Fire-fighting robot and robot control method

Abstract

The present invention relates to a fire-fighting robot control method comprising the steps of: acquiring sensing data for determining the presence of a fire; analyzing the acquired sensing data, thereby preliminarily determining the presence of a fire; controlling the fire-fighting robot, thereby spraying a predetermined amount of fire extinguishing agents at a fire area when a fire is preliminarily determined during the preliminary determination; and analyzing changes in the sensing data according to the spray, thereby finally determining the presence of a fire.

Description

Fire fighting robot and robot control method

[0001] The present invention relates to a robot for determining whether there is a fire and for extinguishing the fire.

[0002] Working at fire scenes is extremely dangerous, with numerous hazards such as flames, toxic gases, and structural collapse. These risks can threaten the lives of firefighters and reduce work efficiency. Consequently, firefighting robots are emerging as a key alternative to ensure quick and safe work at fire scenes.

[0003] Firefighting robots are designed to ensure human safety and support firefighters in the event of a fire. They are equipped with a variety of equipment and functions to enable them to work safely at fire scenes.

[0004] If these fire-fighting robots become commercially available, they are expected to be able to respond quickly to fires, saving more lives and property.

[0005] However, several technical challenges remain before firefighting robots can be commercialized. The most critical of these is the ability to accurately assess a fire and respond quickly to the situation.

[0006] Robots may incorrectly detect fires, either recognizing non-fire situations as fires (false detections) or failing to recognize fires (non-detections), which may result in problems such as unnecessary spraying of extinguishing agents, incorrect spraying directions, and inappropriate selection of extinguishing agents.

[0007] These problems pose a risk of delaying fire suppression or causing secondary damage.

[0008] The present invention has been devised to solve the above-described problems, and one purpose of the present invention is to propose a fire handling robot capable of accurately determining whether there is a fire and responding to it, and a control method thereof.

[0009] The objectives of the present invention are not limited to those mentioned above. Other objectives and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objectives and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0010] In order to achieve the above-described object, a method for controlling a fire handling robot according to an embodiment of the present invention includes a step of acquiring sensing data for determining whether there is a fire, a step of analyzing the acquired sensing data to determine in advance whether there is a fire, a step of controlling the fire handling robot to spray a predetermined amount of fire extinguishing agent into a fire area if a fire is determined in advance in the pre-determination, and a step of analyzing a change in the sensing data according to the spray to make a final determination as to whether there is a fire.

[0011] And, the step of acquiring the sensing data may include at least one of a step of acquiring a real-image image captured by a real-image sensor unit, a step of acquiring a thermal image image from a thermal image sensor unit, and a step of acquiring flame detection data from a flame detection sensor.

[0012] And, the step of pre-judging whether there is a fire may include a first pre-judgment step of analyzing the real-world image and the thermal image using a learned first artificial neural network model to determine whether there is a fire, a second pre-judgment step of determining whether there is a fire using the flame detection data, and a step of pre-judgmenting whether there is a fire by synthesizing the first pre-judgment result and the second pre-judgment result.

[0013] In addition, the method may further include a step of analyzing the acquired sensing data to determine the type of fire.

[0014] In addition, the method may further include a step of determining the type and amount of the fire extinguishing agent according to the type of fire.

[0015] In addition, the step of analyzing the change in sensing data according to the above injection to make a final judgment on whether there is a fire can be determined using a second artificial neural network model that has learned the correlation between the temporal change amount of the real image and the thermal image and whether there is a fire.

[0016] And, if the final judgment result determines that there is a fire, the method may further include a step of controlling the fire handling robot to spray a fire extinguishing agent suitable for the type of fire.

[0017] Meanwhile, a fire handling robot according to an embodiment of the present invention for achieving the above-described purpose includes a sensor unit that acquires sensing data for determining whether there is a fire, analyzes the acquired sensing data to determine in advance whether there is a fire, controls the fire extinguishing unit to spray a predetermined amount of fire extinguishing agent into the fire area if the pre-determination determines that there is a fire, and analyzes changes in the sensing data according to the spraying to make a final determination as to whether there is a fire.

