A method, device and storage medium for aircraft attack route planning

Through the particle swarm search algorithm combined with the Dubins path and the air surface weapon delivery zone model, the NP problem in aircraft route planning is solved, and the fast and accurate route planning is achieved in aircraft attack missions, meeting the time efficiency and accuracy requirements.

CN115167526BActive Publication Date: 2024-12-06TIANJIN JINHANG COMP TECH RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211009329.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-22
Publication Date
2024-12-06
Estimated Expiration
2042-08-22

AI Technical Summary

Technical Problem

Vehicle route planning is a typical NP problem. Existing algorithms are difficult to give global optimal solutions in a short time, especially in aircraft attack missions that require rapid response to emergencies. The existing technology is difficult to achieve time efficiency and accuracy. Find balance between them.

Method used

The particle swarm search algorithm is used to combine the Dubins path, and by establishing the target's air surface weapon delivery area model and setting the wall collision strategy of the particle swarm search space, the optimal aircraft attack route is iterated to meet the aircraft's flight constraints and fast navigation needs.

Benefits of technology

Given high-precision aircraft attack routes in a short time, it is suitable for online re-planning and pre-planning, providing quick and effective navigation guidance to ensure that the aircraft reaches the target delivery area quickly and accurately.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115167526B_ABST
    Figure CN115167526B_ABST
Patent Text Reader

Abstract

The present application provides a method, device and storage medium for aircraft attack route planning, the method comprising the following steps: S1, establishing a LAR model of the target's air-to-surface weapon delivery area; S2, establishing a particle swarm search model; S3, setting the wall collision strategies of each dimension of the particle swarm search space according to the LAR model; S4, iterating the optimal Dubins planning path through particle swarm search and outputting it. The present invention takes into account the flight constraints of the aircraft, combines the classic Dubins path and particle swarm optimization intelligent algorithm, can give a high-precision planning route in a relatively short time, and guide the aircraft to the target delivery area as quickly as possible; in addition, the present invention is suitable for online re-planning of the aircraft's route, thereby providing rapid and effective guidance for the pilot to complete the task of attacking the target, or as a functional component of route pre-planning, providing a corresponding planning route for the attack process after entering the battlefield.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] Aircraft route planning refers to finding the optimal route or path for an aircraft from its starting point to its target point while satisfying the aircraft's performance constraints. Unlike the general traveling salesman problem (TSP) and path planning problem, aircraft route planning needs to consider the aircraft's own constraints, thus placing certain requirements on the flyability of the route. For aircraft attack missions, route planning can be mainly divided into two categories: pre-route planning and online route re-planning, depending on the timing of use.

[0003] Pre-planning is to plan the complete route of aircraft take-off, entering the battlefield, attacking targets and returning in advance according to battlefield terrain, weather information, threats and target distribution, etc. During the mission preparation phase, the algorithm with large computational complexity and long solution time but good planning effect can usually be selected because it is executed during the mission preparation phase.

[0004] Online route replanning is when an aircraft is in flight and needs to use onboard avionics equipment to update local routes in a timely manner due to unexpected situations such as target updates and threat changes. Due to the sensitivity of aircraft to time during mission execution, the algorithm used needs to prioritize timeliness without pursuing global optimality. Usually, a suboptimal solution that satisfies accuracy is sufficient.

[0005] Route planning can be classified according to the purpose of use and the type of algorithm. According to the type of algorithm, route planning algorithms can be divided into traditional classical algorithms and modern intelligent algorithms. Traditional classical route planning algorithms include Dijkstra method, artificial potential field method, simulated annealing algorithm, etc. Modern intelligent algorithms and heuristic algorithms include A* algorithm, RRT algorithm, genetic algorithm, ant colony optimization algorithm and particle swarm optimization algorithm, etc.

[0006] Since route planning is a typical NP-hard problem, that is, as the number of route nodes increases, the amount of solution calculation and the required computing resources such as memory increase exponentially, route planning usually cannot give a global optimal solution in a short time through a specific algorithm. To solve the above problems, the present application proposes a method, device and storage medium for aircraft attack route planning. Summary of the invention

[0007] The purpose of this application is to provide a method, device and storage medium for aircraft attack route planning in order to solve the above problems. The specific technical solution is as follows:

[0008] In a first aspect, the present application provides a method for aircraft attack route planning, the method comprising the following steps:

[0009] S1. Establish the LAR model of the target's air-to-surface weapon delivery area;

[0010] S2, establish a particle swarm search model;

[0011] S3, setting the wall collision strategy of each dimension of the particle swarm search space according to the LAR model;

[0012] S4. Iterate the optimal Dubins planning path through particle swarm search and output it.

