A method, device and readable storage medium for deploying unmanned aerial vehicle (UAV) at an intelligent airport

Abstract

The present application provides a method, device and readable storage medium for the deployment of unmanned aerial vehicle (UAV) intelligent airports. For a given set of available intelligent airports, the location of each intelligent airport in a predetermined area is determined to support the scenario of one-dimensional tracking of UAVs. The behavior of the tracked object is modeled and predicted based on historical data. With the goal of maximizing the tracking success rate, a nonlinear 0-1 programming model is established to solve the optimal intelligent airport deployment location. The optimal deployment method of intelligent airports based on the improved genetic algorithm with targeted coding can obtain a solution with sufficiently good performance while fully shortening the calculation time.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and more specifically, to a method, device, and readable storage medium for deploying drones at smart airports. Background Art

[0002] Due to their advantages in flexibility, full-view monitoring capability, and cost-effectiveness, drones have been increasingly used in one-dimensional tracking scenarios, such as Figure 1 In this scenario, when the ground detection system finds a moving boat or illegal vehicle on a river or road, it will notify the drone to track it. When the drone catches up with the target object, it will hover over it to make propaganda or take photos for evidence.

[0003] The endurance of a single UAV flight has always been a bottleneck restricting its large-scale application, especially in scenarios such as one-dimensional tracking where multiple objects are scattered over a large geographical area. Although the use of smart airports with unmanned operation functions can realize automatic charging of UAVs, it is difficult to achieve a high tracking success rate for target objects in the mission area due to the lack of optimized airport site selection and deployment. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a drone intelligent airport deployment method, a control device, and a computer-readable storage medium to solve the above-mentioned problems existing in the prior art and achieve a high tracking success rate for target objects in the mission area.

[0005] In a first aspect, a method for deploying a drone smart airport is provided, the method may include: the smart airport is used for corresponding drones to take off and land, the method includes:

[0006] 1) The channel in the mission area is divided into several directional sub-segments according to the end points of the channel and the intersections between the channels. The channel refers to any directional route for the tracked object from entering the mission area to leaving the mission area; several smart airport alternative points are set around the channel;

[0007] 2) Statistically observe the distribution of multiple tracked objects on the channel or sub-segment in the historical data, and calculate the corresponding probability of any tracked object moving along each channel , where τ represents the τth channel;

[0008] 3) According to the speed of the drone , the location of the smart airport alternative point, the speed of the tracked object, and the time from the tracked object entering the mission area to being discovered by the monitoring system , to determine whether the UAV at each smart airport candidate point can catch up with the tracking object moving along each route, and the judgment value is ; n represents the nth smart airport candidate point; when the UAV at the nth smart airport candidate point can catch up with the tracking object moving along the route τ, =1, otherwise ;

[0009] 4) According to the total number of smart airports m and probability , judgment value , the objective function is set to maximize the tracking success rate, where the tracking success rate refers to the probability that a UAV in at least one smart airport candidate point among all smart airport candidate points deployed as smart airports can catch up with the tracking object moving along any route;

[0010] 5) Solve the objective function and determine The value of is chosen to maximize the value of the objective function, where Characterization n Whether the smart airport candidate point is deployed as a smart airport When When it is not deployed as a smart airport, , , N is the total number of smart airport alternative points;

[0011] The objective function is:

[0012] ,in, W Indicates the tracking success rate.

[0013] In an optional implementation, an improved genetic algorithm is used to solve the objective function, and a targeted coding method is adopted, and the specific steps are as follows:

[0014] 1) Sort the smart airport candidate points according to the length of the overlap between the maximum flight range of the drone and all the routes from large to small;

[0015] 2) The decoding range of the objective function into any component is of m dimensional real-valued vector , The first smart airport deployment location, The second smart airport is located in Indicates rounding up operation;

[0016] 3) Randomly generate the above optimization problem G feasible solutions as the initial population;

[0017] 4) Use the exponential sorting selection method to select individuals in the current population for replication;

[0018] 5) Randomly pair the individuals generated by the selection-copy operation;

[0019] 6) For each individual generated by the crossover operation, a mutation operation is performed with a mutation probability of 0.001-0.1;

[0020] 7) 4) to 6) is one iteration, and the iteration is repeated until the termination condition is met;

[0021] 8) Output the solution with the highest fitness and decode it.

