Unmanned ship cluster area patrol, interception and obstacle avoidance method, system and equipment based on layered architecture

Abstract

The invention discloses an unmanned surface vehicle cluster area patrol, interception and obstacle avoidance method, system and device based on a layered architecture, and relates to the technical field of unmanned surface vehicles, and the method comprises the steps: determining a task area and a protection area of an unmanned surface vehicle cluster; the unmanned ship cluster comprises a plurality of unmanned ships; acquiring position information at the current moment; the position information comprises the position of each unmanned ship, the position of the target ship and the position of the obstacle; the target boat is an interception target; based on the task area, the protection area and the position information at the current moment, calculating the course angle of each unmanned ship at the next moment by adopting a hierarchical control strategy model; the course angle comprises a patrol course angle, an interception course angle and an obstacle avoidance course angle; based on the course angle of each unmanned ship at the next moment, the unmanned ship cluster is controlled to complete area patrol in the protection area at the maximum speed of the unmanned ships, the target ship is intercepted in the task area, and obstacle avoidance is completed in the task area. The task execution efficiency of the unmanned ship can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned surface vessels, and in particular to a method, system and device for area patrol, interception and obstacle avoidance of an unmanned surface vessel cluster based on a hierarchical architecture. Background Art

[0002] An unmanned surface vessel (USV) is a robotic system with autonomous planning, navigation and driving developed to support maritime missions. With the progress of technology, unmanned surface vessels have shown increasingly wide application potential in many fields such as maritime safety, marine information collection and environmental monitoring. Among them, the area protection task of unmanned surface vessels is particularly crucial, aiming to complete the search for targets and collision-free interception tasks in a complex and dynamically changing marine environment.

[0003] For this area protection task, it is necessary to comprehensively monitor the target task area according to the task requirements and environmental conditions (such as wind speed and direction, water flow speed and direction, obstacle distribution, etc.). Most traditional methods focus on the trajectory planning and obstacle avoidance strategies of a single vessel. For simple and deterministic tasks, a single-layer action control strategy is often adopted, lacking the overall grasp and collaborative decision-making ability of the task area.

[0004] Currently, when performing the area protection task, the related technical solutions have the following deficiencies: (1) Only the trajectory planning and obstacle avoidance design of a single unmanned surface vessel are carried out, ignoring the possibility of multi-vessel collaboration; (2) Even in scenarios involving multiple vessels, there is a lack of collaborative control among the vessels, and the trajectory planning and obstacle avoidance are still carried out independently. This not only weakens the overall perception and coordinated response ability to the environment, but also makes it difficult to adapt to complex and changing task requirements, resulting in problems such as loss of area supervision and failure of target interception, leading to low task execution efficiency of unmanned surface vessels. Summary of the Invention

[0005] The purpose of the present application is to provide a method, system and device for area patrol, interception and obstacle avoidance of an unmanned surface vessel cluster based on a hierarchical architecture, which can improve the task execution efficiency of unmanned surface vessels.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a method for area patrol, interception and obstacle avoidance of an unmanned surface vessel cluster based on a hierarchical architecture, including:

[0008] Determine the task area and protection area of the unmanned surface vessel cluster; the unmanned surface vessel cluster includes multiple unmanned surface vessels;

[0009] Obtain the position information at the current moment; the position information includes the positions of each unmanned surface vessel, the position of the target vessel and the positions of obstacles;

[0010] Based on the task area, the protection area, and the position information at the current moment, a hierarchical control strategy model is used to calculate the heading angle of each unmanned boat at the next moment; the heading angles include: patrol heading angle, interception heading angle, and obstacle avoidance heading angle;

[0011] Based on the heading angle of each unmanned boat at the next moment, the unmanned boat cluster is controlled at the maximum speed of the unmanned boat to complete area patrol in the protection area, intercept the target boat in the task area, and avoid obstacles in the task area.

