; the autonomous driving vehicle executes an autonomous driving task according to the received navigation map.

[0167] The electronic device provided in this embodiment can be used to execute the technical solutions of the foregoing method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0168] Reference Figure 6 , which shows a schematic structural diagram of an electronic device 900 suitable for implementing the embodiments of the present application. The electronic device 900 can be a terminal device or a media library. Among them, the terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs for short), tablet computers (PADs for short), portable multimedia players (PMPs for short), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0169] As Figure 6 shown, the electronic device 900 may include an updating device for a navigation map (such as a central processing unit, a graphics processing unit, etc.) 901, which can execute various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The updating device 901 for the navigation map, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0170] Typically, the following devices can be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, magnetic tapes, hard disks, etc.; and a communication device 909. The communication device 909 can allow the electronic device 900 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 6 an electronic device 900 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices can be alternatively implemented or had.

[0171] In particular, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the update device 901 of the navigation map, the above functions defined in the methods of the embodiments of the present application are executed.

[0172] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. And in this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0173] The above computer-readable medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0174] The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to execute the method shown in the above embodiments.

[0175] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or media library. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by connecting through an Internet service provider using the Internet).

[0176] A computer program product provided by this embodiment includes computer instructions, and the computer instructions are executed by a processor to perform the method described in any of the previous items. The implementation principle and technical effects are similar, and will not be elaborated here in this embodiment.

[0177] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0178] The units involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".

[0179] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, the types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0180] In the context of this application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be either a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. A method for updating a navigation map, characterized in that, Including: Obtaining the trajectory point data of each floating car and the road network data; Based on the grid and the direction angle interval, performing correlation statistics on the trajectory point data and the road network data to obtain the road trajectory heat; wherein, the road trajectory heat includes the number of trajectory point data corresponding to different road directions of the road, and the traffic ratio of the road in each road direction; Updating the road direction and the road construction status of the road in the navigation map according to the road trajectory heat.

2. The method for updating a navigation map according to claim 1, characterized in that, Based on the grid and the direction angle interval, performing correlation mapping on the trajectory point data and the road network data to obtain the road trajectory heat, including: Performing trajectory heat statistics processing on each trajectory point data to obtain a trajectory heat result, where the trajectory heat result includes the number of trajectory point data in different grids and different direction angle intervals; Performing data conversion processing on the road network data of each road to obtain the road conversion data of each road, where the road conversion data of each road includes the grid corresponding to the road, and the direction angle interval corresponding to different road directions of the road; Using the grid and the direction angle interval in the trajectory heat result and the road conversion data of each road as correlation conditions to obtain the road trajectory heat.

3. The update method according to claim 2, characterized in that The step of using the grid and the direction angle interval in the trajectory heat result and the road conversion data of each road as correlation conditions to obtain the road trajectory heat includes: Using the grid in the trajectory heat result and the grid in the road conversion data as correlation conditions, and statistically calculating the number of trajectory point data corresponding to each road in different direction angle intervals to obtain the number of trajectory point data corresponding to different road directions of the road; Determining the total number of trajectory point data corresponding to the entire road direction of the road according to the number of trajectory point data corresponding to different road directions of the road; Determining the traffic ratio of the road in each road direction according to the number of trajectory point data corresponding to different road directions of the road and the total number of trajectory point data corresponding to the entire road direction of the road.

4. The update method according to claim 2, wherein The step of performing trajectory heat statistics processing on each trajectory point data to obtain a trajectory heat result includes: Performing coordinate conversion on the geographic coordinates in the trajectory point data to obtain the grid corresponding to the trajectory point data; Performing direction angle conversion on the heading information in the trajectory point data to obtain the direction angle interval corresponding to the trajectory point data; Statistically calculating the number of trajectory point data in each grid and each direction angle interval to obtain the trajectory heat result.

5. The update method according to claim 2, wherein The step of performing data conversion processing on the road network data of each road to obtain the road conversion data of each road includes: Determining the longitude and latitude point sequence of each road according to the road network data of each road; Performing grid conversion processing and heading conversion processing on the longitude and latitude point sequence of each road to obtain the grid corresponding to each road and the direction angle interval of the forward road direction; Performing direction angle interval conversion processing on the direction angle interval of the forward road direction of each road to obtain the direction angle interval of the reverse road direction of each road; The grid corresponding to each road, the direction angle interval of the forward road direction, and the direction angle interval of the reverse road direction constitute the road conversion data of each road.

6. The update method according to any one of claims 1-5, characterized in that, Updating the road direction and road construction status of roads in the navigation map according to the road trajectory heat, including: Inputting the road trajectory heat into a preset road direction determination model and a preset road construction status determination model to obtain a road direction determination result and the road construction status determination result; Updating the road direction and road construction status of roads in the navigation map according to the road direction determination result and the road construction status determination result.

7. The update method according to claim 6, characterized in that Before the step of inputting the road trajectory heat into a preset road direction determination model and a preset road construction status determination model to obtain a road direction determination result and the road construction status determination result, it further includes: Predicting the road direction and road construction status of a road according to the road trajectory heat to obtain a prediction result of the road direction and a prediction result of the road construction status; If the prediction result of the road direction of the road is inconsistent with the road direction of the road in the navigation map, or if the road construction status of the road is inconsistent with the road construction status of the road in the navigation map, then execute the step of inputting the road trajectory heat into a preset road direction determination model and a preset road construction status determination model.

8. The update method according to claim 7, wherein The predicting the road direction and road construction status of a road according to the road trajectory heat includes: Predicting the road direction of a road according to the passing ratio of each road direction in the road trajectory heat; Predicting the road construction status of a road according to the number of trajectory point data corresponding to the road in different road directions in the road trajectory heat.

9. An update device for a navigation map, characterized in that, Including: A data acquisition module for acquiring trajectory point data of each floating car and road network data; A road trajectory heat acquisition module for performing correlation statistics on the trajectory point data and the road network data based on a grid and a direction angle interval to obtain road trajectory heat; wherein the road trajectory heat includes the number of trajectory point data corresponding to the road in different road directions, and the passing ratio of the road in each road direction; An update module for updating the road direction and road construction status of roads in the navigation map according to the road trajectory heat.

10. An autonomous driving system, characterized in that, Including: An update device for the navigation map and an autonomous driving vehicle; Among them, the update device for the navigation map updates the navigation map according to the navigation map update method according to any one of claims 1-8, and sends the updated navigation map to the autonomous driving vehicle; The autonomous driving vehicle will execute an autonomous driving task according to the received navigation map.

Images