[0018] In addition, the sensor unit may include at least one of a real image sensor unit that acquires a real image, a thermal image sensor unit that acquires a thermal image, and a flame detection sensor unit that acquires flame detection data.

[0019] In addition, the data processing unit can perform a first pre-judgment operation of analyzing the real-world image and the thermal image using a learned first artificial neural network model to determine whether there is a fire, a second pre-judgment operation of determining whether there is a fire using the flame detection data, and an operation of pre-judgment of whether there is a fire by synthesizing the first pre-judgment result and the second pre-judgment result.

[0020] And, the data processing unit can analyze the acquired sensing data to determine the type of fire.

[0021] In addition, the data processing unit can determine the type and amount of the fire extinguishing agent according to the type of fire.

[0022] In addition, the data processing unit can determine whether there is a fire by using a second artificial neural network model that has learned the correlation between the temporal changes in the real-time image and the thermal image and the presence of a fire.

[0023] In addition, the data processing unit can control the fire extinguishing unit to spray a fire extinguishing agent suitable for the type of fire if the final judgment result determines that there is a fire.

[0024] Meanwhile, a computer program according to an embodiment of the present invention for achieving the above-described purpose may be stored in a computer-readable recording medium and include a program code for performing the above-described control method.

[0025] In addition, a computer-readable recording medium according to an embodiment of the present invention for achieving the above-described purpose may record a computer program for executing the above-described control method.

[0026] According to the present invention, the problem of a robot spraying a fire extinguishing agent in a non-fire situation can be solved by accurately judging and responding to the presence or absence of a fire, and in a fire situation, the robot can effectively extinguish the fire.

[0027] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0028] Figures 1 to 3 are conceptual diagrams showing a fire handling robot according to one embodiment of the present invention.

[0029] Figure 4 is a block diagram showing a fire handling robot according to one embodiment of the present invention.

[0030] Figure 5 is a flowchart showing a control method of a fire treatment robot according to one embodiment of the present invention.

[0031] FIG. 6 is a drawing showing a method for determining whether there is a fire in advance according to an embodiment of the present invention.

[0032] Figure 7 is a flowchart showing a control method of a fire treatment robot according to another embodiment of the present invention.

[0033] Figure 8 is a flowchart showing a control method of a fire treatment robot according to another embodiment of the present invention.

[0034] Figure 9 is a block diagram illustrating in detail a data processing unit according to one embodiment of the present invention.

[0035] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, devices, and / or systems described herein. However, these are merely examples and the present invention is not limited thereto.

[0036] In describing embodiments of the present invention, if a detailed description of a known technology related to the present invention is judged to unnecessarily obscure the gist of the present invention, the detailed description will be omitted. In addition, the terms described below are terms defined in consideration of their functions in the present invention, and this may vary depending on the intention or custom of the user or operator. Therefore, the definitions should be made based on the contents throughout this specification. The terminology used in the detailed description is only for the purpose of describing embodiments of the present invention and should not be limited in any way. Unless clearly used otherwise, the singular form includes the plural form. In this description, expressions such as "comprises" or "having" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, and should not be construed to exclude the presence or possibility of one or more other features, numbers, steps, operations, elements, parts or combinations thereof other than those described.

[0037] Additionally, in describing components of embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and the nature, order, or sequence of the components are not limited by the terms.

[0038]

[0039] Figures 1 to 3 are conceptual diagrams showing a fire handling robot according to one embodiment of the present invention.

[0040] Referring to FIGS. 1 to 3, in the present specification, the fire handling robot (100) may be implemented as a mobile robot, and the mobile robot is a general term for all types of robots equipped with a movement (i.e., driving) function. The mobile robot may include a ground robot equipped with a ground movement function and a drone equipped with an aerial movement function.

