An unmanned ship formation path planning method and device, electronic equipment and medium

Abstract

The present application relates to the technical field of path planning, in particular to an unmanned ship formation path planning method and device, electronic equipment and medium. In the present application, by constructing a global path planning model based on time-optimal A algorithm, the total sailing time of the formation is minimized and the current velocity is considered, which improves the sailing efficiency of the global path; the collision avoidance threat degree is dynamically calculated to determine the dynamic priority of the unmanned ship, which effectively reduces the collision risk; when a path intersection conflict occurs, local path re-planning is triggered according to the priority, which guarantees the safety and coordination of the formation sailing; the local path is smoothed and optimized by using B-spline curve, so that the path is more continuous and smooth, the motion mutation is reduced, and the sailing stability is improved. The overall scheme takes into account the sailing efficiency, safe obstacle avoidance and path smoothness, and enhances the path planning capability and sailing performance of the unmanned ship formation in complex marine environment.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, specifically to a method, apparatus, electronic device, and medium for unmanned surface vessel (USV) swarm path planning. Background Technology

[0002] With the intelligent development of tasks such as marine surveillance and maritime search and rescue, the demand for coordinated operations in unmanned surface vessel (USV) formations is rapidly increasing. Global ocean surface currents can reach speeds of 2-5 knots, significantly impacting the efficiency of formation coordination and formation maintenance. Utilizing ocean current data effectively can reduce the overall energy consumption and operational time of USV formations.

[0003] Existing formation path planning methods mostly focus on mission scenarios in static environments, and lack effective solutions for multi-vessel collaborative path planning in dynamic ocean current fields. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and medium for unmanned surface vessel (USV) swarm path planning, in order to address the lack of effective solutions for multi-vessel cooperative path planning in dynamic ocean current fields in the prior art.

[0005] In a first aspect, the present invention provides a method for unmanned surface vessel (USV) formation path planning, the method comprising:

[0006] With the objective of minimizing the total sailing time of the formation, a time-optimal A-type formation is constructed considering ocean current speed. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation; The collision avoidance threat level of each unmanned surface vessel (USV) in the formation is dynamically calculated, and the dynamic priority of each USV is determined based on the collision avoidance threat level. When path intersection conflicts occur, local path replanning is triggered for the unmanned surface vessel according to the dynamic priority order. B-spline curves are used to smooth and optimize the local paths of the replanning.

[0007] In this invention, by constructing a time-optimal A The algorithm's global path planning model minimizes the total convoy's sailing time and considers ocean current speed, improving global path planning efficiency. Dynamically calculating collision avoidance threat levels to determine the dynamic priorities of unmanned surface vessels (USVs) effectively reduces collision risk. When path intersection conflicts occur, local path replanning is triggered according to priority, ensuring the safety and coordination of convoy navigation. B-spline curves are used to smooth and optimize local paths, making them more continuous and smooth, reducing abrupt motion changes, and improving navigation stability. The overall solution balances navigation efficiency, obstacle avoidance safety, and path smoothness, enhancing the path planning capabilities and navigation performance of USV convoys in complex marine environments.

[0008] In one alternative implementation, with the objective of minimizing the total voyage time of the formation, a time-optimal A is constructed considering ocean current speeds. The algorithm's global path planning model generates initial navigation paths for the unmanned surface vessel (USV) convoy, including: With the goal of minimizing the total voyage time of the formation, a cost function is constructed that includes an actual movement cost function, a heuristic function, and a risk cost function. The risk cost function is determined based on the relationship between the resultant velocity and the still water speed of the unmanned surface vessel. The resultant velocity is determined based on the ocean current speed and the speed of the unmanned surface vessel. The constraints are constructed, including static obstacle constraints, dynamic obstacle avoidance constraints, formation collision avoidance constraints, and kinematic and dynamic restriction constraints. Based on the aforementioned cost function and constraints, construct a time-optimal A... The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation.

[0009] In this invention, a cost function containing actual movement costs, a heuristic function, and risk costs based on the resultant velocity (determined by ocean currents and boat speed) is constructed. This function, combined with static obstacles, dynamic obstacle avoidance, formation collision avoidance, and kinematic constraints, establishes a time-optimal A... The global path planning model minimizes the total voyage time of the formation while improving path safety and feasibility.

[0010] In one alternative implementation, when generating the initial navigation path, nodes are expanded using rules of downstream acceleration and upstream detours.

[0011] In this invention, the node expansion rules of downstream acceleration and upstream detour are adopted when generating the initial navigation path. This can make full use of ocean current speed to optimize path planning: downstream acceleration can reduce navigation time, and upstream detour can avoid unnecessary time consumption, making the initial path more in line with actual ocean dynamic conditions. This lays a good foundation for subsequent local path optimization, obstacle avoidance and smoothing, and helps the formation to navigate efficiently and stably in a dynamic ocean environment.

