Laser anti-unmanned aerial vehicle non-global strike priority division method and device

Through the laser anti-UAV non-wide strike priority classification method and device, the neural network model is used to calculate the strike priority and window parameters during drone swarm attack, and the difficulty in generating artificial strike solutions during drone swarm attack is solved. The problem of this problem improves the speed and effectiveness of the low-altitude defense system.

CN118981933AActive Publication Date: 2024-11-19SHANDONG JIGANG AEROSPACE IND DEV CO LTD

Patent Information

Application Number
CN202410355670.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-03-27
Publication Date
2024-11-19
Estimated Expiration
2044-03-27

AI Technical Summary

Technical Problem

In the case of drone swarm attacks, the workload of artificial real-time generation of strike plans is huge, and it cannot be dealt with in a timely, accurate, fast and effective manner. The risk of failure of defense tasks due to the prohibition of regional restrictions on secondary disasters is high.

Method used

Using laser anti-UAV non-wide strike priority classification method and device, the strike range grid is divided through radar detection information and neural network model, and the strike range grid is calculated, each grid's strikeability, strike priority and strike window parameters are realized. Fast and effective crackdown decisions.

Benefits of technology

It greatly improves the speed and effectiveness of combat, provides quantitative judgment basis for low-altitude defense systems, and is suitable for fixed deployment of low-altitude defense systems, reducing manual intervention and improving the accuracy and efficiency of strikes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118981933A_ABST
    Figure CN118981933A_ABST
Patent Text Reader

Abstract

The invention provides a laser anti-unmanned aerial vehicle non-global strike priority division method and device, and belongs to the technical field of anti-unmanned aerial vehicles. The method comprises the following steps: acquiring a strike range of an anti-unmanned aerial vehicle system, dividing the strike range into grids according to a distance precision requirement, taking a center point of the strike range as an original point, and determining a distance between a center point of each grid and the original point and an azimuth angle of the center point of each grid; obtaining a strike index of each grid; establishing and training a laser anti-unmanned aerial vehicle non-global strike priority division network model; acquiring position information of the unmanned aerial vehicle in real time through an anti-unmanned aerial vehicle system, inputting the position information into the trained network model, and obtaining a strike index of the unmanned aerial vehicle; and judging the strike sequence of the unmanned aerial vehicle according to the strike strategy. Whether the laser anti-unmanned aerial vehicle system can strike or not and how high the strike priority are calculated by utilizing the neural network model, and a quantitative judgment basis is provided for combat disposal and decision making of the laser anti-unmanned aerial vehicle system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a laser anti-UAV non-global strike priority division method and device, belonging to the technical field of anti-UAV. Background Art

[0002] The rapid development of drone technology has led to increasingly widespread commercial applications, and drones are increasingly used for reconnaissance and strikes in modern warfare.

[0003] Drone swarm strikes use the numerical advantage of multiple drones to attack key targets simultaneously from multiple directions. For combat commanders, the terrain influence of the defense area, the restrictions of prohibiting secondary disasters, and the complex situation of simultaneous attacks by drones from multiple directions all have an adverse impact on rapid decision-making and rapid strikes in low-altitude defense. In response to drone swarm attacks, commanders need to always grasp the positions and orientations of multiple drones, determine the strike plans of multiple drones, and avoid prohibited areas that are within the strike range but cannot be struck due to prohibition of secondary disasters (such as protected ancient buildings and sites, flammable and explosive places, densely populated areas, forest farms where fireworks are strictly prohibited, etc.). When multiple or a large number of drones approach from multiple directions at the same time, the workload of manually generating strike plans in real time is huge, and it is impossible to deal with them in a timely, accurate, fast, and effective manner. As long as one drone successfully penetrates the defense, it may cause the defense mission to fail.

