An unmanned ship cluster mapping cooperation method, system, device and medium

Abstract

The present application relates to a kind of unmanned ship cluster surveying and mapping cooperation method, system, equipment and medium, method includes: based on surveying and mapping task parameter constructs ideal space-time topology matrix containing the time sequence relationship of each ship expected position;Obtain the current actual position of each ship, current speed, local sea current disturbance vector and adjacent ship actual position and communication link quality index;Based on ideal space-time topology matrix and adjacent ship actual position, the space-time topology consistency error vector between this ship and each neighbor is calculated;According to space-time topology consistency error vector, construct virtual gravitational field, according to the actual distance between ships, construct virtual repulsive force field, and according to communication link quality index and sea current disturbance vector, the action weight of gravity and repulsive force is dynamically adjusted, and is weighted into virtual resultant force;According to virtual resultant force, the expected heading angle and the motion control instruction of updated speed are generated.

Description

Technical Field

[0001] This invention relates to the field of marine surveying and mapping technology, specifically to a collaborative method, system, equipment, and medium for unmanned vessel swarm surveying and mapping. Background Technology

[0002] With the increasing demand for marine resource exploration, environmental monitoring, and waterway mapping, utilizing unmanned surface vessel (USV) swarms to perform large-scale marine mapping tasks has become an important means of improving operational efficiency. In typical collaborative mapping operations, multiple USVs usually travel in parallel along a pre-set parallel route. Each vessel is equipped with a depth sounder or multibeam sonar to continuously scan the seabed topography. By stitching together the scan strips from each vessel, a complete mapping result is formed. This parallel operation mode requires that the vessels maintain a precise relative positional relationship to ensure that there is appropriate overlap between adjacent scan strips and no blind spots, thereby guaranteeing the accuracy and completeness of data stitching.

[0003] However, achieving high-precision collaborative mapping of unmanned surface vessels (USVs) swarms in real-world marine environments faces significant challenges. First, the uneven distribution of tidal currents, prevalent in marine environments, causes vessels to deviate from their planned routes to varying degrees. This results in excessive overlap or gaps between the originally designed parallel scan zones. The former leads to decreased mapping efficiency and wasted resources, while the latter directly results in missing mapping data. Second, the complex and variable communication environment at sea, influenced by factors such as waves, distance, and weather, frequently causes delays, packet loss, or even interruptions in inter-ship communication links. This makes it difficult for centralized collaborative control methods relying on real-time global information exchange to operate stably. Existing technologies often employ fixed formation control or task-pre-assigned zonal mapping strategies. The former lacks dynamic adaptability to environmental disturbances, while the latter cannot adjust operational parameters in real-time to cope with sudden deviations when communication is limited. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a collaborative method, system, device and medium for unmanned surface vessel (USV) swarm mapping that enables autonomous correction of the coverage path of the USV swarm under conditions of incomplete communication reliability and environmental disturbance.

[0005] The objective of this invention is achieved through the following solution:

[0006] In a first aspect, the present invention provides a collaborative mapping method for unmanned surface vessels (USVs), comprising the following steps:

[0007] S1: Based on the obtained boundary of the mapping task area, the width of the scan band of a single ship and the number of participating unmanned ships, parallel scan lines are planned for the boundary of the mapping task area, a corresponding ideal scan trajectory is generated for each unmanned ship, and all ideal scan trajectories are organized according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship.

[0008] S2: Obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and obtain the actual positions of neighboring vessels and corresponding communication link quality indicators recorded by each unmanned vessel.

[0009] S3: Based on the ideal spatiotemporal topology matrix, extract the expected position of the ship at the current moment and the expected positions of each neighbor. Combine the actual positions of neighboring ships to calculate the deviation between the expected relative position and the actual relative position between the ship and each neighbor, and generate a spatiotemporal topology consistency error vector.

[0010] S4: Construct a virtual gravitational field based on the spatiotemporal topological consistency error vector, calculate the actual distance between ships based on the actual position of neighboring ships and the current actual position of this ship, and construct a virtual repulsive field. Dynamically adjust the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and then perform vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on this ship.

[0011] S5: Calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate motion control commands containing the desired heading angle and the updated speed. The motion control commands are used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

[0012] In one embodiment, S1 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0013] S11: Based on the obtained boundary of the mapping task area, the width of the single ship's scan strip, and the number of participating unmanned ships, the boundary of the mapping task area is divided into equal horizontal intervals based on the width of the single ship's scan strip. The expected spacing between adjacent scan lines is calculated, and the starting point coordinates of each scan line are determined according to the number of participating unmanned ships, generating the initial scan baseline corresponding to each ship.

[0014] S12: Apply time dimension synchronization constraints to the initial scan baseline and perform time-series planning. Based on the preset reference speed, register the timestamp corresponding to the same mileage position for each scan line and generate the expected position-time function for each ship.

[0015] S13: Perform matrix encapsulation of the desired position-time function, integrate the desired trajectories of each ship into a multi-dimensional time series data matrix according to the ship number order, and construct an ideal spatiotemporal topology matrix containing global desired position information.

[0016] In one embodiment, S3 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0017] S31: Based on the current time index, perform a table lookup process on the ideal spatiotemporal topology matrix to extract the expected position of the ship and the expected positions of all its neighbors, and generate the expected position set for the current time.

[0018] S32: Perform vector difference operations on the expected position set and the actual positions of neighboring ships, calculate the expected relative displacement vector and the actual relative displacement vector between the ship and each neighbor, and generate paired relative position relationship data.

[0019] S33: Perform pairwise difference and error accumulation processing on the expected relative displacement vector and the actual relative displacement vector, calculate the vector deviation between the two and construct a multidimensional error vector to generate a spatiotemporal topological consistency error vector characterizing the degree of overlap or gap in the scanning band.

[0020] In one embodiment, S4 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0021] S41: Perform gravitational field function mapping on the spatiotemporal topological consistency error vector, introduce a nonlinear attenuation factor to adjust the amplitude gain of each component in the error vector, convert the position deviation into a directional gravitational intensity, and generate the first virtual gravitational vector acting on the ship.

[0022] S42: Calculate the Euclidean distance between the actual position of the neighboring ship and the current actual position, and compare the calculated actual distance between the ships with the repulsive force threshold preset based on the scanning band width. For neighbors whose distance is less than the threshold, trigger the repulsive field function, calculate the repulsive force intensity and direction for neighbors that meet the conditions, and construct a repulsive vector field according to the principle that the closer the distance, the stronger the repulsive force, and generate a second virtual repulsive force vector acting on the ship.

[0023] S43: Perform communication reliability analysis on communication link quality indicators, map the communication quality level to the confidence coefficient of gravitational effect, and at the same time assess the environmental disturbance intensity of local ocean current disturbance vector, adjust the sensitivity coefficient of repulsive effect in the opposite direction according to the strength of ocean current, and generate gravitational weight coefficient and repulsive weight coefficient respectively.

[0024] S44: Perform weighted vector synthesis processing on the virtual gravity vector, virtual repulsion vector, gravity weight coefficient, and repulsion weight coefficient. Then, superimpose the coordinate components of the result of multiplying the gravity vector by the gravity weight coefficient and the repulsion vector by the repulsion weight coefficient to generate the virtual resultant force acting on the ship.

