Methods for Cooperative Search and Encirclement of Unmanned Aerial Vehicle Swarms in Denied Environments

Abstract

This invention discloses a method for collaborative search and capture of unmanned aerial vehicle (UAV) swarms in a denied environment, belonging to the field of UAV swarm technology. The method includes the following steps: The method comprises two phases: a search phase and a capture phase. In the search phase, the UAV swarm, based on jointly solved stimulus values, covers the target area as efficiently as possible, exploring both dynamic and static targets. In the capture phase, the alpha UAV leads the arrived UAVs to attack the target until it is eliminated, completing the mission. This invention introduces a UAV collaborative localization method based on positional confidence, which is more realistic, allows for more accurate target localization, and facilitates decision-making applicable to real-world scenarios.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) swarm technology, and more specifically, relates to a method for collaborative search and capture of UAV swarms in a denied environment. Background Technology

[0002] In modern warfare, operational modes targeting satellite navigation system jamming have become a key development focus for militaries worldwide. For example, the core operation of the US Air-Sea Battle is blinding operations against various military networks, creating a denial environment through electronic warfare and cyberattacks. Such threats pose a significant threat to weapon systems' command systems, payload systems, and communication networks. Therefore, how to achieve target search and capture in a denial environment has become an important research topic in academia.

[0003] In recent years, unmanned aerial vehicles (UAVs) have been widely used in both military and civilian fields due to their low cost, low attrition, zero casualties, and high mobility, stealth, and flexibility. However, the capabilities of a single UAV are limited, and functionality and applicability are often mutually restrictive. A single-function UAV may be powerful in one aspect, but it can only perform tasks related to its own function. In modern warfare, acquiring information from different sources and effectively processing multi-source information are key to gaining the initiative on the battlefield. Therefore, multi-UAV collaborative operations are an inevitable trend in the development of UAV technology.

[0004] Currently, intelligent algorithms are widely used in multi-UAV cooperative operations. The wolf pack algorithm, as a swarm intelligence algorithm, possesses good robustness and global convergence, effectively preventing convergence to local areas. Existing research focuses on applying the wolf pack algorithm to path optimization and search-and-hunt problems, aiming to optimize search accuracy and efficiency. Wolf packs and UAV swarms share similarities. First, in terms of environmental awareness, wolf packs rely on teamwork and mutual assistance to search large hunting environments and grasp the typical characteristics of the hunting environment and targets. UAV swarms, on the other hand, rely on multi-UAV information exchange and fusion to identify and track dynamic targets. Second, regarding cooperation mechanisms, the stability and decision-making consistency of a wolf pack system depend on its strict hierarchical structure. Due to the clear interaction relationships among members, it can quickly make correct decisions. UAVs, by establishing communication links between themselves and their allies, achieve a consensus protocol among swarm members and, combined with accurate situational awareness, make maneuver strategies favorable to the evolving situation. Given this, wolf pack algorithms have broad application prospects in collaborative search and capture with drone swarms, but research on wolf pack algorithms in collaborative search and capture with drone swarms under denied environments is still very scarce. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method for cooperative search and capture of unmanned aerial vehicle (UAV) swarms in denied environments. On one hand, in denied environments with stationary obstacles, the multi-dynamic target search strategy of the UAV swarm is optimized to improve search efficiency and coverage. On the other hand, when GPS navigation fails in denied environments, an improved wolfpack algorithm is introduced to achieve cooperative target localization and capture.

[0006] To address at least one of the aforementioned technical problems, according to one aspect of the present invention, a method for cooperative search and capture of unmanned aerial vehicle (UAV) swarms in a denied environment is provided, comprising the following steps:

[0007] The mission comprises two phases: a search phase and an encirclement phase. In the search phase, the drone swarm, based on jointly solved stimulus values, covers the target area as efficiently as possible, exploring both dynamic and static targets. In the encirclement phase, the alpha drone leads the arriving drones to attack the target until it is eliminated, completing the mission. Specifically, it includes the following steps:

[0008] Specifically, the steps include the following:

[0009] S1. Perform gridded discrete modeling of the search environment. Initially, all drones are scouts. In each time slot, the scouts search in a discrete grid. At the same time, set search stimulus values ​​so that the more drones have searched the grid and the shorter the time since the last exploration, the lower the stimulus value, so as to achieve full coverage of the search range as much as possible. Mark obstacles to prompt the drone swarm to avoid obstacles.

