Target-oriented cooperative hunting method for surface unmanned vehicle cluster

Abstract

The present application relates to the field of marine unmanned system cooperative control and decision-making technology, and particularly relates to a kind of surface unmanned ship cluster cooperative hunting method for target formation, comprising the following steps: obtaining the state information of target formation and surface unmanned ship cluster;Establish a target formation ship field model;Establish a hunting success determination function, determine whether to form effective hunting constraint to target formation;Determine the corresponding hunting target of each surface unmanned ship using a task allocation algorithm;Establish a hunting point optimization model, and determine the optimal hunting point corresponding to each surface unmanned ship using an optimization algorithm;Determine the sailing direction of each surface unmanned ship based on the optimal hunting point, if there is a surface unmanned ship that has not reached the corresponding hunting point, update the state information, re-determine the hunting point and adjust the sailing direction, until all surface unmanned ships reach the corresponding hunting point.The present application realizes the transformation from single target constraint to formation overall constraint, significantly improves the efficiency and success rate of multi-unmanned ship cooperative hunting.

Description

Technical Field

[0001] This invention relates to the field of collaborative control and decision-making technology for marine unmanned systems, specifically to a method for collaborative encirclement and capture of a target-oriented surface unmanned surface vessel swarm. Background Technology

[0002] With the development of marine intelligent equipment technology, unmanned surface vessels (USVs) have been widely used in tasks such as maritime patrol, marine surveillance, and pursuit and control. When carrying out pursuit and control missions in complex marine environments, a single USV is usually unable to effectively control maneuvering targets. Therefore, multiple USVs are usually organized into a swarm to carry out pursuit and control missions in a coordinated manner.

[0003] Currently, most research on the swarming and encirclement of unmanned surface vessels (USVs) focuses on single or multiple independent targets, with limited research on the encirclement of target formations. When encircling a target formation, USVs need to restrict not only the movement of individual target vessels but also the overall movement direction of the entire formation. Therefore, it is necessary to analyze the overall safe movement zone of the formation and design a reasonable encirclement structure accordingly. Furthermore, in collaborative USV swarming and encirclement missions, it is also necessary to rationally allocate the task relationships between USVs and targets and optimize the location of the encirclement points; otherwise, the encirclement efficiency may be low.

[0004] Therefore, there is an urgent need for a collaborative encirclement method that can rationally allocate encirclement tasks, optimize the location of encirclement points, and effectively restrict the safe area of ​​the overall movement of the target formation. Summary of the Invention

[0005] To address the technical problems in existing technologies, such as the inability to effectively constrain target formations as a whole and the lack of joint optimization between encirclement task allocation and encirclement point location, this invention provides a collaborative encirclement method for target formations of unmanned surface vessels (USVs), specifically including the following steps:

[0006] Obtain status information of the target formation and the unmanned surface vessel cluster; Establish a target formation ship domain model based on ship domain theory; A successful encirclement and capture determination function is established based on the target formation vessel domain model to determine whether the surface unmanned vessel cluster forms an effective encirclement and capture constraint on the target formation. A task allocation algorithm is used to determine the capture targets corresponding to each surface unmanned vessel. An optimization model for the capture point was established, and an optimization algorithm was used to determine the optimal capture point for each unmanned surface vessel. Based on the optimal capture point, the navigation direction of each surface unmanned vessel is determined, and each surface unmanned vessel is controlled to move along the navigation direction. If any surface unmanned vessel fails to reach the corresponding capture point, the status information is updated, the capture point is re-determined, and the navigation direction is adjusted until all surface unmanned vessels reach the corresponding capture point.

[0007] Furthermore, the steps for obtaining the state information of the target formation and the surface unmanned surface vessel swarm include: In a geodetic coordinate system, the positions of each target vessel located on the boundary of the target formation are collected, forming a set of target vessel positions. The formula is:

[0008] in, Indicates the target vessel Location, Indicates the number of target ships located on the boundary of the target formation; Obtain the locations of the unmanned surface vessels (USVs) participating in the encirclement and capture mission; the set of USV locations. The formula is:

[0009] in, Indicates unmanned surface vessels Location, This indicates the number of unmanned surface vessels participating in the encirclement and capture operation.