[0012] In one optional implementation, the collision avoidance threat level of each unmanned surface vessel (USV) within the formation is dynamically calculated, and the dynamic priority of each USV is determined based on the collision avoidance threat level, including: The collision avoidance threat level of each unmanned surface vessel is determined based on the distance threat factor, relative speed threat factor, and obstacle size threat factor. The dynamic priority of each unmanned surface vessel (USV) in the formation is determined based on its collision avoidance threat level.

[0013] In this invention, dynamic priorities are determined by dynamically calculating the collision avoidance threat level of each unmanned surface vessel (USV) (combining distance, relative speed, and obstacle size threat factors). This allows for precise quantification of obstacle avoidance urgency and more rational priority allocation. In case of conflict, local replanning based on priority can orderly coordinate the obstacle avoidance behavior of USVs within the formation, avoiding chaos and collisions, and improving the safety and coordination of formation navigation. At the same time, this dynamic priority mechanism makes path adjustment more flexible and efficient, enabling rapid response to environmental changes and ensuring that the formation can stably and efficiently complete navigation tasks in complex scenarios (such as multi-vessel interaction and obstacle interference), balancing safety and efficiency.

[0014] In one optional implementation, the distance threat factor is determined based on the obstacle distance quantized by an exponential decay function, the relative speed threat factor is determined based on a preset collision time, and the obstacle size threat factor is determined based on the obstacle size coefficient and the speed of the unmanned surface vessel.

[0015] In this invention, the distance threat factor quantifies obstacle distance based on an exponential decay function, more accurately reflecting the impact of distance on collision avoidance threat (the closer the distance, the faster the threat increases); the relative speed threat factor is determined based on a preset collision time, intuitively reflecting the collision risk under relative motion; the obstacle size threat factor combines a size coefficient with the speed of the unmanned surface vessel (USV), comprehensively considering the impact of obstacle size and its own motion state on the threat. The combination of these three factors determines the collision avoidance threat level, making threat assessment more comprehensive and accurate. Consequently, the dynamic priority determined based on the threat level is more reasonable, allowing USVs to allocate right-of-way more scientifically during obstacle avoidance, improving the accuracy and efficiency of formation obstacle avoidance, reducing collision risk, and enhancing the safety and coordination of formation navigation in complex environments.

[0016] In one alternative implementation, B-spline curves are used to smooth and optimize the replanned local paths, including: Determine the parametric expression for the B-spline curve of the replanned local path; With the goal of minimizing the total path length, the parameterized expression is optimized based on preset constraints to obtain the optimized path.

[0017] In this invention, B-spline curves are used to smooth and optimize the replanned local paths. First, the parametric expression is determined, and then the expression is optimized based on preset constraints with the goal of minimizing the total path length to obtain the optimized path. This makes the local path smoother and more continuous, reduces motion fluctuations caused by abrupt path changes, and improves the navigation stability of the unmanned surface vessel. Simultaneously, minimizing the path length can further shorten the navigation distance in local optimization, improving navigation efficiency.

[0018] In one optional implementation, the preset constraints include obstacle avoidance constraints, curvature constraints, velocity constraints, and acceleration constraints.

[0019] In this invention, obstacle avoidance constraints ensure the path avoids obstacles, improving navigation safety; curvature constraints limit the path's curvature, ensuring smooth and controllable turning of the unmanned surface vessel (USV); speed constraints adapt to the USV's dynamic performance, preventing overspeeding or underpowered maneuvers; and acceleration constraints reduce the impact of sudden speed changes, improving navigation stability and comfort. These constraints work synergistically to make local path smoothing optimization based on B-spline curves more feasible and practical. Under the premise of meeting safety and dynamic constraints, it can output smooth and efficient local paths, enhancing the USV's ability to adjust local paths in complex environments and improving overall navigation performance and reliability.

[0020] Secondly, the present invention provides an unmanned surface vessel (USV) convoy path planning device, the device comprising: The global path planning module is used to construct a time-optimal A / B path, taking into account ocean current speeds, with the objective of minimizing the total formation sailing time. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation; The dynamic priority calculation module is used to dynamically calculate the collision avoidance threat level of each unmanned surface vessel in the formation, and determine the dynamic priority of each unmanned surface vessel based on the collision avoidance threat level. The local path planning module is used to trigger local path replanning for the unmanned surface vessel according to the dynamic priority order when path intersection conflicts occur. The path optimization module is used to smooth and optimize the replanned local paths using B-spline curves.

[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the unmanned surface vessel formation path planning method of the first aspect or any corresponding embodiment described above.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the unmanned surface vessel formation path planning method of the first aspect or any corresponding embodiment described above.

