Unmanned ship formation path planning method and system based on cloud control

Abstract

The application relates to the technical control field of unmanned ships, in particular to an unmanned ship formation path planning method and system based on cloud control. The method comprises the following steps: obtaining initial position information, target position information and environment information in a navigation area of each unmanned ship in an unmanned ship formation through a cloud platform; constructing a digital map of the navigation area through the cloud platform; planning multiple candidate paths for each unmanned ship through the digital map; calculating a cost function value of each candidate path through a preset cost model, and screening an initial optimal planning path; and updating the optimal planning path by real-time receiving self-position information of each unmanned ship and the environment information in the navigation area through the cloud platform. The application centrally obtains the position information of all unmanned ships in the formation and the environment data of the navigation area through the cloud platform, constructs and real-time updates a unified digital map, and breaks through the limitation of local perception of a single ship in a decentralized control.

Description

Technical Field

[0001] This invention relates to the field of unmanned vessel technology control, and in particular to a cloud-based unmanned vessel formation path planning method and system. Background Technology

[0002] Unmanned surface vessels (USVs) are surface robots that can navigate on water according to pre-set tasks using precise satellite positioning and their own sensors without remote control. These "surface robots" integrate multiple technologies such as ship control, communication, automated control, remote monitoring, and networked systems, achieving functions including autonomous navigation, intelligent obstacle avoidance, long-distance communication, real-time video transmission, and networked monitoring. As a novel technological approach, USVs have already been widely applied in fields such as ocean surveying and maritime defense.

[0003] In existing unmanned surface vessel (USV) platooning path planning methods, some schemes adopt a decentralized control strategy, relying on individual vessels to store route data locally and autonomously adjust their speed to maintain formation. However, this model has significant limitations: due to the lack of globally unified environmental perception and path optimization capabilities, individual vessels can only make decisions based on preset routes and local information, making it difficult to cope with dynamic environmental changes such as the appearance of sudden obstacles or abrupt changes in water flow speed and direction within the navigation area. Furthermore, under decentralized control, the path planning of each vessel is relatively independent, making it difficult to coordinate and optimize the safety and efficiency of the path from a global platooning perspective. This can easily lead to local path redundancy, increased overall platooning energy consumption, and even collision risks due to conflicting trajectories, seriously affecting the reliability of USV platooning mission execution in complex dynamic environments.

[0004] Therefore, it is necessary to design a cloud-controlled unmanned vessel formation path planning method and system. Summary of the Invention

[0005] To address the technical deficiencies in the background technology, this invention proposes a cloud-controlled unmanned vessel formation path planning method and system, which solves the aforementioned technical problems and meets practical needs. The specific technical solution is as follows:

[0006] The cloud-controlled unmanned vessel formation path planning method includes the following steps:

[0007] The initial position information, target position information, and environmental information of each unmanned vessel in the unmanned vessel formation are obtained through the cloud platform.

[0008] Based on environmental information, a digital map of the navigation area is constructed through a cloud platform;

[0009] Based on the initial and target position information of each unmanned vessel, multiple candidate paths are planned for each unmanned vessel using a digital map;

[0010] Based on multiple candidate paths, the cost function value of each candidate path is calculated using a preset cost model, and the initial optimal planning path is selected based on the cost function values ​​of multiple candidate paths.

[0011] During the navigation process according to the initial optimal planned path, each unmanned vessel receives its own position information and environmental information in the navigation area in real time through the cloud platform. The digital map is updated with the environmental information, and the optimal planned path is updated based on the updated digital map and its own position information.

[0012] Furthermore, the environmental information includes obstacle distribution information, water flow speed and direction information, and the digital map divides the navigation area into multiple grid cells, each grid cell corresponding to unique coordinates. The construction of the digital map of the navigation area via a cloud platform specifically includes:

[0013] Based on obstacle distribution information, grid cells containing obstacles are marked as impassable cells via a cloud platform;

[0014] Based on the water flow velocity and direction information, each grid cell is assigned corresponding water flow influence parameters through a cloud platform.

[0015] Furthermore, the process of planning multiple candidate paths for each unmanned vessel using a digital map specifically includes:

[0016] A heuristic search algorithm is used to search and generate multiple paths leading to the destination on the digital map, starting from the grid cell corresponding to the initial position of the unmanned vessel and ending at the grid cell corresponding to the target position, as candidate paths.

[0017] During the search process, ensure that candidate paths do not pass through grid cells marked as impassable.

[0018] Furthermore, the step of calculating the cost function value of each candidate path using a preset cost model specifically includes:

[0019] Calculate the number of grid cells traversed by the candidate path and determine the path length cost;

[0020] Calculate the distance between the center of each grid cell on the candidate path and the nearest obstacle, accumulate the reciprocal of the distance, and determine the distance cost to the obstacle;

[0021] Based on the water flow impact parameters and the angle between the unmanned vessel's navigation direction and the water flow direction, the water flow impact component in each grid cell is calculated. The water flow impact components in all grid cells on the candidate path are accumulated to determine the water flow impact cost.

[0022] The cost function value of the candidate path is obtained by weighting and summing the path length cost, the distance cost from obstacles, and the water flow impact cost according to preset weight coefficients.

[0023] Furthermore, the real-time reception of the unmanned vessel's own position information and environmental information within the navigation area via the cloud platform specifically includes:

[0024] The unmanned vessel obtains its own location information through its onboard positioning equipment and transmits it to the cloud platform through a wireless communication module;

[0025] The unmanned vessel uses its onboard sensors to detect newly appearing obstacles and changes in water flow speed and direction within the navigation area, and transmits the obstacle and change information to the cloud platform via a wireless communication module.

[0026] Furthermore, during the navigation process of each unmanned vessel according to the initial optimal planned path, the following steps are also included:

[0027] Based on the initial optimal planned path of each unmanned vessel in the unmanned vessel formation, calculate the predicted trajectory of any two unmanned vessels in the future period of time, and judge the predicted trajectory of the two unmanned vessels.

