Defense system

Abstract

To provide a system to defend against intruders in work areas.SOLUTION: A defense system includes an unmanned flying object 3, an intruder sensor, an imaging device mounted on the unmanned flying object 3, and a speaker mounted on the unmanned flying object 3. When the intruder sensor detects an intruder X who intrudes a work area 1, the defense system causes the imaging device on the unmanned flying body 3 to capture the intruder X and acquire the face image of the intruder X. The defense system estimates the intruder's age based on the acquired face image of the intruder X, and further selects voice data, which is an output target, based on the estimated age. The defense system causes the speaker on the unmanned flying body 3 to output a voice with an alarm indicated by the selected voice data.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present application relates to a defense system using unmanned aerial vehicles. [Background technology]

[0002] Conventionally, unmanned aerial vehicles known as drones have been used in work areas such as factories or warehouses. For example, Patent Document 1 describes a guidance system that includes a manned guided vehicle operated by an operator, one unmanned aerial vehicle capable of hovering in the air, and a management device that controls the unmanned aerial vehicle.

[0003] In the guidance system described in Patent Document 1, the unmanned aerial vehicle is equipped with a projector that projects a guidance image onto a road surface. The guidance image, for example, displays an arrow pointing in a specific direction and is projected onto the road surface in front of the manned guided vehicle. As a result, an operator operating the manned guided vehicle can be guided to the loading position by checking the guidance image.

[0004] In recent years, automated guided vehicles (AGVs) have been used instead of manned vehicles to reduce work loads. However, when an automated system is used in a work area such as a factory or warehouse, there is a risk that unauthorized intruders may steal or destroy luggage or equipment stored on shelves in the work area. In this regard, if there were a means to effectively warn intruders, it would be possible to expel intruders or deter them from entering the work area. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2020-52629 Summary of the Invention [Problem to be solved by the invention]

[0006] The present application provides a defense system for the purpose of defending against intruders in a work area such as a factory or warehouse. [Means for solving the problem]

[0007] The defense system provided herein comprises: one or more unmanned air vehicles configured to fly in a work area; an intruder sensor for detecting an intruder who has entered the work area; a photographing device provided on the unmanned aerial vehicle for photographing the face of the intruder; a speaker provided on the unmanned aerial vehicle for outputting sound; a voice storage medium storing a plurality of voice data items each showing a voice warning and each having different voice characteristics; an age estimation unit that estimates the age of a person based on a facial image of the person; an audio selection unit that selects audio data to be output from the plurality of audio data stored in the audio storage medium; a warning control unit that controls the operation of the unmanned aerial vehicle to issue a warning; When the intruder sensor detects an intruder, the warning control unit controls the unmanned aerial vehicle equipped with the photographing device to cause the photographing device to photograph the intruder and acquire a facial image of the intruder; the age estimation unit estimates the age of the intruder based on the acquired facial image of the intruder; the voice selection unit selects voice data to be output from the plurality of voice data stored in the voice storage medium based on the estimated age, When the intruder sensor detects the intruder, the warning control unit controls the unmanned aerial vehicle equipped with the speaker to cause the speaker to output the warning indicated by the audio data selected by the audio selection unit to the intruder.

[0008] For example, the audio data is provided for each category defined by age group, The voice selection unit may select, as an output target, the voice data provided for the category corresponding to the age estimated by the age estimation unit.

[0009] For example, the plurality of pieces of voice data may differ from each other in at least one of the voice characteristics: tone of voice, speech tone, and speaking rate.

[0010] For example, the age estimation unit may input the acquired facial image of the intruder into a trained model that estimates the age of a person from the facial image of the person, and estimate the age of the intruder using the output from the trained model.

[0011] The audio storage medium may be provided in the unmanned aerial vehicle equipped with the speaker, or in a management device described in a later embodiment.

