Unmanned cluster dynamic task allocation method and device based on crow search algorithm

Abstract

The present application provides a method and device for dynamic task allocation of an unmanned cluster based on a crow search algorithm. Through the crow search algorithm, a first crow population is allocated to a preset multi-objective task to be optimized, and a drone is allocated to a target task point corresponding to the preset multi-objective task to be optimized through a memory position corresponding to a crow individual with the largest fitness in the first crow population. The preset multi-objective tasks to be optimized can be selected through the crow search algorithm, and an unmanned platform can be allocated to the target task point corresponding to the multi-objective task to be optimized through the finally obtained memory position, so that the coordination plan of the unmanned platform is closer to the requirements of the preset multi-objective task to be optimized, and the execution efficiency of the unmanned platform for the preset multi-objective task to be optimized is improved to a certain extent.

Description

Technical Field

[0001] The present application relates to the field of unmanned aerial vehicle technology, and in particular to a method and device for dynamic task allocation of unmanned aerial vehicle clusters based on a crow search algorithm. Background Art

[0002] With the in-depth development and widespread application of integrated circuits and unmanned control technology, unmanned systems represented by unmanned platforms, unmanned vehicles, unmanned ships and other platforms are profoundly changing the production and lifestyle of human society. Single unmanned systems are already common in various fields. For example, the use of unmanned platforms for oil field inspections, fixed-point shooting, traffic inspections, etc. has achieved initial results; vehicle autonomous driving technology has been widely studied and is being promoted at a significant speed for commercial applications; environmental testing and supervision through unmanned ships has also become an important technical means for relevant departments. At the same time, unmanned platforms mainly used for wide-area reconnaissance and search have been widely used. However, single unmanned systems have problems such as limited resources, low reliability, and poor flexibility, and the accuracy, breadth and depth of perception of unmanned systems are low.

[0003] Among the related technologies, the research on unmanned cluster task allocation mainly focuses on static task allocation, that is, planning the collaborative tasks of multiple unmanned platforms through manual planning. Through their collaborative cooperation, an unmanned cluster with flexible resource allocation, strong adaptability, high reliability, and multi-domain operation can be formed, which can improve the accuracy, breadth and depth of unmanned system perception to a certain extent.

[0004] However, the collaborative solutions of unmanned platforms obtained by the above methods are often not highly matched with actual needs. Unmanned platforms often encounter various problems when performing tasks, such as low resource utilization of unmanned platforms, long task execution time or inability to execute tasks, resulting in low efficiency of unmanned platforms in executing tasks. Summary of the invention

[0005] In view of the above problems, the embodiments of the present application provide a method, device, electronic device and readable storage medium for dynamic task allocation of an unmanned cluster based on a crow search algorithm, so as to overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect, an embodiment of the present application provides an unmanned cluster dynamic task allocation method based on a crow search algorithm, the method comprising:

[0007] Assigning a first crow population to a preset multi-objective task to be optimized, and randomly assigning a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between the unmanned platform and the target task point;

[0008] Determine the individual position information of a first crow corresponding to a first Pareto set of the first crow population;

[0009] Generate position information of a second crow individual of the first crow individual;

[0010] Based on the relative positions between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals, respectively, determining the third crow individual position information of each of the first crow individuals;

[0011] Moving each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population;

[0012] Determine the first fitness corresponding to each second crow individual included in the updated first crow population;

[0013] determining a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses;

[0014] Based on the second memory position, an unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized.

[0015] Optionally, the determining the first crow individual position information corresponding to the first Pareto set of the first crow population includes:

[0016] determining a first Pareto set corresponding to the first crow population;

[0017] When a scene parameter of a real scene corresponding to the preset multi-objective task to be optimized changes, re-determining a second Pareto set corresponding to the first crow population;

[0018] Based on the first center point of the first Pareto set and the second center point of the second Pareto set, the third crow individual corresponding to the first Pareto set is moved to obtain the position information of the first crow individual.

[0019] Optionally, the generating the position information of the second crow individual of the first crow individual includes:

[0020] generating a first random number;

[0021] When the first random number is smaller than the perception probability parameter of the first crow individual, randomly generating position information of a second crow individual of the first crow individual;

[0022] When the first random number is greater than or equal to the perception probability parameter, the second crow individual position information is generated based on the first random number, the first memory position and the flight distance of the first crow individual.

[0023] Optionally, the generating the position information of the second crow individual of the first crow individual includes:

[0024] Based on the flight constraint of the first crow individual, the second crow individual position information of the first crow individual is generated.

[0025] Optionally, the method further comprises:

[0026] Under the condition that the first memory position corresponding to the first crow individual remains unchanged, determining the first memory time of the first crow individual for the first memory position based on the number of iterations of the first crow population;

[0027] Based on the first memory time, the perception probability parameter is determined.

[0028] Optionally, the generating the position information of the second crow individual of the first crow individual includes:

[0029] Based on the second memory times respectively corresponding to the first crow individuals, second crow individual position information of the first crow individuals is generated.

[0030] Optionally, the method further comprises:

[0031] Based on the second memory positions respectively corresponding to the first crow individuals, the flight constraints respectively corresponding to the first crow individuals are determined.

[0032] Optionally, the step of moving each of the first crow individuals to a position corresponding to the position information of the third crow individuals to obtain an updated first crow population includes:

[0033] Adding the position information of the third crow individual to the first memory position of each of the first crow individuals to obtain an updated first memory position;

[0034] Determining a first matching relationship between the unmanned platform and the target task point contained in the updated first memory position;

[0035] Based on the dominance relationship between each of the first matching relationships, the updated first memory position is deleted to obtain an updated first crow population.

