Work Support System

The work support system uses a mobile robot to guide workers to camera lenses with dirty lenses, addressing route uncertainty and construction obstacles, ensuring efficient and timely cleaning.

JP7595816B2Active Publication Date: 2024-12-06MITSUBISHI ELECTRIC BUILDING SOLUTIONS CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2024540225
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-08-12
Publication Date
2024-12-06
Estimated Expiration
2042-08-12

AI Technical Summary

Technical Problem

Workers cleaning camera lenses in buildings face challenges when they are unaware of the travel route to the camera installation location or cannot follow known routes due to unknown construction, leading to significant time delays in reaching the camera for cleaning.

Method used

A work support system utilizing a mobile robot that autonomously moves within a building, guided by a server, to locate and guide workers to camera installation positions with dirty lenses, optimizing movement routes based on camera information and building maps.

Benefits of technology

Enables workers to quickly reach and clean camera lenses by following the mobile robot, reducing time and effort, even in unfamiliar environments, while minimizing server management load and ensuring efficient cleaning operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007595816000001
    Figure 0007595816000001
  • Figure 0007595816000002
    Figure 0007595816000002
  • Figure 0007595816000003
    Figure 0007595816000003
Patent Text Reader

Abstract

The present invention provides a work assisting system for a worker (50) to clean lens smudges of a camera (40) installed in a building, the work assisting system comprising: a server (10) that executes smudge detection processing of detecting the lens smudges on the basis of imaging data captured by the camera (40); and a robot (20) configured to travel autonomously inside the building. The robot (20) is configured to follow a first instruction given by the worker (50) to acquire, from the server (10), camera information that identifies the camera (40) having the detected lens smudges and to guide the worker (50) to the installation position of the camera (40) identified by the acquired camera information.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a work support system, and more particularly to a work support system that enables workers to clean dirt off the lenses of cameras installed in buildings. [Background technology]

[0002] Japanese Patent Laid-Open Publication No. 2017-212596 (Patent Document 1) discloses a camera maintenance support device capable of supporting the maintenance of a camera device installed in a remote location. This maintenance support device determines an inspection level indicating the degree of necessity for inspection of the camera device based on information acquired from the camera device, and notifies the user of the determination result in a manner according to the inspection level (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-212596 A Summary of the Invention [Problem to be solved by the invention]

[0004] In buildings such as shopping malls, when dirt is detected on the lens of an installed camera (such as a security camera), workers generally clean the lens. However, if the worker does not know the route to the camera's installation location, or if the worker is unable to follow the known route due to unknown construction work, it takes a considerable amount of time for the worker to move to the camera's installation location where the lens dirt was detected.

[0005] The present disclosure has been made to solve such problems, and a purpose of the present disclosure is to provide a work support system that supports a worker cleaning a camera where lens dirt has been detected, by quickly moving to the installation location of the camera and performing the work of cleaning the camera. [Means for solving the problem]

[0006] The work support system disclosed herein is a work support system for a worker to clean lens dirt of a camera installed in a building, and includes a server that executes a dirt detection process to detect lens dirt based on image data captured by the camera, and a mobile robot configured to be able to move autonomously within the building. In accordance with a first instruction from the worker, the mobile robot acquires from the server camera information that identifies a camera in which lens dirt has been detected by the dirt detection process, and moves to the installation position of the camera identified by the acquired camera information, thereby guiding the worker to the installation position of the camera in which lens dirt has been detected.

