Joint optimization method of multi-task allocation and trajectory planning for heterogeneous UAV swarm

Abstract

The invention discloses a method for joint optimization of multi-task allocation and track planning of heterogeneous unmanned aerial vehicle clusters, comprising: constructing a constraint model of heterogeneous unmanned aerial vehicle clusters, including task load constraints, range constraints, and task requirement constraints; taking the range, value benefit, and threat probability of the heterogeneous unmanned aerial vehicle cluster as independent variables, and establishing a joint optimization objective function of multi-task allocation and track planning according to the weight coefficients of the respective variables; establishing a joint optimization model for multi-task allocation and track planning of heterogeneous unmanned aerial vehicle clusters, the optimization model maximally improves the combat effectiveness of the unmanned aerial vehicle cluster by collaboratively optimizing the range, value benefit, and threat probability of the unmanned aerial vehicle under the conditions of satisfying the task load, range, and task requirement constraints; finally, using an improved ant colony algorithm to solve the optimization model; the method of the invention realizes better multi-task allocation and better track planning of heterogeneous unmanned aerial vehicle clusters, and effectively improves the combat effectiveness of heterogeneous unmanned aerial vehicle clusters.

Description

Technical Field

[0001] The present invention relates to radar signal processing technology, and in particular to a joint optimization method for multi-task allocation and trajectory planning of a heterogeneous unmanned aerial vehicle cluster. Background Art

[0002] Heterogeneous drone swarms are composed of many different types of drones, which can adapt to different environments and mission requirements, and use information interaction and feedback, incentives and responses to achieve mutual behavioral coordination and complete more complex and efficient flight missions. Even if a small number of drones in the swarm fail, the other drones can still continue to complete the mission. Therefore, the range, value benefits, and threat probability of heterogeneous drone swarms can be optimized to form an objective function that meets specific mission requirements. In addition, by online planning of the trajectory of heterogeneous drone swarms and continuously optimizing their real-time forward direction, the effectiveness of multi-task reconnaissance and strike operations can be effectively improved.

[0003] For multi-task scenarios, under the constraints of heterogeneous UAV cluster mission payload, range and mission requirements, it is necessary to jointly optimize the task allocation and trajectory planning to minimize the range, maximize the value benefit and minimize the probability of being threatened.

[0004] At present, there are many research results on the task allocation and trajectory planning of UAV swarms. However, most of the research solves the task allocation and trajectory planning separately, weakening or ignoring the coupling between the two. When allocating tasks, only the timing constraints of the tasks themselves and the mutual influence between tasks are considered, without considering the UAV's own kinematic constraints, environmental threats, etc.; trajectory planning uses the output of task allocation as its input, and only considers the UAV's own constraints, environmental threats, etc. This approach reduces the complexity of the problem, but it cannot meet the needs in actual combat. Summary of the invention

[0005] Purpose of the invention: The purpose of the present invention is to provide a joint optimization method for multi-task allocation and trajectory planning of heterogeneous UAV clusters.

[0006] Technical solution: The combined optimization method of multi-task allocation and trajectory planning of heterogeneous UAV clusters of the present invention comprises the following steps:

[0007] A constraint model for heterogeneous UAV clusters is constructed, including mission load constraints, range constraints, and mission requirement constraints. The range, value benefit, and threat probability of heterogeneous UAV clusters are used as independent variables, and the joint optimization objective function of multi-task allocation and trajectory planning is established according to the weight coefficients of each variable. A joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters is established. This optimization model maximizes the combat effectiveness of UAV clusters by collaboratively optimizing the range, value benefit, and threat probability of UAVs while meeting the constraints of mission load, range, and mission requirements. Finally, an improved ant colony algorithm is used to solve the optimization model.

[0008] Among them, the improved ant colony algorithm introduces the roulette selection principle and elite strategy on the basis of the ant colony algorithm. First, the sum of the probabilities of each individual in the group being selected is combined into a roulette wheel, in which the probability of each individual being selected is the same. Finally, the cumulative probability is calculated. Use rand() to generate a random number r between [0,1], and determine the selected individual based on the interval where r is located; secondly, at the end of each cycle, the elite ant’s solution is taken out, and the elite ant’s path is adjusted locally with pheromones, so that the optimal solution found so far is more attractive in the next cycle.

