Overwater and underwater topographic survey method based on cooperation of unmanned ship and unmanned aerial vehicle

Abstract

The invention relates to the technical field of topographic survey, in particular to an overwater and underwater topographic survey method based on cooperation of an unmanned ship and an unmanned aerial vehicle. The method comprises the following steps: acquiring platform parameter data of an unmanned ship and an unmanned aerial vehicle; according to the platform parameter data, isomerization grouping based on the residual electric quantity, the communication signal strength, the cruising ability and the measurement precision is carried out, a collaborative formation scheme is determined according to a preset water area measurement task sequence, and collaborative parameter data is obtained; acquiring environment data of a measurement area; and performing regional division modeling based on water area topographic features and environmental complexity according to the environmental data of the measurement region, and applying the collaborative parameter data to a regional model to obtain a topological model of the measurement region. The unmanned ship is used as a mobile charging platform, real-time electric quantity monitoring and docking charging mechanisms are combined, the endurance guarantee of the unmanned aerial vehicle is realized through energy supply strategy optimization, and the continuity and stability of tasks are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of topographic surveying, and particularly to a method for water and underwater topographic surveying based on the cooperation of an unmanned ship and an unmanned aerial vehicle. Background Art

[0002] An unmanned ship, also known as an Autonomous Surface Vehicle (ASV), is a ship that can perform functions such as navigation, guidance, perception, and obstacle avoidance through its own sensors, controllers, propulsion systems, etc. without direct human operation. An unmanned ship is a type of surface robot that mainly realizes autonomous navigation through intelligent control. It is a complex system involving multiple professional fields such as ship design, communication transmission, environmental perception, data fusion, motion control, human-computer interaction, and artificial intelligence. An unmanned aerial vehicle (UAV) is an unpiloted aircraft controlled by a radio remote control device or a self-contained program control device. The method for water and underwater topographic surveying based on the cooperation of an unmanned ship and an unmanned aerial vehicle is an advanced surveying and mapping method integrating aerial and surface surveying technologies.

[0003] However, the current methods for water and underwater topographic surveying using the cooperation of an unmanned ship and an unmanned aerial vehicle often have the following problems: The task collaborative allocation of the unmanned ship and the unmanned aerial vehicle needs to consider multiple constraints (such as remaining battery power, communication signal strength, terrain complexity, etc.), and it is difficult for traditional algorithms to achieve dynamic optimal path planning; In complex waters, the unmanned aerial vehicle may be unable to complete the task due to battery depletion, and the movement speed of the unmanned ship is relatively slow. How to reasonably allocate the measurement areas of the two to avoid duplication and omission is a key difficulty. The endurance capabilities of the unmanned ship and the unmanned aerial vehicle in complex environments are limited, and insufficient energy management strategies may lead to the equipment running out of power before the task is completed; The unmanned aerial vehicle may only be able to fly continuously for 30 minutes in high power consumption mode and is difficult to cover the target area and return to the charging station in vast waters. Although the endurance time of the unmanned ship is long, its movement speed is slow. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide a method for water and underwater topographic surveying based on the cooperation of an unmanned ship and an unmanned aerial vehicle to solve at least one of the above technical problems.

[0005] To achieve the above objective, a method for water and underwater topographic surveying based on the cooperation of an unmanned ship and an unmanned aerial vehicle includes the following steps: Step S1: Obtain the platform parameter data of the unmanned ship and the unmanned aerial vehicle; perform heterogeneous grouping based on the remaining battery power, communication signal strength, endurance capability, and measurement accuracy according to the platform parameter data, and determine the collaborative formation plan according to the preset water area measurement task sequence to obtain the collaborative parameter data; Step S2: Obtain the environmental data of the measurement area; perform regional division modeling based on the water area terrain features and environmental complexity according to the environmental data of the measurement area, and apply the collaborative parameter data to the regional model to obtain the topological model of the measurement area; optimize the sub-region task allocation for the topological model of the measurement area to obtain the collaborative measurement task allocation scheme; Step S3: Construct a fuzzy logic path planning model according to the collaborative measurement task allocation scheme, and perform dynamic path optimization based on the platform status data obtained from real-time monitoring to obtain the collaborative measurement path planning scheme with minimum repeated coverage and omission; Step S4: Use the unmanned boat as a mobile charging platform, trigger the fast docking charging or battery swapping mechanism according to the remaining power of the drone in the platform status data and the preset power threshold, and optimize the timing and location of energy replenishment according to the collaborative measurement path planning scheme to obtain the dynamic energy replenishment strategy data; Step S5: Perform real-time scheduling of the collaborative tasks of the unmanned boat and the drone according to the dynamic energy replenishment strategy data, the collaborative measurement path planning scheme, and the collaborative measurement task allocation scheme, so as to realize the topographic survey of the water surface and underwater.

[0006] The present invention groups and manages heterogeneous devices by obtaining platform parameters such as the remaining power, communication signal strength, endurance, and measurement accuracy of unmanned boats and drones. Heterogeneous grouping enables different devices to play their respective advantages during task execution. For example, unmanned boats provide stable platform support, and drones are responsible for flexible aerial measurement. According to the preset measurement task sequence and device capabilities, a formation plan is determined to avoid problems such as waste of device capabilities or poor task adaptation. The obtained collaborative parameter data provides a unified formation benchmark for subsequent steps. Combining the measurement area environmental data, through regional division modeling of water area terrain features and environmental complexity, the characteristics of the measurement area can be accurately characterized, ensuring that the measurement plan adapts to complex environments. Regional modeling reduces repeated measurements and omissions, improving measurement accuracy and coverage. Applying the collaborative parameter data to the regional model, a topological model of the measurement area is generated, and sub-region task optimization allocation is carried out. The optimized task allocation scheme effectively avoids device task conflicts, reasonably allocates resources, and improves collaborative efficiency. The fuzzy logic path planning model can dynamically adjust the measurement path according to the task objective and real-time monitored device status data, solving the problem of poor adaptability of traditional path planning methods to environmental changes and ensuring more flexible and efficient path planning. The optimized path planning scheme significantly reduces the repeated coverage or omission phenomena that occur during the measurement of unmanned boats and drones, improving measurement efficiency and data integrity. The dynamic optimization mechanism ensures that even when device status changes (such as insufficient power, weak signal, etc.) occur during task execution, the path can be quickly adjusted to ensure the smooth completion of the task. Using the unmanned boat as a mobile charging platform, by real-time monitoring the remaining power of the drone, the fast docking charging or battery replacement mechanism is intelligently triggered, effectively solving the problem of insufficient endurance of the drone. The introduction of the dynamic replenishment strategy reduces the risk of task interruption and improves the continuity of collaborative measurement. Optimizing the replenishment timing and location according to the collaborative measurement path planning scheme avoids resource waste caused by frequent replenishment or over-replenishment, while improving the efficiency and reliability of task completion. The organic combination of the dynamic energy replenishment strategy, path planning scheme, and task allocation scheme realizes real-time scheduling and precise collaboration between unmanned boats and drones, enhancing the overall execution ability of the system. Coordinating water surface and underwater measurement tasks, using the unmanned boat to support the underwater measurement function on the water surface and the drone to provide aerial assistance to form a complete measurement link; systematic collaborative operation can significantly improve the accuracy, speed, and coverage of terrain measurement. Through real-time scheduling, emergencies or environmental changes (such as sudden bad weather, equipment failures, etc.) can be responded to, ensuring that the measurement task can be adjusted in a timely manner and completed smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments read with reference to the accompanying drawings: Figure 1This is a schematic diagram of the step process of the method for measuring water and underwater terrain based on the cooperation of an unmanned ship and an unmanned aerial vehicle in the present invention; Figure 2 is Figure 1 a detailed schematic diagram of the step S1 in Figure 3 is Figure 1 a detailed schematic diagram of the step S2 in Specific embodiments

[0008] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts belong to the scope of protection of the present invention.

[0009] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0010] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0011] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for measuring water and underwater terrain based on the cooperation of an unmanned ship and an unmanned aerial vehicle, and the method includes the following steps: In an embodiment of the present invention, referring to Figure 1 shown, this is a schematic diagram of the step process of a method for measuring water and underwater terrain based on the cooperation of an unmanned ship and an unmanned aerial vehicle in the present invention. In this example, the method for measuring water and underwater terrain based on the cooperation of an unmanned ship and an unmanned aerial vehicle includes the following steps: Step S1: Obtain the platform parameter data of the unmanned ship and the unmanned aerial vehicle (UAV); perform heterogeneous grouping based on the remaining battery power, communication signal strength, endurance, and measurement accuracy according to the platform parameter data, and determine the cooperative formation plan according to the preset water area measurement task sequence to obtain the cooperative parameter data; In an embodiment of the present invention, in a complex water area measurement task, the key platform parameter data of the unmanned ship and the UAV are obtained, including the maximum flight time of the UAV (30 minutes), the signal coverage radius (5 kilometers), and the maximum navigation endurance time of the unmanned ship (12 hours) and the communication stability parameter. According to the remaining battery power of the UAV (80% - 20%) and the communication signal strength (RSSI value - 50dBm), as well as the endurance of the unmanned ship and the accuracy of the high-precision laser rangefinder sensor carried by the UAV (1 cm), heterogeneous grouping is performed, and the high-precision UAV is preferentially assigned to the complex measurement area. Combining the preset measurement task sequence, such as water depth measurement, terrain modeling, etc., the cooperative formation plan is determined, and the cooperative method of setting the unmanned ship to dominate the surface measurement and provide relay signal support for the UAV is set, and the cooperative parameter data is output for subsequent area modeling and task allocation.

[0012] Step S2: Obtain the measurement area environment data; perform regional division and modeling based on the water area terrain features and environmental complexity according to the measurement area environment data, and apply the cooperative parameter data to the regional model to obtain the measurement area topological model; perform sub-region task allocation optimization on the measurement area topological model to obtain the cooperative measurement task allocation plan; In an embodiment of the present invention, for the target water area environment, the high-resolution images collected by the UAV and the data of the sonar system carried by the unmanned ship are used to obtain the terrain features of the water area (such as shoals, deep trenches, reefs, etc.) and the environmental complexity (such as wind speed 10 m / s, flow rate 1.2 m / s). Based on this data, the water area is divided into regions through a clustering algorithm, a regional model including deep water areas, complex terrain areas, and shoal areas is established, and the cooperative parameter data is applied to the model. The sub-region task allocation of the measurement area topological model is optimized through an optimization algorithm. For example, the shoal area is assigned to the UAV with weaker endurance, while the complex terrain area is assigned to the combination of the unmanned ship and the UAV with stronger signal transmission ability, and finally the optimal cooperative measurement task allocation plan is obtained.

[0013] Step S3: Construct a fuzzy logic path planning model according to the cooperative measurement task allocation plan, and perform path dynamic optimization based on the platform status data obtained by real-time monitoring to obtain the cooperative measurement path planning plan with the least repeated coverage and omission; In the embodiments of the present invention, a cooperative measurement task allocation scheme is utilized to construct a fuzzy logic path planning model. The subtask and path planning are input into the model, and the path is dynamically optimized according to the real-time state data of the unmanned aerial vehicle (such as 15% remaining flight power and 5° heading deviation). By combining the A* algorithm and real-time monitoring data, the optimal flight path of the unmanned aerial vehicle and the optimal navigation path of the unmanned ship are generated, ensuring that the path coverage rate is above 98% and the repeated coverage rate is controlled below 2%. For example, the unmanned aerial vehicle preferentially measures the central area of the complex area and covers the peripheral boundary area with a polygon coverage strategy, and finally outputs a cooperative measurement path planning scheme that reduces repeated coverage and omissions.