[0004] Laser anti-UAV is an effective means of dealing with low-altitude threats. It has incomparable combat advantages over other means, such as instantaneous destruction, high tracking accuracy, and continuous light strikes. It provides an effective means to deal with drone swarm attacks and creates favorable conditions for continuous and rapid strikes in complex situations. Summary of the invention

[0005] The purpose of the present invention is to provide a laser anti-UAV non-global strike priority division method and device, so as to form a rapid strike plan to deal with the multi-directional attack of UAV swarms under the condition of strike constraints, and provide a fast and effective strike decision-making plan.

[0006] In order to achieve the above object, the present invention is implemented through the following technical solutions: Collect the strike range of the anti-UAV system and divide the strike range into grids according to the distance accuracy requirements. Take the center point of the strike range as the origin, determine the distance between each grid center point and the origin, and the azimuth of each grid center point; Obtain the strike index of each grid, including strikeability, strike priority and strike window parameter; strikeability indicates whether the target can be struck, strike priority indicates the order of striking the target if it can be struck, and strike window parameter indicates that under the same strike priority, further select the incoming target with a smaller strike window; Establish and train a laser anti-UAV non-global strike priority classification network model; The UAV location information is collected in real time through the anti-UAV system, and the distance between the center point and the origin of the grid where the UAV target is located, the azimuth of the grid where the UAV target is located, the fourth-level defense level, and the prohibition level of the grid where the third-level UAV target is located are input into the trained laser anti-UAV non-global strike priority division network model to obtain the strikeability, strike priority, and strike window parameters of the UAV; Determine the order of drone strikes based on the strike strategy.

[0007] Preferably, the laser anti-UAV non-global strike priority division network model includes an input layer, an output layer and a hidden layer; the input layer is an association relationship input, that is, the input layer contains 9 elements, including the distance between the center point of the grid where the UAV target is located and the origin, the azimuth of the grid where the UAV target is located, the four-level defense level and the prohibition level of the grid where the three-level UAV target is located; the output layer contains 3 elements, including the strikeability of the grid where the UAV target is located, the strike priority of the grid where the UAV target is located and the strike window parameter of the grid where the UAV target is located; the number of layers of the hidden layer and the number of neurons in each layer are hyperparameters, which are 3 layers or more. Preferably, the laser anti-UAV non-global strike priority division network model adopts a BP neural network.

[0008] Preferably, the input layer of the laser anti-UAV non-global strike priority division network model is a non-associative relationship input, and the input layer contains 4 elements, including the distance between the center point of the grid where the UAV target is located and the origin, the azimuth of the grid where the UAV target is located, the current defense level, and the prohibition level of the grid where the current UAV target is located.

[0009] Preferably, the defense level classification value intervals in the model training stage are as follows: general defense level (0.0, 0.05], intermediate defense level [0.4, 0.5], advanced defense level [0.7, 0.8], and highest defense level [0.9, 1.0); During the model training phase, the prohibited level is divided into the following value ranges: general prohibited strikes (0.0, 0.1], intermediate prohibited strikes, [0.4, 0.6], and advanced prohibited strikes [0.9, 1.0].

[0010] Preferably, the principles for selecting the value of the attackability in the model training phase are as follows: The range of the striking value in the non-prohibited striking zone is [0.95, 1.0); the range of the striking value in the prohibited striking zone is (0.0, 0.5); The principles for selecting strike window parameters during the model training phase are as follows: The value range of the first-level attack window is [0.9, 1.0); the value range of the second-level attack window is [0.5, 0.6]; the value range of the third-level attack window is [0.1, 0.2]; The strike priority p is calculated as follows: p=1-d / R, where d represents the distance between the center point of the grid where the drone target is located and the origin, and R represents the effective radius of the laser strike.

[0011] Preferably, the attack strategy is as follows: Determine the attackability. If it is greater than or equal to 0.5, it is considered to be attackable and enters the attackability sorting queue, which is sorted from high to low according to the attackability. If the attackability is less than 0.5, it is considered to be unattackable. Determine the strike priority of drones in the strike queue, and give priority to drones with higher strike priority; If drone targets with the same priority appear, continue to judge the strike window parameters and strike the drone targets in the order of the first-level strike window, the second-level strike window, and the third-level strike window.

