An unmanned ship intelligent charging and autonomous berthing cooperation method
By prioritizing and controlling autonomous berthing, combined with a flow field disturbance model, the problems of charging position scheduling and flow field disturbance in large-scale water areas of unmanned vessels were solved, achieving efficient, safe and stable charging and berthing of unmanned vessels.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING HAIZHOU UNMANNED SHIP TECH CO LTD
- Filing Date
- 2026-04-28
- Publication Date
- 2026-07-21
AI Technical Summary
In existing technologies, unmanned vessels lack priority-based coordinated scheduling of charging positions in large-scale waters, resulting in berth conflicts and excessively long waiting times. Furthermore, the local flow field disturbances caused by neighboring vessels are not fully considered during the berthing phase, affecting berthing stability and safety.
By collecting real-time status and environmental data of unmanned vessels, energy consumption coefficients are calculated by dividing the data into grid cells. Berths are allocated based on priority index ranking. Autonomous berthing control is achieved by using conflict detection and speed adjustment, combined with a flow field disturbance proxy model. The course and thrust are dynamically adjusted to overcome flow field disturbances.
It effectively avoids competition for charging spots and path conflicts when multiple unmanned vessels return to port, reduces queuing time, ensures that high-priority tasks are charged first, improves mission continuity and berthing success rate, and reduces collision risk.
Smart Images
Figure CN122431349A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of unmanned vessel charging technology, specifically to a method for intelligent charging and autonomous berthing coordination of unmanned vessels. Background Technology
[0002] With the rapid growth in demand for unmanned equipment in fields such as water monitoring, environmental sampling, and emergency rescue, unmanned vessel swarm operations have become a development trend. In large-scale water areas (such as reservoir groups, watershed rivers, and near-shore aquaculture areas), it is usually necessary to deploy multiple unmanned vessels to coordinate and perform tasks such as inspection, sampling, and early warning.
[0003] However, currently each unmanned surface vessel (USV) triggers its return to recharge independently, without considering the limited number of charging spots. When multiple USVs return simultaneously or sequentially, the lack of priority-based coordinated scheduling can easily lead to berth conflicts or excessively long waiting times, affecting the overall mission continuity. Furthermore, when multiple USVs are docked and charging at multiple berths, the local flow field disturbances caused by neighboring vessels are not fully considered during the USV's berthing phase, resulting in poor berthing stability and even collision winds. Summary of the Invention
[0004] To address this, the present invention provides a collaborative method for intelligent charging and autonomous berthing of unmanned vessels, which solves the problems in the prior art where multiple unmanned vessels return simultaneously or sequentially, lack of priority-based collaborative scheduling, and insufficient consideration of local flow field disturbances caused by neighboring vessels during the berthing phase.
[0005] To achieve the above objectives, the present invention provides the following technical solution:
[0006] A method for coordinated intelligent charging and autonomous berthing of unmanned vessels includes the following steps:
[0007] S1: Collect real-time status data of each unmanned vessel and environmental data of the operating area. Simultaneously, divide the operating area into M×M grid cells and calculate the energy consumption coefficient per unit distance for each grid cell. ;
[0008] Energy consumption coefficient per unit distance The calculation formula is as follows:
[0009]
[0010] in, This represents the historical baseline energy consumption of the grid under still water and windless conditions. and These are the preset influence weights for water flow and wind force, respectively. To effectively reverse the flow rate, The current wind speed. For battery health;
[0011] S2: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return based on real-time status data. And according to priority index The values are sorted in descending order for all ships waiting to return, and then target berths are assigned to each ship in sequence.
[0012] S3: Calculate the path length from the unmanned vessel to the target berth based on the spatiotemporal energy consumption grid map, then determine the estimated arrival time of the unmanned vessel to the target berth, and perform conflict detection;
[0013] S4: When the unmanned vessel enters the preset proximity area of the target berth, it obtains the neighborhood state information of the target berth from the berth occupancy status table and outputs the composite velocity vector at the entrance of the target berth using the pre-trained flow field disturbance proxy model.
[0014] S5: Based on the composite velocity vector at the entrance of the target berth Calculate the attitude stability value of the unmanned surface vessel. Then determine the attitude stability value. Whether the safety threshold is exceeded, and calculate the additional corrected thrust vector and target rudder angle required by the unmanned vessel propulsion system in the current state based on the judgment result.
