Distributed anti-unmanned aerial vehicle collaborative decision-making system and method

Abstract

The invention provides a distributed anti-unmanned aerial vehicle collaborative decision-making system and method. The distributed anti-unmanned aerial vehicle collaborative decision-making system comprises at least one heterogeneous anti-unmanned aerial vehicle module, a self-organizing network module and a distributed collaborative decision-making module, the self-organizing network module is used for constructing a decentralized network topology structure and supporting communication connection among the functional modules; the heterogeneous anti-unmanned aerial vehicle module is used for detecting, tracking and acquiring related information of an unmanned aerial vehicle target, and sharing the related information to the distributed collaborative decision-making module in real time through the self-organizing network module; the target countering module receives a target countering instruction from the distributed collaborative decision-making module and counters the unmanned aerial vehicle target; and the distributed collaborative decision module is used for receiving the real-time shared data from the self-organizing network module, analyzing the real-time shared data based on a swarm intelligence algorithm, generating a target countering instruction for each heterogeneous anti-unmanned aerial vehicle module, and sending the target countering instruction to the corresponding heterogeneous anti-unmanned aerial vehicle module. Therefore, countering resource collaboration and optimization of multiple unmanned aerial vehicle targets in a complex airspace environment are realized.

Description

Technical Field

[0001] This invention relates to the field of anti-drone technology, specifically to a distributed anti-drone collaborative decision-making system and method. Background Technology

[0002] Traditional counter-drone systems mostly employ individual soldier operations or centralized command models, which have revealed numerous shortcomings when dealing with increasingly complex drone threats, especially multi-target and swarm drone attacks. Existing counter-drone technologies mainly face the following challenges:

[0003] 1) Delayed response and low efficiency: In a centralized command model, all decisions must be processed through a central node. When facing a large number of drone targets or a rapidly changing battlefield situation, the central node can easily become a bottleneck, leading to decision delays and an inability to achieve rapid response;

[0004] 2) Uneven resource allocation and low utilization: Single or centralized systems often struggle to efficiently and dynamically coordinate and allocate heterogeneous counter-drone resources deployed in a dispersed manner. For example, when multiple drones simultaneously intrude into different areas, some areas may experience overloaded counter-measure resources while others remain idle, resulting in low overall counter-measure efficiency.

[0005] 3) Poor robustness and resilience: In a centralized system, the entire system may be paralyzed if the central node is damaged or communication is interrupted. This makes the system vulnerable to malicious attacks or harsh environments, making it difficult to operate stably and continuously.

[0006] 4) Lack of coordination and intelligent decision-making: Existing technologies mostly focus on single countermeasures, lacking intelligent coordination and optimization between different countermeasure units. For example, multiple countermeasures such as radar, electro-optical devices, jammers, and physical interception are difficult to form an organic whole, and cannot dynamically adjust the optimal combination of countermeasures based on the actual threat situation. Summary of the Invention

[0007] To address these issues, this invention provides a distributed anti-drone collaborative decision-making system and method, aiming to solve the technical problems of existing anti-drone technologies, such as slow response, uneven resource allocation, poor robustness, and lack of collaborative decision-making capabilities when dealing with complex threats.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] According to a first aspect of the present invention, the present invention provides a distributed anti-drone collaborative decision-making system, the system comprising: at least one heterogeneous anti-drone module, a self-organizing network module, and a distributed collaborative decision-making module; wherein the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module are communicatively connected to each other;

[0010] The self-organizing network module is used to construct a decentralized network topology, supporting communication connections between the heterogeneous anti-drone modules, as well as communication connections between the heterogeneous anti-drone modules and the distributed collaborative decision-making module.

[0011] The heterogeneous anti-drone module is used to detect and track drone targets, obtain relevant information about the drone targets, and share the relevant information in real time with the distributed collaborative decision-making module through the self-organizing network module; the relevant information includes the characteristic information and dynamic information of the drone targets;

[0012] The distributed collaborative decision-making module is used to receive real-time shared data from the self-organizing network module, analyze the real-time shared data based on the swarm intelligence algorithm, generate target countermeasure commands for each of the heterogeneous anti-drone modules, and send the target countermeasure commands to the corresponding heterogeneous anti-drone modules.

[0013] The heterogeneous anti-drone module is also used to receive target countermeasure instructions from the distributed collaborative decision-making module, and to counter the drone target based on the target countermeasure instructions;

[0014] The real-time shared data includes relevant information about each of the UAV targets, local situational information, and / or the self-information of each of the heterogeneous anti-UAV modules.

[0015] Furthermore, the distributed collaborative decision-making module is distributed within each of the heterogeneous anti-drone modules, and includes an information input unit, a threat assessment unit, a local decision generation unit, a collaborative decision-making unit, and a decision output unit connected in sequence;

[0016] The information input unit is used to acquire real-time shared data from the self-organizing network module;

[0017] The threat assessment unit is used to analyze the relevant information based on a preset assessment model and assess the threat assessment result of the UAV target; the threat assessment result includes threat level, threat intent and / or countermeasure priority; the threat intent includes at least one of reconnaissance, interference, attack and accidental intrusion;

[0018] The local decision generation unit is used to analyze the threat assessment results of the UAV target and the corresponding self-information of the heterogeneous anti-UAV module based on the local countermeasure model, and generate local countermeasure intentions for each of the heterogeneous anti-UAV modules.

[0019] The collaborative decision-making unit is used to broadcast the local countermeasure intentions and self-information of each of the heterogeneous anti-drone modules through the self-organizing network module, and to use a collaborative countermeasure model based on swarm intelligence algorithm to perform distributed training and optimization of the collaborative countermeasure strategy to obtain the target collaborative countermeasure strategy.