[0014] Step S4: Regarding the unmanned ship as a mobile charging platform, trigger a fast docking charging or battery exchange mechanism according to the remaining power of the unmanned aerial vehicle in the platform state data and a preset power threshold, and optimize the timing and location of energy replenishment according to the cooperative measurement path planning scheme to obtain dynamic energy replenishment strategy data; In the embodiments of the present invention, when the power of the unmanned aerial vehicle is lower than a set threshold (such as 30%), the unmanned ship enables the mobile charging function. The unmanned ship calculates the optimal charging docking point according to the real-time position and flight trajectory of the unmanned aerial vehicle in the platform state data. In a specific task, when it is predicted that the unmanned aerial vehicle will run out of power within 5 minutes and the distance to the nearest unmanned ship is 2 kilometers, a fast charging docking mechanism is triggered, and the battery is replaced within 3 minutes after docking or charged by 50% using a magnetic interface. At the same time, adjust the charging position and travel time of the unmanned ship according to the cooperative measurement path planning scheme, so as to optimize the energy replenishment strategy and ensure that the unmanned aerial vehicle continues to operate without deviating from the measurement task.

[0015] Step S5: According to the dynamic energy replenishment strategy data, the cooperative measurement path planning scheme, and the cooperative measurement task allocation scheme, perform real-time scheduling on the cooperative tasks of the unmanned ship and the unmanned aerial vehicle, so as to realize topographic survey on water and underwater.

[0016] In the embodiments of the present invention, based on the dynamic energy replenishment strategy data, the cooperative measurement path planning scheme, and the cooperative measurement task allocation scheme, a task scheduling algorithm is used to perform real-time scheduling on the tasks of the unmanned ship and the unmanned aerial vehicle. For example, in a shoal area, after the unmanned aerial vehicle completes the measurement task and needs to return to replenish power, and the endurance of the unmanned ship allows it to continue working, the system assigns the unmanned ship to take over the remaining measurement tasks in the shoal and simultaneously support the unmanned aerial vehicle to complete the measurement of the complex area. By coordinating the real-time positions, task states, and environmental data of the unmanned aerial vehicle and the unmanned ship, finally realize efficient and accurate topographic survey on water and underwater in the measurement area, with a measurement accuracy of more than 95% and a time efficiency improvement of 30%.

[0017] Preferably, step S1 includes the following steps: Step S11: Collect the remaining power, communication signal strength, current endurance, and measurement device status parameters of the hardware equipment of the unmanned ship to obtain the unmanned ship platform parameter data; Step S12: Obtain the unmanned aerial vehicle platform parameter data, including the remaining flight power, flight endurance, current communication signal quality, and sensor working status information of the unmanned aerial vehicle; Step S13: Upload the unmanned ship platform parameter data and the unmanned aerial vehicle platform parameter data to the measurement and control center through the data transmission interface to obtain the platform parameter data; Step S14: Denoise the platform parameter data and perform time synchronization processing to obtain the standardized platform parameter data; Step S15: Perform heterogeneous grouping based on the remaining power, communication signal strength, endurance, and measurement accuracy according to the standardized platform parameter data to obtain the heterogeneous grouping scheme data; Step S16: Generate a collaborative formation plan according to the preset water area measurement task sequence and the heterogeneous grouping scheme data to obtain the collaborative parameter data.

[0018] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow diagram of Step S1 in Step S11: Collect the remaining power, communication signal strength, current endurance, and measurement device status parameters of the hardware equipment of the unmanned ship to obtain the unmanned ship platform parameter data; In the embodiment of the present invention, the unmanned ship collects the hardware status parameters through its embedded control module and sensors. For example, the remaining power is 70%, the communication signal strength is -80 dBm, the current endurance is 6 hours, and the measurement device status is "normal operation". These data are collected in real time through the RS-485 interface and stored by the data recording module. The collection frequency is set to once per minute to ensure real-time performance. To verify the data accuracy, the collected data of the battery management system (BMS) and the signal strength receiving module are cross-checked through the system self-check program, and finally an unmanned ship platform parameter data file including power, signal strength, endurance time, and measurement device status is generated.

[0019] Step S12: Obtain the unmanned aerial vehicle platform parameter data, including the remaining flight power, flight endurance, current communication signal quality, and sensor working status information of the unmanned aerial vehicle; In the embodiment of the present invention, the drone collects platform parameter data through the sensor module integrated in the flight control system. For example, the remaining flight power is 50%, the endurance is 25 minutes, the current communication signal quality is -70 dBm, and the status of the optical sensor is "working properly". During the collection process, the battery voltage and current data are obtained through the I2C interface on the drone flight control board to calculate the remaining power; the signal quality is measured in real time through the communication module; the device working status is obtained through the sensor status monitoring interface. These data are stored in JSON format and recorded in the flight control log file with a sampling interval of 30 seconds.

[0020] Step S13: Upload the unmanned ship platform parameter data and the drone platform parameter data to the measurement and control center through the data transmission interface, so as to obtain the platform parameter data; In the embodiment of the present invention, the unmanned ship and the drone upload the platform parameter data to the measurement and control center through the data transmission interface. For example, the LoRa wireless communication module is used to transmit data in the 2.4 GHz frequency band, and the communication distance is within 5 kilometers. The unmanned ship and the drone send data packets to the measurement and control center every minute. The content of the data packet includes the platform status, device status, and location information. The measurement and control center uses a multi-threaded listening program on the server of the receiving site to receive the data, parse the uploaded JSON file, merge the data streams of the unmanned ship and the drone, and finally generate a complete multi-platform parameter data file.

[0021] Step S14: Denoise the platform parameter data and perform time synchronization processing to obtain the standardized platform parameter data; In the embodiment of the present invention, the platform parameter data is processed. First, the wavelet denoising algorithm is used to filter out the noise generated during the transmission process. For example, the abnormally fluctuating values in the communication signal strength are removed (such as the interference data that drops to -110 dBm in a short time). Then, through the time synchronization module, based on the GPS timestamp, the data records of the unmanned ship and the drone are time-aligned. During the processing, a tolerance threshold of 0.5 seconds is selected to ensure the consistency of the data time sequence. After processing, a time-series platform parameter data in a standard format is generated for subsequent grouping and formation calculation.

[0022] Step S15: Perform heterogeneous grouping based on the remaining power, communication signal strength, endurance, and measurement accuracy according to the standardized platform parameter data to obtain the heterogeneous grouping scheme data; In an embodiment of the present invention, standardized platform parameter data is utilized to perform heterogeneous grouping based on a multi-attribute decision-making method. For example, weight values (0.4, 0.3, 0.2, and 0.1 respectively) are assigned to the remaining battery power, communication signal strength, endurance, and measurement accuracy, and the comprehensive score is calculated through weighted summation. The unmanned boats and unmanned aerial vehicles are grouped according to the sorted comprehensive scores. For example, they are divided into three groups: the high-battery long-endurance group, the medium-battery group, and the low-battery group, to ensure the highest collaborative measurement efficiency of platforms with different characteristics, and finally generate heterogeneous grouping scheme data.

[0023] Step S16: Generate a collaborative formation plan according to the preset water area measurement task sequence and the heterogeneous grouping scheme data, so as to obtain collaborative parameter data.

[0024] In an embodiment of the present invention, according to the preset water area measurement task sequence, for example, the target tasks include regions A, B, and C, and the priority is A > B > C, and in combination with the heterogeneous grouping scheme data, a genetic algorithm is used to generate a collaborative formation plan. During the calculation process, the maximization of the measurement coverage range and the optimization of the signal coverage are used as the objective functions, and the constraints are the endurance and real-time measurement accuracy of the unmanned boats and unmanned aerial vehicles. In an actual scenario, the unmanned boats are assigned to the deep water area A, and the unmanned aerial vehicles are assigned to the shallow water area B and the tidal flat area C. The generated collaborative parameter data includes the detailed planning of task allocation, formation formation, and communication liaison nodes.

[0025] The present invention collects the remaining power, communication signal strength, endurance, and measurement device status of the unmanned ship, enabling a comprehensive understanding of its current operating conditions and task execution capabilities; such refined collection provides accurate basic data for subsequent task planning, contributing to improving the reliability of the overall system decision-making; through the real-time collection of the remaining power and device status, potential faults or mission interruption risks can be quickly identified and avoided during the planning stage. Collecting the remaining power, endurance, communication signal quality, and sensor working status of the unmanned aerial vehicle can accurately determine the available time, flight ability, and environmental adaptability of the unmanned aerial vehicle; such comprehensive collection can provide more targeted data support for collaborative measurement task allocation and formation optimization. The real-time acquisition of the communication signal quality can evaluate the working ability of the unmanned aerial vehicle in a complex communication environment, optimize its execution plan in advance, and reduce the impact of signal interruption or delay. The parameter data of the unmanned ship and the unmanned aerial vehicle are uploaded to the measurement and control center through the data transmission interface, forming a centralized data processing mode, which is convenient for unified management and real-time analysis. Centralized processing can avoid data one-sidedness or errors caused by single-node decision-making, and improve the overall system collaboration efficiency. Centralized uploading enables the measurement and control center to receive the changing data of the platform status in real time, providing efficient support for subsequent task planning and adjustment. Through data denoising processing, interference factors and noise in the original data are eliminated, ensuring that the data for subsequent task planning is more accurate and reliable. Time synchronization processing ensures the unity of the status data of the unmanned ship and the unmanned aerial vehicle under the same time reference, making subsequent heterogeneous grouping and task formation more accurate and coordinated. Standardization processing solves the problem of inconsistent data formats of different platforms, reducing decision-making errors caused by data differences. Heterogeneous grouping based on the remaining power, communication signal strength, endurance, and measurement accuracy can select the most suitable device combination for different tasks, giving full play to the performance advantages of the devices. Heterogeneous grouping ensures the device adaptability and execution efficiency of the measurement task, and improves the mission success rate. Through grouping optimization, the problem of capacity conflict or mismatch between devices is reduced, enhancing the fluency and efficiency of collaborative execution. According to the water area measurement task sequence and the heterogeneous grouping scheme, a collaborative formation scheme is generated, making the task allocation more scientific and reasonable, avoiding resource waste and duplicate labor. The collaborative parameter data provides a clear collaboration framework for subsequent path planning and task execution. The formation scheme combines device performance and task requirements, and can flexibly adapt to multi-task execution in a complex measurement environment, ensuring the comprehensiveness and accuracy of the measurement. The formation scheme fully considers the collaboration and redundancy design between devices in task planning, improving the anti-interference ability and robustness of the system, and ensuring the successful completion of the task.

[0026] Preferably, step S15 includes the following steps: Step S151: Set the priority weights of parameter indicators according to the standardized platform parameter data, where the remaining battery power has the highest weight, followed by communication signal strength, endurance, and measurement accuracy, so as to form grouped weight configuration parameters; In the embodiment of the present invention, weight indicators are set according to the standardized platform parameter data. First, weights are set for the four parameters of remaining battery power, communication signal strength, endurance, and measurement accuracy according to the task requirements. For example, the weight of the remaining battery power is 0.4, the weight of the communication signal strength is 0.3, the weight of the endurance is 0.2, and the weight of the measurement accuracy is 0.1. On this basis, combined with the preset task requirement table, for example, it is required that the endurance has a higher proportion in the far measurement area, so the endurance weight is adjusted to 0.25 specifically for the deep-water area task. A grouped weight configuration parameter file is generated through the weight configuration program and stored in the grouped parameter library of the task planning system to ensure that the weight configuration can be flexibly adjusted for different task scenarios.