[0009] Furthermore, the task load constraint is expressed as:

[0010]

[0011] in, Indicates drone u i Execute Task j Required load resources; Indicates drone u i The total mission payload resources carried; TA represents the UAV u i A collection of tasks;

[0012] The range constraint is expressed as:

[0013]

[0014] in, Indicates drone u i Execute Task j the distance travelled; Indicates drone u i Total mission range;

[0015] The task requirement constraints are expressed as:

[0016]

[0017] and

[0018]

[0019] Among them, x ij represents the task decision variable, and N represents the number of drones contained in the heterogeneous drone cluster.

[0020] Furthermore, the established joint optimization objective function F of multi-task allocation and trajectory planning is:

[0021]

[0022] Among them, δ1, δ2, and δ3 represent the weight coefficients of the range, value benefit, and threat probability of the heterogeneous UAV cluster, respectively; L Tmax Represents the maximum value of all drone ranges; V Tmax It represents the maximum value of all the UAVs’ missions. Tmax Indicates the maximum value of the probability of all drones being threatened; L T Indicates drone u i The total distance of the mission; V T Indicates drone u i The sum of the value gains obtained from executing the task; P T Indicates drone u i The probability of being threatened while performing the task.

[0023] Furthermore, drones i The probability of being threatened during the task execution is P T It is expressed as:

[0024]

[0025] Among them, ω1 represents the passive threat weight coefficient; ω2 represents the active threat weight coefficient; TA represents the UAV u i The task set of t j represents the jth task in the total task set T consisting of M tasks;

[0026] P p Indicates the probability of a drone entering a passive threat area:

[0027]

[0028] P a Indicates the probability of the drone being threatened by an active threat:

[0029]

[0030] Among them, r ij Indicates drone u i With the task j The distance betweenj Represents task t j The scope of action of K a represents the proportionality constant, which is related to the distance between the active threat and the UAV.

[0031] Furthermore, the established joint optimization model of multi-task allocation and trajectory planning for heterogeneous UAV clusters is:

[0032]

[0033]

[0034] Among them, F is the joint optimization objective function of multi-task allocation and trajectory planning; L T represents the i-th drone u i The total distance of the mission; V T represents the i-th drone u i The sum of the value gains obtained from executing the task; P T represents the i-th drone u i The probability of being threatened during the mission execution; δ1, δ2, δ3 represent the weight coefficients of the range, value benefit and threat probability of the heterogeneous UAV cluster respectively; L Tmax Represents the maximum value of all drone ranges; V Tmax It represents the maximum value of all the UAVs’ missions. Tmax represents the maximum value of the probability of all drones being threatened; x ij represents the task decision variable; N represents the number of drones contained in the heterogeneous drone cluster; represents the i-th drone u i Execute Task j Required load resources; represents the i-th drone u i The total mission payload resources carried; TA represents the i-th UAV u i The task set of t j Represents the jth task in the total task set T consisting of M tasks.

[0035] Furthermore, the roulette selection principle is introduced into the ant colony algorithm, specifically:

[0036] The probability P(x) of each individual in the population being selected i )for:

[0037]

[0038] Among them, x i is an individual, i=1,2,...,ant, ant is the number of ants, f(x i ) is individual xi The fitness value is P(x1)+P(x2)+...+P(x ant )=1 forms a roulette wheel.

[0039] Furthermore, the elite strategy is introduced into the ant colony algorithm, where the pheromone adjustment parameters are as follows:

[0040]

[0041] in, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best It represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; e represents the adjustment parameter, which is related to the length of the elite path.

