system

Abstract

The system according to this embodiment aims to efficiently perform wide-area surveillance and real-time tracking of suspicious individuals. [Solution] The system according to the embodiment comprises a plurality of ground robots equipped with an image processing module, a plurality of aerial robots equipped with high-resolution cameras, a communication module, a tracking control means, a surround control means, and a control algorithm. The plurality of ground robots equipped with image processing modules detect suspicious persons. The plurality of aerial robots equipped with high-resolution cameras monitor a wide area. The communication module shares information regarding the location and movement path of suspicious persons between the ground robots and the aerial robots. The tracking control means allows the aerial robots to predict the movement path of suspicious persons and transmit that information to the ground robots. The surround control means operates so that the ground robots and aerial robots cooperate to restrict the escape route of suspicious persons. The control algorithm enables cooperative control.

Description

Technical Field

[0001] This disclosure relates to a system.

Background Art

[0002] In conventional security systems, surveillance by fixed cameras and personnel has been the mainstream. These systems can monitor a specific area, but have limitations in wide-area surveillance and real-time tracking. Also, when a suspicious person moves, it is difficult to track them and block their escape route. Furthermore, due to insufficient information sharing among multiple surveillance cameras and security guards, the effect in situations where prompt response is required has been limited.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there has been a problem that it is difficult to conduct wide-area surveillance and real-time tracking of suspicious persons, and efficient security has not been achieved.

[0005] The system according to the embodiment aims to efficiently perform wide-area surveillance and real-time tracking of suspicious persons.

Means for Solving the Problems

[0006] The system according to the embodiment includes a plurality of ground robots equipped with an image processing module for detecting suspicious persons, and a plurality of aerial robots equipped with a high-resolution camera for wide-area surveillance. The ground robots acquire the position information of suspicious persons in real time by the image processing module, and the aerial robots detect the movement route of suspicious persons using the high-resolution camera. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently perform wide-area surveillance and real-time tracking of suspicious individuals. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of the system configuration according to the embodiment. [Figure 2] Figure 2 is a block diagram of the control device according to the embodiment. [Figure 3] Figure 3 is a block diagram of an aerial robot control device according to this embodiment. [Figure 4] Figure 4 is a block diagram of a ground robot control device according to an embodiment. [Figure 5] Figure 5 is a flowchart showing the processing procedure performed by the aerial robot according to this embodiment. [Figure 6] Figure 6 is a flowchart showing the processing procedure performed by the ground robot according to this embodiment. [Figure 7] Figure 7 is a schematic diagram showing an example of a computer hardware configuration that functions as a ground robot or an aerial robot. [Modes for carrying out the invention]

[0009] The following describes in detail the embodiments for implementing the system relating to this application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the system relating to this application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] First, an overview of the system according to the embodiment will be described using Figure 1. Figure 1 is a diagram showing an example of the configuration of the system according to the embodiment. The system according to the embodiment functions as security system 1 shown in Figure 1.

[0011] As shown in Figure 1, the security system 1 comprises a ground robot 2, an aerial robot 3, and a control device 10. Although Figure 1 illustrates one ground robot 2 and one aerial robot 3, the security system 1 can include multiple ground robots 2 and multiple aerial robots 3. Furthermore, as shown in Figure 1, the ground robot 2, the aerial robot 3, and the control device 10 can communicate with each other via a predetermined network N.

[0012] The security system 1 according to an embodiment of the present invention is a system in which a group of ground robots 2 and aerial robots 3 work together to corner a suspicious person. The security system 1 uses "swarm technology (group control technology)" in which multiple drones and ground robots work together to surround and track a suspect or block their escape route.

[0013] Ground robot 2 is an autonomous robot equipped with a camera and an image processing module. For example, ground robot 2 can detect suspicious individuals by analyzing images captured by its camera using its image processing module. Ground robot 2 can also cooperate with aerial robot 3 and other ground robots 2 to restrict the suspicious individual's path or surround them.

[0014] Aerial Robot 3 is a robot that floats in the air using the buoyancy generated by the rotation of its propellers. Aerial Robot 3 is equipped with a high-resolution camera for wide-area surveillance and to detect the movement paths of suspicious individuals.

[0015] Ground robot 2 and aerial robot 3 are each equipped with communication modules that enable them to communicate with each other, allowing them to share information in real time via these modules.

[0016] For example, the aerial robot 3 predicts the escape route of a suspicious person from images captured by its high-resolution camera and transmits that information to the ground robot 2. Based on the information received from the aerial robot 3, the ground robot 2 calculates the optimal route and tracks the suspicious person while moving.

[0017] In addition, the ground robot 2 and the aerial robot 3 cooperate and operate to restrict the escape route of a suspicious person. In the security system 1 according to the embodiment, when a suspicious person enters a specific area, the aerial robot 3 monitors the position of the suspicious person with high precision and notifies the ground robot 2, thereby causing the ground robot 2 to execute an operation of surrounding the suspicious person.

[0018] The control device 10 is a device that manages the ground robot 2 and the aerial robot 3. For example, the control device 10 controls the ground robot 2 and the aerial robot 3 based on information transmitted from the ground robot 2 and the aerial robot 3. Note that some or all of the functions of the control device 10 may be performed by the ground robot 2 or the aerial robot 3.

[0019] Next, a configuration example of the control device 10 according to the embodiment will be described with reference to FIG. 2. FIG. 2 is a block diagram of the control device 10 according to the embodiment. As shown in FIG. 2, the control device 10 according to the embodiment includes a communication unit 11, a storage unit 12, and a control unit 13.

