A cluster control method and system for underwater unmanned equipment

Abstract

The application relates to the technical field of underwater equipment control, in particular to a cluster control method and system for underwater unmanned equipment, which comprises the following steps: obtaining historical task data, a current task area and a current task type of the underwater unmanned equipment; determining the difficulty degree corresponding to the current task based on the historical task data, the current task area and the current task type; comparing the difficulty degree corresponding to the current task with a preset difficulty degree threshold value, and determining the cluster control mode of the underwater unmanned equipment according to the comparison result; and controlling the underwater unmanned equipment to execute the current task in the current task area according to the cluster control mode of the underwater unmanned equipment. In the application, the cluster control mode of the underwater unmanned equipment is determined by obtaining the difficulty degree corresponding to the current task, and the self-adaptive cluster control of the underwater unmanned equipment with non-electric variables is realized through the cluster control mode.

Description

Technical Field

[0001] This invention relates to the field of underwater equipment control technology, specifically to a cluster control method and system for unmanned underwater equipment. Background Technology

[0002] Underwater unmanned equipment (UAVs) refers to mechanical devices capable of autonomous or remotely controlled operation in underwater environments to perform various tasks. The swarm control technology for underwater UAVs is rapidly developing, with continuous advancements in areas such as autonomous navigation, mission planning, data fusion, and communication protocols. Underwater UAVs are widely used in marine scientific research, seabed resource exploration, environmental monitoring, search and rescue operations, and military reconnaissance. Through swarm control, underwater UAVs can collaboratively complete more complex and extensive tasks, improving operational efficiency and the accuracy of data collection.

[0003] In the swarm control of underwater unmanned equipment, a centralized control method is typically used, with a central control system directing all underwater unmanned equipment. While this method offers high control precision and good coordination, its drawback is its heavy reliance on communication; if communication is interrupted, swarm operations will be severely affected. Distributed control, on the other hand, can operate independently of a central control system (avoiding signal interruption issues) and is more adaptable to real-world environments, capable of handling local obstacles and task changes in complex environments. However, it also faces challenges related to system complexity, communication latency, and cost. Both centralized and distributed control methods have certain limitations for controlling underwater unmanned equipment.

[0004] Therefore, how to achieve adaptive swarm control of underwater unmanned equipment is a problem that urgently needs to be solved. Summary of the Invention

[0005] To address the technical problem of adaptive swarm control for underwater unmanned equipment, the present invention aims to provide a swarm control method and system for underwater unmanned equipment, the specific technical solution of which is as follows:

[0006] This application provides a cluster control method for underwater unmanned equipment, the method comprising:

[0007] Acquire historical mission data, current mission area, and current mission type of underwater unmanned equipment;

[0008] Based on the historical task data, the current task region, and the current task type, the difficulty level of the current task is determined;

[0009] The difficulty level of the current task is compared with a preset difficulty threshold, and the control mode of the underwater unmanned equipment cluster is determined based on the comparison result.

[0010] According to the underwater unmanned equipment cluster control method, the underwater unmanned equipment is controlled to perform the current task in the current task area.

[0011] In some embodiments, determining the underwater unmanned equipment cluster control method based on the comparison results includes:

[0012] When the comparison result indicates that the difficulty level of the current task is greater than or equal to the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be distributed control.

[0013] When the comparison result indicates that the difficulty level of the current task is less than the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be centralized control.

[0014] In some embodiments, the historical task data includes historical task regions and the number of times historical tasks were executed. Determining the difficulty level of the current task based on the historical task data, the current task region, and the current task type includes:

[0015] The scope of the historical task area is overlaid and analyzed to determine the familiarity level of the first task corresponding to each sub-region in the historical task area.

[0016] Based on the number of times the historical tasks were executed, the execution status of multiple historical task types was analyzed to determine the familiarity with the second task corresponding to each historical task type.

[0017] Obtain the region ratio of the sub-region in the current task region, and combine the region ratio with the second task familiarity level corresponding to the current task type and the first task familiarity level corresponding to the sub-region to determine the difficulty level of the current task.

[0018] In some embodiments, the historical task region includes multiple regions corresponding to historical tasks, and the step of performing overlay analysis on the range of the historical task region to determine the familiarity with the first task corresponding to each sub-region in the historical task region includes:

[0019] The ranges of the areas corresponding to the multiple historical tasks are marked;

[0020] Based on the range of the regions corresponding to the marked historical tasks, the overlapping ranges are superimposed to obtain multiple sub-regions;

[0021] The familiarity level of the first task corresponding to each sub-region is determined based on the total number of times the multiple sub-regions are superimposed and the number of times each sub-region is superimposed.

[0022] In some embodiments, the number of historical task executions includes the number of executions for multiple historical task types. The step of analyzing the execution status of the multiple historical task types based on the number of historical task executions to determine the familiarity level of the second task corresponding to each historical task type includes:

[0023] The total number of times the historical task was executed is determined based on the number of times each of the multiple historical task types was executed.

[0024] The execution count of each historical task type is compared with the total number of historical task executions to obtain the second task familiarity level corresponding to each historical task type.

[0025] In some embodiments, controlling the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control method includes:

[0026] When the underwater unmanned equipment cluster control mode is distributed control, the target number of underwater unmanned equipment is determined based on the historical task data and the current task type.

[0027] Acquire signal data and environmental water flow data corresponding to multiple candidate underwater unmanned devices, and determine the assignment priority corresponding to each candidate underwater unmanned device based on the signal data and environmental water flow data;

[0028] Based on the number of target underwater unmanned devices and the assignment priority of each candidate underwater unmanned device, a target underwater unmanned device is determined from the plurality of candidate underwater unmanned devices, so that the target underwater unmanned device performs the current task in the current task area.

[0029] In some embodiments, determining the number of target underwater unmanned devices based on the historical mission data and the current mission type includes:

[0030] Based on the historical mission data, determine the number of underwater unmanned devices corresponding to multiple historical mission types;

[0031] The current task type is matched with the multiple historical task types, and the number of underwater unmanned devices corresponding to the matched historical task types is used as the reference number of underwater unmanned devices for the current task type.

[0032] The average number of reference underwater unmanned devices is taken as the target number of underwater unmanned devices.

[0033] In some embodiments, determining the assignment priority of each candidate underwater unmanned device based on the signal data and environmental water flow data includes:

[0034] Based on the signal data, the communication signal strength of the candidate underwater unmanned equipment within the target time period is determined, and the fluctuation analysis of the communication signal strength is performed to obtain the signal stability degree corresponding to each candidate underwater unmanned equipment.

[0035] Based on the environmental water flow data, the water flow direction and velocity are determined, and the changes in the water flow direction and velocity are analyzed to obtain the environmental friendliness of each candidate underwater unmanned device.

[0036] By combining the signal stability and environmental friendliness, the assignment priority corresponding to each candidate underwater unmanned device is obtained.

[0037] In some embodiments, the step of analyzing the changes in the water flow direction and the water flow velocity to obtain the environmental friendliness level corresponding to each of the candidate underwater unmanned devices includes:

[0038] Based on the water flow velocity, construct a time-series-based curve of water flow velocity variation.

[0039] Based on the water flow velocity variation curve, multiple extreme points were determined;

[0040] Obtain the difference in water flow velocity and time between the extreme point and its adjacent extreme points, and determine the difference in water flow direction between the extreme point and its adjacent extreme points based on the water flow direction.

[0041] The degree of water flow velocity interference is determined based on the difference in water flow velocity and time difference between the extreme point and the adjacent extreme point.

[0042] The degree of interference in the direction of water flow is determined based on the difference in water flow velocity and the difference in water flow direction between the extreme point and the adjacent extreme points.

[0043] Based on the degree of interference from the water flow velocity and the degree of interference from the water flow direction, the environmental friendliness level corresponding to each candidate underwater unmanned device is obtained.

[0044] This application embodiment also provides a cluster control system for underwater unmanned equipment, the system comprising:

[0045] The data acquisition module is used to acquire historical mission data, current mission area, and current mission type of the underwater unmanned equipment.

[0046] The difficulty level determination module is used to determine the difficulty level of the current task based on the historical task data, the current task region, and the current task type.

[0047] The control mode determination module is used to compare the difficulty level of the current task with a preset difficulty level threshold, and determine the control mode of the underwater unmanned equipment cluster based on the comparison result.

[0048] The cluster control module is used to control the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control mode.