[0012] In one example, the defense system includes, as the unmanned aerial vehicle: a first unmanned aerial vehicle equipped with the intruder sensor and the photographing device, the first unmanned aerial vehicle flying to detect the intruder and photograph the intruder; The vehicle may also include a second unmanned aerial vehicle equipped with the speaker, which, when the intruder sensor detects the intruder, flies toward the intruder to output audio to the intruder.

[0013] In this example, the first unmanned air vehicle may be equipped with a camera that functions as the intruder sensor and the photographing device.

[0014] In another example, the defense system includes: The system may also include a single unmanned aerial vehicle equipped with the intruder sensor, the photographing device, and the speaker, and whose operation is controlled by the warning control unit to detect the intruder, photograph the intruder, and output audio to the intruder.

[0015] In another example, the defense system includes: a first unmanned aerial vehicle equipped with the intruder sensor, the first unmanned aerial vehicle flying to detect the intruder; a second unmanned aerial vehicle equipped with the photographing device, which, when the intruder sensor detects the intruder, flies toward the intruder to photograph the intruder; The system may also include a third unmanned aerial vehicle equipped with the speaker, which, when the intruder sensor detects the intruder, flies toward the intruder to output audio to the intruder.

[0016] The intruder sensor may be provided on the unmanned aerial vehicle or may be installed in the work area. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic diagram illustrating an exemplary defense system. [Figure 2] Figure 2A is a diagram illustrating an example unmanned aerial vehicle, and Figure 2B is a block diagram of the unmanned aerial vehicle's own control unit. [Figure 3] FIG. 3 is a block diagram of an exemplary management device. [Figure 4] FIG. 4 is a table illustrating the audio data stored in the audio storage medium. [Figure 5] FIG. 5 is a flow diagram of an example defense process performed by the management device of FIG. [Figure 6] FIG. 6 is a schematic diagram illustrating an example defense process. [Figure 7] FIG. 7 is a schematic diagram illustrating another exemplary defense process. DETAILED DESCRIPTION OF THE INVENTION

[0018] A defense system according to an embodiment of the present invention will now be described with reference to the accompanying drawings, which are merely exemplary of the present invention. The drawings are schematic only and may not be drawn to scale. It should also be understood that the same reference numerals are used throughout the figures to represent the same or similar components.

[0019] 1 is a schematic diagram of an exemplary defense system. The defense system photographs an intruder X who has entered a predetermined work area 1 without permission, and defends the work area 1 (e.g., luggage, equipment, etc. within the work area 1) from the intruder X.

[0020] The defense system of FIG. 1 includes a work area 1, at least one work vehicle 2, a plurality of unmanned aerial vehicles 3, and a management device 4 that controls the work vehicle 2 and the unmanned aerial vehicles 3.

[0021] The work area 1 is an area where the work vehicle 2 performs work and is also an area monitored by the unmanned aerial vehicle 3. For example, the work area 1 may be an area within any facility, including a factory or warehouse. The work area 1 is provided with a plurality of shelves 10, and cargo is stored on the shelves 10. The shelves 10 may be fixed shelves, or may be movable shelves configured to be movable under the control of the management device 4, or may include both.

[0022] The work vehicle 2 is a vehicle that performs work within the work area 1. The work vehicle 2 is, for example, a forklift that performs loading and unloading work. The work vehicle 2 may be a manned work vehicle or an unmanned work vehicle. In the example shown in FIG. 1, the work vehicle 2 is an unmanned forklift, and a plurality of reflectors 11 are provided in the work area 1 (for example, the wall of a facility) to guide the work vehicle 2 with a laser.

[0023] 1 projects a laser from a laser scanner into the surrounding area, detects the light reflected from multiple reflectors 11, and estimates its own position in real time based on the principle of triangulation. As a result, the work vehicle 2 travels along the movement route determined by the management device 4 based on its estimated own position, and can perform loading and unloading on the shelves 10.

[0024] In the example of Figure 1, two unmanned aerial vehicles 3a and 3b are used. Although these unmanned aerial vehicles 3a and 3b have different roles, most of their configurations are the same. When there is no need to distinguish between them, the symbol "3" is used, and when there is a need to distinguish between them, "3a" and "3b" are used. Unmanned aerial vehicle 3 is a drone.

