Unmanned Aerial Vehicle Multipath Planning Method and System, Computer Device and Storage Medium

Abstract

The present invention discloses a multi-path planning method and system for unmanned aerial vehicles, a computer device, and a storage medium. The method includes constructing a two-dimensional grid model of a swarm of unmanned aerial vehicles; obtaining the data on the cost of the grid planning path of the unmanned aerial vehicles; obtaining information on multiple optimal flight paths of the unmanned aerial vehicles; sending one of the information on the optimal flight paths of the unmanned aerial vehicles to the unmanned aerial vehicle among the information on multiple optimal flight paths of the unmanned aerial vehicles, and the unmanned aerial vehicle flies to the grid area corresponding to the target point according to the received information on the optimal flight path of the unmanned aerial vehicle. The present invention obtains the data on the cost of the grid planning path of the unmanned aerial vehicle through the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the swarm of unmanned aerial vehicles, performs route planning on the flight path of the unmanned aerial vehicle based on the target evolutionary algorithm, and obtains information on multiple optimal flight paths of the unmanned aerial vehicle, which facilitates the diverse selection of the flight path of the unmanned aerial vehicle and effectively improves the completion degree of the flight mission of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular, to a multi-path planning method and system for unmanned aerial vehicles, a computer device, and a storage medium. Background Art

[0002] Due to characteristics such as low cost, high mobility, flexible deployment, and "zero casualties", unmanned aerial vehicles are widely used in military and civilian fields. When performing tasks such as military surveillance and reconnaissance, and search and rescue in large disaster scenarios, unmanned aerial vehicles face adverse factors such as a vast mission area, complex and changeable environment, limited sensor perception ability, and uncertain flight risk levels, which can easily lead to mission failure.

[0003] An existing method for path planning of unmanned aerial vehicles cannot take into account multiple optimal paths existing in the same environmental conditions. Among them, the shortest path is always the first consideration target for this type of problem, and decision-makers often can only passively select the optimal path planned by the system.

[0004] Therefore, there is an urgent need to propose a multi-path planning method for unmanned aerial vehicles to solve the problems raised. Summary of the Invention

[0005] Based on this, in view of the deficiencies of the prior art, it is necessary to provide a multi-path planning method and system for unmanned aerial vehicles, a computer device, and a storage medium, to obtain multiple optimal flight paths for unmanned aerial vehicles, facilitate the selection of diverse flight paths for unmanned aerial vehicles, and improve the completion rate of unmanned aerial vehicle flight missions.

[0006] To solve the above technical problems, the technical solutions adopted by the present invention are as follows:

[0007] In a first aspect, a multi-path planning method for unmanned aerial vehicles is provided, which includes the following steps:

[0008] Step S110: Construct a two-dimensional grid model of the unmanned aerial vehicle group, and obtain the risk coefficient R of each grid in the two-dimensional grid model of the unmanned aerial vehicle group i,j ; where each grid is represented by a set of indexes (i, j), and R i,j ∈[0, 1];

[0009] Step S120: According to the grid corresponding to the initial point and the grid corresponding to the target point of the unmanned aerial vehicle in the two-dimensional grid model of the unmanned aerial vehicle group, obtain the data on the cost of the grid planning path of the unmanned aerial vehicle;

[0010] Step S130: Based on the target evolutionary algorithm, perform route planning on the flight path of the unmanned aerial vehicle to obtain multiple pieces of information on the optimal flight paths of the unmanned aerial vehicle;

[0011] Step S140: Among the multiple optimal UAV flight path information, send one of the optimal UAV flight path information to the UAV, and the UAV flies to the grid area corresponding to the target point according to the received optimal UAV flight path information.

[0012] In a second aspect, a UAV multi-path planning system is provided, which includes:

[0013] A spatial grid modeling module, configured to construct a two-dimensional grid model of the UAV swarm and obtain the danger coefficient R of each grid in the two-dimensional grid model of the UAV swarm i,j ;

[0014] A planned path cost module, configured to obtain UAV grid planned path cost data according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the UAV swarm;

[0015] A path planning module, configured to perform route planning on the UAV flight path based on the target evolutionary algorithm and obtain multiple optimal UAV flight path information;

[0016] A flight path execution module, configured to send one of the multiple optimal UAV flight path information to the UAV, and the UAV flies to the grid area corresponding to the target point according to the received optimal UAV flight path information.