[0049] The present invention has the following beneficial effects:

[0050] First, historical mission data, current mission area, and current mission type of the underwater unmanned equipment (UAV) are acquired. Then, based on the historical mission data, the current mission area, and the current mission type, the difficulty level of the current mission is determined. Next, the difficulty level of the current mission is compared with a preset difficulty threshold, and the control method for the UAV swarm is determined based on the comparison result. Finally, according to the control method, the UAVs are controlled to execute the current mission in the current mission area. This application acquires multifaceted information related to the mission, providing a foundation for subsequent decision-making. Through historical mission data, the characteristics of different mission areas and mission types can be learned and understood, enabling more informed choices based on past experience when facing new missions. Based on the collected information, the difficulty level of the current mission is assessed. By quantifying the difficulty level, the complexity of the current mission can be dynamically perceived, and the control strategy adjusted accordingly. This means that the most suitable control method can be flexibly selected based on the actual needs of the mission, rather than relying solely on a fixed control mode. The assessed level of difficulty is compared with a preset threshold to determine whether centralized or distributed control should be used. Centralized control is suitable for relatively simple tasks, while distributed control is more suitable for complex or high-risk tasks. This step ensures that the most suitable control method is automatically selected based on the actual difficulty of the current task. When the task is relatively simple, centralized control can improve coordination and efficiency; while when the task is complex or there is a risk of communication interruption, distributed control can enhance the system's robustness and anti-interference ability. This dynamic selection mechanism allows the system to exhibit optimal performance in different task scenarios. Once the control method is determined, the underwater unmanned equipment can be directed to perform tasks within the current task area according to the selected control strategy, realizing adaptive swarm control of underwater unmanned equipment. Attached Figure Description

[0051] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1This is a schematic diagram illustrating the implementation environment of a cluster control method for underwater unmanned equipment provided in one embodiment of the present invention.

[0053] Figure 2 This is a flowchart illustrating a cluster control method for underwater unmanned equipment according to an embodiment of the present invention.

[0054] Figure 3 This is a schematic diagram of a cluster control system for underwater unmanned equipment provided in one embodiment of the present invention. Detailed Implementation

[0055] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a swarm control method and system for underwater unmanned equipment proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0056] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0058] The following description, in conjunction with the accompanying drawings, details a specific scheme for a cluster control method and system for underwater unmanned equipment provided by the present invention.

[0059] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating the implementation environment of a cluster control method for underwater unmanned equipment according to an embodiment of the present invention. Figure 1As shown, the implementation environment includes a cluster control terminal 101 and an underwater unmanned device 102. The cluster control terminal 101 can be a terminal device configured with a cluster control system for the underwater unmanned device, including but not limited to laptops, tablets, handheld computers, PADs (tablet computers), desktop computers, etc., with local computing capabilities. The cluster control system for the underwater unmanned device can be implemented as a target client, which can be a video client, instant messaging client, browser client, or other client that supports cluster control for the underwater unmanned device. The cluster control terminal 101 can communicate with the underwater unmanned device 102 via a network, including but not limited to wired networks and wireless networks. The wired network includes local area networks (LANs), metropolitan area networks (MANs), and wide area networks (WANs). The wireless network includes Bluetooth, Wi-Fi (Wireless Fidelity, a technology that allows electronic devices to connect to wireless LANs), and other networks that enable wireless communication. The cluster control terminal 101 may include, but is not limited to, a human-machine interface screen, a processor, and a memory. The human-machine interface screen may be used, but is not limited to, to display the cluster control method for the underwater unmanned device. The aforementioned processor may, but is not limited to, be used to respond to human-computer interaction operations, execute corresponding operations, or generate corresponding instructions.

[0060] As an optional approach, there may be multiple underwater unmanned devices 102; the cluster control terminal 101 can acquire historical mission data, current mission area and current mission type of the underwater unmanned devices; the cluster control terminal 101 can also acquire signal data and environmental water flow data of the underwater unmanned devices 102.

[0061] As an alternative, the aforementioned cluster control terminal 101 can also be a server. This server can be a single server, a server cluster consisting of multiple servers, or a cloud server. The above is merely an example, and this embodiment does not impose any limitations on it.

[0062] As an alternative approach, the following steps of the cluster control method for underwater unmanned equipment can be executed on the cluster control terminal 101:

[0063] Acquire historical mission data, current mission area, and current mission type of underwater unmanned equipment;

[0064] Based on the historical task data, the current task region, and the current task type, the difficulty level of the current task is determined;

[0065] The difficulty level of the current task is compared with a preset difficulty threshold, and the control mode of the underwater unmanned equipment cluster is determined based on the comparison result.

[0066] According to the underwater unmanned equipment cluster control method, the underwater unmanned equipment is controlled to perform the current task in the current task area.

[0067] The above methods acquire multifaceted information related to the task, providing a foundation for subsequent decision-making. Historical task data allows for the learning and understanding of the characteristics of different task areas and types, enabling more informed choices based on past experience when facing new tasks. Based on the collected information, the difficulty of the current task is assessed. By quantifying the difficulty, the complexity of the task can be dynamically perceived, and control strategies adjusted accordingly. This means that the most suitable control method can be flexibly selected based on the actual needs of the task, rather than relying solely on a fixed control mode. The assessed difficulty is compared with a preset threshold to determine whether centralized or distributed control should be used. Centralized control is suitable for relatively simple tasks, while distributed control is more suitable for complex or high-risk tasks. This step ensures that the most suitable control method is automatically selected based on the actual difficulty of the current task. When the task is relatively simple, centralized control can improve coordination and efficiency; while when the task is complex or there is a risk of communication interruption, distributed control can enhance the system's robustness and anti-interference capabilities. This dynamic selection mechanism allows the system to exhibit optimal performance in different task scenarios. Once the control method is determined, the underwater unmanned equipment can be directed to perform tasks within the current mission area according to the selected control strategy, thus realizing adaptive cluster control of underwater unmanned equipment.

[0068] As an optional example, this embodiment does not limit the executing entity of the above-described cluster control method for underwater unmanned equipment. The above-described cluster control method for underwater unmanned equipment can be executed on the cluster control terminal 101. For example, if the cluster control terminal 101 is a desktop computer, some or all of the steps of the above-described cluster control method for underwater unmanned equipment can be executed on the desktop computer.

[0069] The above section introduced the exemplary implementation environment of the technical solution of this application. Next, we will continue to introduce the swarm control method for underwater unmanned equipment of this application.

[0070] To address the problem of adaptive swarm control of underwater unmanned equipment in the prior art, embodiments of this application propose a swarm control method and a swarm control system for underwater unmanned equipment, which will be described in detail below.

[0071] Please see Figure 2 , Figure 2 This is a flowchart illustrating a swarm control method for underwater unmanned equipment according to an embodiment of the present invention. This method can be applied to... Figure 1 The implementation environment is shown. It should be understood that this method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0072] like Figure 2 As shown, in an exemplary embodiment, the swarm control method for underwater unmanned equipment includes at least steps S210 to S240, which are described in detail below:

[0073] In step S210, the historical mission data, current mission area, and current mission type of the underwater unmanned equipment are acquired.

[0074] Historical mission data refers to various information accumulated by underwater unmanned equipment in past missions, including but not limited to the geographical features of the mission area, mission type, mission execution time, obstacles or anomalies encountered, communication status, environmental conditions (such as water flow, temperature, pressure, etc.), and the quality and efficiency of mission completion. By analyzing historical mission data, the system can understand the characteristics of different mission areas and mission types, identify which areas or mission types have encountered difficulties in the past, and thus provide a reference for the evaluation of the current mission. Historical mission data is the foundation for achieving adaptive control, helping the system "learn" from past experiences and avoid repeating mistakes.

[0075] The current mission area refers to the specific geographical location and environmental conditions under which the underwater unmanned equipment will perform its mission. This includes the size, depth, topography, current conditions, marine life distribution, and potential obstacles of the mission area. Information about the current mission area directly affects the complexity and difficulty of the mission. Different areas may present different challenges; for example, deep-sea areas may face high pressure and low temperatures, while shallow-sea areas may have more marine life or human activity disturbances. The system needs to assess the feasibility of the mission based on the actual conditions of the current mission area and select an appropriate control strategy.

[0076] The current mission type refers to the specific nature of the task that the underwater unmanned equipment (UAV) is about to perform, such as seabed resource exploration, environmental monitoring, search and rescue operations, and military reconnaissance. Each mission type has different requirements for the UAV, potentially involving different operating modes, sensor configurations, and data processing methods. The mission type determines the mission's objectives and requirements, influencing its complexity and difficulty. For example, resource exploration missions may require high-precision navigation and positioning, while search and rescue missions emphasize rapid response and flexibility. The system needs to adjust its control strategy according to the different mission types to ensure the successful completion of the mission.

[0077] In step S220, the difficulty level of the current task is determined based on the historical task data, the current task region, and the current task type.

[0078] The core of this step, determining the difficulty level of the current task based on historical task data, the current task region, and the current task type, involves combining these factors to comprehensively assess the complexity and challenge of the current task. The assessment of difficulty can be quantified through various factors, such as the geographical complexity of the task region, the failure rate in historical tasks, communication conditions, and environmental changes. By assessing the difficulty level of the task, the system can dynamically perceive the actual needs of the task, thereby providing a basis for selecting subsequent control methods.

