Route planning method and device, computer equipment and storage medium

Abstract

The invention discloses an air route planning method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining the air route planning information of flight equipment and a grid map of the flight equipment, and enabling the grid map to comprise a plurality of grids; a first risk parameter and a second risk parameter of each grid in the multiple grids are determined, the first risk parameter is used for representing the ground risk level of each grid, and the second risk parameter is used for representing the air risk level of each grid; based on the first risk parameter and the second risk parameter, determining a comprehensive risk parameter of each grid; and performing route planning on the flight equipment based on the route planning information and the comprehensive risk parameters to obtain a target route of the flight equipment. According to the embodiment of the invention, the ground risk level and the air risk level of each grid can be quantified, path planning is carried out in combination with the ground risk and the air risk, and the method is suitable for path planning of a large unmanned aerial vehicle.

Description

Technical Field

[0001] The present application relates to the technical field of route planning, and in particular to a route planning method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of computer technology, drones and autonomous aircraft and other flying equipment are widely used in all aspects of people's lives, such as drone logistics transportation, drone cruising, drone spraying of pesticides, etc. Flying equipment needs to plan routes in advance before performing flight missions. Existing route planning methods usually use the shortest path or fly around important facilities and important airspace to achieve route planning. Since the system reliability of large drones is not as high as that of civil airliners, the existing route planning methods are not suitable for large drones. Summary of the invention

[0003] The embodiments of the present application provide a route planning method, apparatus, computer equipment and storage medium, which can quantify the ground risk level and air risk level of each grid, and perform route planning based on the ground risk and air risk, and are suitable for path planning for large unmanned aerial vehicles.

[0004] On the one hand, the present application provides a route planning method, the route planning method comprising:

[0005] Acquire route planning information of the flight equipment and generate a grid map of the flight equipment, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids;

[0006] Determine a first risk parameter and a second risk parameter for each grid in the plurality of grids, the first risk parameter being used to characterize a ground risk level for each grid, and the second risk parameter being used to characterize an air risk level for each grid;

[0007] Determining a comprehensive risk parameter for each grid based on the first risk parameter and the second risk parameter;

[0008] The flight equipment is routed based on the route planning information and comprehensive risk parameters to obtain the target route of the flight equipment.

[0009] In some embodiments of the present application, determining a first risk parameter and a second risk parameter for each grid in a plurality of grids comprises:

[0010] Obtain ground information and airspace information of each grid in multiple grids;

[0011] Based on the ground information, determining a first risk parameter for each grid;

[0012] Based on the spatial domain information, a second risk parameter for each grid is determined.

[0013] In some embodiments of the present application, the ground information includes ground population information. Based on the ground information, determining the first risk parameter of each grid includes:

[0014] Get the grid size of each grid;

[0015] Based on the ground population information and grid size, determine the population density information of each grid;

[0016] Based on the population density information, determine the population density range to which each grid belongs;

[0017] A preset first corresponding relationship is obtained, and a first risk parameter of each grid is determined based on the population density range and the first corresponding relationship, where the first corresponding relationship is a corresponding relationship between the population density range and the first risk parameter.

[0018] In some embodiments of the present application, the airspace information includes an airspace type, and based on the airspace information, determining the second risk parameter of each grid includes:

[0019] Acquire a preset second corresponding relationship, where the second corresponding relationship is a corresponding relationship between the airspace type and the second risk parameter;

[0020] Based on the airspace type and the second corresponding relationship, a second risk parameter of each grid is determined.

[0021] In some embodiments of the present application, the route planning information includes the flight start point and the flight end point of the flight equipment. The route planning of the flight equipment is performed based on the route planning information and the comprehensive risk parameters to obtain the target route of the flight equipment, including:

[0022] Based on the flight start point and the flight end point, multiple candidate routes of the flight equipment and the distance information of each candidate route in each grid are determined;

[0023] Based on the comprehensive risk parameters and distance information, determine the target risk parameters for each candidate route;

[0024] Based on the target risk parameter, a target route of the flight equipment is determined from multiple candidate routes, and the target route is the route with the smallest target risk parameter among the multiple candidate routes.

[0025] In some embodiments of the present application, based on the comprehensive risk parameter and distance information, the target risk parameter of each candidate route is determined, including:

[0026] Based on the comprehensive risk parameters and distance information, determine the grid risk parameters of each grid under each candidate route;

[0027] Based on the grid risk parameters, the target risk parameter of each candidate route is determined, and the target risk parameter is the sum of the grid risk parameters of multiple grids under each candidate route.

[0028] In some embodiments of the present application, generating a grid map of a flight device includes:

[0029] Obtain equipment information of flight equipment and a map of the area corresponding to route planning information;

[0030] Determine grid sizes of the plurality of grids based on the device information;

[0031] The map is divided into a plurality of grids based on the grid size to obtain a grid map of the flight equipment.