[0042] Based on the same inventive concept, the heterogeneous UAV cluster multi-task allocation and trajectory planning joint optimization system of the present invention includes:

[0043] The constraint model building module is used to build a constraint model for heterogeneous UAV clusters, including mission load constraints, range constraints, and mission requirement constraints;

[0044] The objective function establishment module is used to establish the joint optimization objective function of multi-task allocation and trajectory planning based on the weight coefficients of the heterogeneous UAV cluster’s range, value benefit and threat probability as independent variables;

[0045] The optimization model building module is used to establish a joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters. This optimization model maximizes the combat effectiveness of UAV clusters by collaboratively optimizing the range, value benefits and threat probability of UAVs while meeting the constraints of mission load, range and mission requirements;

[0046] A model solving module is used to solve the optimization model using an improved ant colony algorithm;

[0047] Among them, the improved ant colony algorithm introduces the roulette selection principle and elite strategy on the basis of the ant colony algorithm. First, the sum of the probabilities of each individual in the group being selected is combined into a roulette wheel, in which the probability of each individual being selected is the same. Finally, the cumulative probability is calculated. Use rand() to generate a random number r between [0,1], and determine the selected individual based on the interval where r is located; secondly, at the end of each cycle, the elite ant’s solution is taken out, and the elite ant’s path is adjusted locally with pheromones, so that the optimal solution found so far is more attractive in the next cycle.

[0048] Based on the same inventive concept, a device for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters of the present invention comprises:

[0049] A memory storing executable program code;

[0050] a processor coupled to the memory;

[0051] The processor calls the executable program code stored in the memory to execute the above-mentioned heterogeneous UAV cluster multi-task allocation and trajectory planning joint optimization method.

[0052] Based on the same inventive concept, a computer-readable storage medium of the present invention stores computer instructions, which, when called, are used to execute the above-mentioned joint optimization method for multi-task allocation and trajectory planning of heterogeneous drone clusters.

[0053] Beneficial effects: Compared with the prior art, the method for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters of the present invention considers the mutual coordination and cooperation between heterogeneous UAVs in a two-dimensional threat environment, and conducts reconnaissance and strikes on multiple tasks dispersedly deployed in space; a constraint model is constructed; on this basis, an objective function including the UAV range, value benefit and threat probability is defined; with task load, range and task requirements as constraints, and minimizing the range, maximizing the value benefit and minimizing the threat probability as optimization goals, a joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters is established, and the UAV range, value benefit and threat probability are collaboratively optimized to prove the superiority of the proposed method; by collaboratively optimizing parameters such as the range, value benefit and threat probability of heterogeneous UAV clusters in multi-task scenarios, under the constraints of meeting the task load, range and task requirements, a better heterogeneous UAV cluster multi-task allocation and a better trajectory planning are achieved, thereby maximizing the combat effectiveness of the UAV cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of the method of the present invention;

[0055] Figure 2 This is a schematic diagram of the simulation results of joint optimization of task allocation and trajectory planning;

[0056] Figure 3 It is the objective function curve. DETAILED DESCRIPTION

[0057] The structure and working process of the present invention are further described below in conjunction with the accompanying drawings and specific embodiments.

[0058] Starting from the actual combat scenario, the present invention proposes a joint optimization method for multi-task allocation and trajectory planning of heterogeneous UAV clusters. Under the constraints of given mission payload, range and mission requirements, the range, value benefit and threat probability of the UAVs are collaboratively optimized with the optimization goals of minimizing the range, maximizing the value benefit and minimizing the threat probability, thereby proving the superiority of the proposed method.

[0059] The present invention considers the coordination and cooperation between heterogeneous UAVs in a two-dimensional threat environment, and conducts reconnaissance and strikes on multiple tasks dispersed in space. First, a constraint model is constructed; on this basis, an objective function including the UAV range, value benefit and threat probability is defined; secondly, with the task load, range and task requirements as constraints, and minimizing the range, maximizing the value benefit and minimizing the threat probability as optimization goals, a joint optimization model of multi-task allocation and trajectory planning of heterogeneous UAV clusters is established, and the UAV range, value benefit and threat probability are collaboratively optimized to prove the superiority of the proposed method.

[0060] like Figure 1 As shown, a method for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters of the present invention comprises the following steps:

[0061] S1. Consider a two-dimensional combat scenario with a heterogeneous UAV cluster consisting of N UAVs U = {u1,u2,…,u i ,…,u N},u i represents the i-th drone in the heterogeneous drone cluster, i = 1, 2, ..., N, and the total task set T = {t1, t2, ..., t j ,…,t M}, t j represents the jth task in the total task set T, j = 1, 2, ..., M. After task allocation, each drone will be assigned its own task. TA represents the i-th drone u i The task set of all drones constitutes the total task set T. Construct a constraint model.