[0012] In a second aspect, the present application provides a system for area patrol, interception, and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture, including:

[0013] An area determination module, configured to determine the task area and the protection area of the unmanned boat cluster; the unmanned boat cluster includes multiple unmanned boats;

[0014] An acquisition module, configured to acquire the position information at the current moment; the position information includes the positions of each unmanned boat, the position of the target boat, and the position of the obstacle;

[0015] A hierarchical control strategy module, configured to calculate the heading angle of each unmanned boat at the next moment by using a hierarchical control strategy model based on the task area, the protection area, and the position information at the current moment; the heading angles include: patrol heading angle, interception heading angle, and obstacle avoidance heading angle;

[0016] A control module, configured to control the unmanned boat cluster to complete area patrol in the protection area, intercept the target boat in the task area, and avoid obstacles in the task area at the maximum speed of the unmanned boat based on the heading angle of each unmanned boat at the next moment.

[0017] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for area patrol, interception, and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture described in the first aspect above.

[0018] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0019] The present application provides a method, system, and device for area patrol, interception, and obstacle avoidance of unmanned boat clusters based on a hierarchical architecture. By determining the task area and protection area of the unmanned boat cluster and obtaining the position information at the current moment, and adopting a hierarchical control strategy model, the heading angles (patrol heading angle, interception heading angle, and obstacle avoidance heading angle) of each unmanned boat for the tasks to be executed at the next moment are determined, so as to complete area patrol in the protection area and complete interception and obstacle avoidance in the task area. The present application uses a hierarchical control strategy model to determine the tasks (patrol, interception, or obstacle avoidance) to be executed by each unmanned boat, enabling the unmanned boat cluster to give full play to the advantages of collaborative operation and improving the efficiency of the unmanned boat in executing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a schematic flowchart of a method for area patrol, interception, and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture in an embodiment of the present application;

[0022] Figure 2 It is a schematic diagram of a hierarchical control strategy model provided in an embodiment of the present application;

[0023] Figure 3 It is a schematic diagram of the positions of an unmanned boat and a target boat provided in an embodiment of the present application;

[0024] Figure 4 It is a schematic diagram of the positions of virtual patrol points provided in an embodiment of the present application;

[0025] Figure 5 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0027] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0028] In an exemplary embodiment, as Figure 1 shown, a method for regional patrol, interception, and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture is provided. This method is executed by a computer device, specifically, it can be executed alone by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking the application of this method to a server as an example for illustration, it includes the following steps 1 to step 5.

[0029] Among them:

[0030] Step 1: Determine the task area and protection area of the unmanned boat cluster; the unmanned boat cluster includes multiple unmanned boats. Specifically, it includes: obtaining the position of the protected target; taking the position of the protected target as the center of a circle and determining a first area with a first preset distance as the radius; taking the position of the protected target as the center of a circle and determining a protection area with a second preset distance as the radius; the first preset distance is greater than the second preset distance; the non-overlapping part of the first area and the protection area is determined as the task area.

[0031] Specifically, the unmanned boat cluster includes a team unit composed of multiple unmanned boats; the unmanned boat cluster contains one or more main boats, called main nodes; the rest are slave boats, called slave nodes; the number of main nodes is determined by the number of boat units in the unmanned boat cluster that can communicate independently with other boats; each main node unit can independently calculate and output the heading angles of all unmanned boats in its set to the console, and this heading angle is calculated by a hierarchical strategy model; each slave node unit can communicate independently with the console and receive control instructions sent by the main node in real time; when a main node loses communication, other slave nodes in its corresponding set switch to main nodes and undertake the task of calculation results; the first area is a circular area with a radius of R, and the protected target is abstracted as the center point of this circle; the protection area of the unmanned boat is also an area surrounded by a circle with a radius of r centered on this center point; the task area of the unmanned boat is the non-overlapping part of the first area and the protection area.

[0032] Step 2: Obtain the position information at the current moment; the position information includes the positions of each unmanned boat, the position of the target boat, and the position of the obstacle.

