Unmanned ship group self-organizing optimal task subgroup generation method suitable for approaching electromagnetic spectrum reconnaissance scene

Abstract

The invention discloses an unmanned ship group self-organizing optimal task subgroup generation method suitable for approaching an electromagnetic spectrum reconnaissance scene, and the method comprises the steps: a ground station randomly selects a node from an unmanned ship group as an initial candidate cluster head, transmits a tactical task and related parameters, calculates a weighting measurement function value through a heuristic algorithm, and carries out the self-organizing optimal task subgroup generation. If not, a result is sent back to the initial candidate cluster head node, the node with the maximum weighted metric function value is selected as a candidate cluster head node of a second round, iteration of the second round is carried out until the candidate cluster head node is stable and unchanged, and iteration is ended; and the cluster head node decomposes the tactical task into individual tasks executable by each node according to a task decomposition algorithm module. According to the method, the calculation burden of a central control system is greatly reduced, the problem of dimension disasters caused by nonlinear growth of the cluster scale is effectively solved, grouping of unmanned ship nodes can be more targeted and effective, and the success rate and efficiency of task completion can also be improved.

Description

Technical Field

[0001] The present invention relates to the field of cluster collaborative electromagnetic spectrum confrontation, and in particular to a method for generating optimal task subgroups of unmanned boat swarms for self-organization in close-range electromagnetic spectrum reconnaissance scenarios. Background Art

[0002] In the field of electromagnetic spectrum reconnaissance technology of unmanned clusters, the formation of corresponding task subgroups by unmanned clusters according to the specific electromagnetic spectrum reconnaissance tactical tasks issued by combat command is an extremely important link in cluster coordination. Most of the existing subgroup generation mechanisms use traditional precise programming to search for the best subgroup under a centralized or distributed topology structure. The generation mechanism under the centralized topology structure has poor robustness and cannot cope with emergencies, such as task replanning, node failure, and node being tracked by firepower; the distributed topology causes redundancy to the resources of the cluster network to a certain extent; traditional precise programming will inevitably encounter the "dimensional disaster" problem as the cluster scale is upgraded. At the same time, the optimization parameters of the current optimization algorithm do not take into account the specific scenarios of electromagnetic spectrum reconnaissance, so the generalization ability is poor. Therefore, according to the specific tactical scenarios of electromagnetic spectrum reconnaissance, under a specific system topology architecture, it is of great research value to design a generation mechanism for task subgroups. Summary of the invention

[0003] Purpose of the invention: The purpose of the present invention is to provide a method for generating optimal task subgroups of self-organized unmanned boat groups suitable for close-in electromagnetic spectrum reconnaissance scenarios.

[0004] Technical solution: The present invention comprises the following steps:

[0005] (1) The ground station randomly selects a node from the unmanned boat group as the initial candidate cluster head. The ground station sends tactical tasks and related parameters to the selected node. If the randomly selected node receives these instructions, it will send its own coordinates and task parameters to other nodes.

[0006] (2) Other nodes will use heuristic algorithms to calculate their own weighted metric function values ​​based on task parameters and their own information, and send the results back to the initial candidate cluster head node. The initial candidate cluster head node will sort the weighted metric function values ​​of each node and select the node with the largest weighted metric function value as the candidate cluster head node for the second round, and then perform the second round of iteration. This process continues until the candidate cluster head node is stable and unchanged, and the iteration ends.

[0007] (3) The cluster head node will decompose the tactical task into individual tasks that can be executed by each node according to the task decomposition algorithm module.

[0008] Furthermore, the cluster head election process and task instruction transmission process in the unmanned boat group in step (1) include: the ground station randomly selects a node as the initial candidate cluster head to initiate the task instruction. If the node receives the task instruction, it will send its own coordinates and task parameters to other nodes to form a cluster head. This cluster head is responsible for coordinating the actions of other nodes to complete the task.