[0020] The communication unit 11 is wirelessly connected to the network N. The communication unit 11 transmits and receives information to and from the ground robot 2 and the aerial robot 3 via the network N.

[0021] The storage unit 12 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a HDD (Hard Disk Drive), a SSD (Solid State Drive), or an optical disk. Various programs and various data are stored in the storage unit 12.

[0022] The control unit 13 is a controller and includes, for example, a microcomputer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM, input / output ports, and various circuits. Alternatively, the control unit 13 may be composed of hardware such as an integrated circuit (ASIC) or FPGA (Field Programmable Gate Array).

[0023] The control unit 13 controls the ground robot 2 and the aerial robot 3. For example, the control unit 13 generates information about the travel path of the ground robot 2 and the flight path of the aerial robot 3 using a text generation model (a so-called AI chat engine). The text generation model can be interpreted as an algorithm and calculations for automated dialogue processing using text.

[0024] The control unit 13 generates questions about the suspicious person from various pieces of information detected by the ground robot 2. First, the control unit 13 generates questions, for example, using a language generation model.

[0025] For example, if movement is detected by the infrared sensor of Ground Robot 2, questions such as, "The infrared sensor detected this movement. Is this movement indicative of a suspicious person? From a criminal's perspective, what action would they take next?" will be generated.

[0026] When such questions are input to the text generation model, the control unit 13 generates a sentence such as, "This person is likely a suspicious individual. They will flee if they sense a human presence." The generated sentence is transmitted to the ground robot 2 as information about the travel path, and the ground robot 2 sets a travel path to approach the person suspected of being a suspicious individual at a low speed.

[0027] Furthermore, for example, if a sound is detected by the sensor on Ground Robot 2 that detects minute sounds, a question will be generated such as, "I hear a beeping sound from 2 meters away. What is this sound?"

[0028] When such a question is input to the text generation model, the control unit 13 generates a sentence such as, "An alarm is sounding." The generated sentence is transmitted to the ground robot 2 as information about the travel route, and the ground robot 2 identifies the person as a suspicious person and sets a travel route to approach the suspicious person via the shortest route, for example.

[0029] The control unit 13 may also generate information regarding the ground robot 2's travel path based on other information detected by the ground robot 2. The control unit 13 may also generate information regarding the ground robot 2's travel path based on information obtained from a 360-degree sensing high-sensitivity camera, LiDAR, thermal camera, and radar. The control unit 13 may also generate information regarding the ground robot 2's travel path based on information obtained from sensors such as vision recognition, ultrasound, vibration, ultraviolet light, and electromagnetic waves.

[0030] Furthermore, based on the multiple pieces of information detected by the ground robot 2, information regarding the ground robot 2's travel path may also be generated. The control unit 13 may also set the ground robot 2's travel path.

[0031] The document generation model generates information about the travel path of the ground robot 2, which allows the ground robot 2 to accurately identify a suspicious person, for example, and to approach the suspicious person without being noticed.

[0032] Furthermore, the control unit 13 may generate information regarding the flight path of the aerial robot 3. For example, the control unit 13 may generate information regarding the flight path using a text generation model.

[0033] For example, if a suspicious person is detected by ground robot 2, and the suspicious person is a car, and the license plate number of the suspicious person is detected as "AA-BB", then control unit 13 will use a language generation model to create a sentence that says, "Photograph the car with the license plate number AA-BB." Then, control unit 13 will input the generated sentence into a text generation model to generate information about the flight path. For example, control unit 13 will use the camera of aerial robot 3 to photograph the car with the license plate number "AA-BB" and generate a flight program for aerial robot 3 to track the car with the license plate number "AA-BB". Then, the generated flight program will be generated as information about the flight path. When the generated information about the flight path is transmitted to aerial robot 3, aerial robot 3 will fly to track the car with the license plate number "AA-BB".

[0034] For example, by generating information about the flight path of the aerial robot 3 using a document generation model, the ability of the aerial robot 3 to track suspicious individuals can be improved.

[0035] The generation of information regarding the travel path of the ground robot 2 using a text generation model may be performed by the ground robot 2 itself.

[0036] Next, an example of the configuration of the aerial robot control device 20 will be described using Figure 3. Figure 3 is a block diagram of the aerial robot control device 20 according to this embodiment. The aerial robot control device 20 shown in Figure 3 is a control device that controls the aerial robot 3.

[0037] As shown in Figure 3, the aerial robot control device 20 comprises a communication unit 21, a storage unit 22, and a control unit 23. The aerial robot control device 20 is connected to various sensors mounted on the aerial robot 3, as well as propellers and other components used to keep the aerial robot 3 afloat.

[0038] The communication unit 21 is wirelessly connected to the network N. The communication unit 21 transmits and receives information with the ground robot 2 and the control device 10 via the network N.

[0039] The storage unit 22 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as HDDs, SSDs, and optical discs. Various programs and various data are stored in the storage unit 22.

[0040] The control unit 23 is a controller and includes, for example, a microcomputer having a CPU, ROM, RAM, input / output ports, etc., and various circuits. The control unit 13 may also be composed of hardware such as an integrated circuit like an ASIC or FPGA.

[0041] The control unit 23 controls the aerial robot 3. The control unit 23 functions as a detection unit and a flight control unit. The detection unit detects suspicious persons (e.g., suspicious individuals). The detection unit detects suspicious persons by, for example, performing predetermined image processing on images captured by a camera mounted on the aerial robot 3. If the aerial robot 3 is equipped with an infrared sensor, the detection unit may also detect suspicious persons according to the detection results from the infrared sensor. The detection unit may also detect suspicious persons using an AI-based suspicious person detection model.