[0017] In a third aspect, a device is provided, which includes a memory and a processor. A computer program is stored on the memory, and when the processor executes the computer program, the above-mentioned UAV multi-path planning method is implemented.

[0018] In a fourth aspect, a storage medium is provided, which stores a computer program. The computer program includes program instructions, and when the program instructions are executed, the above-mentioned UAV multi-path planning method is implemented.

[0019] In summary, the UAV multi-path planning method and system, computer device and storage medium of the present invention obtain UAV grid planned path cost data through the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the UAV swarm, perform route planning on the UAV flight path based on the target evolutionary algorithm, and obtain multiple optimal UAV flight path information, which is convenient for the UAV to make diverse choices of flight paths and effectively improves the completion degree of the UAV flight mission. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic flowchart of the first UAV multi-path planning method provided by an embodiment of the present invention;

[0021] Figure 2It is a schematic flowchart of the second multi-path planning method for unmanned aerial vehicles provided by an embodiment of the present invention;

[0022] Figure 3 It is a schematic flowchart of the third multi-path planning method for unmanned aerial vehicles provided by an embodiment of the present invention;

[0023] Figure 4 It is a schematic flowchart of the fourth multi-path planning method for unmanned aerial vehicles provided by an embodiment of the present invention;

[0024] Figure 5 It is a schematic flowchart of the fifth multi-path planning method for unmanned aerial vehicles provided by an embodiment of the present invention;

[0025] Figure 6 It is a structural block diagram of the first multi-path planning system for unmanned aerial vehicles provided by an embodiment of the present invention;

[0026] Figure 7 It is a structural block diagram of the second multi-path planning system for unmanned aerial vehicles provided by an embodiment of the present invention;

[0027] Figure 8 It is a structural block diagram of the third multi-path planning system for unmanned aerial vehicles provided by an embodiment of the present invention;

[0028] Figure 9 It is a structural block diagram of a computer device provided by an embodiment of the present invention;

[0029] Figure 10 It is a schematic diagram of two optimal paths for the flight of an unmanned aerial vehicle provided by an embodiment of the present invention. Detailed implementation manners

[0030] To further understand the features, technical means, and specific purposes and functions achieved by the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0031] Figure 1 It is a schematic flowchart of the first multi-path planning method for unmanned aerial vehicles provided by an embodiment of the present invention. As Figure 1 shown, this multi-path planning method for unmanned aerial vehicles includes steps S110 to S140, which are specifically as follows:

[0032] Step S110: Construct a two-dimensional grid model of the unmanned aerial vehicle group, and obtain the danger coefficient R of each grid in the two-dimensional grid model of the unmanned aerial vehicle group i,j ; where each grid is represented by a set of indexes (i, j), and R i,j ∈ [0, 1].

[0033] In this embodiment, the passing grade P corresponding to the grid can be obtained through the danger coefficient R of the grid i,j i,j, P i,j ∈ [0, 1].

[0034] The method of step S110 specifically includes the following operations:

[0035] Obtain the risk information of each location of the UAV swarm in the mission execution area. The risk information includes the building range, building spacing, communication signal strength, etc. in the mission execution area. By mapping the geographical space where the UAV swarm mission execution area is located, detect the signal strength of the corresponding communication band in the UAV swarm mission execution area.

[0036] Divide the mission execution area into multiple grids according to the preset grid size, and construct a two-dimensional grid model of the UAV swarm; among them, the grid size is determined according to needs. In this embodiment, the grid area size of the mission execution area is 1m * 1m;

[0037] Obtain the danger coefficient R of each grid in the two-dimensional grid model of the UAV swarm based on the risk information i,j ; where each grid is represented by a set of indexes (i, j). Based on the judgment of the risk information of each location in the mission execution area, obtain the corresponding danger coefficient when the UAV passes through different grids. The risk information corresponding to the grid is the sampling result of the grid center point. The grid passing level refers to the probability of the UAV passing through the grid, and the grid danger coefficient refers to the degree of danger of the UAV passing through the grid. When there are areas corresponding to grids such as buildings and high-intensity reconnaissance, they are divided into non-passable areas, the passing level intensity of this grid is recorded as 0, and the danger coefficient of this grid is infinite. In this embodiment, the danger coefficient intensity of this grid can be recorded as 1.

