Multi-UAV collaborative task allocation method and system based on hybrid-discrete particle swarm algorithm

By adopting hybrid-discrete particle swarm algorithm in multi-UAV task allocation, combining task allocation benefits and loss cost models, the problems of irregular encoding and slow convergence speed in the existing technology are solved, and more efficient task allocation and Optimization results.

CN113887919BActive Publication Date: 2024-11-08NANJING UNIV OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111139671.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-28
Publication Date
2024-11-08
Estimated Expiration
2041-09-28

AI Technical Summary

Technical Problem

The existing multi-UAV task allocation algorithm has problems such as irregular coding, premature convergence and difficulty in parameter adjustment, and it is difficult to effectively balance the global and local search capabilities of particles, resulting in unsatisfactory allocation results.

Method used

Using hybridization-discrete particle swarm algorithm, the traditional particle swarm algorithm is improved by establishing a task allocation benefit and loss cost model, combining constraints, and nonlinear iterative method and discrete encoding method to enhance the diversity and search ability of particles, and improve the traditional particle swarm algorithm. Convergence speed and allocation results.

Benefits of technology

A more reasonable and excellent multi-UAV collaborative task allocation result is achieved, the convergence speed and allocation effect of the algorithm are improved, the shortcomings of the traditional particle swarm algorithm are made up for, and a more reasonable allocation plan is obtained.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113887919B_ABST
    Figure CN113887919B_ABST
Patent Text Reader

Abstract

The present invention discloses a multi-UAV collaborative task allocation method and system based on hybrid-discrete particle swarm algorithm, establishes a model for multi-UAV collaborative task allocation, and takes the benefits obtained by the UAVs from executing tasks and the loss costs of executing tasks as the two most important factors to measure the quality of task allocation schemes. And further considers indicators such as the probability of successful execution of tasks, the probability of damage, the time to complete tasks, and the probability of resource loss as the optimization objective function of multi-objective task allocation, and realizes the simultaneous optimization of these indicators. Aiming at the characteristics of the problem of multi-UAV collaborative task allocation, the present invention discretizes the particle swarm algorithm, designs new coding rules, improves the accuracy of problem measurement, and also incorporates a hybrid mechanism to effectively improve the convergence speed and convergence accuracy of the algorithm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of multi-agent collaborative control, and in particular relates to a multi-UAV collaborative task allocation method and system based on a hybridization-discrete particle swarm algorithm. Background Art

[0002] Unmanned combat aircraft, with its advantages of large combat radius, strong endurance, fast speed, high stealth, high mobility, and zero casualties, will replace manned combat aircraft to perform various complex tasks in boring, harsh, and dangerous environments, such as air defense suppression, large-scale search and strike, electronic attack, intelligence reconnaissance and surveillance, etc. Faced with such complex combat tasks, it is impossible to rely on a single drone to execute and complete them alone. It often requires multiple aircraft to work and cooperate with each other to complete them together. Therefore, the rationality and effectiveness of the task allocation plan are very important in the entire operation.

[0003] In order to effectively assign tasks to multiple drones, domestic and foreign scholars have conducted some research. The current research is mainly based on intelligent optimization algorithms, intelligent search algorithms and other algorithms to solve problems. For example, when using genetic algorithms to solve problems, it is easy to produce shortcomings such as irregular coding and premature convergence of the algorithm. Although the most common particle swarm algorithm solves the problem of irregular coding in genetic algorithms, it will be difficult to adjust parameters and cannot balance the global and local search capabilities of particles well. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-UAV collaborative task allocation method and system based on hybridization-discrete particle swarm algorithm to address the problems existing in the above-mentioned prior art.

[0005] The technical solution to achieve the purpose of the present invention is: a multi-UAV collaborative task allocation method based on hybrid-discrete particle swarm algorithm, the method comprising the following steps:

[0006] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0007] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0008] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0009] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0010] A system for multi-UAV collaborative task allocation method based on hybridization-discrete particle swarm algorithm, the system comprising:

[0011] The first building module is used to establish a task allocation benefit model during the UAV's mission execution process based on battlefield environment information;

[0012] The second building module is used to establish a loss cost model of the UAV during the mission execution process based on the battlefield environment information;

[0013] The third building module is used to establish an overall model of multi-UAV collaborative task allocation based on the model obtained by the first building module and the second building module, adding constraints in the UAV task execution process;

[0014] The solution module is used to solve the model obtained by the third building module by using a hybrid-discrete particle swarm algorithm.