[0020] The decision output unit is used to send target countermeasure instructions to each of the heterogeneous anti-drone modules based on the target collaborative countermeasure strategy; the target countermeasure instructions carry the specified target, countermeasure method, countermeasure time and responsible module;

[0021] The swarm intelligence algorithm includes at least one of the following: improved ant colony algorithm, multi-objective particle swarm optimization, and reinforcement learning-based collaborative decision-making algorithm.

[0022] Furthermore, the collaborative decision-making unit is also used to treat each of the heterogeneous anti-drone modules as an intelligent agent, perform local decision iterative updates until the objective function is minimized, and obtain the globally optimal target collaborative countermeasure strategy;

[0023] The mathematical expression of the objective function is as follows:

[0024] J = α·T min +β·R cost +γ·S rate -δ·C collision

[0025] Where J represents the objective function; T min R represents minimizing the countermeasure time; cost S represents minimizing resource consumption; rate This indicates maximizing the reaction success rate; C collision This represents the penalty for avoiding resource conflicts or accidental damage; α, β, γ, and δ represent the weight coefficients of the corresponding items.

[0026] Furthermore, the heterogeneous anti-drone module includes a device detection unit, a feature recognition unit, a device tracking unit, and a countermeasure implementation unit connected in sequence;

[0027] The device detection unit is used to detect drone targets using detection sensors;

[0028] The feature recognition unit is used to identify the feature information of the UAV target using a feature recognition device; the feature information includes at least one of the UAV type, model, and payload.

[0029] The device tracking unit is used to continuously track the dynamic information of the UAV target using a target tracking device; the dynamic information includes at least one of the UAV trajectory, speed, and altitude;

[0030] The countermeasure implementation unit is used to counter the UAV target using multi-dimensional countermeasure equipment.

[0031] Furthermore, the heterogeneous anti-drone module also includes: a local control unit and / or a module communication unit;

[0032] The module communication unit is connected to the device detection unit, the feature recognition unit, the device tracking unit, and the countermeasure implementation unit, respectively, and is used to establish data transmission with the self-organizing network module and the distributed collaborative decision-making module;

[0033] The local control unit is connected to the module communication unit and the countermeasure implementation unit respectively, and is used to parse the target countermeasure command from the distributed collaborative decision module into a target countermeasure strategy, and control the countermeasure implementation unit to counter the UAV target according to the target countermeasure strategy; and / or, to store its own information and / or report it to the distributed collaborative decision module;

[0034] The self-information includes its own status and / or its own capabilities.

[0035] Furthermore, the self-organizing network module is used to realize communication connections between various functional modules based on direct communication mechanisms, multi-hop routing mechanisms, dynamic topology maintenance mechanisms, secure communication mechanisms, and / or information sharing mechanisms;

[0036] The direct communication mechanism includes: each of the heterogeneous anti-drone modules directly communicates point-to-point or multi-point via a wireless link;

[0037] The multi-hop routing mechanism includes: when communication between any functional modules is impossible, communication is achieved through multiple forwardings via intermediate functional modules;

[0038] The dynamic topology maintenance mechanism includes: adaptively discovering new neighbor nodes and updating the routing table to ensure continuous communication;

[0039] The secure communication mechanism includes: using an encryption algorithm to encrypt the communication between the functional modules;

[0040] The information sharing mechanism includes: each of the heterogeneous anti-drone modules shares the relevant information, its own information, and / or the local situation information in real time by setting a publish / subscribe mode or a request / response mode.

[0041] Furthermore, the system also includes a global situational awareness module that is communicatively connected to the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module, respectively.

[0042] The global situation awareness module is used to aggregate local situation information and / or its own information from the heterogeneous anti-drone module, real-time shared data from the self-organizing network module, and / or target collaborative countermeasure strategies from the distributed collaborative decision-making module to form a real-time monitoring macro battlefield situation view.

[0043] According to a second aspect of the present invention, the present invention provides a distributed anti-drone collaborative decision-making method, applied to a distributed anti-drone collaborative decision-making system as described in any one of the first aspects of the present invention, the method comprising:

[0044] Each heterogeneous anti-drone module independently senses relevant information and local situational information of drone targets in the surrounding airspace. The real-time shared data containing the relevant information, the local situational information and / or the information of the heterogeneous anti-drone module itself is encrypted by a self-organizing network module, and the real-time shared data is transmitted to the distributed collaborative decision-making module.

[0045] By utilizing the distributed collaborative decision-making modules disposed within each of the heterogeneous anti-drone modules, the real-time shared data is analyzed based on swarm intelligence algorithms to generate target countermeasure commands for each of the heterogeneous anti-drone modules, and the target countermeasure commands are fed back to the corresponding heterogeneous anti-drone modules.

[0046] Each of the heterogeneous anti-drone modules parses the target countermeasure instructions from the distributed collaborative decision-making module into a target countermeasure strategy, and implements countermeasures against the drone target based on the target countermeasure strategy.

[0047] Furthermore, the analysis of the real-time shared data based on the swarm intelligence algorithm to generate target countermeasure commands for each of the heterogeneous anti-drone modules includes:

[0048] Based on a preset assessment model, a threat assessment is performed on the UAV target according to the relevant information to obtain a threat assessment result that includes threat level, threat intent, and / or countermeasure priority; the threat intent includes at least one of reconnaissance, interference, attack, and accidental intrusion;

[0049] Based on the local countermeasure model, the threat assessment results of the UAV target and the corresponding self-information of the heterogeneous anti-UAV module are analyzed to generate local countermeasure intentions for each of the heterogeneous anti-UAV modules.

