KR20230157192A - Method, apparatus and system for intellignece shield using uav swarm - Google Patents

Abstract

An intelligent defense method, device, and system using swarm unmanned aerial vehicles are disclosed. A method of protecting an object using a swarm unmanned aerial vehicle using an electronic device according to an embodiment of the present invention includes receiving information obtained about a target; Recognizing the target from target information received through a predefined algorithm and estimating relative motion information for the recognized target; Generating corresponding defense control information of a swarm unmanned aerial vehicle for defending the object based on relative motion information estimated with respect to the recognition target; and transmitting the generated swarm unmanned aerial vehicle response defense control information.

Description

Intelligent defense method, device and system using swarm unmanned aerial vehicle {METHOD, APPARATUS AND SYSTEM FOR INTELLIGNECE SHIELD USING UAV SWARM}

The present invention relates to defense technology using unmanned aerial vehicles, and more specifically, to intelligent defense methods, devices, and systems for objects from targets using swarm unmanned aerial vehicles.

The way war is fought and the aspects of battle continue to change. In particular, various attack methods using small drones have been developed recently, and since the production cost of drones is relatively low, they are also used by terrorist groups and for military purposes.

On the other hand, it is not easy to defend against attacks using such small drones with existing weapon systems, and even if possible, the cost-effectiveness is low due to the relatively expensive weapon system.

Accordingly, in order to solve the above situation, a method using a communication jammer is being studied as a drone defense system. However, although this method can generally defend against commercial drones that use standard communication methods, it has the problem of not being able to defend against attack drones that have modified software or were developed in-house to not use standard communication methods.

Accordingly, there is a demand for the development of a physical defense system that can protect warships or major military facilities using small drones that are economical and easy to move and maintain.

(0001) Korean Patent Publication No. 10-1895343 (Registration date: 2018.08.30) (0002) Korean Patent Publication No. 10-2281804 (Registration date: 2021.07.20)

One object of the present invention is to provide an intelligent defense method, device, and system for an object from a target using a swarm of unmanned aerial vehicles.

Another object of the present invention is to provide a method of automatically performing an operation to defend an object from a target using artificial intelligence technology.

The technical problems to be achieved in the present invention are not limited to the above technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

A method of defending an object using a swarm unmanned aerial vehicle using an electronic device according to an embodiment of the present invention to solve the above-described problem includes receiving information obtained about a target; Recognizing the target from target information received through a predefined algorithm and estimating relative motion information for the recognized target; Generating corresponding defense control information of a swarm unmanned aerial vehicle for defending the object based on relative motion information estimated with respect to the recognition target; and transmitting the generated swarm unmanned aerial vehicle response defense control information.

According to an embodiment of the present invention, the swarm unmanned aerial vehicle response defense control information may include first control information regarding the alignment and flight of each or group of the swarm unmanned aerial vehicle.

According to an embodiment of the present invention, the swarm unmanned aerial vehicle response defense control information may include second control information regarding response to the target.

According to an embodiment of the present invention, the second control information includes high-speed movement and collision control information based on relative motion information estimated for the target, and the swarm unmanned aerial vehicle when the distance to the target is within a predetermined range. Self-destruction and carbonation control information of the aircraft may be included.

According to an embodiment of the present invention, the target may include at least one unmanned aerial vehicle.

According to an embodiment of the present invention, the information acquired about the received target may include image data acquired by a sensor module mounted on an individual unmanned aerial vehicle forming a swarm.

According to an embodiment of the present invention, the sensor module may include at least one of an image sensor including a camera, a lidar sensor, and a radar sensor.

According to an embodiment of the present invention, the predefined algorithm may include a CNN of a deep learning technique.

An apparatus for defending an object using a swarm unmanned aerial vehicle according to an embodiment of the present invention includes: a memory; and a processor, wherein the processor receives information obtained about a target, recognizes the target from the target information received through a predefined algorithm, estimates relative motion information for the recognized target, and recognizes the target. Based on the relative motion information estimated for the target, response defense control information of the swarm unmanned aerial vehicle for defending the object is generated and transmitted.

A system for defending an object using a swarm unmanned aerial vehicle according to an embodiment of the present invention includes drones that include a sensor module that acquires information about the target and form a swarm; and a control system including a memory and a processor, wherein the processor receives information obtained about the target, recognizes the target from the target information received through a predefined algorithm, and responds to the recognized target. Motion information is estimated, and response defense control information of the swarm unmanned aerial vehicle for defending the object is generated and transmitted based on the relative motion information estimated for the recognition target.