[0032] On the other hand, the present application provides a route planning device, the route planning device comprising:

[0033] An information acquisition unit, used to acquire route planning information of the flight equipment and generate a grid map of the flight equipment, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids;

[0034] A first determining unit, configured to determine a first risk parameter and a second risk parameter for each of the plurality of grids, wherein the first risk parameter is used to characterize a ground risk level of each grid, and the second risk parameter is used to characterize an air risk level of each grid;

[0035] A second determining unit, configured to determine a comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter;

[0036] The route planning unit is used to plan the route of the flight equipment based on the route planning information and the comprehensive risk parameters to obtain the target route of the flight equipment.

[0037] In some embodiments of the present application, the first determining unit is specifically used to:

[0038] Obtain ground information and airspace information of each grid in multiple grids;

[0039] Based on the ground information, determining a first risk parameter for each grid;

[0040] Based on the spatial domain information, a second risk parameter for each grid is determined.

[0041] In some embodiments of the present application, the ground information includes ground population information, and the first determining unit is further configured to:

[0042] Get the grid size of each grid;

[0043] Based on the ground population information and grid size, determine the population density information of each grid;

[0044] Based on the population density information, determine the population density range to which each grid belongs;

[0045] A preset first corresponding relationship is obtained, and a first risk parameter of each grid is determined based on the population density range and the first corresponding relationship, where the first corresponding relationship is a corresponding relationship between the population density range and the first risk parameter.

[0046] In some implementation schemes of the present application, the airspace information includes an airspace type, and the first determining unit is further configured to:

[0047] Acquire a preset second corresponding relationship, where the second corresponding relationship is a corresponding relationship between the airspace type and the second risk parameter;

[0048] Based on the airspace type and the second corresponding relationship, a second risk parameter of each grid is determined.

[0049] In some embodiments of the present application, the route planning information includes the flight start point and flight end point of the flight equipment, and the route planning unit is specifically used to:

[0050] Based on the flight start point and the flight end point, multiple candidate routes of the flight equipment and the distance information of each candidate route in each grid are determined;

[0051] Based on the comprehensive risk parameters and distance information, determine the target risk parameters for each candidate route;

[0052] Based on the target risk parameter, a target route of the flight equipment is determined from multiple candidate routes, and the target route is the route with the smallest target risk parameter among the multiple candidate routes.

[0053] In some embodiments of the present application, the route planning unit is further used to:

[0054] Based on the comprehensive risk parameters and distance information, determine the grid risk parameters of each grid under each candidate route;

[0055] Based on the grid risk parameters, the target risk parameter of each candidate route is determined, and the target risk parameter is the sum of the grid risk parameters of multiple grids under each candidate route.

[0056] In some embodiments of the present application, the information acquisition unit is specifically used to:

[0057] Obtain equipment information of flight equipment and a map of the area corresponding to route planning information;

[0058] Determine grid sizes of the plurality of grids based on the device information;

[0059] The map is divided into a plurality of grids based on the grid size to obtain a grid map of the flight equipment.

[0060] On the other hand, the present application also provides a computer device, the computer device comprising:

[0061] one or more processors;

[0062] Memory; and

[0063] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement any one of the route planning methods in the first aspect.

[0064] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and the computer program is loaded by a processor to execute the steps in the route planning method of any one of the first aspects.

[0065] The present application determines the first risk parameter and the second risk parameter of each grid. The ground risk level and the air risk level of each grid can be quantified through the first risk parameter and the second risk parameter. The comprehensive risk parameter of each grid is determined based on the first risk parameter and the second risk parameter. Route planning is then performed based on the comprehensive risk parameter. Both ground risk and air risk are considered during the route planning process, which can effectively reduce the ground and air risks of flight equipment. The application is suitable for path planning for large unmanned aerial vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0067] Figure 1 is a schematic diagram of a scenario of a route planning system provided by an embodiment of the present application;

[0068] Figure 2 This is a schematic diagram of an embodiment of a route planning method provided in an embodiment of the present application;

[0069] Figure 3 It is a schematic diagram of a specific embodiment of the route planning method provided in the embodiments of the present application;

[0070] Figure 4 is a schematic diagram of a specific embodiment of the candidate routes provided in the embodiments of the present application;

[0071] Figure 5It is a schematic diagram of the structure of an embodiment of a route planning device provided in an embodiment of the present application;

[0072] Figure 6 It is a schematic diagram of the structure of an embodiment of a computer device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0074] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", and "third" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first", "second", and "third" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0075] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0076] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data for processing by the computer device. The details will not be repeated here.

[0077] The embodiments of the present application provide a route planning method, apparatus, computer equipment and storage medium, which are described in detail below.

[0078] See also Figure 1 , Figure 1 Schematic diagram of a route planning system provided in an embodiment of the present application. The route planning system may include a computer device 100, in which a route planning device is integrated. Figure 1 Computer equipment in.

[0079] In the embodiment of the present application, the computer device 100 is mainly used to obtain the route planning information of the flight equipment and the grid map of the flight equipment, wherein the grid map includes multiple grids; determine the first risk parameter and the second risk parameter of each grid in the multiple grids, wherein the first risk parameter is used to characterize the ground risk level of each grid, and the second risk parameter is used to characterize the air risk level of each grid; determine the comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter; perform route planning for the flight equipment based on the route planning information and the comprehensive risk parameter to obtain the target route of the flight equipment. The computer device 100 can quantify the ground risk level and the air risk level of each grid, and perform route planning in combination with the ground risk and the air risk, which can effectively reduce the ground and air risks of the flight equipment and is suitable for path planning for large unmanned aerial vehicles.