[0027] Step S152: Use the clustering algorithm to calculate the heterogeneity scores of each platform device based on the grouped weight configuration parameters, and divide the devices into multiple cooperative task execution groups, so as to obtain preliminary grouped scheme data, where the heterogeneity score = the normalized value of the device's remaining battery power × remaining battery power weight + the normalized value of the communication signal strength × communication signal strength weight + the normalized value of the endurance × endurance weight + the normalized value of the measurement accuracy × measurement accuracy weight; In the embodiment of the present invention, the K-means clustering algorithm is used to group each platform device. First, the standardized data of remaining battery power, communication signal strength, endurance, and measurement accuracy are normalized. For example, the remaining battery power range is mapped to the [0, 1] interval. Then, the heterogeneity score of each platform device is calculated. For example, the heterogeneity score of a certain unmanned ship is calculated as: the normalized value of the remaining battery power 0.8 × weight 0.4 + the normalized value of the communication signal strength 0.6 × weight 0.3 + the normalized value of the endurance 0.7 × weight 0.2 + the normalized value of the measurement accuracy 0.9 × weight 0.1 = 0.76. According to the heterogeneity scores, the devices are divided into three groups using the K-means algorithm, with the smallest difference in heterogeneity scores within the groups and the largest difference between the groups. The preliminary grouped scheme data is stored in the CSV format, where the grouped number and score of each device are recorded.

[0028] Step S153: Perform an equilibrium consistency check based on multiple indicators on the preliminary grouped scheme data, and perform grouped optimization and adjustment to obtain optimized grouped scheme data; In the embodiments of the present invention, the initial grouping scheme data is subjected to balanced consistency check, and the mean and variance of the indexes within the group are calculated. For example, for a certain group, the mean of the remaining battery power within the group is calculated to be 0.75 and the variance is 0.02, and it is determined that its consistency is good; if the variance of the communication signal strength of a certain group exceeds the threshold (such as 0.05), it needs to be readjusted. The grouping is adjusted by a genetic algorithm based on multi-objective optimization, and some high-score devices are reallocated to weak groups to achieve the purpose of balance. For example, drones with excellent signal strength are reallocated to task groups with poor communication coverage. Finally, the optimized grouping scheme data is output, and the task adaptability score of each group is marked and stored in the grouping optimization library of the task planning system.

[0029] Step S154: According to the optimized grouping scheme data, as well as the current geographical location and the starting state of task execution of the platform devices, determine the collaborative numbers and allocation orders of the grouped devices, so as to obtain the heterogeneous grouping scheme data.

[0030] In the embodiments of the present invention, according to the optimized grouping scheme data and the geographical location information of each device, the task planning system generates a collaborative number and a task order for each device. For example, in combination with the real-time GPS coordinates and the starting task state, the unmanned ship near the deep water area and the drone in the signal coverage area are preferentially numbered as group A, and their task execution order is set as "preferably measure area A". The system optimizes the task allocation path through a greedy algorithm to ensure that the collaborative numbers and grouped tasks maximize the satisfaction of the measurement coverage rate and time benefit requirements. Finally, the heterogeneous grouping scheme data, including device numbers, task orders and task area allocations, is generated and stored in JSON format for subsequent calls by the path planning module.

[0031] The remaining battery power of the present invention is set as the highest weight, ensuring that the device can prioritize sufficient power when performing tasks and reducing the risk of task interruption; arranging other indicators (communication signal strength, endurance, and measurement accuracy) according to priority can comprehensively consider the device performance and task requirements, providing a scientific basis for subsequent grouping. The flexibility of weight configuration enables the system to adjust priorities according to different task scenarios (such as long-term navigation tasks, complex communication environments, etc.), enhancing the adaptability of task execution. The setting of weights provides a quantitative standard for the calculation of heterogeneous scores, reducing the influence of human subjective factors and improving the objectivity and accuracy of the grouping process. The heterogeneous scores calculated using normalization and weights can intuitively reflect the comprehensive performance and task adaptability of the device, providing a quantitative reference for device grouping; the heterogeneous score formula comprehensively considers various performance indicators, ensuring that the grouping basis is comprehensive and scientific. The automatic grouping of devices is achieved through a clustering algorithm, greatly improving the grouping efficiency and adapting to the complex task requirements of multi-device collaboration; the clustering algorithm can divide task groups according to the similarity of scores, ensuring the performance complementarity and task synergy of the grouped devices. The preliminary grouping optimally combines devices with different performances, giving full play to the unique advantages of the devices while reducing resource waste. The multi-index equilibrium consistency check performs a refined verification on the preliminary grouping, ensuring the balance and adaptability of the device performance within each group and improving the grouping quality; the optimization adjustment can correct the problem of over-reliance on a single indicator that may exist in the preliminary grouping, making the grouping more reasonable. The optimized grouping scheme ensures that the devices within each group complement each other in performance, enhancing the overall efficiency during the execution of collaborative tasks; the load balance during task execution is improved, avoiding the impact of some devices being overloaded or having insufficient performance on the overall task process. The optimized grouping not only considers the current task but also has a certain degree of generality, adapting to the possible dynamic task adjustment requirements in the future. The collaborative number and allocation order are determined according to the optimized grouping scheme, the device geographical location, and the starting state, making the task allocation clearer and reducing the chaos during resource scheduling; after the number and order are clear, a reliable operation basis is provided for the real-time scheduling of the device. The grouped devices work collaboratively according to the number and order, which can minimize resource waste and task delay caused by location or state differences; the reasonable allocation order optimizes the time and space coordination of collaborative work. The collaborative number and allocation order can be dynamically adjusted during the task execution process, adding redundant design to the system and improving the fault tolerance and robustness of task execution.

[0032] Preferably, step S16 includes the following steps: Step S161: Extract information on the time sequence, area division, measurement depth requirements, and accuracy standards of the task according to the preset water area measurement task sequence, so as to obtain task sequence feature data; In an embodiment of the present invention, task feature information is extracted according to a water area measurement task sequence. The system first reads a preset measurement task sequence configuration table, which includes a task execution time period (such as 8:00 - 12:00), a measurement area number (such as Area A to Area C), a target water depth range (such as 5 - 50 meters), and a measurement accuracy requirement (such as a depth measurement accuracy of ±0.5 meters). By parsing the task configuration table, the system extracts the time sequence, area division, measurement depth, and accuracy standard of the task, and performs structured processing on these parameters to generate a task sequence feature data file. Taking a specific task as an example, the feature data of Task A includes a time of "8:00 - 9:00", an area of "Deep Water Area A", a depth requirement of "20 - 50 meters", an accuracy standard of "±0.5 meters", and the data format is a JSON file for subsequent module calls.

[0033] Step S162: Based on the heterogeneous grouping scheme data, perform measurement requirement matching on the task sequence feature data, and determine the collaborative measurement task assignment situation for each group, so as to generate preliminary formation task assignment data; In an embodiment of the present invention, measurement requirement matching is performed on the task sequence feature data according to the heterogeneous grouping scheme data. The system first extracts the device characteristic data in the grouping scheme. For example, Group A includes 1 unmanned ship and 2 unmanned aerial vehicles. The device characteristics include the maximum endurance time of the unmanned ship being 10 hours, the effective communication radius of the unmanned aerial vehicle being 500 meters, and the measurement device accuracy being ±0.3 meters, etc. Then, by comparing the task feature data, the device capabilities and task requirements are matched. For example, if Task A requires deep water measurement, the system preferentially matches an unmanned ship with high endurance and deep water measurement capabilities, and assigns 2 unmanned aerial vehicles as communication and auxiliary measurement devices. Finally, preliminary formation task assignment data is generated. For example, Group A executes Task A, and the output content includes device numbers, assigned areas, and task priorities.

[0034] Step S163: Perform a feasibility analysis on the preliminary formation task assignment data based on the remaining power, endurance, communication range, and measurement device accuracy of the unmanned ship and the unmanned aerial vehicle, and screen out the device groups that meet the task execution conditions, so as to generate task device matching data; In an embodiment of the present invention, a feasibility analysis is performed on the preliminary formation task assignment data. The system checks the assignment results based on the remaining power, endurance, communication range, and measurement device accuracy of the unmanned ship and the unmanned aerial vehicle. For example, if the current remaining power of a certain unmanned aerial vehicle is 30%, which is not enough to complete the measurement range of Task A, the task priority is re - assigned or the device is replaced. The system uses a Constraint Satisfaction Problem (CSP) algorithm to simulate the task execution process and screen out the device groups that meet the conditions. For example, finally, an unmanned ship with a remaining power higher than 70% and two unmanned aerial vehicles with an endurance exceeding 90 minutes are selected as the execution device group for Task A. The task device matching data records each group of devices and their task suitability scores, and outputs them for use by the subsequent path optimization module.

[0035] Step S164: Preliminarily optimizing the equipment position and navigation path of the collaborative formation based on the task equipment matching data, thereby generating preliminary formation plan data; The embodiment of the present invention performs preliminary optimization of the formation equipment position and navigation path based on the task equipment matching data. The system uses the geographic information data of the task execution area (such as water depth distribution, obstacle location) and the current coordinates of the equipment, combined with the A* path planning algorithm to generate the navigation path of the unmanned ship and the drone. For example, to perform task A, the system plans the unmanned ship to move along the edge of the deep water area from the starting point, and the drone synchronously covers the communication blind spots in the task area to ensure real-time data transmission. The preliminary formation plan data includes the initial position of the equipment, navigation path points, path length and estimated energy consumption, and is output in XML format for dynamic simulation module calls.

[0036] Step S165: Dynamically simulate and verify the preliminary formation plan data, evaluate the task execution efficiency, path coverage and communication stability of the collaborative formation in different water measurement scenarios, identify potential bottlenecks and make adjustments and optimizations, so as to obtain optimized formation plan data; The embodiment of the present invention performs dynamic simulation verification on the preliminary formation plan data. The system loads the water geographical model and equipment characteristic parameters in the simulation environment, and simulates the task execution efficiency, path coverage and communication stability in different scenarios through simulation software. For example, in complex waters (such as deep water areas with many obstacles), the system evaluates whether the current formation plan will cause repeated path coverage or communication interruption. If it is found that the efficiency of a certain drone is affected by a communication blind spot, its path is adjusted or relay equipment support is added. After identifying the bottleneck problem through simulation results, the navigation path and equipment formation are adjusted, and finally the formation plan data is optimized to ensure that the measurement efficiency is improved by more than 10%.

[0037] Step S166: Determine the formation, communication protocol and task allocation strategy of the unmanned ship and the unmanned aerial vehicle according to the optimized formation plan data, so as to obtain the coordination parameter data.

[0038] The embodiment of the present invention determines the formation and task allocation strategy of unmanned ships and drones based on the optimized formation plan data. The system first designs a star formation with the unmanned ship as the center based on the optimized equipment position and task sequence. The drones are distributed within the communication coverage range with a radius of 500 meters, and the communication protocol is set to enhance the stability of data transmission (for example, using an adaptive frequency band switching protocol). The task allocation strategy stipulates that the unmanned ship is mainly responsible for deep-water area measurements, and the drone is responsible for fine measurements in shallow water areas and real-time supplementation of communication blind spots. The collaborative parameter data finally generated includes formation plans, task allocation rules and communication protocol configurations, which are stored as database files for the scheduling module to call.