According to various embodiments of the present invention, the following effects can be provided.

According to the present invention, it is possible to provide an intelligent defense method, device, and system using swarm unmanned aerial vehicles.

According to the present invention, it is possible to safely defend an object by automatically controlling unmanned swarm drones using artificial intelligence technology.

However, the effects that can be achieved through the present invention are not limited to this.

Figure 1 is a diagram illustrating an intelligent defense system using swarm drones according to an embodiment of the present invention.
Figure 2 is a block diagram of an individual swarm drone according to an embodiment of the present invention.
Figure 3 is a block diagram of a control system according to an embodiment of the present invention.
Figure 4 is a flow chart illustrating an intelligent defense method according to an embodiment of the present invention.
Figure 5 is a diagram illustrating the operation of an individual drone according to an embodiment of the present invention.
Figure 6 is a diagram illustrating an operation to defend an object from a target using a swarm of drones according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. While describing each drawing, similar reference numerals are used for similar components.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be named a second component, and similarly, the second component may also be named a first component without departing from the scope of the present invention. The term and/or includes any of a plurality of related stated items or a combination of a plurality of related stated items.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "include" or "have" should be understood as not precluding the existence or addition possibility of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. .

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains.

Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Hereinafter, various embodiments of a method for protecting an object from a target using an unmanned aerial vehicle according to the present invention are disclosed.

At this time, the term “unmanned aerial vehicle” refers to an aircraft that is not directly boarded and controlled by a person, and includes, for example, a drone. At this time, such unmanned aerial vehicles do not necessarily have to be remotely controlled by humans, but may also include flying vehicles that move on their own according to software such as various control programs. Meanwhile, in the present invention, for convenience of explanation, the unmanned air vehicle will be described by taking drones, particularly drones under swarm control (hereinafter referred to as 'swarm drones'), as an example. However, the present invention is not necessarily limited to this.

The term “object” refers to an object that is the object of defense against intrusion or attack from the outside, and such objects may include facilities, vehicles, ships, etc.

Additionally, the term “target” may refer to any type of object that enters or approaches the object or a preset area from the outside for the purpose of intruding or attacking the object. These targets may include unmanned aerial vehicles, missiles, etc., but for convenience of explanation, the unmanned aerial vehicle, that is, a drone, is used as an example for explanation. However, the present invention is not limited to this. Meanwhile, the target does not necessarily have to be one.

In addition, the term "defense" means protecting the object from any external intrusion, attack, etc., and such defense includes not only shooting down or destroying the target, but also performing the target's intended role, such as impeding access or leaving a predetermined area. It can refer to any action or action that is impossible or difficult.

Meanwhile, it should be noted in advance that unmanned aerial vehicles such as drones can use conventionally known devices or technologies, and a separate detailed explanation thereof will be omitted.

Figure 1 is a diagram illustrating an intelligent defense system (hereinafter referred to as 'intelligent defense system') using swarm drones 110 according to an embodiment of the present invention.

The intelligent defense system may be comprised of a swarm drone 110 and a control system 120.

Depending on the embodiment, the intelligent defense system may further include one or more components in addition to the configuration shown in FIG. 1. For example, the intelligent defense system may further include at least one of a communication network, a repeater, a satellite, etc. that supports or performs various data communications such as data and control commands between the components shown in FIG. 1.

The swarm drone 110 may collect or acquire (hereinafter referred to as 'acquisition') image data about a target approaching from the outside to an object or a preset area around the object (hereinafter, 'object' for convenience).

Individual drones or at least some of them belonging to the swarm drone 110 may be equipped with a computing device such as a computer for processing the acquired image data.

Depending on the embodiment, the swarm drone 110 may directly transmit the acquired raw image data to the control system 120 without directly processing it.

In the above, the processed image data or raw image data may or may not be transmitted directly to the control system 120 from the individual drones forming the swarm. In the latter case, each drone in the swarm transmits image data to the command drone or leader drone of the group to which the drone belongs, and the command drone can integrate it and transmit it to the control system 120. . At this time, the command drone may integrate or primary process the image data according to time synchronization such as a time stamp, assign an identifier, and transmit it to the control system 120. In a similar manner, the command drone refers to the identifier assigned to each individual drone to identify the source or origin of the image data contained in the body of the image frame. ) may include information about the drone's identifier and location information and then transmit it to the control system 120.