[0013] According to the technical solutions provided by certain embodiments of the present application, the LAR model of the target air-to-surface weapon delivery area is established in step S1, which specifically includes:

[0014] S11. According to the planned height target position of the aircraft, solve the minimum launch distance d of air-to-surface weapons Near and the maximum transmission distance d Far ;

[0015] S12. Establish the LAR model of the target air-to-surface weapon delivery area based on whether there is a heading constraint. When there is no heading constraint, the LAR model is composed of d Near and d Far is the radius, a closed circle around the target; when there is a heading constraint, the LAR model is composed of d Near and d Far The radius is a closed sector ring around the target.

[0016] According to the technical solutions provided by some embodiments of the present application, a particle swarm search model is established in step S2, specifically including:

[0017] S21, setting a search space; the search space is the distance from the end point of the route to the target, and the relative azimuth between the end point of the route and the target;

[0018] S22, using the Dubins path as the actual flight track from the starting point to the end point of the route of the aircraft, and calculating the minimum turning radius of the Dubins path according to the maximum normal overload and the planned speed of the aircraft;

[0019] S23. The path length of the Dubins path is used as the cost function value of the particle.

[0020] According to the technical solutions provided by some embodiments of the present application, in step S3, setting the wall collision strategies of each dimension of the particle swarm search space according to the LAR model specifically includes:

[0021] S31, setting the particle swarm search collision strategy in each dimension to completely absorb the wall, restricting the position to the wall after colliding with the wall, and setting the speed to zero;

[0022] S32. Determine whether there is a route restriction constraint. If yes, set the azimuth dimension in the search space to a transparent wall. Normalize the azimuth after colliding with the wall, and keep the speed unchanged.

[0023] According to the technical solutions provided in some embodiments of the present application, in step S4, the optimal Dubins planning path is iterated through particle swarm search and output, which specifically includes:

[0024] S41, randomly initialize the position and velocity of each particle within the constraint range;

[0025] S42, updating the velocity and position of each particle, and performing relevant processing according to the wall collision strategy;

[0026] S43, respectively updating the historical optimal position and cost function value of each particle and population;

[0027] S44, repeating the above updating process until the convergence condition is met or the maximum number of iterations is reached;

[0028] S45. Output the Dubins path represented by the historical optimal position of the population as the attack planning route of the aircraft.

[0029] In a second aspect, the present application further provides an aircraft attack route planning device, the aircraft attack route planning device comprising:

[0030] A memory, a processor, and a computer program stored in the memory and executable on the processor;

[0031] When the computer program is executed by the processor, the steps of any one of the above-mentioned aircraft attack route planning methods are implemented.

[0032] In a third aspect, the present application also provides a computer-readable storage medium, on which is stored an aircraft attack route planning program, which, when executed by a processor, implements the steps of any of the above-mentioned aircraft attack route planning methods.

[0033] Compared with the prior art, the beneficial effects of the present application are as follows: the aircraft attack route planning method provided by the present application first solves the LAR model of the target's air-to-surface weapon delivery area, then establishes a particle swarm search model, each particle represents a Dubins planned route with good flyability, and then sets the wall collision strategies of each dimension of the particle swarm search space according to the LAR model, and finally iterates the optimal Dubins planned path through the particle swarm search and outputs it; the present invention takes into account the flight constraints of the aircraft, combines the classic Dubins path and the particle swarm optimization intelligent algorithm, and can give a high-precision planned route in a shorter time, guiding the aircraft to the target delivery area as quickly as possible; in addition, the present invention is suitable for online re-planning of the aircraft's route, thereby providing rapid and effective guidance for the pilot to complete the target's strike mission, or as a functional component for route pre-planning, providing a corresponding planned route for the attack process after entering the battlefield. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of the aircraft attack route planning method provided in Example 1 of the present application;

[0035] Figure 2 A schematic diagram of a LAR model of an aircraft attack route planning method provided in Example 1 of the present application;

[0036] Figure 3 A detailed flowchart of the method for aircraft attack route planning provided in Example 1 of the present application;

[0037] Figure 4 A schematic diagram of the structure of the server provided in Example 4 of the present application.