[0036] Optionally, the determining the first fitness corresponding to each second crow individual included in the updated first crow population includes:

[0037] Determining, based on the position information of the third crow individual, the third fitness corresponding to each second crow individual included in the updated first crow population;

[0038] Determining the fourth fitness of the first memory positions corresponding to each of the second crow individuals;

[0039] The maximum value between the third fitness and the fourth fitness is determined as the first fitness corresponding to each of the second crow individuals.

[0040] In a second aspect, an embodiment of the present application provides an unmanned cluster dynamic task allocation device based on a crow search algorithm, the device comprising:

[0041] A first allocation module is used to allocate a first crow population to a preset multi-objective task to be optimized, and randomly allocate a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between the unmanned platform and the target task point;

[0042] A first determining module, configured to determine position information of a first crow individual corresponding to a first Pareto set of the first crow population;

[0043] A generating module, used for generating position information of a second crow individual of the first crow individual;

[0044] A second determination module is used to determine the third crow individual position information of each of the first crow individuals based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals;

[0045] An updating module, configured to move each of the first crow individuals to a position corresponding to the position information of the third crow individual, to obtain an updated first crow population;

[0046] A third determination module is used to determine the first fitness corresponding to each second crow individual included in the updated first crow population;

[0047] A fourth determination module is used to determine a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses;

[0048] The second allocation module is used to allocate an unmanned platform to a target task point corresponding to the preset multi-objective task to be optimized based on the second memory position.

[0049] Optionally, the first determining module includes:

[0050] A first determination submodule, used to determine a first Pareto set corresponding to the first crow population;

[0051] A second determination submodule is used to re-determine the second Pareto set corresponding to the first crow population when the scene parameters of the real scene corresponding to the preset multi-objective task to be optimized change;

[0052] The third determining submodule is used to move the third crow individual corresponding to the first Pareto set based on the first center point of the first Pareto set and the second center point of the second Pareto set to obtain the position information of the first crow individual.

[0053] Optionally, the generating module includes:

[0054] A first generating submodule, used to generate a first random number;

[0055] A second generating submodule, configured to randomly generate position information of a second crow individual of the first crow individual when the first random number is smaller than a perception probability parameter of the first crow individual;

[0056] The third generating submodule is used to generate the second crow individual position information based on the first random number, the first memory position and the flight distance of the first crow individual when the first random number is greater than or equal to the perception probability parameter.

[0057] Optionally, the generating module includes:

[0058] The fourth generating submodule is used to generate the second crow individual position information of the first crow individual based on the flight constraint condition of the first crow individual.

[0059] Optionally, the device further comprises:

[0060] a fifth determining module, configured to determine, when the first memory position corresponding to the first crow individual remains unchanged, a first memory time of the first crow individual for the first memory position based on the number of iterations of the first crow population;

[0061] A sixth determination module is used to determine the perception probability parameter based on the first memory time.

[0062] Optionally, the generating module includes:

[0063] The fifth generating submodule is used to generate the second crow individual position information of the first crow individual based on the second memory time corresponding to the first crow individual.

[0064] Optionally, the device further comprises:

[0065] The seventh determination module is used to determine the flight constraint conditions corresponding to the first crow individuals based on the second memory positions corresponding to the first crow individuals.

[0066] Optionally, the update module includes:

[0067] An adding submodule, used for adding the position information of the third crow individual to the first memory position of each of the first crow individuals to obtain an updated first memory position;

[0068] A fourth determination submodule is used to determine a first matching relationship between the unmanned platform contained in the updated first memory position and the target task point;

[0069] A deletion submodule is used to delete the updated first memory positions based on the dominance relationship between each of the first matching relationships to obtain an updated first crow population.

[0070] Optionally, the third determining module includes:

[0071] A fifth determination submodule, configured to determine, based on the position information of the third crow individuals, the third fitness corresponding to each second crow individual included in the updated first crow population;

[0072] A sixth determination submodule, used to determine the fourth fitness of the first memory positions respectively corresponding to the second crow individuals;

[0073] The seventh determination submodule is used to determine the maximum value of the third fitness and the fourth fitness as the first fitness corresponding to each of the second crow individuals.

[0074] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the unmanned cluster dynamic task allocation method based on the crow search algorithm as described in any one of the above.

[0075] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the unmanned cluster dynamic task allocation method based on the crow search algorithm as described in any one of the above items is implemented.

[0076] The specific beneficial effects are:

[0077] The embodiment of the present application assigns a first crow population to a preset multi-objective task to be optimized, and randomly assigns a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of first crow individuals; the memory position represents a matching relationship between the unmanned platform and the target task point, determines the first crow individual position information corresponding to the first Pareto set of the first crow population, generates the second crow individual position information of the first crow individual, determines the third crow individual position information of each first crow individual based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each first crow individual, and moves each first crow individual to the position of the third crow individual position information pair. The corresponding position is obtained, and the updated first crow population is obtained. The first fitness corresponding to each second crow individual contained in the updated first crow population is determined, and the second memory position of the second crow individual corresponding to the maximum fitness in the first fitness is determined. Based on the second memory position, the unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized. The preset multi-objective task to be optimized can be selected through the crow search algorithm, and the unmanned platform can be allocated to the target task point corresponding to the multi-objective task to be optimized through the finally obtained second memory position, so that the coordination plan of the unmanned platform is closer to the needs of the preset multi-objective task to be optimized, and the execution efficiency of the unmanned platform for the preset multi-objective task to be optimized is improved to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0079] Figure 1 It is a flowchart of a method for dynamic task allocation of an unmanned cluster based on a crow search algorithm provided in an embodiment of the present application;

[0080] Figure 2 is a schematic diagram of a task allocation coding provided in an embodiment of the present application;

[0081] Figure 3 It is a flowchart of another unmanned cluster dynamic task allocation method based on the crow search algorithm provided in an embodiment of the present application;

[0082] Figure 4 It is a logic block diagram of an unmanned cluster dynamic task allocation device based on a crow search algorithm provided in an embodiment of the present application;

[0083] Figure 5It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] The exemplary embodiments of the present application will be described in more detail below in conjunction with the accompanying drawings in the embodiments of the present application. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to enable the scope of the present application to be fully communicated to those skilled in the art.