[0079] In step S230, the difficulty level of the current task is compared with a preset difficulty level threshold, and the underwater unmanned equipment cluster control mode is determined based on the comparison result.

[0080] Among them, the underwater unmanned equipment (UAV) cluster control method refers to the control strategy used to command multiple UAVs to work collaboratively. Depending on the difficulty of the task, the system can choose between two main methods: centralized control and distributed control. Centralized control involves a central control system that uniformly commands all UAVs. This is suitable for relatively simple tasks with good communication conditions. The advantages of centralized control are strong coordination and high control precision, but it is heavily reliant on communication; if communication is interrupted, the task may be affected. Distributed control allows each UAV to make autonomous decisions based on local information. This is suitable for complex tasks, variable environments, or unstable communication scenarios. The advantages of distributed control are strong robustness and the ability to cope with local obstacles and task changes, but the system complexity and communication latency may increase. Choosing the appropriate cluster control method is crucial to ensuring mission success. Centralized control is suitable for simple tasks, while distributed control is more suitable for complex tasks or high-risk scenarios. By dynamically selecting the control method, the system can exhibit optimal performance in different task scenarios.

[0081] In step S240, the underwater unmanned equipment is controlled to perform the current task in the current task area according to the underwater unmanned equipment cluster control method.

[0082] Once the cluster control method is determined, the system will direct the underwater unmanned equipment (UAVs) to perform tasks within the current mission area according to the selected control strategy. Whether in centralized or distributed control, the system ensures the smooth execution of the mission and adjusts the behavior of each UAV as needed. For example, in distributed control mode, the UAVs can autonomously adjust their paths or task assignments based on real-time environmental changes, while in centralized control mode, the central control system can perform global optimization based on the overall mission progress.

[0083] For example, suppose there is a group of underwater unmanned devices tasked with exploring seabed resources in a complex ocean area. The system has recorded multiple resource exploration missions previously conducted in the same area. In some of these missions, strong currents and complex seabed topography (such as canyons and rocky areas) were encountered, leading to extended mission times or communication interruptions for some devices. The current mission area is located in the same ocean area, but extends slightly northward. According to map and sensor data, this area is deeper, has faster currents, and contains some unknown seabed structures. The current mission is seabed resource exploration, with the goal of mapping the seabed topography and detecting mineral resources. The mission requires high-precision navigation and data acquisition, and necessitates the collaborative work of multiple underwater unmanned devices to cover a larger area. The system first analyzes historical mission data and finds that in past missions, strong currents and complex topography in similar areas caused communication interruptions and mission delays. Considering the depth and current conditions of the current mission area, the system assesses the difficulty level of the current mission as high. The system compares the difficulty level of the current mission with a preset threshold and finds that it exceeds the threshold, therefore deciding to adopt a distributed control approach. Each underwater drone can make autonomous decisions based on local water flow, terrain, and other information, avoiding mission failure due to communication interruptions. The drones maintain contact via short-range communication to ensure data synchronization and mission coordination. In distributed control mode, each drone autonomously selects the optimal path for exploration based on its own sensor data and mission plan. When a drone encounters strong currents or obstacles, it can flexibly adjust its course without affecting the operation of other drones. The system also dynamically adjusts the task allocation for each drone based on real-time feedback, ensuring the entire cluster can complete its mission efficiently.

[0084] As can be seen from steps S210 to S240 above, the solution proposed in this embodiment acquires multifaceted information related to the task. This information provides a foundation for subsequent decision-making. Through historical task data, the characteristics of different task areas and task types can be learned and understood, enabling more informed choices based on past experience when facing new tasks. Based on the collected information, the difficulty level of the current task is assessed. By quantifying the difficulty level, the complexity of the current task can be dynamically perceived, and the control strategy can be adjusted accordingly. This means that the most suitable control method can be flexibly selected according to the actual needs of the task, rather than relying solely on a fixed control mode. The assessed difficulty level is compared with a preset threshold to determine whether to use centralized or distributed control. Centralized control is suitable for relatively simple tasks, while distributed control is more suitable for complex or high-risk tasks. This step ensures that the most suitable control method can be automatically selected according to the actual difficulty of the current task. When the task is relatively simple, centralized control can improve coordination and efficiency; while when the task is complex or there is a risk of communication interruption, distributed control can enhance the robustness and anti-interference ability of the system. This dynamic selection mechanism enables the system to exhibit optimal performance in different task scenarios. Once the control method is determined, the underwater unmanned equipment can be directed to perform tasks within the current mission area according to the selected control strategy, thus realizing adaptive cluster control of underwater unmanned equipment.

[0085] In one embodiment of this application, determining the underwater unmanned equipment cluster control method based on the comparison results includes:

[0086] When the comparison result indicates that the difficulty level of the current task is greater than or equal to the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be distributed control.

[0087] When the comparison result indicates that the difficulty level of the current task is less than the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be centralized control.

[0088] For example, there is a group of underwater unmanned devices whose mission is to conduct seabed resource exploration and environmental monitoring in complex sea areas.

[0089] The system has recorded multiple resource exploration missions conducted in similar sea areas in the past. During these missions, some areas encountered problems such as strong currents and complex seabed topography (e.g., canyons, rocky areas), leading to equipment communication interruptions or mission delays. The current mission area is located in a deep-sea region exceeding 3000 meters in depth, with fast currents and some unknown seabed structures. According to sensor data, the terrain in this area is very complex, potentially containing steep cliffs and narrow channels. The current mission is seabed resource exploration, with the goal of mapping the seabed topography and detecting mineral resources. The mission requires high-precision navigation and data acquisition, and necessitates the collaborative work of multiple underwater unmanned devices to cover a larger area. Analysis of historical mission data revealed that strong currents and complex terrain in similar areas in past missions caused equipment communication interruptions and mission delays. Considering the depth and current conditions of the current mission area, the system assesses the current mission's difficulty level as high, exceeding the preset difficulty threshold. Since the difficulty level of the current mission is greater than or equal to the preset difficulty threshold, distributed control is selected. In distributed control mode, each underwater drone can make autonomous decisions based on local water flow, terrain, and other information, avoiding mission failure due to communication interruptions. Underwater drones maintain communication via short-range communication to ensure data synchronization and mission coordination. When an underwater drone encounters strong currents or obstacles, it can flexibly adjust its course without affecting the operation of other underwater drones. The system also dynamically adjusts the task allocation of each underwater drone based on real-time feedback, ensuring the entire cluster can complete tasks efficiently.

[0090] For example, consider a group of underwater unmanned devices tasked with seabed resource exploration and environmental monitoring in shallow waters. The system has recorded multiple past environmental monitoring missions conducted in these areas. In these missions, the devices typically operated smoothly under good communication conditions, with relatively flat terrain and gentle currents. The current mission area is located in a shallow sea region, no deeper than 100 meters, with slow currents, flat terrain, and no significant obstacles. According to sensor data, the environmental conditions in this area are relatively stable, suitable for long-term environmental monitoring. The current mission is environmental monitoring, with the goal of periodically collecting seawater samples and monitoring water quality changes. The mission requires multiple underwater unmanned devices to patrol along a predetermined route and transmit data back to the central control system. Analyzing historical mission data, the system finds that in past missions, environmental conditions in similar areas were relatively stable, device communication was good, and mission execution was smooth. Considering the terrain and current conditions of the current mission area, the system assesses the difficulty level of the current mission as low, below a preset difficulty threshold. Since the difficulty level of the current mission is less than the preset threshold, the system selects centralized control. In centralized control mode, the central control system uniformly commands all underwater unmanned equipment, ensuring they perform inspections along predetermined routes. Due to the relatively stable environmental conditions and good communication in the mission area, centralized control can fully leverage its advantages of strong coordination and high control precision. The central control system can adjust the paths and task assignments of each underwater unmanned device based on real-time data, ensuring the efficient completion of the mission.