[0041] Additionally, the mobile robot may include a remote-controlled robot controlled by a remote control device (or system), an autonomous robot moving according to autonomous judgment, and a semi-autonomous robot equipped with both remote control and autonomous movement functions.

[0042] For example, a remote-controlled robot is a robot that is remotely controlled by a human operator via a remote control system. The remote control system can control a mobile robot located at a remote location by transmitting control values ​​(e.g., steering angle, speed) input by the human operator to the mobile robot in real time.

[0043] As another example, an autonomous robot may be a robot that autonomously drives remotely based on target control values, such as control values ​​generated by an autonomous driving module.

[0044] Meanwhile, the fire treatment robot (100) of the present invention may be provided with a function for judging whether there is a fire at a fire scene and extinguishing the fire in addition to the function of a mobile robot.

[0045] For example, a fire handling robot (100) may include a sensor unit (170) that collects sensing data to determine the fire situation at a fire scene (e.g., whether there is a fire, the type of fire, etc.) and a fire extinguisher (180) that sprays a fire extinguishing agent to extinguish the fire.

[0046] Here, the material stored in the fire extinguisher (180) can be of various types, such as a liquid type such as water, a solid type such as a fire extinguishing powder, or a gas type such as a fire extinguishing spray.

[0047] In addition, the fire extinguisher (180) may be of various types, such as a gas fire extinguisher type, a spray type, or a throwing type, depending on the fire extinguishing method.

[0048] For example, FIG. 1 is a fire treatment robot of a carry type that stores and moves a fire extinguisher (180) inside a translucent window of a fire treatment robot (100). The fire treatment robot (100) according to FIG. 1 can be used in a manner in which the robot autonomously determines and automatically sprays the extinguishing agent, or in a manner in which the user takes out the extinguishing agent stored in the robot (100) and then sprays the extinguishing agent of the extinguishing agent into the fire area.

[0049] As another example, FIG. 2 is an automatic type fire handling robot according to another embodiment of the present invention, and the fire handling robot (100) according to FIG. 2 can automatically spray a fire extinguishing agent by autonomously judging by the robot, and the nozzle angle can be adjusted in the up-and-down direction to effectively spray the fire extinguishing agent in the fire area.

[0050] As another example, FIG. 3 is an automatic fire handling robot according to another embodiment of the present invention, and the fire handling robot (100) according to FIG. 3 can spray a fire extinguishing agent automatically by making an autonomous judgment by the robot. In the case of FIG. 3(a), the robot can spray a fire extinguishing agent to a fire area while holding a fire extinguisher (180) with a robot arm equipped on the robot, and in the case of FIG. 3(b), the robot can spray a fire extinguishing agent to a fire area while wearing fire extinguishers (180) on both sides.

[0051] Additionally, the robot arm is designed to rotate in multiple axes, enabling flexible spraying of fire extinguishing agents even in complex fire scenes.

[0052] This fire handling robot (100) will be described in more detail with reference to FIG. 4.

[0053] Fig. 4 is a block diagram illustrating a fire handling robot according to an embodiment of the present invention. Referring to Fig. 4, the fire handling robot (100) may include a driving unit (110), a power supply unit (120), an output unit (130), an input unit (140), a communication unit (150), a storage unit (160), a sensor unit (170), a fire extinguisher (180), and a data processing unit (190).

[0054] The driving unit (110) can provide driving force for movement (driving) of the fire treatment robot (100). For example, the driving unit (110) can include a motor, a gear assembly, etc.

[0055] Additionally, the drive unit (110) may include a function that automatically switches between various modes (e.g., high-speed driving, precision driving) to optimize driving according to terrain. This allows the robot to move smoothly according to the terrain of the fire scene and maintain stability even in unstable environments.

[0056] The power supply unit (120) supplies power for the operation of the fire handling robot (100). Specifically, the power supply unit (120) supplies power to each functional unit constituting the fire handling robot (100), and when the remaining power is insufficient, the robot can be charged by receiving charging current. Here, the power supply unit (120) can be implemented as a rechargeable battery.