[0033] Specifically, use a sensing module to determine the position of each unmanned boat at the current moment; use a marine radar to detect and obtain the position of the target boat and the position of the obstacle.

[0034] Step 3: Based on the task area, protection area, and the position information at the current moment, use a hierarchical control strategy model to calculate the heading angle of each unmanned boat at the next moment; the heading angle includes: patrol heading angle, interception heading angle, and obstacle avoidance heading angle.

[0035] Among them, as Figure 2As shown, the hierarchical control strategy model includes: target allocation at the top layer, action strategies at the middle layer, and security guarantees at the bottom layer. The hierarchical control strategy model uses an auction algorithm for target assignment in target allocation at the top layer; then, in the action strategies at the middle layer, an adaptive guidance method is used to determine the patrol course angle and interception course angle of the unmanned boat respectively, so as to control the unmanned boat for distal interception, patrol search, and proximal interception subsequently; meanwhile, in the security guarantee layer at the bottom layer, obstacle avoidance detection is carried out based on the obstacle avoidance technology of the artificial potential field method (Artificial Potential Field, APF), and finally the desired speed v exp (i.e., the maximum speed) and the desired heading angle ψ exp (i.e., the course angle of each unmanned boat at the next moment) are used to control the unmanned boat to complete patrol, interception, and obstacle avoidance.

[0036] Specifically, step 3 specifically includes the following steps:

[0037] Step 31: With the best match between the target boat and the unmanned boat as the goal and the existence of a matching relationship between the target boat and the unmanned boat as the constraint, a target function is constructed.

[0038] Step 32: When the position of the obstacle is not obtained in the mission area, based on the position of the target boat and the position of the unmanned boat, the auction algorithm is used in the target assignment layer of the hierarchical control strategy model to calculate the target function and determine the matching relationship between the unmanned boat and the target boat; the matching relationship includes: no match and best match.

[0039] In a specific example, steps 31 - 32 specifically include: The overall computational complexity of the auction algorithm is O(N 2 ), where N is the number of USVs and targets.

[0040] The expression of the target function is:

[0041]

[0042] α ik = 1 / (L 1 + L 2 ).

[0043] Where, a ik is the cost variable between the i-th unmanned boat and the k-th target boat; α ik is the matching relationship between the i-th unmanned boat and the k-th target boat, where, α ik ∈{0, 1}, when α ik = 1, it means there is a matching relationship between the i-th unmanned boat and the k-th target boat, and when α ik = 0, it means there is no matching relationship between the i-th unmanned boat and the k-th target boat; M is the number of target boats; N is the number of unmanned boats; L 1is the distance between the i-th unmanned boat and the k-th target boat; L 2 is the distance between the i-th unmanned boat and the extreme interception point.

[0044] In target allocation, the distance between the target boat and the corresponding best-matched unmanned boat and the distance between the corresponding best-matched unmanned boat and the extreme interception point are used, that is Figure 3 where L 1 and L 2 to determine the optimal pairing solution. From the expression of the objective function, it can be seen that if the sum of the distances between all matched unmanned boats and the targets and the distances between the unmanned boats and the final interception point is the smallest, the objective function reaches the maximum value. Therefore, target assignment is essentially a process of traversing and solving the minimum distance sum.

[0045] To successfully complete the interception mission and prevent the target from entering the protection area Ω p , the concept of the extreme interception point is introduced, that is Figure 3 the point B in p . Geometrically, the point B represents the intersection of the line connecting the target and the center of the protection area Ω p and the boundary of Ω

[0046] The calculation formula for the extreme interception point is:

[0047]

[0048] where B is the position of the extreme interception point; is the position of the k-th target boat; Ω p is the position of any point in the protection area.

[0049] Step 33: Based on the matching relationship between the unmanned boats and the target boats, the adaptive guidance method is used in the action strategy layer of the hierarchical control strategy model to determine the patrol course angle and interception course angle of the unmanned boats. It specifically includes the following steps:

[0050] Step 331: When the matching relationship is no match, the boundary of the protection area is determined as the travel trajectory of the unmanned boat.