[0010] S2. After locating the target, the drone determines the ammunition resources required and acts as the alpha wolf to summon other drones for an attack. Until enough drones arrive, the alpha wolf must maintain tracking of the target. Since GPS navigation fails in a denied environment, a drone swarm cooperative positioning method based on location confidence is needed to better locate the target. The drone sends the target's current location to the swarm system at fixed intervals.

[0011] S3: The alpha wolf will organize the arriving wolves to attack until the target is eliminated. After the target disappears, the alpha wolf will transform into a scout wolf to continue the search mission.

[0012] S4. After the attack is completed, the drone swarm continues to search within the search area until there are no more targets within the area, at which point the search process ends.

[0013] The search area in S1 is modeled using a gridded discrete model. Each target exists within a discrete grid, and each grid contains at most one target. Targets can move between grids. Each obstacle also exists within a grid, and each grid contains at most one obstacle. Obstacles cannot move. Furthermore, after gridded modeling, the UAV moves from one grid center to the center of an adjacent grid each time. Therefore, the UAV's flight direction is discretely divided into eight directions: East, South, West, North, Southeast, Northeast, Southwest, and Northwest. However, the UAV can only choose to continue flying forward, to its left, or to its right. The movement of enemy targets also follows this principle.

[0014] In S2, after the target of the attack is found to be the alpha wolf, the following situations may occur:

[0015] If the alpha wolf is an offensive drone and carries sufficient attack ammunition, it will not summon other drones but will directly attack the target until the target is destroyed.

[0016] If the alpha wolf is an offensive drone and its munitions are insufficient, the alpha wolf will initiate a summoning action and assign tasks based on an improved wolf pack algorithm.

[0017] When the alpha wolf is tasked with scouting drones, it directly initiates a summoning action and assigns tasks based on an improved wolf pack algorithm.

[0018] The specific steps for task allocation based on the improved wolf pack algorithm are as follows:

[0019] The guiding factor value for whether a drone needs to advance toward a target is calculated based on the combined results of individual-individual interactions and individual-environment interactions.

[0020] If the drone needs to rush towards the target based on the guidance factor value, then the mission status is set to 1 and the role is changed to a wolf; otherwise, the status is set to 0 and the rush is not carried out.

[0021] The specific steps of the UAV cooperative positioning method based on location confidence are as follows:

[0022] Relative positioning is calculated using real-time measured sensor data, and the drone's own positioning information is exchanged during the relative positioning process.

[0023] The drones perform collaborative positioning based on the location reliability.

[0024] The attitude output of the UAV is corrected by fusing extended Kalman filters (EKF).

[0025] According to another aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for cooperative search and capture of unmanned aerial vehicle swarms in a denied environment according to the present invention.

[0026] According to another aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for cooperative search and capture of unmanned aerial vehicle swarms under denied conditions of the present invention.

[0027] Compared with the prior art, the present invention has at least the following beneficial effects:

[0028] This invention employs an improved wolf pack algorithm to search for and surround targets in a denied environment. Considering the failure of GPS navigation in a denied environment, a UAV cooperative positioning method based on positional confidence is introduced, which is more realistic, can more accurately locate targets, and is more conducive to making decisions applicable to real-world scenarios.

[0029] Compared to other inventions, this invention applies the wolf pack algorithm to search for dynamic and static targets in a denied environment. Based on the characteristics of the denied environment, the wolf pack algorithm is improved by adding obstacle avoidance operations and achieving joint optimization of stimulus values. This achieves the effect of making full use of the drone swarm resources, carrying out more effective and stable encirclement and capture, and greatly improving the robustness and environmental adaptability of the system. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments will be briefly described below. Obviously, the drawings described below only relate to some embodiments of the present invention and are not intended to limit the present invention.

[0031] Figure 1 A flowchart of the method for collaborative search and capture of unmanned aerial vehicle swarms under denied conditions of the present invention is shown;

[0032] Figure 2 Flowchart for invention;

[0033] Figure 3 This is a flight path diagram for the drone. Within the search range, the drone can choose to travel in three directions: forward, left front, and right front each time. Detailed Implementation

[0034] 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, not all, of the embodiments of the present invention.