[0057] The output unit (130) displays visual data or outputs auditory data, and the output unit (130) can be implemented as a display unit formed on the front of a speaker processing robot (100), for example.

[0058] In addition, the output unit (130) provides a function for monitoring the status of the robot and the fire suppression status in real time, and can generate an alarm sound when a dangerous situation occurs (e.g., fire occurs, battery is low, fire extinguishing agent is low, etc.).

[0059] The input unit (140) can receive user input for operating the fire treatment robot (100). For example, the input unit (140) can include a touch sensor that detects a user's touch input.

[0060] The communication unit (150) may include one or more modules that enable the fire treatment robot (100) to communicate with other devices (e.g., a remote control system, a server, another robot, etc.).

[0061] The storage unit (160) can store programs and map data for the operation of the fire treatment robot (100).

[0062] The sensor unit (170) can obtain sensing data for determining whether there is a fire. Here, the sensor unit (170) can include a real-image sensor unit (not shown) that captures real-image images and a thermal image sensor unit (not shown) that obtains thermal images.

[0063] For example, the real-time image sensor unit (not shown) can be implemented with an RGB camera, and the thermal image sensor unit (not shown) can be implemented with an infrared (infra-red) camera.

[0064] Additionally, the sensor unit (170) may further include a flame detection sensor that detects flames based on an infrared sensor. In this case, the flame detection sensor may be distinguished from the thermal imaging sensor unit in that it does not capture images.

[0065] Additionally, the sensor unit (170) may include a hazardous gas detection sensor and may detect toxic gases generated at a fire scene.

[0066] Meanwhile, the fire extinguisher (180) stores a fire extinguishing agent to extinguish a fire, and can spray the fire extinguishing agent into the fire area under the control of the data processing unit (190).

[0067] The data processing unit (190) performs preliminary and final judgments on whether there is a fire based on the sensing data collected from the sensor unit (170), and if a fire is finally determined, the fire extinguisher (180) can be controlled to spray a fire extinguishing agent into the fire area.

[0068] The operation of this data processing unit (190) will be described in more detail later with reference to the drawings.

[0069]

[0070] Figure 5 is a flowchart showing a control method of a fire treatment robot according to one embodiment of the present invention.

[0071] Referring to FIG. 5, the sensor unit (170) of the fire handling robot (100) can acquire sensing data for determining whether a fire has occurred (S110). At this time, the sensing data may include at least one of a visual image, a thermal image, and flame detection data.

[0072] In addition, the data processing unit (190) can analyze the acquired sensing data to determine in advance whether there is a fire (S120).

[0073] Here, the step (S120) for pre-judging whether there is a fire may include a first pre-judgment step for analyzing a real-world image and a thermal image using a learned first artificial neural network model to determine whether there is a fire, a second pre-judgment step for determining whether there is a fire using flame detection data, and a step for pre-judgment whether there is a fire by synthesizing the first pre-judgment result and the second pre-judgment result.

[0074] For example, referring to FIG. 6, for the first pre-judgment step, the data processing unit (190) can estimate whether there is a fire using an artificial neural network model modeled by learning the correlation between "real-time images and thermal images" and "whether there is a fire." Here, an example of the artificial neural network model may be a CNN (Convolution Neural Network).

[0075] In the first pre-judgment step of the data processing unit (190) described above, data obtained from a visual (RGB) and infrared (IR) camera can be processed using an architecture called YoloX, and this system operates at a speed of about 15 frames per second (FPS) and can be specialized in detecting fire or flames. At this time, fire detection is possible within a maximum distance of 2 m, flame detection can be performed within 50 cm, and the detection method accurately detects fire and flames by utilizing CNN. This process is run on the PyTorch framework, and hardware called AGX can be used.

