An Unmanned System Cluster Uniform Load Coverage Method and System for a Restricted Surface

Abstract

The present invention belongs to the technical field of cooperative control of unmanned systems, and specifically relates to a method and system for uniform load coverage of an unmanned system cluster on a restricted surface, including: determining a target coverage area, and constructing a communication network for the unmanned system cluster based on multiple individual unmanned systems; discretizing the split axis interval to obtain a set of initial split axis values, and assigning an initial split axis value to each individual unmanned system's split axis; performing balanced load segmentation on the determined target coverage area to obtain multiple sub-regions, and finding a local optimal sub-region deployment point for each individual unmanned system within its corresponding sub-region; calculating the loss of each individual unmanned system at each initial split axis value, and designing an optimal deployment control law based on the split axis with the minimum loss and its corresponding local optimal sub-region deployment point, so that each individual unmanned system is deployed to the selected sub-region deployment point.

Description

Technical Field

[0001] The present invention belongs to the technical field of cooperative control of unmanned systems, and particularly relates to a method and system for uniform load coverage of an unmanned system cluster on a restricted surface. Background Art

[0002] With the current rapid economic growth, the monitoring requirements in the maritime area are increasing day by day. Especially around key islands, comprehensive and real-time monitoring is required to prevent unauthorized vessels from intruding. However, the maritime environment is complex and changeable. When encountering adverse weather conditions, unmanned systems are often restricted by specific flight surfaces and cannot operate freely. In this case, traditional multi-agent cooperative coverage technologies face challenges because these technologies cannot be directly applied when unmanned systems are subject to surface constraints. In addition, current coverage strategies mostly follow the principle of "divide and conquer". This strategy first divides the area to be covered and then deploys coverage for the divided sub-areas. However, existing area division methods are mainly applicable to convex environments and are difficult to directly apply to concave environments. Moreover, existing division methods are difficult to ensure that the task amount borne by each unmanned system individual is consistent, resulting in heavy task amounts for some unmanned system individuals. Summary of the Invention

[0003] The present invention aims to provide a method for effectively dividing a restricted surface area by performing balanced load division on a target coverage area, ensuring load balance of the divided sub-areas, and thus ensuring that the task amount of each unmanned system individual is consistent. Based on the optimal sub-area deployment points, an optimal deployment control law is designed, and this control law enables the unmanned system cluster to reach the deployment points for deployment completely and quickly under surface constraints, realizing uniform task amount coverage and deployment of the area.

[0004] A method for uniform load coverage of an unmanned system cluster on a restricted surface includes:[[]]

[0005] Determine a target coverage area and construct a communication network of the unmanned system cluster based on multiple unmanned system individuals;

[0006] Discretize the division axis interval to obtain an initial set of division axis values, and assign an initial division axis value to the division axis of each unmanned system individual;

[0007] Perform balanced load division on the determined target coverage area to obtain multiple sub-areas, and find local optimal sub-area deployment points for each unmanned system individual within its corresponding sub-area;

[0008] Calculate the loss of each unmanned system individual at each initial division axis value, and design an optimal deployment control law based on the division axis with the minimum loss and its corresponding local optimal sub-area deployment point, so that each unmanned system individual is deployed to the selected sub-area deployment point.

[0009] By performing balanced load segmentation on the target coverage area, the restricted surface area is effectively segmented, and the load balance of the segmented sub-areas is ensured. Furthermore, the task volume of each individual unmanned system is guaranteed to be consistent. Based on the optimal sub-area deployment points, an optimal deployment control law is designed, and this control law enables the unmanned system cluster to reach the deployment points completely and quickly for deployment under the surface constraint, achieving uniform task volume coverage and deployment in the area.