In addition, individual drones belonging to the swarm drone 110 or at least some of them may be further equipped with hardware devices such as a communication unit and memory for data transmission and reception with the control system 120 or a pre-designated command drone.

Depending on the embodiment, individual drones or at least some of them belonging to the swarm drone 110 may be further equipped with hardware devices necessary for a physical defense method according to the corresponding defense control information according to the present invention. In the above, the physical defense method refers to a physical response to a target, such as a radar self-destruction attack aircraft such as the Harpy, a direct impact attack, a low-speed cruise missile, etc., for the defense of an object.

The swarm drone 110 includes n (where n is a natural number) drones or n * m (where n and m are natural numbers) drones. Generally, n and/or m are at least 2, but the swarm It can be appropriately determined considering operating costs while ensuring the minimum effectiveness of object defense through . From this point of view, it is preferable that n or m is at least 4 considering all directions, but may be 1 at a specific point in time.

Meanwhile, the number of swarm drones 110 subject to control may vary depending on the time or method of operation. For example, the number of drones operated in peacetime mode, such as before target recognition, and the number of drones operated in defense mode based on target recognition and estimation results may be different.

As described above, the swarm drone 110 may be controlled by grouping at least two or more drones according to various criteria, or may be controlled by dividing them into at least one command drone and a plurality of operation drones. In the latter case, the at least one command drone directly performs data communication with the control system 120 and may also control individual drones belonging to it.

The control system 120 may receive image data about the target from the swarm drone 110, recognize the target by analyzing the received image data, and estimate relative motion information of the recognized target. In the above analysis process, the control system 120 may use artificial intelligence technology, especially deep learning technology. Depending on the embodiment, image data about the target may be collected through a sensor device other than the swarm drone 110. The other sensor devices may include, for example, a Lidar sensor, a radar sensor, etc.

The control system 120 may generate response defense control information of the swarm drones 110 for object defense based on the relative motion information estimated for the recognized target and transmit the generated response defense control information.

The transmission method may include a broadcast method, a method of transmitting only to at least one command drone in the swarm, and a method of transmitting directly to individual drones in the swarm.

The control system 120 does not necessarily need to be one, and may exist in plural. In the latter case, each control system may all have the same configuration. Depending on the embodiment, each control system may have a different configuration depending on the mission or role assigned to each unit.

Meanwhile, the control system 120 may usually be located on the ground, but is not necessarily limited thereto. That is, the control system 120 may be located underground or in the air, and its location may vary depending on the defense object (not shown). For example, if the object of defense is a trap, the control system 120 may be located on the ship.

The control system 120 may be located within or around the defense object, or may be located remotely. Additionally, the control system 120 may be operated unmanned.

Figure 2 is a block diagram of individual drones forming a swarm according to an embodiment of the present invention.

Referring to FIG. 2, individual drones forming a swarm according to an embodiment of the present invention can be broadly divided into a processor and a memory 250, and the processor includes a communication unit 210, a sensor unit 220, and a calculation unit 230. ) and a control unit 240.

At this time, as described above, when the function of the calculation unit 230, which will be described later depending on the embodiment, is performed in the control system 120, it may be omitted.

Additionally, the composition of each drone forming a swarm may not all be the same. For example, the configuration of the command drone and the drone being commanded may be different.

The communication unit 210 supports data communication through communication with the control system 120 and other drones forming a swarm, and can exchange various data.

The sensor unit 220 may acquire image data about a potential target approaching an object. At this time, the sensor unit 220 may be configured to include at least one of an image sensor such as a camera sensor, a lidar sensor, and a radar sensor.

Meanwhile, according to the present invention, the configuration of the sensor unit 220 included in individual drones forming a swarm may be different from each other. For example, the sensor unit of the first drone may include an image sensor, the sensor unit of the n-1th drone may include a lidar sensor, and the sensor unit of the nth drone may include a radar sensor. In the above, n is a natural number.

In other words, one drone may include all sensors to form a sensor unit, or it may include only some of them or only one sensor. For this reason, the subject that processes the sensed data, that is, the drone or control system 120, may be determined depending on the configuration of the sensor unit.

Image data described herein may include moving image data as well as still image data.

If meaningful data is sensed from the image data sensed by the sensor unit 220 of a predetermined number (e.g., at least one drone) of drones forming a group, the so sensed image data Based on the processed results, sensing of the sensor unit 220 of another drone may be controlled.

Conversely, if no meaningful data is sensed from the image data sensed through the sensor unit of a predetermined number of drones among the drones forming a cluster at a specific time, the data sensed from each drone is ignored. Therefore, post-processing may not be possible. The post-processing may represent processing in each drone or control system 120.