[0025] As shown in FIG. 2A, the unmanned aerial vehicle 3 includes a main body 30, rotors 31, legs 32, a camera 33, a speaker 34, a light 35, a communication device 36, and an aircraft control unit 37.

[0026] The main body 30 includes a body incorporating a speaker 34, a light 35, a communication device 36, and a control unit 37 for the machine, and multiple arms (four in this example) extending radially from the body. A rotor 31 is provided at the top end of each arm, and a pair of legs 32 and a camera 33 are attached to the bottom of the body.

[0027] The camera 33, under the control of the aircraft control unit 37, takes video and / or still images during flight and transmits the acquired image data to the management device 4 via the communication device 36. The camera 33 may further include an infrared sensor and a light that emits light when taking pictures. In this example, one camera 33 of the unmanned aerial vehicle 3a functions as the "intruder sensor" of the present invention and also functions as the "photography device" of the present invention.

[0028] The speaker 34 outputs sound under the control of the device control unit 37. The speaker 34 is configured to output predetermined alarm sounds such as beeps and sirens, and also to output sound indicated by audio data. The speaker 34 is preferably a directional speaker.

[0029] The light 35 outputs visible light and may be, for example, composed of at least one LED light. The light 35 may change the state of output of visible light. For example, the light may be a constantly lit light or a flashing light. The light 35 may also be equipped with an irradiation angle adjustment mechanism that can change the irradiation angle of the visible light.

[0030] The communication device 36 is for wireless communication with the management device 4, and is thereby capable of transmitting and receiving information to and from the management device 4.

[0031] The aircraft's own control unit 37 controls the operation of each component of the aircraft based on the output of sensors (such as an orientation sensor and an altitude sensor) not shown and commands from the management device 4. As shown in Fig. 2B, the aircraft's own control unit 37 includes a position information acquisition unit 371, a flight control unit 372, a camera control unit 373, a speaker control unit 374, and a light control unit 375. The aircraft's own control unit 37 may be configured, for example, by a digital circuit using a microcontroller or DSP, or may be configured by a circuit that combines a digital circuit and an analog circuit.

[0032] The position information acquisition unit 371 is configured to acquire position information of the main body 30, for example, using a satellite positioning system such as GPS. The position information includes, for example, latitude information, longitude information, and altitude information. The position information acquisition unit 371 outputs the acquired position information to the flight control unit 372 and transmits the position information to the management device 4. Note that the position information acquisition unit 371 is not limited to a satellite positioning system such as GPS, and any known configuration can be adopted, for example, the configuration described in Patent Document 1. However, if the configuration described in Patent Document 1 is adopted, a ceiling marker must be provided on the ceiling of the work area 1. Furthermore, the position information acquisition unit 371 may identify the direction in which its own camera 33 is facing and transmit information regarding the direction to the management device 4 together with the position information. Alternatively, the management device 4 may analyze image data from the camera 33 to identify the direction in which the camera 33 is facing.

[0033] The flight control unit 372 performs flight control of the main body 30 based on the position information from the position information acquisition unit 371 and commands from the management device 4. Specifically, the flight control unit 372 controls the rotation of the rotors 31 as part of flight control of the main body 30. The flight control unit 372 can make the unmanned aerial vehicle 3 hover (stop in the air) by setting the rotation speeds of the electric motors of each rotor 31 to the same speed, raise the unmanned aerial vehicle 3 by simultaneously increasing the rotation speeds of each electric motor in the hovering state to the same extent, and change the direction of travel of the unmanned aerial vehicle 3 by changing the rotation speeds of the four electric motors at different rates. This allows the unmanned aerial vehicle 3 to fly to its destination along the travel route (flight route) determined by the management device 4.