[0062] Then the task load constraint is expressed as:

[0063]

[0064] In the formula, represents the i-th drone u i Execute Task j Required load resources; represents the i-th drone u i Total mission payload resources carried.

[0065] The range constraint of heterogeneous UAV cluster is expressed as:

[0066]

[0067] In the formula, represents the i-th drone u i Execute Task j the distance travelled; represents the i-th drone u i Total mission range.

[0068] The task requirement constraints are expressed as:

[0069]

[0070] and

[0071]

[0072] In the formula, x ij represents the task decision variable.

[0073] S2. Taking the range, value benefit and threat probability of heterogeneous UAV cluster as independent variables, define the joint optimization objective function F of multi-task allocation and trajectory planning:

[0074]

[0075] In the formula, δ1, δ2, and δ3 represent the weight coefficients of the range, value benefit, and threat probability of the heterogeneous UAV cluster respectively; L Tmax Represents the maximum value of all drone ranges; V Tmax It represents the maximum value of all the UAVs’ missions. Tmax It represents the maximum value of the probability of all drones being threatened.

[0076] In formula (5), L T represents the i-th drone u i Total mission distance:

[0077]

[0078] V T represents the i-th drone u i The sum of the value gains from executing tasks:

[0079]

[0080] Where V ij represents the i-th drone u i Execute Task j The value of the benefit at that time.

[0081] In formula (5), P T represents the i-th drone u i Probability of being threatened during mission execution:

[0082]

[0083] Where ω1 represents the passive threat weight coefficient; ω2 represents the active threat weight coefficient.

[0084] In formula (8), P p Indicates the probability of a drone entering a passive threat area:

[0085]

[0086] P a Indicates the probability of the drone being threatened by an active threat:

[0087]

[0088] In the formula, r ij represents the i-th drone u i With the task j The distance between j Represents task t j The scope of action of K a represents the proportionality constant, which is related to the distance between the active threat and the UAV.

[0089] S3. Establish a joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters.

[0090] By collaboratively optimizing the range, value benefits, and threat probability of drones, the combat effectiveness of the drone cluster is maximized under the constraints of mission payload, range, and mission requirements. The joint optimization model is shown in the following formula:

[0091]

[0092] In formula (11), the first constraint 0≤L T ≤L Tmax Represents the range of the UAV's flight distance; the second constraint is 0≤V T ≤V Tmax represents the value range of the drone's performance of different tasks; the third constraint 0≤P T ≤P Tmax The fourth constraint condition is Indicates the number of drones required to perform the mission; the fifth constraint Indicates the value range of the UAV's mission payload resources.

[0093] S4. Using the ant colony algorithm, the roulette wheel selection principle and the elite strategy are introduced to solve the optimization model (11).

[0094] The basic principle of roulette is that the probability of an individual being selected in a group is proportional to its fitness. Let the individual be represented by x i (i=1,2,...,ant), ant is the number of ants, then its fitness value is f(x i ), the probability of each individual in the population being selected is:

[0095]

[0096] From P(x1)+P(x2)+...+P(x ant )=1 to form a roulette wheel, in which each individual has the same probability of being selected, and finally the cumulative probability is calculated. Use rand() to generate a random number r between [0,1], and determine the selected individual based on the interval where r is located. If q k-1 <r≤q k , then select individual k. Introducing the roulette selection principle into the ant colony algorithm can increase the randomness of node selection and prevent the algorithm from falling into the local optimum too early.

[0097] The basic idea of ​​the elite strategy is to take out the solution of the elite ants at the end of each cycle and make local pheromone adjustments to the elite ants' paths, so that the best solution found so far is more attractive in the next cycle. The pheromone adjustment parameters are as follows:

[0098]

[0099] In the formula, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; e represents the adjustment parameter, which is related to the length of the elite path. Introducing the elite strategy into the ant colony algorithm can update the pheromone concentration in real time, increasing the convergence speed of the algorithm.

[0100] like Figure 1 As shown, the solution is:

[0101] S41, initialize various parameters: number of ants ant, pheromone enhancement coefficient Q, etc.;

[0102] S42, updating pheromones according to formula (13);

[0103] S43, determine whether the target position has been reached, if not, return to step S42; otherwise, execute step S44;

[0104] S44, determine whether the task has been fully executed, if not, return to step S42 to execute; otherwise, end the solution.