[0010] Furthermore, the expression of the target coverage area is:

[0011] ;

[0012] In the formula, represents the target coverage area; represents the surface enclosed by the outer boundary line; represents the surface enclosed by the inner boundary line; represents a point in the XYZ coordinate system, , , respectively represent the coordinates in this three-dimensional coordinate system; represents the function of the projection area of the surface on the XOY plane; represents the surface enclosed by the outer boundary line in the projection area on the XOY plane, that is , represents the outer boundary of the restricted area; represents the surface enclosed by the inner boundary line in the projection area on the XOY plane, that is , represents the inner boundary of the restricted area; represents the polar angle of the segmentation axis of the restricted area; represents the polar radius of the restricted area; represents the real number space.

[0013] Furthermore, the communication networking of the unmanned system cluster is defined as an undirected graph, and its expression is:

[0014] ;

[0015] In the formula, represents the undirected graph in which the communication networking of the unmanned system cluster is defined; represents the set of N individual unmanned systems existing in the undirected graph, that is ; represents the connection situation between every two individual unmanned systems, that is , , represent two different individual unmanned systems, i.e., ; represents the adjacency matrix of an undirected graph, which is used to store the weights of the connecting edges between each individual unmanned system and other individual unmanned systems.

[0016] Further, the discretization process of the segmentation axis interval to obtain the initial set of segmentation axis values and assign the initial segmentation axis values to the segmentation axes of each individual unmanned system includes:

[0017] Discretize the segmentation axis interval to obtain multiple intervals, and construct a set of initial segmentation axis values based on the discretized intervals;

[0018] Randomly select an individual unmanned system, initialize its segmentation axis according to each element in the initial set of segmentation axis values, and randomly initialize the initial segmentation axis values of the remaining individual unmanned systems.

[0019] Further, the expression of the initial set of segmentation axis values is:

[0020] ;

[0021] In the formula, represents the initial value of the polar angle of the segmentation axis of the th individual unmanned system; represents the ordinal number of the interval; represents the discretization fineness, i.e., the total number of intervals.

[0022] Further, the balanced load segmentation of the determined target coverage area to obtain multiple sub-regions and find the local optimal sub-region deployment points for each individual unmanned system in each sub-region includes:

[0023] Based on the communication networking of the unmanned system cluster, each individual unmanned system obtains the sub-region load of the remaining individual unmanned systems;

[0024] Based on the obtained sub-region load, perform balanced load segmentation on the determined target coverage area to obtain multiple sub-regions;

[0025] Each individual unmanned system randomly initializes within its corresponding sub-region to generate a set of initial points;

[0026] Construct an objective optimization function based on the loss function of each individual unmanned system at the initial points, and use the gradient descent method to iteratively solve to obtain a set of local optimal deployment point sets;

[0027] Select the optimal solution from the set of local optimal deployment points to obtain the local optimal sub-region deployment points.

[0028] Further, the expression of the sub-region load of the individual unmanned system is:

[0029] ;

[0030] In the formula, represents the sub-region load of the th individual unmanned system; represents the sub-region of the th individual unmanned system; represents the density function of the total region , and is bounded, ; ; represents the surface integral;

[0031] The expression of the balanced load segmentation is:

[0032] ;

[0033] ;

[0034] In the formula, represents the polar angle of the segmentation axis of the th individual unmanned system region; represents the derivative; represents the control gain constant of the segmentation axis; represents the estimated value of the sub-region load of the th individual unmanned system; represents the control gain constant of the estimator; represents the weight of the communication connection edge between the th individual unmanned system and the th individual unmanned system; represents the estimated value of the sub-region load of the th individual unmanned system.