[0028] If the predicted trajectories have the potential to intersect, adjust the initial optimal planning path of one of the unmanned vessels according to priority. Based on the adjusted optimal planning path, recalculate whether the predicted trajectories of the adjusted unmanned vessel intersect with those of other unmanned vessels in the unmanned vessel formation. If there is a possibility of intersection, readjust the optimal planning path of the unmanned vessel until there is no possibility of intersection between the predicted trajectories of the adjusted unmanned vessel and those of other unmanned vessels in the unmanned vessel formation. If there is no possibility of intersection, continue to check other unmanned vessel pairs until there is no possibility of intersection between the predicted trajectories of all unmanned vessels.

[0029] Furthermore, the determination of the predicted trajectories of the two unmanned vessels specifically includes:

[0030] The system obtains the initial planned path, maximum speed, minimum turning radius, and current position information of any two unmanned vessels in the unmanned vessel formation. Based on a preset time interval, it calculates the predicted position coordinates of the two unmanned vessels at several future time nodes.

[0031] Based on the predicted position coordinates of two unmanned vessels at several future time points, the distance between the predicted positions of the two unmanned vessels at the same time point is calculated. If the distance is less than the preset safe distance threshold, and the predicted trajectories of the two unmanned vessels before and after the time point show a trend of gradually approaching each other, it is determined that the predicted trajectories of the two unmanned vessels may intersect.

[0032] The safe distance threshold is dynamically adjusted based on the length, width, and speed of the unmanned vessel.

[0033] Furthermore, the adjustment of the initial optimal planned path of one of the unmanned vessels according to priority specifically includes:

[0034] Based on mission priority, current load status, and remaining distance to the target location, determine the unmanned vessels that need to adjust their optimal planning paths;

[0035] Select a new path from multiple candidate paths whose cost function value differs from the original path within a preset range and which can avoid the risk of collision.

[0036] If there is no candidate path whose cost function value differs from the original path within a preset range, the original optimal planning path is locally optimized. During local optimization, turning points are added near the predicted collision area.

[0037] The setting of the turning point must meet the minimum turning radius constraint of the unmanned vessel, and the path after the turn must be staggered in time and space from the predicted trajectory of another unmanned vessel.

[0038] Furthermore, the updating of the digital map through environmental information specifically includes:

[0039] Based on the newly detected obstacle information, update the passage status of the corresponding grid cell in the digital map, and mark the grid cell where the newly appeared obstacle is located as an impassable cell;

[0040] Update the water flow impact parameters of each grid cell in the digital map based on the new water flow velocity and direction information;

[0041] Using the grid cell corresponding to the current position of the unmanned vessel as the new starting point and the grid cell corresponding to the target position as the ending point, a heuristic search algorithm is used again to generate multiple candidate paths, and the optimal planned path is selected again.

[0042] A cloud-controlled unmanned vessel formation path planning system includes a processor and a memory for storing executable instructions of the processor.

[0043] The processor is configured to execute the instructions to implement the steps of the cloud-controlled unmanned vessel formation path planning method described above.

[0044] Compared with existing technologies, the cloud-controlled unmanned vessel formation path planning method and system provided by this invention have the following advantages:

[0045] This invention centrally acquires the position information of all unmanned vessels in a fleet and environmental data of the navigation area through a cloud platform, constructs and updates a unified digital map in real time, overcoming the limitations of "single-vessel local perception" in distributed control. Based on the global digital map, it dynamically generates the optimal path, enabling rapid response to sudden environmental changes and solving the problems of path pre-setting and difficulty in adapting to dynamic environments inherent in distributed methods.

[0046] This invention uses a pre-defined cost model to comprehensively consider multiple factors such as path length, distance to obstacles, and water flow effects to select the globally optimal path. Compared to decentralized methods that only maintain formation through speed adjustments, this invention achieves a balance between safety and efficiency during the path planning stage, reducing ineffective navigation costs.

[0047] This invention uses a cloud platform to predict the future trajectories of each unmanned vessel in real time and adjusts the global priority of potential intersections, ensuring that vessels in the formation navigate at off-peak times in both time and space. This mechanism is superior to the collision avoidance method in decentralized control that relies on fine-tuning the speed of individual vessels, and can fundamentally avoid trajectory conflicts, thus improving the safety of formation coordination. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the cloud-controlled unmanned vessel formation path planning method of the present invention. Detailed Implementation

[0049] In the description of this invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "middle," and "inner," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, it should be noted that unless otherwise explicitly specified and limited, the terms "installed," "connected," and "joined" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention through specific circumstances.

[0050] The embodiments of the present invention will be described below with reference to the accompanying drawings and related examples. The embodiments of the present invention are not limited to the following examples, and the present invention relates to the relevant necessary components in this technical field, which should be regarded as well-known technology in this technical field and can be known and mastered by those skilled in this technical field.

[0051] See Figure 1This invention provides a cloud-controlled unmanned vessel formation path planning method, comprising the following steps:

[0052] Step S100: Obtain the initial position information, target position information, and environmental information within the navigation area of ​​each unmanned vessel in the unmanned vessel formation through the cloud platform.

[0053] The cloud platform is a distributed computing and storage system based on cloud computing technology. Its functions include data fusion, algorithm computation, and command issuance, and it can enable collaborative work among multiple terminal devices through IoT protocols. Initial position information refers to the geographic coordinates of the unmanned surface vessel (USV) at the start of the mission, typically obtained through satellite positioning or inertial navigation systems. Target position information refers to the coordinates of the destination that each USV needs to reach, pre-set or dynamically adjusted by the mission planning system. Environmental information includes the distribution of dynamic and static obstacles within the navigation area, water flow speed and direction, and meteorological data, collected in real time through sensor networks and external data interfaces.

[0054] This is achieved by establishing a communication link to receive and integrate multi-source heterogeneous data. Specifically, this includes the unmanned surface vessel uploading real-time coordinates, the cloud platform receiving target location commands, and the invocation of the environmental monitoring system to obtain real-time environmental parameters. This operation can provide a global data foundation for subsequent path planning, overcoming the limitations of single-vessel local perception and ensuring the integrity of environmental data.