[0010] Furthermore, the steps for establishing a target formation vessel domain model include: Based on shipbuilding theory, in the target ship Establish a ship domain around the area to describe the safe navigation zone. The shipbuilding field The formula is:

[0011] By taking the union of the ship domains of each target in the target formation, a ship domain model of the target formation is established. The formula is:

[0012] in This indicates the number of target vessels located on the boundary of the target formation. Indicates the target vessel's number.

[0013] Furthermore, a successful encirclement determination function is established based on the target formation vessel domain model. The formula is:

[0014] in, Indicates the area of ​​the target fleet's vessel domain with respect to time. The derivative, This indicates an assembly of unmanned surface vessels. Indicates the first Unmanned surface vessel The decision function for whether to enter the fleet of ships. The formula is:

[0015] If each vessel on the boundary of the target formation moves in a direction that would prevent the area of ​​the target formation's territory from decreasing, then all of them will have Upon entering the target fleet's territory, the function for determining successful encirclement is then executed. ,otherwise .

[0016] Furthermore, a task allocation algorithm is used to assign task relationships between each surface unmanned surface vessel and each target vessel, thereby determining the capture target corresponding to each surface unmanned surface vessel. The formula is:

[0017] in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel.

[0018] Furthermore, the steps for determining the optimal capture point for each surface unmanned vessel include: An optimization model for the capture point is established with the goal of minimizing the cost of capture. The formula is:

[0019] in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel. This indicates the generation of a set of capture points outside the target fleet's vessel territory; An optimization algorithm is used to optimize the location of the encirclement point, so that the unmanned surface vessels assigned to the same target form the optimal encirclement structure around the target. The formula is as follows:

[0020] in, This represents the set of optimal capture points.

[0021] Furthermore, based on the optimal encirclement point, the navigation direction of each surface unmanned vessel is determined. :

[0022] in Indicates the first Unmanned surface vessel The corresponding optimal capture point.

[0023] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention constructs a target formation vessel domain model, mapping multiple individual targets into a unified formation-level safety area, thereby transforming the constraint from "single target constraint" to "formation-wide constraint". Compared with traditional methods that target only a single target, this invention can effectively restrict the overall movement direction of the target formation, preventing targets from escaping through formation coordination, thus significantly improving the integrity and success rate of the encirclement.

[0024] (2) The present invention constructs a successful encirclement determination function based on the change of the area of ​​the fleet of ships, which can determine in real time whether the encirclement has formed an effective constraint during the encirclement process, improve the certainty and stability of the system decision, and provide a clear basis for automatic control.

[0025] (3) This invention forms a hierarchical collaborative optimization mechanism by jointly modeling task allocation and encirclement point optimization, so that the matching relationship between the unmanned surface vessel and the target and the encirclement structure can be optimized synchronously, thereby forming a reasonable spatial distribution of unmanned surface vessels, avoiding the problem of unmanned surface vessels gathering or uneven distribution, and significantly improving the efficiency of multi-unmanned vessel collaborative encirclement. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the 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 based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a target-oriented unmanned surface vessel swarm collaborative encirclement and capture method according to the present invention.

[0028] Figure 2 This is a flowchart of a target-oriented unmanned surface vessel swarm collaborative encirclement and capture method in an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] As attached Figure 1 As shown, this invention discloses a method for the coordinated encirclement and capture of a target formation of unmanned surface vessels, mainly including the following steps: Obtain status information of the target formation and the unmanned surface vessel cluster; Establish a target formation ship domain model based on ship domain theory; A successful encirclement and capture determination function is established based on the target formation vessel domain model to determine whether the surface unmanned vessel cluster forms an effective encirclement and capture constraint on the target formation. A task allocation algorithm is used to determine the capture targets corresponding to each surface unmanned vessel. An optimization model for the capture point was established, and an optimization algorithm was used to determine the optimal capture point for each unmanned surface vessel. Based on the optimal capture point, the navigation direction of each surface unmanned vessel is determined, and each surface unmanned vessel is controlled to move along the navigation direction. If any surface unmanned vessel fails to reach the corresponding capture point, the status information is updated, the capture point is re-determined, and the navigation direction is adjusted until all surface unmanned vessels reach the corresponding capture point.