[0038] Specifically, move the UAV used for identification in the mission execution area. Assume that the UAV can pass through a blank area unobstructed on the horizontal plane at a fixed height in space. There are risk areas and danger coefficients in the grid space of the two-dimensional grid model of the UAV swarm, and the passing level of whether to allow passage can be added to the fixed height horizontal plane of the two-dimensional grid model of the UAV swarm.

[0039] Step S120: Obtain the UAV grid planning path cost data according to the grid corresponding to the initial point and the grid corresponding to the target point of the UAV in the two-dimensional grid model of the UAV swarm; where the initial point of the UAV is the flight starting point of the UAV, and the target point of the UAV is the flight end point of the UAV set by the user. The UAV planning path cost data represents the difficulty of the UAV flying from the initial grid point to the target grid point. The UAV planning path cost data is the UAV flight path f1 = ∑path and the UAV flight grid area danger coefficient f2 = ∑path * R ijThe accumulation, where path represents the set of grid points corresponding to the grids traversed by the UAV flight path. That is, all the grids passed by the UAV flight path are set as grid points to form a set of grid points. The given grid points are represented by the index (i, j). By accumulating the risk coefficients corresponding to the grids passed by the UAV flight path, the risk coefficient of the UAV flight grid area is obtained.

[0040] Specifically, the method in step S120 is specifically operated as follows:

[0041] Based on the multi-objective evolutionary algorithm, the multi-objective evolutionary algorithm is initialized according to the grid corresponding to the initial point and the grid corresponding to the target point of the UAV in the two-dimensional grid model of the UAV swarm. The multi-objective evolutionary algorithm conducts a preliminary exploration of the population to optimize the UAV flight path and the risk coefficient of the UAV flight grid area, and obtain the data on the cost of the UAV grid planning path. Among them, the multi-objective evolutionary algorithm is initialized by using a heuristic rule, and the heuristic rule is completed by the traditional A* algorithm, which is a known technology and will not be elaborated here.

[0042] Since most UAVs fly at a constant altitude, the UAV flight space is set on a horizontal plane at a fixed altitude. Assuming the area where the UAV flies is a blank area, the obstacles that appear in the space must be marked first so that the UAV can avoid colliding with it. If the obstacle is a large object, such as a building, it is considered a continuous obstacle, and the passing level intensity of the multiple grids corresponding to this obstacle is 0, and the risk coefficient intensity is 1.

[0043] According to the target location set by the user, in this embodiment, it is assumed that the starting point coordinates are in the upper left corner of the two-dimensional grid map, as Figure 10 shown, two schematic diagrams of the optimal paths in this embodiment are given. Among them, the small black dots represent that the area can be passed, the large black dots represent that there are risks in the area, and the large gray dots correspond to the initial point and the target point on the UAV flight path. Among these two feasible paths, the path lengths are both 41, and the number of risk areas passed through is 4. However, these two paths are completely different.

[0044] Information such as risk preference is used to initialize the multi-objective evolutionary algorithm. Specifically, the multi-objective evolutionary algorithm uses an initialization method containing heuristic rules to conduct a preliminary exploration of the population, and can optimize two objective functions simultaneously: the UAV flight path objective function and the UAV flight grid area risk coefficient objective function. The data on the cost of the UAV grid planning path is obtained by accumulating the UAV flight path and the UAV flight grid area risk coefficient. The multi-objective evolutionary algorithm adopts a multi-modal multi-objective evolutionary algorithm.

[0045] Step S130: Based on the target evolutionary algorithm, perform route planning on the UAV flight path to obtain multiple pieces of optimal UAV flight path information, which facilitates the diverse selection of the UAV flight path and improves the completion rate of the UAV flight mission.

[0046] For users, different risk levels often correspond to different path lengths and mission costs. When users want to know multiple paths with the same objective value, in this case, it is very important to improve the diversity of the obtained solutions; on the other hand, in the case of the same risk level and path length, if multiple different paths can be obtained, it is extremely helpful for the completion of the mission. If multiple optimal paths are pre-planned through a calculation method and then the user selects the preferred path and provides it to the UAV, the mission completion rate can be greatly improved.