[0039] The present invention extracts key information such as the chronological order, regional division, measurement depth requirements, and accuracy standards of extraction tasks to ensure that key task requirements are not omitted during subsequent formation and allocation processes; the clear task feature data provides a sufficient reference basis for group matching, reducing task understanding deviations. Extracting multi-dimensional features can adapt to the requirements of different water area measurement tasks (such as shallow water, high-precision measurement, etc.), enhancing the task diversification ability of the system. The extraction of feature data realizes the standardization and structuring of task information, providing an easy-to-operate basic data format for subsequent task allocation and formation optimization. Based on the heterogeneous grouping scheme, it quickly matches task requirements to generate preliminary formation task allocation data, ensuring the rapid matching of tasks and equipment performance; reducing human intervention and achieving the intelligence and high efficiency of task allocation. Each equipment group matches according to its own performance and task characteristics, can give full play to the equipment capabilities, and avoid resource waste or uneven task allocation. Determine the preliminary allocation of collaborative measurement tasks, laying a foundation for subsequent formation plan optimization, and improving formation execution efficiency and task coverage. Based on the feasibility analysis of remaining power, endurance, communication range, and measurement equipment accuracy, eliminate equipment that cannot meet task requirements, enhancing the reliability and effectiveness of task allocation; avoiding situations where equipment fails or is interrupted due to insufficient performance during task execution. The matched equipment group has clear execution capabilities, ensuring the continuity and stability of tasks during actual execution; matching the equipment groups screened after feasibility analysis further optimizes resource allocation, improving the overall utilization rate of the system and task execution efficiency. Conduct preliminary optimization based on equipment matching data to generate a reasonable equipment position distribution and navigation path, reducing task duplicate coverage and measurement omissions, and improving efficiency; the preliminary optimized path avoids possible conflicts between equipment, providing a good foundation for subsequent dynamic optimization. Through the optimization of equipment positions and paths, improve the collaborative work efficiency of the formation, reduce equipment energy consumption, and extend the endurance time; the optimized formation plan can adapt to the requirements of different water area measurement tasks, such as complex terrain, dynamic environment, etc., providing support for the diversification of task scenarios. Evaluate the execution efficiency of the formation in different water area scenarios through simulation verification to ensure that the plan adapts to complex environments; dynamic simulation can discover bottleneck problems in the plan in advance, avoiding serious mistakes in actual tasks. Analyze path coverage and communication stability during simulation to ensure the comprehensiveness of tasks and the continuity of information transmission, and make adjustments and optimizations for possible bottlenecks to improve the overall task completion quality of the formation. The simulation verification results provide a reliability guarantee for the formation plan, and the optimized and adjusted plan is more robust and has enhanced ability to adapt to sudden environmental changes. Determine the formation formation of unmanned ships and unmanned aerial vehicles to make equipment cooperation more efficient, avoiding unnecessary equipment conflicts and path interferences; generate clear task allocation strategies to ensure that each equipment clearly understands its task objectives and execution steps. Develop appropriate communication protocols to ensure the stability and real-time nature of information interaction between equipment and improve the overall performance of collaborative work.The generation of collaborative parameter data integrates all the results of grouping, matching, optimization, and verification to ensure the efficient operation of the system from planning to execution.

[0040] Preferably, step S2 includes the following steps: Step S21: Obtain the environmental data of the measurement area, including water area terrain features, water depth distribution, water flow velocity, bottom geological composition, water body transparency, and geographical obstacle information; Step S22: Perform data fusion and standardization processing on the environmental data of the measurement area to establish a unified environmental data feature vector, where the environmental data feature vector includes water area terrain feature data, bottom geological data, and water flow velocity and water body transparency data; Step S23: Perform multi-scale and multi-dimensional terrain feature and complexity analysis on the measurement area based on the environmental data feature vector to construct a regional terrain complexity assessment model; Step S24: Divide the measurement area into several sub-areas with similar terrain features and measurement difficulties according to the regional terrain complexity assessment model, and establish a mapping of the topological relationship of the sub-areas to obtain the topological relationship data of the sub-areas; Step S25: Correlate and match the collaborative parameter data with the topological relationship data of the sub-areas, and construct a topological model of the measurement area including equipment capabilities, task constraints, and terrain features; Step S26: Use a multi-objective optimization algorithm to optimize the sub-area task allocation of the topological model of the measurement area based on the constraint conditions of measurement coverage, data consistency, energy efficiency, and measurement accuracy, so as to generate a collaborative measurement task allocation scheme.

[0041] As an embodiment of the present invention, refer to Figure 3 shown in Figure 1 is a detailed step flow diagram of step S2 in Step S21: Obtain the environmental data of the measurement area, including water area terrain features, water depth distribution, water flow velocity, bottom geological composition, water body transparency, and geographical obstacle information; In an embodiment of the present invention, environmental data of a measurement area is obtained. The system acquires information on water area environmental characteristics by integrating various sensing devices and external data sources. For example, a multi-beam echosounder is used to scan the water depth distribution, a high-resolution camera mounted on an unmanned aerial vehicle collects images of geographical obstacles, an underwater detector measures the bottom geological composition, a water flow monitor records the water flow velocity, and an optical sensor analyzes the water transparency. Taking an actual scenario as an example, for an inland lake with an area of 2 square kilometers, the water depth data collected by the system ranges from 3 to 15 meters, the water flow velocity is 0.5 m / s, the transparency is 3 meters, the geological composition is a sand and gravel mixed structure, and the geographical obstacles include 1 small island and several aquatic vegetation distributions. The multi-source data collected is finally saved as a unified environmental data file in the GeoJSON format.

[0042] Step S22: Perform data fusion and standardization processing on the environmental data of the measurement area, thereby establishing a unified environmental data feature vector, where the environmental data feature vector includes water area terrain feature data, bottom geological data, and water flow velocity and water transparency data; In an embodiment of the present invention, data fusion and standardization processing are performed on the obtained environmental data of the measurement area. The system uses a weighted fusion algorithm to align data from different sources in the spatial and temporal dimensions. For example, interpolation is used to generate regular grid data for the water depth data throughout the measurement area, and at the same time, normalization processing is performed on the water flow velocity and transparency data to adjust their numerical ranges to [0, 1] for subsequent analysis. Combining multi-dimensional environmental data, the system generates an environmental data feature vector, which includes water area terrain feature values (such as slope and elevation difference), bottom geological type codes (1.2 for sand and gravel mixture at the bottom), average water flow velocity (0.5), and average transparency (0.8). Finally, the feature vector data is output and stored in a table format, with each row representing the data features of a grid cell.

[0043] Step S23: Based on the environmental data feature vector, perform multi-scale and multi-dimensional terrain feature and complexity analysis on the measurement area, thereby constructing a regional terrain complexity assessment model; In an embodiment of the present invention, terrain feature analysis is performed on the measurement area based on the environmental data feature vector. The system uses a hierarchical multi-scale analysis method to calculate the terrain slope change rate, surface roughness, and depth gradient distribution within the area, and at the same time evaluates the terrain complexity using the variation ranges of geological features and water flow velocity. For example, the system calculates that the maximum slope of a certain area is 45 degrees, the standard deviation of the depth gradient is 3.5, and the surface roughness index is 0.7. Combining these data, a regional terrain complexity assessment model is generated. This model classifies the feature vector through a clustering algorithm and outputs a regional complexity score (such as the score range is 0 to 10, and a complexity of 6.8 indicates a moderately complex area) for further guiding regional division.

[0044] Step S24: Divide the measurement area into several sub-areas with similar terrain features and measurement difficulties according to the regional terrain complexity evaluation model, and establish a mapping of the sub-area topological relationship, so as to obtain the sub-area topological relationship data; In the embodiment of the present invention, the measurement area is divided into sub-areas according to the terrain complexity evaluation model. The system uses the K-means clustering algorithm to divide the entire measurement area into several sub-areas with similar terrain features. At the same time, the topological relationship between the sub-areas is analyzed, such as adjacency, shared boundary length, and positional relationship. Taking a lake with a measurement area of 2 square kilometers as an example, the system divides it into 5 sub-areas. Among them, the complexity score of sub-area A is 7.2, the area is 0.4 square kilometers, it is adjacent to sub-area B, and the shared boundary length is 150 meters. The generated sub-area topological relationship data is represented in a graph structure, the nodes are the sub-area numbers, the edges are the weights of the adjacent relationships, and the output format is XML for subsequent task allocation modules to call.

[0045] Step S25: Correlate and match the collaborative parameter data with the sub-area topological relationship data, and construct a measurement area topological model including device capabilities, task constraints, and terrain features; In the embodiment of the present invention, the collaborative parameter data is correlated and matched with the sub-area topological relationship data. The system extracts the capability parameters of the device (such as maximum measurement depth, communication range, battery life) and task constraints (such as measurement accuracy and time window), and then combines the terrain features of the sub-areas to generate a regional topological model. For example, the maximum measurement depth of unmanned ship A is 50 meters, and the battery life is 8 hours, which matches sub-area A with a higher complexity score and a larger area. The communication range of unmanned aerial vehicle B is 500 meters, which matches sub-areas C and D with higher coverage requirements. The regional topological model includes a list of task allocation devices for each sub-area and their capability matching scores, and the output is in the format of a network diagram for subsequent optimization.

[0046] Step S26: Use a multi-objective optimization algorithm to optimize the sub-area task allocation of the measurement area topological model based on the constraint conditions of measurement coverage rate, data consistency, energy efficiency, and measurement accuracy, so as to generate a collaborative measurement task allocation scheme.

[0047] In the embodiment of the present invention, a multi-objective optimization algorithm is used to optimize the task allocation of the regional topological model. The system sets the coverage rate, data consistency, energy efficiency, and measurement accuracy as constraint conditions, and iteratively calculates the optimal task allocation scheme for each device through the particle swarm optimization algorithm. For example, to ensure that the coverage rate of sub-area A reaches more than 90%, the system adjusts the path planning and task time allocation of the unmanned ship and the unmanned aerial vehicle, and at the same time optimizes the energy consumption so that the remaining battery power of the unmanned ship is greater than 20% after the task is completed. Finally, a collaborative measurement task allocation scheme is generated, which includes the task list, coverage range, and estimated energy consumption of each device, and the output format is a JSON file for the collaborative execution module to call.

[0048] The present invention comprehensively collects environmental data of the measurement area by obtaining water area terrain features, water depth distribution, water flow velocity, bottom geological composition, water body transparency, and geographical obstacle information, ensuring a full understanding of the natural conditions involved in the measurement task; the comprehensiveness of the data provides multi-dimensional support for subsequent analysis, optimization, and decision-making, avoiding the omission of key environmental factors. By collecting multi-dimensional data of the water area environment, the measurement strategy and collaboration plan of the system can be flexibly adjusted according to the requirements of specific measurement tasks, enabling the system to adapt to complex and changeable water area environments. The obtained environmental data provides accurate data support for subsequent modeling and optimization, ensuring the effectiveness and practical applicability of the model and optimization algorithm. Through fusion and standardization processing, environmental data from different sources and in different formats can be unified into feature vectors, simplifying the data processing flow and enhancing the operability of the data. Data fusion and standardization processing help remove noise and redundant information, improve the quality and reliability of the data, and lay a foundation for subsequent analysis and modeling. The unified environmental data feature vectors can ensure the consistency of data in the subsequent multi-dimensional analysis and modeling process, avoiding errors or deviations caused by inconsistent data formats. Based on the environmental data feature vectors, multi-scale and multi-dimensional terrain complexity analysis is carried out to comprehensively evaluate the terrain features and complexity of the measurement area. This can help identify areas with higher measurement difficulty and potential challenge points. Terrain complexity assessment helps better match the task with specific terrain features, improving the feasibility and execution efficiency of the task. High-precision equipment can be specially arranged or the task execution method can be optimized in complex areas. Terrain complexity assessment provides an important decision-making basis for subsequent area division, sub-area task allocation, and path planning, ensuring that the system can flexibly adjust strategies according to terrain features. According to the terrain complexity assessment model, the measurement area is divided into several sub-areas with similar terrain features and measurement difficulty. This division helps achieve an accurate match of tasks, making the task execution in each sub-area more efficient. By establishing a mapping of sub-area topological relationships, the spatial relationships between various sub-areas can be clarified, providing a clear spatial organizational structure for task allocation and collaborative operations. The division of sub-areas not only helps improve measurement accuracy and efficiency but also optimizes resource allocation, enabling each device to perform tasks in a suitable area, thereby reducing energy waste and equipment wear. By associating and matching the collaboration parameter data with the sub-area topological relationship data, suitable tasks can be assigned according to the performance characteristics of the equipment (such as remaining power, measurement accuracy, endurance, etc.), ensuring the executability of the tasks and the optimal allocation of resources. Association and matching help adjust the execution order and execution equipment of collaborative tasks according to terrain features and task requirements, making the overall execution of tasks more efficient and seamlessly connected. By considering the relevance of multi-dimensional data, the ability of the system to respond to changes in complex task environments can be enhanced, improving the adaptability and flexibility of the system.Optimizing the topological model of the measurement area using a multi-objective optimization algorithm can balance multiple objectives (such as measurement coverage, data consistency, energy efficiency, and measurement accuracy) to ensure the best execution of each task objective. Multi-objective optimization can maximize the utilization of various resources in the system (such as devices, energy, time, etc.), avoiding resource waste and redundant operations during task execution. The optimized task allocation scheme can ensure the smooth progress of tasks, avoiding task interruptions or failures caused by improper task allocation or insufficient device capabilities. Through reasonable task allocation and optimization, different devices and sub-regions can cooperate better, further enhancing the collaborative operation ability of the entire measurement system and ensuring the efficient and high-quality completion of tasks.