[0015] Furthermore, S1 can also collect historical navigation data stored in the central database, including the actual energy consumption E, navigation distance d, and background current speed and wind speed when a ship passes through a grid.
[0016] Furthermore, the specific steps of S2 are as follows:
[0017] S2.1: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return. ;
[0018] S2.2: Collect berth occupancy status data, generate a berth occupancy status table, and record the occupancy status, occupant vessel ID, and physical parameters of each berth.
[0019] S2.3: Sort the returning vessels according to their priority index from high to low, and combine the information on available berths in the berth occupancy status table with the current position of the vessels, and assign a unique target berth to each returning vessel according to the allocation rules.
[0020] Furthermore, the priority index The calculation formula is as follows:
[0021]
[0022] in, The safe return threshold indicates that if the battery level falls below this value, the vessel must return immediately. For unmanned ships The current remaining battery power, For unmanned ships The remaining estimated time for the current task. The total duration determined during task allocation The preset task type weight coefficients, , and These are the preset weighting coefficients.
[0023] Furthermore, the allocation rules are as follows:
[0024] 1) Filter the berth occupancy status table to find the set of all berths that are in an available state;
[0025] 2) For the currently unmanned vessels awaiting allocation Calculate the geometric distance between its current position and each available berth. ;
[0026] 3) Select geometric distance The most recent vacant berths are used for unmanned vessels. The target berth;
[0027] 4) Update the target berth status to occupied and record the occupied vessel ID and physical parameters;
[0028] 5) Repeat steps 2)-4) until all returning vessels have been assigned.
[0029] Furthermore, the conflict determination condition is as follows: A preset time difference threshold is set, and there are overlapping conflicts in the optimal energy consumption grid paths; among them, For unmanned ships The estimated arrival time, For unmanned ships The estimated arrival time;
[0030] If a conflict is detected where the estimated arrival time difference of two or more vessels is less than a preset threshold and the paths conflict, the priority index will be adjusted based on the adjustment rules. Adjustments are made to vessels with smaller values to generate a conflict-free return trajectory sequence.
[0031] Furthermore, the adjustment rule calculates the new speed within the safe speed range. This makes its new estimated arrival time similar to the estimated arrival time of ships with higher priority index values. Meets the preset time difference threshold and safety margin sum;
[0032] New speed The calculation formula is as follows:
[0033]
[0034] in, Priority index The estimated arrival time of the large unmanned vessel. The preset time difference threshold, The path length of the energy-optimal path .
[0035] Furthermore, the specific steps of S4 are as follows:
[0036] S4.1: Obtain the neighborhood status of the target berth: Read the physical parameters and current positions of adjacent moored vessels from the berth occupancy status table;
[0037] S4.2: Using a pre-trained flow field disturbance proxy model, the physical parameters of adjacent moored vessels, background velocity, and current position are input. The output is the additional disturbance velocity vector caused by the neighboring vessels. The background velocity and the additional disturbance velocity are superimposed to obtain the composite velocity vector at the entrance of the target berth. .
[0038] Furthermore, the corrected thrust vector The calculation formula is as follows:
[0039]
[0040] in, and These are the proportional gain and differential gain coefficients, respectively. Let be the angle between the composite velocity vector and the ship's expected direction of travel. The rate of change of the unmanned vessel's lateral position deviation;
[0041] The target rudder angle The calculation formula is as follows:
[0042]
[0043] in, This is the current main propulsion force for unmanned ships. It is a symbolic function.
[0044] This invention offers the following advantages: By prioritizing scheduling and pre-allocating berths, combined with conflict detection and speed adjustment, it effectively avoids charging station contention and path conflicts when multiple unmanned surface vessels (USVs) return simultaneously, reducing queuing time, ensuring high-priority vessels can charge first, and improving overall mission continuity. Simultaneously, real-time updates to the berth occupancy status table ensure the accuracy of berth allocation and prevent collisions.
[0045] Furthermore, by utilizing a local composite flow field model, the impact of adjacent moored vessels on the water flow can be predicted in real time, generating composite velocity vectors and providing crucial environmental information for autonomous berthing of unmanned vessels. Combined with autonomous berthing control, the unmanned vessel can dynamically adjust its course and thrust to overcome flow field disturbances, achieving precise and stable berthing, reducing attitude instability and collision risks caused by changes in water flow, and improving the berthing success rate.