[0080] In the embodiment of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiment of the present application includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0081] It is understandable that the computer device 100 used in the embodiments of the present application may be a device including both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, a tablet computer, a laptop computer, etc.

[0082] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one computer device is shown in the figure. It can be understood that the route planning system can also include one or more other services, which are not limited here.

[0083] In addition, if Figure 1 As shown, the route planning system may further include a memory 200 for storing data, such as a first correspondence, for example, a first risk parameter corresponding to a population density range (0, 10] is 1, a first risk parameter corresponding to a population density range (10, 100] is 2, a first risk parameter corresponding to a population density range (100, 1500] is 3, etc., such as a second correspondence, for example, a second risk parameter corresponding to an airport control area is 1, a second risk parameter corresponding to a civil aviation restricted area is 2, a second risk parameter corresponding to a military aviation restricted area is 3, etc.

[0084] It should be noted that Figure 1 The scenario diagram of the route planning system shown is merely an example. The route planning system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the route planning system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0085] First, a route planning method is provided in an embodiment of the present application, and the executor of the route planning method is a route planning device, and the route planning device is applied to a computer device. The route planning method includes: obtaining route planning information of the flight equipment and generating a grid map of the flight equipment, the grid map is obtained by rasterizing the map of the area corresponding to the route planning information, and the grid map includes multiple grids; determining a first risk parameter and a second risk parameter of each grid in the multiple grids, the first risk parameter is used to characterize the ground risk level of each grid, and the second risk parameter is used to characterize the air risk level of each grid; based on the first risk parameter and the second risk parameter, determining a comprehensive risk parameter of each grid; and performing route planning on the flight equipment based on the route planning information and the comprehensive risk parameter to obtain a target route of the flight equipment.

[0086] like Figure 2 As shown, it is a schematic diagram of an embodiment of a route planning method in an embodiment of the present application. The route planning method may include the following steps 301 to 304, which are as follows:

[0087] 301. Obtain route planning information of a flight device and generate a grid map of the flight device. The grid map is obtained by rasterizing a map of an area corresponding to the route planning information. The grid map includes a plurality of grids.

[0088] Flight equipment is equipment that requires route planning, including but not limited to drones, aircraft that support autopilot, etc. Route planning information is information required for route planning of flight equipment, including but not limited to the flight starting point and flight destination of the flight mission of the flight equipment, etc. The flight starting point is the take-off point of the flight mission of the flight equipment, and the flight destination is the destination of the flight mission of the flight equipment.

[0089] The grid map is obtained by rasterizing the map of the area corresponding to the route planning information, and the grid map includes multiple grids. The grid size of each grid can be set as needed. For example, considering that the turning radius of a large UAV flight route is about 1km, when planning the route of a large UAV, the route map of the large UAV can be divided into a 1km×1km grid map, that is, the size of each grid in the grid map is 1km×1km.

[0090] 302. Determine a first risk parameter and a second risk parameter for each grid in a plurality of grids, wherein the first risk parameter is used to characterize a ground risk level of each grid, and the second risk parameter is used to characterize an air risk level of each grid.

[0091] The first risk parameter is used to characterize the ground risk level of each grid, and the second risk parameter is used to characterize the air risk level of each grid. After acquiring the grid map of the flight equipment, this embodiment determines the first risk parameter and the second risk parameter of each grid in the grid map, and quantifies the ground risk level and the air risk level of each grid by the first risk parameter and the second risk parameter. For example, the grid map includes grid A, grid B and grid C, and the first risk parameters of grid A, grid B and grid C are determined to be 2, 1, and 4 respectively, and the second risk parameters of grid A, grid B and grid C are determined to be 3, 4, and 5 respectively.

[0092] 303. Determine a comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter.

[0093] The comprehensive risk parameter is a comprehensive quantitative parameter of the first risk parameter and the second risk parameter, and the comprehensive risk parameter can comprehensively characterize the ground risk and air risk of each grid. After determining the first risk parameter and the second risk parameter of each grid, this embodiment determines the comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter, and performs path planning based on the comprehensive risk parameter. Path planning can be performed in combination with ground risk and air risk at the same time, effectively reducing the ground risk and air risk of the flight equipment during the flight mission.

[0094] In a specific implementation, the comprehensive risk parameter is obtained by weighted summing the first risk parameter and the second risk parameter, wherein the calculation formula of the comprehensive risk parameter is: RC = K1*GRC+K2*ARC, wherein RC represents the comprehensive risk parameter, GRC represents the first risk parameter, ARC represents the second risk parameter, K1 represents the weight of the first risk parameter, K2 represents the weight of the second risk parameter, and K1 and K2 can be set as needed. For example, K1 = 1, K2 = 1, the first risk parameters of grid A, grid B, and grid C are 2, 1, and 4 respectively, and the second risk parameters of grid A, grid B, and grid C are 3, 4, and 5 respectively, then the comprehensive risk parameters of grid A, grid B, and grid C are 5, 5, and 9 respectively.