[0076] In addition, in the second pre-judgment stage of the data processing unit (190), a flame detection sensor can be used to detect flames and fires, and this system operates on AGX hardware and the PyTorch framework, and fires can be detected at a maximum distance of 50 m, and flames can be detected within 5 m. In addition, it is sensitive even at a distance of 3 cm when detecting fire, and can detect small fires within a range of 16 cm, and the method can operate based on a flame sensor.

[0077] In addition, the data processing unit (190) can assign reliability weights to each of the judgment results of the first pre-judgment stage and the second pre-judgment stage, and can pre-judge whether there is a fire based on the assigned reliability weights.

[0078] In addition, the data processing unit (190) can analyze the acquired sensing data to determine in advance whether there is a fire (S130).

[0079] Meanwhile, if a fire is preliminarily determined through the aforementioned preliminary judgment, the data processing unit (190) can control the fire extinguisher (180) to spray a predetermined amount of extinguishing agent into the fire area (S140). At this time, the predetermined amount of extinguishing agent to be sprayed is sufficient to lower the temperature of the fire.

[0080] In addition, the data processing unit (190) can analyze the change in sensing data of the sensor unit (170) according to the spraying of the fire extinguishing agent to make a final judgment on whether there is a fire (S150).

[0081] Specifically, in order to make a final judgment on whether there is a fire, the data processing unit (190) can make a final judgment on whether there is a fire by using an artificial neural network model modeled by learning the correlation between “the change value over time of at least one of the real-time image, the thermal image, and the flame detection data and the amount of extinguishing agent sprayed” and “whether there is a fire.”

[0082] For example, the data processing unit (190) can analyze the temporal change in sensing data according to the amount of fire extinguishing agent sprayed to make a final judgment on whether or not there is a fire.

[0083] If the final judgment result is a fire, the data processing unit (190) can control the fire extinguisher to spray a fire extinguishing agent to extinguish the fire.

[0084]

[0085] Figure 7 is a flowchart showing a control method of a fire treatment robot according to another embodiment of the present invention.

[0086] In explaining Fig. 7, detailed descriptions of parts overlapping with Fig. 5 will be omitted.

[0087] Referring to Fig. 7, the sensor unit (170) of the fire handling robot (100) can obtain sensing data for determining whether there is a fire (S210).

[0088] In addition, the data processing unit (190) can analyze the acquired sensing data to determine in advance whether there is a fire (S220).

[0089] In addition, the data processing unit (190) can analyze the acquired sensing data to determine the type of fire in advance (S230).

[0090] Specifically, because appropriate fire suppression methods vary depending on the type of fire, it's important to determine the type of fire in advance. These fires can range from solid-material fires, oil fires, gas fires, metal fires, kitchen and vegetable oil fires, and electrical fires.

[0091] At this time, the temperature range may vary depending on the type of fire, for example, a solid fire may be over 500 degrees, an oil fire may be over 700 degrees, and a gas fire may be over 1000 degrees.

[0092] Accordingly, the data processing unit (190) can estimate whether there is a fire by using an artificial neural network model modeled by learning the correlation between “real-time image and thermal image” and “type of fire.”

[0093] In addition, the data processing unit (190) can analyze the acquired sensing data to determine in advance whether there is a fire (S240).

[0094] In addition, the data processing unit (190) can determine the type of extinguishing agent and the amount of extinguishing agent to be sprayed depending on the type of fire (S250). For example, in the case of a solid material fire, a method of extinguishing the fire using water may be appropriate, in the case of an oil fire, a method of extinguishing the fire using a foam extinguishing agent, CO2 gas extinguishing agent, or foam extinguishing agent may be appropriate, and in the case of a metal fire, a method of extinguishing the fire using metal powder may be appropriate.

[0095] Accordingly, the data processing unit (190) can determine the type of fire extinguishing agent according to the type of fire, and determine the amount of fire extinguishing agent to be sprayed as the minimum amount that can lower the temperature of the fire.

[0096] And, the data processing unit (190) can control the fire extinguisher (180) to spray a predetermined amount of fire extinguishing agent into the fire area (S260).