[0035] Furthermore, the expression of the objective optimization function is:

[0036] ;

[0037] ;

[0038] In the formula, represents the loss function value of the th individual unmanned system at the generated initial point, represents the estimated values of the polar radius and polar angle of the initial point of the th individual unmanned system; represents the straight-line distance function between two points on the surface, that is ; represents the function with respect to The partial derivative of, that is ; Denote the function with respect to The partial derivative of, that is ; Denote the optimal splitting axis of the -th individual unmanned system generated by the balanced load splitting; Denote the optimal splitting axis of the -th individual unmanned system generated by the balanced load splitting; Denote the lower limit of the estimated polar angle of the initial point of the -th individual unmanned system; Denote the upper limit of the estimated polar angle of the initial point of the -th individual unmanned system;

[0039] The expression for iterative solution using the gradient descent method is:

[0040] ;

[0041] In the formula, Denote the augmented Lagrangian variable of the -th individual unmanned system; Denote the control gain constant of the augmented Lagrangian variable; Denote the augmented Lagrangian function of the -th individual unmanned system; Denote the slack variable, that is ; Denote the Lagrange multiplier, that is ; Denote the transpose; Denote the Lagrange parameter, and ; Denote the constraint condition of the objective function of the -th individual unmanned system, that is , where ; ; ; ;

[0042] Furthermore, the expression of the optimal deployment control law is:

[0043] ;

[0044] ;

[0045] In the formula, Denote the position of the -th individual unmanned system, that is ; represents the speed control input of the th unmanned system individual, i.e., ; represents the constraint matrix corresponding to the th unmanned system individual; represents the Lagrange multiplier corresponding to the th unmanned system individual; represents the error term of the projection plane corresponding to the th unmanned system individual, i.e., ; represents the estimated value of the speed control input of the th unmanned system individual, i.e., ; represents the partial derivative of the constraint matrix corresponding to the th unmanned system individual with respect to , i.e., ; represents the partial derivative of the constraint matrix corresponding to the th unmanned system individual with respect to , i.e., ; , , , .

[0046] A system for an evenly loaded coverage method of an unmanned system cluster on a restricted surface, comprising:

[0047] A coverage area determination module, which is used to determine a target coverage area and construct a communication network for the unmanned system cluster based on multiple unmanned system individuals;

[0048] An initialization module, which is used to discretize the split axis interval to obtain a set of initial split axis values and assign an initial split axis value to the split axis of each unmanned system individual;

[0049] A local optimization module, which is used to perform balanced load splitting on the determined target coverage area to obtain multiple sub-areas and find local optimal sub-area deployment points for each unmanned system individual within its corresponding sub-area;

[0050] A deployment design module, which is used to calculate the loss of each unmanned system individual at each initial split axis value and design an optimal deployment control law based on the split axis with the minimum loss and its corresponding local optimal sub-area deployment point, so that each unmanned system individual is deployed to the selected sub-area deployment point.

[0051] The beneficial effects of the present invention are:

[0052] The present invention effectively divides a limited curved surface area by performing balanced load segmentation on a target coverage area, and ensures load balance of the sub-areas after segmentation, thereby ensuring that the task amounts of each individual unmanned system are consistent; designs an optimal deployment control law based on the optimal sub-area deployment points, and uses this control law to enable the unmanned system cluster to reach the deployment points completely and quickly for deployment under the curved surface constraint, so as to achieve the coverage and deployment of a uniform task amount in the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flowchart of the present invention;

[0054] Figure 2 is a schematic structural diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0056] It should be noted that the following description relates to various aspects of embodiments within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on this disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of the aspects described herein can be used to implement an apparatus and / or practice a method. In addition, this apparatus can be implemented and this method can be practiced using other structures and / or functionality in addition to one or more of the aspects described herein.

[0057] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] Embodiment 1

[0059] Figure 1Shown is a method for uniform load coverage of an unmanned system cluster on a restricted surface. By evenly dividing the target coverage area, the restricted surface area is effectively segmented, and the load balance of the segmented sub-areas is ensured, thereby ensuring that the task volume of each individual unmanned system is the same. Based on the optimal sub-area deployment points, an optimal deployment control law is designed, and this control law enables the unmanned system cluster to reach the deployment points completely and quickly for deployment under the surface constraint, realizing the coverage and deployment of a uniform task volume in the area. Specifically, it includes:

[0060] S1: Determine the target coverage area and construct a communication network for the unmanned system cluster based on multiple individual unmanned systems.