[0095] In another specific implementation, when the comprehensive risk parameter is determined based on the first risk parameter and the second risk parameter, the first risk parameter and the second risk parameter can be input into the first prediction model, and the first prediction model outputs the comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter. The risk prediction model is obtained by training a preset first network model based on a preset first training sample set, and the preset first network model can adopt a deep learning model or a machine learning model, for example, a convolutional neural network (CNN), a deconvolutional neural network (DN), etc.

[0096] Furthermore, the first training sample set includes a plurality of sample parameter pairs and a true comprehensive parameter of each sample parameter pair. When training the preset first network model, firstly, the plurality of sample parameter pairs are input into the preset first network model, and the predicted comprehensive parameter of each sample parameter pair is output through the first network model, and then the first loss value is determined according to the true comprehensive parameter, the predicted comprehensive parameter and the loss function of the first network model. When the first loss value does not meet the preset first condition, the model parameters of the first network model are corrected according to the preset first parameter learning rate, and the step of inputting the plurality of sample parameter pairs into the preset first network model is continued until the first loss value meets the preset first condition, thereby obtaining the first prediction model. Among them, the first loss value meeting the preset first condition can be that the first loss value is less than the preset first threshold value, or the difference between the first loss values ​​obtained twice before and after is less than the preset second threshold value.

[0097] 304. Perform route planning for the flight equipment based on the route planning information and the comprehensive risk parameters to obtain a target route for the flight equipment.

[0098] The target route is the flight route of the flight equipment for this flight mission determined based on the route planning information and the comprehensive risk parameters. This embodiment plans the route of the flight equipment based on the route planning information and the comprehensive risk parameters. During the route planning process, the ground risk level and the air risk level of each grid are simultaneously considered, which can effectively reduce the ground risk and the air risk during the flight of the flight equipment, and is suitable for path planning for large UAVs.

[0099] In a specific embodiment, Figure 3 As shown, determining the first risk parameter and the second risk parameter of each grid in the plurality of grids in step 302 may include the following steps 401 to 403, which are specifically as follows:

[0100] 401. Obtain ground information and airspace information of each grid in a plurality of grids;

[0101] 402. Determine a first risk parameter of each grid based on ground information;

[0102] 403. Determine a second risk parameter of each grid based on the airspace information.

[0103] The ground information is the ground environment information of the ground area corresponding to each grid, including but not limited to ground population information (such as population size, flow of people, etc.), ground building information (such as commercial areas, dense residential areas, gas stations, etc.), ground natural environment information (rivers, lakes, mountains, etc.), etc. The airspace information is the information of the air area corresponding to each grid, including but not limited to airspace type (airport control area, civil aviation restricted area, military aviation restricted area, civil aviation route area, air restricted area, etc.), airspace environment information, obstacle information (obstacles, no obstacles), etc.

[0104] The ground information in step S402 may include multiple ground information, such as ground population information, ground building information, ground natural environment information, etc. In a specific implementation, when the ground information includes multiple ground information, step S402 may specifically include: inputting multiple ground information into the second prediction model, and outputting the first risk parameter of each grid based on the multiple ground information through the second prediction model. For example, inputting the ground population information, ground building information and ground natural environment information into the second prediction model, and outputting the first risk parameter of each grid based on the ground population information, ground building information and ground natural environment information through the second prediction model. Among them, the second prediction model is obtained by training a preset second network model based on a preset second training sample set, and the preset second network model can adopt a deep learning model or a machine learning model, for example, a convolutional neural network (CNN), a deconvolutional neural network (DN), etc.

[0105] Furthermore, the second training sample set includes multiple first sample data sets and the first real risk parameter of each first sample data set, wherein each first sample data set includes multiple sample ground information. When training the preset second network model, first input multiple first sample data sets into the preset second network model, output the first predicted risk parameter of each first sample data set through the second network model, and then determine the second loss value according to the first real risk parameter, the first predicted risk parameter and the loss function of the second network model. When the second loss value does not meet the preset second condition, the model parameters of the second network model are corrected according to the preset second parameter learning rate, and the step of inputting multiple first sample data sets into the preset second network model is continued until the second loss value meets the preset second condition, thereby obtaining the second prediction model. Among them, the second loss value meets the preset second condition for the second loss value to be less than the preset third threshold, or the difference between the second loss values ​​obtained twice before and after is less than the preset fourth threshold.

[0106] In another specific implementation, when the ground information includes multiple ground information, step S402 may specifically include: determining multiple third risk parameters of each grid based on the multiple ground information, and then determining the first risk parameter of each grid based on the multiple third risk parameters. For example, the multiple ground information includes ground population information, ground building information, and ground natural environment information, and the multiple third risk parameters of each grid are determined to be 2, 1, and 3 based on the ground population information, the ground building information, and the ground natural environment information, and then the multiple third risk parameters are weighted and summed to obtain the first risk parameter of each grid.