[0025] In one embodiment, S5 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0026] S51: Perform vector direction calculation on the virtual resultant force, calculate the azimuth angle of the resultant force vector relative to the reference coordinate system through the arctangent function, and perform relative turning angle conversion based on the current heading of the hull to generate the desired heading angle;

[0027] S52: Perform vector amplitude calculation and dynamic mapping on the virtual resultant force, divide the resultant force by the virtual mass and multiply by the control period to obtain the speed adjustment amount, and perform smoothing filtering on the speed adjustment amount to eliminate high-frequency jitter and generate the speed adjustment amount.

[0028] S53: Perform algebraic superposition on the speed adjustment amount and the preset reference speed, superimpose the adjustment amount to the reference speed to obtain the preliminary updated speed, and apply a ship dynamic constraint range limit to the preliminary updated speed to generate a constrained updated speed.

[0029] S54: Performs instruction encoding and protocol encapsulation processing on the desired heading angle and constraint update speed, converts the control parameters into a data frame format that conforms to the ship autopilot communication protocol, and generates motion control commands that can be parsed by the unmanned vessel actuators.

[0030] Secondly, this invention provides an unmanned vessel swarm mapping collaborative system, which is configured with the following modules:

[0031] The watershed topology modeling module is used to plan parallel scan lines for the boundary of the surveying task area based on the acquired boundary of the surveying task area, the width of the scan band of a single ship and the number of participating unmanned ships. It generates a corresponding ideal scan trajectory for each unmanned ship and organizes all ideal scan trajectories according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship.

[0032] The three-source runoff simulation module is used to obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and to obtain the actual position of each neighboring vessel and the corresponding communication link quality index recorded by the unmanned vessel.

[0033] The river network confluence evolution module is used to extract the expected position of the ship and the expected positions of each neighbor at the current moment based on the ideal spatiotemporal topology matrix, and calculate the deviation between the expected relative position and the actual relative position between the ship and each neighbor by combining the actual positions of neighboring ships, and generate a spatiotemporal topology consistency error vector.

[0034] The intelligent parameter inversion optimization module is used to construct a virtual gravitational field based on the spatiotemporal topological consistency error vector, calculate the actual distance between ships based on the actual position of neighboring ships and the current actual position of the ship, and construct a virtual repulsive field. It also dynamically adjusts the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and performs vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on the ship.

[0035] The model parameter hot reload module is used to calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate motion control commands containing the desired heading angle and the updated speed. The motion control commands are used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

[0036] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above-mentioned unmanned vessel swarm mapping collaborative methods.

[0037] Fourthly, this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any of the above-mentioned unmanned vessel swarm mapping collaborative methods.

[0038] In summary, the unmanned surface vessel (USV) swarm mapping collaborative method provided in this application offers a unified spatiotemporal reference for multi-ship collaborative mapping by constructing an ideal spatiotemporal topology matrix. Based on this, a spatiotemporal topology consistency error vector is generated by combining real-time sensed ship position, ocean current, and communication quality information to accurately quantify the degree of scan zone offset caused by environmental disturbances. Furthermore, a virtual gravitational field is used to correct and guide the error, while a virtual repulsive field is used to avoid excessive overlap between ships. The weights of the two types of forces are dynamically adjusted based on communication link quality and ocean current intensity, enabling the control strategy to adapt to complex environments such as incompletely reliable communication and ocean current disturbances. Finally, the generated virtual resultant force is used to calculate the desired course and speed, forming adaptive motion control commands that guide the USV to autonomously correct its coverage path under the combined effect of local perception and global topological constraints. This method effectively suppresses uneven overlap and coverage blind spots between scan zones, ensuring the integrity and consistency of mapping data, and achieving highly robust collaborative mapping operations for USV swarms under weak communication and dynamic sea conditions.

[0039] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0040] Figure 1 A flowchart illustrating a collaborative mapping method for unmanned surface vessels (USVs) swarms, as provided in an embodiment of this application.

[0041] Figure 2 This is a schematic diagram of the structure of an unmanned vessel swarm mapping collaborative system provided in another embodiment of this application. Detailed Implementation

[0042] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Preferred embodiments of the invention are shown in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the invention.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0044] In one embodiment, such as Figure 1 As shown, a collaborative mapping method for unmanned surface vessels (USVs) swarms is provided. This embodiment illustrates the method applied to a terminal, but it is understood that the method can also be applied to a server, or to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] S1: Based on the obtained boundary of the mapping task area, the width of the scan band of a single ship and the number of participating unmanned ships, parallel scan lines are planned for the boundary of the mapping task area, a corresponding ideal scan trajectory is generated for each unmanned ship, and all ideal scan trajectories are organized according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship.

[0046] Specifically, the system acquires the boundary of the mapping task area, the width of the scan band for a single vessel, and the number of participating unmanned surface vessels (USVs). Based on the acquired parameters, the system executes a parallel scan line planning algorithm to plan parallel scan lines along the boundary of the mapping task area. The system determines the distribution pattern of each scan line through the planning algorithm, ensuring that the scan lines cover the entire mapping task area and that adjacent scan lines maintain a preset overlap relationship to meet data stitching requirements. The system generates a corresponding ideal scan trajectory for each USV. The ideal scan trajectory is stored in the form of a coordinate sequence, containing the expected position of each time node on the trajectory. The ideal scan trajectories are parallel to each other and evenly spaced, adapting to the width of the scan band for a single vessel and the number of participating USVs.

[0047] Furthermore, the system organizes all ideal scanning trajectories according to time synchronization constraints. These constraints require all participating unmanned surface vessels (USVs) to maintain a consistent operational sequence, ensuring that each vessel starts its mapping operation simultaneously and arrives at the corresponding node on its trajectory at the same time, thus avoiding misalignment of the scanning band due to timing deviations. Based on the ideal scanning trajectories under time synchronization constraints, the system constructs an ideal spatiotemporal topology matrix. This matrix records the expected positions of each USV at different time nodes and implicitly contains the expected relative positional relationships between the vessels. At any two time nodes, the expected relative positions of any two USVs can be calculated using the coordinate differences of the corresponding elements in the matrix.

[0048] S2: Obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and obtain the actual positions of neighboring vessels and corresponding communication link quality indicators recorded by the unmanned vessel.

[0049] Specifically, the system controls the positioning module and inertial navigation system of each unmanned surface vessel (USV) to collect its current actual position. The system obtains the current actual position coordinates through data fusion processing between the positioning module and the inertial navigation system. The system sets the sampling frequency of the positioning module and compensates for positioning errors through the inertial navigation system. The system controls the USV's speedometer to collect the current speed, sets the speedometer sampling frequency, and ensures that speed and positioning data are synchronized. The system controls the USV's current sensor to collect local ocean current disturbance vectors, converts the current velocity and direction into vector form, and sets the current sensor sampling frequency. The system controls the communication module of each USV to interact with neighboring USVs, determines the range of neighboring USVs, and controls the communication module to receive the actual positions of neighboring USVs.

[0050] The system control communication module collects quality indicators for each communication link, and the system records relevant parameters of the communication links. All collected data is stored in the shipboard data cache module, and the system uses timestamp alignment for data synchronization. The system ensures the temporal consistency of its own data with data from neighboring vessels and environmental data, avoiding calculation errors caused by data asynchrony. The system performs preliminary verification of the collected position data, speed data, ocean current data, and communication link data, and discards invalid data.