[0051] Step 332: Based on the number of unmanned boats and the travel trajectories of the unmanned boats, the method of equally spaced arrangement is used to determine the virtual patrol points of the unmanned boats.

[0052] Step 333: Based on the virtual patrol points of the unmanned boats, the adaptive interception strategy function is used to calculate the patrol adjustment value to be adjusted of the unmanned boats.

[0053] The expression of the adaptive interception strategy function:

[0054]

[0055] Among them, ψ esp2 is the patrol adjustment value to be adjusted for the unmanned boat; is the current heading angle of the i-th unmanned boat (clockwise relative to true north, range 0 - 360°); B patrol is the relative azimuth angle of the virtual patrol point currently tracked by the unmanned boat (clockwise relative to true north, range 0 - 360°); is the position of the k-th target boat corresponding to the i-th unmanned boat; Ω s is the mission area.

[0056] Specifically, when the unmanned boat is not assigned a corresponding intercept target, the unmanned boat enters a separate patrol module to perform the target patrol task.

[0057] Step 334: Adjust the current heading angle of the unmanned boat based on the patrol adjustment value to be adjusted for the unmanned boat to obtain the patrol heading angle of the unmanned boat.

[0058] Step 335: When the matching relationship is the best match, determine whether the distance between the position of the target boat and the extreme intercept point is greater than the distance between the best unmanned boat and the extreme intercept point; the best unmanned boat is the unmanned boat that has the best matching relationship with the target boat.

[0059] Step 336: If so, based on the position of the target boat and the position of the best unmanned boat, use the adaptive interception strategy function to calculate the interception adjustment value to be adjusted for the best unmanned boat.

[0060] Step 337: If not, based on the position of the best unmanned boat and the position of the extreme intercept point, use the adaptive interception strategy function to calculate the interception adjustment value to be adjusted for the best unmanned boat.

[0061] Expression of the adaptive interception strategy function:

[0062]

[0063] Among them, ψ esp1 is the difference between the i-th unmanned boat and the interception heading angle, that is, the interception adjustment value to be adjusted; ψ esp2 is the difference between the i-th unmanned boat and the patrol heading angle, that is, the patrol adjustment value to be adjusted; is the current heading angle of the i-th unmanned boat (clockwise relative to true north, range 0 - 360°); is the relative azimuth angle of the k-th target boat (clockwise relative to true north, range 0 - 360°); L 2 is the distance between the i-th unmanned boat and the extreme intercept point; L 3 is the distance between the k-th target boat and the extreme intercept point; d s is the preset distance; B is the position of the extreme intercept point;

[0064] Specifically, when L 2 <L 3 -d s it is considered that the distance of the target boat reaching the extreme interception point is greater than that of the unmanned boat reaching the extreme interception point, that is, the threat degree of the target boat to the protection area is relatively small, and a certain margin d s is reserved. At this time, it can directly go to the front point of the target boat for interception. The margin d s includes the distance loss caused by the steering difference between the current heading angle and the desired heading angle (i.e., the interception heading angle) of the unmanned boat.

[0065] When L 2 >L 3 -d s it is exactly the opposite. At this time, it is considered that the threat degree of the target boat to the protection area is relatively large. Intercepting directly at the front point of the target boat may lead to interception failure due to turning inertia. Therefore, at this time, the unmanned boat must go to the extreme interception point for interception.

[0066] Step 338: Adjust the current heading angle of the unmanned boat based on the interception adjustment value of the unmanned boat to obtain the interception heading angle of the unmanned boat.

[0067] In a specific embodiment, as Figure 4 shown, in order to ensure complete supervision coverage of the mission area Ω s , patrol tasks are performed at N s equidistant points on Ω p . These equidistant points are also called virtual patrol points. The angle interval between each point is given by 360 / N p , where N p is the number of patrol unmanned boats, which is obtained from the total number of unmanned boats N a - the number of target matching pairs N d .