[0107] The airspace information in step S403 may include multiple airspace information, such as airspace type, airspace environment information, obstacle information, etc. In a specific implementation, when the airspace information includes multiple airspace information, step S403 may specifically include: inputting multiple airspace information into a third prediction model, and outputting the second risk parameter of each grid based on multiple airspace information through the third prediction model, for example, inputting the airspace type, airspace environment information and obstacle information into the third prediction model, and outputting the second risk parameter of each grid based on the airspace type, airspace environment information and obstacle information through the third prediction model. The third prediction model is obtained by training a preset third network model based on a preset third training sample set, and the preset third network model can adopt a deep learning model or a machine learning model, for example, a convolutional neural network (CNN), a deconvolutional neural network (DN), etc.

[0108] Furthermore, the third training sample set includes multiple second sample data sets and the second real risk parameter of each second sample data set, wherein each second sample data set includes multiple sample airspace information. When training the preset third network model, firstly, multiple second sample data sets are input into the preset third network model, and the second predicted risk parameter of each second sample data set is output through the third network model. Then, according to the second real risk parameter, the second predicted risk parameter and the loss function of the third network model, the third loss value is determined. When the third loss value does not meet the preset third condition, the model parameters of the third network model are corrected according to the preset third parameter learning rate, and the step of inputting multiple second sample data sets into the preset third network model is continued until the third loss value meets the preset third condition, thereby obtaining the third prediction model. Among them, the third loss value meets the preset third condition for the third loss value to be less than the preset fifth threshold, or the difference between the third loss values ​​obtained twice before and after is less than the preset sixth threshold.

[0109] In another specific implementation, when the airspace information includes multiple airspace information, step S403 may specifically include: determining multiple fourth risk parameters of each grid based on the multiple airspace information, and then determining the second risk parameter of each grid based on the multiple fourth risk parameters. For example, the multiple airspace information includes airspace type, airspace environment information and obstacle information, and the multiple fourth risk parameters of each grid are determined to be 2, 4, and 1 based on the airspace type, airspace environment information and obstacle information, and then the multiple fourth risk parameters are weighted and summed to obtain the second risk parameter of each grid.

[0110] In a specific implementation, the ground information includes ground population information. In step 402, determining the first risk parameter of each grid based on the ground information may include the following steps 501 to 504, which are as follows:

[0111] 501. Obtain the grid size of each grid;

[0112] 502. Determine population density information of each grid based on ground population information and grid size;

[0113] 503. Based on the population density information, determine the population density range to which each grid belongs;

[0114] 504. Obtain a preset first corresponding relationship, and determine a first risk parameter for each grid based on the population density range and the first corresponding relationship, where the first corresponding relationship is a corresponding relationship between the population density range and the first risk parameter.

[0115] The grid size is information related to the size of each grid. For example, a grid of 1km×1km has a grid size of 1km×1km. The population density information is the number of people per square kilometer. For example, a population density information of 10 indicates that there are 10 people per square kilometer. The first corresponding relationship is the corresponding relationship between the preset population density range and the first risk parameter. For example, the first corresponding relationship is: the first risk parameter corresponding to the population density range (0, 10] is 1; the first risk parameter corresponding to the population density range (10, 100] is 2; the first risk parameter corresponding to the population density range (100, 1500] is 3; the first risk parameter corresponding to the population density range (1500, 15000] is 4; the first risk parameter corresponding to the population density range above 15000 is 5.

[0116] In a specific implementation, the first risk parameter is determined based on ground population information. When determining the first risk parameter based on ground population information, the grid size of each grid is first obtained, and then the population density information of each grid is determined based on the ground population information and the grid size. Then, based on the population density information, the population density range to which each grid belongs is determined, and finally, the first risk parameter of each grid is determined based on the population density range and the first corresponding relationship. For example, if the population density information of grid A is 7, then based on the population density information, it can be determined that the population density range to which grid A belongs is (10, 100], and the first risk parameter corresponding to the population density range (0, 10] in the first corresponding relationship is 1, then the first risk parameter of grid A is determined to be 1.

[0117] The calculation formula for population density information is: Among them, P density represents population density, P represents the number of ground population, which is determined by ground population information, and S represents the grid size of the grid. For example, P = 7, S = 1km × 1km, then

[0118] In a specific implementation, the airspace information includes the airspace type. In step 403, determining the second risk parameter of each grid based on the airspace information may include the following steps 505 to 506, which are as follows:

[0119] 505. Obtain a preset second corresponding relationship, where the second corresponding relationship is a corresponding relationship between the airspace type and the second risk parameter;

[0120] 506. Determine a second risk parameter of each grid based on the airspace type and the second corresponding relationship.

[0121] The second corresponding relationship is the corresponding relationship between the pre-set airspace type and the second risk parameter. For example, the airspace type may include airport control area, civil aviation restricted area, military aviation restricted area, civil aviation route area, and air restricted area. The second corresponding relationship can be: airport control area, ARC=1; civil aviation restricted area, ARC=2; military aviation restricted area, ARC=3; civil aviation route area, ARC=4; air restricted area, ARC=+∞.