[0051] S3: Based on the ideal spatiotemporal topology matrix, extract the expected position of the ship at the current moment and the expected positions of each neighbor. Combine the actual positions of neighboring ships to calculate the deviation between the expected relative position and the actual relative position between the ship and each neighbor, and generate a spatiotemporal topology consistency error vector.

[0052] Specifically, the system invokes the constructed ideal spatiotemporal topology matrix to extract the expected position of the current ship and the expected positions of each neighboring ship. The system performs a coordinate transformation operation on the extracted expected position coordinates, converting them into a coordinate form that facilitates the calculation of relative positions, eliminating calculation biases caused by different coordinate systems. The system invokes the obtained actual positions of neighboring ships and the current actual position of the current ship to calculate the expected and actual relative positions between the current ship and each neighboring ship. The expected relative position is calculated using the coordinate difference between the expected positions of the current ship and neighboring ships, and the actual relative position is calculated using the coordinate difference between the actual positions of the current ship and neighboring ships. The system calculates the relative position deviation between the current ship and each neighboring ship; this deviation is the difference between the actual and expected relative positions, reflecting the degree of deviation between the actual and ideal relative positions. The system arranges the relative position deviations between the current ship and all neighboring ships in a preset order, generating a spatiotemporal topology consistency error vector. This error vector centrally represents the spatiotemporal topology consistency deviation between the current ship and neighboring ships; each element in the vector corresponds to the relative position deviation between the current ship and a certain neighboring ship, providing core input parameters for the construction of the virtual gravitational field.

[0053] S4: Construct a virtual gravitational field based on the spatiotemporal topological consistency error vector, calculate the actual distance between ships based on the actual position of neighboring ships and the current actual position of this ship, and construct a virtual repulsive field. Dynamically adjust the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and then perform vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on this ship.

[0054] Specifically, the system constructs a virtual gravitational field based on the spatiotemporal topological consistency error vector. This virtual gravity is used to guide the vessel towards its ideal relative position, correcting positional deviations. The magnitude of the virtual gravity is positively correlated with the magnitude of the error vector, and its direction is opposite to the error vector. Changes in the magnitude of the error vector correspond to changes in the intensity of the virtual gravity. The system calculates the actual distance between the vessels based on the actual positions of neighboring vessels and the current actual position of the vessel itself, using the distance formula between two points in a Cartesian coordinate system. Based on this actual distance, the system constructs a virtual repulsive field. This virtual repulsive force is used to prevent collisions between unmanned vessels and to prevent excessive overlap of adjacent scan zones. The magnitude of the virtual repulsive force is negatively correlated with the actual distance between the vessels, and its direction is away from that of neighboring vessels. The system dynamically adjusts the weights of gravity and repulsion based on communication link quality indicators and local ocean current disturbance vectors. The weight adjustment follows a preset logic: changes in communication link quality correspond to inverse changes in gravity and repulsion weights, and changes in ocean current disturbance intensity correspond to inverse changes in repulsion and gravity weights. The system performs a vector synthesis operation on the weighted gravitational and repulsive forces to generate a virtual resultant force acting on the ship. During the vector synthesis process, the system first performs weighted calculations on the virtual gravitational and repulsive forces corresponding to each neighboring ship, and then performs overall vector superposition on all weighted gravitational and repulsive forces, so that the virtual resultant force can take into account the influence of all neighboring ships and adapt to the dynamic changes in communication quality and environmental disturbances.

[0055] S5: Calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate motion control commands containing the desired heading angle and the updated speed. The motion control commands are used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

[0056] Specifically, the system calculates the desired heading angle based on the direction of the virtual resultant force. The direction angle of the virtual resultant force is calculated using the arctangent function in a Cartesian coordinate system. The system performs a smoothing operation on the calculated heading angle to eliminate abrupt changes and prevent drastic changes in the unmanned surface vessel's heading from affecting the mapping data. The system calculates a speed adjustment based on the magnitude of the virtual resultant force. The speed adjustment is positively correlated with the magnitude of the virtual resultant force; changes in the magnitude of the virtual resultant force correspond to changes in the magnitude of the speed adjustment, used to quickly correct positional deviations. The system superimposes the speed adjustment with the reference speed to obtain the updated speed. The system then applies a range restriction operation to the updated speed to ensure it meets the requirements of the mapping operation, balancing data quality and operational efficiency. The system generates motion control commands containing the desired heading angle and the updated speed. These commands are transmitted to the unmanned surface vessel's onboard control system using a standardized communication protocol. After parsing the commands, the onboard control system drives the unmanned surface vessel to perform the corresponding actions, controlling it to navigate according to the corrected heading and speed. The system receives navigation status data from the shipboard control system and uses it as the basis for the next round of deviation calculation, virtual force field generation, and control command adjustment, forming a closed-loop control system to maintain the ideal spatiotemporal topology of the unmanned vessel cluster and ensure the smooth execution of the surveying and mapping mission.

[0057] In summary, the unmanned surface vessel (USV) swarm mapping collaborative method provided in this application offers a unified spatiotemporal reference for multi-ship collaborative mapping by constructing an ideal spatiotemporal topology matrix. Based on this, a spatiotemporal topology consistency error vector is generated by combining real-time sensed ship position, ocean current, and communication quality information to accurately quantify the degree of scan zone offset caused by environmental disturbances. Furthermore, a virtual gravitational field is used to correct and guide the error, while a virtual repulsive field is used to avoid excessive overlap between ships. The weights of the two types of forces are dynamically adjusted based on communication link quality and ocean current intensity, enabling the control strategy to adapt to complex environments such as incompletely reliable communication and ocean current disturbances. Finally, the generated virtual resultant force is used to calculate the desired course and speed, forming adaptive motion control commands that guide the USV to autonomously correct its coverage path under the combined effect of local perception and global topological constraints. This method effectively suppresses uneven overlap and coverage blind spots between scan zones, ensuring the integrity and consistency of mapping data, and achieving highly robust collaborative mapping operations for USV swarms under weak communication and dynamic sea conditions.

[0058] In one embodiment, S1 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0059] S11: Based on the acquired boundary of the mapping task area, the width of the single-ship scan band, and the number of participating unmanned vessels, the boundary of the mapping task area is divided into equal horizontal intervals based on the width of the single-ship scan band. The expected spacing between adjacent scan lines is calculated, and the starting point coordinates of each scan line are determined according to the number of participating unmanned vessels, generating the initial scan baseline corresponding to each ship.

[0060] Specifically, the system acquires the boundary of the mapping task area, the width of the single-ship scan strip, and the number of participating unmanned surface vessels (USVs). Using the width of the single-ship scan strip as the core basis, the system performs lateral equal-spacing division of the mapping task area boundary. During the division process, the system ensures that the divided scan area completely covers the mapping task area, while maintaining a preset overlap relationship between adjacent divided areas. This overlap relationship ensures effective stitching of subsequent ship scan data and avoids mapping blind spots. The system calculates the expected spacing between adjacent scan lines using relevant algorithms. The calculation of the expected spacing is derived by combining the single-ship scan strip width and overlap requirements, ensuring that the scan strips corresponding to adjacent scan lines can achieve effective overlap while avoiding excessive overlap that would waste operational resources. Based on the number of participating USVs, the system allocates the divided scan lines, determining the USV affiliation for each scan line. The system, combined with the geometric characteristics of the mapping task area boundary, determines the starting point coordinates of each scan line. The starting point coordinates must fall on the boundary of the mapping task area, and the starting points of each scan line must be evenly distributed to ensure that the starting position of each ship's scanning operation is reasonable. The system integrates the starting point coordinates and extension direction of each scan line to generate the initial scan baseline for each ship. The initial scan baseline serves as the basis for subsequent timing planning and trajectory optimization, and contains complete path information of the scan line.