[0023] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the unmanned surface vessel formation path planning method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the first type of unmanned surface vessel (USV) formation path planning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the second process of the unmanned surface vessel formation path planning method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the third process of the unmanned surface vessel formation path planning method according to an embodiment of the present invention; Figure 4 This is a structural block diagram of an unmanned surface vessel (USV) formation path planning device according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0026] As described in the background section, existing formation path planning methods mostly focus on mission scenarios in static environments, lacking effective solutions for multi-vessel collaborative path planning in dynamic ocean current fields. The complex interference environment composed of ocean current dynamic disturbances, irregular sea ice distribution, sudden obstacles, and abrupt changes in water depth leads to three problems with traditional formation path planning methods: (1) The global path does not consider the spatiotemporal differences of ocean current fields, which can increase the risk of collisions between vessels by 3-5 times in strong countercurrent areas. (2) Local obstacle avoidance lacks a multi-vessel collaborative mechanism and does not consider the differences in ocean current fields experienced by formation members, which can easily lead to deadlock and collision risks. (3) Insufficient path smoothness leads to frequent servo motor actions, violating the dynamic constraints of unmanned surface vessels.

[0027] To address the unmanned surface vessel (USV) swarm path planning problem under ocean current interference, this invention provides a USV swarm path planning method. Based on constraints such as mission constraints, environmental constraints, USV kinematics and kinematic constraints, USV collision avoidance constraints, obstacle avoidance constraints, and path curvature continuity, a time-cost-based A / B algorithm is employed. The algorithm performs global path planning to generate an initial safe navigation path; it adopts a dynamic priority mechanism based on obstacle threat to adjust local path planning and resolve the conflict between real-time obstacle avoidance and formation collision avoidance paths; it uses B-spline curves with kinematic constraints to smooth the planned path, realizing dynamic planning and optimization of formation navigation paths in harsh environments, and generating a safe and time-efficient optimal path.

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. 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.

[0029] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0030] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0031] According to an embodiment of the present invention, an embodiment of an unmanned surface vessel (USV) formation path planning method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] This embodiment provides a method for unmanned surface vessel (USV) convoy path planning. Figure 1 This is a flowchart of an unmanned surface vessel (USV) formation path planning method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: With the objective of minimizing the total sailing time of the formation, construct a time-optimal A-type formation considering ocean current speed. The algorithm's global path planning model generates initial navigation paths for unmanned surface vessel (USV) formations. Here, "formation" refers to a fleet of USVs composed of multiple USVs. Therefore, path planning requires determining the navigation paths of all USVs within the formation. The initial navigation path determined in this step is the path planned for all USVs from the starting point to the destination after the starting and ending points of the USV formation are determined before navigation.

[0033] Specifically, A in the relevant technology The algorithm optimizes the geometric shortest path during path planning, ignoring the vector superposition effect of ocean currents on the unmanned surface vessel's motion, and may choose a counter-current path that actually takes longer. However, in this embodiment, when using A... When the algorithm performs initial navigation path planning, it constructs A with the objective of minimizing the total navigation time of the formation. The algorithm's cost function is to determine the travel time by considering the path length and the speed of the unmanned surface vessel (USV) when taking into account ocean current speed. Then, path planning is performed to minimize the travel time, thereby obtaining the initial travel path of the USV formation.

[0034] Step S102: Dynamically calculate the collision avoidance threat level of each unmanned surface vessel in the formation, and determine the dynamic priority of each unmanned surface vessel based on the collision avoidance threat level.

[0035] Specifically, after an initial navigation path is planned for an unmanned surface vessel (USV) convoy, the individual USVs in the convoy may navigate along this path at a safe distance. However, during navigation, collisions may occur due to ocean current disturbances or slight differences in speed, and obstacles may suddenly appear on the initial navigation path. Therefore, to address the safe navigation requirements of USV convoys in avoiding external obstacles and internal collisions during missions, each USV dynamically calculates its collision threat level during real-time navigation. This calculation treats all encountered new obstacles and other USVs in the convoy as obstacles in the collision threat level calculation.

[0036] It should be noted that if no new obstacles are encountered, only the collision avoidance threat level of other unmanned surface vessels (USVs) is calculated in real time. If a new obstacle is encountered, the collision avoidance threat level needs to be calculated by comprehensively considering both other USVs and the new obstacle. After the collision avoidance threat level is calculated in real time, the dynamic priority of each USV is determined based on the magnitude of the collision avoidance threat level. That is, the priority of each USV is not static, but changes accordingly with the changes in the navigation process.

[0037] Step S103: When a path intersection conflict occurs, trigger local path replanning for the unmanned surface vessel according to the dynamic priority order.