[0015] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0016] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0017] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0018] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0019] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0020] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0021] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0022] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0023] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0024] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0025] Compared with the prior art, the present invention has the following significant advantages: 1) a discrete encoding method is proposed, and the encoding information includes not only the task allocation plan but also the priority of task execution, which is more in line with the actual task allocation needs; 2) the traditional linear update method of w, c1, and c2 is improved, and a nonlinear iterative method is adopted, thereby improving the convergence speed of the algorithm; 3) the advantages of the hybrid algorithm are used to make up for the shortcomings of the traditional particle swarm, and the diversity of particles is enhanced, thereby obtaining a more reasonable and excellent allocation result.

[0026] The present invention is further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The present invention is a flowchart of a multi-UAV collaborative task allocation method based on a hybridization-discrete particle swarm algorithm. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] In one embodiment, in combination Figure 1 , a multi-UAV collaborative task allocation method based on hybrid-discrete particle swarm algorithm is provided, which includes the following steps:

[0030] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0031] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0032] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0033] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0034] Furthermore, in one embodiment, in step 1, a task allocation benefit model is established in the process of the UAV performing the task according to the battlefield environment information, specifically including:

[0035] The value benefit of a drone attacking a single sub-target is the product of the damage caused by the drone's weapons to the sub-target and the value of the sub-target. When drones perform tasks in clusters, the damage to the sub-target refers to the damage caused by the drone cluster to the sub-target.

[0036] remember is the damage degree to the corresponding sub-target when the type l UAV formation performs the attack mission via path p;

[0037] The sub-goal uniquely determined by path p is denoted as J p , the sub-goal value is V JP , then the target value benefit of the UAV formation is:

[0038]

[0039] Therefore, the target value benefit index, that is, the task allocation benefit model, is:

[0040]

[0041] In the formula, L is the number of drones, P is the number of targets, and Pr lp byI l Model UAV and K p Model weapon suitability K p Model Weapon Pair J P Sub-target damage Joint decision, i.e. V l is the speed of the lth UAV, V max is the maximum value among all speeds; N a is the number of drone formations that actually participate in attacking sub-targets in the task assignment, x lp For the allocation scheme of drones, is the total number of formations, 1 / N a V max is the normalization factor. Maximizing the index function f1 can maximize the target value benefit of multi-UAV coordinated attack.

[0042] Furthermore, in one embodiment, the step 2 of establishing a loss cost model of the UAV during the mission execution according to the battlefield environment information specifically includes:

[0043] (1) Shortest flight distance index f2. The longer the flight path of a drone in performing a mission, the longer the mission takes and the greater the possibility of non-combat losses along the way. When assigning attack sub-target tasks to a drone formation, in order to shorten the mission time, save resources, and reduce unnecessary losses along the way, the principle of proximity is generally adopted.

[0044] Assume D lp is the flight length when the type l UAV formation selects path p. The combat radius of the UAV formation is given by the row vector R = (R l),l=1,2,...,L, the shortest flight distance indicator is formalized as follows:

[0045]

[0046] In the formula, is the length of the longest path, λ1 and λ2 represent the weights of the two factors, R l is the combat radius of the UAV;

[0047] (2) Minimum cost index f3 for ammunition consumption. Since the costs of various weapons are different, if two types of weapons can achieve the same or similar goals for the same sub-target, the weapon with the lower cost will be given priority.

[0048] The formalization of the minimum cost indicator of ammunition consumption is shown in the following formula:

[0049]

[0050] In the formula, K p Unit cost of model weapon, C max =m P axC Kp ;

[0051] (3) Maximum index of sub-target coverage degree f4. An important manifestation of the coordination of multi-UAV combat is to attack as many sub-targets as possible within the limited force while ensuring the damage degree to the sub-targets.