[0061] S12: Apply time-dimensional synchronization constraints to the initial scan baseline and perform timing planning. Based on the preset reference speed, register the timestamp corresponding to the same mileage position for each scan line and generate the expected position-time function for each ship.

[0062] Specifically, the system extracts the initial scanning baselines generated for each vessel, applies time-dimensional synchronization constraints to all initial scanning baselines, and performs time-series planning. The core purpose of the time-dimensional synchronization constraints is to ensure that the scanning operations of all participating unmanned surface vessels maintain temporal consistency, avoiding misalignment of scanning bands due to timing deviations between vessels, which would affect the stitching quality of the mapping data. The system calls a preset reference speed, set according to the overall requirements of the mapping operation, to unify the speed benchmark of each vessel and ensure that the speed of each vessel along the scanning line remains consistent. Based on the reference speed, the system assigns a timestamp corresponding to the same mileage position for each scanning line. The mileage position is calculated from the starting point of the scanning line and gradually increases along the direction of the scanning line. Each mileage position corresponds to a unique timestamp, ensuring that the operation time of each vessel at the same mileage position remains synchronized. Through the correspondence between timestamps and mileage positions, combined with the path information of the initial scanning baselines, the system constructs the desired position-time function for each vessel. This function can clearly reflect the expected position of the unmanned vessel at different points in time, establish a clear correspondence between time and position, provide standardized data for subsequent matrix encapsulation processing, and ensure that the expected trajectory of each vessel can meet the time synchronization requirements.

[0063] S13: Perform matrix encapsulation of the desired position-time function, integrate the desired trajectories of each ship into a multi-dimensional time series data matrix according to the ship number order, and construct an ideal spatiotemporal topology matrix containing global desired position information.

[0064] Specifically, the system extracts the generated expected position-time functions for each vessel and performs matrix encapsulation processing on each function. This matrix encapsulation process converts the expected position-time functions into standardized time-series data. The system then extracts the expected position coordinates corresponding to each time point in sequence, forming a time-series position data sequence for each vessel. This sequence contains the expected position information for the vessel at all time points, ensuring data integrity and order. The system integrates the time-series position data sequences of all unmanned vessels according to their vessel numbers, constructing a multi-dimensional time-series data matrix. In this matrix, rows correspond to different vessel numbers, columns correspond to different time points, and matrix elements represent the expected position coordinates of the corresponding vessel number at the corresponding time point, enabling centralized storage and unified management of the expected trajectories of all vessels. Based on this multi-dimensional time-series data matrix, the system constructs an ideal spatiotemporal topology matrix. The ideal spatiotemporal topology matrix contains global expected position information, which can fully reflect the expected positions of all unmanned vessels at different time points. It also implies the expected relative positional relationship between the vessels. The expected relative positions of any two unmanned vessels at any time point can be calculated by the coordinate difference of the corresponding elements in the matrix. This provides global reference data for the subsequent collaborative control and trajectory correction of the unmanned vessel cluster, ensuring the orderly conduct of collaborative mapping operations.

[0065] In one embodiment, S3 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0066] S31: Based on the current time index, perform a table lookup process on the ideal spatiotemporal topology matrix to extract the expected position of the ship and the expected positions of all its neighbors, and generate the expected position set for the current time.

[0067] Specifically, the system obtains the time index of the current moment, which corresponds one-to-one with the time dimension nodes of the ideal spatiotemporal topology matrix, used to locate relevant data for the current moment in the matrix. The system performs a lookup operation on the ideal spatiotemporal topology matrix, determining the target row and target column based on the time index. The target row corresponds to the ID of each unmanned surface vessel (USV), and the target column corresponds to the time node of the current moment. The system extracts the expected position corresponding to its own vessel through the lookup operation, and simultaneously extracts the expected positions corresponding to all neighbors. Neighbor identification is based on the determination of USVs within the inter-vessel communication range, ensuring that the extracted neighbor expected positions are all USV position data that have overlapping scan bands with the current vessel. The system integrates the extracted expected position of the current vessel and the expected positions of all neighbors to generate the expected position set for the current moment. The mathematical expression for the expected position set is defined as follows:

[0068]

[0069] in, This represents the expected set of positions at the current moment. This represents the time index of the current moment. This represents the expected position vector of the ship at the current moment. Let $k$ represent the expected position vectors of each neighbor at the current time, and let $$k$$ represent the number of neighbors. The expected position set provides the basic data for subsequent calculations of relative displacement vectors.

[0070] S32: Perform vector difference operations on the desired position set and the actual positions of neighboring ships, calculate the desired relative displacement vector and the actual relative displacement vector between the ship and each neighbor, and generate paired relative position relationship data.

[0071] Specifically, the system extracts the expected position set generated by S31 at the current moment, and simultaneously calls the previously acquired actual position data of neighboring ships. This actual position data is transmitted to the system by each neighboring ship via inter-ship communication links. The system verifies the validity of the transmitted data to ensure it can be used for subsequent calculations. The system performs vector difference operations on the expected position set and the actual positions of neighboring ships. The vector difference operation uses the ship's own position as a reference to calculate the expected relative displacement vector and the actual relative displacement vector between the ship and each neighboring ship. The expected relative displacement vector is obtained by the vector difference between the ship's expected position and the corresponding neighbor's expected position, and the actual relative displacement vector is obtained by the vector difference between the ship's current actual position and the corresponding neighbor's actual position. The system defines the calculation expressions for the expected relative displacement vector and the actual relative displacement vector as follows:

[0072]

[0073]

[0074] in, This represents the expected relative displacement vector between the ship and its j-th neighbor at the current moment. This represents the expected location vector of the j-th neighbor. This represents the actual relative displacement vector between the ship and its j-th neighbor at the current moment. This represents the current actual position vector of the ship. This represents the actual position vector of the j-th neighbor. The system associates and stores each pair of expected relative displacement vectors and actual relative displacement vectors, generating pairs of relative position relationship data to provide paired comparison data for subsequent error calculation.

[0075] S33: Perform pairwise difference and error accumulation processing on the expected relative displacement vector and the actual relative displacement vector, calculate the vector deviation between the two and construct a multidimensional error vector to generate a spatiotemporal topological consistency error vector characterizing the degree of overlap or gap in the scanning band.