[0038] The text annotations in the figure represent:

[0039] 400, server; 401, central processing unit (CPU); 402, read-only memory (ROM); 403, random access memory (RAM); 404, bus; 405, input / output (I / O) interface; 406, input part; 407, output part; 408, storage part; 409, communication part; 410, drive; 411, removable media. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Embodiment 1

[0042] The current design of route planning algorithms usually focuses on threat avoidance, terrain following, etc. In the process of developing and designing new aircraft, for target attack missions, quickly guiding the aircraft to the target designated launch area (LAR) and completing the attack mission is an important direction for the development of today's aircraft attack route planning.

[0043] This embodiment provides a method for aircraft attack route planning. A brief flowchart of the method is shown below: Figure 1 As shown, the method comprises the following steps:

[0044] S1. Establish the LAR model of the target's air-to-surface weapon delivery area.

[0045] When the aircraft is in the delivery area and its heading is aligned with the target, the attack mission is considered completed. The LAR model of the target's air-to-surface weapon delivery area is established, including:

[0046] S11. According to the planned height target position of the aircraft, solve the minimum launch distance d of air-to-surface weapons Near and the maximum transmission distance d Far ;

[0047] According to the target coordinate position (x t ,y t ), the type of air-to-surface weapon used, and combined with the planned altitude of the aircraft, the air-to-surface weapon delivery distance limit can be solved by the polynomial fitting method. Here, the delivery distance limit refers to the distance between the weapon delivery point and the target position. It is a range. Only when the distance between the weapon delivery point and the target position is within d Near ~d Far Only when you are within range can you hit the target.

[0048] S12. Establish the LAR model of the target air-to-surface weapon delivery area based on whether there is a heading constraint. When there is no heading constraint, the LAR model is composed of d Near and d Far is the radius, a closed circle around the target; when there is a heading constraint, the LAR model is composed of d Near and d Far The radius is a closed sector ring around the target.

[0049] Please refer to Figure 2 If there is no heading constraint during the attack process, the target's air-to-surface weapon release area (LAR) is given by d Near and d Far is the radius of the closed circle around the target; if there is a heading constraint, LAR .... Near and d Far is the radius and the side boundary is and Together they form a closed fan ring, in which and They refer to the attack heading, that is, the angle between the velocity vector of the aircraft when it flies to this point and the true north direction. This is the range of the angle between the velocity vector and the true north direction under the heading constraint. For example, assuming The value is 0°. If the value is 10°, the target can only be attacked from 0° to 10°. At this time, the aircraft is south of the target, that is, 180° to 190° from the target.

[0050] In summary, the target air-to-surface weapon delivery zone LAR model established in the embodiment of the present application is divided into a closed circular ring or a closed sector ring with side boundaries.

[0051] S2. Establish a particle swarm search model.

[0052] A particle swarm search model is established, and the search space is set as the distance and azimuth from the end point of the route to the target. Each particle represents the end point of a route. The Dubins path from the starting point of the aircraft to the end point is used as the actual flight track, and the minimum turning radius of Dubins is calculated by the maximum normal overload constraint of the aircraft, and the Dubins path length is set as the cost function value. The specific steps include:

[0053] S21, setting a search space; the search space is the distance from the end point of the route to the target, and the relative azimuth between the end point of the route and the target;

[0054] Specifically, the search space is first set. The search space in this embodiment is a two-dimensional search space, that is, it has two dimensions. The search space is X=[x1, x2], where x1 is the end point of the route planning (x e ,y e ) is the distance r1 to the target, and x2 is the relative azimuth between the end point of the route planning and the target , that is, X is the polar coordinate, and each particle represents the end point of a route.

[0055] S22, using the Dubins path as the actual flight track from the starting point to the end point of the route of the aircraft, and calculating the minimum turning radius of the Dubins path according to the maximum normal overload and the planned speed of the aircraft;

[0056] Starting point of route planning (x s ,y s ) is known, from the starting point of the aircraft (x s ,y s) to the end of the route, the Dubins path is used as the actual flight track, where the minimum turning radius r2 of the Dubins path is determined by the performance of the aircraft, which is specifically determined by the maximum normal overload n given by the aircraft. y And the planned speed v is determined, that is

[0057] For each particle, its position is calculated as the coordinate of the end point of the route (x e ,y e ), whose coordinate x2 is the heading of the end point of the Dubins path According to the starting point of the aircraft (x s ,y s ), starting heading Route end point coordinates (x e ,y e ), terminal heading To calculate the Dubins path.

[0058] S23. The path length of the Dubins path is used as the cost function value of the particle.

[0059] In this embodiment, the route length d of the Dubins path is selected as the cost function value of the particle, and the one with a smaller cost function value is used as the better planned route.