[0038] Specifically, multiple sensors are installed on the unmanned surface vessel (USV), and the USV can also connect to satellite monitoring systems such as space-based intelligence systems. This allows it to determine the distance to other USVs in real time and monitor whether there are new obstacles on the initial navigation path. When the distance to other USVs is less than the safe distance or a new obstacle is detected (i.e., when there is a path intersection conflict), it is necessary to obtain the dynamic priority of each USV calculated in step S102, and then plan a new local path in order of priority.

[0039] Specifically, high-priority unmanned surface vessels (USVs) perform local path planning first, followed by low-priority USVs (with a small time difference, e.g., within milliseconds). When planning their paths, low-priority USVs must avoid the local paths planned by high-priority USVs, i.e., they must not overlap with them. During local path planning, the time-optimal A method described in step S101 above can be used. The algorithm allows low-priority unmanned surface vessels (USVs) to add the planned local paths of high-priority USVs to the constraints, thereby avoiding overlap of local paths.

[0040] Step S104 involves using B-spline curves to smooth and optimize the replanned local paths. Specifically, since most of the planned local paths are curves, this embodiment uses B-spline curves to smooth and optimize the local paths of each unmanned surface vessel (USV) to obtain curved local paths. After the USVs perform obstacle avoidance or collision avoidance according to the smoothed and optimized local paths, they will return to their initial navigation paths and continue to perform real-time dynamic priority calculations until the USV convoy reaches its destination, thus achieving the convoy's navigation from the starting point to the destination.

[0041] This embodiment provides a method for unmanned surface vessel (USV) formation path planning, which includes the following steps: Step S201: With the objective of minimizing the total sailing time of the formation, construct a time-optimal A-type formation considering ocean current speed. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation.

[0042] Specifically, step S201 includes: Step S2021: With the goal of minimizing the total voyage time of the formation, a cost function is constructed that includes an actual movement cost function, a heuristic function, and a risk cost function. The risk cost function is determined based on the relationship between the resultant velocity and the still water speed of the unmanned surface vessel. The resultant velocity is determined based on the ocean current speed and the speed of the unmanned surface vessel.

[0043] Specifically, the objective function for minimizing the total formation sailing time is expressed as follows:

[0044] In the formula, The total number of waypoints on the global path planned for the unmanned surface vessel formation. For the first global path of the formation Path points, For the first The coordinates of the path points For from the first From the path point to the first The sailing time for each waypoint.

[0045] The global path is the initial navigation path that needs to be generated. When using A... When the algorithm plans the path from the starting point to the destination, it begins at the starting point and expands the nodes sequentially until the destination is reached. Therefore, a path point can be understood as a node in the algorithm, i.e., any location point within the range of the starting and ending points. Based on the objective of minimizing the total convoy travel time, and considering the influence of ocean current speed on the speed of the unmanned surface vessel, the actual movement cost function and heuristic function are expressed by the following formulas:

[0046]

[0047] In the formula, This represents the resultant velocity of the unmanned surface vessel under ocean currents. For unmanned surface vessels speed, , This refers to the ocean current velocity. It is the planned path length from the starting point to the real-time location of the navigator unmanned surface vessel. The real-time location of the Navigator unmanned surface vessel. This represents the real-time location of the target point. Based on the above formula, the actual movement cost function represents the actual cumulative time from the starting point to node n, while the heuristic function represents the remaining time from node n to the destination. By setting this actual movement cost function and heuristic function in the cost function, this A can be achieved. The algorithm is time-optimal.

[0048] In addition to the actual movement cost function and the heuristic function, a risk cost function c(n) is also set in the cost function. This function can increase the directional cost in the node expansion direction or prohibit expansion, and increase the path safety weight in strong ocean current areas. Specifically, in areas where the resultant velocity is less than 30% of the unmanned surface vessel's still-water speed, a high penalty value is assigned to c(n), forcing the unmanned surface vessel to detour. Therefore, the cost function can be expressed by the following formula:

[0049] In the formula, , and This is a scenario-dependent parameter; that is, this parameter can be adaptively adjusted according to different application scenarios.

[0050] In one optional implementation, node expansion employs a rule of downstream acceleration and upstream detour. Specifically, this embodiment uses a node expansion rule of downstream acceleration and upstream detour, where downstream acceleration can be understood as filtering out unreachable courses based on the ship's maneuverability, such as... Among the neighboring nodes, priority is given to directions with smaller angles between the unmanned surface vessel's speed and the current speed to reduce energy consumption and travel time. for The heading angle at any moment, This represents the maximum change in the heading angle per unit time. Countercurrent maneuvering involves adjusting the heading to utilize the lateral component of the ocean current, avoiding direct confrontation with a strong countercurrent. Here, the countercurrent primarily refers to the opposing force of the water flow in the longitudinal direction (along the centerline of the unmanned surface vessel, from stern to bow). It also possesses a lateral (left-right) component. By actively adjusting the unmanned surface vessel's heading, aligning the direction of the current received by the vessel with the lateral component of the ocean current, and utilizing the lateral thrust of the current to "ride the current," the vessel can "sail by its own strength," instead of directly confronting the longitudinal countercurrent head-on. This reduces power consumption and navigation resistance.