[0091] In this embodiment, the most suitable control method is automatically selected based on the difficulty of the task, ensuring that the system can perform optimally in different task scenarios. Whether facing complex deep-sea exploration tasks or relatively simple shallow-sea monitoring tasks, the system can make optimal decisions based on the actual situation. For tasks with high difficulty, the system selects distributed control, enhancing the system's robustness and anti-interference capabilities, and ensuring the success rate of the task. For tasks with lower difficulty, the system selects centralized control, improving task coordination and efficiency, and simplifying the operation process. Distributed control is particularly suitable for complex or high-risk task environments, effectively responding to emergencies (such as communication interruptions, environmental changes, etc.) and ensuring the smooth completion of the task. Centralized control is suitable for scenarios with stable environments and good communication, fully leveraging its strong coordination advantages and reducing the possibility of task failure. By rationally selecting the control method, the system can optimize resource utilization in different task scenarios. For example, in complex tasks, distributed control can reduce dependence on communication and reduce the risk of communication interruptions; while in simple tasks, centralized control can improve task execution efficiency and ensure that resources are used most effectively. This approach considers not only the static characteristics of the task (such as the task area and task type) but also dynamic factors (such as real-time environmental changes and communication status). This flexibility allows the system to better cope with the changing underwater environment and ensure the smooth execution of the task. In distributed control mode, communication between underwater unmanned devices is no longer the sole reliance; the system can complete the task through local decision-making and short-range communication. This reduces dependence on long-range communication and mitigates the risks associated with communication interruptions, especially in complex environments. By appropriately selecting control methods, the system can optimize the task execution process in different task scenarios, reducing unnecessary waiting and adjustment time, thereby improving the overall efficiency of the task. Centralized control is suitable for simple tasks and can quickly coordinate the work of multiple underwater unmanned devices; while distributed control is suitable for complex tasks, flexibly responding to environmental changes and ensuring the efficient completion of the task.

[0092] In one embodiment of this application, the historical task data includes a historical task region and the number of times a historical task has been executed. Determining the difficulty level of the current task based on the historical task data, the current task region, and the current task type includes:

[0093] The scope of the historical task area is overlaid and analyzed to determine the familiarity level of the first task corresponding to each sub-region in the historical task area.

[0094] Based on the number of times the historical tasks were executed, the execution status of multiple historical task types was analyzed to determine the familiarity with the second task corresponding to each historical task type.

[0095] Obtain the region ratio of the sub-region in the current task region, and combine the region ratio with the second task familiarity level corresponding to the current task type and the first task familiarity level corresponding to the sub-region to determine the difficulty level of the current task.

[0096] The historical mission area refers to the geographical area covered by underwater unmanned equipment during past missions. Each historical mission area may include multiple sub-regions, each with different geographical features, environmental conditions, and mission difficulty. By analyzing historical mission areas, the system can understand information such as topography, water flow, and obstacle distribution in different sub-regions, and assess the mission complexity of each sub-region. This is crucial for assessing the difficulty of the current mission, especially when the current mission area overlaps with the historical mission area.

[0097] The historical task execution count refers to the frequency with which an underwater unmanned device has performed the same type of task in the past, under a specific task type. This includes the total number of executions for each task type and the number of executions in different sub-regions. The historical task execution count reflects the system's familiarity with a certain task type. The more executions, the more proficient the system is with that task type, and the higher the probability of task success. By analyzing the historical task execution count, the system can assess its familiarity with different types of tasks, thus providing a reference for assessing the difficulty of the current task.

[0098] Overlay analysis involves superimposing the ranges of multiple historical task areas to identify the frequency with which each sub-region was covered in multiple tasks. In this way, the system can determine which sub-regions were frequently accessed in past tasks and which were relatively unfamiliar. The results of the overlay analysis are used to assess the first-task familiarity of each sub-region. If a sub-region is frequently accessed in historical tasks, it indicates that the system is very familiar with the environment and task requirements of that region, and the task difficulty is low; conversely, if a sub-region is rarely accessed, it indicates that the system has less experience with that region, and the task difficulty is high.

[0099] This involves statistically analyzing the execution counts of different historical task types to assess the system's mastery of various task types. Specifically, the system calculates the execution count for each task type and compares it to the total execution count to determine the secondary task familiarity level for each type. By analyzing the execution counts of historical tasks, the system can determine its familiarity with different task types. For task types with a high number of executions, the system has higher experience and success rate, and the task difficulty is lower; while for task types with fewer executions, the system lacks experience, and the task difficulty is higher. This analysis helps to more accurately assess the difficulty level of the current task.

[0100] The region percentage refers to the proportion of each sub-region's area within the current task area to the entire task area. By calculating the region percentage, the system can determine which sub-regions within the current task area are the primary work areas and which are secondary. Calculating the region percentage helps to combine the analysis results of historical task areas with the current task area. If a large proportion of the sub-regions in the current task area are familiar to the system, the overall difficulty of the task is lower; conversely, if a large proportion of the sub-regions in the current task area are unfamiliar to the system, the overall difficulty of the task is higher.

[0101] In this embodiment, by overlaying and analyzing historical task areas, the system can more accurately assess the task familiarity of each sub-region. Combined with the analysis of task execution counts, the system can comprehensively understand its mastery of different task types. This multi-dimensional evaluation method enables the system to more accurately determine the difficulty of the current task, avoiding biases caused by single-factor evaluation. Based on the accurate assessment of task difficulty, the system can select the most suitable cluster control method. For example, in cases of high task difficulty, the system will choose distributed control to cope with the risks of complex environments and communication interruptions; while in cases of low task difficulty, the system can choose centralized control to improve task coordination and efficiency. This dynamic selection mechanism ensures that the system can exhibit optimal performance in different task scenarios. This scheme not only considers the static characteristics of the task (such as task area and task type) but also combines historical task data and real-time environmental changes. Through overlay analysis and analysis of task execution counts, the system can better adapt to the changing underwater environment, ensuring the smooth execution of tasks. Even when facing unknown or complex task areas, the system can make reasonable decisions based on historical experience.

[0102] In one embodiment of this application, the historical task region includes multiple regions corresponding to historical tasks. The step of performing overlay analysis on the range of the historical task region to determine the familiarity level of the first task corresponding to each sub-region within the historical task region includes:

[0103] The ranges of the areas corresponding to the multiple historical tasks are marked;

[0104] Based on the range of the regions corresponding to the marked historical tasks, the overlapping ranges are superimposed to obtain multiple sub-regions;

[0105] The familiarity level of the first task corresponding to each sub-region is determined based on the total number of times the multiple sub-regions are superimposed and the number of times each sub-region is superimposed.

[0106] The step of marking the geographical areas corresponding to the multiple historical tasks involves clearly identifying and recording the geographic region corresponding to each historical task. Specifically, the system marks these areas on a map based on information such as the actual execution path and coverage of each historical task. Each marked area represents the activity range of a historical task. By marking the historical task areas, the system can clearly identify the specific coverage of each task and provide basic data for subsequent overlay analysis. The marked areas include not only the main work area of ​​the task but may also include transitional or exploration areas traversed during the task. This helps the system comprehensively understand the historical activity range of different tasks, providing accurate data support for further analysis.

[0107] The process of overlaying repeated regions to obtain multiple sub-regions involves analyzing the overlay of regions corresponding to multiple historical tasks to identify instances where each sub-region is accessed multiple times. Specifically, the system overlays all marked historical task regions to identify which sub-regions are repeatedly accessed across multiple tasks and which appear only in a few tasks. In this way, the system can divide the entire task region into multiple sub-regions, each corresponding to a different access frequency. The results of the overlay analysis are used to determine the first task familiarity of each sub-region. If a sub-region is frequently accessed in multiple historical tasks, it indicates that the system is very familiar with the task environment of that region, and the task difficulty is low; conversely, if a sub-region is rarely accessed, it indicates that the system has less experience with that region, and the task difficulty is high. This overlay analysis method allows the system to more accurately assess the task complexity of each sub-region, thus providing a basis for assessing the difficulty of the current task.

[0108] For example, based on the mission records of each historical mission, the area where the underwater unmanned equipment worked during each historical underwater mission is obtained and marked; based on the area marked by each historical mission, areas belonging to the same area are superimposed (only completely identical areas are superimposed, and non-completely identical areas are not superimposed), thus finally obtaining the superposition count of each superimposed area.

[0109] For example, the familiarity level of the first task corresponding to the i-th sub-region can be represented as follows:

[0110] in, The familiarity level of the first task corresponding to the i-th sub-region; Let i be the number of times the i-th sub-region is superimposed. This represents the total number of times multiple sub-regions are superimposed.

[0111] in, The larger the value, the more familiar the user is with the sub-region in previous unmanned equipment operations. In this case, the data collected in the past, such as seabed topography, water flow characteristics, biological distribution, and resource locations, will be more helpful in providing relevant data support for the current mission, thereby reducing the difficulty of exploring the current superimposed area in the future.

[0112] In this embodiment, by marking and overlaying analysis of regions corresponding to multiple historical tasks, the system can more accurately identify the task familiarity level of each sub-region. Overlay analysis not only considers the coverage of a single task but also integrates historical data from multiple tasks, enabling the system to gain a more comprehensive understanding of the characteristics of the task region. This multi-dimensional evaluation method improves the accuracy of task evaluation, ensuring the system can make more reasonable decisions. Based on the evaluation of sub-region familiarity, the system can select the most suitable cluster control method. For example, in regions with high task difficulty, the system will choose distributed control to cope with the risks of complex environments and communication interruptions; while in regions with low task difficulty, the system can choose centralized control to improve task coordination and efficiency. This dynamic selection mechanism ensures that the system can exhibit optimal performance in different task scenarios.