[0055] Step S200: Based on environmental information, construct a digital map of the navigation area through a cloud platform.

[0056] Digital maps are virtual spaces that digitally model physical spaces, containing multi-dimensional data such as geographic coordinate systems, obstacle outlines, and hydrological features, and are in the form of raster maps.

[0057] In step S300, based on the initial position information and target position information of each unmanned vessel, multiple candidate paths are planned for each unmanned vessel using a digital map.

[0058] The candidate path is a set of multiple feasible routes from the starting point to the destination, generated using a heuristic search algorithm. Digital map applications can use obstacles and hydrological data as constraints for path planning, such as setting no-navigation zones or weighting the impact of water flow.

[0059] This is achieved through path search and cost setting. Specifically, it involves determining the path search range based on the initial and target positions, setting the movement cost of path nodes, and using an algorithm to traverse feasible paths and record multiple routes that meet the constraints. This operation can provide diversity in path selection and offer alternative solutions for subsequent optimization.

[0060] Step S400: Based on multiple candidate paths, calculate the cost function value of each candidate path using a preset cost model, and select the initial optimal planning path based on the cost function values ​​of multiple candidate paths.

[0061] The cost model is a mathematical function that integrates path length, safety margin, energy consumption, and mission time. For example, the safety cost can be defined as the reciprocal of the minimum distance between the path and obstacles, while the energy cost can be calculated by combining the direction of water flow and the ship's dynamics model. The cost function value is a comprehensive evaluation value obtained through weighted summation or multiplication; the lower the value, the better the path.

[0062] Specifically, this includes defining the weighting rules for the cost function, calculating the total path length for each candidate path, evaluating the minimum distance between each point on the path and obstacles, simulating the travel time of the path under water flow conditions, and obtaining the comprehensive cost through a weighted formula. This operation can achieve a quantitative balance between safety and efficiency, such as prioritizing paths that avoid strong current areas to reduce energy consumption.

[0063] In step S500, during the navigation process according to the initial optimal planned path, each unmanned vessel receives its own position information and environmental information in the navigation area in real time through the cloud platform. The digital map is updated through the environmental information, and the optimal planned path is updated based on the updated digital map and its own position information.

[0064] Real-time reception is achieved through 5G / satellite communication technology, ensuring that the data update frequency matches the unmanned vessel's travel speed. The digital map update mechanism is implemented through incremental updates, for example, updating map data only in areas where obstacles have moved.

[0065] This can be achieved through closed-loop control and prediction algorithms, specifically including continuously collecting data, detecting environmental changes, triggering local map updates, re-executing path planning, and issuing new paths. This operation can enhance the ability to adapt to dynamic environments, such as quickly adjusting the path to maintain formation when there are sudden changes in water flow, while avoiding global path redundancy caused by local obstacle avoidance.

[0066] This invention integrates data from the entire formation via a cloud platform to eliminate the limitations of local decision-making by individual vessels, constructs a real-time updated global environment model to support dynamic response, generates multiple candidate paths and quantifies and selects the optimal path based on a cost model, and achieves dynamic path adjustment through closed-loop control. This achieves the technical effects of globally optimizing navigation efficiency and safety, rapidly responding to environmental changes, and reducing navigation redundancy. Through centralized computation and real-time feedback, this method overcomes the shortcomings of traditional distributed control in terms of dynamic environment adaptability, global path optimization, and collaborative safety, providing reliable technical support for unmanned surface vessel (USV) formation missions in complex waters.

[0067] In one embodiment of the present invention, the environmental information includes obstacle distribution information, water flow speed and direction information, the digital map divides the navigation area into multiple grid units, each grid unit corresponding to a unique coordinate, and the construction of the digital map of the navigation area through the cloud platform specifically includes: based on the obstacle distribution information, marking the grid units containing obstacles as impassable units through the cloud platform; and based on the water flow speed and direction information, assigning corresponding water flow influence parameters to each grid unit through the cloud platform.

[0068] In this system, grid cells are regular two-dimensional or three-dimensional spatial units that divide the navigation area on a digital map. Each cell has a unique coordinate identifier and can be divided using uniform or adaptive grids. Their function is to discretize the continuous space, facilitating rapid retrieval and calculation by path planning algorithms. Impassable cells are grid cells occupied by obstacles or posing a navigation risk. After obtaining obstacle distribution information through sensors or external data sources, a coordinate matching algorithm is used to determine and mark the grids covered by obstacles. For example, if the radar detects a fixed obstacle at the center point (x, y) of a grid, that grid and its surrounding area may be marked as impassable. Water flow influence parameters are the velocity and direction data of the water flow in each grid cell, usually represented in vector form. Their purpose is to quantify the resistance or assist effect of water flow on the unmanned vessel's navigation; for example, downstream navigation reduces energy consumption, while upstream navigation requires increased power output.

[0069] The cloud platform first divides the navigation area into grid cells according to a preset resolution, assigning unique coordinates to each cell. Then, based on obstacle distribution information, it uses a coordinate mapping algorithm to determine impassable cells. For example, this process can be achieved by matching obstacle positions with grid coordinates and marking no-navigation zones, thus directly eliminating collision-risk paths in the path planning. For water flow parameters, the system spatially interpolates or assigns the collected water flow velocity and direction data according to grid positions. For instance, it uses bilinear interpolation to map continuous water flow field data to a discrete grid. This process must ensure the spatiotemporal consistency of the water flow parameters. For example, in areas with abrupt changes in water flow direction, a higher resolution grid is used to improve data accuracy, thereby providing accurate input for the subsequent cost model regarding the dynamic environmental impact.