[0049] Preferably, step S23 includes the following steps: Step S231: Use a spatial interpolation algorithm to perform continuous completion and smoothing processing on the water depth based on the water area terrain feature data, so as to obtain the water depth distribution grid data of the measurement area; In the embodiment of the present invention, a spatial interpolation algorithm is used to complete and smooth the water area terrain feature data. The system uses the Kriging Interpolation method to predict the incomplete water depth measurement data, and combines the measurement point data and the water area boundary conditions to generate continuous water depth distribution grid data. In a lake measurement scenario, the sampling point spacing of the known water depth data is 50 meters, and there are vacancies in some areas due to insufficient sampling. The system generates water depth grid data with a resolution of 2 meters through interpolation, and uses a Gaussian smoothing filter to eliminate local outliers, finally forming a complete water depth distribution grid, and the data format is GeoTIFF.

[0050] Step S232: Classify the underwater geological data based on different geological components, and extract the distribution ranges and physical properties of each category, so as to generate geological composition feature data; In the embodiment of the present invention, the underwater geological data is classified. The system first divides the underwater geology into three main components: sand and gravel layer, clay layer, and silt layer through spectral feature analysis, and then uses the support vector machine (SVM) classification algorithm to extract the spatial distribution range of each component. In practical applications, the distribution density of the geological data point set obtained by underwater sonar detection is 200 points per square kilometer. After classification, it is determined that the coverage rate of the sand and gravel layer is 40%, the clay layer is 35%, and the silt layer is 25%. At the same time, its physical properties such as porosity (0.3 for the sand and gravel layer, 0.5 for the clay layer) are extracted to generate geological composition feature data including geological types and physical properties, and stored in the Shapefile format.

[0051] Step S233: Based on the water flow velocity and water body transparency data, conduct water flow velocity distribution modeling, calculate the velocity change field and optical transparency field of the target water area, so as to obtain hydrodynamic and optical distribution characteristic data; In the embodiment of the present invention, modeling is carried out based on water flow velocity and water body transparency data. The system uses a computational fluid dynamics model (CFD) to calculate the velocity change field and a distributed optical attenuation model (DOM) to calculate the optical transparency field. In the measurement of a certain river section, the sampling point spacing of the water flow velocity data is 10 meters, and the transparency data is collected every 20 meters through an optical sensor. The system generates a 3D velocity distribution model through data fitting and combines it with the transparency field to form complete hydrodynamic and optical distribution characteristic data. The results show that the water flow velocity range in the target area is 0.3 - 2.1 m / s, and the transparency distribution range is 2 - 8 meters. The output is a grid vector file for subsequent processing.

[0052] Step S234: Map the bathymetric distribution grid data, geological composition characteristic data, and hydrodynamic and optical distribution characteristic data into a unified coordinate system, and divide the measurement area into uniform small units based on the grid method, so as to obtain a multi-characteristic grid data model, where each grid unit in the multi-characteristic grid data model contains topographic and environmental parameters; In the embodiment of the present invention, multi-dimensional environmental data is mapped into a unified coordinate system. The system uses a geographic information system (GIS) tool to align the coordinates of the bathymetric grid, geological composition characteristics, and hydrodynamic and optical distribution characteristics, and uses a grid algorithm to divide the measurement area into small units of 10 m × 10 m. In the modeling of a certain port area, the system generates a multi-characteristic grid data model containing 10,000 grid units. Each grid unit contains environmental parameters such as water depth (e.g., 5 meters), geological type (e.g., gravel layer), flow velocity (e.g., 1.2 m / s), and transparency (e.g., 3.5 meters), and is finally saved in the HDF5 format to support efficient calculation and storage.

[0053] Step S235: Conduct multi-scale, multi-dimensional topographic feature and complexity analysis on the multi-characteristic grid data model, so as to construct a regional topographic complexity assessment model.

[0054] In the embodiment of the present invention, multi-scale and multi-dimensional topographic complexity analysis is carried out on the multi-characteristic grid data model. The system uses the fractal dimension method to calculate the topographic complexity index, and combines the slope change rate, hydrodynamic gradient, and geological distribution inhomogeneity to generate a regional topographic complexity assessment model. In a lake measurement scenario, the system calculates the fractal dimension as 1.75 with a 20-meter unit, the average slope change rate is 15%, and the hydrodynamic gradient change rate is 8%. The final model shows that the regional complexity score is distributed in the range of 0 to 10, and the area with a complexity score higher than 7 accounts for 35% of the total area. The evaluation results are exported in JSON file format for subsequent measurement task planning and optimization.

[0055] The present invention performs complementation and smoothing processing on bathymetry data through a spatial interpolation algorithm, which can fill in blank areas caused by insufficient measurement or equipment limitations, and generate continuous and smooth bathymetry distribution data. This makes the representation of water area terrain features more accurate and complete. The spatial interpolation method can effectively reduce measurement errors and data noise, ensure the smooth transition of bathymetry data, and avoid affecting subsequent analysis and modeling due to mutations or noise. The bathymetry distribution grid data after complementation and smoothing processing provides reliable basic data for subsequent terrain analysis, sub-region division, and mission planning, which helps to improve the accuracy of mission execution. Based on the classification processing of different geological components, the geological composition of the water bottom can be accurately identified, providing information about the distribution of geological layers, lithology types, and other physical characteristics, which helps to optimize and adjust subsequent missions. Extracting the distribution ranges and physical properties of various categories provides key references for the execution of measurement missions and equipment scheduling. For example, different geological components may have different requirements for the performance of measurement equipment, and understanding the geological characteristics can optimize the selection of equipment and the arrangement of missions. Understanding the specific composition and characteristics of the water bottom geology helps to evaluate the impact of geological factors on water area measurement and ensure the accuracy and reliability of measurement data. Through the modeling based on water flow velocity and water body transparency data, the variation of water flow velocity and the distribution characteristics of optical transparency of the water body can be accurately simulated. This provides a key basis for considering the changes in water flow and water body transparency during subsequent water area measurement. Modeling the variation of water flow velocity and transparency field can help to determine the optimal time and location for underwater measurement. For example, areas with too high water flow velocity or low transparency may have a negative impact on measurement missions, and prior modeling and prediction help to optimize and adjust missions. When multiple devices collaborate to execute missions, understanding the hydrodynamic and optical distribution characteristics helps to optimize the collaborative work and mission allocation between devices and ensure the maximization of system efficiency. Mapping data from different sources (such as bathymetry, geology, water flow velocity, transparency, etc.) to a unified coordinate system helps to integrate multi-dimensional data together, simplifies the subsequent analysis process, and avoids complexities or errors caused by inconsistent data formats. Mapping the data to the same coordinate system ensures the spatial consistency between different data, avoids positioning deviations during data docking, and ensures the accuracy of regional analysis and mission planning. The multi-feature grid data model can effectively integrate multiple environmental and terrain features, making each grid cell contain complete terrain and environmental parameters, providing high-quality data support for subsequent complexity analysis, mission allocation, and path planning. Through multi-scale and multi-dimensional analysis, it is possible to perform more refined matching and adjustment of measurement missions according to factors such as terrain complexity, geological characteristics, and water flow conditions in different regions. Analyzing the multi-feature grid data model can evaluate the complexity of the measurement area and provide an optimization basis for measurement missions and equipment resource allocation. For example, areas with higher complexity can be specifically arranged with high-precision equipment or adjusted mission execution strategies.By comprehensively analyzing the terrain complexity and environmental parameters, the adaptability of the system in a changing environment can be enhanced, ensuring that the measurement tasks can be efficiently executed under different terrain conditions. This analysis helps to optimize decision-making in the measurement area planning, thereby improving the task execution efficiency, reducing unnecessary resource waste, and effectively enhancing the measurement accuracy and path coverage rate.

[0056] Preferably, step S26 includes the following steps: Establish a multi-objective optimization function based on the measurement area topology model to obtain the target optimization function data. The function objectives in the multi-objective optimization function include maximizing the measurement coverage rate, optimizing the data consistency, maximizing the energy efficiency, and minimizing the deviation of the measurement accuracy. The constraint conditions in the multi-objective optimization function include the device battery life, communication range, and task time window. Optimize the sub-region task allocation of the measurement area topology model according to the target optimization function data to generate a collaborative measurement task allocation scheme.

[0057] In the embodiment of the present invention, for the measurement area topology model, a multi-objective optimization algorithm (such as NSGA-II) is used to establish an optimization function. The objective functions include: ① Maximizing the measurement coverage rate, defined as the ratio of the measured sub-region area to the total region area, and the goal is to make the ratio close to 1; ② Optimizing the data consistency, based on the similarity metric (such as cosine similarity) after data fusion, and the goal is to improve the consistency of the measurement data between sub-regions; ③ Maximizing the energy efficiency, calculating the ratio of the energy consumption of each device to its covered area, and the goal is to minimize the energy consumption per unit area; ④ Minimizing the deviation of the measurement accuracy, defined as the root mean square error (RMSE) between the measurement result and the true value, and the goal is to make the RMSE close to 0. The constraint conditions include: ① The device battery life (the battery power is greater than the minimum threshold required for measurement); ② The communication range (ensuring that the communication delay between collaborative devices is less than 50 ms); ③ The task time window (the completion time of all tasks does not exceed the set threshold). In a measurement scenario of a certain reservoir, the specific form of the target optimization function is Where represent the coverage rate, consistency, and energy efficiency respectively, With time, power, and communication distance constraints, the system outputs target optimization function data for sub-region task allocation. Based on the target optimization function data, an improved Particle Swarm Optimization (PSO) algorithm is used to optimize the sub-region task allocation of the measurement area topology model. Each particle represents a task allocation scheme, including the matching relationship between devices and sub-regions. The fitness function of the particle is calculated by the optimization function. The algorithm finds the global optimal solution through the update of velocity and position. In a certain reservoir scenario, the devices include 10 unmanned boats (with a endurance time of 6 hours) and 5 drones (with a communication radius of 2 km). The task area is divided into 50 sub-regions. The goal is to reasonably allocate tasks to the device group and maximize the objective function. Through algorithm optimization, the generated allocation scheme shows that the unmanned boats mainly cover the sub-regions near the shore (due to complex terrain), and the drones are responsible for the farther areas (due to stronger endurance). The coverage rate of the entire measurement task reaches 95%, the data consistency score is 0.92, the energy efficiency is increased by 15%, the total task time is 4 hours, and the output is a collaborative measurement task allocation scheme file (in JSON format), including device numbers, allocated sub-region IDs, task time periods, and communication configuration parameters.