[0113] In one embodiment of this application, the number of historical task executions includes the number of executions of multiple historical task types. The step of analyzing the execution status of the multiple historical task types based on the number of historical task executions to determine the familiarity level of the second task corresponding to each historical task type includes:

[0114] The total number of times the historical task was executed is determined based on the number of times each of the multiple historical task types was executed.

[0115] The execution count of each historical task type is compared with the total number of historical task executions to obtain the second task familiarity level corresponding to each historical task type.

[0116] For example, the familiarity level of the second task corresponding to the m-th type of historical task can be represented as follows:

[0117]

[0118] in, The familiarity with the second task corresponding to the m-th type of historical task; Let m be the number of times the m-th type of historical task is executed. This represents the total number of times a historical mission has been executed.

[0119] in, The higher the level of familiarity with the second task, the more efficient and accurate the underwater unmanned equipment will be in handling similar tasks.

[0120] For example, suppose there is a group of underwater unmanned devices that have performed various types of tasks in the past. The system records multiple tasks performed in a complex sea area, involving different task types, including seabed resource exploration, environmental monitoring, search and rescue operations, and military reconnaissance. The number of executions for each task type varies, as follows: resource exploration tasks were performed 30 times; environmental monitoring tasks were performed 50 times; search and rescue operations were performed 20 times; and military reconnaissance tasks were performed 10 times. The current task is seabed resource exploration, with the goal of mapping the seabed topography and detecting mineral resources. The system first counts the total number of executions for all historical tasks. According to the records, the system has performed a total of 110 tasks in the past (30 resource explorations + 50 environmental monitorings + 20 search and rescue operations + 10 military reconnaissances), so the total number of historical task executions = 110. Next, the number of executions for each task type is compared with the total number of executions to calculate the relative execution frequency of each task type, i.e., the second task familiarity. Familiarity with the second task of resource exploration: Familiarity with the second task of resource exploration = Number of resource exploration tasks executed divided by the total number of historical tasks executed = 30 ÷ 110 ≈ 0.273. Familiarity with the second task of environmental monitoring: Familiarity with the second task of environmental monitoring = Number of environmental monitoring tasks executed divided by the total number of historical tasks executed = 50 ÷ 110 ≈ 0.455. Familiarity with the second task of search and rescue operations: Familiarity with the second task of search and rescue operations = Number of search and rescue operations executed divided by the total number of historical tasks executed = 20 ÷ 110 ≈ 0.182. Familiarity with the second task of military reconnaissance: Familiarity with the second task of military reconnaissance = Number of military reconnaissance tasks executed divided by the total number of historical tasks executed = 10 ÷ 110 ≈ 0.091. Since the current task is seabed resource exploration, based on the above calculations, the familiarity with the second task of the current task is determined to be 0.273. This indicates that the system has some experience with resource exploration tasks, but its familiarity with other task types (such as environmental monitoring) is relatively low.

[0121] In this embodiment, by statistically analyzing the execution frequency of multiple historical task types, the system can more accurately assess its familiarity with each task type. Specifically, the system calculates the relative execution frequency of each task type to obtain a second level of familiarity. This multi-dimensional evaluation method improves the accuracy of task evaluation, ensuring the system can make more reasonable decisions. Based on the assessment of familiarity with task types, the system can select the most suitable cluster control method. For example, in cases of high task difficulty, the system will choose distributed control to cope with the risks of complex environments and communication interruptions; while in cases of low task difficulty, the system can choose centralized control to improve task coordination and efficiency. This dynamic selection mechanism ensures that the system can exhibit optimal performance in different task scenarios.

[0122] For example, the difficulty level of the current task can be represented as follows:

[0123]

[0124] in, The level of difficulty corresponding to the current task; K represents the familiarity level with the second task corresponding to the current task type; K represents the number of sub-regions in the current task area. This represents the percentage of the k-th sub-region within the current task region. This represents the familiarity level with the first task corresponding to the k-th sub-region.

[0125] In one embodiment of this application, controlling the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control method includes:

[0126] When the underwater unmanned equipment cluster control mode is distributed control, the target number of underwater unmanned equipment is determined based on the historical task data and the current task type.

[0127] Acquire signal data and environmental water flow data corresponding to multiple candidate underwater unmanned devices, and determine the assignment priority corresponding to each candidate underwater unmanned device based on the signal data and environmental water flow data;

[0128] Based on the number of target underwater unmanned devices and the assignment priority of each candidate underwater unmanned device, a target underwater unmanned device is determined from the plurality of candidate underwater unmanned devices, so that the target underwater unmanned device performs the current task in the current task area.

[0129] When underwater operations are conducted, multiple underwater unmanned devices (UAVs) typically collaborate to complete complex tasks, such as marine exploration, underwater ecological surveys, and seabed mining. During this process, it's crucial to consider factors such as the equipment status and environmental interference of the UAVs in complex underwater environments. In particular, the familiarity of the task area and the complexity of the task itself can significantly impact the swarm control of the UAVs. In practical applications, UAVs are deployed to specific missions based on newly defined objectives. Before deployment, the signal stability of the UAVs must be considered. This is because the signal strength of the UAVs can be affected by their own internal factors, such as sensor aging, electronic component wear, and battery degradation, as well as external factors like suspended matter (such as silt, organic matter, or microorganisms) causing signal scattering, absorption, or attenuation. These factors can lead to signal instability, affecting the communication stability of the UAVs and posing a potential threat to the successful execution of the mission.

[0130] The step of determining the target number of underwater unmanned vehicles (UAVs) based on historical mission data and the current mission type involves the system determining the number of UAVs required to execute the current mission. Specifically, the system analyzes factors such as the number of UAVs used in similar past missions, mission completion time, and mission success rate, and combines this with the specific requirements of the current mission to determine a reasonable target number of UAVs. By referencing historical mission data, the system can more accurately estimate the resource requirements of the current mission, avoiding resource shortages or over-configuration. For different types of missions, the system can dynamically adjust the number of UAVs based on the complexity and difficulty of the mission to ensure efficient mission completion.

[0131] Signal data refers to information such as the strength and quality of communication signals between underwater unmanned devices (UAVs). This data reflects the communication status between UAVs, including signal transmission distance, signal stability, and latency. Signal data is used to assess the communication capabilities between UAVs, especially in distributed control modes, where good communication is crucial for successful mission execution. By analyzing signal data, the system can identify which UAVs have good communication quality and which may be at risk of communication interruption, thus providing a basis for subsequent mission allocation.

[0132] Environmental current data refers to information such as water flow velocity, direction, and changes within the current mission area. This data reflects the hydrological conditions of the mission area and directly impacts the navigation path, energy consumption, and mission efficiency of underwater unmanned equipment (UAVs). Environmental current data is used to assess the navigation conditions of underwater UAVs within the mission area. For example, strong currents may increase the energy consumption of underwater UAVs, affecting their endurance; complex current changes may cause underwater UAVs to deviate from their planned paths. By analyzing environmental current data, the system can optimize the mission planning of underwater UAVs, select the most suitable navigation path, and improve the mission success rate.

[0133] Assignment priority refers to the order in which each candidate underwater drone is prioritized in task allocation. Priority is determined based on multiple factors, including the communication signal quality of the underwater drone, environmental current conditions, equipment status, and mission experience. Underwater drones with higher priority will be assigned tasks first. By determining the assignment priority for each candidate underwater drone, the system can select the most suitable group of drones from among multiple drones to perform the task. Priority settings ensure the rationality of task allocation and avoid resource waste and the risk of task failure.

[0134] The process of determining the assignment priority for each candidate underwater drone (UAV) based on the signal and current data involves the system comprehensively evaluating its performance potential in the current mission and assigning it an assignment priority. Specifically, the system considers multiple factors such as the UAV's communication quality, navigation conditions, mission experience, and equipment status to calculate the priority of each UAV. By comprehensively evaluating the signal and current data, the system can gain a more comprehensive understanding of the strengths and weaknesses of each candidate UAV, ensuring the rationality of mission allocation. Higher-priority UAVs typically have better communication capabilities and are better adapted to the navigation conditions of the current mission area, making them more suitable for the mission.