[0022] In an optional implementation, the distribution of multiple tracked objects in the historical data observed when they were found by the monitoring system in the sub-segments is calculated, and the probability of any tracked object moving along each sub-segment when it is found by the monitoring system is calculated. Based on this, the probability of any tracked object moving along each channel is further calculated. , where the monitoring system is a random patrol, and the probability of the monitoring system finding the tracking object in any time period after the tracking object enters the task area is the same.

[0023] In an optional implementation, the probability of any tracked object moving along each sub-segment when discovered by the monitoring system is calculated as follows:

[0024] Assume that the total number of tracking objects discovered by the monitoring system in the observed historical data is M, then: , Indicates that from the intersection To the intersection The intersection point refers to the end point of the route or the intersection point between the routes; Indicates that the tracking object is found along the intersection point To the intersection The probability of moving the sub-segment of Indicates that in historical data, when the monitoring system discovers To the intersection The total number of tracked objects moved by the sub-segment.

[0025] In an optional implementation, the probability of any tracked object moving along any channel τ is The calculation method is as follows:

[0026] For the intersection Move to intersection The tracking object is calculated from the intersection point Move to intersection Probability ,

[0027] ;

[0028] in Indicates the intersection The set of all sub-segments starting from the origin;

[0029] ,in , …, They represent the first, second, third, ..., qth intersection points of the channel τ, respectively. Indicated by the intersection , …, The waterway formed by connecting in sequence.

[0030] In an optional implementation, determining n Can drones catch up with mobile flight paths at smart airport alternatives? The method for moving tracking objects is as follows:

[0031] use Indicates the channel and at the location point n The last intersection point of the maximum flight range of the UAV at the smart airport is:

[0032]

[0033] in: Indicates along the waterway The moving tracking object starts from entering the mission area to moving to The time required It indicates the time from when the tracking object enters the mission area to when it is discovered by the monitoring system; Indicates the nth smart airport candidate point and The straight-line distance between them, v represents the corresponding average speed of the UAV; By tracking the speed of the object and the time from entering the mission area to moving to the mission area The voyage is calculated at It is a conditional judgment function, which is equal to 1 when the condition is met and equal to 0 when the condition is not met;

[0034] If the channel and at the location point n There is no intersection in the maximum flight range of the UAV at the smart airport. is a point at infinity, Is infinite.

[0035] In an optional embodiment, the maximum flight radius of the drone is ,in: Indicates the upper limit of energy consumption of a single flight of the drone. The energy consumed by the drone when hovering over the tracking object. is the speed of the drone, The energy consumption per unit time when the drone flies in a straight line is, Indicates the maximum flight radius of the nth drone.

[0036] In a second aspect, a device is provided, comprising a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of implementing any method described in the first aspect are performed.

[0037] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any method described in the first aspect are implemented.

[0038] Beneficial effects: 1) In the one-dimensional tracking scenario, the deployment location optimization of a given set of available UAV smart airports is considered, and the behavior of the tracking object is modeled and predicted based on historical data to maximize the tracking success rate of the target object in the mission area, which can provide further guidance for one-dimensional tracking applications for UAVs; 2) An optimal deployment method for smart airports based on an improved genetic algorithm with targeted coding is proposed. This method can obtain a solution with sufficiently good performance while significantly shortening the calculation time; 3) If the channels are complex and intertwined, the total number of channels will be far greater than the number of sub-segments, so a large amount of sample data is required. Compared with directly estimating the probability of the channel through the channel distribution, estimating through the distribution of sub-segments will reduce a large amount of sample data and further reduce the amount of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A scenario applicable to the embodiments of the present application;

[0041] Figure 2 A flowchart of a method for deploying a drone at an intelligent airport provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of the distribution of alternative points of a waterway and a smart airport provided in an embodiment of the present application;