[0060] In other words, the planning goal of the Dubins path is to select the shortest path, that is, the path that can reach the target area the fastest and whose relative azimuth angle of the end point of the route is aligned with the target as the optimal planned route.

[0061] S3. Setting the wall collision strategies of each dimension of the particle swarm search space according to the LAR model.

[0062] Set the wall collision strategy in each dimension of the search space. By default, each dimension is to completely absorb the wall. After colliding with the wall, the position is restricted to the wall and the speed is set to 0. In particular, when there are route restrictions, the azimuth dimension in the search space is set to a transparent wall. After colliding with the wall, the azimuth is normalized and the speed remains unchanged. In addition, according to the range limit of each dimension, the maximum speed in that dimension is set as the limit for particle updates. The specific steps include the following:

[0063] S31, setting the particle swarm search collision strategy in each dimension to completely absorb the wall, restricting the position to the wall after colliding with the wall, and setting the speed to zero;

[0064] First, the default particle swarm search collision strategy in each dimension is to completely absorb the wall, that is, the i-th particle updates its position to the dimension range (x imin ,x imax ) outside, set the coordinate x of that dimensioni is the boundary x imin or x imax and the speed v i Cleared to 0.

[0065] S32. Determine whether there is a route restriction constraint. If yes, set the azimuth dimension in the search space to a transparent wall. Normalize the azimuth after colliding with the wall, and keep the speed unchanged.

[0066] Next, determine whether the LAR model of the air-to-surface weapon delivery area solved in step S1 has a heading constraint restriction; if there is no heading constraint restriction, maintain the collision strategy of the x2 dimension unchanged and continue to step S4; otherwise, set the collision strategy of the x2 dimension to a transparent wall, that is, set the search space range of x2 =[-π, π]. When the particle updates beyond this boundary, the velocity v is kept constant and the formula x is used. 2new =x2+k·2π, where k is an arbitrary integer, and the particle coordinate x2 is normalized to [-π, π].

[0067] S33. Setting a constraint model for each particle in the search space.

[0068] According to step S1, set the particle solution space position constraint x1∈(d Near ,d Far )and The particle solution space velocity constraint is |v i |<0.2·(x imax -x imin ).

[0069] In summary, during the particle swarm search process, particles will gradually converge in the optimal direction, but they are random and will collide with the surrounding areas of the LAR model in the launch area. This can strike a balance between global convergence and local convergence speed. In the process of convergence, some problems may be encountered. Therefore, it is necessary to formulate wall collision strategies for each dimension of the particle swarm search space.

[0070] Specifically, for example, when searching along the direction of the search speed, the coordinates in a certain search space suddenly exceed the boundary. The boundary here refers to the LAR model, which involves boundaries in two dimensions.

[0071] The first dimension is the radius boundary, which is the radius of the Near d Far The boundary is determined by , which is defined as a completely absorbing wall. In this case, if an over-boundary situation occurs, the coordinates of the particle are redefined to be on the boundary, that is, d Near or Far At the same time, reset its speed to zero, that is, let it restart free search from the wall point.

[0072] The second dimension is It is divided into two cases, namely Figure 2 The case of a closed ring in and For the case of a closed sector ring with constraints and In the case of a closed sector of a constraint, if the angle exceeds the and If it is out of the constraint range, it will be returned to the wall and its speed will be reset to zero; for the case of an unconstrained omnidirectional closed ring, its angle range is -180°~180°. If it exceeds the above range, its angle value needs to be readjusted to within the range of -180°~180° by adding or subtracting integer multiples of 180°, and its speed is kept unchanged. For this case, that is, the transparent wall defined above, in the case of a transparent wall, the particle's speed is not processed, but its coordinates are renormalized.

[0073] S4. Iterate the optimal Dubins planning path through particle swarm search and output it.

[0074] The iterative search process of the particle swarm is as follows: first, the position and velocity of each particle are randomly initialized within the constraint range; next, the particle velocity and position are updated and processed according to the wall collision strategy; then, the historical optimal position and cost function value of each particle and the swarm are updated respectively, and the above update process is repeated until the convergence condition is met or the maximum number of iterations is reached. At this time, the Dubins path represented by the historical optimal position of the swarm is output as the attack planning route of the aircraft, which specifically includes the following steps:

[0075] S41, randomly initialize the position and velocity of each particle within the constraint range;

[0076] According to the total number of particles N and the constraint model in step S33, the position x of each particle is randomly initialized within the constraints of each dimension of the search space. i and speed v i .