Meanwhile, the sensor unit 220 may include one or more other sensors in addition to the sensor for acquiring image data for the target. For example, the additional sensor may include a thermal image sensor, an infrared sensor, etc.

The calculation unit 230 is responsible for processing the acquired image data and may include a computer, etc.

At this time, the calculation process may include a calculation operation for recognizing (or identifying) the target from the acquired image data. Meanwhile, in relation to the target recognition, artificial intelligence object recognition technology may be used. That is, the calculation unit 230 includes a module equipped with a machine learning or deep learning artificial intelligence object recognition algorithm and can recognize the target from the acquired image data. In the present invention, for convenience, a deep learning algorithm is used, and among them, a convolution neural network (CNN) is used as an example, but is not limited thereto.

For example, the calculation unit 230 may use the SSD (Single-shot Multibox Detection) of a convolution neural network as a deep learning method, classify the acquired image by region, and use the SSD technique for each region. By classifying using , you can quickly detect the region of interest (ROI) where the target exists.

Depending on the embodiment, the calculation unit 230 may use the semantic segmentation method of a convolution neural network as a deep learning method, and determine the image data obtained through this on a pixel basis and use it as a target. You can decide whether it is something that can be judged or not. Since the semantic segmentation is determined on a pixel basis, the detection speed may be low, but the accuracy is relatively high compared to SSD, which is a region-specific detection method. Therefore, the calculation unit 230 can use semantic segmentation on the detected regions of interest to detect only the regions of interest for the potential target portion on a per-pixel basis.

Depending on the embodiment, the calculation unit 230 may recognize the target by analyzing the detected regions of interest in detail. The calculation unit 230 can also recognize the target using a multi-label classification method of a convolutional neural network (CNN) as a deep learning method.

The calculation unit 230 may perform an operation to obtain relative motion estimation information of a target recognized from acquired image data.

At this time, the calculation unit 230 may read and use an algorithm for estimating the relative motion of an object previously stored in the memory 250 to estimate the relative motion of the recognition target. At least one relative motion estimation algorithm may be stored in the memory 250. The calculation unit 230 can calculate relative motion estimation for the target by selecting and using an appropriate relative motion estimation algorithm based on the previously recognized target type, target speed, etc. For example, if the target is recognized as a low-speed aircraft such as a drone, the relative motion estimation algorithm of the low-speed target can be used. Meanwhile, in the present invention, algorithms for estimating relative motion of objects that are known or developed in the future can be referred to or used, and a detailed description thereof will be omitted.

At least part of the operation of the calculation unit 230 may be performed by the control unit 240, which will be described later.

The control unit 240 may be responsible for or involved in overall control of the drone.

Depending on the embodiment, the control unit 240 controls the received image data and the recognition result thereof to be stored in the memory 250, so that the memory 250 can form big data, and each component 220 to 230 ) can improve deep learning learning and inference performance.

The control unit 240 can control the swarm drones 110 to hover for a predetermined period of time in the formation of the swarm drones 110, if necessary during a counter-defense operation process to be described later.

The memory 250 may permanently or temporarily store various data, and such data may include image data for determining target identification of a potential target, data sensed through the sensor unit 220, etc.

Figure 3 is a block diagram of the control system 120 according to an embodiment of the present invention.

Referring to FIG. 3, the control system 120 according to an embodiment of the present invention can be largely divided into a processor and a memory 350, and the processor includes a communication unit 310, a data pre-processing unit 320, and a processing unit 330. ) and a control unit 340.

The communication unit 310 receives a control input from a control device (not shown) that wishes to control the unmanned flying device 120 and transmits it to the flight control unit 320. Additionally, the communication unit 310 transmits the image of the wind power generator captured by the image capture unit 340 to the defect analysis device 110.

The data preprocessing unit 320 may preprocess data to be processed by the processing unit 330, that is, image data received from the swarm drone 110.

The processing unit 330 may process pre-processed image data. At this time, the processing unit 330 can perform all of the operations of the calculation unit 230 of FIG. 2 described above.

Depending on the embodiment, both the calculation unit 230 of FIG. 2 and the processing unit 330 of FIG. 3 may be present to cross-verify the results.

Depending on the embodiment, the calculation unit 230 of FIG. 2 may only perform operations for target recognition, and the processing unit 330 of FIG. 3 may estimate relative motion for the recognized target.