[0052] The formalization of the maximum index of the coverage degree of sub-targets by multi-UAV cooperative combat is shown in the following formula:

[0053]

[0054] Furthermore, in one embodiment, step 3 is based on the model obtained in step 1 and step 2, and adds the constraints in the process of UAV executing the task to establish an overall model of multi-UAV collaborative task allocation, which specifically includes:

[0055] Combining the above four indicators, f1 makes all drone formations attack the sub-target with the greatest value, f2 makes drones attack the sub-target closest to them, f3 makes the resources consumed in combat minimized, and f4 makes drone formations disperse as much as possible to attack as many sub-targets as possible. There are potential conflicts between the above four objective functions, and it is impossible to reach the optimal value at the same time. Obviously, this is a multi-objective optimization problem, and the overall evaluation function is:

[0056] min f=α1f1-(α2f2+α3f3+α4f4)

[0057] The constraints include:

[0058] (1) Constraint c1: The number of troops deployed at each airport is fixed, so the number of UAV formations of each type cannot exceed the number of UAV formations of that type deployed, that is:

[0059]

[0060] (2) The combat effectiveness of multi-UAV coordination depends not only on the combat effectiveness of a single UAV and the degree of damage to a single sub-target, but more importantly on the overall combat effectiveness of the multi-UAV formation, that is, it is expected to achieve a certain degree of damage to a single sub-target while covering as many sub-targets as possible. Let row vector Attack = {Attack1, Attack2, ...Attack J} is the threshold of the number of drone formations allowed to attack the same sub-target, then the number of drone formations attacking a sub-target at the same time should not exceed the given threshold:

[0061]

[0062] In the formula, Attack is the set of allowed attack targets, and J is the maximum number of tasks that can be assigned to the drone.

[0063] Further, in one embodiment, the step 4 uses the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3, specifically including:

[0064] Step 4-1, the key to multi-UAV collaborative task allocation is to determine: 1) which UAV will perform the task; 2) the priority of the UAV to perform the task; thus, a 2*m-dimensional discrete particle swarm encoding method is constructed, where m is the number of tasks to be performed by the UAV, and each particle contains two m-dimensional vectors; the first m-dimensional represents the serial number of the UAV performing the task, with a value range of [1,n], and n is the number of UAVs performing the task; the second m-dimensional is the priority of the UAV to perform the task, with a value range of [1,m];

[0065] Step 4-2, based on the discrete particle swarm encoding method proposed in step 4-1, a hybrid-discrete particle swarm algorithm is proposed. The specific steps are as follows:

[0066] (1) Randomly set the speed and position of each particle according to the encoding method of step 4-1;

[0067] (2) According to the overall model of multi-UAV collaborative task allocation, the fitness of each particle is solved, and the particle position and fitness value are stored in the particle's individual extreme value p best In the bestThe individual position and fitness value of the best fitness value in are stored in the global extreme value g best middle;

[0068] (3) Update particle position and velocity

[0069] x i,j (t+1)=x i,j (t)+v i,j (t+1)

[0070] v i,j (t+1)=ω·v i,j (t)+c1r1[p i,j -x i,j (t)]+c2r2[p g,j -x i,j (t)]

[0071] in,

[0072]

[0073] In the formula, x i,j is the particle’s position information, v i,j represents the velocity information of the particle, t is the current iteration number, c1 and c2 are the learning factors of the particle, and p i,j is the local optimal value of the particle, p g,j is the global optimal value of the particle, ω min is the minimum value of the set parameter, ω max is the maximum value of the set iteration parameter, f represents the real-time objective function value of the particle, and f avg and f min They represent the average value and minimum target value of the current particle respectively; from the formula, it can be seen that the inertia weight changes with the change of the particle objective function value. When the particle target values ​​are dispersed, the inertia weight is reduced; when the particle target values ​​are consistent, the inertia weight is increased;

[0074] In addition, since the search of particles has strong nonlinear capabilities, nonlinear adjustment of c1 and c2 can better adjust the global and local search capabilities of particles. Due to the rapid growth characteristics of exponential functions, the convergence speed can be accelerated in the form of exponentials. The specific formula is as follows:

[0075]

[0076]

[0077] in, The following table s and f represent the initial and final values ​​of each control parameter, t and t max Represent the current number of iterations and the total number of iterations respectively, and β is a constant;

[0078] (4) Compare the fitness value of each particle with the best position of the particle. If the difference between the two is within the preset range, the fitness value of the current particle is taken as the best position of the particle. best and g best , update g best ;

[0079] (5) Select a specified number of particles according to the preset hybridization probability and put them into the hybridization pool. The particles in the pool randomly hybridize with each other to produce the same number of offspring particles;

[0080] (6) When the algorithm reaches the preset stop condition, stop searching and output the results; otherwise, go to step (3) to continue searching.