[0068] In the action strategy layer of the hierarchical control strategy model, by continuously calculating and updating the positions of the virtual patrol points, the unmanned boat can effectively move along the predetermined patrol route. The positions of these virtual patrol points are determined according to the center point and the speed of the unmanned boat.

[0069] In a specific embodiment, the speed of the unmanned boat can be adjusted in real time. The positions of the virtual patrol points are updated with the changes of speed and time. The proportional navigation algorithm is used to calculate the required speed of the unmanned boat. This algorithm ensures that the unmanned boat can adjust its speed in real time and patrol along the planned path by adjusting the speed of the unmanned boat in real time.

[0070] Step 34: When the position of the obstacle is obtained in the task area, based on the position of the obstacle and the position of the unmanned boat, use the artificial potential field method to calculate the enhanced potential field function to obtain the resultant force vector acting on the unmanned boat.

[0071] Specifically, the enhanced potential field function includes: a repulsive force function and an attractive force function.

[0072] Expression of the enhanced potential field function:

[0073]

[0074] Among them, is the resultant force vector acting on the i-th unmanned boat; is the attractive force vector acting on the i-th unmanned boat from any obstacle; is the repulsive force vector acting on the i-th unmanned boat from the j-th obstacle.

[0075] The calculation formula of the repulsive force function is:

[0076]

[0077] Among them, is the magnitude of the repulsive force acting on the i-th unmanned boat from any obstacle; the scalar distance between the i-th unmanned boat and the j-th obstacle is the position of the i-th unmanned boat, is the position of the j-th obstacle corresponding to the i-th unmanned boat; D avo is a scalar for controlling the influence of the repulsive force field; is the repulsive force field coefficient; D min is the emergency avoidance distance; β is a hyperparameter for adjusting the repulsive force field strength in an emergency.

[0078] Among them, dividing the repulsive force (i.e., the repulsive force) into multiple parts helps to prevent the unmanned boat from over-maneuvering or under-reacting during obstacle avoidance, ensuring a smooth transition and making the movement of the unmanned boat more natural and smooth. The direction of the repulsive force is adjusted according to whether the obstacle is on the left or right side of the defender, and the design is as follows:

[0079]

[0080] Among them, is the direction of the repulsive force acting on the unmanned boat from the obstacle; in the formula, θ rel = θ I - ψ, θ rel is the azimuth angle of the obstacle relative to the unmanned boat; θ I is the azimuth angle of the obstacle relative to the unmanned boat in the northeast coordinate system, and ψ is the heading angle of the unmanned boat in the same coordinate system. As Figure 3As shown, when θ rel < 0, the target is on the left side of the unmanned boat; when θ rel ≥ 0, the target is on the right side of the unmanned boat. Δα is an empirical determined value obtained from actual experiments, which is used to optimize the repulsive force angle, aiming to ensure that the unmanned boat can safely and stably avoid the target. After fine-tuning, this value optimizes the obstacle avoidance strategy, enabling the unmanned boat to effectively avoid the target while maintaining smooth navigation and reliable mission execution.

[0081] The calculation formula of the gravitational function is:

[0082]

[0083] where is the gravitational force magnitude of the i-th unmanned boat affected by any obstacle.

[0084] where is in the direction from the current position of the i-th unmanned boat to the following target point; the distance ratio is defined. Where the gravitational force is proportional to the distance J j to the target. By dynamically adjusting the coupling of the gravitational force and the repulsive force is realized, ensuring that the unmanned boat can effectively avoid obstacles when tracking the target in a complex scenario. In addition, the existence of the repulsive force prevents the unmanned boat from falling into local minima, and the dynamic adjustment of the gravitational force further improves the convergence efficiency and overall path optimization.