[0035] Unless otherwise defined, the technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0036] like Figure 1-3 As shown,

[0037] Example 1:

[0038] This embodiment provides a method for cooperative search and capture of drone swarms in a denied environment, comprising two phases: a search phase and a capture phase. In the search phase, the drone swarm, based on jointly solved stimulus values, covers the target area as efficiently as possible, exploring both dynamic and static targets. In the capture phase, the alpha drone leads the arrived drones to attack the target until it is destroyed, completing the mission. Specifically, it includes the following steps:

[0039] S1. Perform gridded discrete modeling of the search environment. Initially, all drones are scouts. In each time slot, the scouts search in a discrete grid. At the same time, set search stimulus values ​​so that the more drones have searched the grid and the shorter the time since the last exploration, the lower the stimulus value, so as to achieve full coverage of the search range as much as possible. Mark obstacles to prompt the drone swarm to avoid obstacles.

[0040] S2. After locating the target, the drone determines the ammunition resources required and acts as the alpha wolf to summon other drones for an attack. Until enough drones arrive, the alpha wolf must maintain tracking of the target. Since GPS navigation fails in a denied environment, a drone swarm cooperative positioning method based on location confidence is needed to better locate the target. The drone sends the target's current location to the swarm system at fixed intervals.

[0041] S3: The alpha wolf will organize the arriving wolves to attack until the target is eliminated. After the target disappears, the alpha wolf will transform into a scout wolf to continue the search mission.

[0042] S4. After the attack is completed, the drone swarm continues to search within the search area until there are no more targets within the area, at which point the search process ends.

[0043] The search area in S1 is modeled using a gridded discrete model. Each target exists within a discrete grid, and each grid contains at most one target. Targets can move between grids. Each obstacle also exists within a grid, and each grid contains at most one obstacle. Obstacles cannot move. Furthermore, after gridded modeling, the UAV moves from one grid center to the center of an adjacent grid each time. Therefore, the UAV's flight direction is discretely divided into eight directions: East, South, West, North, Southeast, Northeast, Southwest, and Northwest. However, the UAV can only choose to continue flying forward, to its left, or to its right. The movement of enemy targets also follows this principle.

[0044] In S2, after the target of the attack is found to be the alpha wolf, the following situations may occur:

[0045] If the alpha wolf is an offensive drone and carries sufficient attack ammunition, it will not summon other drones but will directly attack the target until the target is destroyed.

[0046] If the alpha wolf is an offensive drone and its munitions are insufficient, the alpha wolf will initiate a summoning action and assign tasks based on an improved wolf pack algorithm.

[0047] When the alpha wolf is tasked with scouting drones, it directly initiates a summoning action and assigns tasks based on an improved wolf pack algorithm.

[0048] The specific steps for task allocation based on the improved wolf pack algorithm are as follows:

[0049] The guiding factor value for whether a drone needs to advance toward a target is calculated based on the combined results of individual-individual interactions and individual-environment interactions.

[0050] If the drone needs to rush towards the target based on the guidance factor value, then the mission status is set to 1 and the role is changed to a wolf; otherwise, the status is set to 0 and the rush is not carried out.

[0051] The specific steps of the UAV cooperative positioning method based on location confidence are as follows:

[0052] Relative positioning is calculated using real-time measured sensor data, and the drone's own positioning information is exchanged during the relative positioning process.

[0053] The drones perform collaborative positioning based on the location reliability.

[0054] The attitude output of the UAV is corrected by fusing extended Kalman filters (EKF).

[0055] Example 2:

[0056] The computer-readable storage medium of this embodiment stores a computer program that, when executed by a processor, implements the steps of the method for cooperative search and capture of unmanned aerial vehicle swarms in a denied environment as described in Embodiment 1.

[0057] The computer-readable storage medium in this embodiment can be an internal storage unit of the terminal, such as the terminal's hard disk or memory; the computer-readable storage medium in this embodiment can also be an external storage device of the terminal, such as a plug-in hard disk, smart memory card, secure digital card, flash memory card, etc. equipped on the terminal; furthermore, the computer-readable storage medium can include both the terminal's internal storage unit and external storage devices.

[0058] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0059] Example 3:

[0060] The computer device of this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the method for collaborative search and capture of unmanned aerial vehicle swarms under denial conditions in Embodiment 1.

[0061] In this embodiment, the processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The memory can include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory can also include non-volatile random access memory. For example, the memory can also store device type information.