[0097] In addition, the data processing unit (190) can analyze the change in sensing data of the sensor unit (170) according to the spraying of the fire extinguishing agent to make a final judgment on whether there is a fire (S270).

[0098] According to the present invention, the problem of a robot spraying a fire extinguishing agent in a non-fire situation can be solved by accurately judging and responding to the presence or absence of a fire, and the fire can be effectively extinguished in a fire situation.

[0099]

[0100] Figure 8 is a flowchart showing a control method of a fire treatment robot according to another embodiment of the present invention.

[0101] In explaining Fig. 8, detailed descriptions of parts overlapping with Fig. 5 or Fig. 6 will be omitted.

[0102] Referring to FIG. 8, the sensor unit (170) of the fire handling robot (100) obtains sensing data for determining whether there is a fire (S1100), and the data processing unit (190) analyzes the obtained sensing data to determine in advance whether there is a fire (S1200) and the type of fire (S1300).

[0103] In addition, the data processing unit (190) analyzes the acquired sensing data to determine in advance whether there is a fire, and if it is determined in advance that a fire has occurred (S1400, YES), the type of fire extinguishing agent and the amount of fire extinguishing agent to be sprayed can be determined according to the type of fire (S1500).

[0104] Next, the data processing unit (190) can request cooperation from other adjacent fire treatment robots (100) depending on the type of fire and the amount of extinguishing agent sprayed (S1600).

[0105] Specifically, the data processing unit (190) comprehensively considers the remaining amount of extinguishing agent of the current fire treatment robot (100), the range of fire that can be treated, etc., and if it is determined that it is difficult to extinguish the fire with the current fire treatment robot (100), it may request cooperation from another adjacent fire treatment robot (100).

[0106] For example, when a fire is large in scale or complex and a single fire handling robot (100) does not have enough fire extinguishing agents, when a different type of fire extinguishing agent is required for a specific fire or when two or more fire extinguishing agents must be used in parallel, or when the fire area is large and it is difficult to cover the fire extinguishing range with a single fire handling robot (100), the data processing unit (190) may request collaboration with another adjacent fire handling robot (100).

[0107] In addition, when collaboration is determined to be necessary, the data processing unit (190) may request collaboration from a fire handling robot (100) located close to the current location, as well as request collaboration from a fire handling robot (100) most suitable for the current fire. In this case, the most suitable fire handling robot (100) refers to a robot capable of effectively extinguishing a fire.

[0108] For example, if fire treatment robot A is deployed in an area where an electrical fire has occurred and it is determined that there is not enough CO2 extinguishing agent, the data processing unit (190) of fire treatment robot A can request collaboration with an adjacent robot B that has sufficient CO2 extinguishing agent.

[0109] As another example, if fire handling robot B is located closest to the scene of a fire but does not have enough extinguishing agent remaining and its battery is low, the data processing unit (190) of fire handling robot A can request collaboration from fire handling robot C, which has enough extinguishing agent remaining and its battery is sufficiently charged.

[0110] That is, the data processing unit (190) can request collaboration from a fire handling robot (100) capable of effectively extinguishing a fire by comprehensively considering the type of fire extinguishing agent, resource status (fire extinguishing agent and battery), current work situation, location, etc. according to the characteristics of the fire.

[0111] Next, the data processing unit (190) can produce a work plan for fire suppression with another adjacent fire treatment robot (100) (S1700).

[0112] Specifically, the data processing unit (190) can comprehensively consider the current location, type and remaining amount of extinguishing agent, battery status, and current work status of other fire handling robots (100) that have accepted the collaboration request to derive a work plan for fire suppression. Here, the work plan includes data on the operations of multiple fire handling robots (100) for fire suppression, and the work plan may include work division, work path, resource management, etc. among the fire handling robots (100), and may include a flexible role transition plan to ensure continuity of fire suppression work without work interruption.