[0012] Preferably, the strike priority allows an error range of 0-0.1.

[0013] The advantages of the present invention are as follows: Based on radar detection information, the present invention uses a neural network model to design a swarm attack determination method for a laser anti-UAV system under non-global conditions. Based on objective factors such as target distance and orientation obtained by radar detection, as well as subjective factors such as defense level requirements and prohibited attack level demarcation, a neural network model is used to calculate whether it can be attacked and how high its attack priority is, providing a quantitative judgment basis for the combat disposal and decision-making of the laser anti-UAV system, which is suitable for fixed low-altitude defense systems. The rapidity and effectiveness of operations are greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0015] Figure 1 It is a schematic diagram of the process of the present invention.

[0016] Figure 2 This is a schematic diagram of an example of the strike area within the defense zone of the present invention. A i Indicates a prohibited strike zone. B i Indicates the permitted strike zone. U i Represents a drone target.

[0017] Figure 3It is a schematic diagram of the effectiveness of different prohibited areas under different defense levels of the present invention.

[0018] Figure 4 Schematic diagram of the neural network model structure. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1 like Figure 1 As shown, a laser anti-UAV non-global strike priority division method is implemented by the following technical solutions: S1: Collect the strike range of the anti-UAV system and divide the strike range into grids according to the distance accuracy requirements. Take the center point of the strike range as the origin, determine the distance between each grid center point and the origin and the azimuth of each grid center point; the grid size can be set according to the distance accuracy requirements in actual application. For example, if the laser strike radius is 1000m, the grid can be divided into small grids of 5m×5m, 10m×10m or 20m×20m. The center point of each grid represents the distance from the grid to the origin and the azimuth with the positive direction of the X-axis as 0 and counterclockwise as positive. Figure 1 A point P in the universe is d away from the origin and has an azimuth angle of θ, denoted as [d, θ].

[0021] S2: Obtain the strike index of each grid, including strikeability, strike priority and strike window parameters; strikeability indicates whether the target can be struck, strike priority indicates the order of attack of the target if it can be struck, and strike window parameters indicate that under the same strike priority, the incoming target with a smaller strike window is further selected.

[0022] S3: Establish and train a laser anti-UAV non-global strike priority division network model. The laser anti-UAV non-global strike priority division network model includes an input layer, an output layer and a hidden layer.

[0023] like Figure 4As shown in the figure, the input layer is an associative input, that is, the input layer contains 9 elements, including the distance between the center point and the origin of the grid where the drone target is located, the azimuth of the grid where the drone target is located, the four-level defense level, and the prohibition level of the grid where the drone target is located; the output layer contains 3 elements, including the strikeability of the grid where the drone target is located, the strike priority of the grid where the drone target is located, and the strike window parameter of the grid where the drone target is located; the number of layers of the hidden layer and the number of neurons in each layer are hyperparameters, which are 3 layers or more. The input layer inputs each defense level and the prohibition level at the same time, which can increase the characteristics of more levels of the system, strengthen the network's learning of the multi-level characteristics of the system, and improve the output neuron's ability to recognize complex situations.

[0024] Optionally, the input layer of the laser anti-UAV non-global strike priority division network model is a non-associative input, and the input layer contains 4 elements, including the distance between the center point of the grid where the UAV target is located and the origin, the azimuth of the grid where the UAV target is located, the current defense level, and the prohibition level of the grid where the current UAV target is located. A maximum of 4×3=12 models of defense level and prohibition level are generated, corresponding to 12 application scenarios. This situation is equivalent to splitting the model into 12 independent models. The input layer only learns specific defense level and prohibition level features, and the model structure is simple and the amount of calculation is small.

[0025] Optionally, the laser anti-UAV non-global strike priority division network model adopts a BP neural network.