[0042] The flight control unit controls the flight of the aerial robot 3. When the detection unit detects a suspicious person, the flight control unit activates the warning lights mounted on the aerial robot 3, and also sounds an alarm and alerts nearby residents via an alarm device mounted on the aerial robot 3. The flight control unit may also initiate the alarm and alert nearby residents if it anticipates the suspicious person's movement and detects the suspicious person there.

[0043] For example, the flight control unit sets a flight path that allows tracking of a suspicious person and flies along the set flight path. For example, the trackable flight path includes information about the position and altitude at which the suspicious person can be photographed by the camera of the aerial robot 3.

[0044] For example, the flight control unit uses a text generation model to set the flight path. For instance, the flight control unit inputs text such as "Calculate a location where a suspicious person can be photographed over a wide area" to the text generation model at predetermined intervals. The text generation model then appropriately calculates the position of the aerial robot 3 based on these texts. The flight control unit then moves the aerial robot 3 to the position specified by the text generation model, enabling the aerial robot 3 to properly monitor the suspicious person.

[0045] Furthermore, the flight control unit may set the flight path of the aerial robot 3 based on the predicted escape path of the suspicious person. The predicted escape path is generated, for example, by an escape path prediction model. The escape path prediction model predicts the suspicious person's escape path from the suspicious person's location information, map information, traffic information, etc.

[0046] For example, an escape route prediction model can use MapGPT. For example, an escape route prediction model is a text generation model (a so-called AI chat engine), and can be interpreted as an algorithm and calculation for automatic dialogue processing using text. A text generation model is, for example, Japanese Patent Publication No. 2018-081444 or chatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> As it is publicly known as disclosed in [the relevant document], a detailed explanation will be omitted. Such text generation models are composed of large-scale language models (LLMs).

[0047] The flight control unit's prediction of the suspicious person's escape route is then shared with the ground robots 2 via the communication unit 21. Based on the prediction, the ground robots 2 restrict the suspicious person's escape route or surround them. For example, in this case, the ground robots 2 restrict the suspicious person's escape route in order to corner them in a specific area.

[0048] For example, the ground robot 2 restricts the escape route of a suspicious person by cornering them in a dead end within a specific area. This allows the security system 1 according to this embodiment to effectively corner the suspicious person.

[0049] Furthermore, in this case, the ground robot 2 may also pre-notify security guards or security companies of information regarding a specific area where the suspicious person will be pursued. This would allow security guards or security companies to appropriately apprehend the suspicious person in that specific area.

[0050] Furthermore, the ground robot 2 may restrict the escape route of a suspicious person by cornering them in a specific area, such as the nearest police station, police box, police substation, or the location of a moving police vehicle.

[0051] In this way, the security system 1 according to this embodiment restricts the escape route of a suspicious person through the cooperation of multiple aerial robots 3 and multiple ground robots 2. As a result, the security system 1 according to this embodiment can appropriately capture the suspicious person.

[0052] Next, using Figure 4, an example of the configuration of the ground robot control device 30 that controls the ground robot 2 according to the embodiment will be described. Figure 4 is a block diagram of the ground robot control device 30 according to the embodiment.

[0053] As shown in Figure 4, the ground robot control device 30 comprises a communication unit 31, a storage unit 32, and a control unit 33. The ground robot control device 30 is connected to various sensors mounted on the ground robot 2 and to the power source (e.g., a motor) that moves the ground robot 2.

[0054] The communication unit 21 is wirelessly connected to the network N. The communication unit 21 transmits and receives information with the aerial robot 3 and the control device 10 via the network N.

[0055] The storage unit 32 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as HDDs, SSDs, and optical discs. Various programs and various data are stored in the storage unit 32.

[0056] The control unit 33 is a controller and includes, for example, a microcomputer having a CPU, ROM, RAM, input / output ports, etc., and various circuits. Alternatively, the control unit 33 may be composed of hardware such as an integrated circuit (ASIC) or FPGA.

[0057] The control unit 33 implements "swarm technology" in which multiple aerial robots 3 and multiple ground robots 2 work together to surround and track a suspicious person or block their escape route.

[0058] The control unit 33 may generate information regarding the travel path of the ground robot 2. For example, the control unit 33 generates information regarding the travel path of the ground robot 2 using a text generation model (a so-called AI chat engine). The text generation model can be interpreted as an algorithm and calculations for automated text-based dialogue processing, as described above.

[0059] The control unit 33 generates questions about the suspicious person from various pieces of information detected by the ground robot 2. First, the control unit 33 generates questions, for example, using a language generation model.

[0060] For example, if movement is detected by the infrared sensor of ground robot 2, the following question will be generated: "The infrared sensor detected this movement. Is this movement indicative of a suspicious person? From a criminal's perspective, what action would they take next?"

[0061] When such questions are input to the text generation model, the control unit 33 generates a sentence such as, "This person is likely a suspicious individual. They will flee if they sense a human presence." The generated sentence is transmitted to the ground robot 2 as information about the travel path, and the ground robot 2 sets a travel path to approach the person suspected of being a suspicious individual at a low speed.

[0062] Furthermore, for example, if a sound is detected by the sensor on Ground Robot 2 that detects minute sounds, a question will be generated such as, "I hear a beeping sound from 2 meters away. What is this sound?"

[0063] When such a question is input to the text generation model, the control unit 33 generates a sentence such as, "An alarm is sounding." The generated sentence is transmitted to the ground robot 2 as information about the travel route, and the ground robot 2 identifies the person as a suspicious person and sets a travel route to approach the suspicious person via the shortest route, for example.