[0043] Figure 4 A schematic diagram of the distribution of a waterway, smart airport candidate points, and smart airport deployment points provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] 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 of the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Unless otherwise defined, the technical terms or scientific terms used in this application should be the usual meanings understood by people with general skills in the field to which the present invention belongs. The "first", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0046] The drone intelligent airport deployment method provided in the embodiment of the present application can be applied to Figure 1 In the scenario shown, Figure 1 As shown, there are intersecting rivers and land separated from the rivers in the tracking mission area in this scene, and the object to be tracked can be a ship or a car. The monitoring system monitors the target's ship or car entering the mission area, and it may find the target entering, or it may fail to monitor. The monitoring system can be a radar, a video recognition monitoring system, a remote sensing system, or a manual patrol system. The time when the monitoring system finds the target is related to the position of the monitoring system, the direction and position of the target in the mission area, etc. In the embodiment of the present application, the monitoring system used is a random patrol, and the probability of the monitoring system finding the tracking object at any time period after the tracking object enters the mission area is the same.

[0047] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0048] Figure 2 A flowchart of a method for deploying a drone in an intelligent airport provided in an embodiment of the present application. The method may include:

[0049] Step 1: Mission area representation: The drone can fly in a straight line between the smart airport and any point within the range, and the tracked object can only move along a given route. A route refers to any directional route for the tracked object from entering the mission area to leaving the mission area. At the same time, each drone has a maximum flight range, which is a circular area with the maximum flight distance of the drone as the radius and the location of the drone's smart airport as the center.

[0050] In order to simplify the calculation process, the route can be equivalent to a one-dimensional curve, and the position of the smart airport candidate point can be equivalent to a point. For a given application scenario, the position of each one-dimensional curve and each smart airport candidate point in the mission area is known and can be represented by a plane coordinate system. For example, a one-dimensional curve can be represented by y=f(x), and the position of the smart airport candidate point can be represented by (x, y). In addition, the impact of the UAV's flight altitude can be ignored and simply equivalent to moving in a plane coordinate system.

[0051] In addition, the mission area boundary is also known, and its boundary can also be represented by a plane coordinate system. The UAV intelligent airport alternative point can be set within the mission area or outside the mission area.

[0052] The process includes:

[0053] 1. All candidate points where smart airports can be deployed are sorted to form a set of smart airport candidate points:

[0054] (13)

[0055] In formula (13), express N A set of smart airport candidate points. In this example, , the smart airport alternative points are Figure 3 As shown in the circle in the figure, the circle indicates the serial numbers of the smart airport alternative points.

[0056] 2. Maximum flight radius of drone-smart airport:

[0057] (14)

[0058] In formula (14), express N The maximum flight radius of each drone-smart airport at the location point is a set. Indicates n The maximum flight radius of the drone at each smart airport candidate point. All drones are of the same model.

[0059] 3. Divide the waterways in the monitored mission area into several directional sub-segments according to the endpoints of the waterways and the intersections between the waterways. The endpoints of the waterway refer to the starting point and the end point of the waterway. The area formed by connecting the endpoints of all waterways in sequence is the mission area. The endpoints of the waterways and the intersections between the waterways are called intersections. The set of intersections is:

[0060] (15)

[0061] In formula (15), Represents the set of endpoints of the channels and the intersections between channels, Indicates i In this case, the intersection points are Figure 3 As shown in the triangle in the figure, the intersection points are marked in the triangle;

[0062] 4. For any intersection point ,use Represents the set of intersection points directly connected to it;

[0063] 5. If the intersection and intersection Directly connected, use Indicates a sub-segment with a direction, whose direction is from the intersection point Move to intersection ;

[0064] 6. In the assembly In the example above, take out all the endpoints of the channel to form a subset In this example, ;

[0065] 7. The number of available smart airports is m In this example, ;

[0066] Step 2: A method for modeling the behavior of a tracked object, based on the historical data of the tracked object's movement, calculates the probability of it moving along any channel. It includes the following process:

[0067] 1. Sort out the historical data of the movement of the tracking object and unify all the historical data into The format is: Indicates that a tracking object is in t The moment is discovered and is at the intersection Move to intersection ;

[0068] 2. After being sorted according to the above format, the historical data of the movement of the tracking object is M In this case, ;

[0069] 3. After being sorted according to the above format, when the tracking object is found, record its intersection Move to intersection The data is shared by In this case, , , , , , , , , , ;