[0026] Optionally, the defense level classification value ranges in the model training stage are as follows: general defense level (0.0, 0.05], intermediate defense level [0.4, 0.5], advanced defense level [0.7, 0.8], and highest defense level [0.9, 1.0].

[0027] During the model training phase, the prohibited level is divided into the following value ranges: general prohibited strikes (0.0, 0.1], intermediate prohibited strikes, [0.4, 0.6], and advanced prohibited strikes [0.9, 1.0].

[0028] The principles for selecting the value of attackability during the model training phase are as follows: The strike value range in the non-strike-forbidden zone is [0.95, 1.0), for example, the value may be 0.98.

[0029] The striking value range in the prohibited striking zone is (0.0, 0.5), for example, the value may be 0.1.

[0030] The principles for selecting strike window parameters during the model training phase are as follows: The value range of the first-level strike window is [0.9, 1.0); the value range of the second-level strike window is [0.5, 0.6]; the value range of the third-level strike window is [0.1, 0.2].

[0031] The strike priority p is calculated as follows: p=1-d / R, where d represents the distance between the center point of the grid where the drone target is located and the origin, and R represents the effective radius of the laser strike.

[0032] S4: The UAV location information is collected in real time through the anti-UAV system, and the distance between the center point and the origin of the grid where the UAV target is located, the azimuth of the grid where the UAV target is located, the fourth-level defense level, and the prohibition level of the third-level UAV target grid are input into the trained laser anti-UAV non-global strike priority division network model to obtain the strikeability, strike priority and strike window parameters of the UAV.

[0033] S5: Determine the strike order of the drones according to the strike strategy. The strike strategy is as follows: Determine the hitability. If it is greater than or equal to 0.5, it is considered hitable and enters the hitability sorting queue, which is sorted from high to low according to the hitability. If it is less than 0.5, it is considered unhackable. o The first step of filtering is performed on the targets to reduce the number of targets and reduce interference.

[0034] Determine the strike priority of drones in the strike queue, and give priority to drones with high strike priority; generally, the strike priority represents the distance of the target from the defense center. The closer the target is to the defense center, the greater the threat to the defense center, and the higher the priority should be to solve the greatest threat. Priority is a key indicator to pay attention to, and the decision on whether to strike or not is based on the strike priority.

[0035] If there are drone targets with the same priority, the strike window parameters will continue to be determined, and the drone targets will be struck in the order of the first strike window, the second strike window, and the third strike window. For targets with similar distances, the strike priorities are not much different, so they can be sorted and struck according to the strike priority. In actual scenarios, the strike windows of incoming drones at the same distance vary depending on the strikeable areas. At this time, in the strikeable target queue, the larger the strike window parameter, the shorter the strike window of the target, and the higher it should be sorted and struck first; the smaller the strike window parameter, the larger the strike window, the longer the time allowed for the strike, and the lower the sorting.

[0036] Optionally, the allowable error range of the strike priority is 0-0.1. If the strike priority is between 0-0.1, it is considered to be the same. At this time, the strike window parameter judgment is started, and the strike window parameter with a larger value is sorted first, and the strike window parameter with a smaller value is sorted last.

[0037] The present invention is applicable under the following premises: The radar can obtain the distance and direction information of UAV targets within the 360° range of the defense area (excluding radar detection blind spots or targets that are not detected due to obstruction).

[0038] Within the laser strike radius, the laser is reachable as long as the strike is allowed.

[0039] To comply with the expression convention, the coordinate system uses the radar deployment point as the coordinate origin, the target azimuth is uniformly based on the X-axis as the starting point, counterclockwise rotation is positive, and the value range is [0, 2π]. In general, the target detection azimuth output by the radar system is not defined in this way, but it can be converted to the target azimuth in this coordinate system through a simple conversion, and the coordinate conversion does not affect the essence of the problem.