[0034] The camera control unit 373 causes the camera 33 to take videos and / or still images during flight and transmits the image data obtained thereby to the management device 4 via the communication device 36. If the camera 33 is equipped with an infrared sensor and / or lighting, the camera control unit 373 also controls the infrared sensor and / or lighting. The camera control unit 373 also has a storage medium for saving the taken videos and / or still images. This makes it possible to save the taken videos and / or still images even if communication with the management device 4 is unstable.

[0035] The speaker control unit 374 outputs sound from the speaker 34 based on a command from the management device 4.

[0036] The light control unit 375 controls the on / off (lighting on / off) of the light 35. If the light 35 is equipped with an irradiation angle adjustment mechanism, the light control unit 375 controls the irradiation angle adjustment mechanism to vary the irradiation angle of visible light.

[0037] 1, the management device 4 is preferably provided outside the work area 1, but may also be provided inside the work area 1. The management device 4 is configured, for example, by a computer including an arithmetic unit and a storage device.

[0038] 3, the management device 4 includes a communication device 40, an age estimation unit 41, a voice selection unit 42, a warning control unit 43, and a storage medium 44. In this example, the age estimation unit 41, the voice selection unit 42, and the warning control unit 43 are functional units that are realized by one or more processors of the arithmetic unit of the management device 4 executing programs stored in a storage device (hard disk or memory) of the management device 4. The storage medium 44 is configured by one or more storage devices of the management device 4. The storage medium 44 includes a model storage medium 440 and a voice storage medium 441.

[0039] The communication device 40 communicates wirelessly with each unmanned aerial vehicle 3. Specifically, the communication device 40 is used to receive image data acquired by the camera 33 from each unmanned aerial vehicle 3, and to transmit various commands and data to each unmanned aerial vehicle 3.

[0040] The age estimation unit 41 estimates the age of a person based on a facial image (facial image data) of the person. In this example, the age estimation unit 41 estimates the age using a trained model stored in a model storage medium 440. Here, the trained model is generated by machine learning using a large amount of training data consisting of a facial image of a person and the age of the person as corresponding correct answer data. As a result, the trained model is configured to estimate the age of a person when a facial image of the person is input. The age estimation unit 41 is used to estimate the age of an intruder X who has invaded the working area 1, as will be described below.

[0041] The audio selection unit 42 selects audio data to be output from the speaker 34 of the unmanned aerial vehicle 3 from the plurality of audio data stored in the audio storage medium 441 .

[0042] Here, the audio data stored in the audio storage medium 441 indicates an audio warning against intrusion into the working area 1. For example, the specific audio warning may be something like "You are trespassing. Leave immediately" or "We have called the police. Please do not move," calling for people to leave or surrender.

[0043] The multiple pieces of audio data stored in the audio storage medium 441 have different audio characteristics. The audio characteristics in this example include tone of voice, tone of speech, and speaking rate, and the multiple pieces of audio data differ from each other in at least one of these. FIG. 4 is a table explaining the audio characteristics of audio data according to one example. In this example, three pieces of audio data A to C are stored in the audio storage medium 441. The warnings in the audio data A to C all have the same content, calling for an intruder to leave or surrender in response to an intrusion into the working area 1, but the audio characteristics differ in the following ways.

[0044] Regarding voice tone: the voice of voice data A is that of a person in their 20s, the voice of voice data B is that of a person in their 40s, and the voice of voice data C is that of a person in their 60s.

[0045] Regarding tone of voice: the voice warning in voice data A is in a strong tone, the voice warning in voice data B is in a strong tone, and the voice warning in voice data C is in a polite tone. A voice warning in a "strong tone" may be, for example, "Get out of here immediately," using an imperative sentence with large changes in intonation and / or an emphasized tone, so as to intimidate the other person. On the other hand, a voice warning in a "polite tone" may be, for example, "Please leave here immediately," using polite language with small changes in intonation and / or an emphasized tone, so as to urge the other person to leave.