[0009] Furthermore, the calculation process of step (2) is:

[0010] Assuming there are N nodes in total, the base station randomly selects a node as the candidate cluster head in the first round, and broadcasts the information that it becomes the cluster head and the numbers of other cluster head nodes to the cluster head node. Then the cluster head node announces itself as the cluster head of this round to the other N-1 nodes. The communication content is the information of "becoming the cluster head" and its own ID number.

[0011] Calculate the clustering metric weight between itself and the cluster head, add the node with the largest clustering metric weight on the edge connected to itself, and send a response message and coordinate message to the corresponding cluster head. After the cluster head receives the clustering metric weight of the member, it selects the member with the highest clustering metric weight as the next round of candidate cluster head, and iterates in this cycle;

[0012] According to the clustering loss function, the iteration ends when the sum of squared errors of each sample from the center point of the cluster to which it belongs no longer decreases.

[0013] Furthermore, it is characterized in that the nodes are based on the clustering metric weight formula:

[0014] R=Q 1 d mi +Q 2 I+Q 3 S+Q 4 T+Q 5 E m

[0015] Where Q * is the weight coefficient, d mi is the distance between the node and the center of the mission area, I is the node direction finding accuracy, S is the sensitivity, T is the health index, E m is the current oil level of the cluster head.

[0016] Furthermore, the step (3) includes the cluster head node decomposing the tactical-level tasks into atomic tasks executable by individual nodes according to a preset strategy, decomposing the task instructions based on timing, using a timing diagram to characterize the tactics, outputting an atomic task sequence file, and initiating a tender within the cluster.

[0017] Furthermore, the calculation process of step (3) is:

[0018] (3.1) According to the mission content, imagine the actual mission scenario, formulate the corresponding mission implementation rules and planning scope, set the mission purpose and environmental planning route of the entire cluster according to the mission requirements, establish the mission trajectory route and working mode mathematical model of all unmanned nodes in the whole mission process, and find the optimal mission model through theoretical deduction;

[0019] (3.2) Based on the theoretical mathematical model and the preset parameters of the task, calculate the actual trajectory route and corresponding working mode of each unmanned node required during the actual task execution;

[0020] (3.3) Decompose the actual flight path and corresponding working mode of each unmanned node into a corresponding cluster task sequence, and initiate bidding for each atomic task in the sequence within the cluster.

[0021] Furthermore, the step (3.1) uses the diagonal coordinates of the area to determine the search area, and adopts a regional search method, that is, according to the number of unmanned boats, the larger target area is divided into a corresponding number of small areas, and then each unmanned boat is responsible for searching and path planning the corresponding small area.

[0022] Furthermore, the calculation process of the regional search method includes:

[0023] The diagonal coordinates of the rectangular search area are known, the rectangular search range is determined, the number of search sub-areas is determined when the number of unmanned boats and unmanned boat formations is known, and the unmanned boats and unmanned boats are assigned to each sub-area for regional search;

[0024] The search radius is determined based on the sensitivity of the unmanned boat and the unmanned boat, and then the scope of the area that can be searched is determined.

[0025] Furthermore, the method for calculating the searchable area range is:

[0026] The detection area of ​​the unmanned boat search radar is circular. If the change of the unmanned boat attitude angle is not considered, the detection range of the unmanned boat is a circle with a radius of r.

[0027] The coordinates of the upper left corner of the rectangular search area (x L ,y L ) and the lower right corner coordinate (x R ,y R ), determine the rectangular search range, set the number of unmanned boat formations to be M and N respectively, determine the number of search sub-areas, and use a specific algorithm to assign the unmanned boats to each sub-area to perform the regional search task, and set the length and width of the unmanned boat sub-area to be L and W respectively;

[0028] like The unmanned boat does not need to move, and can search the entire area by fixing the center of the sub-area; if The unmanned boat needs to plan its path according to the following rules so that the entire area is covered.