[0051] In using A When determining neighboring nodes based on the current node, the algorithm first uses the above-mentioned node expansion rules to screen and filter nodes, and then calculates the cost function for the screened nodes to achieve node updates.

[0052] Step S2022: Construct constraints, which include static obstacle constraints, dynamic obstacle avoidance constraints, formation collision avoidance constraints, and kinematic and dynamic restriction constraints.

[0053] Specifically, the static obstacle constraint means that the node determined in the algorithm needs to be greater than the static obstacle avoidance safety distance. Based on the kinematic constraints and the braking capability of the unmanned surface vessel's control system (used to realize the motion control of the unmanned surface vessel, such as heading, speed, attitude, etc.), the static obstacle avoidance safety distance is expressed by the following formula:

[0054] in, Let be the th obstacle; This is the minimum turning radius of the unmanned surface vessel; For unmanned surface vessels speed, For the control system response time; This is a safety margin factor, which includes the additional safety distance required for braking or steering. It should be noted that the parameters used in calculating the static obstacle avoidance safety distance can be obtained through actual testing of the unmanned surface vessel's design and the performance of its onboard power equipment, such as diesel engines, injection pumps, and propellers.

[0055] Dynamic obstacle constraints indicate that nodes determined in the algorithm must exceed a certain dynamic obstacle avoidance safety distance. In complex dynamic environments, this dynamic obstacle avoidance safety distance can be dynamically adjusted based on obstacle speed and ship speed to ensure sufficient time and space for avoidance. Dynamic obstacle avoidance safety distance Calculations typically consider the relative velocity factor:

[0056] =( )

[0057] In the formula, It is an unmanned surface vessel. Avoiding dynamic obstacles Obstacle avoidance safe distance; It is a dynamic obstacle speed; For dynamic obstacles Speed ​​of unmanned boat The projection of speed. It should be noted that static and dynamic obstacles can be determined through observation before navigation.

[0058] Formation collision avoidance constraints mean that the distance between each unmanned surface vessel (USV) in a formation must be greater than the safe collision avoidance distance between the formation's crew during navigation. Based on the ship's maneuverability and the braking capability of its control system, the safe collision avoidance distance between formation members is expressed by the following formula:

[0059] In the formula, The speed of the two unmanned boats is and Braking distance at that time.

[0060] Considering the motion characteristics, response characteristics under force, and propulsion system performance of the unmanned surface vessel, the kinematic and dynamic constraints are expressed by the following formulas:

[0061]

[0062]

[0063]

[0064] In the formula, The thruster power and drag model sets the upper limit of the unmanned surface vessel's speed; It is an acceleration limit to prevent acceleration from causing overload of the propulsion system; To achieve the maximum rate of change of heading angle, to avoid sudden turns and loss of control; This refers to the maximum economic speed. The method used in determining the upper speed limit of the unmanned surface vessel (USV) through a propeller power and drag model can be implemented using relevant technologies, which will not be elaborated upon here. Furthermore, the acceleration limit, maximum rate of change of heading angle, and maximum economic speed can be core thresholds determined through engineering calculations and real-ship testing, based on USV hull design, power / control system performance models, and navigation safety constraints. In practical applications, these thresholds can be dynamically adapted to the specific navigation scenarios.

[0065] Step S2023: Construct a time-optimal A based on the cost function and constraints. The algorithm's global path planning model generates initial navigation paths for the unmanned surface vessel (USV) convoy. Specifically, considering the aforementioned cost function and constraints, it can be implemented according to the relevant technology A... The algorithm's path planning method, which generates the initial navigation path, will not be elaborated upon here.

[0066] Step S202: Dynamically calculate the collision avoidance threat level of each unmanned surface vessel in the formation, and determine the dynamic priority of each unmanned surface vessel based on the collision avoidance threat level.

[0067] Specifically, step S202 includes: Step S2021: Determine the collision avoidance threat level of each unmanned surface vessel based on the distance threat factor, relative speed threat factor, and obstacle size threat factor.

[0068] The distance threat factor is determined based on the obstacle distance quantized using an exponential decay function. Specifically, this distance threat factor is expressed by the following formula:

[0069] In the formula, The attenuation coefficient is... This refers to the relative distance. The relative distance represents the distance between the current unmanned surface vessel (USV) and other USVs or other dynamic obstacles.

[0070] The relative speed threat factor is determined based on a preset collision time, and specifically, the relative speed threat factor is expressed by the following formula:

[0071] In the formula, To estimate the collision time, It is a very small constant to prevent numerical explosion when the collision time is extremely short.