[0085] Reference Figure 1 , Figure 1 A flow chart of a method for dynamic task allocation of an unmanned cluster based on a crow search algorithm provided in an embodiment of the present application, the method comprising:

[0086] Step 101, assigning a first crow population to a preset multi-objective task to be optimized, and randomly assigning a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between an unmanned platform and a target task point.

[0087] In an embodiment of the present application, a multi-objective task to be optimized refers to a task that contains multiple optimization objectives, for example, minimizing the cost of the task solution, maximizing the benefit of the task solution, minimizing the execution time of the task solution, and so on. In order to obtain a task solution that can achieve these optimization goals, a Crow Search Algorithm (CSA) can be used to derive the optimal task solution. The Crow Search Algorithm is a meta-heuristic optimization algorithm that simulates the behavior of crows hiding food in nature. The algorithm finds the optimal solution to optimization problems such as engineering by simulating the behavior of crows hiding food in different locations and retrieving it when needed. The preset multi-objective task to be optimized in an embodiment of the present application may refer to an assignment task that assigns an unmanned platform to a target task point to perform a corresponding task. After obtaining the preset multi-objective task to be optimized, a first crow population can be assigned to the task, and a first memory position can be randomly assigned to the first crow individual in the first crow population. Among them, the first crow population may include a preset number of first crow individuals. In order to make the crow search algorithm have a sufficiently high diversity, the number of first crow individuals may be greater than or equal to the number of target task points; the memory position may represent the matching relationship between the unmanned platform and the target task point, that is, each crow individual may save the matching relationship between the unmanned platform and the target task point. In addition, it is also possible to prevent the matching relationship between the same target task point and different unmanned platforms from appearing in the first memory position of each first crow individual, so as to avoid invalid data in the first crow population and improve the execution efficiency of the crow search algorithm. It should be noted that even if the number and content of the matching relationship stored in the first memory position are not limited here, it will not affect the optimal result finally obtained, but will only affect the duration of the optimization process.

[0088] For example, if there are 4 target task points corresponding to the preset multi-target task to be optimized and 4 unmanned platforms, there can be 4×4=16 matching relationships between the target task points and the unmanned platforms. These 16 matching relationships can be divided into 4 groups according to the target task points. The first memory position corresponding to each first crow individual can save 1 of each group of matching relationships, for a total of 4.

[0089] Step 102: Determine the individual position information of the first crow corresponding to the first Pareto set of the first crow population.

[0090] In the embodiments of the present application, Pareto Optimality is an ideal state of resource allocation, that is, it is impossible to make one person better off by changing the resource allocation without harming others. The improvement under this state is called Pareto improvement, and the state that cannot be further improved is Pareto Optimality. To describe it in mathematical language, if the allocation plan corresponding to the allocation task is regarded as a decision, then in the decision space In time slot t, given the solution , x is a Pareto optimal solution if and only if there is no other solution that dominates it. Decision space The set of all Pareto optimal solutions in is called Pareto Set (PS), as shown in Equation 1:

[0091] (Formula 1)

[0092] In formula 1, represents the first Pareto set, For decision space, x and y Both decision spaces The solution of " means to dominate, , that is y Dominate x The definition of "dominance" is that, at time slot t, given two solutions x and y, when the constraints shown in Formula 2 are satisfied, then x is said to dominate y, which is as follows:

[0093] (Formula 2)

[0094] Formula 2 can be explained as follows: For any , both , and exists , so that .in, Represents the set of fitness functions.

[0095] In an embodiment of the present application, the first Pareto set of the first crow population can be obtained by randomly assigning the first memory position to the first crow individual in the first crow population and then screening the first memory position by the above definition. After determining the first Pareto set of the first crow population, the corresponding first crow individual can be determined according to the first memory position contained in the first Pareto set, so that the first crow individual position information of the first crow individual can be further determined. It should be noted that in the crow search algorithm, each crow individual can exist in the same search space, and the crow individual position information is the position information of the crow individual in the search space. The memory position can also exist in the search space, but the memory position can include the matching relationship between the unmanned platform and the target task point, while other spatial positions may not include the above matching relationship because they do not meet the matching conditions (such as 2 unmanned platforms are assigned to the same target point).

[0096] Step 103: Generate position information of a second crow individual of the first crow individual.

[0097] In an embodiment of the present application, the first crow individual can move in the search space to obtain the memory position information of other first crow individuals. At the same time, the first crow individual can also take some measures to avoid being obtained by other first crow individuals. That is to say, each first crow individual can move in the search space. In order to achieve this purpose, the second crow individual position information of the first crow individual can be generated according to a certain method, such as randomly generated or generated according to the first memory position of the first crow individual.

[0098] Step 104: determine the third crow individual position information of each of the first crow individuals based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals.

[0099] In an embodiment of the present application, the relative position between the first crow individual position and the second crow individual position corresponding to each first crow individual can be obtained, so that the third crow individual position information of the first crow individual can be determined according to the relative position. Among them, each first crow individual can have a certain range constraint, and the first crow individual can independently determine whether the relative position meets its own range constraint. If it meets, the second crow individual position information can be determined as the third crow individual position information. If not, the first crow individual position information can be determined as the third crow individual position information. In this way, after traversing all the first crow individuals, the third crow individual position information of each first crow individual can be obtained. It should be noted that when the first crow individual makes a judgment, it can make a judgment according to the second crow individual position information corresponding to itself, or it can make a judgment according to the second crow individual position information corresponding to other first crow individuals.