[0070] This invention achieves the technical effects of improving the efficiency of path planning algorithms, enhancing adaptability to dynamic environments, and optimizing the accuracy of energy consumption prediction by dividing the navigation area into grid cells with unique coordinates, eliminating collision-risk paths by marking impassable units, and quantifying the impact of the dynamic environment on navigation energy consumption by assigning water flow influence parameters. Specifically, the structured digital map enables the path planning algorithm to efficiently retrieve obstacle distribution and water flow characteristics, the local parameter update mechanism reduces computational resource consumption, and the heuristic search algorithm in discrete space can quickly converge the path. Ultimately, this enhances the accuracy of environmental perception and the speed of dynamic response. For example, in the event of sudden changes in water flow, the path can be quickly adjusted through local grid parameter updates instead of relying on a full-area recalculation.

[0071] In one embodiment of the present invention, the step of planning multiple candidate paths for each unmanned vessel using a digital map specifically includes: using a heuristic search algorithm, taking the grid cell corresponding to the initial position of the unmanned vessel as the starting point and the grid cell corresponding to the target position as the ending point, searching and generating multiple paths leading to the endpoint on the digital map as candidate paths; during the search process, ensuring that the candidate paths do not pass through grid cells marked as impassable.

[0072] Among them, heuristic search algorithms are pathfinding methods that evaluate node expansion priorities using heuristic functions. Their core is balancing path exploration efficiency and optimality; exemplified algorithms include A-star, Dijkstra's A-star, or RRT algorithms. The heuristic function is a mathematical model that estimates the remaining cost from a node to its destination; exemplified, Manhattan distance or Euclidean distance is used to calculate the straight-line distance, combined with path length or actual energy consumption cost parameters for comprehensive ranking. Impassable cell exclusion is a path planning strategy that filters specific grid cells using preset rules; exemplified, when an adjacent grid is marked as an obstacle area or a no-navigation zone, path expansion in that direction is directly terminated.

[0073] This can be achieved through the following steps: First, use the grid cells of the digital map as search nodes, where inaccessible cells are pre-set to be unreachable. Second, define the weight parameters for the heuristic function and the actual cost function, for example, using the straight-line distance between the destination and the current node as the heuristic function value, combined with movement energy consumption as the actual cost. Third, expand the path branches using a priority queue, prioritizing paths with lower total costs, and checking in real time whether a path contains inaccessible cells; if so, discard the path. Finally, generate multiple feasible candidate paths by adjusting the heuristic function weights or introducing path diversity parameters. For example, in the A-star algorithm, the conservatism of the heuristic function can be relaxed or random perturbations can be added to prevent paths from converging in a single direction. This operation ensures that paths avoid obstacle areas, improves search efficiency, and provides diverse path options for subsequent selection.

[0074] This invention combines a heuristic search algorithm with the structured data foundation of a gridded digital map. It achieves efficient path exploration through a comprehensive evaluation of heuristic functions and actual costs, while ensuring path safety by eliminating impassable units. Furthermore, it generates multiple candidate paths based on parameter adjustments to cope with dynamic environmental changes. This achieves the technical effect of rapidly generating feasible paths in scenarios with complex obstacle distributions or sudden changes in water flow. Through the synergy of algorithms and data structures, this scheme achieves efficiency, safety, and adaptability in path planning. For example, it can quickly respond to changes in obstacles in a real-time updated digital map, or prioritize downstream paths by adjusting the heuristic function to reduce energy consumption.

[0075] In one embodiment of the present invention, calculating the cost function value of each candidate path using a preset cost model specifically includes:

[0076] Calculate the number of grid cells traversed by the candidate path and determine the path length cost;

[0077] Calculate the distance between the center of each grid cell on the candidate path and the nearest obstacle, accumulate the reciprocal of the distance, and determine the distance cost to the obstacle;

[0078] Based on the water flow impact parameters and the angle between the unmanned vessel's navigation direction and the water flow direction, the water flow impact component in each grid cell is calculated. The water flow impact components in all grid cells on the candidate path are accumulated to determine the water flow impact cost.

[0079] The cost function value of the candidate path is obtained by weighting and summing the path length cost, the distance cost from obstacles, and the water flow impact cost according to preset weight coefficients.

[0080] Path length cost is a numerical indicator that measures the total path length by the number of grid cells traversed or the actual distance traveled by the candidate path. It can be calculated using the grid resolution of a digital map. For example, if each grid cell corresponds to a 10m × 10m actual area, the path length cost can directly use the number of grid cells or the actual distance as the base value. Its purpose is to prioritize routes with shorter paths to reduce travel time or energy consumption. In a specific embodiment, the calculation of path length cost includes traversing each grid cell on the candidate path, counting the total number, or converting the actual distance using a preset grid side length to form the base value of the path length.

[0081] The obstacle distance cost is a quantified measure of the proximity of the path to an obstacle by summing the reciprocals of the distances from the center points of each grid along the path to the nearest obstacle. For example, if a grid center is 5 meters from an obstacle, its reciprocal value is 0.2; a grid 10 meters away has a reciprocal value of 0.1. This design transforms the goal of "maximizing safe distance" into minimizing a cost function through mathematical transformation. In one specific embodiment, the obstacle distance cost is calculated by retrieving the distance to the nearest obstacle in the digital map for each grid center point along the path, calculating the reciprocal values, and summing them to form a comprehensive safety cost.

[0082] The cost of water flow impact is quantified by the cosine function of the angle between the water flow velocity vector and the unmanned vessel's navigation direction, combined with the sum of the comprehensive components calculated from the water flow velocity. For example, when the angle between the water flow direction and the navigation direction is 0°, the water flow impact component is positive; when the angle is 180°, the component is negative. In a specific embodiment, the calculation of the water flow impact cost includes extracting the water flow velocity vector and the navigation direction vector for each grid cell on the path, calculating the angle θ, substituting them into the formula to calculate the component value, and summing the components of all grid cells.