[0046] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. Attached Figure Description
[0047] To more intuitively illustrate the prior art and this application, exemplary drawings are provided below. It should be understood that the specific shapes and structures shown in the drawings should not generally be regarded as limiting conditions for implementing this application; for example, based on the technical concept disclosed in this application and the exemplary drawings, those skilled in the art are able to easily make conventional adjustments or further optimizations to the addition / reduction / classification, specific shapes, positional relationships, connection methods, size ratios, etc. of certain units (components).
[0048] Figure 1 This is a flowchart illustrating the implementation of a collaborative method for intelligent charging and autonomous berthing of unmanned vessels according to the present invention. Detailed Implementation
[0049] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these embodiments are merely for further explanation of the present invention and should not be construed as limiting the scope of protection of the present invention. Technical engineers in the field can make some non-essential improvements and adjustments to the present invention based on the above-described content. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0050] Please see Figure 1 A method for coordinated intelligent charging and autonomous berthing of unmanned vessels includes the following steps:
[0051] S1: Collect real-time status data of each unmanned vessel and environmental data of the operating area. Simultaneously, divide the operating area into M×M grid cells. Based on historical navigation data and real-time environmental data, calculate the energy consumption coefficient per unit distance for each grid cell. The larger the value, the more electricity is consumed by passing through that area, thus generating a spatiotemporal energy consumption grid map. Energy consumption coefficient per unit distance. The calculation formula is as follows:
[0052]
[0053] in, This represents the historical baseline energy consumption of the grid under still water and windless conditions. , This represents the actual energy consumption of a ship passing through this grid in historical navigation data. This represents the distance traveled. and These are the preset influence weights for water flow and wind force, respectively. To effectively reverse the flow rate, The current wind speed. Battery health status (a decimal between 0 and 1, such as 0.9 indicating 90% health).
[0054] Effective countercurrent velocity The calculation formula is as follows:
[0055]
[0056] in, The current water flow velocity. This is the angle between the direction of the water flow and the intended direction of the ship's journey. When going against the current, It is a negative number, if it flows downstream. =0, the faster the counter-current speed. The larger the value, the higher the energy consumption coefficient per unit distance. The larger.
[0057] Real-time status data includes current coordinates, the angle between the current direction and the ship's expected sailing direction, remaining battery power, battery health, current mission type, estimated remaining mission time, and ship physical parameters; ship physical parameters include length, beam, and draft.
[0058] Environmental data are measured in real time by an ADCP (Acoustic Doppler Current Profiler) array deployed in the water, including the magnitude and direction of flow velocity, as well as wind speed and direction at each grid location.
[0059] S1 can also collect historical navigation data stored in the central database. Each piece of historical navigation data includes the actual energy consumption E, navigation distance d, and background current speed and wind speed when a ship passes through a grid.
[0060] S2: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return based on real-time status data. And according to priority index The values are sorted in descending order for all ships waiting to return, and then target berths are assigned to each ship in sequence.
[0061] The specific steps of S2 are as follows:
[0062] S2.1: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return. This index takes into account the urgency of remaining battery power, task completion rate, and task type weighting.
[0063] Priority Index The calculation formula is as follows:
[0064]
[0065] in, The safe return threshold indicates that if the battery level falls below this value, the vessel must return immediately. For unmanned ships The current remaining battery power, For unmanned ships The remaining estimated time for the current task. The total duration determined during task allocation These are preset task type weighting coefficients, representing the importance of different tasks. For example, an emergency task is assigned a weight of 3, a routine task a weight of 1, and a return mission a weight of 0. , and These are the preset weighting coefficients. .
[0066] S2.2: Collect berth occupancy status data, generate a berth occupancy status table, and record the occupancy status, occupant vessel ID, and physical parameters of each berth; this table is updated in real time each time the berth status changes (such as when a vessel enters or leaves).
[0067] S2.3: Based on priority index, vessels awaiting return are sorted from highest to lowest. Combining this with information on available berths in the berth occupancy status table and the vessel's current position, a unique target berth is assigned to each vessel awaiting return. Details are as follows:
[0068] First, based on the priority index All vessels awaiting return are sorted in descending order to obtain a scheduling queue, and target berths are assigned to each vessel sequentially according to the queue order. The allocation rules are as follows:
[0069] 1) Filter the berth occupancy status table to find the set of all berths that are in an available state;
[0070] 2) For the currently unmanned vessels awaiting allocation Calculate the geometric distance between its current position and each available berth. The calculation formula is as follows:
[0071]
[0072] in, For unmanned ships The current position coordinates, The coordinates of the available berths.