[0047] Specifically, the method of step S130 specifically includes the following operations:

[0048] Step S131: In the search stage of the target evolutionary algorithm, the target evolutionary algorithm pays attention to the diversity index of the population. In each iterative calculation, it can retain potential optimal individuals according to the current population characteristics, retain different individuals with similar objective functions, and finally output multiple pieces of optimal UAV flight path information; among them, since the path cost data consists of two objective functions, namely the UAV flight path objective function and the flight area risk coefficient objective function, corresponding to the grid point number and the danger coefficient respectively. For the same path cost data, such as a grid point number of 10 and a danger coefficient of 0.8, there may be multiple different UAV flight paths to meet the requirements, and the target evolutionary algorithm can automatically obtain the UAV flight paths corresponding to the same path cost data.

[0049] Furthermore, the method of retaining potential optimal individuals according to the current population characteristics in step S131 specifically operates as follows:

[0050] In each generation of iterative evolution of the target evolutionary algorithm, an improved population crowding degree calculation method is used to select and sort individuals. The population crowding degree f i d The calculation method is expressed as

[0051]

[0052] where L i 、L j represent the path length, represents the common path length of two paths, CD max is the maximum value in CD i,j and CD i,j represents the difference size between individual i and individual j.

[0053] In each generation of iterative evolution, the target evolutionary algorithm uses a special environmental selection strategy to select the offspring population. Specifically, first, a duplication check is performed on all individuals, and exactly the same individuals are deleted. Then, the individuals are sorted using Pareto dominance sorting and population crowding degree as sorting criteria, and the offspring individuals are selected; an individual refers to a solution in the population; deleting exactly the same individuals (solutions) means that if the paths represented by two individuals are exactly the same, then one of them is deleted; Pareto dominance sorting is an existing algorithm, and the population crowding degree is the index f i d , and the individuals are sorted according to two criteria, Pareto dominance sorting and population crowding degree, and the first N (population size) individuals are selected to enter the next generation.

[0054] As Figure 2 shown, in one embodiment, before the step S130, it further includes

[0055] Step S130-1: Set the risk coefficient threshold of the UAV flight grid area; according to the risk preference information provided by the user, set the risk coefficient threshold of the UAV flight grid area, which is represented by a value between 0 and 1. The higher the risk coefficient threshold of the UAV flight grid area, the greater the UAV flight risk that the user can bear, and there are more possibilities for the UAV flight path.

[0056] Step S140: Send one of the multiple UAV flight optimal path information to the UAV among the multiple UAV flight optimal path information. The UAV flies to the grid area corresponding to the target point according to the received UAV flight optimal path information, realizing the automatic flight operation of the UAV; specifically, the user selects one of the multiple UAV flight optimal path information according to the demand, and the UAV automatically reaches the grid area where the target point is located according to the path planning result, facilitating the diverse selection of the UAV flight path and improving the completion degree of the UAV flight mission.

[0057] Among them, the multiple UAV flight optimal path information obtained in step S130 will be provided for the user to select. In this process, the user can choose to dispatch more than one UAV to execute the task. Different UAVs automatically reach the target point according to different UAV flight optimal path information selected by the user. By deploying more than one UAV to execute the task on the optimal path, the possibility of the UAV task being successful will be greatly improved.

[0058] As Figure 3 shown, in one embodiment, after the step S140, it further includes

[0059] Step S150: When the UAV performs a mission based on the received optimal flight path information of the UAV, it determines whether there are obstacles on the path of the UAV from the current grid point to the next grid point. If so, it identifies the obstacles that cannot be jumped over, and uses the communication unit to obtain the next optimal flight path information of the UAV from the computer device; if not, it executes step S140; wherein the communication unit is a device brought into the UAV to establish a wireless communication network between the UAV and the computer device.

[0060] like Figure 4 As shown, in one embodiment, after step S140, the process further includes

[0061] Step S160: When the UAV performs a task based on the received UAV flight optimal path information, it determines whether the current UAV flight optimal path meets the pass conditions. If so, step S140 is executed; if not, the communication unit is used to obtain the next UAV flight optimal path information from the computer device; wherein the communication unit is a setting provided by the UAV to establish a wireless communication network between the UAV and the computer device.

[0062] A multi-path planning method for unmanned aerial vehicles (UAVs) of the present invention obtains the grid planning path consumption data of the UAVs through the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the UAV swarm, plans the flight path of the UAVs based on the target evolution algorithm, obtains the optimal flight path information of multiple UAVs, facilitates the UAVs to make diverse flight path selections, and effectively improves the completion rate of the UAV flight mission.