[0076] Specifically, the system extracts the paired relative positional relationship data generated by S32, performs pairwise differencing on each pair of expected and actual relative displacement vectors, calculates the difference between each pair of vectors, and obtains the deviation of a single pair of relative displacement vectors. The system then performs error accumulation processing on the deviations of all single pairs of relative displacement vectors, integrating all individual deviations to eliminate the impact of a single deviation on the overall error assessment and ensure the accuracy of the error representation. Through pairwise differencing and error accumulation processing, the system calculates the vector deviation between the expected and actual relative displacement vectors, and then constructs a multidimensional error vector. The system defines the expression for the spatiotemporal topological consistency error vector as follows:

[0077]

[0078] in, This represents the spatiotemporal topology consistency error vector of the ship at the current moment. This represents the relative displacement vector deviation between the current ship and its j-th neighbor at the current moment. It is calculated as the difference between the expected relative displacement vector and the actual relative displacement vector. This represents the transpose operation of a vector. This represents the number of neighbors. This error vector can characterize the degree of overlap or gaps in the scan bands. When the magnitude of the error vector is large, it indicates that there is excessive overlap or coverage gaps in the scan bands. The system uses this error vector as the core input parameter for subsequent virtual force field construction.

[0079] In one embodiment, S4 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0080] S41: Perform gravitational field function mapping on the spatiotemporal topological consistency error vector, introduce a nonlinear attenuation factor to adjust the amplitude gain of each component in the error vector, convert the position deviation into a directional gravitational intensity, and generate the first virtual gravitational vector acting on the ship.

[0081] Specifically, the system calls the spatiotemporal topological consistency error vector for gravitational field function mapping. The system introduces a nonlinear attenuation factor, which adjusts the amplitude gain of each component in the error vector to prevent a sudden surge in gravitational intensity due to excessive error, thus avoiding abrupt changes in the unmanned vessel's course. Simultaneously, it ensures that gravity can effectively drive position correction when the error is small. Through mapping, the system converts the position deviation into a directional gravitational intensity, the direction of which aligns with the direction of the position deviation, used to drive the vessel back to its ideal relative position. Specifically, the formula for calculating the first virtual gravitational vector is:

[0082]

[0083] in, This is the first virtual gravitational vector. Let be the spatiotemporal topological consistency error vector. The gravitational coefficient, Let be the scaling parameter for Gaussian decay. For communication link quality indicators, For the desired scan band spacing, This is an asymmetric adjustment coefficient.

[0084] To achieve adaptive adjustment of gravitational strength, the system introduces an optimization formula for communication link quality indicators:

[0085]

[0086] in, Let be the signal-to-noise ratio of the communication between this ship and its j-th neighbor at the current moment. The maximum signal-to-noise ratio of the communication link. This represents the packet loss rate of the communication link between the ship and its j-th neighbor at the current moment. The system uses this innovative formula to quantify the communication link quality into a gravity adjustment coefficient, ensuring that the intensity of the gravitational force can be adaptively matched when communication quality varies, generating the first virtual gravity vector acting on the ship, and providing gravity input for subsequent weighted synthesis.

[0087] S42: Calculate the Euclidean distance between the actual position of the neighboring ship and the current actual position, and compare the calculated actual distance between the ships with the repulsive force threshold preset based on the scan band width. For neighbors whose distance is less than the threshold, trigger the repulsive field function, calculate the repulsive force intensity and direction for neighbors that meet the conditions, and construct a repulsive vector field according to the principle that the closer the distance, the stronger the repulsive force, and generate a second virtual repulsive force vector acting on the ship.

[0088] Specifically, the system calls the actual positions of neighboring vessels and the current actual position of the current vessel obtained by S2, calculates the Euclidean distance between the two types of position data, and obtains the actual distance between the current vessel and each neighbor. The system calls a repulsive force threshold preset based on the scan band width, compares the calculated actual distance between vessels with the repulsive force threshold, and filters out neighbors whose actual distance between vessels is less than the repulsive force threshold, triggering the repulsive field function for these neighbors. Following the principle that the closer the distance, the stronger the repulsive force, the system calculates the repulsive force intensity and direction for neighbors that meet the conditions. The repulsive force intensity increases as the actual distance between vessels decreases, and the repulsive force direction is away from the corresponding neighbor, used to avoid collisions between unmanned vessels. The formula for calculating the second virtual repulsive force vector is:

[0089]

[0090] in, This is the second virtual repulsion vector. This is the actual distance between the ships. The threshold of repulsive force. The repulsion coefficient is... This is the adaptive boundary weight function. To achieve dynamic adaptive adjustment of the repulsive force, the system defines an adaptive boundary weight function:

[0091]

[0092] in, The threshold of repulsive force. The actual distance between the ships is denoted as . This innovative formula dynamically changes the weights based on the distance between the ships; the closer the ships are, the greater the weight and the more significant the repulsive force. The system constructs a repulsive vector field, integrates the repulsive forces of all neighboring ships that meet the conditions, and generates a second virtual repulsive force vector acting on the ship itself.

[0093] S43: Perform communication reliability analysis on the communication link quality index, map the communication quality level to the confidence coefficient of the gravitational effect, and at the same time assess the environmental disturbance intensity of the local ocean current disturbance vector, adjust the sensitivity coefficient of the repulsive effect in the opposite direction according to the strength of the ocean current, and generate the gravitational weight coefficient and the repulsive weight coefficient respectively.

[0094] Specifically, the system calls the acquired communication link quality indicators and performs communication reliability analysis on them. During the analysis, the system quantifies the communication link quality indicators and maps them to a confidence coefficient of gravitational effect based on the communication quality level. The higher the communication quality, the larger the confidence coefficient, and the higher the weight of the gravitational effect, ensuring that position deviations are corrected by gravity first when communication is reliable. Simultaneously, the system calls the acquired local ocean current disturbance vector and assesses the environmental disturbance intensity of the local ocean current disturbance vector. During the assessment, the system calculates the magnitude of the ocean current disturbance vector and adjusts the sensitivity coefficient of the repulsive effect in the opposite direction based on the strength of the ocean current. The stronger the ocean current disturbance, the larger the sensitivity coefficient, and the higher the weight of the repulsive effect, ensuring that collisions between ships are avoided first when ocean current disturbances are severe. Preferably, the system calculates the gravity weight coefficient using the following formula:

[0095]

[0096] in, For gravity weighting coefficients, This represents the average quality index of all neighboring communication links at the current moment. This is the assessment value for the intensity of ocean current disturbance. Further, the system calculates the repulsive force weighting coefficient. ,in This is the repulsive force weighting coefficient. This is the gravity weighting coefficient. It is obtained by averaging the communication link quality indicators of all neighbors. The system generates gravitational weight coefficients and repulsive weight coefficients respectively through the two innovative formulas mentioned above, obtained by quantifying the magnitude of the local ocean current disturbance vector, thereby realizing the dynamic adaptive adjustment of the weights of gravitational and repulsive forces.

[0097] S44: Perform weighted vector synthesis processing on the virtual gravity vector, virtual repulsion vector, gravity weight coefficient, and repulsion weight coefficient. Then, superimpose the coordinate components of the result of multiplying the gravity vector by the gravity weight coefficient and the repulsion vector by the repulsion weight coefficient to generate the virtual resultant force acting on the ship.