[0062] Those skilled in the art will understand that the content disclosed in the embodiments can be provided as a method, system, or computer program product. Therefore, this solution can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this solution can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage) containing computer-usable program code.

[0063] This solution is described with reference to flowchart illustrations and / or block diagrams of methods and computer program products according to embodiments of this solution. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0067] The examples described herein are merely preferred embodiments of the invention and are not intended to limit the concept and scope of the invention. Any modifications and improvements made by those skilled in the art to the technical solutions of the invention without departing from the design concept of the invention should fall within the protection scope of the invention.

Claims

1. A method for collaborative search and capture of unmanned aerial vehicle (UAV) swarms in a denied environment, characterized in that, The method comprises two phases: a search phase and a capture phase. During the search phase, the drone swarm covers the target area as efficiently as possible, exploring both dynamic and static targets, based on the jointly solved stimulus values. During the encirclement phase, the alpha wolf leads the arrived drones to attack the target until the target is eliminated, thus completing the mission. S1. Perform gridded discrete modeling of the search environment; initially, all drones are scouts. In each time slot, the scouts search in a discrete grid. At the same time, set search stimulus values ​​so that the more drones have searched the grid and the shorter the time since the last exploration, the lower the stimulus value, so as to achieve full coverage of the search range as much as possible. Mark obstacles to prompt the drone swarm to avoid obstacles. S2. After the target is located, the drone determines the ammunition resources required by the target and acts as the alpha wolf to summon the wolves to attack it. Before enough wolves arrive, the alpha wolf needs to keep tracking the target. Since GPS navigation fails in the denied environment, in order to better locate the target, a drone swarm cooperative positioning method based on position confidence needs to be introduced to locate the target. The target's current position is sent to the swarm system at fixed intervals. S3: The alpha wolf will organize the arriving wolves to attack until the target is eliminated. After the target disappears, the alpha wolf will transform into a scout wolf to continue the search mission. S4. After the attack is completed, the drone swarm continues to search within the search area until there are no more targets within the area, at which point the search process ends.

2. The method according to claim 1, characterized in that, The search area in S1 is modeled using a gridded discrete model. Each target exists in a discrete grid, and there can be at most one attack target in each grid. Targets can move between grids. Each obstacle also exists in a grid, and there can be at most one obstacle in each grid. Obstacles cannot move. After gridded modeling, the UAV moves from one grid center to the center of an adjacent grid each time. Therefore, the UAV's flight direction is discrete into 8 flight directions: east, south, west, north, southeast, northeast, southwest, and northwest. However, the UAV can only choose to continue flying forward, to the left front, and to the right front. The movement of enemy targets also follows this principle.

3. The method according to claim 2, characterized in that, In S2, after the target is detected to be the alpha wolf, the following situation may occur: If the alpha wolf is an offensive drone and carries sufficient attack ammunition resources, the alpha wolf will not summon any drones and will directly attack the target until the target is destroyed. If the alpha wolf is an offensive drone and its attack ammunition resources are insufficient, the alpha wolf will summon other drones and assign tasks based on the improved wolf pack algorithm. When the alpha wolf is tasked with scouting drones, it directly initiates a summoning action and assigns tasks based on an improved wolf pack algorithm.

4. The method according to claim 3, characterized in that, The specific steps for task allocation based on the improved wolf pack algorithm are as follows: The guiding factor value for whether a drone needs to advance toward the target is calculated based on the combined results of individual-individual interactions and individual-environment interactions. If the drone needs to rush towards the target based on the guidance factor value, then the mission status is set to 1 and the role is changed to a wolf; otherwise, the status is set to 0 and the rush is not carried out.

5. The method according to claim 4, characterized in that, The specific steps of the UAV cooperative positioning method based on location confidence are as follows: Relative positioning is calculated using real-time measured sensor data, and the drone's own positioning information is exchanged during the relative positioning process. Unmanned aerial vehicles (UAVs) perform collaborative positioning based on location reliability. The attitude output of the UAV is corrected by fusing extended Kalman filters.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by the processor, the program implements the steps in the method for cooperative search and capture of unmanned aerial vehicle swarms in a denied environment as described in any one of claims 1 to 5.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for collaborative search and capture of unmanned aerial vehicle swarms in a denied environment as described in any one of claims 1 to 5.

Images