[0122] In a specific implementation, the second risk parameter is determined based on the airspace type. When determining the second risk parameter based on the airspace type, first obtain the preset second correspondence, and then determine the second risk parameter of each grid based on the airspace type and the second correspondence. For example, the airspace types of grid A, grid B, and grid C are respectively civil aviation restricted area, military aviation restricted area, and civil aviation route area, then based on the airspace information and the second correspondence, the second risk parameters of grid A, grid B, and grid C are respectively 2, 3, and 4.

[0123] In a specific implementation, the route planning information includes the flight start point and flight end point of the flight equipment, such as Figure 3 As shown, in step 304, the flight equipment is routed based on the route planning information and the comprehensive risk parameters to obtain the target route of the flight equipment, which may include the following steps 404 to 406, which are as follows:

[0124] 404. Based on the flight start point and the flight end point, determine multiple candidate routes of the flight equipment and distance information of each candidate route in each grid;

[0125] 405. Determine the target risk parameter for each candidate route based on the comprehensive risk parameter and distance information;

[0126] 406. Based on the target risk parameter, determine a target route of the flight equipment from multiple candidate routes, the target route being the route with the smallest target risk parameter among the multiple candidate routes.

[0127] Multiple candidate routes are flight routes determined based on the flight start point and the flight end point. Generally speaking, without considering other factors, multiple flight routes can be determined based on the flight start point and the flight end point. The target risk parameter is the risk parameter of each candidate route determined based on the comprehensive risk parameter of each grid and the distance information of each candidate route in each grid. The target risk parameter can comprehensively represent the ground risk, air risk and distance cost of each candidate route. The target route is the route with the smallest target risk parameter among multiple candidate routes.

[0128] In a specific implementation, the route planning information includes the flight starting point and flight destination of the flight equipment. When the route planning of the flight equipment is performed based on the route planning information and the comprehensive risk parameters, multiple candidate routes for the flight equipment and the distance information of each candidate route in each grid can be determined based on the flight starting point and the flight destination. Then, based on the comprehensive risk parameters and the distance information, the target risk parameters of each candidate route can be determined. Finally, based on the target risk parameters, the target route of the flight equipment is determined from multiple candidate routes. The target route is determined in combination with the comprehensive risk parameters and the distance information. While reducing the ground and air risks of the flight equipment, the shortest distance can be achieved to save power loss or fuel loss.

[0129] In a specific implementation, determining the target risk parameter of each candidate route based on the comprehensive risk parameter and the distance information in step 405 may include the following steps 507 to 508, which are as follows:

[0130] 507. Based on the comprehensive risk parameter and distance information, determine the grid risk parameter of each grid under each candidate route;

[0131] 508. Based on the grid risk parameter, determine the target risk parameter of each candidate route, where the target risk parameter is the sum of the grid risk parameters of multiple grids under each candidate route.

[0132] The grid risk parameter is the grid risk parameter of each grid under each candidate route determined based on the comprehensive risk parameter and distance information. The grid risk parameter can characterize the risk level and distance cost of each grid under each candidate route. The calculation formula of the grid risk parameter is: R = RC*L, R represents the grid risk parameter, RC represents the comprehensive risk parameter, and L represents the distance information. For example, Figure 4 For the candidate route shown, assuming that the grid is 1km×1km, for grid 2, L=0.5km+0.5*1.414km, then the grid risk parameter of grid 2 under the candidate route is R=RC*(0.5+0.5*1.414).

[0133] The target risk parameter is the sum of the grid risk parameters of multiple grids under each candidate route. Therefore, after determining the grid risk parameter of each grid under each candidate route, the grid risk parameters of multiple grids under each candidate route can be added to obtain the target risk parameter of each candidate route. Since the distance information of the grid that the candidate route has not passed is 0, the calculation process of the target risk parameter can be expressed as: R total =R 1 +R 2 +R 3 +…+R n , R total represents the target risk parameter, R1 Represents the grid risk parameter of the grid to which the flight origin belongs, R 2 ~R n-1 Represents the grid risk parameter of the candidate route passing through the grid, R n The grid risk parameter that represents the grid to which the flight destination belongs. Figure 4 The candidate routes shown, R total =R 1 +R 2 +R 3 +…+R 14 .

[0134] In a specific implementation, generating a grid map of the flying device in step 301 may include the following steps 407 to 409, which are as follows:

[0135] 407. Obtain equipment information of the flight equipment and a map of the area corresponding to the route planning information;

[0136] 408. Determine grid sizes of the plurality of grids based on the device information;

[0137] 409. Divide the map into a plurality of grids based on the grid size to obtain a grid map of the flight device.

[0138] The equipment information is the information of the flight equipment. When obtaining the grid map of the flight equipment in this embodiment, the equipment information of the flight equipment and the map of the area corresponding to the route planning information are first obtained, and then the grid size of the multiple grids is determined based on the equipment information, and finally the map is divided into multiple grids based on the grid size, so as to obtain the grid map of the flight equipment. For example, the equipment information includes the turning radius of the flight equipment, and the grid size of the multiple grids is determined based on the turning radius, and then the map is divided into multiple grids based on the grid size. If the turning radius of the flight equipment is 1km, the grid size of the multiple grids is determined to be 1km×1km, and then the map is divided into a 1km×1km grid map using the WGS84 coordinate system.