[0098] Specifically, the system calls the first virtual gravity vector, the second virtual repulsion vector, as well as the gravity weight coefficient and the repulsion weight coefficient, to perform weighted vector synthesis on the above four parameters. During the synthesis process, the system first multiplies the first virtual gravity vector with the gravity weight coefficient to obtain a weighted virtual gravity vector, which reflects the actual driving effect of gravity on the ship's navigation under current communication quality and ocean current disturbance conditions. Simultaneously, the system multiplies the second virtual repulsion vector with the repulsion weight coefficient to obtain a weighted virtual repulsion vector, which reflects the actual constraint effect of repulsion on the ship's navigation under current environmental conditions. The system then superimposes the coordinate components of the weighted virtual gravity vector and the weighted virtual repulsion vector, summing the components along the x-axis and y-axis respectively to obtain the synthesized vector components. Preferably, the system completes the weighted vector synthesis using the following formula:

[0099]

[0100] in, For the virtual resultant force acting on the ship, For gravity weighting coefficients, This is the first virtual gravitational vector. This is the repulsive force weighting coefficient. This is the second virtual repulsive force vector. This innovative formula achieves the synergistic effect of attraction and repulsion. The system ensures the accuracy of the synthesis process by superimposing coordinate components, generating a virtual resultant force acting on the ship. The direction of the virtual resultant force determines the direction of the ship's course correction, and the magnitude determines the adjustment range of course and speed.

[0101] In one embodiment, S5 of the unmanned vessel swarm mapping collaborative method provided by the present invention specifically includes the following steps:

[0102] S51: Perform vector direction calculation on the virtual resultant force, calculate the azimuth angle of the resultant force vector relative to the reference coordinate system through the arctangent function, and perform relative turning angle conversion based on the current heading of the hull to generate the desired heading angle.

[0103] Specifically, the system calls the virtual resultant force generated by S44 and performs vector direction calculation on the virtual resultant force. During the calculation, the system first determines a reference coordinate system, which is used to unify the calculation reference for the vector direction and ensure consistency in the azimuth angle calculation. The system calculates the azimuth angle of the virtual resultant force vector relative to the reference coordinate system using the arctangent function. The azimuth angle is used to characterize the absolute direction of the virtual resultant force, providing a basis for generating the heading angle. Simultaneously, the system obtains the ship's current heading, which is the actual direction of the ship's current navigation. Based on the ship's current heading, the system converts the calculated absolute azimuth angle into a relative turning angle to eliminate the deviation between the absolute azimuth angle and the ship's heading, obtaining the relative turning angle, and then generating the desired heading angle. Preferably, the system uses the following formula to complete the calculation of the desired heading angle:

[0104]

[0105] in, The desired heading angle at the current moment. and These represent the components of the virtual resultant force along the x-axis and y-axis of the reference coordinate system, respectively. The current bow orientation of the ship. This is the heading adjustment factor. This represents the heading deviation at the current moment. The value is obtained from the difference between the current heading and the expected heading angle at the previous moment. Used to adjust the smoothness of heading change, the system uses this formula to accurately calculate the heading angle, and the generated expected heading angle can accurately reflect the steering direction indicated by the virtual resultant force.

[0106] S52: Perform vector amplitude calculation and dynamic mapping on the virtual resultant force, divide the resultant force by the virtual mass and multiply by the control period to obtain the speed adjustment amount, and perform smoothing filtering on the speed adjustment amount to eliminate high-frequency jitter and generate the speed regulation amount.

[0107] Specifically, the system calls the generated virtual resultant force, calculates its vector magnitude, and obtains its magnitude through vector magnitude calculation. The magnitude of the resultant force directly reflects the intensity of the heading and speed adjustment requirements. The system performs dynamic mapping on the virtual resultant force magnitude, converting it into a speed adjustment amount that conforms to the ship's motion characteristics. The system divides the resultant force magnitude by the virtual mass and then multiplies it by the control cycle to obtain the preliminary speed adjustment amount. The virtual mass is used to simulate the inertial characteristics of the ship's motion, and the control cycle is used to match the system's data sampling and control cycle frequency to ensure that the speed adjustment amount is consistent with the system's control rhythm. Since the speed adjustment amount may contain high-frequency jitter, affecting the stability of ship navigation and the quality of mapping data, the system performs smoothing filtering on the speed adjustment amount to eliminate high-frequency jitter components and obtain a stable speed adjustment amount. The system implements smoothing filtering through the following formula:

[0108]

[0109] in, This is the smoothed speed adjustment amount at the current moment. These are the filter coefficients. This is the initial speed adjustment for the current moment. This represents the speed adjustment amount after smoothing from the previous moment. This formula is used to adjust the filtering effect and balance the adjustment response speed and smoothness. The system generates the speed adjustment amount through this formula to ensure that the adjustment amount is stable and reliable and meets the ship speed control requirements.

[0110] S53: Perform algebraic superposition of the speed adjustment amount and the preset reference speed, add the adjustment amount to the reference speed to obtain the preliminary updated speed, and apply the ship dynamic constraint range limit to the preliminary updated speed to generate the constraint updated speed.

[0111] Specifically, the system calls the speed adjustment amount and the preset baseline speed, performs algebraic superposition on them, and adds the speed adjustment amount to the baseline speed to obtain the initial updated speed. The baseline speed is the system's preset basic ship speed, used to ensure the efficiency and data quality of surveying operations. The speed adjustment amount is used to dynamically correct the speed based on the virtual resultant force, ensuring that the ship can respond promptly to position deviations and environmental disturbances. Due to the dynamic constraints of the ship's propulsion system, the initial updated speed may exceed the ship's operational speed range, leading to propulsion system overload or malfunction. The system applies a dynamic constraint range limiting process to the initial updated speed, restricting it within the range that the ship's propulsion system can withstand, thus generating a constrained updated speed. Preferably, the system uses the following formula to complete the limiting process:

[0112]

[0113] in, To constrain the updated speed at the current moment, The minimum operational speed of the vessel. The maximum operating speed of the ship. To preset the baseline speed, This represents the speed adjustment amount at the current moment. and Determined by the characteristics of the ship's propulsion system, the system achieves constrained speed control through this formula. The generated constrained updated speed can both respond to the adjustment requirements of the virtual resultant force and ensure the safe and stable operation of the ship's propulsion system.

[0114] S54: Performs instruction encoding and protocol encapsulation processing on the desired heading angle and constraint update speed, converts the control parameters into a data frame format that conforms to the ship autopilot communication protocol, and generates motion control commands that can be parsed by the unmanned vessel actuators.

[0115] Specifically, the system calls the desired heading angle and the constraint-updated speed, and encodes these two control parameters. During encoding, the system converts the desired heading angle and constraint-updated speed into standardized digital signals to ensure the accuracy and consistency of parameter transmission. Simultaneously, the system performs protocol encapsulation on the encoded digital signals, converting the control parameters into a data frame format conforming to the protocol specifications, according to the communication protocol requirements of the ship's autopilot. The data frame format must include synchronization fields, address fields, control parameter fields, and check fields to ensure that the unmanned surface vessel's actuators can correctly identify and parse it. The system completes the data frame encapsulation using the following formula:

[0116]

[0117] in, This is the communication data frame at the current moment. This is a synchronization field used to achieve synchronization identification of data frames. This is the address field for unmanned surface vessels (USVs), used to distinguish different USVs. For the desired heading angle, To constrain the speed of updates, This is a verification field used to check the integrity of the data frame and prevent errors during data transmission. The system uses this formula to encapsulate the data frame, generate motion control commands that can be parsed by the unmanned vessel's actuators, and send the commands to the ship's propulsion system and steering gear system to drive the ship to sail according to the corrected course and speed.