[0063] like Figure 5 As shown, in order to make the technical solution of the present invention clearer, the preferred embodiments are described below.

[0064] Step S110: construct a two-dimensional grid model of the drone swarm and obtain the risk coefficient R of each grid in the two-dimensional grid model of the drone swarm. i,j ;

[0065] Step S120: Obtaining the grid planning path cost data of the drone according to the grid corresponding to the initial point and the grid corresponding to the target point of the drone in the two-dimensional grid model of the drone swarm;

[0066] Step S130-1, setting a danger factor threshold for the UAV flight grid area;

[0067] Step S130: planning the flight path of the UAV based on the target evolution algorithm to obtain optimal flight path information of multiple UAVs;

[0068] Step S140: Among the multiple pieces of optimal UAV flight path information, send one piece of optimal UAV flight path information to the UAV. The UAV flies to the grid area corresponding to the target point according to the received optimal UAV flight path information;

[0069] Step S150: When the UAV executes a task according to the received optimal UAV flight path information, determine whether there are obstacles on the path of the UAV from the current grid point to the next grid point. If so, it is recognized that there are obstacles that cannot be flown over, and the next piece of optimal UAV flight path information is obtained from the computer device using the communication unit; if not, execute Step S140.

[0070] Figure 6 It is the structural block diagram of the first UAV multi-path planning system provided by the embodiments of the present invention. As Figure 6 shown, corresponding to the above UAV multi-path planning method, the present invention also provides a UAV multi-path planning system. The UAV multi-path planning system includes modules for executing the above UAV multi-path planning method. This system can be configured in terminals such as computer devices. Applying the UAV multi-path planning system of the present invention, by the UAV in the grids corresponding to the initial point and the target point in the two-dimensional grid model of the UAV swarm, the data on the cost of the UAV grid planning path is obtained, and the flight path of the UAV is route-planned based on the target evolutionary algorithm to obtain multiple pieces of optimal UAV flight path information, which facilitates the diverse selection of the UAV flight path and effectively improves the completion degree of the UAV flight task.

[0071] Specifically, as Figure 6 shown, the UAV multi-path planning system includes a spatial grid modeling module, a planned path cost module, a path planning module, and a flight path execution module.

[0072] The spatial grid modeling module is used to construct a two-dimensional grid model of the UAV swarm and obtain the risk coefficient R of each grid in the two-dimensional grid model of the UAV swarm i,j ;

[0073] The planned path cost module is used to obtain the UAV grid planning path cost data according to the grids corresponding to the initial point and the target point in the two-dimensional grid model of the UAV swarm;

[0074] The path planning module is used to perform route planning on the UAV flight path based on the target evolutionary algorithm to obtain multiple pieces of optimal UAV flight path information;

[0075] The flight path execution module is used to send one piece of optimal UAV flight path information among the multiple pieces of optimal UAV flight path information to the UAV. The UAV flies to the grid area corresponding to the target point according to the received optimal UAV flight path information.

[0076] Figure 7 It is the structural block diagram of the second UAV multi-path planning system provided by the embodiments of the present invention. As Figure 7 shown, a UAV multi-path planning system provided in this embodiment is based on the above-mentioned UAV multi-path planning system and adds an obstacle judgment module. The obstacle judgment module is used to judge whether there are obstacles on the path of the UAV from the current grid point to the next grid point when the UAV executes a task according to the received optimal UAV flight path information. If so, the next optimal UAV flight path information is obtained from the computer device by using the communication unit.

[0077] Figure 8 It is the structural block diagram of the second UAV multi-path planning system provided by the embodiments of the present invention. As Figure 8 shown, a UAV multi-path planning system provided in this embodiment is based on the above-mentioned UAV multi-path planning system and adds a threshold setting module. The threshold setting module is used to set the risk coefficient threshold of the UAV flight grid area; according to the risk preference information provided by the user, the risk coefficient threshold of the UAV flight grid area is set, which is represented by a value between 0 and 1. The higher the risk coefficient threshold of the UAV flight grid area, the greater the UAV flight risk that the user can bear, and there are more selection possibilities for the UAV flight path.

[0078] It should be noted that those skilled in the art can clearly understand the specific implementation processes of the above-mentioned UAV multi-path planning system and each module, and can refer to the corresponding descriptions in the foregoing method embodiments. For the convenience and conciseness of description, they will not be elaborated here.