[0072] The obstacle size threat factor is determined based on the obstacle size coefficient and the speed of the unmanned surface vessel. Specifically, the obstacle size threat factor is expressed by the following formula:

[0073] This formula indicates that speed is weighted by obstacle size; larger obstacles have a greater impact on threat level due to changes in speed. In the formula, It is the obstacle size factor. It is the minimum circumcircle radius of the obstacle. As a baseline for measuring obstacle size. It is the projection of the obstacle's velocity onto the unmanned surface vessel's (USV) travel direction. This is the maximum speed of the unmanned surface vessel.

[0074] Step S2022: Determine the dynamic priority of each unmanned surface vessel (USV) in the formation based on its collision avoidance threat level. Specifically, the collision avoidance threat level is expressed by the following formula:

[0075] In the formula, , and It is a normalization process for each threat factor. , , . , and These are weighting coefficients, and their values ​​range from [value range missing]. ,and Among them, unmanned surface vessels with a higher collision avoidance threat level have higher priority.

[0076] Step S203: When a path intersection conflict occurs, trigger local path replanning for the unmanned surface vessel according to the dynamic priority order; for details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0077] Step S204 involves using B-spline curves to smooth and optimize the replanned local paths. Specifically, step S204 includes: Step S2041: Determine the parametric expression of the B-spline curve of the replanned local path; specifically, the parametric expression of the B-spline curve of the replanned local path... The path points are used as B-spline curves. There are control points, given node vectors. ,but The parametric expression for a B-spline curve is:

[0078]

[0079]

[0080] In the formula, These are the coordinates of the control points; For node vectors; Number of control points; The order of the B-spline curve; For the first Each node vector, control point, or basis function; For the first indivual B-order spline basis functions, and control points Correspondingly.

[0081] Step S2042: With the goal of minimizing the total path length, the parameterized expression is optimized based on preset constraints to obtain the optimized path. Specifically, based on the parameterized expression of the B-spline curve, an optimization objective function based on the total path length is constructed and solved using the interior point method to minimize obstacle avoidance energy consumption. The constraints of this optimization objective function include obstacle avoidance constraints, curvature constraints, velocity constraints, and acceleration constraints. Therefore, the optimization objective function is expressed by the following formula:

[0082] In the formula, To control the displacement of the point, To control the number of points, For spatial dimensions, For the first Displacement vectors of control points. yes The unit vector pointing to the obstacle. Representing vectors In the normal vector The projected length in the direction is used to determine whether a safe obstacle avoidance distance can be maintained after the path point is adjusted. , These are the center coordinates of the obstacle. and Let be the first and second derivative vectors of the B-spline curve, i.e., the velocity curve and the acceleration curve. This represents the maximum curvature. and These represent the maximum speed and maximum acceleration of the unmanned surface vessel.

[0083] As one or more specific application embodiments of the present invention, such as Figure 2 and Figure 3 As shown, the unmanned surface vessel (USV) formation path planning method is implemented using the following process: Step S1: Global Path Planning. To improve the navigation efficiency of the unmanned surface vessel, a time-optimal A... The algorithm plans a navigation path for the unmanned surface vessel (USV) convoy, enabling the convoy to quickly pass through sea areas with inconsistent ocean current distribution.

[0084] Specifically, step S1 includes: Step S11: Modeling of the unmanned surface vessel formation system.

[0085] consider An unmanned surface vessel and Each unmanned surface vessel (USV) can obtain pose information shared by its fellow USVs, prior map information, real-time location information and water depth of identified dynamic obstacles, as well as ocean current and sea ice information collected by space-based intelligence systems. Through global planning and local fine-tuning, the USV convoy can achieve safe and efficient navigation in harsh sea environments. The objective of the model is to minimize the convoy navigation time. The constraints in the model include static obstacle constraints, dynamic obstacle avoidance constraints, convoy collision avoidance constraints, and kinematic and dynamic constraints.

[0086] Step S12, global path planning.

[0087] Traditional A The algorithm only considers application scenarios with constant movement speed and free direction during planning, ignoring the vector superposition effect of ocean currents on the motion of the unmanned surface vessel (USV). It only optimizes the geometric shortest path, which may result in choosing a counter-current path that takes longer in actual operation. This embodiment constructs a time-optimal A... The algorithm automatically avoids areas with strong countercurrents, prioritizes paths with high combined speeds, and optimizes the travel time.

[0088] Step S2: Dynamic Priority Calculation. Based on the threat level of obstacles, the obstacle avoidance priority of each vessel in the formation is dynamically assigned. Higher-priority unmanned surface vessels (USVs) choose their paths first, while lower-priority USVs replan their routes locally to avoid collisions, reducing the probability of intersection conflicts.