[0113] And, the data processing unit (190) sprays a predetermined amount of fire extinguishing agent into the fire area together with another fire treatment robot (100) according to the generated work plan (S1800), and the data processing unit (190) analyzes the change in sensing data of the sensor unit (170) according to the spraying of the fire extinguishing agent to make a final judgment on whether there is a fire (S1900).

[0114] In this way, when a plurality of fire-fighting robots cooperate to simultaneously suppress fires in multiple areas, the fire suppression time can be shortened compared to when a single robot handles all areas.

[0115] In addition, the present invention efficiently distributes resources by considering the remaining amount of fire extinguishing agent or battery status of each robot through collaboration, thereby preventing situations where work is interrupted due to lack of fire extinguishing agent or battery, and can achieve maximum suppression effect.

[0116] This data processing unit (1900) will be described in more detail with reference to FIG. 9.

[0117] Figure 9 is a block diagram showing a data processing unit according to one embodiment of the present invention.

[0118] Referring to FIG. 9, the data processing unit (190) may be implemented as a computing device. One or more of each module constituting the computing device according to an embodiment of the present invention is implemented on a general-purpose computing processor and thus may include a processor (308), an input / output I / O (302), a memory (340), an interface (306), and a bus (314). The processor (308), the input / output device (302), the memory (304), and / or the interface (306) may be coupled to each other via the bus (314). The bus (314) corresponds to a path through which data is moved.

[0119] Specifically, the processor (308) may include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphics Processing Unit), a microprocessor, a digital signal processor, a microcontroller, an application processor (AP), and logic elements capable of performing functions similar thereto.

[0120] The input / output device (302) may include at least one of a keypad, a keyboard, a touchscreen, and a display device. The memory device (304) may store data and / or programs, etc.

[0121] The interface (306) may perform a function of transmitting data to or receiving data from a communication network. The interface (306) may be wired or wireless. For example, the interface (306) may include an antenna or a wired / wireless transceiver. The memory (304) may further include high-speed DRAM and / or SRAM, etc., as a volatile operating memory that enhances the operation of the processor (308) while protecting personal information.

[0122] Additionally, the memory (304) stores programming and data configurations that provide the functionality of some or all of the modules described herein. For example, it may include logic for performing selected aspects of the learning method described above.

[0123] A program or application is loaded as a set of instructions including each step of performing the above-described acquisition method stored in memory (304) and causes the processor to perform each step.

[0124] Furthermore, the various embodiments described herein may be implemented in a recording medium readable by a computer or similar device, for example, using software, hardware, or a combination thereof.

[0125] In terms of hardware implementation, the embodiments described herein can be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, micro-controllers, microprocessors, and other electrical units for performing functions. In some cases, the embodiments described herein can be implemented as a control module itself.

[0126] In a software implementation, the procedures and functions described herein, as well as other embodiments, may be implemented as separate software modules. Each of these software modules may perform one or more of the functions and operations described herein. The software code may be implemented as a software application written in a suitable programming language. The software code may be stored in a memory module and executed by a control module.

[0127]

[0128] Meanwhile, the methods according to the various embodiments of the present invention described above can be implemented as programs and provided to servers or devices. Accordingly, each device can access the server or device where the program is stored and download the program.

[0129] In addition, the methods according to the various embodiments of the present invention described above may be implemented as programs and stored and provided on various non-transitory computer-readable media. A non-transitory computer-readable medium refers to a medium that permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the various applications or programs described above may be stored and provided on non-transitory computer-readable media, such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM.

[0130] While various embodiments of the present invention have been described in detail above, those skilled in the art will appreciate that various modifications to the above-described embodiments are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined not only by the claims set forth below but also by equivalents thereof.