[0040] Non-relationship The non-association relationship is relatively simple. The importance of the defense level and the prohibited strike area is defined by the user. That is, at different defense levels, whether a certain area is allowed to be struck is determined by the user based on specific circumstances. For example, at the highest defense level, a certain area can still be designated as prohibited from being struck, indicating that the area is not allowed to shoot down incoming drones under any circumstances to ensure that secondary disasters do not occur.

[0041] Relationship The association relationship refers to the certain association between the prohibited strike area and the defense level. The specific meaning is: At the general defense level, all designated no-strike zones are in effect, and strikes are not allowed in these zones, such as Figure 2 or Figure 3 a).

[0042] At the intermediate defense level, the general prohibited strike zone is invalid, and strikes can be carried out within this area, such as Figure 3 b).

[0043] At the advanced defense level, the prohibited strike areas below the intermediate level (including the intermediate level) are invalid, and strikes can be carried out within this area, such as Figure 3 c).

[0044] At the highest defense level, all prohibited strike areas are invalid, and all incoming targets within the strike range can be struck, such as Figure 3 d).

[0045] Figure 3 Four examples of incoming drones are drawn in the figure, indicating different disposal states of incoming drones, among which: It refers to a drone that has not yet entered the strike range but can be detected by radar.

[0046] It is a drone that has entered the strike range and can strike normally, but its strike timing will be temporarily interrupted or restored.

[0047] A drone that has entered the strike range and can strike normally.

[0048] To enter the strike range of drones, but the strike is prohibited for various reasons.

[0049] , , , , They represent several types of restricted areas where strikes cannot be implemented or are prohibited, including: forest farms with high fire prevention levels, important ancient buildings that need to be protected, important military and political sites, residential areas, important livelihood infrastructure, etc. Most of these areas are irregular in shape and cannot be described by an exact function. Some areas are completely inaccessible, while others are interspersed with one or more small areas that can be struck.

[0050] , , They represent the strikeable areas nested in the strike-forbidden areas. The shapes of these areas are mostly irregular and cannot be described by an exact function. At the same time, more complex situations also include areas where strike-forbidden areas are nested in these areas, such as .

[0051] Example 2 The embodiment of the present disclosure provides a laser anti-UAV non-global strike priority division device, including a processor and a memory. Optionally, the device may also include a communication interface and a bus. Among them, the processor, the communication interface, and the memory can communicate with each other through the bus. The communication interface can be used for information transmission. The processor can call the logic instructions in the memory to execute the laser anti-UAV non-global strike priority division method of the above embodiment.

[0052] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0053] The memory, as a computer-readable storage medium, can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor executes the function application and data processing by running the program instructions / modules stored in the memory, that is, the laser anti-UAV non-global strike priority division method in the above embodiment is implemented.

[0054] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory.

[0055] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned laser anti-UAV non-global strike priority division method.

[0056] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0057] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0058] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A laser anti-UAV non-global strike priority division method, characterized in that: include: Collect the strike range of the anti-UAV system and divide the strike range into grids according to the distance accuracy requirements. Take the center point of the strike range as the origin, determine the distance between each grid center point and the origin, and the azimuth of each grid center point; Obtain the strike index of each grid, including strikeability, strike priority and strike window parameter; strikeability indicates whether the target can be struck, strike priority indicates the order of striking the target if it can be struck, and strike window parameter indicates that under the same strike priority, further select the incoming target with a smaller strike window; Establish and train a laser anti-UAV non-global strike priority classification network model; The UAV location information is collected in real time through the anti-UAV system, and the distance between the center point and the origin of the grid where the UAV target is located, the azimuth of the grid where the UAV target is located, the fourth-level defense level, and the prohibition level of the grid where the third-level UAV target is located are input into the trained laser anti-UAV non-global strike priority division network model to obtain the strikeability, strike priority, and strike window parameters of the UAV; Determine the order of drone strikes based on the strike strategy.