[0083] Weighted summation is a linear combination of path length cost, obstacle distance cost, and water flow impact cost, each multiplied by a preset weight coefficient. An example total cost can be expressed as: Total Cost = Weight 1 × Path Length Cost + Weight 2 × Obstacle Distance Cost + Weight 3 × Water Flow Impact Cost. The weight coefficients can be adjusted according to task requirements. For example, in a safety-first scenario, the weight of obstacle distance cost can be set to 0.4, while path length cost and water flow impact cost each account for 0.3. This operation achieves multi-objective quantification and balancing, enabling path planning to simultaneously meet requirements such as navigation distance, safety, and energy efficiency.

[0084] This invention optimizes navigation efficiency by calculating path length costs, strengthens safety constraints through obstacle distance reciprocal design, enhances energy consumption optimization depth through refined modeling of the angle between water flow direction and navigation direction, and achieves multi-objective dynamic balance through weighting coefficients. It can achieve coordinated optimization of path length, safety distance, and energy consumption in complex aquatic environments, while also possessing enhanced dynamic environmental response capabilities and configurability. This scheme significantly improves the scientific rigor and adaptability of path planning through the spatial benchmark of a gridded digital map, candidate path filtering generated by heuristic search, and cost recalculation triggered by real-time environmental parameter updates. For example, in the event of sudden changes in water flow or obstacle distribution, the system can quickly generate an optimal path that balances downstream navigation and obstacle avoidance, thereby improving the execution efficiency and reliability of formation missions.

[0085] In one embodiment of the present invention, the step of receiving the real-time location information of each unmanned vessel and the environmental information within the navigation area through the cloud platform specifically includes:

[0086] The unmanned vessel obtains its own location information through its onboard positioning equipment and transmits it to the cloud platform through a wireless communication module;

[0087] The unmanned vessel uses its onboard sensors to detect newly appearing obstacles and changes in water flow speed and direction within the navigation area, and transmits the obstacle and change information to the cloud platform via a wireless communication module.

[0088] The positioning device is a coordinate positioning apparatus used to determine the real-time geographic coordinates of the unmanned vessel, including a satellite positioning module or an inertial navigation system. For example, the satellite positioning module can be a device such as GPS or BeiDou that obtains latitude and longitude coordinates by receiving satellite signals, with an accuracy down to the meter level; the inertial navigation system measures displacement and heading using accelerometers and gyroscopes, and is suitable for areas where satellite signals are obstructed. The wireless communication module is a communication device that supports bidirectional data transmission, and its technology types include, but are not limited to, 5G, LoRa, satellite communication, or cellular networks. In one specific embodiment, this module achieves stable data transmission through low-latency transmission and high-bandwidth characteristics, while also possessing anti-interference capabilities to cope with complex electromagnetic environments.

[0089] Sensors are sensing devices used to detect changes in the navigation environment, including radar, Doppler current profilers, sonar, and weather sensors. For example, radar is used to detect the distance and orientation of obstacles, Doppler current profilers measure water flow velocity and direction, sonar detects underwater obstacles, and weather sensors monitor parameters such as wind speed and wave height. Sensor data requires preprocessing steps, such as filtering and noise reduction or coordinate system transformation, to ensure correlation with the grid cells of a digital map.

[0090] Location information acquisition and transmission are achieved through the following method: the unmanned vessel's positioning equipment continuously receives satellite signals or calculates displacement through inertial navigation, generating position coordinates at preset time intervals. Subsequently, the wireless communication module packages the coordinate data into a standardized protocol and adds a timestamp to ensure data synchronization before sending it to the cloud platform. This process improves the real-time performance of data acquisition, and the redundant design of satellite positioning and inertial navigation reduces the risk of data loss due to the failure of a single device.

[0091] This invention achieves real-time acquisition and transmission of location information through positioning equipment and wireless communication modules on unmanned surface vessels (USVs). It acquires environmental change information through collaborative detection and data fusion technology using multiple types of sensors, and optimizes bandwidth utilization efficiency through intelligent scheduling strategies of the wireless communication module. This achieves the following technical effects: the cloud platform can quickly respond to local environmental changes, dynamically update the grid cell status of the digital map, and predict the USV's trajectory using predictive algorithms, triggering path replanning, thereby improving the system's adaptability to complex dynamic environments. For example, it can construct high-precision digital maps through multi-ship sensor data fusion in dense waterways, or maintain the reliability of formation missions through real-time path replanning during sudden changes in water flow, ultimately achieving a comprehensive improvement in the real-time performance, accuracy, and anti-interference capability of formation path planning.

[0092] In one embodiment of the present invention, during the navigation process of each unmanned vessel according to the initial optimal planned path, the following steps are further included: based on the initial optimal planned path of each unmanned vessel in the unmanned vessel formation, calculate the predicted trajectory of any two unmanned vessels in the future period of time, and judge the predicted trajectory of the two unmanned vessels; if there is a possibility that the predicted trajectory may intersect, adjust the initial optimal planned path of one of the unmanned vessels according to priority; based on the adjusted optimal planned path, recalculate whether there is a possibility that the predicted trajectory of the adjusted unmanned vessel may intersect with the predicted trajectory of other unmanned vessels in the unmanned vessel formation; if there is a possibility that they may intersect, readjust the optimal planned path of the unmanned vessel until there is no possibility that the predicted trajectory of the adjusted unmanned vessel may intersect with the predicted trajectory of other unmanned vessels in the unmanned vessel formation; if not, continue to check other unmanned vessel pairs until there is no possibility that the predicted trajectories of all unmanned vessels may intersect.

[0093] The predicted trajectory is generated through a kinematic or dynamic model, based on the mathematical extrapolation of the unmanned surface vessel's (USV) trajectory within a future time window using a motion model. For example, the kinematic model assumes the USV travels along a preset path at a predetermined speed, calculating its future position coordinates through integration. The dynamic model, on the other hand, simulates the actual trajectory by incorporating environmental parameters. Priority adjustment rules are a decision-making mechanism for determining the objects of path adjustments. This is achieved through task urgency, path adjustment costs, or dynamic allocation mechanisms. For example, task urgency includes keeping high-priority tasks like rescue vessels on their original paths, while path adjustment costs involve energy consumption differences due to deviations from the original path. The possibility of intersecting predicted trajectories can be determined through a spatial-temporal intersection detection algorithm. For example, this includes checking whether the grid cells of the two vessel trajectories overlap at the same or adjacent times, or whether the predicted position spacing is less than a safe distance threshold.