[0046] Regarding speech speed: The speech speed of the warning voice in audio data A is fast, the speech speed of the warning voice in audio data B is normal, and the speech speed of the warning voice in audio data C is slow. For example, the speech speed for "fast" is 7.5 [mora / sec], the speech speed for "normal" is 6.0 [mora / sec], and the speech speed for "slow" is 4.5 [mora / sec]. Here, the unit of speech speed [mora / sec] is the number of characters (hiragana) spoken per second.

[0047] Each piece of voice data is assigned a category defined by age (hereinafter referred to as target age category). In this example, voice data A is assigned to the young age group (under 20s), voice data B is assigned to the middle age group (30-50s), and voice data C is assigned to the elderly age group (over 60s).

[0048] The voice selection unit 42 selects voice data to be output from among the plurality of voice data having different voice characteristics. Specifically, the voice selection unit 42 selects, as the output data, voice data corresponding to the target age category to which the age estimated by the age estimation unit 41 belongs. Therefore, in this example, if the age estimation unit 41 estimates the person's age to be 35 years old, the voice selection unit 42 selects, as the output data, voice data B which is provided for the target age category to which 35 years old belongs, i.e., the middle-aged group. For example, the voice selection unit 42 selects voice data A when the person's age is estimated to be 20 years old, and selects voice data C when the person's age is estimated to be 65 years old.

[0049] In the above example, to facilitate understanding of the subject matter of the invention, three age groups are defined and three corresponding voice data A to C are prepared. Age groups may be divided into smaller groups (for example, by decade) and a corresponding number of voice data may be prepared. Furthermore, it is preferable to determine which voice features are assigned to which age groups so that the warning is effective from an empirical and / or psychological perspective.

[0050] In the example of Figure 4, each of the voice data A to C indicates a voice warning in a voice tone of the same age group as the assigned age group. This is based on the fact that the voice tone of the same age group tends to be more familiar and relatively easy to understand than the voice tone of other age groups. In addition, the speech rate is set slower for older age groups. This is based on the fact that older people tend to be able to understand the content more easily when the speech rate is slower.

[0051] The warning control unit 43 controls the operation of each unmanned aerial vehicle 3 and issues an audio warning to the intruder X, as described below. To this end, the warning control unit 43 includes a position identification unit 430, a route determination unit 431, and a command unit 432, as shown in FIG. 3 .

[0052] The position identification unit 430 identifies the position of the intruder X based on detection by the intruder sensor of the first unmanned aerial vehicle 3a (analysis of image data captured by the camera 33 serving as the intrusion sensor). The position identification unit 430 acquires position information (position coordinates) of the intruder X by analyzing the image data captured by the first unmanned aerial vehicle 3a using a known method. Alternatively, if the first unmanned aerial vehicle 3a is equipped with a distance sensor (e.g., LiDAR, millimeter-wave radar, or stereo camera) for measuring the distance to the target object (intruder X), the position identification unit 430 may calculate the position coordinates of the intruder X based on the position information of the first unmanned aerial vehicle 3a (acquired from the position information acquisition unit 371), information related to the measurement results measured by the distance sensor, and the direction in which the first unmanned aerial vehicle 3a is facing.

[0053] The route determination unit 431 determines the movement route (flight route) of the unmanned aerial vehicle 3b to the intruder X. This movement route is determined based on the position information of the intruder X identified by the position identification unit 430, the position information of the unmanned aerial vehicle 3b (information on the waiting position of the unmanned aerial vehicle 3b and current position information received from the position information acquisition unit 371 of the unmanned aerial vehicle 3b, etc.), an environmental map of the work area 1, etc.

[0054] The command unit 432 wirelessly transmits various commands to the unmanned aerial vehicle 3 via the communication device 40, together with information necessary for warning control as necessary, to remotely control each unmanned aerial vehicle 3.

[0055] Additionally, the management device 4 may have a user interface for the user to select whether or not to use the defense functions described below and / or to assign or change target age categories to audio data.

[0056] The management device 4 creates a schedule for loading and unloading work for the work vehicle 2 (in this example, an unmanned forklift), determines a travel route for smoothly carrying out the loading and unloading work, and transmits this to the work vehicle 2 via the communication device 40.