[0139] In order to better implement the route planning method in the embodiment of the present application, based on the route planning method, the embodiment of the present application also provides a route planning device, such as Figure 5 As shown, the route planning device 600 includes:

[0140] The information acquisition unit 601 is used to acquire the route planning information of the flight equipment and generate a grid map of the flight equipment. The grid map is obtained by rasterizing the map of the area corresponding to the route planning information. The grid map includes a plurality of grids.

[0141] A first determining unit 602 is used to determine a first risk parameter and a second risk parameter for each grid in the plurality of grids, wherein the first risk parameter is used to characterize a ground risk level of each grid, and the second risk parameter is used to characterize an air risk level of each grid;

[0142] A second determining unit 603, configured to determine a comprehensive risk parameter of each grid based on the first risk parameter and the second risk parameter;

[0143] The route planning unit 604 is used to plan the route of the flight equipment based on the route planning information and the comprehensive risk parameters to obtain the target route of the flight equipment.

[0144] In an embodiment of the present application, a first risk parameter and a second risk parameter are determined for each grid. The ground risk level and the air risk level of each grid can be quantified through the first risk parameter and the second risk parameter. A comprehensive risk parameter of each grid is determined based on the first risk parameter and the second risk parameter. Route planning is then performed based on the comprehensive risk parameter. Both ground risk and air risk are considered during route planning, which can effectively reduce the ground and air risks of flight equipment. The method is suitable for path planning for large unmanned aerial vehicles.

[0145] In some embodiments of the present application, the first determining unit 602 is specifically configured to:

[0146] Obtain ground information and airspace information of each grid in multiple grids;

[0147] Based on the ground information, determining a first risk parameter for each grid;

[0148] Based on the spatial domain information, a second risk parameter for each grid is determined.

[0149] In some embodiments of the present application, the ground information includes ground population information, and the first determining unit 602 is further configured to:

[0150] Get the grid size of each grid;

[0151] Based on the ground population information and grid size, determine the population density information of each grid;

[0152] Based on the population density information, determine the population density range to which each grid belongs;

[0153] A preset first corresponding relationship is obtained, and a first risk parameter of each grid is determined based on the population density range and the first corresponding relationship, where the first corresponding relationship is a corresponding relationship between the population density range and the first risk parameter.

[0154] In some embodiments of the present application, the airspace information includes an airspace type, and the first determining unit 602 is further configured to:

[0155] Acquire a preset second corresponding relationship, where the second corresponding relationship is a corresponding relationship between the airspace type and the second risk parameter;

[0156] Based on the airspace type and the second corresponding relationship, a second risk parameter of each grid is determined.

[0157] In some embodiments of the present application, the route planning information includes the flight start point and the flight end point of the flight equipment, and the route planning unit 604 is specifically used to:

[0158] Based on the flight start point and the flight end point, multiple candidate routes of the flight equipment and the distance information of each candidate route in each grid are determined;

[0159] Based on the comprehensive risk parameters and distance information, determine the target risk parameters for each candidate route;

[0160] Based on the target risk parameter, a target route of the flight equipment is determined from multiple candidate routes, and the target route is the route with the smallest target risk parameter among the multiple candidate routes.

[0161] In some embodiments of the present application, the route planning unit 604 is further configured to:

[0162] Based on the comprehensive risk parameters and distance information, determine the grid risk parameters of each grid under each candidate route;

[0163] Based on the grid risk parameters, the target risk parameter of each candidate route is determined, and the target risk parameter is the sum of the grid risk parameters of multiple grids under each candidate route.

[0164] In some embodiments of the present application, the information acquisition unit 601 is specifically used to:

[0165] Obtain equipment information of flight equipment and a map of the area corresponding to route planning information;

[0166] Determine grid sizes of the plurality of grids based on the device information;

[0167] The map is divided into a plurality of grids based on the grid size to obtain a grid map of the flight equipment.

[0168] The embodiment of the present application further provides a computer device, which integrates any one of the route planning devices provided in the embodiment of the present application, and the computer device includes:

[0169] one or more processors;

[0170] Memory; and

[0171] One or more applications, wherein the one or more applications are stored in a memory and configured to be executed by a processor to execute the steps of the route planning method in any of the above route planning method embodiments.

[0172] The present application also provides a computer device that integrates any of the route planning devices provided in the present application. Figure 6 As shown, it shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:

[0173] The computer device may include one or more processing core processors 701, one or more computer readable storage media memories 702, a power supply 703, an input unit 704 and other components. Those skilled in the art will appreciate that Figure 6 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0174] The processor 701 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 702 and calling data stored in the memory 702, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0175] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

[0176] The computer device also includes a power supply 703 for supplying power to various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 703 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0177] The computer device may further include an input unit 704, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0178] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 701 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 702 according to the following instructions, and the processor 701 will run the application programs stored in the memory 702, thereby realizing various functions, as follows:

[0179] Acquire route planning information of the flight equipment and generate a grid map of the flight equipment, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids;

[0180] Determine a first risk parameter and a second risk parameter for each grid in the plurality of grids, the first risk parameter being used to characterize a ground risk level for each grid, and the second risk parameter being used to characterize an air risk level for each grid;

[0181] Determining a comprehensive risk parameter for each grid based on the first risk parameter and the second risk parameter;

[0182] The flight equipment is routed based on the route planning information and comprehensive risk parameters to obtain the target route of the flight equipment.