[0064] The control unit 33 may also generate information regarding the ground robot 2's travel path based on other information detected by the ground robot 2. The control unit 33 may also generate information regarding the ground robot 2's travel path based on information obtained from a 360-degree sensing high-sensitivity camera, LiDAR, thermal camera, and radar. The control unit 33 may also generate information regarding the ground robot 2's travel path based on information obtained from sensors such as vision recognition, ultrasound, vibration, ultraviolet light, and electromagnetic waves.

[0065] Furthermore, based on the multiple pieces of information detected by the ground robot 2, information regarding the ground robot 2's travel path may also be generated. The control unit 33 may also set the ground robot 2's travel path.

[0066] The document generation model generates information about the travel path of the ground robot 2, which allows the ground robot 2 to accurately identify a suspicious person, for example, and to approach the suspicious person without being noticed.

[0067] Next, the processing procedures performed by the aerial robot 3 and the ground robot 2 according to the embodiment will be described using Figures 5 and 6. Figure 5 is a flowchart showing the processing procedures performed by the aerial robot 3 according to the embodiment. Figure 6 is a flowchart showing the processing procedures performed by the ground robot 2 according to the embodiment.

[0068] As shown in Figure 5, the aerial robot 3 first determines whether or not the pursuit of a suspicious person has begun (step S101). The aerial robot 3 determines that the pursuit of a suspicious person has begun if either the aerial robot 3 or any of the ground robots 2 in the security system 1 detects a suspicious person.

[0069] If the aerial robot 3 determines that the pursuit of a suspicious person has begun (step S101; Yes), it will pursue the suspicious person and detect the suspicious person's movement path (step S102). If the aerial robot 3 determines in step S101 that the pursuit of a suspicious person has not begun (step S101; No), it will terminate the process.

[0070] Next, the aerial robot 3 predicts the suspicious person's escape route based on their movement path (step S103) and determines a specific area to surround the suspicious person (step S104). Subsequently, the aerial robot 3 shares information regarding the processing results up to step S104 with the other aerial robots 3 and the ground robot 2 (step S105).

[0071] Next, the aerial robot 3 determines whether the suspicious person is in a specific area (step S106). If the aerial robot 3 determines that the suspicious person is in a specific area (step S106; Yes), it surrounds the suspicious person in the specific area (step S107) and terminates the process.

[0072] Furthermore, if the aerial robot 3 determines in step S106 that the suspicious person is not in the designated area (step S106; No), it continues to perform the processing from step S102 onward.

[0073] Next, the processing procedure performed by the ground robot 2 according to the embodiment will be described using Figure 6. As shown in Figure 6, the ground robot 2 determines whether or not the pursuit of a suspicious person has been initiated (step S201).

[0074] If the ground robot 2 determines that the pursuit of a suspicious person has begun (step S201; Yes), it pursues the suspicious person and detects the suspicious person's location information (step S202). If the ground robot 2 determines in step S201 that the pursuit of a suspicious person has not begun (step S201; No), it terminates the process.

[0075] Next, ground robot 2 shares the suspicious person's location information with other ground robots 2 and aerial robot 3 (step S203). Then, ground robot 2 moves to a position that restricts the suspicious person's escape route (step S204).

[0076] For example, the ground robot 2 restricts the escape route of the suspicious person based on the prediction of the escape route shared by the aerial robot 3. Then, for example, the ground robot 2 surrounds the suspicious person in response to instructions from the aerial robot 3 (step S205) and terminates the process.

[0077] Figure 7 is a schematic diagram showing an example of a computer hardware configuration that functions as a ground robot 2 and an aerial robot 3. A program installed on computer 1200 can cause computer 1200 to function as one or more "parts" of the apparatus according to this embodiment, or to cause computer 1200 to execute operations associated with the apparatus according to this embodiment or such one or more "parts", and / or to cause computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by CPU 1212 to cause computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0078] The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0079] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0080] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0081] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0082] The program is provided on a computer-readable storage medium such as a DVD-ROM or IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0083] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area provided on the recording medium.

[0084] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0085] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0086] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0087] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0088] A computer-readable storage medium may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0089] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar languages.

[0090] Computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or a programmable circuit, either locally or via a wide area network (WAN) such as a local area network (LAN) or the internet, so that the computer-readable instructions may be executed by the processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, in order to generate means for performing operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

[0091] The following describes another example of the tracking system according to the embodiment. First, multiple ground robots are equipped with image processing modules for detecting suspicious persons and acquiring their location information in real time. Furthermore, the aerial robot is equipped with a high-resolution camera for monitoring a wide area and detecting the suspicious person's movement path. Next, a communication module is provided for sharing information about the suspicious person's location and movement path between the ground robot and the aerial robot, thereby enabling the ground and aerial robots to share information in real time. The aerial robot predicts the suspicious person's movement path and transmits this information to the ground robot. Based on this information, the ground robot calculates the optimal path and tracks the suspicious person while moving. Furthermore, the ground and aerial robots work together to restrict the suspicious person's escape route. When a suspicious person enters a specific area, the aerial robot monitors their location with high precision and notifies the ground robot, which then performs a siege. The system implements an algorithm for achieving cooperative control, which consists of the following steps: When a suspicious person is detected, the aerial robot monitors a wide area and predicts the suspicious person's movement path. Based on information from the aerial robots, ground robots move at the appropriate time towards the suspicious person's location. When the suspicious person reaches a specific area, multiple ground robots coordinate their movements to surround the suspicious person. If necessary, the aerial robots provide additional surveillance and track the suspicious person's new movements. This system allows for efficient tracking and encirclement of suspicious persons through the coordinated operation of multiple ground and aerial robots. Furthermore, by utilizing surveillance information from the aerial robots' perspective, a wide-area and rapid response becomes possible, resulting in a higher effectiveness compared to conventional security systems. In this way, the security system enables multiple ground and aerial robots to cooperate in tracking and encircling suspicious persons.