[0070] 4. Calculate the intersection of the tracked object when it is found. Move to intersection Probability:

[0071] (16)

[0072] In formula (16), Indicates that the tracking object is moving from the intersection point when it is discovered Move to intersection The probability of

[0073] 5. For the intersection Move to intersection The tracking object is calculated from the intersection point Move to intersection Probability:

[0074] (17)

[0075] In formula (17), Indicates that for the intersection Move to intersection The tracking object will then be Move to intersection The probability of

[0076] 6. Divide any channel of the tracked object into sub-segments based on the intersection points:

[0077] (18)

[0078] in , …, They represent the first, second, third, ..., qth intersection points of the channel τ, respectively. Indicated by the intersection , …, The waterway formed by connecting in sequence.

[0079] 7. Calculate the probability that the tracked object moves along any channel:

[0080] (19)

[0081] In formula (19), Indicates that the tracking object follows the curve Probability of moving.

[0082] About any channel The probability calculation can also be calculated using other statistical data. If the distribution of the tracking object moving along each channel within a certain period of time is directly used to calculate the channel If the channels are complex and intertwined, the total number of channels will be much larger than the number of sub-segments, so a large amount of sample data is required. However, estimating by the distribution of sub-segments will reduce a large amount of sample data. In this embodiment, the channel probability is estimated by the distribution of sub-segments.

[0083] In addition, when there are enough samples in the historical data, the samples can also be classified. The monitoring system is used to obtain the license plate or appearance of the tracked object, and the samples are classified, such as the size of the tracked object and the type of cargo carried. After classification, combined with the distribution, the accuracy of the channel probability calculation can be further improved.

[0084] Furthermore, when there is sufficient sample data and computing power, the movement trajectory of the target can be continuously monitored and tracked, and its future movement path can be predicted based on the movement of several consecutive sub-segments, further improving the accuracy of the channel probability calculation.

[0085] Therefore, the specific calculation method of the channel probability can be selected according to the actual needs based on the number of samples and computing power.

[0086] Step 3: With the goal of maximizing the tracking success rate, the optimal deployment problem of the smart airport is modeled as a nonlinear 0-1 programming problem and solved using an improved genetic algorithm. This includes the following steps:

[0087] 1. Use Indicates the channel and at the location point n The last intersection point of the maximum flight range of the smart airport at;

[0088] 2. The energy consumption per unit time when the drone flies in a straight line is In this example, ;

[0089] 3. After the drone catches up with the target, the energy consumed when hovering over it is In this example, ;

[0090] 4. Use Represents any two points i and j The straight-line distance between

[0091] 5. The average speed of the drone in straight-line flight is In this example, ;

[0092] 6. Calculate the maximum flight radius of the smart airport:

[0093] (20)

[0094] In formula (20), Indicates the upper limit of energy consumption of a single flight of the drone. In this example, , which can be calculated ;

[0095] 7. No. n The decision variable value of whether to set up a smart airport for each smart airport candidate point:

[0096] (twenty one),

[0097] In formula (21), Characterization n Whether to set the variable of smart airport for the candidate smart airport point. When the smart airport is set, When , it means no smart airport is set up;

[0098] 8. Constraints on the number of available smart airports:

[0099] (twenty two);

[0100] 9. Determine the n Can the drone at the smart airport at the alternative point catch up with the drone along the route? Objects to move:

[0101] (twenty three),

[0102] In formula (23), Indicates along the curve The moving object starts from entering the task area to moving to The time required It indicates the time from when the tracking object enters the mission area to when it is discovered by the monitoring system. is a conditional judgment function, which is equal to 1 when the condition is met and equal to 0 when the condition is not met. In this example, By tracking the speed of the object and the time from entering the mission area to moving to the mission area The speed of the tracking object is 300. If the channel and at the location point n There is no intersection in the maximum flight range of the UAV at the smart airport. is a point at infinity, Is infinite.

[0103] 10. Maximize the tracking success rate and set the objective function:

[0104] (twenty four),

[0105] In formula (24), W Indicates the tracking success rate;

[0106] 11. Summarizing equations (16) to (24), we obtain a smart airport deployment location optimization model with the goal of maximizing the tracking success rate under a given set of available smart airports.