[0183] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0184] To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the route planning methods provided in the embodiments of the present application. For example, the computer program is loaded by a processor to execute the following steps:

[0185] Acquire route planning information of the flight equipment and generate a grid map of the flight equipment, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids;

[0186] Determine a first risk parameter and a second risk parameter for each grid in the plurality of grids, the first risk parameter being used to characterize a ground risk level for each grid, and the second risk parameter being used to characterize an air risk level for each grid;

[0187] Determining a comprehensive risk parameter for each grid based on the first risk parameter and the second risk parameter;

[0188] The flight equipment is routed based on the route planning information and comprehensive risk parameters to obtain the target route of the flight equipment.

[0189] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0190] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0191] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0192] The above is a detailed introduction to a route planning method, system, computer device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A route planning method, characterized in that: The route planning method comprises: Acquire route planning information of a flight device and generate a grid map of the flight device, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids; Determine a first risk parameter and a second risk parameter for each grid in the plurality of grids, wherein the first risk parameter is used to characterize a ground risk level of each grid, and the second risk parameter is used to characterize an air risk level of each grid; Determining a comprehensive risk parameter of each of the grids based on the first risk parameter and the second risk parameter; The flight equipment is routed based on the route planning information and the comprehensive risk parameter to obtain a target route for the flight equipment.

2. The route planning method according to claim 1, characterized in that: The determining of the first risk parameter and the second risk parameter of each grid in the plurality of grids comprises: Acquire ground information and airspace information of each grid in the plurality of grids; Based on the ground information, determining a first risk parameter for each of the grids; Based on the spatial domain information, a second risk parameter of each of the grids is determined.

3. The route planning method according to claim 2, characterized in that: The ground information includes ground population information, and determining the first risk parameter of each grid based on the ground information includes: Obtaining the grid size of each of the grids; Determining population density information of each grid based on the ground population information and the grid size; Based on the population density information, determining the population density range to which each of the grids belongs; A preset first corresponding relationship is obtained, and a first risk parameter of each of the grids is determined based on the population density range and the first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between the population density range and the first risk parameter.

4. The route planning method according to claim 2, characterized in that: The airspace information includes an airspace type, and determining the second risk parameter of each grid based on the airspace information includes: Acquire a preset second corresponding relationship, where the second corresponding relationship is a corresponding relationship between the airspace type and the second risk parameter; Based on the airspace type and the second corresponding relationship, a second risk parameter of each of the grids is determined.

5. The route planning method according to claim 1, characterized in that: The route planning information includes a flight start point and a flight end point of the flight equipment, and the route planning of the flight equipment based on the route planning information and the comprehensive risk parameter to obtain a target route of the flight equipment includes: Based on the flight starting point and the flight end point, determining a plurality of candidate routes of the flight equipment and distance information of each of the candidate routes in each of the grids; Determining a target risk parameter for each of the candidate routes based on the comprehensive risk parameter and the distance information; Based on the target risk parameter, a target route of the flight equipment is determined from the plurality of candidate routes, wherein the target route is the route with the smallest target risk parameter among the plurality of candidate routes.

6. The route planning method according to claim 5, characterized in that: The step of determining a target risk parameter for each candidate route based on the comprehensive risk parameter and the distance information includes: Determining a grid risk parameter of each of the grids under each of the candidate routes based on the comprehensive risk parameter and the distance information; Based on the grid risk parameter, a target risk parameter of each of the candidate routes is determined, wherein the target risk parameter is the sum of the grid risk parameters of a plurality of the grids under each of the candidate routes.

7. The route planning method according to any one of claims 1 to 6, characterized in that: The generating of the grid map of the flight equipment comprises: Acquire equipment information of the flight equipment and a map of the area corresponding to the route planning information; Determining grid sizes of a plurality of the grids based on the device information; The map is divided into a plurality of grids based on the grid size to obtain a grid map of the flying equipment.

8. A route planning device, characterized in that: The route planning device comprises: An information acquisition unit, used to acquire route planning information of a flight device and generate a grid map of the flight device, wherein the grid map is obtained by rasterizing a map of an area corresponding to the route planning information, and the grid map includes a plurality of grids; A first determining unit, configured to determine a first risk parameter and a second risk parameter for each of the plurality of grids, wherein the first risk parameter is used to characterize a ground risk level of each of the grids, and the second risk parameter is used to characterize an air risk level of each of the grids; A second determining unit, configured to determine a comprehensive risk parameter of each of the grids based on the first risk parameter and the second risk parameter; A route planning unit is used to perform route planning for the flight equipment based on the route planning information and the comprehensive risk parameter to obtain a target route for the flight equipment.

9. A computer device, characterized in that: The computer device comprises: one or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the route planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the route planning method according to any one of claims 1 to 7.

Images