[0073] 3) Select geometric distance The most recent vacant berths are used for unmanned vessels. If there are multiple available berths at the same distance from the current vessel, the berth with the smaller number will be selected as the target berth.
[0074] 4) Update the target berth status to occupied and record the occupied vessel ID and physical parameters;
[0075] 5) Repeat steps 2)-4) until all returning vessels have been assigned.
[0076] S3: Calculate the path length from the unmanned vessel to the target berth based on the spatiotemporal energy consumption grid map, and then determine the estimated arrival time of the unmanned vessel to the target berth. If the estimated arrival time difference of two or more vessels is detected to be less than a preset threshold and the paths conflict, then move to the priority index. The rules for adjusting the sending speed of ships with smaller values are used to generate a conflict-free return trajectory sequence.
[0077] First, using the grid where the unmanned vessel is currently located as the starting grid and the grid where the target berth is located as the ending grid, the A* algorithm is used on the spatiotemporal energy consumption grid map to find a grid path from the starting point to the ending point.
[0078] The cost function for this path search is cumulative energy consumption, which is the sum of the energy consumption coefficient of each grid traversed along the path and the actual travel distance within that grid. The total energy consumption is minimized through optimization, thus obtaining the energy-optimal path. The path length of the energy-optimal path is then calculated. The calculation formula is as follows:
[0079]
[0080] in, For the first on the path The coordinates of the center point of each grid This represents the total number of grid nodes included in the path.
[0081] The aforementioned A* algorithm refers to a heuristic search algorithm widely used in graph search and path planning. Its core principle is to guide the search direction by comprehensively considering the actual cumulative cost from the starting point to the current node and the estimated cost from the current node to the target node, thereby efficiently finding the optimal path from the starting point to the target point. In this invention, the algorithm is applied to a spatiotemporal energy consumption grid map. The starting grid (the current position of the unmanned vessel) and the ending grid (the target berth) are used as search endpoints. The energy consumption coefficient per unit distance passing through each grid on the path is multiplied by the actual navigation distance within that grid as the cumulative cost. A preset heuristic function (e.g., the Euclidean distance from the center of the current grid to the center of the target grid multiplied by the minimum energy consumption coefficient of the entire water area) is used to estimate the remaining cost. By continuously expanding the grid nodes with the minimum total cost estimate, an energy-optimal grid path from the starting point to the end point is finally generated.
[0082] Next, calculate the estimated arrival time of the unmanned vessel to the target berth. And based on the estimated arrival time, all returning vessels will undergo pairwise conflict detection. The conflict determination criteria are as follows: The preset time difference threshold, ( For unmanned ships The estimated arrival time) and the energy-optimal grid path have overlapping conflicts; if a conflict is detected, the priority index is adjusted. Small vessels undergo speed adjustments. The adjustment rule is to calculate the new speed within the safe speed range. This makes its new estimated arrival time similar to the estimated arrival time of ships with higher priority index values. Meets the preset time difference threshold and safety margin The sum of (e.g., 1 minute).
[0083] Unmanned ship Estimated arrival time The calculation formula is as follows:
[0084]
[0085] in, This is the current speed of the unmanned vessel.
[0086] New speed The calculation formula is as follows:
[0087]
[0088] in, Priority index The estimated arrival time of the large unmanned vessel. The preset time difference threshold. And the new speed. Must meet the safe speed range of the vessel If the new speed If the speed exceeds this range, it means that the conflict cannot be resolved by adjusting the speed, thus triggering the berth reallocation mechanism.
[0089] S4: When the unmanned vessel enters the preset proximity area of the target berth, it obtains the neighborhood state information of the target berth from the berth occupancy status table, and outputs the composite velocity vector at the entrance of the target berth using the pre-trained flow field disturbance proxy model.
[0090] The specific steps for S4 are as follows:
[0091] S4.1: Obtain the neighborhood status of the target berth: Read the physical parameters and current positions of adjacent moored vessels from the berth occupancy status table;
[0092] When unmanned boat Upon entering a pre-defined approach area with a radius R centered on the target berth, the ship's controller sends a request to the central dispatch system to retrieve the neighboring status information of the target berth from the berth occupancy status table. Adjacent berths are those that share the same berth terminal as the target berth and have adjacent berth numbers.