[0118] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0119] Based on the same inventive concept, this application also provides an unmanned surface vessel (USV) swarm mapping collaborative system for implementing the aforementioned unmanned surface vessel swarm mapping collaborative method. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more USV swarm mapping collaborative system embodiments provided below can be found in the limitations of the unmanned surface vessel swarm mapping collaborative method described above, and will not be repeated here.

[0120] Preferably, such as Figure 2 As shown, the present invention provides an unmanned vessel swarm mapping collaborative system 600, which is configured with the following modules:

[0121] The watershed topology modeling module 610 is used to plan parallel scan lines on the boundary of the surveying task area based on the acquired boundary of the surveying task area, the width of the scan band of a single ship and the number of participating unmanned ships, generate a corresponding ideal scan trajectory for each unmanned ship, and organize all ideal scan trajectories according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship.

[0122] The three-source runoff simulation module 620 is used to obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and to obtain the actual position of each neighboring vessel and the corresponding communication link quality index recorded by the unmanned vessel.

[0123] The River Network Convergence Evolution Module 630 is used to extract the expected position of the current vessel and the expected positions of each neighbor based on the ideal spatiotemporal topology matrix, and calculate the deviation between the expected relative position and the actual relative position between the current vessel and each neighbor by combining the actual positions of neighboring vessels, and generate a spatiotemporal topology consistency error vector.

[0124] The intelligent parameter inversion optimization module 640 is used to construct a virtual gravitational field based on the spatiotemporal topological consistency error vector, calculate the actual distance between ships based on the actual position of the neighboring ship and the current actual position of the ship, and construct a virtual repulsive field. It also dynamically adjusts the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and performs vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on the ship.

[0125] The model parameter hot reload module 650 is used to calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate motion control commands containing the desired heading angle and the updated speed. The motion control commands are used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

[0126] Preferably, the watershed topology modeling module 610 provided in this application is configured with the following units:

[0127] The scanning baseline division unit is used to divide the boundary of the surveying task area into equal horizontal intervals based on the obtained boundary of the surveying task area, the width of the single ship scanning band and the number of participating unmanned ships, and calculate the expected spacing between adjacent scanning lines and determine the starting point coordinates of each scanning line according to the number of participating unmanned ships, thereby generating the initial scanning baseline corresponding to each ship.

[0128] The timing synchronization planning unit is used to apply time dimension synchronization constraints to the initial scanning baseline for timing planning processing. Based on the preset reference speed, it registers the timestamp corresponding to the same mileage position for each scanning line and generates the expected position-time function for each ship.

[0129] The spatiotemporal topology construction unit is used to perform matrix-based encapsulation of the desired position-time function, integrate the desired trajectories of each ship into a multi-dimensional time-series data matrix according to the ship number order, and construct an ideal spatiotemporal topology matrix containing global desired position information.

[0130] Preferably, the river network confluence evolution module 630 provided in this application is configured with the following units:

[0131] The expected position lookup unit is used to perform a lookup process on the ideal spatiotemporal topology matrix based on the time index of the current time, extract the expected position of the ship and the expected positions of all its neighbors, and generate the expected position set at the current time.

[0132] The relative displacement vector calculation unit is used to perform vector difference operations on the desired position set and the actual position of neighboring ships, and calculates the desired relative displacement vector and the actual relative displacement vector between the ship and each neighbor, generating paired relative position relationship data.

[0133] The topology consistency error construction unit is used to perform pairwise difference and error accumulation processing on the expected relative displacement vector and the actual relative displacement vector, calculate the vector deviation between the two and construct a multidimensional error vector, and generate a spatiotemporal topology consistency error vector characterizing the degree of overlap or gap in the scan band.

[0134] Preferably, the intelligent parameter inversion optimization module 640 provided in this application is configured with the following units:

[0135] The virtual gravity mapping unit is used to perform gravitational field function mapping on the spatiotemporal topological consistency error vector. It introduces a nonlinear attenuation factor to adjust the amplitude gain of each component in the error vector, converts the position deviation into a directional gravitational intensity, and generates the first virtual gravity vector acting on the ship.

[0136] The neighboring ship repulsion field construction unit is used to calculate the Euclidean distance between the actual position of the neighboring ship and the current actual position, and compare the calculated actual distance between the ships with a repulsion action threshold preset based on the scanning band width. For neighbors whose distance is less than the threshold, the repulsion field function is triggered. For neighbors that meet the conditions, the repulsion intensity and direction are calculated, and a repulsion vector field is constructed according to the principle that the closer the distance, the stronger the repulsion. A second virtual repulsion vector is generated that acts on the ship.

[0137] The dynamic weight coefficient generation unit is used to perform communication reliability analysis on communication link quality indicators, and to map the communication quality level to the confidence coefficient of the gravitational effect. At the same time, it assesses the environmental disturbance intensity of the local ocean current disturbance vector, and adjusts the sensitivity coefficient of the repulsive effect in the opposite direction according to the strength of the ocean current, and generates the gravitational weight coefficient and the repulsive weight coefficient respectively.

[0138] The resultant force vector synthesis unit is used to perform weighted vector synthesis processing on the virtual gravity vector, virtual repulsion vector, gravity weight coefficient, and repulsion weight coefficient. The resultant force is generated by superimposing the coordinate components of the resultant force after multiplying the gravity vector by the gravity weight coefficient and the resultant force after multiplying the repulsion vector by the repulsion weight coefficient, thus generating the virtual resultant force acting on the ship.

[0139] Preferably, the model parameter hot reload module 650 provided in this application is configured with the following units:

[0140] The desired heading calculation unit is used to perform vector direction calculation on the virtual resultant force. It calculates the azimuth angle of the resultant force vector relative to the reference coordinate system through the arctangent function, and performs relative turning angle conversion based on the current heading of the ship to generate the desired heading angle.

[0141] The speed adjustment and filtering unit is used to calculate the vector amplitude and perform dynamic mapping processing on the virtual resultant force. The resultant force is divided by the virtual mass and then multiplied by the control period to obtain the speed adjustment amount. The speed adjustment amount is then smoothed and filtered to eliminate high-frequency jitter and generate the speed adjustment amount.

[0142] The speed constraint limiting unit is used to perform algebraic superposition of the speed adjustment amount and the preset reference speed, superimpose the adjustment amount to the reference speed to obtain the initial updated speed, and apply the ship dynamic constraint range limit to the initial updated speed to generate the constraint updated speed.

[0143] The control command encapsulation unit is used to encode and encapsulate the desired heading angle and constraint update speed, convert the control parameters into a data frame format that conforms to the ship autopilot communication protocol, and generate motion control commands that can be parsed by the unmanned vessel actuators.

[0144] In one embodiment, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described unmanned vessel swarm mapping collaborative method.

[0145] In one embodiment, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned unmanned vessel swarm mapping collaborative method.