[0081] In one embodiment, a multi-UAV collaborative task allocation system based on a hybridization-discrete particle swarm algorithm is provided, the system comprising:

[0082] The first building module is used to establish a task allocation benefit model during the UAV's mission execution process based on battlefield environment information;

[0083] The second building module is used to establish a loss cost model of the UAV during the mission execution process based on the battlefield environment information;

[0084] The third building module is used to establish an overall model of multi-UAV collaborative task allocation based on the model obtained by the first building module and the second building module, adding constraints in the UAV task execution process;

[0085] The solution module is used to solve the model obtained by the third building module by using a hybrid-discrete particle swarm algorithm.

[0086] For the specific definition of the multi-UAV collaborative task allocation system based on the hybrid-discrete particle swarm algorithm, please refer to the definition of the multi-UAV collaborative task allocation method based on the hybrid-discrete particle swarm algorithm above, which will not be repeated here. Each module in the above-mentioned multi-UAV collaborative task allocation system based on the hybrid-discrete particle swarm algorithm can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0087] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0088] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0089] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0090] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0091] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0092] For the specific limitations of each step, please refer to the limitations of the high-fidelity image reconstruction method for super-resolution structured light illumination microscopy mentioned above, which will not be repeated here.

[0093] In one embodiment, 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 following steps are implemented:

[0094] Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process;

[0095] Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution;

[0096] Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation;

[0097] Step 4: Use the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3.

[0098] For the specific limitations of each step, please refer to the limitations of the high-fidelity image reconstruction method for super-resolution structured light illumination microscopy mentioned above, which will not be repeated here.

[0099] The present invention solves the multi-UAV task allocation problem based on the hybrid-discrete particle swarm algorithm. First, a cost function to measure the quality of the task allocation scheme is established, and based on this, a discrete particle swarm encoding method is proposed. This method not only considers the task allocation scheme but also the priority of executing the task. Based on this model and encoding method, the hybrid algorithm and the particle swarm algorithm are combined, which improves the convergence accuracy compared with the traditional particle swarm algorithm and can obtain better convergence results.

[0100] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A multi-UAV collaborative task allocation method based on hybrid-discrete particle swarm algorithm, characterized in that: The method comprises the following steps: Step 1: Based on the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process; Step 2: Based on the battlefield environment information, establish a loss cost model for the UAV during the mission execution; Step 3: Based on the models obtained in Steps 1 and 2, the constraints in the UAV task execution process are added to establish an overall model for multi-UAV collaborative task allocation; Step 4, using the hybrid-discrete particle swarm algorithm to solve the model obtained in step 3; In step 1, according to the battlefield environment information, a task allocation benefit model is established during the UAV mission execution process, which specifically includes: remember is the damage degree to the corresponding sub-target when the type l UAV formation performs the attack mission via path p; The sub-goal uniquely determined by path p is denoted as J p , the sub-goal value is Then the target value benefit of the UAV formation is: Therefore, the target value benefit index, that is, the task allocation benefit model, is: In the formula, L is the number of drones, P is the number of targets, and Pr lp byI l Model UAV and K p Model weapon suitability K p Model Weapon Pair J P Sub-target damage Joint decision, i.e. V l is the speed of the lth UAV, V max is the maximum value among all speeds; N a is the number of drone formations that actually participate in attacking sub-targets in the task assignment, x lp For the allocation scheme of drones, is the total number of formations, 1 / N a V max is the normalization factor; In step 2, based on the battlefield environment information, a loss cost model is established during the UAV mission execution process, specifically including: (1) Shortest flight distance indicator f2 Assume D lp is the flight length when the type l UAV formation selects path p. The combat radius of the UAV formation is given by the row vector R = (R l ),l=1,2,...,L, the shortest flight distance indicator is formalized as follows: In the formula, is the length of the longest path, λ1 and λ2 represent the weights of the two factors, R l is the combat radius of the UAV; (2) Minimum cost index of ammunition consumption f3 The formalization of the minimum cost indicator of ammunition consumption is shown in the following formula: In the formula, K p The unit cost of the weapon model, (3) Maximum index of sub-goal coverage f4 The formalization of the maximum index of sub-goal coverage is shown in the following formula:

2. The multi-UAV collaborative task allocation method based on hybridization-discrete particle swarm algorithm according to claim 1 is characterized in that: Step 3 is based on the model obtained in step 1 and step 2, adding the constraints in the process of UAV execution to establish an overall model of multi-UAV collaborative task allocation, which specifically includes: Combining the above four indicators, multi-objective optimization is performed to obtain the overall evaluation function, that is, the overall model of multi-UAV collaborative task allocation: min f=α1f1-(α2f2+α3f3+α4f4) The constraints include: (1) Mission force quantity constraint c1: The number of UAV formations of each type cannot exceed the number of UAV formations of that type deployed, that is: (2) Let row vector Attack = {Attack1, Attack2, ... Attack J } is the threshold of the number of drone formations allowed to attack the same sub-target, then the number of drone formations attacking a sub-target at the same time should not exceed the given threshold: Where Attack is the set of allowed attack targets, and J is the maximum number of tasks that can be assigned to the drone.

3. The multi-UAV collaborative task allocation method based on hybridization-discrete particle swarm algorithm according to claim 2 is characterized in that: Step 4 uses the hybridization-discrete particle swarm algorithm to solve the model obtained in step 3, specifically including: Step 4-1, the key to multi-UAV collaborative task allocation is to determine: 1) which UAV will perform the task; 2) the priority of the UAV to perform the task; thus, a 2*m-dimensional discrete particle swarm encoding method is constructed, where m is the number of tasks to be performed by the UAV, and each particle contains two m-dimensional vectors; the first m-dimensional represents the serial number of the UAV performing the task, with a value range of [1,n], and n is the number of UAVs performing the task; the second m-dimensional is the priority of the UAV to perform the task, with a value range of [1,m]; Step 4-2, based on the discrete particle swarm encoding method proposed in step 4-1, a hybrid-discrete particle swarm algorithm is proposed. The specific steps are as follows: (1) Randomly set the speed and position of each particle according to the encoding method of step 4-1; (2) According to the overall model of multi-UAV collaborative task allocation, the fitness of each particle is solved, and the particle position and fitness value are stored in the particle's individual extreme value p best In the best The individual position and fitness value of the best fitness value in are stored in the global extreme value g best middle; (3) Update particle position and velocity x i,j (t+1)=x i,j (t)+v i,j (t+1) v i,j (t+1)=ω·v i,j (t)+c1r1[p i,j -x i,j (t)]+c2r2[p g,j -x i,j (t)] in, In the formula, x i,j is the particle’s position information, v i,j represents the velocity information of the particle, t is the current iteration number, c1 and c2 are the learning factors of the particle, and p i,j is the local optimal value of the particle, p g,j is the global optimal value of the particle, ω min is the minimum value of the set parameters, ω max is the maximum value of the set iteration parameter, f represents the real-time objective function value of the particle, and f avg and f min Respectively represent the average value and minimum target value of the current particle; (4) Compare the fitness value of each particle with the best position of the particle. If the difference between the two is within the preset range, the fitness value of the current particle is taken as the best position of the particle; and compare all the current p best and g best , update g best ; (5) Select a specified number of particles according to the preset hybridization probability and put them into the hybridization pool. The particles in the pool randomly hybridize with each other to produce the same number of offspring particles; (6) When the algorithm reaches the preset stop condition, stop searching and output the results; otherwise, go to step (3) to continue searching.

4. A system for multi-UAV collaborative task allocation method based on hybridization-discrete particle swarm algorithm according to any one of claims 1 to 3, characterized in that: The system comprises: The first building module is used to establish a task allocation benefit model during the UAV's mission execution process based on battlefield environment information; The second building module is used to establish a loss cost model of the UAV during the mission execution process based on the battlefield environment information; The third building module is used to establish an overall model of multi-UAV collaborative task allocation based on the model obtained by the first building module and the second building module, adding constraints in the UAV task execution process; The solution module is used to solve the model obtained by the third building module by using a hybrid-discrete particle swarm algorithm.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.