[0079] Figure 9 It is the internal structural block diagram of a computer device provided by the embodiments of the present invention. As Figure 9 shown, the computer device provided by the present invention includes a memory, a processor, and a network interface connected through a system bus; a computer program is stored on the memory, and the processor is used to provide computing and control capabilities to support the operation of the entire computer device. When the processor executes the computer program, the above-mentioned UAV multi-path planning method is implemented.

[0080] The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the UAV multi-path planning method.

[0081] The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the multi-path planning method for the unmanned aerial vehicle. The network interface is used for network communication with other devices. Those skilled in the art can understand that Figure 9 The structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on other computer devices to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0082] In one embodiment, the multi-path planning method for the unmanned aerial vehicle provided by this application can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 9 . Each program module that makes up the multi-path planning system for the unmanned aerial vehicle can be stored in the memory of the computer device. For example, Figure 6 The acquisition module 110, transformation module 120, construction module 130, and judgment module 140 shown in. The computer program composed of each program module enables the processor to execute the steps of the multi-path planning system for the unmanned aerial vehicle in each embodiment described in this specification. For example, Figure 6 The computer device shown in can build a two-dimensional grid model of the unmanned aerial vehicle group through the space grid modeling module in the multi-path planning system for the unmanned aerial vehicle as shown in Figure 4 to obtain the risk coefficient R of each grid in the two-dimensional grid model of the unmanned aerial vehicle group i,j ; the path planning cost module obtains the data of the grid planning path cost of the unmanned aerial vehicle according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the unmanned aerial vehicle group; the path planning module plans the flight path of the unmanned aerial vehicle based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal flight paths of the unmanned aerial vehicle; the flight path execution module sends one of the pieces of information on the optimal flight paths of the unmanned aerial vehicle to the unmanned aerial vehicle among the multiple pieces of information on the optimal flight paths of the unmanned aerial vehicle, and the unmanned aerial vehicle flies to the grid area corresponding to the target point according to the received information on the optimal flight path of the unmanned aerial vehicle.

[0083] In one embodiment, a computer device is proposed, including a memory and a processor. The memory and the processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to execute the following steps: Step S110, build a two-dimensional grid model of the unmanned aerial vehicle group, and obtain the risk coefficient R of each grid in the two-dimensional grid model of the unmanned aerial vehicle group i,j; Step S120: Obtain the data on the cost of the grid planning path of the UAV according to the grids corresponding to the initial point and the target point in the two-dimensional grid model of the UAV swarm; Step S130: Perform route planning on the UAV flight path based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal UAV flight paths; Step S140: Send one of the pieces of information on the optimal UAV flight paths to the UAV among the multiple pieces of information on the optimal UAV flight paths, and the UAV flies to the grid area corresponding to the target point according to the received information on the optimal UAV flight path.

[0084] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, and the storage medium is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0086] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, where the computer program includes program instructions. When the program instructions are executed by the processor, the processor performs the following steps: Step S110: Construct a two-dimensional grid model of the UAV swarm and obtain the risk coefficient R of each grid in the two-dimensional grid model of the UAV swarm i,j; Step S120: Obtain the data on the cost of the grid planning path of the UAV according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the UAV swarm; Step S130: Perform route planning on the flight path of the UAV based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal flight paths of the UAV; Step S140: Send one piece of information on the optimal flight path of the UAV among the multiple pieces of information on the optimal flight paths of the UAV to the UAV, and the UAV flies to the grid area corresponding to the target point according to the received information on the optimal flight path of the UAV.

[0087] The storage medium may be various computer-readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disc that can store program codes.

[0088] In summary, in a UAV multi-path planning method, system, device, and storage medium according to the present invention, the data on the cost of the grid planning path of the UAV is obtained according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the UAV swarm, and route planning is performed on the flight path of the UAV based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal flight paths of the UAV, which facilitates the diverse selection of the flight path of the UAV and effectively improves the completion degree of the flight mission of the UAV.

[0089] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0090] In several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and 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.

[0091] The steps in the method of the embodiments of the present invention can be adjusted in sequence, combined, and deleted according to actual needs. The units in the device of the embodiments of the present invention can be combined, divided, and deleted according to actual needs. In addition, the functional units in various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a device (which can be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention.

[0092] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the appended claims.