[0107] 12. The above optimization model belongs to a nonlinear 0-1 programming model. The present invention uses an improved genetic algorithm to solve the problem and adopts a targeted coding method. The specific steps are: 1) Sort the 19 position points in descending order according to the length of the overlap between their maximum flight range and all the routes; 2) The solution of the above optimization problem is encoded into a value range of any component The 3-dimensional real-valued vector . The first smart airport deployment location, The deployment location of the second smart airport, This is the deployment location of the third smart airport. Indicates rounding up operation; 3) Randomly generate 100 feasible solutions to the above optimization problem as the initial population; 4) Use the exponential sorting selection method to select individuals in the current population for replication; 5) Randomly pair the individuals generated by the selection-replication operation; 6) For each individual generated by the crossover operation, perform a mutation operation with a mutation probability of 0.1; 7) 4) to 6) is an iteration. Repeat this iteration until the 20th generation; 8) Output the solution with the highest fitness, and after decoding, obtain the optimal deployment plan for the smart airport.

[0108] In this case, the tracking success rate can be solved as W The maximum value of is 0.886, and can be solved as Figure 4The optimal deployment scheme of smart airports is shown in Figure 1. The solid circle is the deployment point of the smart airport, and the circle with the solid circle as the center is the maximum flight radius of the corresponding smart airport.

[0109] In the one-dimensional tracking scenario, the optimization of the deployment location of a given set of available UAV smart airports is considered to maximize the tracking success rate of the target object in the mission area, which can provide further guidance for the one-dimensional tracking application of UAVs; in addition, an optimal deployment method for smart airports based on an improved genetic algorithm with targeted coding is proposed. This method can obtain a solution with sufficiently good performance while fully shortening the calculation time.

[0110] Corresponding to the above method, the embodiment of the present disclosure also provides a device, which is an electronic device 400, such as Figure 5 As shown, it is a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present disclosure, including: a processor 41, a memory 42, and a bus 43; the memory 42 is used to store execution instructions, including a memory 421 and an external memory 422; the memory 421 here is also called an internal memory, which is used to temporarily store the operation data in the processor 41, and the data exchanged with the external memory 422 such as a hard disk. The processor 41 exchanges data with the external memory 422 through the memory 421. When the electronic device 400 is running, the processor 41 communicates with the memory 42 through the bus 43, so that the processor 41 executes Figure 2 Steps of the UAV smart airport deployment method.

[0111] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for deploying a drone smart airport described in the above method embodiment are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0112] The disclosed embodiments also provide a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, the steps of the drone intelligent airport deployment method described in the above method embodiment can be executed. For details, please refer to the above method embodiment, which will not be repeated here.

[0113] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0114] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0117] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0118] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be described in the protection scope of the claims.

Claims

1. A method for deploying a drone smart airport, wherein the smart airport is used for corresponding drone takeoff and landing, characterized in that: The method comprises: 1) The waterway in the monitored mission area is divided into several directional sub-segments according to the endpoints of the waterway and the intersections between the waterways. The waterway refers to any directional route for the tracked object from entering the mission area to leaving the mission area; several intelligent airport alternative points are set around the waterway; 2) Statistically observe the distribution of multiple tracked objects on the channel or sub-segment in the historical data, and calculate the corresponding probability of any tracked object moving along each channel , where τ represents the τth channel; 3) According to the speed of the drone , the location of the smart airport alternative point, the speed of the tracked object, and the time from the tracked object entering the mission area to being discovered by the monitoring system , to determine whether the UAV at each smart airport candidate point can catch up with the tracking object moving along each route, and the judgment value is ; n represents the nth smart airport candidate point; when the UAV at the nth smart airport candidate point can catch up with the tracking object moving along the route τ, =1, otherwise ; 4) According to the total number of smart airports m and probability , judgment value , the objective function is set to maximize the tracking success rate, where the tracking success rate refers to the probability that a UAV in at least one smart airport candidate point among all smart airport candidate points deployed as smart airports can catch up with the tracking object moving along any route; 5) Solve the objective function and determine The value of is chosen to maximize the value of the objective function, where , , N is the total number of smart airport alternative points, Characterization n Whether the smart airport candidate point is deployed as a smart airport When When it is not deployed as a smart airport.