[0061] Among them, the expression of the target coverage area is:

[0062] ;

[0063] In the formula, represents the target coverage area; represents the surface enclosed by the outer boundary line; represents the surface enclosed by the inner boundary line; represents a point in the XYZ coordinate system, , , respectively represent the coordinates in this three-dimensional coordinate system; represents the function of the projection area of the surface on the XOY plane; represents the surface enclosed by the outer boundary line on the projection area on the XOY plane, that is , represents the outer boundary of the restricted area; represents the surface enclosed by the inner boundary line on the projection area on the XOY plane, that is , represents the inner boundary of the restricted area; represents the polar angle of the segmentation axis of the restricted area; represents the polar radius of the restricted area; represents the real number space.

[0064] Among them, the communication network of the unmanned system cluster is defined as an undirected graph, and its expression is:

[0065] ;

[0066] In the formula, represents the undirected graph in which the communication network of the unmanned system cluster is defined; represents the set of N individual unmanned systems existing in the undirected graph, that is ; Indicates the situation where every two unmanned system individuals are interconnected, that is, , 、 Indicates two different unmanned system individuals, that is, ; Indicates the adjacency matrix of an undirected graph, which is used to store the weights of the connection edges between each unmanned system individual and other unmanned system individuals.

[0067] In this embodiment, by constructing the communication network of the unmanned system cluster, the communication of each unmanned system individual within the communication network is ensured to be smooth.

[0068] S2: Discretize the segmentation axis interval to obtain the initial set of segmentation axis values, and assign the initial segmentation axis values to the segmentation axes of each unmanned system individual;

[0069] S21: Discretize the segmentation axis interval to obtain multiple intervals, and construct a set of initial segmentation axis values based on the discretized intervals;

[0070] Among them, the expression of the initial set of segmentation axis values is:

[0071] ;

[0072] In the formula, Represents the initial value of the segmentation axis polar angle of the th unmanned system individual; Represents the ordinal number of the interval; Represents the discretization fineness, that is, the total number of intervals, is an integer, and when is larger, it means that each interval is divided finer, and when is smaller, it means that each interval is divided coarser;

[0073] In this embodiment, by increasing the subsequent process can be made more accurate.

[0074] S22: Randomly select the th unmanned system individual, initialize its segmentation axis according to each element in the initial set of segmentation axis values, and randomly initialize the initial segmentation axis values of the remaining unmanned system individuals ;

[0075] Among them, the range of the segmentation axis is .

[0076] S3: Perform balanced load segmentation on the determined target coverage area to obtain multiple sub-regions, and find the local optimal sub-region deployment points for each unmanned system individual within its corresponding sub-region;

[0077] S31: Based on the communication networking of the unmanned system cluster, each unmanned system individual obtains the sub-region load of the remaining unmanned system individuals;

[0078] Among them, the expression of the sub-region load of the unmanned system individual is:

[0079] ;

[0080] In the formula, represents the sub-region load of the th unmanned system individual; represents the sub-region of the th unmanned system individual; represents the density function of the total region , and is bounded, ; ; represents the surface integral;

[0081] S32: Based on the obtained sub-region loads, perform balanced load splitting on the determined target coverage area to obtain multiple sub-regions;

[0082] Among them, the expression of the balanced load splitting is:

[0083] ;

[0084] ;

[0085] In the formula, represents the splitting axis polar angle of the th unmanned system individual area; represents the derivative; represents the control gain constant of the splitting axis; represents the estimated value of the sub-region load of the th unmanned system individual; represents the control gain constant of the estimator; represents the th unmanned system individual and the th unmanned system individual communication connection edge weight; represents the estimated value of the sub-region load of the th unmanned system individual;

[0086] In this embodiment, ; ; takes the value of 0 or 1.