[0100] For example, if the relative position between the first crow individual position [a, b] of crow individual A and the second crow individual position [c, d] of A itself satisfies the range constraint of A, then the third crow individual position information of crow individual A can be [c, d]; if the relative position between the first crow individual position of crow individual A and the second crow individual position [e, f] of crow individual B satisfies the range constraint of A, then the third crow individual position information of crow individual A can be [e, f]; if the relative position does not satisfy the range constraint of A, then the third crow individual position information of A can be [a, b].

[0101] Step 105: Move each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population.

[0102] In an embodiment of the present application, each first crow individual can be moved to a position corresponding to the position information of the third crow individual, so that the first crow individuals in the first crow population can be updated to obtain an updated first crow population.

[0103] Step 106: determine the first fitness corresponding to each second crow individual included in the updated first crow population.

[0104] In an embodiment of the present application, the first fitness corresponding to each second crow individual contained in the updated first crow population can be calculated according to the fitness function corresponding to the preset multi-objective task to be optimized. Among them, for the preset multi-objective task to be optimized, each target contained therein can correspond to a fitness function, and the fitness function corresponding to the multi-objective task can be obtained by weighted averaging the fitness functions corresponding to each target separately. Among them, the weight of each target can be the same, or it can be set manually. Among them, the fitness function of each target can be calculated by the matching relationship between the target task point and the unmanned platform obtained in the end, that is, the optimal memory position. For example, if the goal is to minimize the task time and minimize the task profit loss, the corresponding fitness functions can be shown in Formulas 3 and 4 respectively:

[0105] (Formula 3)

[0106] (Formula 4)

[0107] In Equations 3 and 4, the task time Including the time it takes for the unmanned platform to fly to the target point and the time it takes to perform tasks at the target point; loss of revenue It is the product of the probability of failure of the unmanned platform to perform the task at the target point and the task benefit. Indicates the number of unmanned platforms in the cluster. Indicates the number of target mission points, is the decision variable for task allocation. If the unmanned platform At the target mission point If the task is executed on ,otherwise ;in addition, , , , , are the inherent parameters of the preset multi-objective tasks to be optimized. It is an unmanned platform With the target mission point The distance It is an unmanned platform speed, It is an unmanned platform At the target mission point The time required to perform the task, The target mission point The task execution income, It is an unmanned platform At the target mission point The success probability of executing the task.

[0108] In the embodiments of the present application, if the fitness metrics of different objectives are different, the metrics can be unified first. If the optimization objectives include minimum optimization objectives and maximum optimization objectives, they can be unified into minimum or maximum values ​​and then weighted averaged; if the fitness functions included in the optimization objectives have different value ranges, the fitness functions can be normalized first (e.g., using Function), and then perform weighted averaging to obtain the fitness function of the multi-objective task to be optimized.

[0109] Step 107: determine a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses.

[0110] In an embodiment of the present application, the maximum fitness among the first fitness can be determined, and the second crow individual corresponding to the maximum fitness can be further determined, so that the second memory position of the second crow individual can be obtained. It should be noted that in the process of obtaining the second memory position, the process from step 102 to step 106 can be repeated iteratively multiple times so that the fitness of the second memory position finally obtained meets the task requirements. After each iteration, the Pareto set can be updated by the updated memory position of the crow individual. Usually, the second memory position can be one or more Pareto optimal solutions in the updated Pareto set.

[0111] Step 108: Based on the second memory position, an unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized.

[0112] In an embodiment of the present application, the matching relationship between the unmanned platform and the target task point can be stored in the second memory position. Therefore, the unmanned platform can be allocated to the target task point corresponding to the preset multi-target task to be optimized according to the second memory position.

[0113] In a possible embodiment, the second memory location may also include priority parameters of each matching relationship and output them in a coded form. Figure 2 As shown, Figure 2A schematic diagram of a task allocation code provided for an embodiment of the present application. In the figure, the task allocation code corresponding to the second memory position is {1.25, 1.5, 3.2, 2.8, 2.1, 1.8}, and the position of each part of the code in the entire task allocation code corresponds to the target task point T1 to T6. The integer part of the code corresponds to the serial number U1 to U3 of the unmanned platform, and the decimal part corresponds to the priority parameter of the matching relationship between the unmanned platform and the corresponding target task point. The smaller the priority parameter, the higher its priority. The task execution time and range of unmanned platforms U1, U2, and U3 are all different. In the figure, unmanned platform U1 is assigned to target task points T1, T2 and T6, unmanned platform U2 is assigned to T4 and T5, and unmanned platform U3 is assigned to T3. For unmanned platform U1, since T1 has the highest priority, T6 has the lowest priority, and T2 has a priority between T1 and T6, when unmanned platform U1 performs tasks, it can perform tasks serially in the order of "T1→T2→T6". Similarly, unmanned platform U2 can execute tasks in the order of "T5→T4", and unmanned platform U3 can execute tasks at T3. Different unmanned platforms can execute tasks in any order and will not affect each other.