2. The method for deploying a drone intelligent airport according to claim 1 is characterized in that: The objective function is: ,in, W Indicates the tracking success rate.

3. The method for deploying a drone intelligent airport according to claim 2 is characterized in that: The improved genetic algorithm is used to solve the objective function, and a targeted coding method is adopted. The specific steps are as follows: 1) Sort the smart airport candidate points according to the length of the overlap between the maximum flight range of the drone and all the routes from large to small; 2) The decoding range of the objective function into any component is of m dimensional real-valued vector , The first smart airport deployment location, For the deployment location of the second smart airport,… is the deployment location of the mth smart airport, where Indicates rounding up operation; 3) Random generation G feasible solutions as the initial population; 4) Use the exponential sorting selection method to select individuals in the current population for replication; 5) Randomly pair the individuals generated by the selection-copy operation; 6) For each individual generated by the crossover operation, a mutation operation is performed with a mutation probability of 0.001-0.1; 7) 4) to 6) is one iteration, and the iteration is repeated until the termination condition is met; 8) Output the solution with the highest fitness and decode it.

4. The method for deploying a drone intelligent airport according to claim 1 or 2, characterized in that: The distribution of multiple tracked objects in the sub-segments when they are discovered by the monitoring system in the historical data of statistical observations is calculated, and the probability of any tracked object moving along each sub-segment when it is discovered by the monitoring system is calculated. Based on this, the corresponding probability of any tracked object moving along each channel is further calculated. , where the monitoring system is a random patrol, and the probability of the monitoring system finding the tracking object in any time period after the tracking object enters the task area is the same.

5. The method for deploying a drone intelligent airport according to claim 4 is characterized in that: The probability of any tracked object moving along each sub-segment when detected by the surveillance system is calculated as follows: Assume that the total number of tracking objects discovered by the monitoring system in the observed historical data is M, then: , Indicates that from the intersection To the intersection The intersection point refers to the end point of the route or the intersection point between the routes; Indicates that the tracking object is found along the intersection point To the intersection The probability of moving the sub-segment of Indicates that in historical data, when the monitoring system discovers To the intersection The total number of tracked objects moved by the sub-segment.

6. The method for deploying a drone intelligent airport according to claim 5 is characterized by: The probability of any tracked object moving along any channel τ The calculation method is as follows: For the intersection Move to intersection The tracking object is calculated from the intersection point Move to intersection Probability , ； in Indicates the intersection The set of all sub-segments starting from the origin; ,in , …, They represent the first, second, third, ..., qth intersection points of the channel τ, respectively. Indicated by the intersection , …, The waterway is formed by connecting them in sequence.

7. The method for deploying a drone intelligent airport according to claim 1 or 2, characterized in that: Judgement n Can drones catch up with mobile flight paths at smart airport alternatives? The method for moving tracking objects is as follows: use Indicates the channel and at the location point n The last intersection point of the maximum flight range of the UAV at the smart airport is: in: Indicates along the waterway The moving tracking object starts from entering the mission area to moving to The time required It indicates the time from when the tracking object enters the mission area to when it is discovered by the monitoring system; Indicates the nth smart airport candidate point and The straight-line distance between them, v represents the corresponding UAV speed; By tracking the speed of the object and the time from entering the mission area to moving to the mission area The voyage is calculated at It is a conditional judgment function, which is equal to 1 when the condition is met and equal to 0 when the condition is not met; If the channel and at the location point n There is no intersection in the maximum flight range of the UAV at the smart airport. is a point at infinity, Is infinite.

8. The method for deploying a drone intelligent airport according to claim 7 is characterized by: Maximum flight radius of the drone: ,in: Indicates the upper limit of energy consumption of a single flight of the drone. The energy consumed by the drone when hovering over the tracking object. is the speed of the drone, is the energy consumption per unit time when the drone flies in a straight line, Indicates the maximum flight radius of the nth drone.

9. A device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method as described in any one of claims 1 to 8 are performed.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of any method described in claims 1 to 8 are implemented.

Images