[0085] Step 35: Based on the resultant force vector received by the unmanned boat, determine the obstacle avoidance course angle of the unmanned boat in the safety guarantee layer of the hierarchical control strategy model.

[0086] Specifically, the calculation formula of the obstacle avoidance course angle of the unmanned boat is:

[0087]

[0088] where is the obstacle avoidance course angle of the i-th unmanned boat; is the component of the resultant force vector received by the i-th unmanned boat on the y-axis; is the component of the resultant force vector received by the i-th unmanned boat on the x-axis.

[0089] Step 4: Based on the course angle of each unmanned boat at the next moment, control the unmanned boat cluster to complete area patrol in the protection area and complete interception and obstacle avoidance in the mission area at the maximum speed of the unmanned boat.

[0090] The beneficial effects of the method for area patrol, interception and obstacle avoidance of the unmanned boat cluster based on the hierarchical architecture proposed in this application are mainly manifested in:

[0091] By determining the mission area and protection area of the unmanned boat cluster, and obtaining the position information at the current moment, a hierarchical control strategy model is adopted to determine the heading angle of each unmanned boat for the mission to be executed at the next moment. Among them, the unmanned boat cluster completes area patrol through the patrol heading angle and the maximum speed of the unmanned boat; the unmanned boat cluster completes the interception of the target boat through the interception heading angle and the maximum speed of the unmanned boat; the unmanned boat cluster completes obstacle avoidance of the obstacle through the obstacle avoidance heading angle and the maximum speed of the unmanned boat. This application uses a hierarchical control strategy model to determine the tasks (patrol, interception, or obstacle avoidance) to be executed by each unmanned boat, solves the problems of unclear task allocation of unmanned boats, low target exploration and interception efficiency, etc. in the area protection task, enables the unmanned boat cluster to give full play to the advantages of collaborative operations, and improves the efficiency of unmanned boats in executing tasks.

[0092] Based on the same inventive concept, the embodiment of the present application also provides a system for realizing the area patrol, interception and obstacle avoidance of an unmanned boat cluster based on the above-mentioned hierarchical architecture. The implementation solutions provided by this system to solve problems are similar to the implementation solutions recorded in the above method. Therefore, the specific limitations in one or more embodiments of the area patrol, interception and obstacle avoidance system of the unmanned boat cluster based on the hierarchical architecture provided below can refer to the limitations on the area patrol, interception and obstacle avoidance method of the unmanned boat cluster based on the hierarchical architecture in the above text, and will not be repeated here.

[0093] In an exemplary embodiment, a system for area patrol, interception and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture is provided, including:

[0094] An area determination module for determining the mission area and protection area of the unmanned boat cluster.

[0095] An acquisition module for acquiring the position information at the current moment; the position information includes the positions of each unmanned boat, the position of the target boat and the position of the obstacle; the target boat is the interception target.

[0096] A hierarchical control strategy module for calculating based on the mission area, protection area and the position information at the current moment by using a hierarchical control strategy model to obtain the heading angle of each unmanned boat at the next moment; the heading angle includes: patrol heading angle, interception heading angle and obstacle avoidance heading angle.

[0097] A control module for controlling the unmanned boat cluster to complete area patrol in the protection area, and interception and obstacle avoidance in the mission area at the maximum speed of the unmanned boat based on the heading angle of each unmanned boat at the next moment.

[0098] In an exemplary embodiment, a computer device is provided. This computer device can be a server or a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the heading angles calculated by the hierarchical control strategy model. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes a method for regional patrol, interception, and obstacle avoidance of an unmanned boat cluster based on a hierarchical architecture.