[0032] As a preferred embodiment of this application, the steps for obtaining the state information of the target formation and the surface unmanned surface vessel swarm include: In a geodetic coordinate system, the positions of each target vessel located on the boundary of the target formation are collected, forming a set of target vessel positions. The formula is:

[0033] in, Indicates the target vessel Location, Indicates the number of target ships located on the boundary of the target formation; Obtain the locations of the unmanned surface vessels (USVs) participating in the encirclement and capture mission; the set of USV locations. The formula is:

[0034] in, Indicates unmanned surface vessels Location, This indicates the number of unmanned surface vessels participating in the encirclement and capture operation.

[0035] As a preferred embodiment of this application, the steps for establishing a target formation vessel domain model include: Based on shipbuilding theory, in the target ship Establish a ship domain around the area to describe the safe navigation zone. The shipbuilding field The formula is:

[0036] By taking the union of the ship domains of each target in the target formation, a ship domain model of the target formation is established. The formula is:

[0037] in This indicates the number of target vessels located on the boundary of the target formation. Indicates the target vessel's number.

[0038] As a preferred embodiment of this application, a successful encirclement determination function is established based on a target formation ship domain model. The formula is:

[0039] in, Indicates the area of ​​the target fleet's vessel domain with respect to time. The derivative, This indicates an assembly of unmanned surface vessels. Indicates the first Unmanned surface vessel The decision function for whether to enter the fleet of ships. The formula is:

[0040] If each vessel on the boundary of the target formation moves in a direction that would prevent the area of ​​the target formation's territory from decreasing, then all of them will have Upon entering the target fleet's territory, the function for determining successful encirclement is then executed. ,otherwise .

[0041] In a preferred embodiment of this application, a task allocation algorithm is used to assign task relationships between each surface unmanned surface vessel and each target vessel, thereby determining the capture target corresponding to each surface unmanned surface vessel. The formula is:

[0042] in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel.

[0043] As a preferred embodiment of this application, the steps for determining the optimal capture point for each surface unmanned vessel include: An optimization model for the capture point is established with the goal of minimizing the cost of capture. The formula is:

[0044] in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel. This indicates the generation of a set of capture points outside the target fleet's vessel territory; An optimization algorithm is used to optimize the location of the encirclement point, so that the unmanned surface vessels assigned to the same target form the optimal encirclement structure around the target. The formula is as follows:

[0045] in, This represents the set of optimal capture points.

[0046] As a preferred embodiment of this application, the navigation direction of each unmanned surface vessel is determined based on the optimal encirclement point. :

[0047] in Indicates the first Unmanned surface vessel The corresponding optimal capture point.

[0048] Example The following is in conjunction with the appendix Figure 2The present invention will be further described in detail with reference to specific embodiments.

[0049] S1. Obtain the status information of the target formation and the surface unmanned surface vessel cluster. In a geodetic coordinate system, the positions of each target vessel located on the boundary of the target formation are collected, forming a set of target vessel positions. The formula is:

[0050] in, Indicates the target vessel Location, This indicates the number of target ships located on the boundary of the target formation.

[0051] Obtain the locations of the unmanned surface vessels (USVs) participating in the encirclement and capture mission; the set of USV locations. The formula is:

[0052] in, Indicates unmanned surface vessels Location, This indicates the number of unmanned surface vessels participating in the encirclement and capture operation.

[0053] S2. Establish a target formation vessel domain model. Based on shipbuilding theory, in the target ship Establish a ship domain around the area to describe the safe navigation zone. The shipbuilding field The formula is:

[0054] in, This indicates the radius of the area of ​​a circular vessel.

[0055] By taking the union of the ship domains of each target in the target formation, a ship domain model of the target formation is established. The formula is:

[0056] in This indicates the number of target vessels located on the boundary of the target formation. Indicates the target vessel's number.

[0057] The ship domain model is used to describe the overall navigation safety space of the target formation.