[0029] Furthermore, the minimum turning radius constraint of the unmanned boat is:

[0030] The minimum turning radius R is equal to the detection range radius r;

[0031] The minimum number of turns for an unmanned boat is The unmanned boat formation conducts a straight line-right turn-straight line area search, and repeats this process until the reconnaissance or monitoring mission of the target area is completed;

[0032] When W = 2nr, the unmanned boat can just scan the area, and no extra area is scanned;

[0033] When 2nr<W<2(n+1)r, considering the turning process without gap, an area S=[2(n+1)rW]·L is scanned redundantly.

[0034] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages:

[0035] The present invention is based on a decentralized wireless network architecture and is driven by collaborative electromagnetic spectrum confrontation tactical tasks. Task subgroups of the unmanned boat group are generated through self-organization and negotiation by a distributedly deployed intelligent decision-making software system. Distributed optimization strategies are used in the process of realizing cluster self-organization actions, which greatly reduces the computational burden of the central control system and effectively solves the "dimensionality disaster" caused by the nonlinear growth of the cluster scale, so that this mechanism can play a good control effect in large-scale unmanned node cluster tasks. In the process of realizing the cluster heuristic algorithm, a multi-level judgment program is used to ensure that the grouping of unmanned boat nodes is more targeted and effective, and the success rate and efficiency of task completion can also be improved. In the self-organization process, five factors are considered, including the distance from the center of the mission area, sensitivity, direction finding accuracy, remaining fuel, and health index, and they are combined and assigned different weights respectively, so that the optimization result achieves the best effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of an unmanned swarm system;

[0037] Figure 2 Schematic diagram of the information flow generated for the unmanned vehicle swarm mission subgroup. DETAILED DESCRIPTION

[0038] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0039] The present invention comprises the following steps:

[0040] Step 1: The ground station first randomly selects a node from the unmanned boat group as the initial candidate cluster head. The ground station sends a tactical task (such as area search) and related parameters (such as mission area and mission start time) to the node. If the randomly selected node receives these instructions, it will send its coordinates and mission parameters to other nodes.

[0041] The cluster head election process and task instruction transmission process in the unmanned boat group are as follows: the ground station in the unmanned boat group randomly selects a node as the initial candidate cluster head to initiate the task instruction. If the node receives the task instruction, it will send its coordinates and task parameters to other nodes to form a cluster head. This cluster head will be responsible for coordinating the actions of other nodes to complete the task. The random selection method of nodes is an effective and fair random selection method within the group to ensure the equality of each individual in the distributed structure.

[0042] Step 2: Other nodes will use the heuristic algorithm to calculate their own weighted metric function values ​​according to the task parameters and their own information, and send the results back to the initial candidate cluster head node. The initial candidate cluster head node will sort the weighted metric function values ​​of each node, and select the node with the largest weighted metric function value as the candidate cluster head node for the second round, and then perform the second round of iterations. This process will continue until the candidate cluster head node is stable and unchanged, and the iteration ends. Among them, each node calculates its own weighted metric function value according to the task parameters and its own information, and sends the results back to the initial candidate cluster head node. Then, the initial candidate cluster head node will sort the weighted metric function values ​​of each node, and select the node with the largest weighted metric function value as the candidate cluster head node for the second round, and then perform the second round of iterations. This process will continue until the candidate cluster head node is stable and unchanged, and the iteration ends. The algorithm requires some prior parameters and information, such as task parameters and node information, which are contained in the task instructions. The convergence speed of the algorithm may be affected by factors such as the number of nodes, initial values, and the selection of weighted metric functions, so these factors must be reasonably set and adjusted.

[0043] Step 3: The final cluster head node will decompose the tactical task into individual tasks that can be executed by each node according to the task decomposition algorithm module. It is a task decomposition algorithm rule, and its rules vary according to the tactical tasks of electromagnetic spectrum reconnaissance. Taking the regional search task as an example, the specific steps are as follows: First, the algorithm uses the diagonal coordinates of the region to determine the search area, and uses the total number of unmanned boats to divide the number of sub-areas, so as to achieve coverage search of the entire area. Taking the rectangular search area as an example, the algorithm adopts a regional search method. Specifically, according to the number of unmanned boats, the larger target area is divided into a corresponding number of small areas, and then each unmanned boat is responsible for searching and path planning the corresponding small area. Therefore, this algorithm is a distributed collaborative decision-making algorithm, which can help multiple unmanned boats to collaboratively complete the search task and improve the search efficiency and accuracy.