[0089] Specifically, to address the safety navigation requirements of unmanned surface vessel (USV) convoys performing missions, including obstacle avoidance and collision avoidance, while simultaneously reducing collision risks, this embodiment employs a dynamic priority calculation mechanism based on obstacle threat levels. This mechanism dynamically allocates obstacle avoidance priorities to each USV within the convoy based on the degree of obstacle threat (e.g., speed, distance). For USVs with intersecting obstacle avoidance paths, path selection is performed according to priority to resolve path conflict issues. For example, a combined threat level is determined using distance threat factors, relative speed threat factors, and obstacle size threat factors; USVs with higher combined threat levels are assigned higher priorities.

[0090] Step S3: Local Path Optimization. Considering task constraints, navigation constraints, obstacle avoidance and collision avoidance constraints, etc., based on the obstacle avoidance priorities of each vessel calculated in S2, for unmanned surface vessels with lower priority in obstacle avoidance path intersection conflicts, the time-cost-optimal A1 method from Step S1 is adopted. The algorithm adjusts the obstacle avoidance path to resolve the formation path conflict problem.

[0091] Specifically, based on the composite threat level of the unmanned surface vessels (USVs) calculated above, USVs are prioritized. USVs with higher priority choose their paths first, while those with lower priority choose their paths later. USVs of different priorities can all adopt the time-optimal A / B algorithm of this embodiment. The algorithm performs local path replanning and detours to reduce the probability of intersection conflicts.

[0092] Step S4: Path Smoothing. Based on the obstacle avoidance paths calculated in steps S2 and S3, B-spline curves are used to smooth them. The smoothed path is optimized by adjusting the control points to avoid path conflicts after smoothing, thus generating safe and smooth obstacle avoidance paths for the unmanned surface vessel formation.

[0093] Specifically, in path smoothing, the obstacle avoidance path first generated by local planning... The path points are used as B-spline curves. There are control points, given node vectors. ,Sure The parameterized expression of the third-order B-spline curve is then derived. Based on the locally optimal obstacle avoidance path, path smoothing is performed. To ensure that the smoothed path satisfies obstacle avoidance constraints, kinematic constraints, and dynamic constraints, control point optimization is performed on the quasi-uniform third-order B-spline curve based on obstacle avoidance path points. An optimization objective function based on the total path length is constructed and solved using the interior point method to minimize obstacle avoidance energy consumption.

[0094] This invention addresses the issues of track deviation, path oscillation, and energy loss caused by the spatiotemporal differences in ocean current fields. It proposes a method for unmanned surface vessel (USV) formation path planning under ocean current constraints. This method, based on constraints such as mission constraints, environmental constraints, USV kinematics and kinematic constraints, USV collision avoidance constraints, obstacle avoidance constraints, and path curvature continuity, proposes an A-factor algorithm based on time cost. The global path planning method, the dynamic priority mechanism based on obstacle threats, and the B-spline curve path smoothing method with kinematic constraints prioritize downstream or cross-current paths, avoid upstream and high-risk areas, and are compatible with unmanned surface vessel (USV) maneuver constraints. This solves the problem of local path conflicts in USV formations, realizes dynamic planning and optimization of formation navigation paths in harsh environments, and generates safe and time-efficient optimal paths.

[0095] Furthermore, this invention achieves multi-dimensional technological breakthroughs in solving the unmanned surface vessel (USV) path planning problem, targeting two core scenarios: formation collaboration and dynamic ocean current environments, while also overcoming limitations in related technologies. First, addressing the needs of USV formation collaboration, it proposes a dynamic priority calculation mechanism based on obstacle threat levels. This mechanism includes other USVs within the formation as dynamic obstacles, allocating obstacle avoidance priorities through a composite threat level model. High-priority USVs prioritize path planning, while low-priority USVs undergo local replanning, thoroughly resolving the multi-USV collision avoidance conflict problem. Second, fully considering the spatiotemporal differences in ocean current fields, it designs a time-optimal A-mode mechanism in global path planning. The algorithm achieves optimal path planning in ocean current environments by calculating the resultant velocity, imposing risk penalties (higher penalties in strong countercurrent areas), and extending node expansion rules for downstream acceleration and countercurrent detours, thereby reducing energy consumption and navigation time. Finally, the path is smoothed using B-spline curves, while incorporating multiple constraints such as kinematics and obstacle / collision avoidance, ensuring both path smoothness and the safety and efficiency of formation coordination.