[0093] S4.2: Using a pre-trained flow field disturbance proxy model, the physical parameters of adjacent moored vessels, background velocity, and current position are input. The output is the additional disturbance velocity vector caused by the neighboring vessels. The background velocity and the additional disturbance velocity are superimposed to obtain the composite velocity vector at the entrance of the target berth. The calculation formula is as follows:
[0094]
[0095] in, For a moment Environmental velocity vector This is a proxy model function for flow field disturbance. For the physical parameter vector of the adjacent ship, This represents the relative positional distance between the berthing vessel and its neighboring vessels.
[0096] The flow field disturbance surrogate model employs a deep neural network (DNN) architecture and is pre-trained offline using sample data of different operating conditions generated by computational fluid dynamics (CFD) software. It can predict in real time the additional disturbance velocity vector caused by obstruction of the water flow by adjacent vessels. The training samples include flow field disturbance data from historical navigation data under different combinations of adjacent vessel drafts, distances, and background flow velocity magnitudes and directions.
[0097] S5: Based on the composite velocity vector at the entrance of the target berth Calculate the attitude stability value of the unmanned surface vessel. This is used to assess the intensity of disturbances during berthing. Attitude stability value. The calculation formula is as follows:
[0098]
[0099] in, For the composite velocity vector The instantaneous lateral hydrodynamic force generated in the underwater part of the hull under the action of the current. This is the maximum lateral thrust resistance that the propulsion system of this type of unmanned surface vessel can provide. This represents the current roll angle of the unmanned vessel. The maximum roll angle safety threshold for unmanned vessels. This represents the current pitch angle of the unmanned vessel. This is the maximum pitch angle safety threshold for the unmanned vessel. , and These are the preset weighting coefficients.
[0100] Then determine the attitude stability value Does it exceed the safety threshold? If the attitude stability value If the safety threshold is exceeded, calculate the additional corrected thrust vector required by the unmanned surface vessel's thrusters in the current state. and target rudder angle The command is then transmitted to the unmanned vessel's onboard controller. Upon receiving the command, the onboard controller dynamically adjusts the corresponding thrust direction and rudder angle of the propellers to counteract the effects of flow field disturbances, enabling the vessel to maintain a stable course and accurately dock in the complex flow field.
[0101] Corrected thrust vector The calculation formula is as follows:
[0102]
[0103] in, and These are the proportional gain and differential gain coefficients, respectively. Let be the angle between the composite velocity vector and the ship's expected direction of travel. This represents the rate of change of the unmanned vessel's lateral position deviation.
[0104] Target rudder angle The calculation formula is as follows:
[0105]
[0106] in, This is the current main propulsion force for unmanned ships. The sign function determines the direction of the rudder angle (left or right rudder).
[0107] This invention effectively avoids charging spot contention and path conflicts when multiple unmanned surface vessels (USVs) return simultaneously by prioritizing scheduling and pre-allocating berths, combined with conflict detection and speed adjustment. This reduces queuing time, ensures high-priority vessels can charge first, and improves overall mission continuity. Simultaneously, real-time updates to the berth occupancy status table ensure accurate berth allocation and prevent collisions.
[0108] Furthermore, by utilizing a local composite flow field model, the impact of adjacent moored vessels on the water flow can be predicted in real time, generating composite velocity vectors and providing crucial environmental information for autonomous berthing of unmanned vessels. Combined with autonomous berthing control, the unmanned vessel can dynamically adjust its course and thrust to overcome flow field disturbances, achieving precise and stable berthing, reducing attitude instability and collision risks caused by changes in water flow, and improving the berthing success rate.