[0114] In an embodiment of the present application, a first crow population is assigned to a preset multi-objective task to be optimized, and a first memory position is randomly assigned to a first crow individual in the first crow population; wherein the first crow population includes a preset number of first crow individuals; the memory position represents a matching relationship between the unmanned platform and the target task point, the first crow individual position information corresponding to the first Pareto set of the first crow population is determined, the second crow individual position information of the first crow individual is generated, and based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each first crow individual, the third crow individual position information of each first crow individual is determined respectively, and each first crow individual is moved to the third crow individual position information The position corresponding to the information is obtained to obtain the updated first crow population, the first fitness corresponding to each second crow individual contained in the updated first crow population is determined, and the second memory position of the second crow individual corresponding to the maximum fitness in the first fitness is determined. Based on the second memory position, the unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized, the preset multi-objective task to be optimized can be selected through the crow search algorithm, and the unmanned platform can be allocated to the target task point corresponding to the multi-objective task to be optimized through the finally obtained second memory position, so that the coordination plan of the unmanned platform is closer to the needs of the preset multi-objective task to be optimized, and the execution efficiency of the unmanned platform for the preset multi-objective task to be optimized is improved to a certain extent.

[0115] Reference Figure 3 , Figure 3A flow chart of another unmanned cluster dynamic task allocation method based on a crow search algorithm provided in an embodiment of the present application, the method may include:

[0116] Step 201, assigning a first crow population to a preset multi-objective task to be optimized, and randomly assigning a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between an unmanned platform and a target task point.

[0117] In the embodiments of the present application, the implementation content of this step can refer to the embodiment content of step 101, which will not be repeated here.

[0118] Step 202: Determine the individual position information of the first crow corresponding to the first Pareto set of the first crow population.

[0119] In the embodiments of the present application, the implementation content of this step can refer to the implementation content of step 102, which will not be repeated here.

[0120] Optionally, step 202 may include the following sub-steps:

[0121] Sub-step 2021: determining a first Pareto set corresponding to the first crow population.

[0122] In the embodiment of the present application, after obtaining the first crow population corresponding to the preset multi-objective task to be optimized, the first Pareto set corresponding to the first crow population can be determined. The specific implementation content of determining the first Pareto set can refer to the embodiment content of step 102, which will not be repeated here.

[0123] Sub-step 2022, when the scene parameters of the real scene corresponding to the preset multi-objective task to be optimized change, re-determine the second Pareto set corresponding to the first crow population.

[0124] In an embodiment of the present application, the real scene corresponding to the preset multi-objective task to be optimized can be monitored to obtain the real-time scene parameters of the real scene. Among them, the scene parameters may include environmental parameters such as temperature, wind speed, wind direction, and rainfall. If the scene parameters of the real scene corresponding to the preset multi-objective task to be optimized change, the Pareto optimal solution in the first Pareto set may no longer be the Pareto optimal solution after the scene parameters change. Therefore, the second Pareto set corresponding to the first crow population can be re-determined. The implementation method for determining the second Pareto set is similar to that for determining the first Pareto set. Please refer to the embodiment content of step 102, which will not be repeated here.

[0125] Sub-step 2023: Based on the first center point of the first Pareto set and the second center point of the second Pareto set, move the third crow individual corresponding to the first Pareto set to obtain the position information of the first crow individual.

[0126] In an embodiment of the present application, the center point of the Pareto set may refer to the mean point of the Pareto optimal solution contained in the Pareto set. If both the first Pareto set and the second Pareto set are distributed in a two-dimensional plane, the Pareto optimal solution may be in the form of a "point". These "points" may be surrounded by a plane figure, and the "point" located at the center of the plane is the Pareto optimal solution in the middle of the Pareto set, that is, the center point of the Pareto set. On this basis, the offset direction and offset size of the first crow population may be determined according to the first center point of the first Pareto set and the second center point of the second Pareto set. Among them, the offset direction of the first crow population refers to the offset direction of each first crow individual contained in the first crow population in the crow search space. In addition, the offset size of the first memory position may be determined according to the distance between the first center point and the second center point. For example, the offset size may be equal to the distance between the first center point and the second center point, or may be in a certain proportion. After obtaining the offset direction and offset size of the first crow population, the third crow individual corresponding to the first Pareto set can be moved according to the above offset direction and offset size, so that the position information of the moved third crow individual in the search space can be used as the position information of the first crow individual.

[0127] Step 203: Generate position information of a second crow individual of the first crow individual.

[0128] In the embodiments of the present application, the implementation content of this step can refer to the implementation content of step 103, which will not be repeated here.

[0129] Optionally, step 203 may include the following sub-steps:

[0130] Sub-step 2031, when the first memory position corresponding to the first crow individual remains unchanged, determining the first memory time of the first crow individual for the first memory position based on the number of iterations of the first crow population.

[0131] In an embodiment of the present application, during the iteration process of the first population, the first memory position of the first crow individual may or may not change. In the crow search algorithm, if the first crow individual perceives that it is being tracked by other first crow individuals, it will randomly move to any position in the search space, and the first memory position of the first crow individual will not change; if the first crow individual does not perceive that it is being tracked by other first crow individuals, it will move to one of the first memory positions or track other first crow individuals, so that it will be captured by other first crow individuals to a new memory position or it will be captured to a new memory position by itself. If the first memory position corresponding to the first crow individual remains unchanged, it means that the first memory position of the first crow individual may have a good fitness, resulting in the first memory position of the first crow individual not changing during the iteration process. At this time, the first memory time of the first crow individual for the first memory position can be determined. The memory time in the present application can be the number of iterations of the first crow population, without a unit of measurement. For example, if the number of iterations of the first crow population is 10, and the first memory position of the first crow individual remains unchanged, then the first memory time of the first memory position of the first crow individual is 10. When the first memory position changes, the first memory time may be initialized to 0.

[0132] Sub-step 2032: determining the perception probability parameter based on the first memory time.