[0077] S42, updating the velocity and position of each particle, and performing relevant processing according to the wall collision strategy;

[0078] Specifically, according to the formula Update particle velocity according to the formula Update the particle position and perform corresponding processing according to the constraint range of each dimension and the wall collision strategy in step S3; is the local optimum, that is, the optimal position of the particle in all historical moments, is the global optimum, that is, the optimal position of all particles in the particle swarm at the historical moment; c1 is the individual learning factor, c2 is the population learning factor, ω is the inertia weight, r m 、r n are random numbers between [0,1].

[0079] S43, respectively updating the historical optimal position and cost function value of each particle and population;

[0080] According to the definition in step S2, the Dubins path and cost function of each particle are calculated, and the historical optimal position of the particle and its cost function value are recorded and updated.

[0081] S44, repeating the above updating process until the convergence condition is met or the maximum number of iterations is reached;

[0082] S45. Output the Dubins path represented by the historical optimal position of the population as the attack planning route of the aircraft.

[0083] Determine whether the change in the cost function value of the historical optimal position of the group is less than the convergence precision ebs for M consecutive iterations, or whether the maximum number of receptions has been reached. If neither is satisfied, return to step S42 to continue iteration; otherwise, output the Dubins path represented by the historical optimal position in the group as the attack planning route, and end the route planning process.

[0084] Specifically, please refer to Figure 3 , Figure 3 Detailed step flow chart of the aircraft attack route planning method of this embodiment, the steps are summarized as follows: first, establish a target LAR model, establish a particle swarm search model, and set the wall collision strategy of each dimension to completely absorb the wall by default; then determine whether the LAR model has a heading constraint, if so, set the heading dimension collision strategy to a transparent wall strategy, and randomly initialize the particle position and speed; if not, directly randomly initialize the particle position and speed; the next is the particle swarm search process, which specifically includes updating the particle speed and position, calculating the Dubins path according to the updated particle position, updating the current evaluation value of the particle, updating the historical optimal evaluation value of the particle, updating the historical optimal evaluation value of the group, and determining whether the maximum number of iterations is reached or the convergence condition is met. If so, output the group's optimal historical position and the corresponding Dubins path. If not, iteratively update the individual speed and position and subsequent steps until the maximum number of iterations is reached or the convergence condition is met.

[0085] The aircraft attack route planning method provided in the embodiment of the present application first solves the target launch area (LAR) model, then establishes a particle swarm search model, each particle represents a Dubins planning route with good flyability, then sets the wall collision strategy of the search space according to the LAR model, and finally iterates the optimal Dubins planning path through particle swarm search and outputs it. The present invention takes into account the flight constraints of the aircraft, combines the classic Dubins path and the particle swarm optimization intelligent algorithm, and can give a high-precision planning route in a relatively short time, guiding the aircraft to the target launch area as quickly as possible.

[0086] The present invention is suitable for online re-planning of the route of an aircraft, thereby providing rapid and effective guidance for pilots to complete the task of attacking targets, or as a functional component of route pre-planning, providing a corresponding planned route for the attack process after entering a battlefield.

[0087] The aircraft attack route planning method provided by this application has the following advantages:

[0088] (1) Combined with the air-to-surface weapon drop zone model, the given flight path can meet the aircraft's attack mission on the target.

[0089] (2) The Dubins path is used as the actual planned route, and the turning radius is limited by the maximum normal overload, which has good flyability.

[0090] (3) Through particle swarm search, a particle swarm that meets the accuracy requirements (optimal heading) can be obtained in a relatively short time (<200ms in a typical X86 PC and Windows 7 operating system environment). ) route solution can meet the performance requirements of pre-planning and online re-planning.

[0091] Embodiment 2

[0092] This embodiment provides an aircraft attack route planning device, the aircraft attack route planning device comprising:

[0093] A memory, a processor, and a computer program stored in the memory and executable on the processor;

[0094] When the computer program is executed by the processor, the following is achieved: Figure 1 The steps of the aircraft attack path planning method.

[0095] Embodiment 3

[0096] This embodiment provides a computer-readable storage medium on which an aircraft attack route planning program is stored. When the aircraft attack route planning program is executed by a processor, the following is achieved: Figure 1The steps of the aircraft attack route planning method described in.

[0097] Embodiment 4

[0098] This embodiment provides a server 400, such as Figure 4 As shown, the server 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part to the random access memory (RAM) 403. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, ROM 402 and RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0099] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0100] In particular, according to an embodiment of the present invention, the above reference Figure 1 The described processes may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product comprising a computer program carried on a computer readable medium, the computer program including a computer program for executing Figure 1 In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 409 , and / or installed from the removable medium 411 .