[0092] The security system according to this embodiment comprises a plurality of ground robots equipped with an image processing module, a plurality of aerial robots equipped with high-resolution cameras, a communication module, tracking control means, encirclement control means, and a control algorithm. The image processing module has a function for detecting suspicious persons. For example, the image processing module acquires images of the surroundings using a camera and identifies suspicious persons using image analysis technology. The image processing module can also analyze the images in real time and acquire the location information of suspicious persons. Furthermore, the image processing module can integrate images from multiple cameras to perform wide-area surveillance. For example, the image processing module analyzes camera images in real time and tracks the movements of suspicious persons. The image processing module can also detect persons with specific characteristics from the images and determine their location. The high-resolution camera has a function for monitoring a wide area. For example, the high-resolution camera acquires high-resolution images and performs detailed surveillance. Furthermore, the high-resolution camera has a zoom function and can observe distant objects in detail. Furthermore, the high-resolution camera can acquire clear images even at night or in bad weather. For example, the high-resolution camera uses an infrared camera to perform surveillance even at night. Furthermore, the high-resolution camera is waterproof and can operate normally even in rainy weather. The communication module has the function of sharing information about the location and movement path of suspicious persons between ground robots and aerial robots. The communication module sends and receives data between ground robots and aerial robots using, for example, wireless communication technology. The communication module also has a protocol for sharing information in real time, enabling rapid information transmission. In addition, the communication module can build a network for efficient information sharing among multiple robots. For example, the communication module communicates data between ground robots and aerial robots and shares the location information of suspicious persons in real time. The communication module can also monitor the network status and ensure the stability of communication. The tracking control means has the function of the aerial robot predicting the movement path of suspicious persons and transmitting that information to the ground robot.The tracking and control means, for example, analyzes video footage acquired by the aerial robot to predict the movement pattern of a suspicious person. The tracking and control means can also transmit the predicted movement path to the ground robot, providing information for the ground robot to select the optimal path. Furthermore, the tracking and control means can share information among multiple aerial robots to predict movement paths more accurately. For example, the tracking and control means analyzes video footage acquired by the aerial robot in real time to predict the direction of movement of a suspicious person. It also transmits movement path information to the ground robot, supporting the ground robot in efficient tracking. The encirclement control means has functions to restrict the escape route of a suspicious person through cooperation between the ground robot and the aerial robot. For example, if a suspicious person enters a specific area, the encirclement control means allows the aerial robot to monitor their location with high precision and notify the ground robot. The encirclement control means can also control the movement of the ground robots to coordinately encircle the suspicious person. Furthermore, the encirclement control means is equipped with algorithms for efficient cooperation among multiple robots, enabling rapid encirclement operations. For example, the encirclement control means identifies the location of a suspicious person based on images acquired by the aerial robot and instructs the ground robot to perform an encirclement action. The encirclement control means can also calculate the optimal path for the ground robots to cooperate in encircling the suspicious person. The control algorithm has functions to realize cooperative control. For example, when a suspicious person is detected, the control algorithm allows the aerial robot to monitor a wide area and predict the suspicious person's movement path. The control algorithm can also assist the ground robot in moving at the appropriate time based on information from the aerial robot and heading towards the suspicious person's location. Furthermore, if the suspicious person reaches a specific area, the control algorithm can control the movement of multiple ground robots to cooperate in encircling the suspicious person. For example, the control algorithm predicts the direction of movement of the suspicious person based on images acquired by the aerial robot and instructs the ground robot to move. The control algorithm can also calculate the optimal path for the ground robots to cooperate in encircling the suspicious person.As a result, the security system according to this embodiment can track and surround intruders in cooperation with multiple ground robots and aerial robots.

[0093] The image processing module has the functionality to detect suspicious individuals. For example, the image processing module acquires surrounding video using a camera and identifies suspicious individuals using image analysis technology. Specifically, the image processing module implements an image recognition algorithm using deep learning, which enables high-precision identification of people and objects in the video. For example, it can identify a specific person using facial recognition technology and track their movements. The image processing module can also analyze video in real time and acquire the location information of suspicious individuals. This allows the system to constantly know the current location of suspicious individuals and respond quickly. Furthermore, the image processing module can integrate video from multiple cameras to perform wide-area surveillance. For example, it can integrate video from multiple cameras onto a single screen, allowing for an overview of the entire situation at a glance. This makes it possible to monitor the situation of the entire surveillance area in real time and track the movements of suspicious individuals. The image processing module can also detect individuals with specific characteristics from the video and pinpoint their location. For example, it can identify individuals wearing or carrying specific clothing or items and track their movements. This enables surveillance based on specific conditions, resulting in more effective security.

[0094] High-resolution cameras have the capability to monitor a wide area. For example, they can acquire high-resolution video for detailed surveillance. Specifically, by acquiring 4K or 8K high-resolution video, distant objects and details can be observed clearly. High-resolution cameras also have zoom capabilities, allowing for detailed observation of distant objects. For example, the zoom function can be used to identify the faces of people or license plates of vehicles from a distance. Furthermore, high-resolution cameras can acquire clear images even at night or in bad weather. For example, using high-sensitivity sensors or infrared cameras, they can acquire bright and clear images even at night. High-resolution cameras are also waterproof, allowing them to operate normally even in rainy weather. This enables all-weather surveillance, achieving a 24 / 7 monitoring system. Additionally, high-resolution cameras have video analysis capabilities, allowing for real-time analysis of acquired footage. For example, they can detect movement within the video and identify individuals exhibiting suspicious behavior. As a result, high-resolution cameras enable wide-area and detailed surveillance, maximizing the effectiveness of security systems.