[0057] An example defense process is described below. For ease of explanation, at the start of the example defense process shown in Figure 5, the first unmanned aerial vehicle 3a is flying over the work area 1 based on receiving a monitoring command from the command unit 432, and is in the process of monitoring the work area 1 with its own camera 33. The second unmanned aerial vehicle 3b is waiting at a predetermined waiting position.

[0058] While flying, the first unmanned aerial vehicle 3a takes video with the camera 33. The warning control unit 43 receives image data acquired by the camera 33, which serves as an intruder sensor, from the first unmanned aerial vehicle 3a in real time, and determines whether the first unmanned aerial vehicle 3a has detected an intruder X (S1).

[0059] If the image data shows the intruder X, the warning control unit 43 determines that the first unmanned aerial vehicle 3a (camera 33 as an intruder sensor) has detected the intruder X (YES in S1). On the other hand, if the image data does not show the intruder X, the warning control unit 43 determines that the first unmanned aerial vehicle 3a (camera 33 as an intruder sensor) has not detected the intruder X (NO in S1).

[0060] If the answer is YES in step S1, proceed to step S2. In step S2, the warning control unit 43 (command unit 432) sends a photography command to the unmanned aerial vehicle 3a to acquire a facial image of the intruder X. At the same time, the warning control unit 43 (position identification unit 430) acquires the position information of the intruder X using the method described above. Then, the warning control unit 43 (route determination unit 431) determines the movement route of the unmanned aerial vehicle 3b to the intruder X using the method described above, and sends a movement command to the unmanned aerial vehicle 3b together with information indicating the determined movement route.

[0061] Upon receiving the shooting command, the unmanned aerial vehicle 3a photographs the face of the intruder X. The unmanned aerial vehicle 3a references the position of the intruder X with its own camera 33 and flies around the intruder X, capturing still images multiple times with the camera 33 as a shooting device. As a result, at least the head of the intruder X is photographed from various angles, and the face of the intruder X is included in at least one of the acquired images (image data). Alternatively, the unmanned aerial vehicle 3a may reference the position of the intruder X with its own camera 33 and fly around the intruder X, capturing video with the camera 33 and acquiring a facial image of the intruder X. The unmanned aerial vehicle 3a transmits the image acquired in this step to the management device 4 as a facial image of the intruder X.

[0062] When the age estimation unit 41 receives the facial image of the intruder X, it estimates the age of the intruder X based on the facial image (S3). In this example, the age estimation unit 41 inputs the facial image of the intruder X into the trained model and estimates the age of the intruder X using the output from the trained model. Then, the age estimation unit 41 sends information indicating the estimated age to the voice selection unit 42.

[0063] When the audio selection unit 42 receives information indicating the estimated age of the intruder X from the age estimation unit 41, it selects audio data to be output from the plurality of audio data stored in the audio storage medium 441 based on the estimated age of the intruder X (S4). The method for selecting audio data is as described above. The audio selection unit 42 sends information identifying the selected audio data to the warning control unit 43.

[0064] When the warning control unit 43 (command unit 432) receives information identifying the selected audio data, it sends an audio output command to the unmanned aerial vehicle 3b together with the selected audio data (S5) and controls the operation of the unmanned aerial vehicle 3b as follows.

[0065] Based on receiving the movement command, unmanned aerial vehicle 3b flies along the determined movement route and heads toward the location of intruder X. When unmanned aerial vehicle 3b reaches the vicinity of intruder X (for example, a position where intruder X can be seen with its own camera 33) and receives the audio output command and the selected audio data, it responds by first adjusting its own position and orientation based on the detection of intruder X by its own camera 33, and pointing its own directional speaker 34 toward the intruder.

[0066] As shown in Figure 6, the unmanned aerial vehicle 3b then outputs the selected audio data from the speaker 34 while hovering with the speaker 34 facing the intruder X. In other words, the unmanned aerial vehicle 3b outputs the warning indicated by the selected audio data from the speaker 34.