[0105] Simulation results:

[0106] In the 100km×100km two-dimensional threat map, N=6, M=6, the simulation results of task allocation and trajectory planning are as follows: Figure 2 As shown in the figure, blue indicates the threat range of anti-aircraft guns, red indicates the threat range of radars, and both anti-aircraft guns and radars are active threats. Green indicates the passive threat range. Figure 2 As can be seen from the figure, the task allocation results are: UAV 1 → Task 2, UAV 2 → Task 5, UAV 3 → Task 4, UAV 4 → Task 1, UAV 5 → Task 6, UAV 6 → Task 3. The objective function curve is shown in Figure 3 As shown, from Figure 3 It can be seen that the objective function ranges from 0.65 to 0.75.

[0107] Table 1 shows the target comprehensive cost comparison results of the three methods in three different threat environments (complexity: environment 1> environment 2> environment 3). It can be seen from Table 1 that the target comprehensive cost of the method of the present invention is higher than that of the other two methods, which verifies the superiority of the method of the present invention; it can also be seen that with the increase of the complexity of the threat scene, the target comprehensive cost of the three methods gradually increases, indicating that the method of the present invention is more suitable for complex environments with multiple tasks.

[0108] Table 1 Target comprehensive cost

[0109]

[0110] The working principle and working process of the invention are as follows:

[0111] The present invention considers the coordination and cooperation between heterogeneous UAVs in a two-dimensional threat environment, and conducts reconnaissance and strikes on multiple tasks dispersedly deployed in space. First, a constraint model is constructed; on this basis, an objective function including the range, value benefit and threat probability of the UAV is defined, which is used as a measure of the joint optimization effect of the multi-task allocation and trajectory planning of the heterogeneous UAV cluster; then, with the task load, range and task requirements as constraints, and minimizing the range, maximizing the value benefit and minimizing the threat probability as optimization goals, a joint optimization model of multi-task allocation and trajectory planning of the heterogeneous UAV cluster is established; finally, the roulette selection principle and elite strategy are introduced, and the ant colony algorithm with elite strategy is used to solve this optimization model. The UAV range, value benefit and threat probability are collaboratively optimized to prove the superiority of the proposed method. By solving the optimization model, the optimal solution of the model is obtained under the constraints of meeting the task load, range and task requirements of the heterogeneous UAV cluster, making the range, value benefit and threat probability the optimal solution of the model.

[0112] The invention of the present invention:

[0113] 1. Assume that several tasks are dispersedly deployed in a two-dimensional threat environment, and a heterogeneous drone cluster conducts reconnaissance and attack on these tasks. For this heterogeneous drone cluster multi-task scenario, an objective function including drone range, value benefit and threat probability is constructed as a measure of the joint optimization effect of heterogeneous drone cluster multi-task allocation and trajectory planning;

[0114] 2. Construct an objective function that includes the range, value benefit, and threat probability of UAVs, and use it as a measure of the joint optimization effect of multi-task allocation and trajectory planning of heterogeneous UAV clusters. Take the task load, range, and task requirements as constraints, minimize the range, maximize the value benefit, and minimize the threat probability as optimization goals, establish a joint optimization model of multi-task allocation and trajectory planning of heterogeneous UAV clusters, and use the ant colony algorithm with elite strategy to solve this optimization model. By solving the optimization model, the optimal solution of the model with range, value benefit, and threat probability is obtained under the constraints of satisfying the task load, range, and task requirements of the heterogeneous UAV cluster.