Claims

1. A method for multi-path planning of an unmanned aerial vehicle, characterized in that, It includes the following steps: Step S110: Construct a two-dimensional grid model of the UAV swarm and obtain the danger coefficient R of each grid in the two-dimensional grid model of the UAV swarm i,j ; where each grid is represented by a set of indices (i, j), and R i,j ∈[0, 1]; Step S120: Obtain the data of the drone grid planning path cost according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the drone swarm. Step S130: Perform route planning on the drone flight path based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal drone flight paths. Step S140: Send one piece of information on the optimal drone flight path among the multiple pieces of information on the optimal drone flight paths to the drone, and the drone flies to the grid area corresponding to the target point according to the received information on the optimal drone flight path. Among them, the method of step S130 specifically includes the following operations: In the search stage of the target evolutionary algorithm, the target evolutionary algorithm focuses on the diversity index of the population. In each iterative calculation, it can retain potential optimal individuals according to the characteristics of the current population, retain different individuals with similar objective functions, and finally output multiple pieces of information on the optimal drone flight paths. Among them, the method of retaining potential optimal individuals according to the characteristics of the current population in each iterative calculation is specifically as follows: In each generation of iterative evolution of the target evolutionary algorithm, an improved population crowding degree calculation method is used to select and sort individuals, and the population crowding degree f i d The calculation method is expressed as Among them, Li and L j represent the path length, represents the common path length of two paths, CD max is CD i,j the maximum value in CD i,j represents the difference between individual i and individual j, and N represents the population size.

2. The multi-path planning method for an unmanned aerial vehicle according to claim 1, wherein: Before step S130, it also includes Step S130-1: Set the threshold of the risk coefficient of the drone flight grid area.

3. The method for multi-path planning of an unmanned aerial vehicle according to claim 1, wherein The method of step S110 specifically includes the following operations: Obtain the risk information of each location in the task execution area of the drone swarm. Divide the task execution area into multiple grids according to the preset grid size, and construct a two-dimensional grid model of the drone swarm. Obtain the risk coefficient of each grid in the two-dimensional grid model of the drone swarm based on the risk information.

4. The multi-path planning method for an unmanned aerial vehicle according to claim 1, characterized in that The method of step S120 is specifically as follows: Based on the multi-objective evolutionary algorithm, initialize the multi-objective evolutionary algorithm according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the drone swarm. The multi-objective evolutionary algorithm conducts a preliminary exploration of the population to optimize the drone flight path and the risk coefficient of the drone flight grid area, and obtain the data of the drone grid planning path cost.

5. A multi-path planning system for an unmanned aerial vehicle, characterized in that, It includes: Spatial grid modeling module, used to construct a two-dimensional grid model of the UAV swarm and obtain the risk coefficient R of each grid in the two-dimensional grid model of the UAV swarm i,j ; A planned path cost module, which is used to obtain the data of the drone grid planning path cost according to the grid corresponding to the initial point and the grid corresponding to the target point in the two-dimensional grid model of the drone swarm. A path planning module, which is used to perform route planning on the drone flight path based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal drone flight paths. A flight path execution module, which is used to send one piece of information on the optimal drone flight path among the multiple pieces of information on the optimal drone flight paths to the drone, and the drone flies to the grid area corresponding to the target point according to the received information on the optimal drone flight path. Among them, the method of the path planning module for performing route planning on the drone flight path based on the target evolutionary algorithm to obtain multiple pieces of information on the optimal drone flight paths specifically includes the following operations: In the search stage of the target evolutionary algorithm, the target evolutionary algorithm pays attention to the diversity index of the population. In each iterative calculation, it can retain potential optimal individuals according to the characteristics of the current population, retain different individuals with similar objective functions, and finally output multiple pieces of optimal path information for UAV flight. Among them, the method of retaining potential optimal individuals according to the characteristics of the current population in each iterative calculation is specifically as follows: In each generation of iterative evolution of the target evolutionary algorithm, an improved population crowding degree calculation method is used to select and sort individuals, and the population crowding degree f i d The calculation method is expressed as Among them, Li and L j represent the path length, represents the common path length of two paths, CD max is CD i,j the maximum value in CD i,j represents the difference between individual i and individual j, and N represents the population size.

6. A device, characterized in that: The device includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, it implements the UAV multi-path planning method according to any one of claims 1-4.

7. A storage medium, characterized in that: The storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed, they implement the UAV multi-path planning method according to any one of claims 1-4.

Images