[0058] S3. Establish a function to determine the success of target formation and encirclement. A successful encirclement determination function is established based on a target formation vessel domain model. The formula is:

[0059] in, Indicates the area of ​​the target fleet's vessel domain with respect to time. The derivative, This indicates an assembly of unmanned surface vessels. Indicates the first Unmanned surface vessel The decision function for whether to enter the fleet of ships. The formula is:

[0060] If each vessel on the boundary of the target formation moves in a direction that would prevent the area of ​​the target formation's territory from decreasing, then all of them will have Upon entering the target fleet's territory, the function for determining successful encirclement is then executed. ,otherwise .

[0061] To ensure that the target vessel can only move in the direction that shrinks the area of ​​its fleet, at least two unmanned surface vessels need to be placed at the boundary of the target vessel's area to prevent the target vessel from moving in a direction that would expand the area of ​​the target fleet's area.

[0062] S4. Determine the capture targets corresponding to each surface unmanned vessel. The Hungarian algorithm was used for task allocation to obtain the capture targets corresponding to each surface unmanned vessel. The steps are as follows: S41. Establish the target allocation matrix :

[0063] Among them, matrix elements in The formula is:

[0064] The element The constraints to be satisfied are:

[0065]

[0066] in, This indicates the number of target vessels located on the boundary of the target formation. This indicates the number of unmanned surface vessels participating in the encirclement and capture operation.

[0067] S42. Calculate the distance between the unmanned surface vessel and the target, and construct the cost matrix. :

[0068] Among them, the cost matrix elements The formula is:

[0069] in, Indicates unmanned surface vessels To the target vessel The distance between them.

[0070] S43. Establish a task allocation optimization model :

[0071] in, This represents the target allocation matrix.

[0072] S44. Solve the task allocation optimization model using the Hungarian algorithm to obtain the optimal allocation matrix. Determine the corresponding capture targets for each unmanned surface vessel. :

[0073] in, A set representing the positions of the target vessel. This represents the transpose of the matrix.

[0074] S5. Determine the capture points corresponding to each surface unmanned vessel. The steps for finding the optimal capture point for each unmanned surface vessel using the particle swarm optimization algorithm are as follows: S51. Extract and capture target vessels unmanned surface vessels The formula is:

[0075] in, and This indicates the location of the two unmanned surface vessels.

[0076] S52. Identify the target vessel for the encirclement and capture. unmanned surface vessels Corresponding capture points :

[0077] Among them, the encircling angle Encirclement point The line connecting to the geometric center of the target ship's domain and the positive The angle between axes.

[0078] S53. Calculate the objective function :

[0079] in, and These are weighting coefficients. Indicates unmanned surface vessels to the encirclement point Time, Indicates unmanned surface vessels to the encirclement point The distance.

[0080] S54. Calculate the target vessel for encirclement and capture. Optimal capture point for unmanned surface vessels Let the position vector of the particle swarm optimization algorithm be... for:

[0081] objective function As the fitness function of the particle swarm optimization algorithm, the objective function is solved using the particle swarm optimization algorithm. The optimal encirclement angle vector corresponding to the minimum value That is, to obtain the target ship for the encirclement and capture Optimal capture point for unmanned surface vessels for: .

[0082] S6. Determine the course of each surface unmanned surface vessel. Based on the determined optimal capture point for each surface unmanned surface vessel (USV), the navigation direction of each USV is set, and each USV travels in this direction. The steps for calculating the navigation direction of each USV are as follows: S61, Calculation of unmanned surface vessels Corresponding capture points For the aforementioned unmanned surface vessel gravitational potential field :

[0083] in, Represents the gravitational gain coefficient. This indicates the size of an unmanned surface vessel. Arrival at the capture point The Euclidean distance between them, in the direction from the unmanned surface vessel. Pointing to the encirclement point The vector.

[0084] S62, Calculate Obstacles unmanned surface vessels repulsive potential field :

[0085] in, Indicates the repulsive force gain coefficient. Indicates the range of influence of the obstacle. This indicates the size of an unmanned surface vessel. Reach the obstacle location The Euclidean distance between them, in the direction from the location of the obstacle. Pointing to the surface unmanned boat The vector.

[0086] S63, Calculation of unmanned surface vessels Affected by the overall external situation : .