[0050] The local countermeasure intent and self-information of each heterogeneous anti-drone module are broadcast through the self-organizing network module, and the cooperative countermeasure strategy is distributedly trained and optimized using a cooperative countermeasure model based on swarm intelligence algorithm to obtain the target cooperative countermeasure strategy. Based on the target cooperative countermeasure strategy, the target countermeasure command is sent to each heterogeneous anti-drone module. The target cooperative countermeasure strategy includes a cooperative countermeasure strategy and / or resource scheduling strategy for each heterogeneous anti-drone module.

[0051] Furthermore, the method also includes:

[0052] After the heterogeneous anti-drone module counters the drone target, it feeds back the countermeasure effect data and / or its own change data as feedback information to the distributed collaborative decision-making module through the self-organizing network module.

[0053] The distributed collaborative decision-making module uses collected countermeasure effect data and / or its own change data to optimize and adjust the preset evaluation model, the local countermeasure model, and / or the collaborative countermeasure model.

[0054] The present invention, by adopting the above technical solution, has at least the following beneficial effects:

[0055] This invention proposes a distributed anti-drone collaborative decision-making system, comprising: at least one heterogeneous anti-drone module, a self-organizing network module, and a distributed collaborative decision-making module; the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module are interconnected in pairs; the self-organizing network module is used to construct a decentralized network topology, supporting communication connections between the heterogeneous anti-drone modules and between the heterogeneous anti-drone modules and the distributed collaborative decision-making module; the heterogeneous anti-drone module is used to detect and track drone targets, obtain relevant information about the drone targets, and share the relevant information in real time to the distributed collaborative decision-making module through the self-organizing network module; the distributed collaborative decision-making module is used to receive real-time shared data from the self-organizing network module, analyze the real-time shared data based on a swarm intelligence algorithm, generate target countermeasure commands for each heterogeneous anti-drone module, and send the target countermeasure commands to the corresponding heterogeneous anti-drone modules; the heterogeneous anti-drone module is also used to receive target countermeasure commands from the distributed collaborative decision-making module and implement countermeasures against the drone targets based on the target countermeasure commands. Therefore, a novel anti-drone system capable of distributed, high-efficiency, robust, and intelligent collaborative decision-making is proposed, solving the technical problem of resource coordination and optimization in the face of multiple drone targets and complex airspace environments.

[0056] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0057] 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A schematic diagram of the structure of a distributed anti-drone collaborative decision-making system provided in an embodiment of the present invention is shown;

[0059] Figure 2 A schematic diagram of the structure of a heterogeneous anti-drone module provided in an embodiment of the present invention is shown;

[0060] Figure 3 A schematic diagram illustrating the communication principle of a self-organizing network module provided in an embodiment of the present invention is shown.

[0061] Figure 4 A schematic diagram of the structure of a distributed collaborative decision-making module provided in an embodiment of the present invention is shown;

[0062] Figure 5 A schematic diagram of the structure of a distributed anti-drone collaborative decision-making system provided in another embodiment of the present invention is shown;

[0063] Figure 6 A flowchart illustrating a distributed anti-drone collaborative decision-making method according to an embodiment of the present invention is shown. Detailed Implementation

[0064] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0066] This invention provides a distributed anti-drone collaborative decision-making system, such as... Figure 1 As shown, the system may include: at least one heterogeneous anti-drone module 100, a self-organizing network module 120, and a distributed collaborative decision-making module 130; the heterogeneous anti-drone module 100, the self-organizing network module 200, and the distributed collaborative decision-making module 300 are connected in pairs.

[0067] The self-organizing network module 200 can be used to construct a decentralized network topology, supporting communication connections between the heterogeneous anti-drone modules 100 and between the heterogeneous anti-drone modules 100 and the distributed collaborative decision-making module 300. The heterogeneous anti-drone modules 100 can detect and track drone targets, obtain relevant information about the drone targets, and share this information in real time with the distributed collaborative decision-making module 300 via the self-organizing network module 200. The distributed collaborative decision-making module 300 can receive real-time shared data from the self-organizing network module 200, analyze the real-time shared data based on swarm intelligence algorithms, generate target countermeasure commands for each heterogeneous anti-drone module 100, and send the target countermeasure commands to the corresponding heterogeneous anti-drone modules 100. The heterogeneous anti-drone modules 100 can also receive target countermeasure commands from the distributed collaborative decision-making module 300 and implement countermeasures against the drone targets based on these commands.

[0068] In this embodiment of the invention, the heterogeneous anti-drone module 100 is the executor and information perceiver of the system. Each heterogeneous anti-drone module 100 has its own independent or cooperative combat capability and can be a variety of anti-drone devices with different combat interference capabilities, including but not limited to radar devices, photoelectric tracking devices, radio jamming devices, laser countermeasure devices, and interceptor drone devices.

[0069] The self-organizing network module 200 is primarily used to construct a decentralized communication network between multiple heterogeneous anti-drone modules 100, rather than a traditional star or bus structure, to achieve real-time secure information sharing and interoperability. It employs Mobile Ad Hoc Network (MANET) or Wireless Sensor Network (WSN) technology, supports multi-hop routing and dynamic topology maintenance, and can be designed with robust communication protocols and data encryption mechanisms to ensure the reliability and security of information transmission.

[0070] The distributed collaborative decision-making module 300, acting as the "brain" of the distributed anti-drone collaborative decision-making system, is responsible for using swarm intelligence algorithms to plan optimal countermeasure strategies and resource scheduling for each functional module based on collected information. It primarily receives real-time shared data from the heterogeneous anti-drone modules 100, which may include relevant information about each drone target, local situational information, and the self-information of each heterogeneous anti-drone module 100. Then, using swarm intelligence algorithms, it independently or collaboratively plans countermeasure strategies and coordinates the scheduling of countermeasure resources. The self-information may include its own status and capabilities; the self-information status may include remaining battery power, ammunition quantity, and equipment integrity; the relevant information may include the characteristics and dynamic information of the drone target.