[0087] S33: Each unmanned system individual randomly initializes within its corresponding sub-region to generate a set of initial points;

[0088] S34: Construct an objective optimization function based on the loss functions of each unmanned system individual at the initial points, and use the gradient descent method for iterative solution to obtain a set of locally optimal deployment point sets;

[0089] Among them, the expression of the objective optimization function is:

[0090] ;

[0091] ;

[0092] In the formula, represents the loss function value of the th unmanned system individual at the generated initial point, represents the estimated values of the polar radius and polar angle of the initial point of the th unmanned system individual; represents the straight-line distance function between two points on the surface, that is, ; represents the distance range between two points; represents the function with respect to partial derivative, that is, ; represents the function with respect to partial derivative, that is, ; represents the optimal splitting axis of the th unmanned system individual generated by balanced load splitting; represents the optimal splitting axis of the th unmanned system individual generated by balanced load splitting; represents the lower limit of the estimated polar angle of the initial point of the th unmanned system individual; represents the upper limit of the estimated polar angle of the initial point of the th unmanned system individual;

[0093] Among them, the expression for iterative solution using the gradient descent method is:

[0094] ;

[0095] In the formula, represents the augmented Lagrangian variable of the th unmanned system individual; represents the augmented Lagrangian variable control gain constant; represents the augmented Lagrangian function of the th unmanned system individual; represents the slack variable, that is, ; represents the Lagrange multiplier, that is ; represents the Lagrange parameter, and ; represents the constraint condition of the objective function of the -th individual of the unmanned system, that is , where ; ; ; ; represents the transpose;

[0096] In this embodiment, the Lagrange parameter .

[0097] S35: Select the optimal solution from the set of locally optimal deployment points to obtain the locally optimal sub-region deployment point;

[0098] S4: Calculate the loss of each unmanned system individual at each initial segmentation axis value, and design the optimal deployment control law based on the segmentation axis with the minimum loss and its corresponding locally optimal sub-region deployment point, so that each unmanned system individual is deployed to the selected sub-region deployment point.

[0099] S41: Calculate the loss of each unmanned system individual at each initial segmentation axis value, and design the optimal deployment control law based on the segmentation axis with the minimum loss and its corresponding locally optimal sub-region deployment point;

[0100] Among them, the expression of the locally optimal sub-region deployment point corresponding to the segmentation axis with the minimum loss is:

[0101] ;

[0102] In the formula, represents the deployment point of the sub-region of the loss function of the -th individual of the unmanned system;

[0103] Among them, the expression of the optimal deployment control law is:

[0104] ;

[0105] ;

[0106] In the formula, represents the position of the -th individual of the unmanned system, that is ; represents the speed control input of the -th individual of the unmanned system, that is ; represents the The constraint matrix corresponding to an individual unmanned system Indicating the Lagrange multiplier corresponding to an individual unmanned system Indicating the Error term of the projection plane corresponding to an individual unmanned system, i.e., ; Indicating the Estimated value of the velocity control input of an individual unmanned system, i.e., ; Indicating the partial derivative of the constraint matrix corresponding to an individual unmanned system with respect to , i.e., ; Indicating the partial derivative of the constraint matrix corresponding to an individual unmanned system with respect to , i.e., ; , , , ;

[0107] S42: Based on the optimal deployment control law, each individual unmanned system is controlled to the selected sub-region deployment point for deployment.

[0108] Embodiment 2

[0109] Based on the same design concept, as shown in Figure 2 , this embodiment provides a system for the uniform load coverage method of an unmanned system cluster on a restricted surface, including a coverage area determination module, an initialization module, a local optimization module, and a deployment design module.

[0110] Specifically, the coverage area determination module is used to determine the target coverage area and construct a communication network for the unmanned system cluster based on multiple individual unmanned systems.

[0111] Specifically, the initialization module is used to discretize the split axis interval to obtain a set of initial split axis values and assign an initial split axis value to the split axis of each individual unmanned system.