[0087] S64, Calculation of Unmanned Surface Vessels The combined force received : .

[0088] S65, Calculation of unmanned surface vessels course : .

[0089] in, Indicates the resultant force along Component of the axis, Indicates the resultant force along The component of the force on the axis.

[0090] S66, Control of unmanned surface vessels With speed along the course Proceed forward; if there are still unmanned surface vessels in the swarm that have not reached their corresponding capture points, return to S1, recalculate the capture points corresponding to each unmanned surface vessel according to S1 to S6, and give the navigation direction of each unmanned surface vessel until all unmanned surface vessels in the swarm have reached their corresponding capture points.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm, characterized in that, Includes the following steps: Obtain status information of the target formation and the unmanned surface vessel cluster; Establish a target formation ship domain model based on ship domain theory; A successful encirclement and capture determination function is established based on the target formation vessel domain model to determine whether the surface unmanned vessel cluster forms an effective encirclement and capture constraint on the target formation. A task allocation algorithm is used to determine the capture targets corresponding to each surface unmanned vessel. An optimization model for the capture point was established, and an optimization algorithm was used to determine the optimal capture point for each unmanned surface vessel. Based on the optimal capture point, the navigation direction of each surface unmanned vessel is determined, and each surface unmanned vessel is controlled to move along the navigation direction. If any surface unmanned vessel fails to reach the corresponding capture point, the status information is updated, the capture point is re-determined, and the navigation direction is adjusted until all surface unmanned vessels reach the corresponding capture point. A successful encirclement determination function is established based on a target formation vessel domain model. The formula is: in, Indicates the area of ​​the target fleet's vessel domain with respect to time. The derivative, This indicates an assembly of unmanned surface vessels. Indicates the first Unmanned surface vessel The decision function for whether to enter the fleet of ships. The formula is: If each vessel on the boundary of the target formation moves in a direction that would prevent the area of ​​the target formation's territory from decreasing, then all of them will have Upon entering the target fleet's territory, the function for determining successful encirclement is activated. ,otherwise .

2. The method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm according to claim 1, characterized in that, The steps to obtain the status information of the target formation and the unmanned surface vessel swarm include: In a geodetic coordinate system, the positions of each target vessel located on the boundary of the target formation are collected, forming a set of target vessel positions. The formula is: in, Indicates the target vessel Location, Indicates the number of target ships located on the boundary of the target formation; Obtain the locations of the unmanned surface vessels (USVs) participating in the encirclement and capture mission; the set of USV locations. The formula is: in, Indicates unmanned surface vessels Location, This indicates the number of unmanned surface vessels participating in the encirclement and capture operation.

3. The method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm according to claim 1, characterized in that, The steps to establish a target formation ship domain model include: Based on theories in the field of shipbuilding, in the target ship Establish a ship domain around the area to describe the safe navigation zone. The shipbuilding field The formula is: By taking the union of the ship domains of each target in the target formation, a ship domain model of the target formation is established. The formula is: in This indicates the number of target vessels located on the boundary of the target formation. Indicates the target vessel's number.

4. The method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm according to claim 1, characterized in that, A task allocation algorithm is used to assign task relationships between each surface unmanned surface vessel and each target vessel, thereby determining the capture target corresponding to each surface unmanned surface vessel. The formula is: in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel.

5. A method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm according to claim 1, characterized in that, The steps to determine the optimal capture point for each surface unmanned vessel include: An optimization model for the capture point is established with the goal of minimizing the cost of capture. The formula is: in, A set representing the locations of unmanned surface vessels. A set representing the positions of the target vessel. This indicates the generation of a set of capture points outside the target fleet's vessel territory; An optimization algorithm is used to optimize the location of the encirclement point, so that the unmanned surface vessels assigned to the same target form the optimal encirclement structure around the target. The formula is as follows: in, This represents the set of optimal capture points.

6. A method for coordinated encirclement and capture of a target-oriented unmanned surface vessel swarm according to claim 1, characterized in that, Based on the optimal encirclement point, the navigation direction of each surface unmanned vessel is determined. : in Indicates the first Unmanned surface vessel The corresponding optimal capture point.

Images