[0095] The communication module has the function of sharing information about the location and movement path of suspicious individuals between ground robots and air robots. The communication module sends and receives data between ground robots and air robots using, for example, wireless communication technology. Specifically, it can send and receive large amounts of data in real time using high-speed wireless communication technologies such as Wi-Fi, LTE, and 5G. The communication module also has protocols for sharing information in real time, enabling rapid information transmission. For example, it can efficiently send and receive data using protocols such as MQTT and HTTP. Furthermore, the communication module can build a network for efficient information sharing among multiple robots. For example, by building a mesh network and having each robot communicate with each other, information sharing over a wide area can be achieved. As a result, the communication module performs data communication between ground robots and air robots and shares information about the location of suspicious individuals in real time. The communication module can also monitor the network status and ensure the stability of communication. For example, by monitoring communication delays and packet loss and changing the communication path as needed, stable communication can be maintained at all times. As a result, the communication module can achieve efficient and stable information sharing and maximize the effectiveness of the security system.

[0096] The tracking and control means has the function of allowing an aerial robot to predict the movement path of a suspicious person and transmit that information to a ground robot. For example, the tracking and control means analyzes the video acquired by the aerial robot to predict the movement pattern of the suspicious person. Specifically, it implements an AI-based prediction algorithm that can predict the suspicious person's next actions based on past movement data and the current situation. The tracking and control means can also transmit the predicted movement path to the ground robot, providing the ground robot with information to select the optimal path. This allows the ground robot to efficiently track the suspicious person. Furthermore, the tracking and control means can share information among multiple aerial robots to make more accurate predictions of movement paths. For example, by integrating video acquired by multiple aerial robots and understanding the situation over a wide area, more accurate predictions can be made. As a result, the tracking and control means analyzes the video acquired by the aerial robot in real time and predicts the direction of movement of the suspicious person. The tracking and control means also transmits information about the movement path to the ground robot, supporting the ground robot in efficiently tracking the suspicious person. This allows the tracking and control system to enable aerial and ground robots to work together to track suspicious individuals, maximizing the effectiveness of the security system.

[0097] The encirclement control system has the function of restricting the escape route of an intruder by coordinating ground robots and aerial robots. For example, if an intruder enters a specific area, the encirclement control system has the aerial robot monitor the intruder's location with high precision and notify the ground robot. Specifically, it analyzes the video acquired by the aerial robot in real time to identify the intruder's location. The encirclement control system can also control the movement of the ground robots to coordinately surround the intruder. This effectively restricts the intruder's escape route. Furthermore, the encirclement control system is equipped with an algorithm for efficient coordination between multiple robots, enabling rapid encirclement operations. For example, the encirclement control system identifies the intruder's location based on the video acquired by the aerial robot and instructs the ground robot to perform encirclement operations. The encirclement control system can also calculate the optimal route for the ground robots to coordinately surround the intruder. In this way, the encirclement control system enables the aerial robots and ground robots to cooperate in surrounding the intruder, maximizing the effectiveness of the security system.

[0098] The control algorithm has functions to achieve cooperative control. For example, when a suspicious person is detected, the control algorithm allows the aerial robot to conduct wide-area surveillance and predict the suspicious person's movement path. Specifically, it implements an AI-based prediction algorithm that can predict the suspicious person's next actions based on past movement data and the current situation. The control algorithm can also assist ground robots in moving at the appropriate time based on information from the aerial robot and heading towards the suspicious person's location. This allows ground robots to efficiently track the suspicious person. Furthermore, if the suspicious person reaches a specific area, the control algorithm can control the movement of multiple ground robots to coordinate and surround the suspicious person. For example, the control algorithm predicts the suspicious person's direction of movement based on video footage acquired by the aerial robot and instructs the ground robots to move. The control algorithm can also calculate the optimal path for ground robots to coordinate and surround the suspicious person. In this way, the control algorithm enables aerial and ground robots to work together to track and surround the suspicious person, maximizing the effectiveness of the security system.

[0099] The image processing module can acquire the location information of suspicious individuals in real time. For example, the image processing module can acquire surrounding video using a camera and identify suspicious individuals using image analysis technology. Furthermore, the image processing module can analyze the video in real time to acquire the location information of suspicious individuals. In addition, the image processing module can integrate video from multiple cameras to perform wide-area surveillance. For example, the image processing module can analyze camera video in real time to track the movements of suspicious individuals. The image processing module can also detect individuals with specific characteristics within the video and determine their location. This allows for a rapid response by acquiring the location information of suspicious individuals in real time.

[0100] High-resolution cameras can detect the movement paths of suspicious individuals. For example, they can acquire high-resolution video for detailed surveillance. They also feature zoom capabilities, allowing for detailed observation of distant objects. Furthermore, high-resolution cameras can acquire clear images even at night or in bad weather. For instance, they utilize infrared technology for nighttime surveillance. Additionally, high-resolution cameras are waterproof, enabling them to function normally even in rainy conditions. This improves tracking accuracy by detecting the movement paths of suspicious individuals.

[0101] The communication module can share information about the location and movement path of suspicious individuals in real time between ground robots and air robots. The communication module uses, for example, wireless communication technology to send and receive data between ground and air robots. It also features a protocol for real-time information sharing, enabling rapid information transmission. Furthermore, the communication module can build a network for efficient information sharing among multiple robots. For example, it can communicate data between ground and air robots to share information about suspicious individuals in real time. The communication module can also monitor the network status to ensure communication stability. This real-time information sharing between ground and air robots enables coordinated operation.