[0135] In this embodiment, by rationally selecting the number and prioritizing of underwater unmanned equipment (UAVs), the system ensures that the task is executed by the most suitable group of equipment, avoiding resource waste and the risk of task failure. Higher-priority UAVs typically have better communication capabilities and are better adapted to the navigation conditions of the current task area, thus enabling them to complete the task more efficiently. In distributed control mode, the system reduces the risk of communication interruption and enhances system robustness by selecting UAVs with better communication quality. Simultaneously, by selecting UAVs with better environmental adaptability, the system can better cope with complex underwater environments, ensuring successful task completion. Through comprehensive analysis of signal data and environmental current data, the system can formulate optimal task plans for each UAV, select the most suitable navigation path, reduce energy consumption, and improve the task success rate. This optimized planning mechanism allows the system to flexibly respond to various challenges in complex underwater environments, ensuring efficient task completion. Through analysis of historical task data, the system can identify potential risky task areas and UAVs in advance. For example, if a particular UAV has a low historical task success rate, or if the current conditions in its area are complex, the system can take preventative measures in the current task to reduce the possibility of task failure. This risk prediction mechanism improves the success rate of tasks and reduces task risks.

[0136] In one embodiment of this application, determining the number of target underwater unmanned devices based on the historical mission data and the current mission type includes:

[0137] Based on the historical mission data, determine the number of underwater unmanned devices corresponding to multiple historical mission types;

[0138] The current task type is matched with the multiple historical task types, and the number of underwater unmanned devices corresponding to the matched historical task types is used as the reference number of underwater unmanned devices for the current task type.

[0139] The average number of reference underwater unmanned devices is taken as the target number of underwater unmanned devices.

[0140] The determination of the number of underwater drones (UAVs) corresponding to multiple historical task types based on historical task data refers to the system calculating the number of UAVs used for each task type in past executions based on historical task data. Specifically, the system analyzes the execution records of each historical task, extracts the number of UAVs used in each task, and associates this number with the task type. By statistically analyzing the historical number of UAVs used for different task types, the system can understand the resource requirements of each task type. For example, some task types may require more UAVs to complete, while other task types require fewer. This statistical result provides important reference for subsequent task planning.

[0141] The process of matching the current task type with multiple historical task types, and using the number of underwater drones corresponding to the matched historical task types as the reference number of underwater drones for the current task type, involves the system comparing the current task type with historical task types to find the most similar historical task type. Then, the system uses the number of underwater drones corresponding to these similar task types as the reference number of underwater drones for the current task type. By matching historical task types, the system can draw on experience from similar past tasks to ensure more rational resource allocation for the current task. The matching process considers not only the task type itself but may also take into account factors such as the task area and task difficulty to ensure the accuracy of the matching results.

[0142] The use of the average number of reference underwater unmanned vehicles (UAVs) as the target number of UAVs refers to the system averaging the number of UAVs across all matched historical mission types. This average is then used as the target number of UAVs for the current mission. By calculating the average, the system can avoid deviations caused by the specific characteristics of individual historical missions, ensuring a more stable and reliable selection of the target number of UAVs. The average method integrates the experience of multiple historical missions and can better reflect the actual needs of the current mission.

[0143] In this embodiment, by matching historical task types and calculating the average, the system can more reasonably determine the number of underwater unmanned devices required for the current task. Compared to single historical task data, the averaging method integrates the experience of multiple historical tasks, avoiding deviations caused by the particularities of individual tasks and ensuring the stability of task planning. Based on the statistical results of historical task data, the system can more accurately estimate the resource requirements of the current task, avoiding resource shortages or over-configuration. For example, for a resource exploration task, the system determines to use 5 underwater unmanned devices based on historical data, ensuring both efficient task completion and avoiding resource waste.

[0144] In one embodiment of this application, determining the assignment priority of each candidate underwater unmanned device based on the signal data and environmental water flow data includes:

[0145] Based on the signal data, the communication signal strength of the candidate underwater unmanned equipment within the target time period is determined, and the fluctuation analysis of the communication signal strength is performed to obtain the signal stability degree corresponding to each candidate underwater unmanned equipment.

[0146] Based on the environmental water flow data, the water flow direction and velocity are determined, and the changes in the water flow direction and velocity are analyzed to obtain the environmental friendliness of each candidate underwater unmanned device.

[0147] By combining the signal stability and environmental friendliness, the assignment priority corresponding to each candidate underwater unmanned device is obtained.

[0148] Communication signal strength refers to the strength of wireless communication signals between underwater unmanned devices (UAVs), typically measured by signal power or Received Signal Strength Indication (RSSI). Communication signal strength reflects the communication quality between UAVs and determines the reliability and real-time performance of data transmission. It is a crucial indicator for evaluating the communication capabilities between UAVs. A stronger communication signal means better communication quality, ensuring stable and timely data transmission during missions; while a weaker signal may lead to data loss or delays, affecting the successful execution of the mission.

[0149] Determining the communication signal strength of the candidate underwater drones within the target time period based on the signal data refers to the system collecting and recording the communication signal strength of each candidate underwater drone within a specific time period (i.e., the target time period). The target time period can be determined based on the needs of the mission; for example, it could be a few minutes before the mission begins, a period during the mission execution, or a summary period after the mission ends. By continuously monitoring the communication signal strength of the underwater drones within the target time period, the system can understand the communication performance of each underwater drone at different time periods, providing data support for subsequent fluctuation analysis. This dynamic monitoring helps identify which underwater drones have good communication quality within a specific time period and which underwater drones may have unstable communication.

[0150] Fluctuation analysis refers to the statistical analysis of changes in communication signal strength to assess the stability of the communication signal for each underwater drone. Specifically, the system calculates indicators such as the fluctuation range and frequency of the communication signal strength to determine the signal stability of each underwater drone. Signal stability reflects the communication reliability of the underwater drone during the mission. A stable communication signal means that the underwater drone can maintain good communication quality throughout the mission, avoiding data loss or communication interruptions due to signal fluctuations. Significant signal fluctuations indicate that the underwater drone may be affected by environmental interference or other factors, posing a communication risk.

[0151] The direction and velocity of water flow refer to the water movement within the current mission area, including the direction and speed of the flow. This information reflects the hydrological conditions of the mission area and directly impacts the navigation path, energy consumption, and mission efficiency of underwater unmanned equipment (UAVs). Water flow direction and velocity are crucial parameters for assessing the navigation conditions of UAVs. Stable water flow helps UAVs complete missions efficiently, while complex water flow variations can increase energy consumption and even cause them to deviate from their planned paths. By analyzing water flow data, the system can select the most suitable navigation route for each UAV and optimize mission planning.

[0152] The change analysis refers to the statistical analysis of changes in water flow direction and velocity to assess the environmental friendliness of each underwater unmanned device (UAV). Specifically, the system calculates indicators such as water flow stability and frequency of change to determine the environmental friendliness of each UAV. Environmental friendliness reflects the navigation conditions of the UAV in the mission area. A friendly environment means the UAV can navigate in relatively stable water flow, reducing energy consumption and improving mission efficiency; while an unfriendly environment indicates that the UAV may face complex water flow changes, increasing the difficulty and risk of the mission. By analyzing water flow data, the system can select the most suitable mission area for each UAV, ensuring mission safety and success rate.

[0153] The assignment priority for each candidate underwater drone (UAV) is determined by combining the signal stability and environmental friendliness. This means the system comprehensively considers both factors when assigning a priority to each UAV. Priority settings are based on two key factors: communication quality and navigation conditions. Higher-priority UAVs typically have more stable communication signals and better environmental conditions, making them more suitable for mission execution. By combining signal stability and environmental friendliness, the system can more comprehensively evaluate the strengths and weaknesses of each UAV, ensuring the rationality of mission allocation. Higher-priority UAVs not only have better communication quality but also can operate in more ideal environments, thereby improving mission success rate and efficiency.

[0154] For example, based on the environment in which each underwater unmanned device is located, the communication signal strength data of each underwater unmanned device in the last 2 minutes is obtained; based on the principle that the higher and more stable the communication signal strength of the underwater unmanned device, the communication signal strength of each underwater unmanned device in the last 2 minutes is used as a benchmark, and the fluctuation of the communication signal strength data of the underwater unmanned device in the last 2 minutes is considered. The greater the fluctuation, the greater the adjustment on the basis of the above benchmark.

[0155] The signal stability of the z-th candidate underwater unmanned device can be represented as follows:

[0156]

[0157] in, The signal stability level corresponding to the z-th candidate underwater unmanned device; This represents the average communication signal strength of the z-th candidate underwater unmanned device over the past two minutes. This represents the standard deviation of the communication signal strength for all communication signals within the corresponding range. This represents the communication signal strength data of the z-th candidate underwater unmanned device within the last two minutes; For norm normalization functions in mathematical calculations; Let be the total number of communication signals from the z-th candidate underwater unmanned device in the last two minutes.