[0094] Route adjustment is a process of correcting conflicting paths through local or global replanning. For example, local replanning involves reconnecting the destination after bypassing the conflict point, while global replanning recalculates the entire route to completely avoid the conflict area. During the adjustment process, the cost model needs to be re-invoked to evaluate the overall cost of the new route, ensuring a balance between safety and efficiency. The process of recalculating the predicted trajectory and repeatedly detecting it can be an iterative verification mechanism. For example, after adjusting a ship's path, its trajectory conflicts with other ships in the formation need to be re-detected until all ship pairs' trajectories have no possibility of intersection.

[0095] It should be noted that the determination of the predicted trajectories of the two unmanned vessels specifically includes: obtaining the initial planned paths, maximum speeds, minimum turning radii, and current positions of any two unmanned vessels in the unmanned vessel formation; calculating the predicted position coordinates of the two unmanned vessels at several future time points based on a preset time interval; calculating the distance between the predicted positions of the two unmanned vessels at the same time point based on the predicted position coordinates of the two unmanned vessels at several future time points; if this distance is less than a preset safe distance threshold, and the predicted trajectories of the two unmanned vessels before and after that time point show a trend of gradually approaching each other, then it is determined that the predicted trajectories of the two unmanned vessels may intersect; wherein, the safe distance threshold is dynamically adjusted according to the hull length, width, and speed of the unmanned vessels.

[0096] Maximum speed is the highest speed of the unmanned surface vessel (USV) under rated power, typically determined by the performance of the propulsion system and obtained through a ship parameter database or real-time sensor feedback. An example is a rated speed limit of 5 m / s. Minimum turning radius is the minimum radius of curvature the USV must have when turning at rated speed. It is determined by the ship's rudder angle limits and propulsion system response characteristics, and can be determined through ship kinematic parameters or experimental calibration data. An example is a minimum turning radius constraint of 8 meters. Current position information is the coordinate data output by the USV's real-time positioning system, collected by sensors such as satellite navigation or inertial measurement units. An example includes latitude and longitude coordinates or two-dimensional coordinate values ​​in a local coordinate system. The preset time interval can be the sampling period of the cloud platform or control system, set through system configuration parameters. An example is a fixed time step of 10 seconds.

[0097] Predicted position coordinates are the result of mathematical derivation of the theoretical position of the unmanned vessel at future moments based on the current state and motion model. The calculation methods include kinematic models or dynamic models. Kinematic models assume the unmanned vessel travels along the path at a constant speed, calculating displacement through integration. Dynamic models, on the other hand, incorporate acceleration limits, water flow effects, and turning inertia to simulate a more realistic trajectory. For example, in turning sections of the path, the constraint condition that the radius of curvature must be greater than or equal to the minimum turning radius must be met. The safe distance threshold is the minimum allowable safe distance between two vessels. Its dynamic adjustment formula can be expressed as: Safe distance = k × (hull length + hull width) + c × relative speed, where k and c are empirical coefficients. For example, when the relative speed between the two vessels is 10 m / s, the coefficient c might be taken as 0.5 to increase the safe distance.

[0098] This invention constructs a predictive model by acquiring initial planned paths, navigation parameters, and real-time position information. It calculates predicted positions using segmented time nodes and combines this with dynamic safety distance thresholds for distance and trend analysis, thereby improving the accuracy and adaptability of trajectory conflict detection. This scheme strengthens physical constraints to avoid misjudging infeasible paths, utilizes a dynamic threshold mechanism to adapt to different ship types and speed scenarios, and filters out false alarms due to brief proximity through trend analysis. Ultimately, it forms a closed-loop optimization with digital maps, cost models, and trajectory adjustment modules, significantly enhancing the safety and robustness of path planning in multi-ship convoy navigation.

[0099] In one embodiment of the present invention, adjusting the initial optimal planned path of one of the unmanned surface vessels (USVs) according to priority specifically includes: determining the USV whose optimal planned path needs to be adjusted based on task priority, current load status, and remaining range from the target location; reselecting from multiple candidate paths a path whose cost function value differs from the original path within a preset range and can avoid collision risk; if no candidate path exists whose cost function value differs from the original path within a preset range, performing local optimization on the original optimal planned path, adding a turning point near the predicted collision area during local optimization; wherein the setting of the turning point must satisfy the minimum turning radius constraint of the USV, and the path after the turn must be staggered in time and space from the predicted trajectory of the other USV.

[0100] Task priority is a quantitative indicator representing the importance of the task currently being performed by the unmanned surface vessel (USV). It can be preset or dynamically adjusted through a task management system. For example, task priorities may include those for emergency rescue, environmental monitoring, and cargo transportation. Current load status is a set of parameters reflecting the real-time operating status of the USV. It can be obtained through sensor data acquisition or status monitoring modules. For example, current load status includes remaining battery power, cargo weight, and sensor operating status. Remaining range from the target location is the remaining distance from the USV's current location to the mission endpoint. It can be calculated using a positioning system and digital map data. For example, the remaining range can be quantified in meters or nautical miles.

[0101] Candidate paths whose cost function value differs from the original path within a preset range are a set of alternative paths that satisfy the path adjustment cost constraint. These paths are obtained through cost function calculation and threshold screening. For example, the preset range is set to ±10% to ±15% of the original path cost function value. Collision avoidance risk is the degree of spatial or temporal overlap between the path and the predicted trajectory of another unmanned vessel. It is obtained through trajectory prediction model evaluation. For example, collision avoidance risk can be determined based on the minimum safe distance threshold between the two vessel paths.