[0102] The tracking and control means allows an aerial robot to predict the movement path of a suspicious person and transmit that information to a ground robot. For example, the tracking and control means analyzes video footage acquired by the aerial robot to predict the suspicious person's movement pattern. The tracking and control means can also transmit the predicted movement path to the ground robot, providing information for the ground robot to select the optimal path. Furthermore, the tracking and control means can share information among multiple aerial robots to make more accurate movement path predictions. For example, the tracking and control means analyzes video footage acquired by the aerial robot in real time to predict the direction of the suspicious person's movement. The tracking and control means also transmits movement path information to the ground robot, supporting the ground robot in efficient tracking. This enables efficient tracking by allowing the aerial robot to predict the suspicious person's movement path and transmit that information to the ground robot.

[0103] The encirclement control means allows an aerial robot to accurately monitor the location of an intruder when they enter a specific area and notify a ground robot, enabling the ground robot to perform an encirclement operation. For example, if an intruder enters a specific area, the encirclement control means monitors the location of the aerial robot with high precision and notifies the ground robot. The encirclement control means can also control the movement of the ground robots to coordinately encircle the intruder. Furthermore, the encirclement control means is equipped with an algorithm for efficient coordination between multiple robots, enabling rapid encirclement operations. For example, the encirclement control means identifies the intruder's location based on video footage acquired by the aerial robot and instructs the ground robot to perform an encirclement operation. The encirclement control means can also calculate the optimal route for the ground robots to coordinately encircle the intruder. This prevents escape by quickly executing an encirclement operation when an intruder enters a specific area.

[0104] The control algorithm allows the aerial robot to perform wide-area surveillance and predict the movement path of a suspicious person when one is detected. For example, the control algorithm analyzes the video footage acquired by the aerial robot to predict the suspicious person's movement pattern. The control algorithm can also transmit the predicted movement path to a ground robot, providing the ground robot with information to select the optimal path. Furthermore, the control algorithm can share information among multiple aerial robots to make more accurate movement path predictions. For example, the control algorithm analyzes the video footage acquired by the aerial robot in real time to predict the suspicious person's direction of movement. The control algorithm also transmits movement path information to the ground robot, supporting the ground robot in efficient tracking. This enables a rapid response by performing wide-area surveillance and predicting the movement path when a suspicious person is detected.

[0105] The control algorithm allows ground robots to move at the appropriate time based on information from aerial robots and head towards the location of the suspicious person. For example, the control algorithm analyzes video footage acquired by the aerial robot to predict the suspicious person's movement pattern. The control algorithm can also transmit the predicted movement path to the ground robot, providing information for the ground robot to select the optimal path. Furthermore, the control algorithm can share information among multiple aerial robots to predict movement paths more accurately. For example, the control algorithm analyzes video footage acquired by the aerial robot in real time to predict the suspicious person's direction of movement. The control algorithm also transmits movement path information to the ground robot, supporting the ground robot in efficient tracking. As a result, the ground robot can move at the appropriate time, leading to efficient tracking of the suspicious person.

[0106] The control algorithm can control the movement of multiple ground robots to surround an intruder when the intruder reaches a specific area. For example, the control algorithm analyzes video footage acquired by the aerial robot to predict the intruder's movement pattern. The control algorithm can also transmit the predicted movement path to the ground robot, providing information for the ground robot to select the optimal path. Furthermore, the control algorithm can share information among multiple aerial robots to make more accurate movement path predictions. For example, the control algorithm analyzes video footage acquired by the aerial robot in real time to predict the intruder's direction of movement. The control algorithm also transmits movement path information to the ground robot to help the ground robot efficiently track the intruder. This allows multiple ground robots to cooperate in surrounding the intruder and prevent escape.

[0107] The control algorithm allows the aerial robot to perform additional monitoring as needed and track any new movements of the suspicious individual. For example, the control algorithm analyzes video footage acquired by the aerial robot to predict the suspicious individual's movement patterns. It can also transmit the predicted movement path to a ground robot, providing the ground robot with information to select the optimal path. Furthermore, the control algorithm can facilitate information sharing among multiple aerial robots to predict movement paths more accurately. For example, the control algorithm analyzes video footage acquired by the aerial robot in real time to predict the suspicious individual's direction of movement. It also transmits movement path information to the ground robot, supporting its efficient tracking. This allows the aerial robot to respond to any new movements of the suspicious individual by performing additional monitoring.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The security system may also be equipped with a voice recognition unit. The voice recognition unit has the function of detecting and analyzing the content of voices emitted by suspicious individuals. For example, the voice recognition unit can acquire ambient sounds using microphones and identify the content of what the suspicious individual is saying using voice analysis technology. This makes it possible to infer the intentions and actions of the suspicious individual from the voice they emit. The voice recognition unit can also detect specific keywords. For example, it can detect highly urgent keywords such as "help" or "run away" and notify the security system. This allows the security system to respond quickly. In addition, the voice recognition unit can determine the direction of the sound source using multiple microphones. For example, the voice recognition unit can determine the direction of the sound source and transmit this information to ground robots and air robots. This makes it possible to pinpoint the location of the suspicious individual more accurately. Furthermore, the voice recognition unit can analyze voice data in real time and feed it back to the security system. For example, the voice recognition unit can analyze the voice emitted by a suspicious individual in real time and transmit the results to the security system. This allows the security system to grasp the actions of the suspicious individual more quickly and take appropriate action.