[0058] Through the design of the multi-objective optimization function, the present invention not only optimizes the measurement coverage rate, energy efficiency, and measurement accuracy, but also considers practical constraints such as data consistency and device capabilities, enabling the system to make flexible adjustments according to environmental changes during actual operation, ensuring the efficiency and accuracy of overall task execution. Through multi-objective optimization, the system can better adapt to dynamic environments and complex task requirements, maximize the optimization of various indicators while meeting the constraints, and enhance the adaptability and task execution flexibility of the system in complex measurement environments. This optimization method can automatically adjust task allocation and path planning according to real-time information of tasks and devices, improve the system's autonomous decision-making ability and intelligent level, reduce the need for manual intervention, and enhance the intelligent operation of the system.

[0059] Preferably, step S31 includes the following steps: Step S31: Extract the characteristics of sub-region division of the measurement area, measurement depth requirements, measurement accuracy standards, time constraints, and device capability limitations from the collaborative measurement task allocation scheme, so as to obtain task characteristic data; In the embodiments of the present invention, within the measurement area, according to the collaborative measurement task allocation scheme, feature extraction is performed on sub-region division data, measurement depth requirements, measurement accuracy standards, time constraints, and equipment capacity limitations. In specific implementation, the terrain complexity information of the sub-region is queried using an SQL database, and the measurement depth requirements (such as 5 meters to 50 meters) and accuracy standards (such as deviation less than 0.1 meter) are parsed into numerical features from the task constraint file. At the same time, the equipment performance parameters of the unmanned ship and the drone (such as the upper limit of the battery power is 500 Wh, and the maximum communication radius is 2 kilometers) are combined to generate a feature vector. Taking the measurement task of a certain reservoir as an example, the data generated after feature extraction includes sub-region numbers (such as A1, A2), the depth range of each region, the accuracy threshold, the time window (such as within 2 hours), and the allocated equipment capacity matrix, and the output is a task feature data file (in CSV format).

[0060] Step S32: Construct an initial path planning model based on fuzzy logic according to the task feature data, and design a multi-dimensional fuzzy membership function including terrain complexity, measurement accuracy, energy consumption, and communication reliability, so as to obtain a fuzzy logic path planning model; The embodiments of the present invention utilize the task feature data generated in step S31 to construct an initial path planning model based on fuzzy logic. Design fuzzy membership functions for terrain complexity (such as slope greater than 30 degrees), measurement accuracy (such as required deviation less than 0.1 meter), energy consumption (such as battery power lower than 20%), and communication reliability (signal strength greater than 80%), and the form of the membership function is a Gaussian function or a trigonometric function. In a certain application scenario, the terrain complexity membership function is defined as: , where is the slope, . Generate a path planning rule set through a fuzzy inference system (such as the Mamdani model), for example, "if the terrain complexity is high and the communication reliability is low, then preferentially select the shortest path within the equipment coverage range", and output a fuzzy logic path planning model (implemented in Python).

[0061] Step S33: Obtain the real-time platform status data of the unmanned ship and the drone, including the current position, remaining battery power, communication signal strength, sensor working status, and environmental dynamic change information; In the embodiment of the present invention, the embedded monitoring system of the unmanned ship and the unmanned aerial vehicle (UAV) collects the platform status data in real time, including the position (GPS coordinates, with an accuracy of less than 2 meters), the remaining battery power (such as 70%), the communication signal strength (such as 80%), the sensor status (such as the temperature sensor is normal), and the environmental dynamic change information (such as the wind speed of 5 m / s and the water flow speed of 0.5 m / s). The data is uploaded to the central control system in real time through the 4G communication module and stored in the MongoDB database, and a dynamic status data set is generated in combination with the time stamp to ensure an update once per second for input into the fuzzy logic path planning model.

[0062] Step S34: Input the platform status data into the fuzzy logic path planning model and generate a preliminary path planning scheme; In the embodiment of the present invention, the platform status data is input into the fuzzy logic path planning model, and the priority of each sub-region and the initial path planning scheme are calculated through fuzzy inference. In a certain measurement task, the unmanned ship with a relatively short distance is preferentially allocated to the area with high terrain complexity (such as a slope greater than 45 degrees), while the UAV with stronger endurance is allocated to the measurement task in the far-distance sub-region. After the preliminary path planning scheme is generated, the initial navigation path of each device (such as the coordinate sequence from the starting point to the target area) and the task sequence (such as preferentially measuring the sub-region with large depth changes) are output.

[0063] Step S35: Use the particle swarm optimization algorithm to perform iterative optimization on the preliminary path planning scheme based on the optimization objectives of maximizing the coverage rate and minimizing the repeated measurement, so as to obtain an optimized path planning scheme; In the embodiment of the present invention, the particle swarm optimization algorithm (PSO) is used to perform iterative optimization on the preliminary path planning scheme, and the goal is to maximize the measurement coverage rate and minimize the repeated measurement. Each particle represents a path sequence, and the fitness function is calculated through the measurement coverage rate and the total path length. The velocity and the optimal solution are referred to when updating the particle position. Taking the measurement of a certain reservoir as an example, during the optimization process, the path coverage rate of the device is increased from 85% to 95%, and the repeated measurement area is reduced to 3%. Finally, the optimized path planning scheme is output, including the device number, the path sequence, and the optimization parameters (such as the total energy consumption is 400 Wh).

[0064] Step S36: Perform simulation on the measurement path performance under different environments and device states for the optimized path planning scheme based on the Monte Carlo simulation method, and output a collaborative measurement path planning scheme including the path coordinates of the unmanned ship and the UAV and the measurement time sequence.

[0065] In the embodiment of the present invention, the optimized path planning scheme is input into the Monte Carlo simulation system, and path performance simulation is carried out based on different environmental parameters (such as the water flow velocity changes within ±0.2 m / s and the wind speed changes within ±1 m / s) and device states (such as the power consumption rate fluctuates within ±5%). In a certain scenario, after 1000 simulations, the average coverage rate of the device path is statistically 93%, and the proportion of communication delays less than 50 ms is 97%. It is also identified that the path may deviate in extreme environments (wind speed greater than 10 m / s), and it is recommended to increase the allocation of standby devices. The final output is a collaborative measurement path planning scheme, including the path coordinates, measurement timing, and optimization suggestions of each device.

[0066] By extracting features such as sub-region division of the measurement area, measurement depth, accuracy standards, time constraints, and equipment capacity limitations, the present invention can comprehensively understand the requirements and challenges of the task. This process provides a detailed data basis for subsequent path planning, task scheduling, and equipment allocation. The extracted task feature data helps the system reasonably match the equipment with the task requirements, ensuring that the execution of each subtask complies with its specific environmental, measurement accuracy, and equipment capacity constraints, and improving the quality and efficiency of task execution. By accurately extracting task feature data, the system can perform more refined task allocation and scheduling according to the different capabilities of the equipment (such as endurance, accuracy, communication capabilities, etc.), thereby reducing resource waste and enhancing the overall operation efficiency. Using a fuzzy logic path planning model, multiple factors such as terrain complexity, measurement accuracy, energy consumption, and communication reliability can be considered simultaneously, helping the system flexibly adapt to different environmental changes and task requirements. Through multi-dimensional membership functions, the path planning model can process complex fuzzy and uncertain information to obtain a relatively ideal preliminary path planning scheme. Fuzzy logic can provide stable path planning under uncertainty and environmental changes. Especially when facing complex terrains or sudden environments, it can adjust the path in real time to ensure that the task can be completed on time and efficiently. In the measurement task, both accuracy and efficiency need to be considered. The fuzzy logic model can balance these factors to ensure that the path planning not only meets the accuracy requirements but also maximizes efficiency, reducing unnecessary repetitive or ineffective paths. Real-time acquisition of the state data of the unmanned ship and the unmanned aerial vehicle, such as the current position, remaining battery power, communication signal strength, sensor status, etc., can timely monitor the operation status of the equipment, ensuring that the path planning conforms to the current equipment capabilities and task requirements in actual operation. By obtaining real-time platform status data, the path planning model can be dynamically adjusted according to the actual situation of the equipment. For example, when the battery power is insufficient, the path is adjusted; when the communication signal is poor, remote areas are avoided, etc., to avoid interruptions or failures during task execution. Combining real-time environmental changes and equipment status can better optimize task scheduling and path selection, enhancing the adaptability and response speed of the system. After inputting the real-time platform status data into the fuzzy logic model, the path can be dynamically adjusted according to the current equipment capabilities and environmental conditions. This real-time optimization ensures that the path planning is always based on the most accurate current equipment and environmental information, thereby improving the efficiency and accuracy of task completion. Based on the real-time status information of the platform, the path planning model can flexibly respond to environmental changes and equipment dynamic status, automatically adjusting the path to meet the actual needs of the measurement task. After inputting the real-time platform status data, the path planning is more in line with the actual situation, and can avoid task failures or inefficient executions caused by poor equipment status (such as insufficient battery power, communication interruption, etc.). The particle swarm optimization (PSO) algorithm can effectively balance global optimization and local search. When searching for the optimal path, it can avoid local optimal solutions and efficiently explore a wider solution space.This global optimization feature is very suitable for path planning of complex tasks. Especially in collaborative measurement tasks, it can obtain the optimal path. The goal of particle swarm optimization is to maximize the coverage rate of the measurement area while minimizing the occurrence of repeated measurement paths, thereby reducing energy consumption and improving measurement efficiency. Through iterative optimization, it ensures that the path planning meets these requirements and enhances the overall task execution efficiency. The particle swarm algorithm has good stability and convergence, and can achieve good path planning optimization effects within a limited number of iterations, reducing resource waste or measurement repetition caused by unreasonable path planning. The Monte Carlo simulation method can simulate path performance under different environments and device states, and evaluate the robustness and adaptability of the path planning scheme. This process can effectively identify potential problems, such as extreme weather, equipment failures, communication losses, etc., to ensure that the path planning can be smoothly executed under various actual conditions. Through multiple simulation runs, potential problems in path planning can be discovered and adjusted and optimized, so as to ensure that the final scheme has high reliability and stability in different operating environments. Monte Carlo simulation can help identify bottlenecks or inefficient areas in path planning, early warning of potential risks of resource shortages or task failures, and optimize and adjust the path to ensure the successful completion of the measurement task.

[0067] Preferably, step S4 includes the following steps: Step S41: Extract the remaining battery percentage, task progress, and navigation status of the drone from the platform status data to obtain drone status data; In the embodiment of the present invention, according to the platform status data, information such as the remaining battery percentage, task progress, and navigation status of the drone is extracted. First, the remaining battery (e.g., 80%), task progress (e.g., 50% completed), and navigation status (e.g., cruising) of the drone are obtained through the internal monitoring system of the drone. These data are usually uploaded to the central control platform through a real-time transmission module (such as LoRa or 4G). Then, these information are converted into data features to generate a drone status data set. Taking an offshore measurement task as an example, assume that at a certain moment, the battery level of the drone is 75%, the task progress is 30%, and the navigation status is "cruising" (moving speed is 12 km / h). These data records will be updated in real time and stored in the database for subsequent processing.