[0044] like Figure 2 As shown, in order to realize the above design, the technical solution provided by the present invention is as follows:

[0045] (1) Figure 1 Each node of the 002 unmanned cluster shown is based on a decentralized wireless communication network architecture, and a distributed auxiliary decision-making system is deployed inside the unmanned boat node.

[0046] (2) Figure 1 As shown, the combat commander 001 issues a regional search task to randomly select 002. The command triggers the dynamic cluster head formation algorithm, and 002 generates a cluster head node through dynamic negotiation within the cluster. The negotiation mechanism takes the clustering algorithm as an example, and the specific implementation method is as follows: Assuming that there are N nodes in total, the base station first randomly selects a node as the first round of candidate cluster heads, and broadcasts the information that it becomes the cluster head and the numbers of other cluster head nodes to the cluster head node. Then the cluster head node announces itself as the cluster head of this round to the other N-1 nodes, and the communication content is the information of "becoming the cluster head" and the number of its own ID. Other nodes are based on the clustering metric weight formula:

[0047] R=Q 1 d mi +Q 2 I+Q 3 S+Q 4 T+Q 5 E m

[0048] Calculate the clustering metric weight between itself and the cluster head, add the node with the largest clustering metric weight on the edge connected to itself, and send a response message and coordinate message to the corresponding cluster head, where Q * is the weight coefficient, d mi is the distance between the node and the center of the mission area, I is the node direction finding accuracy, S is the sensitivity, T is the health index, E m is the current oil level of the cluster head.

[0049] After the cluster head receives the clustering metric weight of the member, it selects the member with the highest clustering metric weight as the candidate cluster head for the next round, and repeats the process in this way. Finally, the iteration ends when the sum of square errors of each sample from the center point of the cluster to which it belongs no longer decreases according to the clustering loss function.

[0050] (3) The cluster head node decomposes the tactical-level task into atomic tasks executable by individual nodes according to the preset strategy. By decomposing the task instructions based on the timing, the timing diagram is used to characterize the tactics, and the atomic task sequence file is output, and a bidding is initiated within the cluster. The specific implementation method is as follows: First, according to the task content, the actual task scenario is envisioned, the corresponding task implementation rules and planning scope are formulated, the task purpose and environmental planning route of the entire cluster are set according to the task requirements, and the mathematical model of the task trajectory route and working mode that all unmanned nodes should have during the entire task process is established. The optimal task model is found through theoretical derivation. According to the theoretical mathematical model and the preset parameters of the task, the actual trajectory route and corresponding working mode of each unmanned node required during the actual task execution are calculated. Finally, as shown in Table 1, it is decomposed into the corresponding cluster task sequence, and each atomic task in the sequence is bid within the cluster.

[0051] Table 1: Schematic diagram of atomic task sequence file format

[0052]

[0053] Taking regional search as an example, first, the algorithm uses the diagonal coordinates of the region to determine the search area, and uses the total number of unmanned boats to divide the number of sub-areas, thereby achieving a coverage search of the entire area.

[0054] The algorithm uses a regional search method. Specifically, according to the number of unmanned boats, the larger target area is divided into a corresponding number of small areas, and then each unmanned boat is responsible for searching and planning the path of the corresponding small area. Therefore, the algorithm is a distributed collaborative decision-making algorithm, which can help multiple unmanned boats to collaboratively complete the search task and improve the search efficiency and accuracy.

[0055] The actual method is as follows:

[0056] (3.1) Now that the diagonal coordinates of the rectangular search area are known, the rectangular search range is determined. The number of unmanned boats and unmanned boat formations is known to determine the number of search sub-areas, and the unmanned boats and unmanned boats are assigned to each sub-area for regional search.