[0158] In this embodiment, by comprehensively evaluating the stability of communication signals and environmental friendliness, the system can assign reasonable assignment priorities to each underwater unmanned device (UAV), ensuring that the task is executed by the most suitable group of devices. Higher-priority UAVs typically have better communication quality and are better adapted to the navigation conditions of the current mission area, enabling them to complete the task more efficiently. In distributed control mode, the system reduces the risk of communication interruption and enhances system robustness by selecting UAVs with better communication quality. Simultaneously, by selecting UAVs with better environmental adaptability, the system can better cope with complex underwater environments, ensuring the successful completion of the task. Through comprehensive analysis of communication signals and environmental current data, the system can formulate optimal task plans for each UAV, select the most suitable navigation path, reduce energy consumption, and improve the success rate of the task. This optimized planning mechanism enables the system to flexibly respond to various challenges in complex underwater environments, ensuring the efficient completion of tasks.

[0159] In one embodiment of this application, the step of analyzing the changes in the water flow direction and the water flow velocity to obtain the environmental friendliness of each candidate underwater unmanned device includes:

[0160] Based on the water flow velocity, construct a time-series-based curve of water flow velocity variation.

[0161] Based on the water flow velocity variation curve, multiple extreme points were determined;

[0162] Obtain the difference in water flow velocity and time between the extreme point and its adjacent extreme points, and determine the difference in water flow direction between the extreme point and its adjacent extreme points based on the water flow direction.

[0163] The degree of water flow velocity interference is determined based on the difference in water flow velocity and time difference between the extreme point and the adjacent extreme point.

[0164] The degree of interference in the direction of water flow is determined based on the difference in water flow velocity and the difference in water flow direction between the extreme point and the adjacent extreme points.

[0165] Based on the degree of interference from the water flow velocity and the degree of interference from the water flow direction, the environmental friendliness level corresponding to each candidate underwater unmanned device is obtained.

[0166] The time-series-based water flow velocity variation curve refers to arranging the water flow velocity data within the task area in chronological order and plotting a curve reflecting the change in water flow velocity over time. This curve can visually demonstrate the trend of water flow velocity changes across different time periods. By constructing the water flow velocity variation curve, the system can comprehensively understand the water flow dynamics within the task area and identify the patterns and fluctuations in water flow velocity. This visualization method is helpful for subsequent extreme point analysis and disturbance level assessment.

[0167] Extreme points refer to local maximum or minimum values ​​in the water flow velocity variation curve. These points reflect the maximum or minimum value reached by the water flow velocity at a certain moment, and are usually indicators of significant changes in the water flow. By identifying extreme points, the system can capture drastic changes in water flow velocity and then analyze the impact of these changes on the navigation of underwater unmanned equipment. The number and distribution of extreme points can help the system assess the complexity and stability of the water flow.

[0168] The velocity difference between an extreme point and its adjacent extreme points refers to the difference in flow velocity between two adjacent extreme points; the time difference refers to the time interval between these two extreme points. The velocity difference reflects the magnitude of changes in flow over a short period, while the time difference reflects the frequency of these changes. By calculating both, the system can quantify the rate of change of flow velocity, thereby assessing the volatility and instability of the flow.

[0169] The flow direction difference refers to the angular difference between the flow directions at two adjacent extreme points. Specifically, it involves calculating the flow direction at each extreme point and comparing the directional changes between adjacent extreme points. The flow direction difference reflects the directional changes of the flow over a short period of time. Especially in complex hydrological environments, frequent changes in flow direction can significantly impact the navigation path of underwater unmanned equipment. By calculating the flow direction difference, the system can assess the stability and complexity of the flow direction.

[0170] The degree of water flow velocity interference refers to the extent to which changes in water flow velocity affect the navigation of underwater unmanned equipment (UAVs). It is typically measured by the difference in water flow velocity and the time difference between extreme points. A larger difference in water flow velocity and a shorter time difference indicate a more drastic change in water flow velocity and a greater impact on the underwater UAV. The degree of water flow velocity interference reflects the impact of changes in water flow velocity on the navigation of underwater UAVs. Significant water flow velocity interference may increase the energy consumption of underwater UAVs and even cause them to deviate from their planned paths. By assessing the degree of water flow velocity interference, the system can select the most suitable mission area for each underwater UAV, ensuring mission safety and success rate.

[0171] The degree of interference from water flow direction refers to the extent to which changes in water flow direction affect the navigation of underwater unmanned equipment (UAVs). It is typically measured by the difference in water flow velocity and direction between extreme points. A larger difference in water flow direction and a larger difference in water flow velocity indicate a more drastic change in water flow direction and a greater impact on the underwater UAV. The degree of interference from water flow direction reflects the influence of changes in water flow direction on the navigation of underwater UAVs. Frequent changes in water flow direction can make it difficult for underwater UAVs to maintain a stable navigation path, increasing the difficulty and risk of the mission. By assessing the degree of interference from water flow direction, the system can select the most suitable mission area for each underwater UAV, ensuring mission safety and success rate.

[0172] The environmental friendliness level of each candidate underwater unmanned device (UAV) is determined based on the interference levels of water flow velocity and direction. This means that the system comprehensively considers both interference levels to assess the environmental friendliness of each UAV. Environmental friendliness reflects the navigation conditions of the UAV in the mission area. A friendly environment means that the UAV can navigate in relatively stable water flow, reducing energy consumption and improving mission efficiency; while an unfriendly environment indicates that the UAV may face complex water flow changes, increasing the difficulty and risk of the mission.

[0173] For example, when underwater unmanned equipment (UAVs) are operating, the water flow can bend, compress, or expand as it passes over obstacles on the seabed (such as ridges, canyons, coral reefs, etc.). These topographical features lead to uneven distribution of water flow velocity, causing turbulence and strong currents, which increases the motion instability of the UAV and affects its directionality and position control. The water flow velocity and direction data, influenced by the actual environment, can be obtained from the UAV's water flow sensors over the past two minutes. Based on the water flow velocity data of the z-th UAV, a time-series water flow velocity variation curve is constructed, and extreme points are identified.

[0174] For example, the environmental friendliness of the z-th candidate underwater unmanned device can be represented as follows:

[0175]

[0176] in, This indicates the environmental friendliness of the z-th candidate underwater unmanned device; The difference in water velocity is obtained by taking the absolute value of the difference in water velocity data between the b-th extreme point of the z-th underwater unmanned device and the next adjacent extreme point, and then normalizing it using the norm normalization function. The time difference is represented by taking the absolute value of the time data difference between the b-th extreme point of the water flow velocity of the z-th underwater unmanned device and the next adjacent extreme point, and then normalizing it using the norm normalization function. The difference in water flow direction is obtained by taking the absolute value of the difference in water flow direction data between the b-th extreme point of water flow velocity of the z-th underwater unmanned device and the next adjacent extreme point, and then normalizing it using the norm normalization function. This represents the number of extreme points of the water flow velocity for the z-th underwater unmanned device.

[0177] in, The larger the value, the more obvious the water flow changes in a short period of time within the stage corresponding to the current adjacent extreme point, that is, the greater the degree of environmental interference, and the smaller the environmental friendliness may be. The larger the value, the more likely the environmental friendliness will decrease due to sudden changes in the direction of water flow, the formation of eddies, or reverse flow caused by environmental disturbances.

[0178] For example, the assignment priority of the z-th candidate underwater unmanned device can be represented as follows:

[0179]

[0180] in, This indicates the assignment priority corresponding to the z-th candidate underwater unmanned device; The familiarity level with the second task corresponding to the current task type; The signal stability level corresponding to the z-th candidate underwater unmanned device; This indicates the environmental friendliness level of the z-th candidate underwater unmanned device.

[0181] Specifically, when the difficulty of the current task is higher, underwater unmanned equipment with better signal strength should be selected to avoid disconnection during subsequent task execution. Conversely, when the difficulty of the current task is lower, more attention should be paid to the environmental friendliness of the area where the underwater unmanned equipment is located. A lower environmental friendliness indicates greater environmental interference in the area where the underwater unmanned equipment is located, which may lead to environmental impacts during its journey to the task area corresponding to the new task.

[0182] In this embodiment, by comprehensively evaluating the interference levels of water flow velocity and direction, the system can assign a reasonable priority to each underwater unmanned device (UAV), ensuring that the task is executed by the most suitable group of devices. Higher-priority UAVs typically have better navigation conditions and can complete tasks more efficiently. In distributed control mode, the system reduces navigation risks caused by changes in water flow by selecting UAVs with better environmental adaptability, thus enhancing the system's robustness. Especially in areas with strong currents, the system can select UAVs with more stable currents, ensuring the safety and reliability of the mission.

[0183] Figure 3 This is a schematic diagram of a cluster control system for underwater unmanned equipment, provided as an embodiment of the present invention. This system can be applied to... Figure 1 The implementation environment shown is not limited to this system. This system can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the system is applicable.