[0110] The security system may also be equipped with an environmental sensor unit. The environmental sensor unit has the function of acquiring and analyzing information about the surrounding environment. For example, the environmental sensor unit can acquire information about the surrounding environment using temperature sensors, humidity sensors, and atmospheric pressure sensors. This allows the security system to identify places where a suspicious person may be hiding. The environmental sensor unit can also detect harmful gases using gas sensors. For example, the environmental sensor unit can detect specific harmful gases and notify the security system of this information. This allows the security system to understand the possibility that a suspicious person is using harmful gases and take appropriate action. The environmental sensor unit can also detect ambient brightness using light sensors. For example, the environmental sensor unit can detect ambient brightness and transmit this information to the security system. This allows the security system to understand the possibility that a suspicious person is hiding in darkness and take appropriate action. Furthermore, the environmental sensor unit can also detect ground vibrations using vibration sensors. For example, the environmental sensor unit can detect ground vibrations and transmit this information to the security system. This allows the security system to understand the possibility that a suspicious person is moving on the ground and take appropriate action.

[0111] The security system may also be equipped with a biometric authentication unit. The biometric authentication unit has the function of acquiring and analyzing the biometric information of a suspicious person. For example, the biometric authentication unit can identify a suspicious person using fingerprint authentication, facial recognition, or iris recognition. This allows the security system to quickly identify the suspicious person and take appropriate action. The biometric authentication unit can acquire a suspicious person's fingerprint using fingerprint authentication. For example, the biometric authentication unit can acquire a suspicious person's fingerprint using a fingerprint sensor and transmit that information to the security system. This allows the security system to identify the suspicious person and take a quick response. Furthermore, the biometric authentication unit can recognize a suspicious person's face using facial recognition. For example, the biometric authentication unit can photograph a suspicious person's face using a camera and transmit that information to the security system. This allows the security system to identify the suspicious person and take a quick response. Additionally, the biometric authentication unit can recognize a suspicious person's iris using iris authentication. For example, the biometric authentication unit can acquire a suspicious person's iris using an iris sensor and transmit that information to the security system. This allows the security system to identify the suspicious person and respond quickly.

[0112] The security system can also be equipped with a drone charging unit. The drone charging unit has the function of automatically charging the aerial robot's battery. For example, the drone charging unit can charge the aerial robot's battery using a charging station installed on the ground. This allows the aerial robot to perform surveillance activities for extended periods. The drone charging unit can also charge the aerial robot's battery using wireless charging technology. For example, the drone charging unit can charge the aerial robot's battery using a wireless charging pad. This allows the aerial robot to charge its battery without using a charging cable. Furthermore, the drone charging unit can charge the aerial robot's battery using solar panels. For example, the drone charging unit can convert sunlight into electricity using solar panels to charge the aerial robot's battery. This allows the aerial robot to charge its battery in an environmentally friendly way. In addition, the drone charging unit has a battery replacement function and can automatically replace the aerial robot's battery. For example, the drone charging unit can automatically replace the battery when the aerial robot returns to the charging station, allowing it to resume surveillance activities. This ensures the aerial robot always has sufficient battery power for extended surveillance activities.

[0113] The security system can also be equipped with an emergency response unit. The emergency response unit has the function of responding quickly to the actions of an intruder. For example, the emergency response unit can issue an alarm if an intruder enters a specific area. This allows for quick notification to security guards and other relevant personnel, enabling appropriate action. In addition to issuing alarms, the emergency response unit can also provide specific response instructions to security guards. For example, it can notify security guards of the intruder's location and movement route to support a rapid response. Furthermore, the emergency response unit can control the operation of the entire security system and direct the optimal actions to respond to an emergency. For example, the emergency response unit can enhance the coordination between aerial and ground robots to quickly block the intruder's escape route. In addition, the emergency response unit can cooperate with external emergency response agencies. For example, the emergency response unit can provide information on the intruder to emergency response agencies such as the police and fire department to support a rapid response. This enables the security system to respond quickly and effectively to emergencies.

[0114] Although embodiments of the present application have been described in detail above, these are illustrative examples, and the present invention can be implemented in various other forms based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. [Explanation of Symbols]

[0115] 1. Security System 2 Ground robots 3. Aerial Robots 10 Control device 20 Aerial robot control system 30 Ground robot control system

Claims

1. Multiple ground robots equipped with image processing modules for detecting suspicious individuals, Multiple aerial robots equipped with high-resolution cameras for wide-area monitoring, Equipped with, The aforementioned ground robot, The aforementioned image processing module acquires the location information of the suspicious person in real time. The aforementioned aerial robot The aforementioned high-resolution camera is used to detect the movement path of a suspicious person. A system characterized by the following features.

2. The ground robot and the aerial robot include a communication module for sharing information regarding the location and movement path of a suspicious person, The ground robot and the aerial robot are, The communication module is used to share information regarding the location and movement path of the suspicious person in real time. The system according to feature 1.

3. The aforementioned aerial robot Using the aforementioned high-resolution camera, the escape route of the suspicious person is predicted from the detected movement path. The aforementioned ground robot, Based on the escape route predicted by the aforementioned aerial robot, the suspicious person is tracked. The system according to claim 2.

4. The ground robot and the aerial robot are, They work together to restrict the escape route of the suspicious person. The system according to claim 3.

5. The aforementioned ground robot, Restricting the escape route of a suspicious person to guide them to a specific area. The system according to feature 4.

6. The aforementioned aerial robot When a suspicious person enters a specific area, the ground robot is instructed to surround the suspicious person. The aforementioned ground robot, The aerial robot, upon receiving instructions from the aforementioned aerial robot, performs an action to surround the suspicious person. The system according to claim 5, characterized in that it is the same as described in claim 5.

Images