[0102] The process of identifying unmanned surface vessels (USVs) requiring path adjustments is achieved through a cloud platform that comprehensively evaluates multi-dimensional parameters of both conflicting parties. Specifically, firstly, task priorities are compared, with higher-priority vessels maintaining their original paths. Secondly, load status is analyzed; if a vessel's maneuverability is limited due to excessive load, another vessel is prioritized for adjustment. Finally, remaining range is considered; vessels with shorter remaining ranges may retain their original paths to avoid mission delays. This process is implemented through weighted scoring or rule-based priority ranking, ultimately determining the USVs requiring path adjustments. This technical operation ensures that the path adjustment strategy strikes a balance between mission criticality, physical feasibility, and time constraints.

[0103] The process of selecting candidate paths can be achieved through cost difference constraints and collision avoidance effectiveness screening. Specifically, it includes: first, calculating the cost function values ​​of multiple candidate paths and filtering out paths whose differences from the original path are within a preset range; second, verifying whether the filtered paths completely avoid the predicted collision area or achieve off-peak traffic through spatiotemporal adjustments. If multiple paths meet the criteria, the path with the lowest cost is selected as the final path. This technique ensures that path adjustments strike a balance between safety and efficiency, avoiding a decline in overall task performance due to excessive deviation from the original path.

[0104] The process of locally optimizing the path can be achieved through the insertion of turning points and the fulfillment of constraints. Specifically, this includes: inserting turning points near the predicted collision area; generating smooth path segments using trajectory planning algorithms such as cubic spline interpolation; ensuring the path curvature radius is not less than the minimum turning radius when calculating the turning point coordinates; and adjusting the turning point position or speed so that the time interval between the two ships passing through the conflict area meets preset requirements. This technique provides a local correction scheme when candidate paths are insufficient, ensuring physical feasibility while avoiding the high computational cost of re-planning globally.

[0105] This invention employs multi-dimensional parameter evaluation to determine path adjustment targets, cost constraints to screen candidate paths, and local path optimization and constraint satisfaction techniques to achieve the following technical effects: an intelligent decision-making mechanism prioritizes low-priority or high-load vessels, reducing interference with critical tasks; path adjustment costs are controlled within a reasonable range, avoiding significant increases in task time; turning point constraints ensure the physical feasibility of the path and prevent power system overload; and a spatiotemporal peak-shifting strategy enables orderly passage of vessels in the formation through conflict zones. These techniques work synergistically to significantly improve the rationality, reliability, and dynamic adaptability of path adjustments, especially in complex multi-ship formation scenarios, effectively coordinating navigation conflicts while ensuring the task execution efficiency and navigation safety of each vessel.

[0106] In one embodiment of the present invention, updating the digital map through environmental information specifically includes: updating the passability status of the corresponding grid cells in the digital map based on newly detected obstacle information, and marking the grid cells where the newly appeared obstacles are located as impassable cells; updating the water flow influence parameters of each grid cell in the digital map based on new water flow speed and direction information; taking the grid cell corresponding to the current position of the unmanned vessel as the new starting point and the grid cell corresponding to the target position as the ending point, re-generating multiple candidate paths using a heuristic search algorithm, and re-selecting the optimal planned path.

[0107] The passage status refers to the binary marker indicating whether a grid cell is passable. This is obtained by mapping the coordinates of obstacles detected by the unmanned surface vessel's (USV) sensors to the coordinates of the digital map grid. For example, the passage status includes extended restricted areas marked based on safety boundaries. Water flow impact parameters include the water flow velocity vector, obtained through the USV's onboard current meter or an external hydrological data interface. For example, the water flow parameters include real-time updated water flow vector field data. After receiving environmental data reported by the USV through the cloud platform, spatial mapping is first performed to convert the coordinates into grid indices. Then, the passage status and water flow vector of the corresponding grid cells are updated. Finally, starting from the current vessel position, a heuristic search algorithm is re-executed to generate a candidate path set. This achieves the technical effects of dynamically avoiding obstacles, adapting to changes in water flow, and ensuring real-time path connectivity.

[0108] The present invention also provides an unmanned vessel platooning path planning system, including a processor and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the steps of the cloud-controlled unmanned vessel platooning path planning method described above.

[0109] The processor refers to the computing unit in the cloud platform or edge computing node. Its functions include executing path planning algorithms and cost model calculations. It can achieve multi-threaded task processing through a parallel computing architecture. For example, the processor may include a multi-core CPU supporting the SIMD instruction set or a GPU configured with CUDA acceleration. The memory is used to persistently store digital map data, sensor information, and intermediate algorithm results. It can be implemented through a hierarchical storage architecture. For example, the memory may include a hybrid storage system combining cache and SSD. By loading the digital map and algorithm code from the memory through the processor, the multi-threaded parallel processing of trajectory prediction and conflict detection for different ships is used when executing multi-ship path planning tasks. At the same time, the hierarchical storage architecture accelerates the read and write operations of high-frequency access data, thereby achieving the technical effect of improving the concurrent processing capability of large-scale formation path planning and reducing system latency.

[0110] This invention reflects environmental changes by updating the traffic status and water flow parameters of a digital map in real time. It combines heuristic path replanning starting from the current ship position to ensure real-time path connection. At the same time, it relies on processor parallel computing and hierarchical storage architecture to achieve efficient execution of high-concurrency path planning tasks. This can significantly improve the timeliness and reliability of path planning in dynamic and complex environments. It supports large-scale formations to maintain low-latency response and generate globally optimal paths even in scenarios such as sudden obstacles and changes in water flow.