Claims

1. In a control method of a fire handling robot, A step of acquiring sensing data for determining whether there is a fire; A step of analyzing the acquired sensing data to determine in advance whether there is a fire; In the case where a fire is determined in advance through the above preliminary judgment, a step of controlling the fire treatment robot to spray a predetermined amount of fire extinguishing agent into the fire area; and A control method for a fire handling robot, comprising: a step of analyzing changes in sensing data according to the above injection to make a final judgment on whether or not there is a fire; 2. In paragraph 1, The step of acquiring the above sensing data is: A step of acquiring a real-time image captured by a real-time sensor unit; A step of acquiring a thermal image from a thermal imaging sensor unit; and A method for controlling a fire treatment robot, characterized in that it comprises at least one of the steps of: obtaining flame detection data from a flame detection sensor; 3. In paragraph 2, The step of pre-determining whether there is a fire is as follows: A first preliminary judgment step of analyzing the real-world image and the thermal image using the learned first artificial neural network model to determine whether there is a fire; A second pre-judgment step for determining whether there is a fire using the above flame detection data; and A control method for a fire handling robot, characterized in that it includes a step of pre-judging whether there is a fire by synthesizing the first pre-judgment result and the second pre-judgment result.

4. In paragraph 1, A control method for a fire handling robot, characterized in that it further includes a step of analyzing the acquired sensing data to determine the type of fire.

5. In paragraph 4, A control method for a fire handling robot, characterized in that it further includes a step of determining the type and the predetermined amount of the fire extinguishing agent according to the type of the fire.

6. In paragraph 2, The step of analyzing the changes in sensing data according to the above injection to make a final judgment on whether there is a fire is as follows: A control method for a fire handling robot, characterized in that the presence or absence of a fire is determined using a second artificial neural network model in which the relationship between the temporal changes in the above-mentioned real-world image and the above-mentioned thermal image and the presence or absence of a fire is learned.

7. In paragraph 1, A method for controlling a fire handling robot, characterized in that it further includes a step of controlling the fire handling robot to spray a fire extinguishing agent suitable for the type of fire if the final judgment result determines that there is a fire.

8. In fire fighting robots, A sensor unit that acquires sensing data for determining whether there is a fire; and A fire handling robot comprising a data processing unit that analyzes the acquired sensing data to determine in advance whether there is a fire, controls the fire extinguishing unit to spray a predetermined amount of extinguishing agent into the fire area if the preliminary determination determines that there is a fire, and analyzes changes in the sensing data according to the spraying to make a final determination as to whether there is a fire.

9. In paragraph 8, The above sensor part, A real-time image sensor unit that acquires real-time images; A thermal imaging sensor unit for acquiring a thermal image; and A fire handling robot characterized by including at least one of a flame detection sensor unit for acquiring flame detection data.

10. In paragraph 9, The above data processing unit, A first pre-judgment operation for analyzing the above-mentioned real-world image and the above-mentioned thermal image using a learned first artificial neural network model to determine whether there is a fire; A second pre-judgment operation for determining whether there is a fire using the above flame detection data; and A fire handling robot characterized in that it performs an operation for pre-judging whether there is a fire by synthesizing the first pre-judgment result and the second pre-judgment result.

11. In paragraph 8, The above data processing unit, A fire handling robot characterized in that it analyzes the acquired sensing data to determine the type of fire.

12. In paragraph 11, The above data processing unit, A fire handling robot characterized in that the type and amount of the fire extinguishing agent are determined according to the type of fire.

13. In paragraph 9, The above data processing unit, A fire handling robot characterized in that it determines whether there is a fire using a second artificial neural network model in which the correlation between the temporal changes in the above real-time image and the above thermal image and the presence of a fire is learned.

14. In paragraph 1, The above data processing unit, A fire handling robot characterized in that, if the final judgment result determines that there is a fire, the fire extinguishing unit is controlled to spray a fire extinguishing agent suitable for the type of fire.

15. A computer program stored in a computer-readable recording medium and including a program code for performing a control method of a fire treatment robot described in any one of claims 1 to 7.

16. A computer-readable recording medium having recorded thereon a computer program for executing a control method of a fire treatment robot described in any one of paragraphs 1 to 7.

Images