[0071] In an alternative embodiment, such as Figure 2 As shown, the heterogeneous anti-drone module 100 may include at least a device detection unit 110, a feature recognition unit 120, a device tracking unit 130, and a countermeasure implementation unit 140 connected in sequence.

[0072] The device detection unit 110 can be used to detect UAV targets using detection sensing devices. These devices can be radar detectors, acoustic sensors, etc.

[0073] The feature recognition unit 120 can be used to identify the feature information of a drone target using a feature recognition device. The feature information includes the drone type, model, and payload, etc.; the feature recognition device can be a photoelectric recognition camera, a radio spectrum analyzer, etc.

[0074] For example, the device detection unit 110 corresponding to a heterogeneous anti-drone module 100 is a radar. It detects an unidentified flying object resembling a small drone, confirms it as a quadcopter drone by turning a high-definition camera towards the target area, captures a 2.4GHz frequency signal (to locate the remote controller's position), and uses a sound channel array to acquire propeller noise, thus obtaining the drone target's characteristic information. Furthermore, the feature recognition unit 120 uses AI to compare with a voiceprint database, confirming the drone model as a DJI Mavic 3.

[0075] The device tracking unit 130 can be used to continuously track the dynamic information of a UAV target using a target tracking device. The dynamic information may include the UAV's trajectory, speed, and altitude; the target tracking device may be an electro-optical tracking device, a high-precision radar, etc.

[0076] The countermeasure implementation unit 140 can be used to counter unmanned aerial vehicle (UAV) targets using multi-dimensional countermeasure devices. These multi-dimensional countermeasure devices can be radio jammers, navigation decoys, laser countermeasure devices, physical interceptors (such as interceptor net UAVs), etc.

[0077] Furthermore, the heterogeneous anti-drone module 100 may also include a module communication unit 150 and a local control unit 160.

[0078] The module communication unit 150 is connected to the device detection unit 110, the feature recognition unit 120, the device tracking unit 130, and the countermeasure implementation unit 140, respectively. It can be used to transmit data with other heterogeneous anti-drone modules 100, including information about the drone target, its own information, and countermeasure strategies. In addition, the module communication unit 160 can also realize data transmission with the self-organizing network module 200 and the distributed collaborative decision-making module 300.

[0079] The local control unit 160, acting as the processor within each heterogeneous anti-drone module 100, is responsible for processing local data, executing received decision commands, and reporting its own information to the distributed collaborative decision-making module 300. Specifically, the local control unit 160 is connected to both the module communication unit 150 and the countermeasure implementation unit 140, and is used to parse the target countermeasure commands from the distributed collaborative decision-making module 300 into target countermeasure strategies, controlling the countermeasure implementation unit 140 to implement countermeasures against the drone target according to the target countermeasure strategies. Additionally, the local control unit 160 can also be used to store and / or report its own information to the distributed collaborative decision-making module 300.

[0080] In an alternative embodiment, such as Figure 3As shown, the self-organizing network module 200 can be used to achieve communication connections between various functional modules based on direct communication mechanisms, multi-hop routing mechanisms, dynamic topology maintenance mechanisms, secure communication mechanisms, and information sharing mechanisms. The direct communication mechanism includes: each heterogeneous anti-drone module 100 communicates directly point-to-point or multi-point via wireless links, without needing a central server; the multi-hop routing mechanism includes: when communication between any functional modules is impossible, communication is achieved through multiple forwarding routes via intermediate functional modules to expand the communication range and enhance network connectivity and robustness; the dynamic topology maintenance mechanism includes: since the network topology changes dynamically with the movement, addition, or failure of units, the self-organizing network can adaptively discover new neighbor nodes and update the routing table to ensure communication continuity; the secure communication mechanism includes: to ensure the confidentiality and integrity of information, network communication uses encryption algorithms such as Advanced Encryption Standard (AES) to encrypt the transmission of communication between functional modules, supplemented by an authentication mechanism; the information sharing mechanism includes: each heterogeneous anti-drone module 100 shares relevant information, its own information, and local situational information in real time by setting publish / subscribe or request / response modes.

[0081] In an alternative embodiment, such as Figure 4 As shown, the distributed collaborative decision-making module 300, as the core of intelligent decision-making, is not a single central processor, but is distributed within each heterogeneous anti-drone module 100, or is undertaken by some heterogeneous anti-drone modules 100 with strong computing capabilities. It may include an information input unit 310, a threat assessment unit 320, a local decision generation unit 330, a collaborative decision-making unit 340, and a decision output unit 350 connected in sequence.

[0082] The information input unit 310 can be used to acquire real-time shared data from the self-organizing network module 200, including relevant information about drone targets acquired by each heterogeneous anti-drone module 100.

[0083] The threat assessment unit 320 can be used to analyze relevant information based on a preset assessment model and evaluate the threat assessment results of the UAV target. The threat assessment results include threat level, threat intent, and / or countermeasure priority; the threat level can include low risk, medium risk, and high risk; the threat intent can include reconnaissance, interference, attack, and accidental intrusion, etc. The preset assessment model in this embodiment of the invention can employ fuzzy logic algorithms, expert experience algorithms, or machine learning classifiers.

[0084] Based on the above example, the threat assessment unit 320, through 30 seconds of trajectory prediction and behavior recognition, determines that the threat intent is an intrusion into the no-fly zone and the threat level is assessed as high risk.

[0085] The local decision generation unit 330 can be used to analyze the threat assessment results of the UAV target and the corresponding self-information of the heterogeneous anti-UAV module 100 based on the local countermeasure model, and generate preliminary local countermeasure intentions for each heterogeneous anti-UAV module 100. The local countermeasure model can be a pre-trained model based on reinforcement learning. For example, when the heterogeneous anti-UAV module 100 is a jammer, it may generate a countermeasure intention of "jamming UAV target A", and when the heterogeneous anti-UAV module 100 is a laser device, it may generate a countermeasure intention of "hard-killing UAV target B".