[0133] In an embodiment of the present application, as the first memory time increases, the perception of the first crow individual to other first crow individuals can be improved, so the perception probability parameter of the first crow individual can be calculated according to the first memory time. Among them, the perception probability parameter (awareness probability, AP) can represent the tracking perception probability of the first crow individual to other first crow individuals, and its initial value can be manually preset. The iterative algorithm of the perception probability parameter with the first memory time is shown in the following formula 5:

[0134] (Formula 5)

[0135] In formula 5, represents the perception probability parameter, Indicates the first memory time.

[0136] Sub-step 2033, generating a first random number.

[0137] In an embodiment of the present application, a first random number may be generated to determine whether the first crow individual senses being tracked, wherein the value interval of the first random number may be [0, 1].

[0138] Sub-step 2034: When the first random number is smaller than the perception probability parameter of the first crow individual, randomly generate the second crow individual position information of the first crow individual.

[0139] In an embodiment of the present application, if the first random number is smaller than the perception probability parameter of the first crow individual, it can be considered that the first crow individual senses that it is being tracked, and at this time, the position of the second crow individual of the first crow individual can be randomly generated.

[0140] Sub-step 2035, when the first random number is greater than or equal to the perception probability parameter, generating the second crow individual position information based on the first random number, the first memory position and the flight distance of the first crow individual.

[0141] In an embodiment of the present application, if the first random number is greater than or equal to the perception probability parameter, it can be considered that the first crow individual does not perceive being tracked, and at this time, the second crow individual position can be generated according to the first memory position of the first crow, the flight distance of the first crow and the first random number. The calculation method of the second crow individual position can be shown in the following formula 6:

[0142] (Formula 6)

[0143] In formula 6, Indicates the first crow individual i The position vector of the first crow's individual position, j Indicates that the first crow individual i The first crow individual tracked, t represents the number of iterations, m Indicates the first crow individual j The first memory position of is the first random number, The first crow i voyage.

[0144] Sub-step 2036, based on the second memory positions corresponding to the first crow individuals, determining the flight constraints corresponding to the first crow individuals.

[0145] In an embodiment of the present application, in a tracking / tracking process, there may be tracking crow individuals and tracked crow individuals, and both the tracking crow individuals and the tracked crow individuals belong to the first crow individual. Therefore, in the entire first crow population, the first crow individuals can be traversed, and the flight constraints corresponding to the first crow individuals can be calculated based on the second memory positions corresponding to the first crow individuals. Among them, the iterative calculation method of the flight constraint is shown in the following formula 7:

[0146] (Formula 7)

[0147] In formula 7, is the flight constraint, is the position dimension value of the tracked crow individual in the search space, To track the position dimension value of individual crows in the search space, is the upper limit of the search space dimension value, is the lower limit of the search space dimension value.

[0148] Sub-step 2037, generating position information of a second crow individual of the first crow individual based on the flight constraint condition of the first crow individual.

[0149] In an embodiment of the present application, the second crow individual position information of the first crow individual can be generated according to the flight constraint of the first crow individual. That is, the distance between the second crow individual position information of the first crow individual and the first crow individual position information can be less than the flight constraint of the first crow individual, so that the first crow individual can fly from the position corresponding to the first crow individual position information to the position corresponding to the second crow individual position information.

[0150] Sub-step 2038, generating second crow individual position information of the first crow individual based on the second memory time corresponding to each of the first crow individuals.

[0151] In an embodiment of the present application, for the first crow individual, when it tracks other first crow individuals, it can obtain the second memory time of other first crow individuals, and the first crow individual will give priority to tracking other first crow individuals with smaller second memory time. In the first crow population, the first crow individuals can be traversed, so that the crow individuals that the current individual should track can be determined according to the second memory times corresponding to the first crow individuals, so that the first crow individual position information of the tracked first crow individual can be used as the second crow individual position information of the first crow individual that performs tracking. To describe it in mathematical language, when each crow individual selects a crow individual to track, it can use 1 / m ( t ) as the selection probability for roulette selection.

[0152] Step 204: determine the third crow individual position information of each of the first crow individuals based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals.

[0153] In the embodiments of the present application, the implementation content of this step can refer to the implementation content of step 104, which will not be repeated here.

[0154] Step 205: Move each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population.

[0155] In the embodiments of the present application, the implementation content of this step can refer to the implementation content of step 105, which will not be repeated here.

[0156] Optionally, step 205 may include the following sub-steps:

[0157] Sub-step 2051, adding the position information of the third crow individual to the first memory position of each of the first crow individuals to obtain an updated first memory position.

[0158] In an embodiment of the present application, after the first crow individuals move to the positions of the respective corresponding third crow individuals, the position information of the third crow individuals may be added to the first memory positions of the respective first crow individuals to obtain updated first memory positions.

[0159] Sub-step 2052: determining a first matching relationship between the unmanned platform contained in the updated first memory position and the target task point.

[0160] In an embodiment of the present application, after the first memory position is updated, a first matching relationship between the unmanned platform and the target task point contained in the updated first memory position can be determined.

[0161] Sub-step 2053: based on the dominance relationship between each of the first matching relationships, delete the updated first memory position to obtain an updated first crow population.

[0162] In the embodiment of the present application, the first matching relationship of the same target task point corresponding to different unmanned platforms may appear in the updated first memory position. At this time, the dominance relationship between the first matching relationships can be determined, and the updated first memory position can be deleted. In this way, after traversing all the first crow individuals, the first crow population can be updated to obtain the updated first crow population. It is easy to understand that the object of deletion can be the dominated first matching relationship, because at this time it is no longer a Pareto optimal solution.

[0163] Step 206: Determine the third fitness corresponding to each second crow individual included in the updated first crow population based on the position information of the third crow individual.