The processing unit 330 generates corresponding defense control information of the swarm drone 110 to defend the object from the target recognized as a result of calculation processing by the calculation unit 230 of FIG. 2 and/or itself and the relative motion estimation information of the target. So, it can be transmitted.

At this time, the response defense control information may include first control information regarding the formation, alignment, and flight of individual or group units forming a swarm, and second control information regarding specific response actions to the target.

The first control information may include information related to allowing individual drones to form a distributed formation at regular intervals and move in a certain trajectory, rather than forming a constant plane formation of n*m squadrons before target recognition. . At this time, the flat formation may include various shapes such as rectangle, square, triangle, and circle. Meanwhile, the distributed formation may be determined based on at least one of, for example, a correspondence range according to the second control information, a mutual communication range, and relative motion estimation information such as the movement speed or direction of movement of the recognized target. .

In the first control information, when a target is recognized while moving, the formation forms a dense formation based on the recognized area, and the movement of the formation can be controlled to obtain more information about the target. At this time, the dense formation may be one of a three-dimensional surface, a sphere, or a cone shape.

Next, the second control information includes information that allows the finally recognized target to be regarded as an enemy and respond to it, for example, from outside a predefined distance based on the relative motion estimation information of the target. Information that controls to move at high speed and collide with an approaching target, information that controls self-destruction and bombardment if the distance to the target is within the predefined distance (e.g., relatively close proximity), etc. may be included. For example, the control information may be generated based on a guidance control technique similar to a missile guidance control method. At this time, the missile guidance control method may refer to or use various techniques that exist or will be developed in the future. For related details, refer to the relevant technical contents and separate detailed descriptions will be omitted here.

Meanwhile, in relation to the high-speed collision technique, at least one of a sequential collision method, a mesh collision method, etc. may be used. The sequential collision method is, for example, a method of assigning collision priorities to individual drones belonging to a formation and attempting to collide with the target sequentially. Meanwhile, the net collision method is a method in which multiple drones approach the target at high speed like a net and attempt to collide at the same time.

Meanwhile, in relation to the second control information or collision method, after controlling the formation to fly in a multi-layer manner, the drone(s) closest to the target in the first attempt to collide in a net collision method, and in the second Individual drones may adopt a method of attempting collisions according to collision priority, or vice versa.

Depending on the embodiment, in relation to the first or second control information or collision method, some drones in the formation are controlled to attempt self-destruction, but the formation of the formation is adjusted considering the effective range of self-destruction of individual drones. can do. The self-destruct method may replace or be combined with the collision method described above. Meanwhile, when determining the formation of the formation, it is desirable to ensure that the self-destruction effective ranges of individual drones overlap each other by more than a certain range. In addition, in relation to the formation formation decision, not only the self-destruction effective range but also the relative motion estimation information of the target may be further referenced.

For reference, FIG. 6 illustrates a response defense method, in which the target 630 recognized on the terminal of the control system 120 or the object, that is, the ship 610, and the relative motion estimation information 620 of the target 630 is output, and accordingly, a conceptual diagram is shown in which the swarm drones 110 form a formation and perform defensive operations such as collisions with the target 630.

Figure 4 is a flow chart illustrating an intelligent defense method according to an embodiment of the present invention.

For convenience, Figure 4 is described from the perspective of the control system 120, but is not necessarily limited thereto.

The control system 120 receives information collected about the target from the swarm drone 110 (S10). At this time, the collected information may include sensed data about the target, that is, image data.

The control system 120 can recognize the target based on the information received from the swarm drone 110 and obtain relative motion estimation information for the recognized target (S20).

The control system 120 determines whether to perform the defense mode based on the recognition result and the relative motion estimation information, and if it is determined to perform the defense mode as a result of the judgment, it can generate corresponding defense control information for the swarm drone 110 (S30) ).

The control system 120 may transmit the response defense control information generated in step S30 to control response defense operations from the target to the object through the swarm drone 110 (S40).

In Figure 4, each process is described as being carried out sequentially, but this is merely an exemplary description of one embodiment of the present invention, and the order may be different from that shown. In other words, a person of ordinary skill in the technical field to which the present invention pertains can change and execute the sequence shown in FIG. 4 or perform one or more of the processes in parallel without departing from the essential characteristics of the technical idea of the present invention. Since it can be applied through various modifications and transformations by execution, FIG. 4 is not limited to a time series order.

Figure 5 is a diagram illustrating the operation of an individual drone according to an embodiment of the present invention.

When a target approaches, the sensor unit 220 of the drone can obtain sensed data, that is, image data, about the approaching target.