[0184] like Figure 3 As shown, this exemplary cluster control system for underwater unmanned equipment includes:

[0185] Data acquisition module 301 is used to acquire historical mission data, current mission area and current mission type of underwater unmanned equipment;

[0186] The difficulty level determination module 302 is used to determine the difficulty level of the current task based on the historical task data, the current task region, and the current task type.

[0187] The control mode determination module 303 is used to compare the difficulty level of the current task with a preset difficulty level threshold, and determine the control mode of the underwater unmanned equipment cluster based on the comparison result.

[0188] The cluster control module 304 is used to control the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control mode.

[0189] In this exemplary swarm control system for underwater unmanned equipment, multifaceted information related to the task is acquired, providing a foundation for subsequent decision-making. Historical task data allows the system to learn and understand the characteristics of different task areas and types, enabling more informed choices based on past experience when facing new tasks. Based on the collected information, the difficulty of the current task is assessed. By quantifying the difficulty, the complexity of the current task can be dynamically perceived, and the control strategy adjusted accordingly. This means that the most suitable control method can be flexibly selected based on the actual needs of the task, rather than relying solely on a fixed control mode. The assessed difficulty is compared with a preset threshold to determine whether centralized or distributed control should be used. Centralized control is suitable for relatively simple tasks, while distributed control is more suitable for complex or high-risk tasks. This step ensures that the most suitable control method is automatically selected based on the actual difficulty of the current task. When the task is relatively simple, centralized control can improve coordination and efficiency; while when the task is complex or there is a risk of communication interruption, distributed control can enhance the system's robustness and anti-interference capabilities. This dynamic selection mechanism allows the system to exhibit optimal performance in different task scenarios. Once the control method is determined, the underwater unmanned equipment can be directed to perform tasks within the current mission area according to the selected control strategy, thus realizing adaptive cluster control of underwater unmanned equipment.

[0190] It should be noted that the cluster control system for underwater unmanned equipment provided in the above embodiments and the cluster control method for underwater unmanned equipment provided in the above embodiments belong to the same concept. The specific ways in which each module and unit performs operations have been described in detail in the method embodiments, and will not be repeated here. In practical applications, the cluster control system for underwater unmanned equipment provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above, and this is not a limitation here.

[0191] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0192] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A swarm control method for underwater unmanned equipment, characterized in that, The method includes: Acquire historical mission data, current mission area, and current mission type of underwater unmanned equipment; Based on the historical task data, the current task region, and the current task type, the difficulty level of the current task is determined; The difficulty level of the current task is compared with a preset difficulty threshold, and the control mode of the underwater unmanned equipment cluster is determined based on the comparison result. According to the underwater unmanned equipment cluster control method, the underwater unmanned equipment is controlled to perform the current task in the current task area; The step of determining the underwater unmanned equipment cluster control method based on the comparison results includes: When the comparison result indicates that the difficulty level of the current task is greater than or equal to the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be distributed control. When the comparison result indicates that the difficulty level of the current task is less than the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be centralized control; the historical task data includes historical task areas and historical task execution counts; determining the difficulty level of the current task based on the historical task data, the current task area, and the current task type includes: The scope of the historical task area is overlaid and analyzed to determine the familiarity with the first task corresponding to each sub-region in the historical task area. Based on the number of times the historical tasks were executed, the execution status of multiple historical task types was analyzed to determine the familiarity with the second task corresponding to each historical task type. Obtain the region ratio of the sub-region in the current task region, and combine the region ratio with the second task familiarity level corresponding to the current task type and the first task familiarity level corresponding to the sub-region to determine the difficulty level of the current task.

2. The cluster control method for underwater unmanned equipment as described in claim 1, characterized in that, The historical task region includes multiple regions corresponding to historical tasks. The process of overlaying and analyzing the range of the historical task region to determine the familiarity level of the first task corresponding to each sub-region within the historical task region includes: The ranges of the areas corresponding to the multiple historical tasks are marked; Based on the range of the regions corresponding to the marked historical tasks, the overlapping ranges are superimposed to obtain multiple sub-regions; The familiarity with the first task corresponding to each sub-region is determined based on the total number of times the multiple sub-regions are superimposed and the number of times each sub-region is superimposed.

3. The cluster control method for underwater unmanned equipment as described in claim 1, characterized in that, The historical task execution count includes the execution counts of multiple historical task types. The step of analyzing the execution status of multiple historical task types based on the historical task execution counts to determine the familiarity with the second task corresponding to each historical task type includes: The total number of times the historical task was executed is determined based on the number of times the various historical task types were executed. The execution count of each historical task type is compared with the total number of historical task executions to obtain the second task familiarity level corresponding to each historical task type.

4. The cluster control method for underwater unmanned equipment as described in claim 1, characterized in that, The step of controlling the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control method includes: When the underwater unmanned equipment cluster control mode is distributed control, the target number of underwater unmanned equipment is determined based on the historical task data and the current task type. Acquire signal data and environmental water flow data corresponding to multiple candidate underwater unmanned devices, and determine the assignment priority corresponding to each candidate underwater unmanned device based on the signal data and environmental water flow data; Based on the number of target underwater unmanned devices and the assignment priority of each candidate underwater unmanned device, a target underwater unmanned device is determined from the plurality of candidate underwater unmanned devices, so that the target underwater unmanned device performs the current task in the current task area.

5. The cluster control method for underwater unmanned equipment as described in claim 4, characterized in that, The step of determining the number of target underwater unmanned devices based on the historical mission data and the current mission type includes: Based on the historical mission data, determine the number of underwater unmanned devices corresponding to multiple historical mission types; The current task type is matched with the multiple historical task types, and the number of underwater unmanned devices corresponding to the matched historical task types is used as the reference number of underwater unmanned devices for the current task type. The average number of reference underwater unmanned devices is taken as the target number of underwater unmanned devices.

6. The cluster control method for underwater unmanned equipment as described in claim 4, characterized in that, The step of determining the assignment priority of each candidate underwater unmanned device based on the signal data and environmental water flow data includes: Based on the signal data, the communication signal strength of the candidate underwater unmanned equipment within the target time period is determined, and the fluctuation analysis of the communication signal strength is performed to obtain the signal stability degree corresponding to each candidate underwater unmanned equipment. Based on the environmental water flow data, the water flow direction and velocity are determined, and the changes in the water flow direction and velocity are analyzed to obtain the environmental friendliness of each candidate underwater unmanned device. By combining the signal stability and environmental friendliness, the assignment priority corresponding to each candidate underwater unmanned device is obtained.

7. The cluster control method for underwater unmanned equipment as described in claim 6, characterized in that, The analysis of changes in the water flow direction and velocity to obtain the environmental friendliness of each candidate underwater unmanned device includes: Based on the water flow velocity, construct a time-series-based curve of water flow velocity variation. Based on the water flow velocity variation curve, multiple extreme points were determined; Obtain the difference in water flow velocity and time between the extreme point and its adjacent extreme points, and determine the difference in water flow direction between the extreme point and its adjacent extreme points based on the water flow direction. The degree of water flow velocity interference is determined based on the difference in water flow velocity and time difference between the extreme point and the adjacent extreme point. The degree of interference in the direction of water flow is determined based on the difference in water flow velocity and the difference in water flow direction between the extreme point and the adjacent extreme points. Based on the degree of interference from the water flow velocity and the degree of interference from the water flow direction, the environmental friendliness level corresponding to each candidate underwater unmanned device is obtained.

8. A cluster control system for underwater unmanned equipment, characterized in that, The system includes: The data acquisition module is used to acquire historical mission data, current mission area, and current mission type of the underwater unmanned equipment. The difficulty level determination module is used to determine the difficulty level of the current task based on the historical task data, the current task region, and the current task type. The control mode determination module is used to compare the difficulty level of the current task with a preset difficulty level threshold, and determine the control mode of the underwater unmanned equipment cluster based on the comparison result. The cluster control module is used to control the underwater unmanned equipment to perform the current task in the current task area according to the underwater unmanned equipment cluster control mode; The step of determining the underwater unmanned equipment cluster control method based on the comparison results includes: When the comparison result indicates that the difficulty level of the current task is greater than or equal to the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be distributed control. When the comparison result indicates that the difficulty level of the current task is less than the preset difficulty level threshold, the underwater unmanned equipment cluster control mode is determined to be centralized control. The historical task data includes historical task regions and the number of times historical tasks were executed. Determining the difficulty level of the current task based on the historical task data, the current task region, and the current task type includes: The scope of the historical task area is overlaid and analyzed to determine the familiarity with the first task corresponding to each sub-region in the historical task area. Based on the number of times the historical tasks were executed, the execution status of multiple historical task types was analyzed to determine the familiarity with the second task corresponding to each historical task type. Obtain the region ratio of the sub-region in the current task region, and combine the region ratio with the second task familiarity level corresponding to the current task type and the first task familiarity level corresponding to the sub-region to determine the difficulty level of the current task.

Images