[0164] In an embodiment of the present application, the third fitness corresponding to each second crow individual included in the updated first crow population can be calculated based on the third crow individual position information. Specifically, the third crow individual position information can be used to update the memory information of each second crow individual. After the memory information is updated, the third fitness of each second crow individual is calculated using the updated memory information. The fitness function used can refer to the implementation content in step 106 and the contents of formula 3 and formula 4.

[0165] Step 207, determining the fourth fitness of the first memory position corresponding to each of the second crow individuals.

[0166] In the embodiment of the present application, the fourth fitness of the first memory position corresponding to each second crow individual can be calculated. The fitness function used in the calculation can refer to the implementation content in step 106 and the content of formula 3 and formula 4.

[0167] Step 208: Determine the maximum value of the third fitness and the fourth fitness as the first fitness corresponding to each of the second crow individuals.

[0168] In the embodiment of the present application, the third fitness and the fourth fitness of the same crow individual can be compared, and the maximum value of the third fitness and the fourth fitness can be determined as the first fitness corresponding to each second crow individual. This comparison and assignment process can be performed independently according to the second crow individual, and different second crow individuals do not affect each other. At the same time, if the third fitness is greater than the fourth fitness, it means that the corresponding second crow individual has obtained a better memory position, and the first memory position of the second crow individual can be updated at this time.

[0169] Step 209: determine a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses.

[0170] In the embodiment of the present application, the implementation content of this step can refer to the implementation content of step 107, which will not be repeated here.

[0171] Step 210: Based on the second memory position, an unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized.

[0172] In the embodiment of the present application, the implementation content of this step can refer to the implementation content of step 108, which will not be repeated here.

[0173] Reference Figure 4 , Figure 4A logic block diagram of an unmanned cluster dynamic task allocation device based on a crow search algorithm provided in an embodiment of the present application, the device 400 may include:

[0174] The first allocation module 401 is used to allocate a first crow population to a preset multi-objective task to be optimized, and randomly allocate a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between the unmanned platform and the target task point;

[0175] A first determination module 402 is used to determine the position information of a first crow individual corresponding to a first Pareto set of the first crow population;

[0176] A generating module 403 is used to generate position information of a second crow individual of the first crow individual;

[0177] A second determination module 404 is used to determine the third crow individual position information of each of the first crow individuals based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals;

[0178] An updating module 405 is used to move each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population;

[0179] A third determination module 406 is used to determine the first fitness corresponding to each second crow individual included in the updated first crow population;

[0180] A fourth determination module 407 is used to determine a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses;

[0181] The second allocation module 408 is used to allocate an unmanned platform to a target task point corresponding to the preset multi-objective task to be optimized based on the second memory position.

[0182] Optionally, the first determining module 402 includes:

[0183] A first determination submodule, used to determine a first Pareto set corresponding to the first crow population;

[0184] A second determination submodule is used to re-determine the second Pareto set corresponding to the first crow population when the scene parameters of the real scene corresponding to the preset multi-objective task to be optimized change;

[0185] The third determining submodule is used to move the third crow individual corresponding to the first Pareto set based on the first center point of the first Pareto set and the second center point of the second Pareto set to obtain the position information of the first crow individual.

[0186] Optionally, the generating module 403 includes:

[0187] A first generating submodule, used to generate a first random number;

[0188] A second generating submodule, configured to randomly generate position information of a second crow individual of the first crow individual when the first random number is smaller than a perception probability parameter of the first crow individual;

[0189] The third generating submodule is used to generate the second crow individual position information based on the first random number, the first memory position and the flight distance of the first crow individual when the first random number is greater than or equal to the perception probability parameter.

[0190] Optionally, the generating module 403 includes:

[0191] The fourth generating submodule is used to generate the second crow individual position information of the first crow individual based on the flight constraint condition of the first crow individual.

[0192] Optionally, the device 400 further includes:

[0193] a fifth determining module, configured to determine, when the first memory position corresponding to the first crow individual remains unchanged, a first memory time of the first crow individual for the first memory position based on the number of iterations of the first crow population;

[0194] A sixth determination module is used to determine the perception probability parameter based on the first memory time.

[0195] Optionally, the generating module 403 includes:

[0196] The fifth generating submodule is used to generate the second crow individual position information of the first crow individual based on the second memory time corresponding to the first crow individual.

[0197] Optionally, the device 400 further includes:

[0198] The seventh determination module is used to determine the flight constraint conditions corresponding to the first crow individuals based on the second memory positions corresponding to the first crow individuals.

[0199] Optionally, the updating module 405 includes:

[0200] An adding submodule, used for adding the position information of the third crow individual to the first memory position of each of the first crow individuals to obtain an updated first memory position;

[0201] A fourth determination submodule is used to determine a first matching relationship between the unmanned platform contained in the updated first memory position and the target task point;

[0202] A deletion submodule is used to delete the updated first memory positions based on the dominance relationship between each of the first matching relationships to obtain an updated first crow population.

[0203] Optionally, the third determining module 406 includes:

[0204] A fifth determination submodule, configured to determine, based on the position information of the third crow individuals, the third fitness corresponding to each second crow individual included in the updated first crow population;

[0205] A sixth determination submodule, used to determine the fourth fitness of the first memory positions respectively corresponding to the second crow individuals;

[0206] The seventh determination submodule is used to determine the maximum value of the third fitness and the fourth fitness as the first fitness corresponding to each of the second crow individuals.