The image data obtained in this way is image processed in an image processing module and input to a mission management module. At this time, the image processing module and the mission management module may be named an on-board visual inspection mission planner and may be, for example, the operation unit 230 of FIG. 2 or included therein. there is.

The output of the mission management module is input as input data to the flight control computer, and the flight control computer uses this to control the flight of a sensor-fused autonomous blade inspection drone that can damage the target, Operations such as collision actions can be controlled. At this time, the flight control computer may be included in the calculation unit 230.

At least one drone described above may be built into, for example, a canister.

Meanwhile, the processes shown in FIG. 4 can be implemented as computer-readable codes on a computer-readable recording medium. Computer-readable recording media include all types of recording devices that store data that can be read by a computer system. In other words, computer-readable recording media include magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.), optical read media (e.g., CD-ROM, DVD, etc.), and carrier wave (e.g., Internet It includes storage media such as transmission through . Additionally, computer-readable recording media can be distributed across networked computer systems so that computer-readable code can be stored and executed in a distributed manner.

The above description is merely an illustrative explanation of the technical idea of the present embodiment, and those skilled in the art will be able to make various modifications and variations without departing from the essential characteristics of the present embodiment. Accordingly, the present embodiments are not intended to limit the technical idea of the present embodiment, but rather to explain it, and the scope of the technical idea of the present embodiment is not limited by these examples. The scope of protection of this embodiment should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be interpreted as being included in the scope of rights of this embodiment.

The present invention relates to an intelligent defense method, device, and system using swarm unmanned aerial vehicles, and can be used in various intelligent defense methods, devices, and systems.

110: Swarm Drones
120: control system
610: object
630: target

Claims (10)

In a method of defending an object using an electronic device, a swarm unmanned aerial vehicle,
Receiving information obtained about a target;
Recognizing the target from target information received through a predefined algorithm and estimating relative motion information for the recognized target;
Generating corresponding defense control information of a swarm unmanned aerial vehicle for defending the object based on relative motion information estimated with respect to the recognition target; and
Including transmitting the generated swarm unmanned aerial vehicle response defense control information,
Method for defending objects using swarm unmanned aerial vehicles. According to paragraph 1,
In the swarm unmanned aerial vehicle response defense control information,
Containing first control information regarding alignment and flight in each or group of the swarm unmanned aerial vehicles,
Method for defending objects using swarm unmanned aerial vehicles. According to paragraph 2,
In the swarm unmanned aerial vehicle response defense control information,
Containing second control information regarding response to the target,
Method for defending objects using swarm unmanned aerial vehicles. According to paragraph 3,
In the second control information,
High-speed movement and collision control information based on the relative motion information estimated for the target, and self-destruction and scattering control information of the swarm unmanned aerial vehicle when the distance to the target is within a predetermined range,
Method for defending objects using swarm unmanned aerial vehicles. According to paragraph 4,
The target includes at least one unmanned aerial vehicle,
Method for defending objects using swarm unmanned aerial vehicles. According to clause 5,
In the information obtained about the received target,
Contains image data acquired by sensor modules mounted on individual unmanned aerial vehicles forming a swarm,
Method for defending objects using swarm unmanned aerial vehicles. According to clause 6,
The sensor module includes at least one of an image sensor including a camera, a lidar sensor, and a radar sensor,
Method for defending objects using swarm unmanned aerial vehicles. In clause 7,
In the predefined algorithm,
Contains CNN of deep learning techniques,
Method for defending objects using swarm unmanned aerial vehicles. In a device for defending an object using a swarm unmanned aerial vehicle,
Memory; and
Including a processor, wherein the processor includes:
Receives information obtained about a target, recognizes the target from the target information received through a predefined algorithm, estimates relative motion information for the recognized target, and based on the estimated relative motion information for the recognition target Generating and transmitting response defense control information of the swarm unmanned aerial vehicle for defending the object,
Object defense device using swarm unmanned aerial vehicles. In a system for defending an object using a swarm unmanned aerial vehicle,
Drones that include sensor modules that acquire information about targets and form swarms; and
Includes a control system including memory and processor,
In the above, the processor:
Receives information obtained about the target, recognizes the target from the target information received through a predefined algorithm, estimates relative motion information for the recognized target, and calculates relative motion information estimated for the recognition target. Based on this, generate and transmit response defense control information of the swarm unmanned aerial vehicle for defending the object,
Object defense system using swarm unmanned aerial vehicles.