2. The laser anti-UAV non-global strike priority division method according to claim 1 is characterized in that: The laser anti-UAV non-global strike priority division network model includes an input layer, an output layer and a hidden layer; the input layer is an association relationship input, that is, the input layer contains 9 elements, including the distance between the center point of the grid where the UAV target is located and the origin, the azimuth of the grid where the UAV target is located, the four-level defense level and the prohibition level of the grid where the three-level UAV target is located; the output layer contains 3 elements, including the strikeability of the grid where the UAV target is located, the strike priority of the grid where the UAV target is located and the strike window parameter of the grid where the UAV target is located; the number of layers of the hidden layer and the number of neurons in each layer are hyperparameters, which are 3 layers or more.

3. The laser anti-UAV non-global strike priority division method according to claim 1 is characterized in that: The laser anti-UAV non-global strike priority division network model adopts BP neural network.

4. The laser anti-UAV non-global strike priority division method according to claim 2 is characterized in that: The input layer of the laser anti-UAV non-global strike priority division network model is a non-associative relationship input, and the input layer contains 4 elements, including the distance between the center point of the grid where the UAV target is located and the origin, the azimuth of the grid where the UAV target is located, the current defense level, and the prohibition level of the grid where the current UAV target is located.

5. The laser anti-UAV non-global strike priority division method according to any one of claims 1 to 4 is characterized in that: The defense level classification value ranges described in the model training stage are as follows: general defense level (0.0, 0.05], intermediate defense level [0.4, 0.5], advanced defense level [0.7, 0.8], and highest defense level [0.9, 1.0); During the model training phase, the prohibited level is divided into the following value ranges: general prohibited strikes (0.0, 0.1], intermediate prohibited strikes, [0.4, 0.6], and advanced prohibited strikes [0.9, 1.0].

6. The laser anti-UAV non-global strike priority division method according to claim 5 is characterized in that: The principles for selecting the value of attackability during the model training phase are as follows: The range of the striking value in the non-prohibited striking zone is [0.95, 1.0); the range of the striking value in the prohibited striking zone is (0.0, 0.5); The principles for selecting strike window parameters during the model training phase are as follows: The value range of the first-level attack window is [0.9, 1.0); the value range of the second-level attack window is [0.5, 0.6]; the value range of the third-level attack window is [0.1, 0.2]; The strike priority p is calculated as follows: p=1-d / R, where d represents the distance between the center point of the grid where the drone target is located and the origin, and R represents the effective radius of the laser strike.

7. The laser anti-UAV non-global strike priority division method according to claim 6 is characterized in that: The combat strategy is as follows: Determine the attackability. If it is greater than or equal to 0.5, it is considered to be attackable and enters the attackability sorting queue, which is sorted from high to low according to the attackability. If the attackability is less than 0.5, it is considered to be unattackable. Determine the strike priority of drones in the strike queue, and give priority to drones with higher strike priority; If drone targets with the same priority appear, continue to judge the strike window parameters and strike the drone targets in the order of the first-level strike window, the second-level strike window, and the third-level strike window.

8. The laser anti-UAV non-global strike priority division method according to claim 6 is characterized in that: The allowable error range of the strike priority is 0-0.

1.

9. A laser anti-UAV non-global strike priority division device, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the laser anti-UAV non-global strike priority division method as described in any one of claims 1 to 8 when running the program instructions.

10. A storage medium storing program instructions, characterized in that: When the program instructions are run, they execute the laser anti-UAV non-global strike priority division method as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Anti-unmanned aerial vehicle control method and system

    CN106708094A

  • Anti-unmanned aerial vehicle task allocation method based on reinforcement learning

    CN112507622A

  • Unmanned aerial vehicle tracking and striking method, server and device

    CN112817329A

  • KR20230095274A

Cited By

  • Laser safety control method for laser anti-unmanned aerial vehicle system

    CN120580377A

  • A laser safety control method for a laser anti-UAV system

    CN120580377B