[0096] This embodiment also provides an unmanned surface vessel (USV) convoy path planning device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0097] This embodiment provides an unmanned surface vessel (USV) platooning path planning device, such as... Figure 4 As shown, it includes: Global path planning module 41 is used to construct a time-optimal A path, taking into account ocean current speed, with the objective of minimizing the total formation sailing time. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation; The dynamic priority calculation module 42 is used to dynamically calculate the collision avoidance threat level of each unmanned surface vessel in the formation, and determine the dynamic priority of each unmanned surface vessel based on the collision avoidance threat level. The local path planning module 43 is used to trigger local path replanning for the unmanned surface vessel according to the dynamic priority order when path intersection conflicts occur. The path optimization module 44 is used to perform smooth optimization of the replanned local path using B-spline curves.

[0098] The unmanned surface vessel (USV) formation path planning device provided in this embodiment of the invention can execute the USV formation path planning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0099] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0100] The following is a detailed reference. Figure 5 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 11, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 12 or a program loaded from memory 18 into random access memory (RAM) 13. The RAM 13 also stores various programs and data required for the operation of the electronic device. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0101] Typically, the following devices can be connected to I / O interface 15: input devices 16 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 17 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 18 including, for example, magnetic tapes, hard disks, etc.; and communication devices 19. Communication device 19 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0102] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 19, or installed from a memory 18, or installed from a ROM 12. When the computer program is executed by the processor 11, it performs the functions defined in the unmanned surface vessel formation path planning method of the embodiments of the present invention.

[0103] Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0104] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the unmanned surface vessel (USV) formation path planning method shown in the above embodiments is implemented.

[0105] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0106] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for unmanned surface vessel (USV) platooning path planning, characterized in that, The method includes: With the objective of minimizing the total sailing time of the formation, a time-optimal A-type formation is constructed considering ocean current speed. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation; The collision avoidance threat level of each unmanned surface vessel (USV) in the formation is dynamically calculated, and the dynamic priority of each USV is determined based on the collision avoidance threat level. When path intersection conflicts occur, local path replanning is triggered for the unmanned surface vessel according to the dynamic priority order. B-spline curves are used to smooth and optimize the local paths of the replanning.

2. The method according to claim 1, characterized in that, With the objective of minimizing the total sailing time of the formation, a time-optimal A-type formation is constructed considering ocean current speed. The algorithm's global path planning model generates initial navigation paths for the unmanned surface vessel (USV) convoy, including: With the goal of minimizing the total voyage time of the formation, a cost function is constructed that includes an actual movement cost function, a heuristic function, and a risk cost function. The risk cost function is determined based on the relationship between the resultant velocity and the still water speed of the unmanned surface vessel. The resultant velocity is determined based on the ocean current speed and the speed of the unmanned surface vessel. The constraints are constructed, including static obstacle constraints, dynamic obstacle avoidance constraints, formation collision avoidance constraints, and kinematic and dynamic restriction constraints. Based on the aforementioned cost function and constraints, construct a time-optimal A... The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation.

3. The method according to claim 1, characterized in that, When generating the initial navigation path, the nodes are expanded using the rules of downstream acceleration and upstream detour.

4. The method according to claim 1, characterized in that, Dynamically calculate the collision avoidance threat level of each unmanned surface vessel (USV) within the formation, and determine the dynamic priority of each USV based on the collision avoidance threat level, including: The collision avoidance threat level of each unmanned surface vessel is determined based on the distance threat factor, relative speed threat factor, and obstacle size threat factor. The dynamic priority of each unmanned surface vessel (USV) in the formation is determined based on its collision avoidance threat level.

5. The method according to claim 4, characterized in that, The distance threat factor is determined based on the obstacle distance quantized by the exponential decay function, the relative speed threat factor is determined based on the preset collision time, and the obstacle size threat factor is determined based on the obstacle size coefficient and the speed of the unmanned surface vessel.

6. The method according to claim 1, characterized in that, B-spline curves are used to smooth and optimize the local paths during replanning, including: Determine the parametric expression for the B-spline curve of the replanned local path; With the goal of minimizing the total path length, the parameterized expression is optimized based on preset constraints to obtain the optimized path.

7. The method according to claim 6, characterized in that, The preset constraints include obstacle avoidance constraints, curvature constraints, velocity constraints, and acceleration constraints.

8. A platooning path planning device for unmanned surface vessels, characterized in that, The device includes: The global path planning module is used to construct a time-optimal A / B path, taking into account ocean current speeds, with the objective of minimizing the total formation sailing time. The algorithm's global path planning model generates the initial navigation path for the unmanned surface vessel formation; The dynamic priority calculation module is used to dynamically calculate the collision avoidance threat level of each unmanned surface vessel in the formation, and determine the dynamic priority of each unmanned surface vessel based on the collision avoidance threat level. The local path planning module is used to trigger local path replanning for the unmanned surface vessel according to the dynamic priority order when path intersection conflicts occur. The path optimization module is used to smooth and optimize the replanned local paths using B-spline curves.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the unmanned surface vessel formation path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the unmanned surface vessel formation path planning method according to any one of claims 1 to 7.

Images