[0086] The collaborative decision-making unit 340 can broadcast the local countermeasure intentions and self-information of each heterogeneous anti-drone module 100 through the self-organizing network module 200, and use a collaborative countermeasure model based on swarm intelligence algorithms to perform distributed training and optimization of the collaborative countermeasure strategy to obtain the target collaborative countermeasure strategy. It should be noted that, in planning the countermeasure strategy, the collaborative decision-making unit 340 of this embodiment comprehensively considers factors such as the threat level, threat intention, number of targets, self-capability, resource consumption, and environmental constraints of the drone target. The swarm intelligence algorithm may include improved ant colony optimization, multi-target particle swarm optimization, and reinforcement learning-based collaborative decision-making algorithms. In actual operation, each heterogeneous anti-drone module 100 is treated as an agent, performing local decision-making iterative updates until the objective function is minimized, obtaining the globally optimal target collaborative countermeasure strategy; the mathematical expression of the objective function is as follows:

[0087] J = α·T min +β·R cost +γ·S rate -δ·C collision

[0088] Where J represents the objective function; T min R represents minimizing the countermeasure time; cost S represents minimizing resource consumption; rate This indicates maximizing the reaction success rate; C collision This represents the penalty for avoiding resource conflicts or accidental damage; α, β, γ, and δ represent the weight coefficients of the corresponding items.

[0089] The decision output unit 350 can be used to send target countermeasure commands to each heterogeneous anti-drone module 100 based on a target collaborative countermeasure strategy. The target countermeasure command carries the specified target, countermeasure method, countermeasure time, and responsible module. It should be noted that these target countermeasure commands are distributed to the corresponding heterogeneous anti-drone modules 100 through the self-organizing network module 200.

[0090] Based on the above examples, a target cooperative countermeasure strategy for directional radio frequency jamming (2.4GHz band power 25W) can be generated, and then the jammer closest to the target can be selected to trigger the landing of the UAV target.

[0091] In an alternative embodiment, such as Figure 5 As shown, the distributed anti-drone collaborative decision-making system may also include a global situational awareness module 400 that is communicatively connected to the heterogeneous anti-drone module 100, the self-organizing network module 200, and the distributed collaborative decision-making module 300.

[0092] The global situation awareness module 400 can be used to aggregate local situation information and / or its own information from the heterogeneous anti-drone module 100, real-time shared data from the self-organizing network module 200, and / or target collaborative countermeasure strategies from the distributed collaborative decision-making module 300, forming a unified macro-battlefield situation view that can be monitored by the operator in real time.

[0093] This invention provides a distributed anti-drone collaborative decision-making system, comprising: at least one heterogeneous anti-drone module, a self-organizing network module, and a distributed collaborative decision-making module; the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module are interconnected in pairs; the self-organizing network module is used to construct a decentralized network topology, supporting communication connections between the heterogeneous anti-drone modules and between the heterogeneous anti-drone modules and the distributed collaborative decision-making module; the heterogeneous anti-drone module is used to detect and track drone targets, obtain relevant information about the drone targets, and share the relevant information in real time to the distributed collaborative decision-making module through the self-organizing network module; the distributed collaborative decision-making module is used to receive real-time shared data from the self-organizing network module, analyze the real-time shared data based on a swarm intelligence algorithm, generate target countermeasure commands for each heterogeneous anti-drone module, and send the target countermeasure commands to the corresponding heterogeneous anti-drone modules; the heterogeneous anti-drone module is also used to receive target countermeasure commands from the distributed collaborative decision-making module and implement countermeasures against the drone targets based on the target countermeasure commands. This invention has at least the following beneficial effects:

[0094] 1) Improved response speed and decision-making efficiency: Utilizing a distributed architecture and decentralized decision-making mechanism, each counter-drone unit can make decisions independently or collaboratively, avoiding the decision-making bottlenecks of centralized systems. When facing threats from multiple targets or swarms of drones, the system can achieve rapid response and efficient decision-making, significantly shortening the countermeasures chain.

[0095] 2) Optimize resource allocation and utilization: Swarm intelligence algorithms can assess the capabilities of each unit and the current threat situation in real time, and dynamically coordinate the allocation of countermeasure resources. Through collaborative optimization, resource overload or idleness can be avoided, maximizing the comprehensive effectiveness of heterogeneous anti-drone units and improving the overall countermeasure success rate.

[0096] 3) Enhanced system robustness and survivability: The decentralized nature of self-organizing networks means that the system does not rely on a single central node. Even if some units are damaged or offline, other units can still maintain communication and collaborative decision-making capabilities, thereby significantly improving the system's survivability and robustness and ensuring continuous combat capability in complex adversarial environments.

[0097] 4) Achieving intelligent collaboration and adaptability: Swarm intelligence algorithms endow the system with self-learning and adaptive capabilities, enabling it to learn and optimize decision-making strategies from actual countermeasures. When facing unknown or novel drone threat patterns, the system can quickly adapt and generate optimal countermeasures through inter-unit collaboration and knowledge sharing.

[0098] 5) Reduced collateral damage and friendly fire: The precise threat assessment and collaborative decision-making mechanism, combined with the precise countermeasure capabilities of each unit, can minimize friendly fire or harmless targets, reduce collateral damage, and improve the accuracy and security of countermeasures.

[0099] To enhance the understanding of those skilled in the art regarding the application of the distributed anti-drone collaborative decision-making system proposed in the embodiments of the present invention, the embodiments of the present invention also provide a distributed anti-drone collaborative decision-making method, applied to the aforementioned distributed anti-drone collaborative decision-making system, such as... Figure 6 As shown, it may include at least the following steps S601 to S603:

[0100] Step S601: Each heterogeneous anti-drone module independently senses relevant information and local situational information of drone targets in the surrounding airspace. The real-time shared data containing relevant information, local situational information and / or the self-organizing network module's own information is encrypted and transmitted to the distributed collaborative decision-making module.