[0111] The above description is only a preferred embodiment of the present invention. It should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A cloud-controlled unmanned vessel platooning path planning method, characterized in that, Includes the following steps: The initial position information, target position information, and environmental information of each unmanned vessel in the unmanned vessel formation are obtained through the cloud platform. Based on environmental information, a digital map of the navigation area is constructed through a cloud platform; Based on the initial and target position information of each unmanned vessel, multiple candidate paths are planned for each unmanned vessel using a digital map; Based on multiple candidate paths, the cost function value of each candidate path is calculated using a preset cost model, and the initial optimal planning path is selected based on the cost function values ​​of multiple candidate paths. During the navigation process according to the initial optimal planned path, each unmanned vessel receives its own position information and environmental information in the navigation area in real time through the cloud platform. The digital map is updated with the environmental information, and the optimal planned path is updated based on the updated digital map and its own position information. The calculation of the cost function value for each candidate path using a preset cost model specifically includes: Calculate the number of grid cells traversed by the candidate path and determine the path length cost; Calculate the distance between the center of each grid cell on the candidate path and the nearest obstacle, accumulate the reciprocal of the distance, and determine the distance cost to the obstacle; Based on the water flow impact parameters and the angle between the unmanned vessel's navigation direction and the water flow direction, the water flow impact component in each grid cell is calculated. The water flow impact components in all grid cells on the candidate path are accumulated to determine the water flow impact cost. The cost function value of the candidate path is obtained by weighting and summing the path length cost, the distance cost from obstacles, and the water flow impact cost according to preset weight coefficients.

2. The unmanned vessel formation path planning method based on cloud control according to claim 1, characterized in that, The environmental information includes obstacle distribution information, water flow speed and direction information. The digital map divides the navigation area into multiple grid cells, each grid cell corresponding to unique coordinates. The construction of the digital map of the navigation area through the cloud platform specifically includes: Based on obstacle distribution information, grid cells containing obstacles are marked as impassable cells via a cloud platform; Based on the water flow velocity and direction information, each grid cell is assigned corresponding water flow influence parameters through a cloud platform.

3. The unmanned vessel platooning path planning method based on cloud control according to claim 2, characterized in that, The process of planning multiple candidate paths for each unmanned vessel using digital maps specifically includes: A heuristic search algorithm is used to search and generate multiple paths leading to the destination on the digital map, starting from the grid cell corresponding to the initial position of the unmanned vessel and ending at the grid cell corresponding to the target position, as candidate paths. During the search process, ensure that candidate paths do not pass through grid cells marked as impassable.

4. The unmanned vessel platooning path planning method based on cloud control according to claim 2, characterized in that, The real-time reception of the unmanned vessel's own position information and environmental information within the navigation area via the cloud platform specifically includes: The unmanned vessel obtains its own location information through its onboard positioning equipment and transmits it to the cloud platform through a wireless communication module; The unmanned vessel uses its onboard sensors to detect newly appearing obstacles and changes in water flow speed and direction within the navigation area, and transmits the obstacle and change information to the cloud platform via a wireless communication module.

5. The unmanned vessel formation path planning method based on cloud control according to claim 1, characterized in that, During the navigation process of each unmanned vessel according to the initial optimal planned path, the following steps are also included: Based on the initial optimal planned path of each unmanned vessel in the unmanned vessel formation, calculate the predicted trajectory of any two unmanned vessels in the future period of time, and judge the predicted trajectory of the two unmanned vessels. If the predicted trajectories have the potential to intersect, adjust the initial optimal planning path of one of the unmanned vessels according to priority. Based on the adjusted optimal planning path, recalculate whether the predicted trajectories of the adjusted unmanned vessel intersect with those of other unmanned vessels in the unmanned vessel formation. If there is a possibility of intersection, readjust the optimal planning path of the unmanned vessel until there is no possibility of intersection between the predicted trajectories of the adjusted unmanned vessel and those of other unmanned vessels in the unmanned vessel formation. If there is no possibility of intersection, continue to check other unmanned vessel pairs until there is no possibility of intersection between the predicted trajectories of all unmanned vessels.

6. The unmanned vessel formation path planning method based on cloud control according to claim 5, characterized in that, The determination of the predicted trajectories of the two unmanned vessels specifically includes: The system obtains the initial planned path, maximum speed, minimum turning radius, and current position information of any two unmanned vessels in the unmanned vessel formation. Based on a preset time interval, it calculates the predicted position coordinates of the two unmanned vessels at several future time nodes. Based on the predicted position coordinates of two unmanned vessels at several future time points, the distance between the predicted positions of the two unmanned vessels at the same time point is calculated. If the distance is less than the preset safe distance threshold, and the predicted trajectories of the two unmanned vessels before and after the time point show a trend of gradually approaching each other, it is determined that the predicted trajectories of the two unmanned vessels may intersect. The safe distance threshold is dynamically adjusted based on the length, width, and speed of the unmanned vessel.

7. The unmanned vessel formation path planning method based on cloud control according to claim 6, characterized in that, The adjustment of the initial optimal planned path of one of the unmanned vessels based on priority specifically includes: Based on mission priority, current load status, and remaining distance to the target location, determine the unmanned vessels that need to adjust their optimal planning paths; Select a new path from multiple candidate paths whose cost function value differs from the original path within a preset range and which can avoid the risk of collision. If there is no candidate path whose cost function value differs from the original path within a preset range, the original optimal planning path is locally optimized. During local optimization, turning points are added near the predicted collision area. The setting of the turning point must meet the minimum turning radius constraint of the unmanned vessel, and the path after the turn must be staggered in time and space from the predicted trajectory of another unmanned vessel.

8. The unmanned vessel formation path planning method based on cloud control according to claim 4, characterized in that, The updating of the digital map using environmental information specifically includes: Based on the newly detected obstacle information, update the passage status of the corresponding grid cell in the digital map, and mark the grid cell where the newly appeared obstacle is located as an impassable cell; Update the water flow impact parameters of each grid cell in the digital map based on the new water flow velocity and direction information; Using the grid cell corresponding to the current position of the unmanned vessel as the new starting point and the grid cell corresponding to the target position as the ending point, a heuristic search algorithm is used again to generate multiple candidate paths, and the optimal planned path is selected again.

9. A cloud-controlled unmanned vessel platooning path planning system, characterized in that, Includes a processor and a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the steps of the cloud-controlled unmanned vessel formation path planning method as described in any one of claims 1 to 8.

Images