[0112] Specifically, the local optimization module is used to perform balanced load splitting on the determined target coverage area to obtain multiple sub-regions and find local optimal sub-region deployment points for each individual unmanned system within its corresponding sub-region.

[0113] ​​Specifically, a deployment design module is configured to calculate the loss of each individual unmanned system at each initial segmentation axis value, and design an optimal deployment control law based on the segmentation axis with the minimum loss and its corresponding local optimal sub-region deployment point, so that each individual unmanned system is deployed to the selected sub-region deployment point.

[0114] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0115] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. An unmanned system cluster uniform load coverage method for a restricted surface, characterized in that Including: Determine the target coverage area and construct a communication network for the unmanned system cluster based on multiple individual unmanned systems; Discretize the split axis interval to obtain a set of initial split axis values, and assign an initial split axis value to the split axis of each individual unmanned system; Perform balanced load splitting on the determined target coverage area to obtain multiple sub-areas, and find local optimal sub-area deployment points for each individual unmanned system within its corresponding sub-area; Calculate the loss of each individual unmanned system at each initial split axis value, and design an optimal deployment control law based on the split axis with the minimum loss and its corresponding local optimal sub-area deployment point, so that each individual unmanned system is deployed to the selected sub-area deployment point; The expression of the target coverage area is: ； In the formula, represents the target coverage area; represents the surface enclosed by the outer boundary line; represents the surface enclosed by the inner boundary line; represents a point in the XYZ coordinate system, , , respectively represent the coordinates in the XYZ coordinate system; represents the function of the surface with respect to the projection area on the XOY plane; represents the surface enclosed by the outer boundary line in the projection area on the XOY plane, that is , represents the outer boundary of the restricted area; represents the surface enclosed by the inner boundary line in the projection area on the XOY plane, that is , represents the inner boundary of the restricted area; represents the polar angle of the division axis of the restricted area; represents the polar radius of the restricted area; represents the real number space; The performing balanced load splitting on the determined target coverage area to obtain multiple sub-areas, and finding local optimal sub-area deployment points for each individual unmanned system in each sub-area includes: Based on the communication network of the unmanned system cluster, each individual unmanned system obtains the sub-area load of the remaining individual unmanned systems; Based on the obtained sub-area load, perform balanced load splitting on the determined target coverage area to obtain multiple sub-areas; Each individual unmanned system randomly initializes within its corresponding sub-area to generate a set of initial points; Construct a target optimization function based on the loss function of each individual unmanned system at the initial points, and use the gradient descent method to iteratively solve to obtain a set of local optimal deployment point sets; Select the optimal solution from the set of local optimal deployment points to obtain the local optimal sub-area deployment point; The expression of the optimal deployment control law is: ； ； In the formula, represents the position of the th individual of the unmanned system, that is ; represents the speed control input of the th individual of the unmanned system, that is ; represents the constraint matrix corresponding to the th individual of the unmanned system; represents the Lagrange multiplier corresponding to the th individual of the unmanned system; represents the error term of the projection plane corresponding to the th individual of the unmanned system, that is ; represents the estimated value of the speed control input of the individual of the unmanned system, that is ; represents the partial derivative of the constraint matrix corresponding to the th individual of the unmanned system with respect to , that is ; represents the partial derivative of the constraint matrix corresponding to the th individual of the unmanned system with respect to , that is ; , , , .

2. The method for uniform load coverage of an unmanned system cluster with a restricted surface according to claim 1, characterized in that The communication network of the unmanned system cluster is defined as an undirected graph, and its expression is: ； Wherein, represents an undirected graph defined for the communication networking of the unmanned system cluster; represents the set of N unmanned system individuals existing in the undirected graph, that is, ; represents the connection situation between every two unmanned system individuals, that is, , , represent two different unmanned system individuals, that is, ; represents the adjacency matrix of the undirected graph, which is used to store the weights of the connection edges between each unmanned system individual and other unmanned system individuals.