[0101] In this embodiment of the invention, each heterogeneous anti-drone module (e.g., radar, electro-optical, jammer, etc.) independently and in real time senses drone target information (e.g., position P) in the surrounding airspace. i (t), velocity V i (t), type, load, etc.) and local situational information, and this perceived information is shared in real time with encryption through a self-organizing network to ensure that all functional units can obtain the latest and most comprehensive battlefield situation. Information sharing can be represented as: I shared (t)=U j∈Units {SensorDataj (t),UnitState j (t)};

[0102] Among them, I shared (t) represents the information sharing data at time t; U j∈Units This represents the integrated data of all j nodes (heterogeneous anti-drone modules); SensorData j (t) represents the sensor data of node j at time t; UnitState j (t) represents the state data of node j at time t.

[0103] Step 602: Utilize the distributed collaborative decision-making modules distributed within each heterogeneous anti-drone module to analyze real-time shared data based on swarm intelligence algorithms, generate target countermeasure commands for each heterogeneous anti-drone module, and feed back the target countermeasure commands to the corresponding heterogeneous anti-drone module.

[0104] Specifically, based on a pre-defined assessment model, a threat assessment of the UAV target can be performed according to relevant information to obtain a threat assessment result including threat level, threat intent, and / or countermeasure priority. Based on a local countermeasure model, the threat assessment result of the UAV target and the self-information of the corresponding heterogeneous anti-UAV modules are analyzed to generate local countermeasure intents for each heterogeneous anti-UAV module. The local countermeasure intents and self-information of each heterogeneous anti-UAV module are broadcast through a self-organizing network module, and a collaborative countermeasure model based on swarm intelligence algorithms is used to perform distributed training and optimization of the collaborative countermeasure strategy to obtain a target collaborative countermeasure strategy. Based on the target collaborative countermeasure strategy, target countermeasure commands are sent to each heterogeneous anti-UAV module. The target collaborative countermeasure strategy includes collaborative countermeasure strategies and / or resource scheduling strategies for each heterogeneous anti-UAV module.

[0105] In other words, each heterogeneous anti-drone module receives shared information and combines it with its own local perception data to perform preliminary situational fusion based on local data or through a distributed collaborative decision-making module set up on a few nodes with high computing power. Based on this, a threat assessment is conducted to determine the threat level T of each drone target. level (For example, a value from 1 to 10, or divided into low risk, medium risk, high risk, etc.), threat intent and countermeasure priority P priority During the evaluation process, target type, flight behavior, and distance (d) can be considered. i Speed ​​v i Factors such as payload. For example, the threat level function can be defined as: T level =f(type,d i ,v i(payload, behavior).

[0106] Furthermore, utilizing swarm intelligence algorithms, local countermeasure strategies are independently generated based on threat assessment results, self-information, and shared information from other functional modules. Information exchange is facilitated through self-organizing network modules to achieve iterative optimization. The ultimate goal is to find a globally optimal cooperative countermeasure strategy II and resource scheduling strategy R, whose mathematical expressions can be:

[0107] II * ,R * =argmin II,R ∑ i∈Targets Cost (Strategy) i Resources i Effect i );

[0108] Where, ∑ i∈Targets Cost(·) represents the sum of costs over all targets (i∈Targets); Strategy i Resources i Effect i These represent the strategy, resources, and impact parameters, respectively.

[0109] It is understandable that in a distributed computing environment, the overall state can be reached through multiple rounds of information interaction and local strategy adjustments. In practical applications, the optimal state can be determined by minimizing the objective function.

[0110] Step 603: Each heterogeneous anti-drone module parses the target countermeasure instructions from the distributed collaborative decision-making module into target countermeasure strategies, and implements countermeasures against the drone target based on the target countermeasure strategies.

[0111] Each heterogeneous anti-drone module executes corresponding countermeasures based on the coordinated countermeasure instructions issued by the distributed collaborative decision-making module.

[0112] In one optional embodiment, after the heterogeneous anti-drone module counters the drone target, it feeds back the countermeasure effect data and its own change data as feedback information to the distributed collaborative decision-making module through the self-organizing network module. The distributed collaborative decision-making module uses the collected countermeasure effect data and its own change data to optimize and adjust the preset evaluation model, the local countermeasure model and / or the collaborative countermeasure model.

[0113] In other words, after the countermeasures are completed, the countermeasures effect data (such as whether the target was destroyed / driven away, whether the countermeasures were successful) and the self-change data (such as resource consumption, whether the equipment was damaged) of each heterogeneous anti-drone module can be used as feedback information and shared again through the self-organizing network, which can be used to evaluate the effectiveness of the countermeasures.

[0114] Based on the above example, radar and electro-optical devices can be used to confirm the landing of a drone target, and the countermeasure data can be transmitted back to the AI ​​hub of the distributed collaborative decision-making module to learn and update the characteristics of the drone type, and to synchronously upgrade the model across the entire network. It can be understood that the collected countermeasure effect data and status feedback information can be used for adaptive learning. By analyzing this data, the parameters of the threat assessment model, the swarm intelligence algorithm, and the countermeasure strategy library can be continuously adjusted and optimized. This allows the distributed collaborative decision-making module to learn from practical experience, improving the accuracy and efficiency of decision-making when facing similar or new threats in the future, and achieving continuous evolution of the system. In practical applications, training can be conducted through reinforcement learning reward and punishment mechanisms or optimized decision-making strategies; this invention does not limit this to any particular approach.