[0101] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0102] The flow chart and block diagram in the accompanying drawings illustrate the possible implementation architecture, function and operation of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, limit the units themselves. The units or modules described may also be set in a processor, for example, may be described as: a processor includes a first generation module, an acquisition module, a search module, a second generation module, and a merging module. The names of these units or modules do not, in some cases, limit the units or modules themselves.

[0104] As another aspect, the present application also provides a computer-readable medium, which may be included in the server described in the above embodiment; or it may exist independently without being installed in the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the aircraft attack route planning method described in the above embodiment. For example, the electronic device can implement Figure 1 The steps shown in .

[0105] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0106] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0107] Through the description of the above implementations, those skilled in the art can easily understand that the example implementations described here can be implemented by software, or by combining software with necessary hardware.

[0108] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0109] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for aircraft attack route planning, characterized in that: The method comprises the following steps: S1. Establish the LAR model of the target's air-to-surface weapon delivery area; S2, establish a particle swarm search model; S3, setting the wall collision strategy of each dimension of the particle swarm search space according to the LAR model; S4, iterate the optimal Dubins planning path through particle swarm search and output; Step S1 includes: S11. Calculate the minimum launch distance of air-to-surface weapons based on the planned altitude target position of the aircraft and maximum transmission distance ; S12. Establish the target's air-to-surface weapon delivery area LAR model in combination with whether there is a heading constraint. When there is no heading constraint, the LAR model is composed of and is a closed circle with radius around the target; when there is a heading constraint, the LAR model is composed of and The radius is a closed sector ring around the target; Step S2 includes: S21, setting a search space; the search space is the distance from the end point of the route to the target, and the relative azimuth between the end point of the route and the target; S22, using the Dubins path as the actual flight track from the starting point to the end point of the route of the aircraft, and calculating the minimum turning radius of the Dubins path according to the maximum normal overload and the planned speed of the aircraft; S23, taking the route length of the Dubins path as the cost function value of the particle; Step S3 includes: S31, setting the particle swarm search collision strategy in each dimension to completely absorb the wall, restricting the position to the wall after colliding with the wall, and setting the speed to zero; S32, determining whether there is a heading restriction constraint, and if so, setting the azimuth dimension in the search space to a transparent wall, normalizing the azimuth after colliding with the wall, and keeping the speed unchanged; S33, setting a constraint model for each particle in the search space; There are two dimensions involved. The first dimension is the boundary of the radius, which is The boundary is determined by the wall, which is defined as a completely absorbing wall. In this case, if an over-boundary situation occurs, the coordinates of the particle are redefined on the boundary, that is, or At the same time, reset its speed to zero, that is, let it restart the free search from the wall point; The second dimension is divided into two cases: closed ring, with and Constrained closed fan ring; for and In the case of a closed sector of a constraint, if the angle exceeds the and If the particle is out of the constraint range, it will be returned to the wall and its speed will be reset to zero. For an unconstrained omnidirectional closed ring, its angle range is -180°~180°. If it exceeds the above range, its angle value needs to be readjusted to the range of -180°~180° by adding or subtracting integer multiples of 180°, and its speed is kept unchanged. This is a transparent wall. In the case of a transparent wall, the particle's speed is not processed, but its coordinates are renormalized. in, and They refer to the attack heading, that is, the angle between the velocity vector of the aircraft when it flies to that point and the north direction.

2. The method for aircraft attack route planning according to claim 1, characterized in that: In step S4, the optimal Dubins planning path is iterated through particle swarm search and output, which specifically includes: S41, randomly initialize the position and velocity of each particle within the constraint range; S42, updating the velocity and position of each particle, and performing relevant processing according to the wall collision strategy; S43, respectively updating the historical optimal position and cost function value of each particle and population; S44, repeating the above updating process until the convergence condition is met or the maximum number of iterations is reached; S45. Output the Dubins path represented by the historical optimal position of the population as the attack planning route of the aircraft.

3. An aircraft attack route planning device, characterized in that: The aircraft attack route planning device comprises: A memory, a processor, and a computer program stored in the memory and executable on the processor; When the computer program is executed by the processor, the steps of the aircraft attack path planning method according to any one of claims 1 to 2 are implemented.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an aircraft attack route planning program, and when the aircraft attack route planning program is executed by the processor, the steps of the aircraft attack route planning method according to any one of claims 1 to 2 are implemented.