[0068] Step S42: Compare the drone status data with a preset power threshold and determine a list of drone devices that require energy replenishment to obtain data of devices to be replenished; In an embodiment of the present invention, the state data of the unmanned aerial vehicle is compared with a preset power threshold to determine which unmanned aerial vehicles need energy replenishment. Assuming that the preset power threshold is 30%, when the remaining power of the unmanned aerial vehicle is lower than this threshold, the device is included in the list of devices to be replenished. In a specific implementation, first, by writing a comparison algorithm, the power data of the unmanned aerial vehicle is monitored in real time. If the power is less than 30% (for example, the remaining power of a certain unmanned aerial vehicle is 28%), it is added to the list of devices to be replenished. The output data includes information such as the device ID, the current location (such as longitude 45.6° and latitude -34.3°), and the current power (such as 28%). Based on this information, the unmanned aerial vehicle devices that need to be charged can be quickly determined for subsequent operations.

[0069] Step S43: Use the unmanned ship as a mobile charging platform, trigger a fast docking charging or battery swapping mechanism according to the data of the device to be replenished, so as to generate docking strategy data, where the docking strategy data includes the docking location and timing scheme information; In an embodiment of the present invention, according to the data of the device to be replenished, the unmanned ship is used as a mobile charging platform for fast docking charging or battery swapping. In a specific operation, first, by analyzing the current location and navigation path of the unmanned aerial vehicle in the data of the device to be replenished, and combining with the real-time location and navigation path of the unmanned ship, the shortest approaching path between the two is calculated. Assuming that the unmanned aerial vehicle to be replenished is located in a deviation area of the navigation path, and the unmanned ship is traveling along a straight-line path, the system will automatically select a proximity point for docking (for example, the distance between the unmanned ship and the unmanned aerial vehicle is 5 km, and the estimated docking time is 10 minutes). The docking strategy data includes the specific docking location (such as longitude and latitude coordinates) and the docking timing (such as triggering docking within 10 minutes after the unmanned ship arrives at this point). In addition, the docking action can also trigger the battery swapping mechanism to ensure a quick recovery of the energy of the unmanned aerial vehicle.

[0070] Step S44: Optimize the timing and location of energy replenishment for the docking strategy data according to the unmanned ship and the mission path of the unmanned aerial vehicle in the collaborative measurement path planning scheme, so as to obtain dynamic energy replenishment strategy data.

[0071] In an embodiment of the present invention, according to the mission paths of the unmanned ship and the unmanned aerial vehicle in the collaborative measurement path planning scheme, the energy replenishment timing and position in the docking strategy data are optimized. First, the dynamic distance, mission progress, and estimated sailing time between the unmanned ship and the unmanned aerial vehicle are calculated through the path planning system, and combined with the power consumption rate, the optimal energy replenishment timing and position are deduced. For example, assume that the mission paths of the unmanned ship and the unmanned aerial vehicle intersect, and the remaining power of the unmanned aerial vehicle is 32%. According to the mission path and the predetermined time, it is estimated that the unmanned aerial vehicle will reach the replenishment point within 2 hours. At this time, considering factors such as the sailing state and mission priority, the energy replenishment strategy is optimized. Assume that after optimization, it is decided to conduct replenishment 10 km away from the unmanned aerial vehicle to ensure that the mission is not affected and the replenishment process is fast and seamless. Finally, the dynamic energy replenishment strategy data is output, including the optimal position and timing information of the replenishment (such as the coordinates of the replenishment point, the estimated arrival time, and the mission status).

[0072] The present invention extracts data such as the remaining battery percentage, mission progress, and navigation status of the unmanned aerial vehicle (UAV), enabling real-time monitoring of the UAV's working status. This provides an accurate basis for subsequent energy replenishment decisions, ensuring that the state changes of the UAV during mission execution are captured in a timely manner. The mission progress data of the UAV helps to understand the current working stage and remaining tasks of the UAV, so that replenishment can be carried out at an appropriate time point to avoid power depletion at critical moments. By extracting these data, the system can better evaluate the actual energy requirements of the UAV, ensuring that the replenishment operation conforms to the actual situation of mission execution rather than preset general rules. By comparing the remaining battery of the UAV with the preset battery threshold, it is possible to intelligently identify which UAVs need to replenish energy. In this way, the system can accurately determine which devices need to be replenished first, avoiding unnecessary resource waste. According to the mission progress and the power consumption of the devices, the system can dynamically manage energy resources, avoiding mission failure or interruption due to insufficient power. By determining the devices to be replenished, the system can reasonably schedule the devices that need to be replenished to ensure the orderly progress of the replenishment task and the measurement task. The unmanned boat, as a mobile charging platform, can provide flexible charging or battery swapping solutions to ensure that the UAV can promptly restore energy when the battery level is low, avoiding mission execution being affected by insufficient power. This flexibility enhances the adaptability of the system. When it is detected that the UAV's battery level is lower than the threshold, the system can quickly trigger the charging or battery swapping mechanism to ensure that the UAV can quickly resume operation, reducing the downtime and improving the mission execution efficiency. By generating docking strategy data (including docking position and timing scheme), it ensures the smooth progress of the charging or battery swapping process and reduces the impact on the mission progress during charging or battery replacement. Based on the mission path in the collaborative measurement path planning scheme, the timing and location of energy replenishment are optimized to ensure that the replenishment operation does not interrupt the measurement task. Through the optimization of the docking timing and location, the energy replenishment efficiency can be maximized, and the impact on the mission progress during the replenishment process can be reduced. Through the optimization of the replenishment strategy, the collaborative operation of the UAV and the unmanned boat is made more efficient, avoiding unnecessary repetitions or ineffective pauses during the path planning process and improving the overall efficiency of mission completion. The optimized dynamic energy replenishment strategy can ensure the continuous operation of the UAV during the measurement task, avoid mission interruption due to energy problems, and improve the continuity and stability of the mission. By optimizing the replenishment timing and location, it is ensured that the UAV can be replenished at the most needed moment and location, avoiding premature or late replenishment behaviors, so that the energy resources can be maximally utilized.

[0073] Preferably, step S44 includes the following steps: Step S441: Generate path interaction point data according to the position of the unmanned boat, the navigation path, and the UAV mission execution path in the collaborative measurement path planning scheme; In an embodiment of the present invention, path interaction point data is generated based on the positions of unmanned ships, navigation paths, and UAV mission execution paths in a collaborative measurement path planning scheme. First, the motion trajectories of the unmanned ship and the UAV are obtained through a path planning algorithm. Assume that the navigation path of the unmanned ship is a straight line segment A - B, with the starting point A being (45.6°, -34.3°) and the ending point B being (46.0°, -34.0°); the mission path of the UAV is a curved path from C (45.7°, -34.4°) to D (45.9°, -34.2°). The intersection points between the paths of the unmanned ship and the UAV are calculated through a spatial analysis method. According to the path intersection calculation method (such as the line segment intersection algorithm), path interaction point data is obtained. For example, the intersection point P1 is (45.8°, -34.3°). The path interaction point data includes the intersection point coordinates and the interaction time for use in subsequent steps.

[0074] Step S442: Based on the path interaction point data and the data of the equipment to be replenished, perform a preliminary matching on the timing plan in the docking strategy data to generate a preliminary energy replenishment plan; In an embodiment of the present invention, based on the path interaction point data and the data of the equipment to be replenished, a preliminary matching is performed on the timing plan in the docking strategy data to generate a preliminary energy replenishment plan. First, by comparing the data of the equipment to be replenished (such as the remaining battery power of the UAV is 28%, and it is expected to have 20% power when reaching the intersection point P1), the replenishment timing is determined according to the path intersection point P1 and the remaining battery power of the UAV. At this time, if the intersection point P1 is about 3 km away from the unmanned ship and is expected to reach the intersection point in 20 minutes, the replenishment timing is set according to the battery power and the time window. Then, in combination with the navigation path of the unmanned ship, the feasible position for energy replenishment (such as at the intersection point P1) is confirmed, and a preliminary replenishment plan is determined through a replenishment plan algorithm. The generated preliminary energy replenishment plan includes information on the replenishment timing (such as when it is expected to reach the intersection point P1) and the position (intersection point P1), ensuring that the energy replenishment timing coincides with the path intersection point.

[0075] Step S443: Verify the feasibility of the docking timing and position in the preliminary energy replenishment plan to obtain an optimized replenishment plan; In an embodiment of the present invention, the feasibility of the docking timing and position in the preliminary energy replenishment plan is verified to obtain an optimized replenishment plan. The feasibility of this step is verified through simulation. Assume that the preliminary energy replenishment plan predicts that the unmanned ship will be replenished at the intersection point P1, but before replenishment, the battery power consumption of the UAV accelerates, and the battery power is low when it reaches the replenishment point in advance. By introducing a battery power consumption rate model (such as a linear regression model based on the real-time battery power data of the UAV), the battery power change is dynamically calculated, and it is verified whether this timing can meet the replenishment requirements. If the preliminary plan does not meet the requirements, modify the timing and position (such as adjusting to the intersection point P2 or increasing the number of replenishments). Through simulation calculation and path correction, the new timing and position plan are verified, and the final feasible replenishment plan is determined.

[0076] Step S444: Dynamically adjust the docking sequence and position of the optimized resupply plan according to the real-time energy state changes of the unmanned ship and the drone, so as to obtain dynamic energy resupply strategy data.

[0077] In the embodiment of the present invention, according to the real-time energy state changes of the unmanned ship and the drone, the docking sequence and position in the optimized resupply plan are dynamically adjusted, so as to obtain dynamic energy resupply strategy data. The energy state data of the unmanned ship and the drone are obtained in real time, and parameters such as the remaining power and mission progress are obtained through wireless communication. Suppose that during the resupply process, the power of the drone drops rapidly and it cannot complete the resupply at the intersection point P1 according to the original plan. At this time, according to the resupply plan optimization algorithm, through real-time data scheduling, the unmanned ship is adjusted to a more suitable position, such as point P2 (assuming that the remaining power of the drone is 12% and it is expected to arrive within 30 minutes), and the continuity and efficiency of the resupply process are ensured. By dynamically monitoring and adjusting the real-time data, dynamic energy resupply strategy data is generated, including the timing, position and sequence of the resupply points, to ensure efficient resupply scheduling in a complex environment.

[0078] The present invention generates path interaction point data based on the positions of unmanned vessels, navigation paths, and the task execution paths of unmanned aerial vehicles in the collaborative measurement path planning scheme. These interaction points are key locations for energy replenishment of unmanned vessels and unmanned aerial vehicles. Generating such interaction point data can accurately identify the possible meeting positions of the two, laying a foundation for subsequent energy replenishment operations. By accurately generating path interaction points, the task execution can be combined with energy replenishment, avoiding path intersections or unnecessary repetitions between the two devices, thereby improving the task execution efficiency. Based on the path interaction point data and the data of the devices to be replenished (such as the battery status of unmanned aerial vehicles), the system can intelligently match the docking timing to ensure that the replenishment timing not only conforms to the task progress but also does not affect the path planning. This can ensure that the unmanned aerial vehicle obtains replenishment in a timely manner when the battery is critically low, avoiding mission interruption due to too low battery power. The preliminary matching timing scheme can optimize the timing of the replenishment operation, avoiding delays in the task progress or waste of resources during the replenishment process caused by premature or late replenishment actions. Through this preliminary matching, the response speed and accuracy of energy replenishment can be improved. The feasibility of the docking timing and position in the preliminary energy replenishment scheme is verified to ensure that the replenishment operation is executable under actual conditions. For example, verifying the device status, battery power sufficiency, path clearance, etc. during replenishment to avoid unrealistic replenishment schemes. Feasibility verification can effectively avoid path conflicts, communication interruptions, or excessive resource consumption of devices caused by inappropriate replenishment timing, improper docking position selection, etc. during the task execution, thereby improving the stability of the system. By verifying the feasibility of the optimized replenishment scheme, it can be ensured that the replenishment operation can proceed smoothly under complex environmental conditions, ensuring the efficient operation of the system and the successful completion of the task. The docking sequence and position of the optimized replenishment scheme are dynamically adjusted according to the real-time energy state changes of the unmanned vessel and the unmanned aerial vehicle. This can respond in real time to possible emergencies, such as rapid battery power decline of devices, changes in task progress, etc., ensuring that the replenishment scheme always meets the actual requirements. The dynamic adjustment scheme increases the adaptability and flexibility of the system. During the task execution, the device status and the external environment may change. By dynamically adjusting the replenishment scheme, it can be ensured that even if the environment changes, the replenishment operation can still be efficiently executed. By adjusting the replenishment timing and position according to the real-time energy state, it can effectively avoid energy shortage or over-replenishment caused by over-reliance on the preset scheme, thereby ensuring the long-term stable operation of the unmanned aerial vehicle and the unmanned vessel. Dynamic adjustment can maximize the energy usage efficiency, avoiding waste of resources due to insufficient battery power or over-replenishment during the task. At the same time, it can ensure that replenishment is carried out at the most critical moment, reducing mission interruptions and device downtime caused by insufficient battery power.