3. The method for uniform load coverage of an unmanned system cluster with a restricted surface according to claim 1, characterized in that, The discretizing the split axis interval to obtain a set of initial split axis values, and assigning an initial split axis value to the split axis of each individual unmanned system includes: Discretize the split axis interval to obtain multiple intervals, and construct a set of initial split axis values based on the discretized intervals; Randomly select an individual unmanned system, initialize its split axis according to each element in the set of initial split axis values, and randomly initialize the initial split axis values of the remaining individual unmanned systems.

4. The method for uniform load coverage of an unmanned system cluster with a restricted surface according to claim 3, wherein The expression of the set of initial split axis values is: ； In the formula, represents the initial value of the polar angle of the splitting axis of the th individual of the unmanned system; represents the ordinal number of the interval; represents the discretization fineness, that is, the total number of intervals.

5. A method for uniform load coverage of an unmanned system cluster with a restricted surface, characterized in that, The expression of the sub-area load of the individual unmanned system is: ； In the formula, represents the sub-region load of the th individual of the unmanned system; represents the sub-region of the th individual of the unmanned system; represents the density function of the total region , and is bounded, ; ; represents the surface integral; The expression of the balanced load splitting is: ； ； In the formula, represents the polar angle of the segmentation axis of the th individual area of the unmanned system; represents the derivative; represents the control gain constant of the segmentation axis; represents the th estimated value of the sub - area load of the th individual of the unmanned system; represents the control gain constant of the estimator; represents the weight of the communication connection edge between the th individual of the unmanned system and the th individual of the unmanned system; represents the th estimated value of the sub - area load of the th individual of the unmanned system.

6. The method for uniform load coverage of an unmanned system cluster with a restricted surface according to claim 1, wherein, The expression of the target optimization function is: ； ； Wherein, represents the loss function value of the th unmanned system individual at the generated initial point, represents the estimated values of the polar radius and polar angle of the initial point of the th unmanned system individual; represents the straight-line distance function between two points on the surface, that is, ; represents the partial derivative of the function with respect to , that is, ; represents the partial derivative of the function with respect to , that is, ; represents the optimal division axis of the th unmanned system individual generated by balanced load division; represents the optimal division axis of the th unmanned system individual generated by balanced load division; represents the lower limit of the estimated polar angle value of the initial point of the th unmanned system individual; represents the upper limit of the estimated polar angle value of the initial point of the th unmanned system individual; The expression of using the gradient descent method for iterative solution is: ； In the formula, represents the augmented Lagrangian variable of the th individual of the unmanned system; represents the control gain constant of the augmented Lagrangian variable; represents the th augmented Lagrangian function of the unmanned system individual; represents the slack variable, that is, ; represents the Lagrange multiplier, that is, ; represents the transpose; represents the Lagrange parameter, and ; represents the constraint condition of the objective function of the th individual of the unmanned system, that is, , where ; ; ; .

7. A system for an unmanned system cluster uniform load coverage method for the restricted surface described in claim 1, characterized in that, Including: A coverage area determination module, which is used to determine the target coverage area and construct a communication network for the unmanned system cluster based on multiple individual unmanned systems; An initialization module, which is used to discretize the split axis interval to obtain a set of initial split axis values, and assign an initial split axis value to the split axis of each individual unmanned system; A local optimization module, which is used to perform balanced load splitting on the determined target coverage area to obtain multiple sub-areas, and find local optimal sub-area deployment points for each individual unmanned system within its corresponding sub-area; A deployment design module is used to calculate the loss of each individual unmanned system at each initial segmentation axis value, and based on the segmentation axis with the minimum loss and its corresponding local optimal sub-region deployment point, design an optimal deployment control law to enable each individual unmanned system to be deployed to the selected sub-region deployment point.

Images