[0207] The unmanned cluster dynamic task allocation device based on the crow search algorithm in the embodiment of the present application can be an electronic device, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the electronic device can be a GPU BOX, a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0208] The unmanned cluster dynamic task allocation device based on the crow search algorithm in the embodiment of the present application can be a device with an operating system. The operating system can be an Android operating system, a Linux, a Windows operating system, etc., and can also be other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0209] The unmanned cluster dynamic task allocation device based on the crow search algorithm provided in the embodiment of the present application can achieve Figures 1 to 3 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0210] The present application embodiment provides an electronic device, see Figure 5 The electronic device 50 includes: a processor 501, a memory 502, and a computer program 5021 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the program, the unmanned cluster dynamic task allocation method based on the crow search algorithm of the aforementioned embodiment is implemented.

[0211] An embodiment of the present application also provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the steps in the unmanned cluster dynamic task allocation method based on the crow search algorithm disclosed in the embodiment of the present application are implemented.

[0212] The embodiment of the present application also provides a computer program product. When the computer program product is run on an electronic device, the processor is enabled to implement the steps in the unmanned cluster dynamic task allocation method based on the crow search algorithm as disclosed in the embodiment of the present application.

[0213] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0214] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices, electronic devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0215] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0216] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0217] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0218] Finally, it should be noted that, in this article, relational terms such as first and second, etc. 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 terminal 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0219] The above is a detailed introduction to the unmanned cluster dynamic task allocation method and device based on the crow search algorithm provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for dynamic task allocation of unmanned clusters based on crow search algorithm, characterized in that: The method comprises: Assigning a first crow population to a preset multi-objective task to be optimized, and randomly assigning a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between the unmanned platform and the target task point; Determine the individual position information of a first crow corresponding to a first Pareto set of the first crow population; Generate position information of a second crow individual of the first crow individual; Based on the relative positions between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals, respectively, determining the third crow individual position information of each of the first crow individuals; Moving each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population; Determine the first fitness corresponding to each second crow individual included in the updated first crow population; determining a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses; Based on the second memory position, an unmanned platform is allocated to the target task point corresponding to the preset multi-objective task to be optimized.

2. The method according to claim 1, characterized in that The step of determining the first crow individual position information corresponding to the first Pareto set of the first crow population includes: determining a first Pareto set corresponding to the first crow population; When a scene parameter of a real scene corresponding to the preset multi-objective task to be optimized changes, re-determining a second Pareto set corresponding to the first crow population; Based on the first center point of the first Pareto set and the second center point of the second Pareto set, the third crow individual corresponding to the first Pareto set is moved to obtain the position information of the first crow individual.

3. The method according to claim 1, characterized in that The step of generating the position information of the second crow individual of the first crow individual includes: generating a first random number; When the first random number is smaller than the perception probability parameter of the first crow individual, randomly generating position information of a second crow individual of the first crow individual; When the first random number is greater than or equal to the perception probability parameter, the second crow individual position information is generated based on the first random number, the first memory position and the flight distance of the first crow individual.

4. The method according to claim 1, characterized in that The step of generating the position information of the second crow individual of the first crow individual includes: Based on the flight constraint of the first crow individual, the second crow individual position information of the first crow individual is generated.

5. The method according to claim 3, characterized in that: The method further comprises: Under the condition that the first memory position corresponding to the first crow individual remains unchanged, determining the first memory time of the first crow individual for the first memory position based on the number of iterations of the first crow population; Based on the first memory time, the perception probability parameter is determined.

6. The method according to claim 1, characterized in that The step of generating the position information of the second crow individual of the first crow individual includes: Based on the second memory times respectively corresponding to the first crow individuals, second crow individual position information of the first crow individuals is generated.

7. The method according to claim 4, characterized in that The method further comprises: Based on the second memory positions respectively corresponding to the first crow individuals, the flight constraints respectively corresponding to the first crow individuals are determined.

8. The method according to claim 1, characterized in that The step of moving each of the first crow individuals to a position corresponding to the position information of the third crow individual to obtain an updated first crow population includes: Adding the position information of the third crow individual to the first memory position of each of the first crow individuals to obtain an updated first memory position; Determining a first matching relationship between the unmanned platform and the target task point contained in the updated first memory position; Based on the dominance relationship between each of the first matching relationships, the updated first memory position is deleted to obtain an updated first crow population.

9. The method according to claim 1, characterized in that: The determining of the first fitness corresponding to each second crow individual included in the updated first crow population includes: Determining, based on the position information of the third crow individual, the third fitness corresponding to each second crow individual included in the updated first crow population; Determining the fourth fitness of the first memory positions corresponding to each of the second crow individuals; The maximum value between the third fitness and the fourth fitness is determined as the first fitness corresponding to each of the second crow individuals.

10. An unmanned cluster dynamic task allocation device based on crow search algorithm, characterized in that: The device comprises: A first allocation module is used to allocate a first crow population to a preset multi-objective task to be optimized, and randomly allocate a first memory position to a first crow individual in the first crow population; wherein the first crow population includes a preset number of the first crow individuals; and the memory position represents a matching relationship between the unmanned platform and the target task point; A first determining module, configured to determine position information of a first crow individual corresponding to a first Pareto set of the first crow population; A generating module, used for generating position information of a second crow individual of the first crow individual; A second determination module is used to determine the third crow individual position information of each of the first crow individuals based on the relative position between the first crow individual position information and the second crow individual position information corresponding to each of the first crow individuals; An updating module, configured to move each of the first crow individuals to a position corresponding to the position information of the third crow individual, to obtain an updated first crow population; A third determination module is used to determine the first fitness corresponding to each second crow individual included in the updated first crow population; A fourth determination module, used to determine a second memory position of a second crow individual corresponding to the maximum fitness among the first fitnesses; The second allocation module is used to allocate an unmanned platform to a target task point corresponding to the preset multi-objective task to be optimized based on the second memory position.

Images