[0109] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for coordinated intelligent charging and autonomous berthing of unmanned vessels, characterized in that, Includes the following steps: S1: Collect real-time status data of each unmanned vessel and environmental data of the operating area. Simultaneously, divide the operating area into M×M grid cells and calculate the energy consumption coefficient per unit distance for each grid cell. ; Energy consumption coefficient per unit distance The calculation formula is as follows: in, The historical baseline energy consumption of the grid under still water and windless conditions. and These are the preset influence weights for water flow and wind force, respectively. To effectively reverse the flow rate, The current wind speed. For battery health; S2: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return based on real-time status data. And according to priority index The values are sorted in descending order for all ships waiting to return, and then target berths are assigned to each ship in sequence. S3: Calculate the path length from the unmanned vessel to the target berth based on the spatiotemporal energy consumption grid map, then determine the estimated arrival time of the unmanned vessel to the target berth, and perform conflict detection; S4: When the unmanned vessel enters the preset proximity area of the target berth, it obtains the neighborhood state information of the target berth from the berth occupancy status table and outputs the composite velocity vector at the entrance of the target berth using the pre-trained flow field disturbance proxy model. S5: Based on the composite velocity vector at the entrance of the target berth Calculate the attitude stability value of the unmanned surface vessel. Then determine the attitude stability value. Whether the safety threshold is exceeded, and calculate the additional corrected thrust vector and target rudder angle required by the unmanned vessel propulsion system in the current state based on the judgment result.
2. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 1, characterized in that, The S1 can also collect historical navigation data stored in the central database, including the actual energy consumption E, navigation distance d, and background current speed and wind speed when a ship passes through a grid.
3. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 1, characterized in that, The specific steps of S2 are as follows: S2.1: Calculate the priority index of the charging needs of each unmanned surface vessel waiting to return. ; S2.2: Collect berth occupancy status data, generate a berth occupancy status table, and record the occupancy status, occupant vessel ID, and physical parameters of each berth. S2.3: Sort the returning vessels according to their priority index from high to low, and combine the information on available berths in the berth occupancy status table with the current position of the vessels, and assign a unique target berth to each returning vessel according to the allocation rules.
4. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 3, characterized in that, The priority index The calculation formula is as follows: in, The safe return threshold indicates that the vessel must return immediately if the battery level falls below this threshold. For unmanned ships The current remaining battery power, For unmanned ships The remaining estimated time for the current task. The total duration determined during task allocation The preset task type weight coefficients, , and These are the preset weighting coefficients.
5. The method for intelligent charging and autonomous berthing coordination of unmanned vessels according to claim 3, characterized in that, The allocation rules are as follows: 1) Filter the berth occupancy status table to find the set of all berths that are in an available state; 2) For the currently unmanned vessels awaiting allocation Calculate the geometric distance between its current position and each available berth. ; 3) Select geometric distance The most recent vacant berths are used for unmanned vessels. The target berth; 4) Update the target berth status to occupied and record the occupied vessel ID and physical parameters; 5) Repeat steps 2)-4) until all returning vessels have been assigned.
6. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 1, characterized in that, The conflict determination condition is as follows: A preset time difference threshold is set, and there are overlapping conflicts in the optimal energy consumption grid paths; among them, For unmanned ships The estimated arrival time, For unmanned ships The estimated arrival time; If a conflict is detected where the estimated arrival time difference of two or more vessels is less than a preset threshold and the paths conflict, the priority index will be adjusted based on the adjustment rules. Adjustments are made to vessels with smaller values to generate a conflict-free return trajectory sequence.
7. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 6, characterized in that, The adjustment rule is to calculate the new speed within the safe speed range. This makes its new estimated arrival time similar to the estimated arrival time of ships with higher priority index values. Meets the preset time difference threshold and safety margin sum; New speed The calculation formula is as follows: in, Priority index The estimated arrival time of the large unmanned vessel. The preset time difference threshold, The path length of the energy-optimal path .
8. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 1, characterized in that, The specific steps of S4 are as follows: S4.1: Obtain the neighborhood status of the target berth: Read the physical parameters and current positions of adjacent moored vessels from the berth occupancy status table; S4.2: Using a pre-trained flow field disturbance proxy model, the physical parameters of adjacent moored vessels, background velocity, and current position are input. The output is the additional disturbance velocity vector caused by the neighboring vessels. The background velocity and the additional disturbance velocity are superimposed to obtain the composite velocity vector at the entrance of the target berth. .
9. The method for coordinated intelligent charging and autonomous berthing of unmanned vessels according to claim 1, characterized in that, The corrected thrust vector The calculation formula is as follows: in, and These are the proportional gain and differential gain coefficients, respectively. Let be the angle between the composite velocity vector and the ship's expected direction of travel. The rate of change of the unmanned vessel's lateral position deviation; The target rudder angle The calculation formula is as follows: in, This is the current main propulsion force for unmanned ships. It is a symbolic function.