[0115] This invention provides a distributed anti-drone collaborative decision-making method, comprising: utilizing each heterogeneous anti-drone module to independently perceive relevant information and local situational information of drone targets in the surrounding airspace; encrypting real-time shared data containing relevant information, local situational information, and / or the self-organizing network module's own information through a self-organizing network module, and transmitting the real-time shared data to a distributed collaborative decision-making module; utilizing the distributed collaborative decision-making module, which is distributed within each heterogeneous anti-drone module, analyzing the real-time shared data based on a swarm intelligence algorithm, generating target countermeasure commands for each heterogeneous anti-drone module, and feeding back the target countermeasure commands to the corresponding heterogeneous anti-drone module; each heterogeneous anti-drone module parsing the target countermeasure commands from the distributed collaborative decision-making module into a target countermeasure strategy, and implementing countermeasures against the drone target based on the target countermeasure strategy. This invention significantly improves the overall performance, response speed, robustness, and survivability of anti-drone systems by constructing a decentralized self-organizing network, integrating heterogeneous anti-drone modules, and introducing swarm intelligence algorithms for distributed collaborative decision-making. It overcomes many limitations of traditional anti-drone systems in dealing with multi-target, complex environments, and swarm drone threats, and achieves effective and precise collaborative countermeasures against complex drone threats, demonstrating significant practical value and technical advantages.

[0116] It should be noted that other corresponding descriptions of the functional modules involved in the distributed anti-drone collaborative decision-making method provided in this embodiment of the invention can be found in [reference]. Figures 1-5 The corresponding description of the system shown will not be repeated here.

[0117] Those skilled in the art will clearly understand that the specific working process of the systems, devices, modules and units described above can be referred to the corresponding process in the foregoing method embodiments. For the sake of brevity, it will not be repeated here.

[0118] Furthermore, the functional units in the various embodiments of the present invention can be physically independent of each other, or two or more functional units can be integrated together, or all functional units can be integrated into one processing unit. The integrated functional units described above can be implemented in hardware, or in software or firmware.

[0119] Those skilled in the art will understand that if the integrated functional unit is implemented in software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or all or part of it, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computing device (e.g., a personal computer, server, or network device) to execute all or part of the steps of the methods described in the embodiments of the present invention when running the instructions. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] Alternatively, all or part of the steps of the foregoing method embodiments can be implemented by hardware (such as a computing device, personal computer, server, or network device) related to program instructions. The program instructions can be stored in a computer-readable storage medium. When the program instructions are executed by the processor of the computing device, the computing device executes all or part of the steps of the methods described in the various embodiments of the present invention.

[0121] 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 within the spirit and principles of the present invention, 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 therein; and these modifications or substitutions do not cause the corresponding technical solutions to depart from the protection scope of the present invention.

Claims

1. A distributed anti-drone collaborative decision-making system, characterized in that, The system includes: at least one heterogeneous anti-drone module, a self-organizing network module, and a distributed collaborative decision-making module; the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module are communicatively connected to each other; The self-organizing network module is used to construct a decentralized network topology, supporting communication connections between the heterogeneous anti-drone modules, as well as communication connections between the heterogeneous anti-drone modules and the distributed collaborative decision-making module. The heterogeneous anti-drone module is used to detect and track drone targets, obtain relevant information about the drone targets, and share the relevant information in real time with the distributed collaborative decision-making module through the self-organizing network module; the relevant information includes the characteristic information and dynamic information of the drone targets; The distributed collaborative decision-making module is used to receive real-time shared data from the self-organizing network module, analyze the real-time shared data based on the swarm intelligence algorithm, generate target countermeasure commands for each of the heterogeneous anti-drone modules, and send the target countermeasure commands to the corresponding heterogeneous anti-drone modules. The heterogeneous anti-drone module is also used to receive target countermeasure instructions from the distributed collaborative decision-making module, and to counter the drone target based on the target countermeasure instructions; The real-time shared data includes relevant information about each of the UAV targets, local situational information, and / or the self-information of each of the heterogeneous anti-UAV modules.

2. The system according to claim 1, characterized in that, The distributed collaborative decision-making module is distributed within each of the heterogeneous anti-drone modules, and includes an information input unit, a threat assessment unit, a local decision generation unit, a collaborative decision-making unit, and a decision output unit connected in sequence. The information input unit is used to acquire real-time shared data from the self-organizing network module; The threat assessment unit is used to analyze the relevant information based on a preset assessment model and assess the threat assessment result of the UAV target; the threat assessment result includes threat level, threat intent and / or countermeasure priority; the threat intent includes at least one of reconnaissance, interference, attack and accidental intrusion; The local decision generation unit is used to analyze the threat assessment results of the UAV target and the corresponding self-information of the heterogeneous anti-UAV module based on the local countermeasure model, and generate local countermeasure intentions for each of the heterogeneous anti-UAV modules. The collaborative decision-making unit is used to broadcast the local countermeasure intentions and self-information of each of the heterogeneous anti-drone modules through the self-organizing network module, and to use a collaborative countermeasure model based on swarm intelligence algorithm to perform distributed training and optimization of the collaborative countermeasure strategy to obtain the target collaborative countermeasure strategy. The decision output unit is used to send target countermeasure instructions to each of the heterogeneous anti-drone modules based on the target collaborative countermeasure strategy; the target countermeasure instructions carry the specified target, countermeasure method, countermeasure time and responsible module; The swarm intelligence algorithm includes at least one of the following: improved ant colony algorithm, multi-objective particle swarm optimization, and reinforcement learning-based collaborative decision-making algorithm.