[0067] That is, in this example, for example, if the unmanned aerial vehicle 3b estimates that the intruder X is 18 years old, it outputs a warning indicated by audio data A from its own speaker 34; if the intruder X is estimated to be 51 years old, it outputs a warning indicated by audio data B; and if the intruder X is estimated to be 65 years old, it outputs a warning indicated by audio data C.

[0068] In this way, a warning is output using different audio features depending on the estimated age (generation) of intruder X, and the way of calling for the intruder to leave the work area 1 or surrender is changed. From an empirical and psychological perspective, the effectiveness of audio warnings is correlated between audio features and the age of the person being warned. Therefore, if an appropriate audio feature is assigned to each age group based on empirical rules and psychology, the warning can be more effective. Therefore, the defense system of the present invention can effectively defend the work area 1 (e.g., luggage, equipment, etc. placed there).

[0069] It is also preferable that the above-mentioned audio warning be repeatedly output to the intruder X. This is expected to provide a higher defensive effect.

[0070] When the management device 4 detects an intruder X, it may actually notify a security company or the police.

[0071] Although the embodiments of the defense system according to the present invention have been described above, the present invention is not limited to the above embodiments.

[0072] For example, in the above configuration, the unmanned aerial vehicles 3a and 3b may be controlled by the warning control unit 43 so that the unmanned aerial vehicle 3a detects the intruder X and outputs audio to the intruder X, and the unmanned aerial vehicle 3b photographs the intruder X.

[0073] In another example, only one unmanned aerial vehicle 3 (e.g., unmanned aerial vehicle 3a) may detect intruder X, photograph the intruder X, and output audio to the intruder X. In this case, when one unmanned aerial vehicle 3 detects intruder X with its own camera 33, it photographs the intruder X with its own camera 33, transmits the acquired facial image to the management device 4, and then, in response to receiving an audio output command together with audio data from the warning control unit 43, outputs an audio warning from its own speaker 34.

[0074] As shown in the example of Figure 7, three unmanned aerial vehicles 3a-3c may be provided, each with a different role. The additional unmanned aerial vehicle 3c may also have the configuration of Figures 2A and 2B. In this example, when unmanned aerial vehicle 3a detects intruder X with its camera 33, unmanned aerial vehicle 3c receives a movement command and a photographing command from the warning control unit 43, flies from its standby position to the intruder X, photographs the intruder X with its camera 33 as described above, and transmits the facial image of the intruder X to the management device 4. Unmanned aerial vehicle 3b outputs an audio warning as in the previous embodiment.

[0075] In another example, the intruder sensor is not provided on the unmanned aerial vehicle 3 but is installed in the work area 1 (for example, on its wall or ceiling). In this case, the intruder sensors may be multiple human presence sensors (such as infrared sensors) installed throughout the work area 1, and when at least one of them detects an intruder X, it transmits a detection signal to the management device 4. The warning control unit 43 (position identification unit 430) identifies the position of the intruder X based on this. Note that the intruder sensor installed in the work area 1 may be a camera. As in the other examples, the photographing of the intruder X and the audio output of a warning to the intruder X are performed by one or two unmanned aerial vehicles 3.

[0076] In the above embodiment, the audio storage medium 441 storing the audio data is provided in the management device 4, but instead, it may be provided in the unmanned aerial vehicle 3 that is responsible for outputting audio to the intruder X. In this case, the command unit 432 sends an audio output command along with information identifying the selected audio data to the unmanned aerial vehicle 3. Upon receiving the audio output command and the information, the unmanned aerial vehicle 3 outputs the selected audio data stored in its own audio storage medium from the speaker 34.

[0077] In yet another example, the audio storage medium 441 and audio selection unit 42 may be provided in the unmanned aerial vehicle 3 that is responsible for audio output. In this case, the command unit 432 sends an audio output command to the unmanned aerial vehicle 3 along with information indicating the estimated age. Upon receiving the audio output command and the information, the unmanned aerial vehicle 3 selects audio data to be output using its own audio selection unit, and outputs the selected audio data stored in its own audio storage medium from the speaker 34.