[0146] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0147] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0148] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A collaborative mapping method for unmanned surface vessels (USVs), characterized in that, Includes the following steps: S1: Based on the obtained boundary of the mapping task area, the width of the scan band of a single ship and the number of participating unmanned ships, parallel scan lines are planned for the boundary of the mapping task area, a corresponding ideal scan trajectory is generated for each unmanned ship, and all ideal scan trajectories are organized according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship. S2: Obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and obtain the actual positions of neighboring vessels and corresponding communication link quality indicators recorded by each unmanned vessel. S3: Based on the ideal spatiotemporal topology matrix, extract the expected position of the ship at the current moment and the expected positions of each neighbor. Combine the actual positions of the neighboring ships to calculate the deviation between the expected relative position and the actual relative position between the ship and each neighbor, and generate a spatiotemporal topology consistency error vector. S4: Construct a virtual gravitational field based on the spatiotemporal topology consistency error vector, calculate the actual distance between the ships based on the actual positions of the neighboring ships and the current actual position of the ship, and construct a virtual repulsive field. Dynamically adjust the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and perform vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on the ship. S5: Calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment amount based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate a motion control command containing the desired heading angle and the updated speed. The motion control command is used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

2. The method according to claim 1, characterized in that, S1 includes: S11: Based on the obtained boundary of the mapping task area, the width of the single-ship scan band and the number of participating unmanned ships, the boundary of the mapping task area is divided into equal horizontal intervals based on the width of the single-ship scan band, the expected spacing between adjacent scan lines is calculated, and the starting point coordinates of each scan line are determined according to the number of participating unmanned ships, generating the initial scan baseline corresponding to each ship. S12: Apply time dimension synchronization constraints to the initial scanning baseline and perform time-series planning processing. Based on the preset reference speed, register the timestamp corresponding to the same mileage position for each scanning line and generate the expected position-time function for each ship. S13: The expected position-time function is matrix-encapsulated, and the expected trajectories of each ship are integrated into a multi-dimensional time-series data matrix according to the ship number order to construct an ideal spatiotemporal topology matrix containing global expected position information.

3. The method according to claim 1, characterized in that, S3 includes: S31: Based on the time index of the current moment, perform a table lookup process on the ideal spatiotemporal topology matrix to extract the expected position of the ship and the expected positions of all its neighbors, and generate the expected position set for the current moment; S32: Perform vector difference operation on the expected position set and the actual position of the neighboring ship to calculate the expected relative displacement vector and the actual relative displacement vector between the ship and each neighbor, and generate paired relative position relationship data. S33: Perform pairwise difference and error accumulation processing on the expected relative displacement vector and the actual relative displacement vector, calculate the vector deviation between the two and construct a multidimensional error vector, and generate a spatiotemporal topological consistency error vector characterizing the degree of overlap or gap of the scanning band.

4. The method according to claim 1, characterized in that, S4 includes: S41: Perform gravitational field function mapping on the spatiotemporal topological consistency error vector, introduce a nonlinear attenuation factor to adjust the amplitude gain of each component in the error vector, convert the position deviation into a directional gravitational intensity, and generate the first virtual gravitational vector acting on the ship. S42: Calculate the Euclidean distance between the actual position of the neighboring ship and the current actual position, and compare the calculated actual distance between the ships with a repulsive force threshold preset based on the scan band width. Trigger the repulsive field function for neighbors whose distance is less than the threshold, calculate the repulsive force intensity and direction for neighbors that meet the conditions, and construct a repulsive vector field according to the principle that the closer the distance, the stronger the repulsive force, and generate a second virtual repulsive force vector acting on the ship. S43: Perform communication reliability analysis on the communication link quality index, map the communication quality level to the confidence coefficient of the gravitational effect, and at the same time assess the environmental disturbance intensity of the local ocean current disturbance vector, adjust the sensitivity coefficient of the repulsive effect in the opposite direction according to the strength of the ocean current, and generate the gravitational weight coefficient and the repulsive weight coefficient respectively. S44: Perform weighted vector synthesis processing on the virtual gravity vector, the virtual repulsion vector, the gravity weight coefficient, and the repulsion weight coefficient. Then, superimpose the coordinate components of the result of multiplying the gravity vector by the gravity weight coefficient and the repulsion vector by the repulsion weight coefficient to generate a virtual resultant force acting on the ship.

5. The method according to claim 4, characterized in that, The formula for calculating the first virtual gravity vector is: in, This is the first virtual gravitational vector. Let be the spatiotemporal topological consistency error vector. The gravitational coefficient, Let be the scaling parameter for Gaussian decay. For communication link quality indicators, For the desired scan band spacing, This is an asymmetric adjustment coefficient.

6. The method according to claim 4, characterized in that, The formula for calculating the second virtual repulsion vector is: in, This is the second virtual repulsion vector. This is the actual distance between the ships. The threshold of repulsive force. The repulsion coefficient is... This is the adaptive boundary weight function.

7. The method according to any one of claims 1-6, characterized in that, S5 includes: S51: Perform vector direction calculation on the virtual resultant force, calculate the azimuth angle of the resultant force vector relative to the reference coordinate system through the arctangent function, and perform relative turning angle conversion according to the current heading of the ship to generate the desired heading angle; S52: Perform vector amplitude calculation and dynamic mapping processing on the virtual resultant force, divide the resultant force by the virtual mass and multiply by the control period to obtain the speed adjustment amount, and perform smoothing filtering on the speed adjustment amount to eliminate high-frequency jitter and generate the speed adjustment amount. S53: Perform algebraic superposition processing on the speed adjustment amount and the preset reference speed, superimpose the adjustment amount to the reference speed to obtain the preliminary updated speed, and apply a ship dynamic constraint range limit to the preliminary updated speed to generate a constraint updated speed. S54: Perform instruction encoding and protocol encapsulation processing on the desired heading angle and the constraint update speed, convert the control parameters into a data frame format that conforms to the ship autopilot communication protocol, and generate motion control commands that can be parsed by the unmanned ship actuators.

8. A collaborative mapping system for unmanned surface vessels (USVs), characterized in that, The system includes: The watershed topology modeling module is used to plan parallel scan lines on the boundary of the surveying task area based on the acquired boundary of the surveying task area, the width of the scan band of a single ship and the number of participating unmanned ships, generate a corresponding ideal scan trajectory for each unmanned ship, and organize all ideal scan trajectories according to time synchronization constraints to construct an ideal spatiotemporal topology matrix containing the temporal relationship of the expected positions of each ship. The three-source runoff simulation module is used to obtain the current actual position, current speed and local ocean current disturbance vector of each unmanned vessel, and to obtain the actual position of each neighboring vessel and the corresponding communication link quality index recorded by the unmanned vessel. The river network confluence evolution module is used to extract the expected position of the ship and the expected positions of each neighbor at the current moment based on the ideal spatiotemporal topology matrix, and calculate the deviation between the expected relative position and the actual relative position between the ship and each neighbor by combining the actual positions of the neighboring ships, and generate a spatiotemporal topology consistency error vector. The intelligent parameter inversion optimization module is used to construct a virtual gravitational field based on the spatiotemporal topology consistency error vector, calculate the actual distance between ships based on the actual position of the neighboring ship and the current actual position of the ship and construct a virtual repulsive field, and dynamically adjust the weights of the gravitational and repulsive forces based on the communication link quality index and the local ocean current disturbance vector, and perform vector synthesis of the weighted gravitational and repulsive forces to generate a virtual resultant force acting on the ship. The model parameter hot reload module is used to calculate the desired heading angle based on the direction of the virtual resultant force, calculate the speed adjustment amount based on the magnitude of the virtual resultant force and superimpose it with the reference speed to obtain the updated speed, and generate motion control commands containing the desired heading angle and the updated speed. The motion control commands are used to instruct the unmanned vessel to navigate according to the corrected heading and speed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images