[0115] Based on the same inventive concept, the heterogeneous UAV cluster multi-task allocation and trajectory planning joint optimization system of the present invention includes:

[0116] The constraint model building module is used to build a constraint model for heterogeneous UAV clusters, including mission load constraints, range constraints, and mission requirement constraints;

[0117] The objective function establishment module is used to establish the joint optimization objective function of multi-task allocation and trajectory planning based on the weight coefficients of the heterogeneous UAV cluster’s range, value benefit and threat probability as independent variables;

[0118] The optimization model building module is used to establish a joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters. This optimization model maximizes the combat effectiveness of UAV clusters by collaboratively optimizing the range, value benefits and threat probability of UAVs while meeting the constraints of mission load, range and mission requirements;

[0119] A model solving module is used to solve the optimization model using an improved ant colony algorithm;

[0120] Among them, the improved ant colony algorithm introduces the roulette selection principle and elite strategy on the basis of the ant colony algorithm. First, the sum of the probabilities of each individual in the group being selected is combined into a roulette wheel, in which the probability of each individual being selected is the same. Finally, the cumulative probability is calculated. Use rand() to generate a random number r between [0,1] and see which interval r is in. If q k-1 <r≤q k , then select individual k; secondly, at the end of each cycle, take out the solution of the elite ant, and make local pheromone adjustments to the elite ant's path, so that the optimal solution found so far is more attractive in the next cycle.

[0121] Based on the same inventive concept, a device for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters of the present invention may include: a memory storing executable program code; a processor 302 coupled to the memory; the processor calls the executable program code stored in the memory to execute the steps in the above-mentioned method for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters.

[0122] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0123] The processor executes various functional applications and data processing by running programs stored in the memory, such as implementing the above-mentioned joint optimization method of multi-task allocation and trajectory planning of heterogeneous drone clusters.

[0124] Based on the same inventive concept, a computer-readable storage medium of the present invention stores computer instructions, which, when called, are used to execute the above-mentioned joint optimization method for multi-task allocation and trajectory planning of heterogeneous drone clusters.

[0125] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0126] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals 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 a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0127] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0128] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0129] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the method provided by any embodiment of the present invention.

Claims

1. A joint optimization method for multi-task allocation and trajectory planning of heterogeneous UAV clusters, including the following steps: Construct a heterogeneous UAV cluster constraint model, including mission payload constraints, range constraints, and mission requirement constraints; Taking the range, value benefit and threat probability of heterogeneous UAV clusters as independent variables, the joint optimization objective function of multi-task allocation and trajectory planning is established according to the weight coefficients of each variable; a joint optimization model of multi-task allocation and trajectory planning of heterogeneous UAV clusters is established. This optimization model maximizes the combat effectiveness of UAV clusters by collaboratively optimizing the range, value benefit and threat probability of UAVs while meeting the constraints of mission load, range and mission requirements; finally, the improved ant colony algorithm is used to solve the optimization model; The task load constraint is expressed as: in, Indicates drone u i Execute Task j Required load resources; Indicates drone u i The total mission payload resources carried; TA represents the UAV u i A collection of tasks; The range constraint is expressed as: in, Indicates drone u i Execute Task j the distance travelled; Indicates drone u i Total mission range; The task requirement constraints are expressed as: and Among them, x ij represents the task decision variable, N represents the number of drones contained in the heterogeneous drone cluster; The established joint optimization objective function F of multi-task allocation and trajectory planning is: Among them, δ1, δ2, and δ3 represent the weight coefficients of the range, value benefit, and threat probability of the heterogeneous UAV cluster, respectively; L Tmax Represents the maximum value of all drone ranges; V Tmax It represents the maximum value of all the UAVs’ missions. Tmax Indicates the maximum value of the probability of all drones being threatened; L T Indicates drone u i The total distance of the mission; V T Indicates drone u i The sum of the value gains obtained from executing the task; P T Indicates drone u i The probability of being threatened during the execution of the mission; UAV i The probability of being threatened during the task execution is P T It is expressed as: Among them, ω1 represents the passive threat weight coefficient; ω2 represents the active threat weight coefficient; t j represents the jth task in the total task set T consisting of M tasks; P p Indicates the probability of a drone entering a passive threat area: P a Indicates the probability of the drone being threatened by an active threat: Among them, r ij Indicates drone u i With the task j The distance between j Represents task t j The scope of action of K a represents the proportionality constant, which is related to the distance between the active threat and the UAV; The established joint optimization model of multi-task allocation and trajectory planning for heterogeneous UAV clusters is: Among them, the improved ant colony algorithm introduces the roulette selection principle and elite strategy on the basis of the ant colony algorithm. First, the sum of the probabilities of each individual in the group being selected is combined into a roulette wheel, in which the probability of each individual being selected is the same. Finally, the cumulative probability is calculated. Use rand() to generate a random number r between [0,1], and determine the selected individual based on the interval where r is located; secondly, at the end of each cycle, the elite ant’s solution is taken out, and the elite ant’s path is adjusted locally with pheromones, so that the optimal solution found so far is more attractive in the next cycle.