[0079] Therefore, in any regard, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0080] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A method for measuring water and underwater terrain based on the collaboration of an unmanned ship and an unmanned aerial vehicle, characterized in that: The following steps are involved: Step S1: Obtaining platform parameter data of the unmanned ship and the unmanned aerial vehicle; According to the platform parameter data, heterogeneous grouping is performed based on the remaining power, communication signal strength, endurance and measurement accuracy, and the collaborative formation plan is determined according to the preset water measurement task sequence to obtain the collaborative parameter data; Step S2: Obtaining the environmental data of the measurement area; performing regional division modeling based on the terrain characteristics of the water area and the complexity of the environment according to the environmental data of the measurement area, and applying the collaborative parameter data to the regional model to obtain a topological model of the measurement area; optimizing the sub-regional task allocation of the topological model of the measurement area to obtain a collaborative measurement task allocation plan; Step S3: construct a fuzzy logic path planning model according to the collaborative measurement task allocation plan, and dynamically optimize the path based on the platform status data obtained by real-time monitoring to obtain a collaborative measurement path planning plan with minimum repeated coverage and omissions; Step S4: Using the unmanned boat as a mobile charging platform, triggering a quick docking charging or battery swapping mechanism according to the remaining power of the UAV in the platform status data and the preset power threshold, and optimizing the timing and location of energy replenishment according to the collaborative measurement path planning scheme to obtain dynamic energy replenishment strategy data; Step S5: According to the dynamic energy replenishment strategy data, the collaborative measurement path planning scheme and the collaborative measurement task allocation scheme, the collaborative tasks of the unmanned ship and the unmanned aerial vehicle are scheduled in real time, so as to realize the terrain measurement above and below the water.

2. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: collecting remaining power, communication signal strength, current endurance and measurement equipment status parameters of the hardware equipment of the unmanned ship, so as to obtain unmanned ship platform parameter data; Step S12: Obtaining the drone platform parameter data, including the remaining flight power, flight endurance, current communication signal quality, and sensor working status information of the drone; Step S13: uploading the unmanned ship platform parameter data and the unmanned aircraft platform parameter data to the measurement and control center through the data transmission interface, thereby obtaining the platform parameter data; Step S14: performing data denoising and time synchronization processing on the platform parameter data, thereby obtaining standardized platform parameter data; Step S15: performing heterogeneous grouping based on remaining power, communication signal strength, endurance and measurement accuracy according to the standardized platform parameter data, thereby obtaining heterogeneous grouping scheme data; Step S16: Generate a collaborative formation plan according to the preset water area measurement task sequence and the heterogeneous grouping plan data, so as to obtain collaborative parameter data.

3. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: setting the priority weights of parameter indicators according to the standardized platform parameter data, wherein the remaining power has the highest weight, followed by communication signal strength, endurance, and measurement accuracy, thereby forming group weight configuration parameters; Step S152: Using a clustering algorithm, the heterogeneous score of each platform device is calculated based on the grouping weight configuration parameters, and the devices are divided into multiple collaborative task execution groups, thereby obtaining preliminary grouping scheme data, where the heterogeneous score = the normalized value of the remaining power of the device Remaining power weight + normalized value of communication signal strength Communication signal strength weight + normalized value of battery life Endurance weight + normalized value of measurement accuracy Measurement accuracy weight; Step S153: performing a balance consistency check based on multiple indicators on the preliminary grouping scheme data, and performing grouping optimization adjustment, thereby obtaining optimized grouping scheme data; Step S154: Determine the coordination number and allocation order of the grouped devices according to the optimized grouping scheme data and the current geographical location of the platform device and the starting state of task execution, thereby obtaining the heterogeneous grouping scheme data.

4. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 3 is characterized in that: Step S16 includes the following steps: Step S161: extracting information on the time sequence, area division, measurement depth requirements, and accuracy standards of the tasks according to the preset water area measurement task sequence, thereby obtaining task sequence feature data; Step S162: Matching the task sequence feature data with the measurement requirements based on the heterogeneous grouping scheme data, and determining the collaborative measurement task allocation of each group, thereby generating preliminary formation task allocation data; Step S163: Perform a feasibility analysis on the preliminary formation task allocation data based on the remaining power, endurance, communication range and measurement equipment accuracy of the unmanned ship and the unmanned aerial vehicle, and select the equipment group that meets the task execution conditions, thereby generating task equipment matching data; Step S164: Preliminarily optimizing the equipment position and navigation path of the collaborative formation based on the task equipment matching data, thereby generating preliminary formation plan data; Step S165: Dynamically simulate and verify the preliminary formation plan data, evaluate the task execution efficiency, path coverage and communication stability of the collaborative formation in different water measurement scenarios, identify potential bottlenecks and make adjustments and optimizations, so as to obtain optimized formation plan data; Step S166: Determine the formation, communication protocol and task allocation strategy of the unmanned ship and the unmanned aerial vehicle according to the optimized formation plan data, so as to obtain the coordination parameter data.

5. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 4 is characterized in that: Step S2 includes the following steps: Step S21: Acquire the environmental data of the measurement area, including the terrain characteristics of the water area, water depth distribution, water flow velocity, underwater geological composition, water transparency and geographical obstacle information; Step S22: performing data fusion and standardization processing on the environmental data of the measurement area, thereby establishing a unified environmental data feature vector, wherein the environmental data feature vector includes water area topographic feature data, underwater geological data, and water flow velocity and water transparency data; Step S23: Perform multi-scale, multi-dimensional terrain characteristics and complexity analysis on the measurement area based on the environmental data feature vector, thereby constructing a regional terrain complexity assessment model; Step S24: dividing the measurement area into several sub-areas with similar terrain features and measurement difficulties according to the regional terrain complexity assessment model, and establishing a sub-area topological relationship mapping, thereby obtaining sub-area topological relationship data; Step S25: Correlate and match the collaborative parameter data with the sub-region topological relationship data, and construct a measurement area topological model including equipment capabilities, task constraints, and terrain features; Step S26: Utilize a multi-objective optimization algorithm to optimize the sub-area task allocation of the measurement area topology model based on measurement coverage, data consistency, energy efficiency, and measurement accuracy constraints, thereby generating a collaborative measurement task allocation solution.

6. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 5 is characterized in that: Step S23 includes the following steps: Step S231: using a spatial interpolation algorithm to perform continuity complement and smoothing processing on the water depth according to the water area terrain feature data, thereby obtaining water depth distribution grid data of the measurement area; Step S232: classifying the underwater geological data based on different geological components, and extracting the distribution range and physical characteristics of each category, thereby generating geological composition characteristic data; Step S233: Modeling the water velocity distribution based on the water velocity and water transparency data, and calculating the velocity variation field and optical transparency field of the target water area, thereby obtaining hydrodynamic and optical distribution characteristic data; Step S234: mapping the water depth distribution grid data, geological formation characteristic data, and hydrodynamic and optical distribution characteristic data into a unified coordinate system, and dividing the measurement area into uniform small units based on a gridding method, thereby obtaining a multi-feature grid data model, wherein each grid unit in the multi-feature grid data model contains terrain and environmental parameters; Step S235: Perform multi-scale, multi-dimensional terrain feature and complexity analysis on the multi-feature grid data model, so as to construct a regional terrain complexity assessment model.

7. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 6 is characterized in that: Step S26 includes the following steps: A multi-objective optimization function is established according to the measurement area topology model to obtain the target optimization function data, where the function objectives in the multi-objective optimization function include maximizing measurement coverage, optimizing data consistency, maximizing energy efficiency, and minimizing measurement accuracy deviation. The constraints in the multi-objective optimization function include equipment endurance, communication range, and task time window. The sub-area task allocation of the measurement area topology model is optimized according to the target optimization function data to generate a collaborative measurement task allocation plan.

8. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 7 is characterized in that: Step S31 includes the following steps: Step S31: dividing the collaborative measurement task allocation plan into sub-areas of the measurement area, extracting the measurement depth requirements, measurement accuracy standards, time constraints, and equipment capability limitation features, thereby obtaining task feature data; Step S32: constructing an initial path planning model based on fuzzy logic according to the task feature data, and designing a multi-dimensional fuzzy membership function including terrain complexity, measurement accuracy, energy consumption and communication reliability, so as to obtain a fuzzy logic path planning model; Step S33: obtaining real-time platform status data of the unmanned ship and the unmanned aerial vehicle, including current location, remaining power, communication signal strength, sensor working status, and environmental dynamic change information; Step S34: inputting the platform status data into the fuzzy logic path planning model and generating a preliminary path planning solution; Step S35: using a particle swarm algorithm to iteratively optimize the preliminary path planning scheme based on the optimization objectives of maximizing coverage and minimizing repeated measurements, thereby obtaining an optimized path planning scheme; Step S36: Simulate the measurement path performance of the optimized path planning scheme under different environments and equipment states based on the Monte Carlo simulation method, and output a collaborative measurement path planning scheme including the path coordinates of the unmanned ship and the unmanned aerial vehicle and the measurement timing.

9. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 8 is characterized in that: Step S4 includes the following steps: Step S41: extracting the remaining power percentage, mission progress and navigation status of the UAV from the platform status data, thereby obtaining the UAV status data; Step S42: comparing the drone status data with a preset power threshold, and determining a list of drone devices that need energy replenishment, thereby obtaining data of devices to be replenished; Step S43: using the unmanned boat as a mobile charging platform, triggering a quick docking charging or battery exchange mechanism according to the data of the equipment to be supplied, thereby generating docking strategy data, wherein the docking strategy data includes docking position and timing plan information; Step S44: Optimize the timing and position of energy replenishment for the docking strategy data according to the unmanned ship and the unmanned aerial vehicle mission path in the collaborative measurement path planning scheme, thereby obtaining dynamic energy replenishment strategy data.

10. The method for measuring water and underwater topography based on the cooperation of unmanned ships and unmanned aerial vehicles according to claim 9, characterized in that: Step S44 includes the following steps: Step S441: Generate path interaction point data according to the unmanned ship position, navigation path and unmanned aerial vehicle task execution path in the collaborative measurement path planning scheme; Step S442: Preliminarily matching the timing plan in the docking strategy data based on the path interaction point data and the data of the equipment to be replenished, thereby generating a preliminary energy replenishment plan; Step S443: verifying the feasibility of the docking timing and position in the preliminary energy replenishment plan, thereby obtaining an optimized replenishment plan; Step S444: Dynamically adjust the docking sequence and position of the optimized replenishment plan according to the real-time energy state changes of the unmanned ship and the unmanned aerial vehicle, so as to obtain dynamic energy replenishment strategy data.

Images