[0057] (3.2) According to step (3.1), the search radius is determined based on the sensitivity of the unmanned boat and the unmanned boat, and then the scope of the area that can be searched is determined.

[0058] The detection area of ​​the unmanned boat search radar is circular. If the change of the unmanned boat's attitude angle is not considered, the detection range of the unmanned boat is a circle with a radius of r.

[0059] Now we know the coordinates of the upper left corner of the rectangular search area (x L ,y L ) and the lower right corner coordinate (x R ,y R ), determine the rectangular search range. Assume that the number of unmanned boat formations is M, N respectively, determine the number of search sub-areas (MN search sub-areas in total), and use a specific algorithm to assign the unmanned boats to each sub-area to perform the regional search task. Assume that the length and width of the unmanned boat sub-area are L and W respectively.

[0060] like The unmanned boat does not need to move, and can search the entire area by fixing the center of the sub-area; if The unmanned boat needs to plan its path according to the following rules so that the entire area is covered.

[0061] In order to solve the problem of the minimum turning radius constraint of the unmanned boat, researchers have proposed many different algorithms, such as serial method and fusion method. In the serial method, the unmanned boat will move along the arc path at the turning point until it reaches the next parallel line. In the fusion method, the search paths on multiple parallel lines are fused together to form a continuous search path.

[0062] Therefore, the minimum turning radius R is equal to the detection range radius r. As shown in the figure, the left side of the search boundary is inside the search area. Therefore, the minimum number of turns of the unmanned boat is

[0063] The unmanned boat formation conducts a straight line-right turn-straight line area search, and repeats this process until the reconnaissance or monitoring mission of the target area is completed. When W = 2nr, the unmanned boat can just scan the area, and no redundant area is scanned; when 2nr < W < 2(n+1)r, considering the turning process without gaps, an area of ​​S = [2(n+1)rW]·L is scanned redundantly.

[0064] The regional search algorithm can realize regional scanning of unmanned boat groups in different areas by changing the regional search range and the radius of the unmanned boat search.

Claims

1. A method for generating optimal task subgroups of unmanned boat swarms for self-organization in close electromagnetic spectrum reconnaissance scenarios, characterized in that: The method comprises the following steps: (1) The ground station randomly selects a node from the unmanned boat group as the initial candidate cluster head. The ground station sends tactical tasks and related parameters to the selected node. If the randomly selected node receives these instructions, it sends its own coordinates and task parameters to other nodes. (2) Other nodes will use heuristic algorithms to calculate their own weighted metric function values ​​based on task parameters and their own information, and send the results back to the initial candidate cluster head node. The initial candidate cluster head node will sort the weighted metric function values ​​of each node and select the node with the largest weighted metric function value as the candidate cluster head node for the second round, and then perform the second round of iteration. This process continues until the candidate cluster head node is stable and unchanged, and the iteration ends. (3) The cluster head node will decompose the tactical task into individual tasks that can be executed by each node according to the task decomposition algorithm module.

2. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 1 is characterized in that: The cluster head election process and task instruction transmission process in the unmanned boat group in step (1) include: the ground station randomly selects a node as the initial candidate cluster head to initiate the task instruction. If the node receives the task instruction, it will send its own coordinates and task parameters to other nodes to form a cluster head. This cluster head is responsible for coordinating the actions of other nodes to complete the task.

3. The method for generating the optimal task subgroup of the unmanned boat group self-organization in the close electromagnetic spectrum reconnaissance scenario according to claim 1 is characterized in that: The calculation process of step (2) is: Assuming there are N nodes in total, the base station randomly selects a node as the candidate cluster head in the first round, and broadcasts the information that it becomes the cluster head and the numbers of other cluster head nodes to the cluster head node. Then the cluster head node announces itself as the cluster head of this round to the other N-1 nodes. The communication content is the information of "becoming the cluster head" and its own ID number. Calculate the clustering metric weight between itself and the cluster head, add the node with the largest clustering metric weight on the edge connected to itself, and send a response message and coordinate message to the corresponding cluster head. After the cluster head receives the clustering metric weight of the member, it selects the member with the highest clustering metric weight as the next round of candidate cluster head, and iterates in this cycle; According to the clustering loss function, the iteration ends when the sum of squared errors of each sample from the center point of the cluster to which it belongs no longer decreases.

4. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 3 is characterized in that: The node clustering metric weight formula is expressed as: R=Q1d mi +Q2I+Q3S+Q4T+Q5E m Where Q * is the weight coefficient, d mi is the distance between the node and the center of the mission area, I is the node direction finding accuracy, S is the sensitivity, T is the health index, E m is the current fuel level of the cluster head.

5. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 1 is characterized in that: The step (3) includes the cluster head node decomposing the tactical-level task into atomic tasks executable by individual nodes according to a preset strategy, decomposing the task instructions based on timing, using a timing diagram to characterize the tactics, outputting an atomic task sequence file, and initiating a tender within the cluster.

6. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 1 is characterized in that: The calculation process of step (3) is: (3.1) According to the mission content, imagine the actual mission scenario, formulate the corresponding mission implementation rules and planning scope, set the mission purpose and environmental planning route of the entire cluster according to the mission requirements, establish the mission trajectory route and working mode mathematical model of all unmanned nodes in the whole mission process, and find the optimal mission model through theoretical deduction; (3.2) Based on the theoretical mathematical model and the preset parameters of the task, calculate the actual trajectory route and corresponding working mode of each unmanned node required during the actual task execution; (3.3) Decompose the actual flight path and corresponding working mode of each unmanned node into a corresponding cluster task sequence, and initiate bidding for each atomic task in the sequence within the cluster.

7. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 1 is characterized in that: The step (3.1) uses the diagonal coordinates of the area to determine the search area, and adopts a regional search method, that is, according to the number of unmanned boats, the larger target area is divided into a corresponding number of small areas, and then each unmanned boat is responsible for searching and path planning the corresponding small area.

8. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 7 is characterized in that: The calculation process of the regional search method includes: The diagonal coordinates of the rectangular search area are known, the rectangular search range is determined, the number of search sub-areas is determined when the number of unmanned boats and unmanned boat formations is known, and the unmanned boats and unmanned boats are assigned to each sub-area for regional search; The search radius is determined based on the sensitivity of the unmanned boat and the unmanned boat, and then the scope of the area that can be searched is determined.

9. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 8 is characterized in that: The method for calculating the searchable area range is: The detection area of ​​the unmanned boat search radar is circular. If the change of the unmanned boat attitude angle is not considered, the detection range of the unmanned boat is a circle with a radius of r. The coordinates of the upper left corner of the rectangular search area (x L ,y L ) and the lower right corner coordinate (x R ,y R ), determine the rectangular search range, set the number of unmanned boat formations to be M and N respectively, determine the number of search sub-areas, and use a specific algorithm to assign the unmanned boats to each sub-area to perform the regional search task, and set the length and width of the unmanned boat sub-area to be L and W respectively; like The unmanned boat does not need to move, and can search the entire area by fixing the center of the sub-area; if The unmanned boat needs to plan its path according to the following rules so that the entire area is covered.

10. The method for generating the optimal task subgroup of the self-organized unmanned boat group in the close electromagnetic spectrum reconnaissance scenario according to claim 9 is characterized in that: The minimum turning radius constraint of the unmanned boat is: The minimum turning radius R is equal to the detection range radius r; The minimum number of turns for an unmanned boat is The unmanned boat formation conducts an area search in a straight line-right turn-straight line, and repeats this process until the reconnaissance or monitoring mission of the target area is completed; When W = 2nr, the unmanned boat can just scan the area, and no extra area is scanned; When 2nr<W<2(n+1)r, considering the turning process without gap, an area S=[2(n+1)rW]·L is scanned redundantly.

Images