[0078] The age estimation unit 41 may detect a person (intruder X) from an image including the face of the person and estimate the age of the person using a known age estimation algorithm, without using artificial intelligence technology such as machine learning. [Explanation of symbols]

[0079] 1 working area 2 Work vehicles 3(3a, 3b, 3c) Unmanned aerial vehicle 33 Camera (as an intruder sensor or photographic device) 34 Speaker 4 Management device 41 Age Estimation Department 42 Audio selection section 43 Warning control section 4 Storage medium 441 Audio storage media X Intruder

Claims

1. one or more unmanned air vehicles configured to fly in a work area; an intruder sensor for detecting an intruder who has entered the work area; a photographing device provided on the unmanned aerial vehicle for photographing the face of the intruder; a speaker provided on the unmanned aerial vehicle for outputting sound; a voice storage medium storing a plurality of voice data items each showing a voice warning and each having different voice characteristics; an age estimation unit that estimates the age of a person based on a facial image of the person; an audio selection unit that selects audio data to be output from the plurality of audio data stored in the audio storage medium; a warning control unit that controls the operation of the unmanned aerial vehicle to issue a warning; When the intruder sensor detects an intruder, the warning control unit controls the unmanned aerial vehicle equipped with the photographing device to cause the photographing device to photograph the intruder and acquire a facial image of the intruder; the age estimation unit estimates the age of the intruder based on the acquired facial image of the intruder; the voice selection unit selects voice data to be output from the plurality of voice data stored in the voice storage medium based on the estimated age, When the intruder sensor detects the intruder, the warning control unit controls the unmanned aerial vehicle equipped with the speaker to cause the speaker to output the warning indicated by the audio data selected by the audio selection unit to the intruder. Defense system.

2. The audio data is provided for each category defined by age, the voice selection unit selects, as an output target, the voice data provided for the category corresponding to the age estimated by the age estimation unit. The defense system of claim 1 .

3. The plurality of pieces of voice data differ from each other in at least one of the voice characteristics: tone of voice, speech tone, and speaking rate. The defense system of claim 1 .

4. The age estimation unit inputs the acquired face image of the intruder into a trained model that estimates the age of a person from a face image of the person, and estimates the age of the intruder using an output from the trained model. The defense system of claim 1 .

5. The audio storage medium is provided on the unmanned aerial vehicle equipped with the speaker. The defense system of claim 1 .

6. The defense system includes, as the unmanned aerial vehicle: a first unmanned aerial vehicle equipped with the intruder sensor and the photographing device, the first unmanned aerial vehicle flying to detect the intruder and photograph the intruder; a second unmanned aerial vehicle equipped with the speaker, which, when the intruder sensor detects the intruder, flies toward the intruder to output audio to the intruder; The defense system of claim 1 .

7. The first unmanned aerial vehicle is equipped with a camera that functions as the intruder sensor and the photographing device. The defense system of claim 6.

8. The defense system includes, as the unmanned aerial vehicle: an unmanned aerial vehicle including the intruder sensor, the photographing device, and the speaker, the unmanned aerial vehicle being operation-controlled by the warning control unit to detect the intruder, photograph the intruder, and output audio to the intruder; The defense system of claim 1 .

9. The defense system includes, as the unmanned aerial vehicle: a first unmanned aerial vehicle equipped with the intruder sensor, the first unmanned aerial vehicle flying to detect the intruder; a second unmanned aerial vehicle equipped with the photographing device, which, when the intruder sensor detects the intruder, flies toward the intruder to photograph the intruder; a third unmanned aerial vehicle equipped with the speaker, which, when the intruder sensor detects the intruder, flies toward the intruder to output audio to the intruder; The defense system of claim 1 .

10. The intruder sensor is installed in the work area. The defense system of claim 1 .

Images