2. The method for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters according to claim 1 is characterized in that: The roulette selection principle is introduced into the ant colony algorithm, specifically: The probability P(x) of each individual in the population being selected i )for: Among them, x i is an individual, i=1,2,...,M, M is the number of ants, f(x i ) is individual x i The fitness value is P(x1)+P(x2)+...+P(x ant )=1 forms a roulette wheel.

3. The method for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters according to claim 1 is characterized in that: The elite strategy is introduced into the ant colony algorithm, where The pheromone adjustment parameters are as follows: in, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best It represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; e represents the adjustment parameter, which is related to the length of the elite path.

4. A joint optimization system for multi-task allocation and trajectory planning of heterogeneous UAV clusters, characterized by: include: The constraint model building module is used to build a constraint model for heterogeneous UAV clusters, including mission load constraints, range constraints, and mission requirement constraints; The objective function establishment module is used to establish the joint optimization objective function of multi-task allocation and trajectory planning based on the weight coefficients of the heterogeneous UAV cluster’s range, value benefit and threat probability as independent variables; The optimization model building module is used to establish a joint optimization model for multi-task allocation and trajectory planning of heterogeneous UAV clusters. This optimization model maximizes the combat effectiveness of UAV clusters by collaboratively optimizing the range, value benefits and threat probability of UAVs while meeting the constraints of mission load, range and mission requirements; A model solving module is used to solve the optimization model using an improved ant colony algorithm; The task load constraint is expressed as: in, Indicates drone u i Execute Task j Required load resources; Indicates drone u i The total mission payload resources carried; TA represents the UAV u i A collection of tasks; The range constraint is expressed as: in, Indicates drone u i Execute Task j the distance travelled; Indicates drone u i Total mission range; The task requirement constraints are expressed as: and Among them, x ij represents the task decision variable, N represents the number of drones contained in the heterogeneous drone cluster; The established joint optimization objective function F of multi-task allocation and trajectory planning is: Among them, δ1, δ2, and δ3 represent the weight coefficients of the range, value benefit, and threat probability of the heterogeneous UAV cluster, respectively; L Tmax Represents the maximum value of all drone ranges; V Tmax It represents the maximum value of all the UAVs’ missions. Tmax Indicates the maximum value of the probability of all drones being threatened; L T Indicates drone u i The total distance of the mission; V T Indicates drone u i The sum of the value gains obtained from executing the task; P T Indicates drone u i The probability of being threatened during the execution of the mission; UAV i The probability of being threatened during the task execution is P T It is expressed as: Among them, ω1 represents the passive threat weight coefficient; ω2 represents the active threat weight coefficient; t j represents the jth task in the total task set T consisting of M tasks; P p Indicates the probability of a drone entering a passive threat area: P a Indicates the probability of the drone being threatened by an active threat: Among them, r ij Indicates drone u i With the task j The distance between j Represents task t j The scope of action of K a represents the proportionality constant, which is related to the distance between the active threat and the UAV; The established joint optimization model of multi-task allocation and trajectory planning for heterogeneous UAV clusters is: Among them, the improved ant colony algorithm introduces the roulette selection principle and elite strategy on the basis of the ant colony algorithm. First, the sum of the probabilities of each individual in the group being selected is combined into a roulette wheel, in which the probability of each individual being selected is the same. Finally, the cumulative probability is calculated. Use rand() to generate a random number r between [0,1], and determine the selected individual based on the interval where r is located; secondly, at the end of each cycle, the elite ant’s solution is taken out, and the elite ant’s path is adjusted locally with pheromones, so that the optimal solution found so far is more attractive in the next cycle.

5. A device for joint optimization of multi-task allocation and trajectory planning of heterogeneous UAV clusters, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the joint optimization method of multi-task allocation and trajectory planning of a heterogeneous UAV cluster as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when called, are used to execute the joint optimization method for multi-task allocation and trajectory planning of a heterogeneous UAV cluster as described in any one of claims 1-3.

Images