3. The system according to claim 2, characterized in that, The collaborative decision-making unit is also used to treat each of the heterogeneous anti-drone modules as an intelligent agent, perform local decision iterative updates until the objective function is minimized, and obtain the globally optimal target collaborative countermeasure strategy. The mathematical expression of the objective function is as follows: J=α·T min +β·R cost +γ·S rate -δ·C collision Where J represents the objective function; T min R represents minimizing the countermeasure time; cost S represents minimizing resource consumption; rate This indicates maximizing the reaction success rate; C collision This represents the penalty for avoiding resource conflicts or accidental damage; α, β, γ, and δ represent the weight coefficients of the corresponding items.

4. The system according to claim 1, characterized in that, The heterogeneous anti-drone module includes a device detection unit, a feature recognition unit, a device tracking unit, and a countermeasure implementation unit connected in sequence. The device detection unit is used to detect drone targets using detection sensors; The feature recognition unit is used to identify the feature information of the UAV target using a feature recognition device; The characteristic information includes at least one of the following: drone type, model, and payload; The device tracking unit is used to continuously track the dynamic information of the UAV target using a target tracking device; the dynamic information includes at least one of the UAV trajectory, speed, and altitude; The countermeasure implementation unit is used to counter the UAV target using multi-dimensional countermeasure equipment.

5. The system according to claim 4, characterized in that, The heterogeneous anti-drone module also includes: a local control unit and / or a module communication unit; The module communication unit is connected to the device detection unit, the feature recognition unit, the device tracking unit, and the countermeasure implementation unit, respectively, and is used to establish data transmission with the self-organizing network module and the distributed collaborative decision-making module; The local control unit is connected to the module communication unit and the countermeasure implementation unit respectively, and is used to parse the target countermeasure command from the distributed collaborative decision module into a target countermeasure strategy, and control the countermeasure implementation unit to counter the UAV target according to the target countermeasure strategy; and / or, to store its own information and / or report it to the distributed collaborative decision module; The self-information includes its own status and / or its own capabilities.

6. The system according to claim 1, characterized in that, The self-organizing network module is used to realize communication connections between various functional modules based on direct communication mechanism, multi-hop routing mechanism, dynamic topology maintenance mechanism, secure communication mechanism and / or information sharing mechanism. The direct communication mechanism includes: each of the heterogeneous anti-drone modules directly communicates point-to-point or multi-point via a wireless link; The multi-hop routing mechanism includes: when communication between any functional modules is impossible, communication is achieved through multiple forwardings via intermediate functional modules; The dynamic topology maintenance mechanism includes: adaptively discovering new neighbor nodes and updating the routing table to ensure continuous communication; The secure communication mechanism includes: using an encryption algorithm to encrypt the communication between the functional modules; The information sharing mechanism includes: each of the heterogeneous anti-drone modules shares the relevant information, its own information, and / or the local situation information in real time by setting a publish / subscribe mode or a request / response mode.

7. The system according to any one of claims 1 to 6, characterized in that, The system further includes a global situational awareness module that is communicatively connected to the heterogeneous anti-drone module, the self-organizing network module, and the distributed collaborative decision-making module, respectively. The global situation awareness module is used to aggregate local situation information and / or its own information from the heterogeneous anti-drone module, real-time shared data from the self-organizing network module, and / or target collaborative countermeasure strategies from the distributed collaborative decision-making module to form a real-time monitoring macro battlefield situation view.

8. A distributed anti-drone collaborative decision-making method, characterized in that, The method, applied to the distributed anti-drone collaborative decision-making system according to any one of claims 1 to 7, comprises: Each heterogeneous anti-drone module independently senses relevant information and local situational information of drone targets in the surrounding airspace. The real-time shared data containing the relevant information, the local situational information and / or the information of the heterogeneous anti-drone module itself is encrypted by a self-organizing network module, and the real-time shared data is transmitted to the distributed collaborative decision-making module. By utilizing the distributed collaborative decision-making modules disposed within each of the heterogeneous anti-drone modules, the real-time shared data is analyzed based on swarm intelligence algorithms to generate target countermeasure commands for each of the heterogeneous anti-drone modules, and the target countermeasure commands are fed back to the corresponding heterogeneous anti-drone modules. Each of the heterogeneous anti-drone modules parses the target countermeasure instructions from the distributed collaborative decision-making module into a target countermeasure strategy, and implements countermeasures against the drone target based on the target countermeasure strategy.

9. The method according to claim 8, characterized in that, The analysis of the real-time shared data based on a swarm intelligence algorithm to generate target countermeasure commands for each of the heterogeneous anti-drone modules includes: Based on a preset assessment model, a threat assessment is performed on the UAV target according to the relevant information to obtain a threat assessment result that includes threat level, threat intent, and / or countermeasure priority; the threat intent includes at least one of reconnaissance, interference, attack, and accidental intrusion; Based on the local countermeasure model, the threat assessment results of the UAV target and the corresponding self-information of the heterogeneous anti-UAV module are analyzed to generate local countermeasure intentions for each of the heterogeneous anti-UAV modules. The local countermeasure intent and self-information of each of the heterogeneous anti-drone modules are broadcast through the self-organizing network module, and the cooperative countermeasure strategy is distributedly trained and optimized using a cooperative countermeasure model based on swarm intelligence algorithm to obtain the target cooperative countermeasure strategy. Based on the target collaborative countermeasure strategy, target countermeasure commands are sent to each of the heterogeneous anti-drone modules; the target collaborative countermeasure strategy includes a collaborative countermeasure strategy and / or a resource scheduling strategy for each of the heterogeneous anti-drone modules.

10. The method according to claim 9, characterized in that, The method further includes: After the heterogeneous anti-drone module counters the drone target, it feeds back the countermeasure effect data and / or its own change data as feedback information to the distributed collaborative decision-making module through the self-organizing network module. The distributed collaborative decision-making module uses collected countermeasure effect data and / or its own change data to optimize and adjust the preset evaluation model, the local countermeasure model, and / or the collaborative countermeasure model.

Images