[0099] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0100] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAMs), magnetoresistive random access memories (MRAMs), ferroelectric random access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0102] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0103] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0104] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for patrolling, intercepting and avoiding obstacles in a cluster of unmanned boats based on a hierarchical architecture, characterized in that: The unmanned boat cluster area patrol, interception and obstacle avoidance method based on the hierarchical architecture includes: Determining a mission area and a protection area of ​​an unmanned boat cluster; the unmanned boat cluster includes a plurality of unmanned boats; Obtaining the current position information; the position information includes the position of each unmanned boat, the position of the target boat and the position of the obstacle; Based on the mission area, the protection area and the current position information, a hierarchical control strategy model is used to calculate the heading angle of each unmanned boat at the next moment; the heading angle includes: patrol heading angle, interception heading angle and obstacle avoidance heading angle; Based on the heading angle of each unmanned boat at the next moment, the unmanned boat cluster is controlled at the maximum speed of the unmanned boat to complete area patrol in the protection area, intercept the target boat in the mission area, and avoid the obstacle in the mission area.

2. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 1 is characterized in that: Determine the mission area and protection area of ​​the unmanned boat cluster, including: Get the location of the protected target; Determine a first area with the position of the protection target as the center and a first preset distance as the radius; The protection area is determined with the position of the protection target as the center and the second preset distance as the radius; the first preset distance is greater than the second preset distance; The non-overlapping portion of the first area and the protection area is determined as a task area.

3. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on hierarchical architecture according to claim 1 is characterized in that: Based on the mission area, the protection area and the current position information, a hierarchical control strategy model is used to calculate and obtain the heading angle of each unmanned boat at the next moment, specifically including: Taking the best match between the target boat and the unmanned boat as the goal and the matching relationship between the target boat and the unmanned boat as the constraint, the objective function is constructed. When the position of the obstacle is not obtained in the mission area, based on the position of the target boat and the position of the unmanned boat, an auction algorithm is used in the target allocation layer of the hierarchical control strategy model to calculate the objective function to determine the matching relationship between the unmanned boat and the target boat; the matching relationship includes: no match and best match; Based on the matching relationship between the unmanned boat and the target boat, the patrol heading angle and intercept heading angle of the unmanned boat are determined by using the adaptive guidance method in the action strategy layer of the hierarchical control strategy model. When the position of the obstacle is obtained in the mission area, the enhanced potential field function is calculated using the artificial potential field method based on the position of the obstacle and the position of the unmanned boat to obtain the resultant force vector acting on the unmanned boat; Based on the resultant force vector acting on the unmanned boat, the obstacle avoidance heading angle of the unmanned boat is determined in the safety assurance layer of the hierarchical control strategy model.

4. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 3 is characterized in that: The expression of the objective function is: q ik =1 / (L1+L2); Among them, a ik is the cost variable between the i-th unmanned boat and the k-th target boat; α ik is the matching relationship between the i-th unmanned boat and the k-th target boat, where α ik ∈{0,1},α ik =1 indicates that there is a matching relationship between the i-th unmanned boat and the k-th target boat, α ik =0 indicates that there is no matching relationship between the ith unmanned boat and the kth target boat; M is the number of target boats; N is the number of unmanned boats; L1 is the distance between the ith unmanned boat and the kth target boat; L2 is the distance between the ith unmanned boat and the extreme interception point; The calculation formula for the extreme intercept point is: Where B is the location of the extreme interception point; is the position of the kth target boat; Ω p is the position of any point in the protected area.

5. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 3 is characterized in that: Based on the matching relationship between the unmanned boat and the target boat, the adaptive guidance method is used in the action strategy layer of the hierarchical control strategy model to determine the patrol heading angle and interception heading angle of the unmanned boat, including: When the matching relationship is no match, the boundary of the protection area is determined as the driving track of the unmanned boat; Based on the number of unmanned boats and their driving tracks, the virtual patrol points of the unmanned boats are determined by arranging them at equal intervals. Based on the virtual patrol point of the unmanned boat, the adaptive interception strategy function is used to calculate the patrol adjustment value of the unmanned boat; The current heading angle of the unmanned boat is adjusted based on the patrol value to be adjusted of the unmanned boat to obtain the patrol heading angle of the unmanned boat; When the matching relationship is the best match, it is determined whether the distance between the position of the target boat and the extreme interception point is greater than the distance between the best unmanned boat and the extreme interception point; the best unmanned boat is the unmanned boat that has the best matching relationship with the target boat; If so, based on the position of the target boat and the position of the best unmanned boat, an adaptive interception strategy function is used to calculate the interception adjustment value of the best unmanned boat; If not, based on the position of the best unmanned boat and the position of the extreme interception point, an adaptive interception strategy function is used to calculate the interception adjustment value of the best unmanned boat; The current heading angle of the unmanned boat is adjusted based on the interception value to be adjusted of the unmanned boat to obtain the interception heading angle of the unmanned boat.

6. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 5 is characterized in that: The expression of the adaptive interception strategy function is: Among them, ψ esp1 is the interception value to be adjusted for the best unmanned boat; ψ esp2 The patrol value of the unmanned boat to be adjusted; is the current heading angle of the optimal unmanned boat; is the relative azimuth of the kth target boat; L2 is the distance between the best unmanned boat and the extreme interception point; L3 is the distance between the kth target boat and the extreme interception point; d s is the preset distance; B is the position of the extreme interception point; is the current heading angle of the i-th unmanned boat; B patrol is the relative azimuth of the virtual patrol point currently tracked by the unmanned boat; is the position of the kth target boat corresponding to the i-th unmanned boat; Ω s For the mission area.

7. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 3 is characterized in that: The enhanced potential field functions include: repulsive force function and attractive force function; The expression of the enhanced potential field function is: in, is the resultant force vector acting on the i-th unmanned boat; is the gravitational vector of any obstacle acting on the i-th unmanned boat; is the repulsive force vector of the j-th obstacle acting on the i-th unmanned boat; The calculation formula of the repulsion function is: in, is the repulsive force of any obstacle on the ith unmanned boat; the distance scalar between the ith unmanned boat and the jth obstacle is the position of the i-th unmanned boat, is the position of the jth obstacle corresponding to the i-th unmanned boat; D avo A scalar to control the influence of the repulsive field; is the repulsive field coefficient; D min is the emergency avoidance distance; β is the hyperparameter for adjusting the repulsive field strength in an emergency; The calculation formula of the gravitational function is: in, is the gravitational force of any obstacle on the i-th unmanned boat.

8. The method for patrolling, intercepting and avoiding obstacles of unmanned boat swarm based on layered architecture according to claim 3 is characterized in that: The calculation formula of the obstacle avoidance heading angle of the unmanned boat is: in, is the obstacle avoidance heading angle of the i-th unmanned boat; is the component of the resultant force vector acting on the i-th unmanned boat on the y-axis; is the component of the resultant force vector acting on the i-th unmanned boat on the x-axis.

9. An unmanned boat cluster area patrol, interception and obstacle avoidance system based on a layered architecture, characterized in that: The unmanned boat swarm area patrol, interception and obstacle avoidance method based on a layered architecture as described in any one of claims 1 to 8, the unmanned boat swarm area patrol, interception and obstacle avoidance system based on a layered architecture comprises: An area determination module, used to determine the mission area and protection area of ​​an unmanned boat cluster; the unmanned boat cluster includes multiple unmanned boats; An acquisition module is used to acquire the current position information; the position information includes the position of each unmanned boat, the position of the target boat and the position of the obstacle; A hierarchical control strategy module is used to calculate the heading angle of each unmanned boat at the next moment using a hierarchical control strategy model based on the mission area, the protection area and the position information at the current moment; the heading angle includes: patrol heading angle, interception heading angle and obstacle avoidance heading angle; The control module is used to control the unmanned boat cluster to complete area patrol in the protection area, intercept the target boat in the mission area, and avoid obstacles in the mission area based on the heading angle of each unmanned boat at the next moment at the maximum speed of the unmanned boat.

10. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the unmanned boat cluster area patrol, interception, and obstacle avoidance method based on a hierarchical architecture as described in any one of claims 1 to 8.

Images