[0007] With the above-mentioned configuration, a mobile robot capable of autonomously moving within a building can be used to guide a worker to the installation location of a camera where lens dirt has been detected. Therefore, even if the worker does not know the movement route to the installation location of the camera to be cleaned or the worker cannot follow the known movement route due to unknown construction work, the worker can quickly move to the installation location of the camera to be cleaned by moving within the building following the mobile robot. Effect of the Invention

[0008] According to the work assistance system of the present disclosure, a worker responsible for cleaning a camera for which lens dirt has been detected can quickly move to the installation location of the camera and perform the task of cleaning the lens of the camera. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing an overall configuration of a work support system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating a hardware configuration of a server illustrated in FIG. [Diagram 3] FIG. 2 is a block diagram functionally showing the configuration of a server. [Figure 4]10 is a flowchart illustrating an example of a procedure of a dirt detection process executed by a dirt detection unit. [Diagram 5] 4 is a diagram showing an example of a data structure of camera information stored in a camera information DB; FIG. [Figure 6] FIG. 2 is a diagram illustrating a hardware configuration of the robot illustrated in FIG. [Figure 7] FIG. 2 is a block diagram showing the functional configuration of the robot. [Figure 8] 11 is a first flowchart illustrating an example of a processing flow in a server and a robot together with an operation by a worker. [Figure 9] 13 is a second flowchart illustrating an example of a processing flow in the server and the robot together with an operation by a worker. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are designated by the same reference characters and their description will not be repeated.

[0011] Fig. 1 is a diagram showing an overall configuration of a work support system according to an embodiment of the present disclosure. With reference to Fig. 1, the work support system includes a server 10 and a mobile robot 20. In the following, the server 10 may be referred to as a "center," and the mobile robot 20 may be referred to simply as a "robot 20."

[0012] This work support system is a system for supporting workers who clean dirt from the lenses of cameras installed in a building. For example, in a building such as a shopping mall, a plurality of cameras 40 are installed on a floor 30. Each camera 40 is, for example, a security camera, and in this example, five cameras 40-1 to 40-5 are installed on the ceiling or the like of the floor 30. In the following, the cameras 40-1 to 40-5 may be collectively referred to as "camera 40".

[0013] Server 10 is configured to be able to communicate with camera 40, and acquires imaging data captured by camera 40 from camera 40. Then, server 10 executes a dirt detection process (described in detail below) for detecting dirt on the lens of camera 40, based on the imaging data acquired from camera 40.

[0014] The robot 20 is a self-propelled mobile robot that can autonomously move around the floor 30 using map information (floor map). The robot 20 is equipped with a camera that can capture images of its surroundings, and can move around the floor 30 while recognizing its current position on the floor 30 based on the images captured by the camera.

[0015] The server 10 and the robot 20 are configured to be able to communicate with each other. A worker 50 is a cleaner who cleans the camera 40 in which lens dirt has been detected. The worker 50 can inquire of the server 10 through the robot 20 about the camera 40 in which lens dirt has been detected. In response to the inquiry from the robot 20, the server 10 transmits information about the camera 40 in which lens dirt has been detected (including the floor number, camera number, etc., hereinafter also referred to as "camera information") to the robot 20.

[0016] If a camera 40 is found to have dirty lenses, the worker 50 moves to the location where the camera is installed and cleans the lens. However, if the worker 50 does not know the route to the location where the camera to be cleaned is installed, or if the worker 50 is unable to follow the known route due to unknown construction or the like, it will take a considerable amount of time for the worker 50 to move to the location where the camera 40 is found to have dirty lenses.

[0017] Therefore, in the work support system according to the present embodiment, the robot 20 guides the worker 50 to the installation location of the camera 40 where the lens dirt has been detected. The robot 20, for example, normally automatically patrols the floor 30, and when it receives camera information from the server 10 in response to an input operation of the worker 50 to the robot 20, it guides the worker 50 to the installation location of the camera 40 where the lens dirt has been detected according to the camera information.

[0018] After the worker 50 has completed the cleaning work of the camera 40, in response to an input operation of the worker 50 to the robot 20 indicating completion of the work, the robot 20 transmits work completion information indicating the completion of the cleaning work of the camera 40 to the server 10. Upon receiving the work completion information from the robot 20, the server 10 executes a dirt detection process for the camera 40 indicated by the work completion information, and transmits the detection result of the dirt on the lens to the robot 20. Based on this detection result, the worker 50 can also perform more thorough cleaning of the lens.

[0019] In addition, in this work support system, when the camera information acquired by the robot 20 from the server 10 includes information on multiple cameras 40, i.e., when there are multiple cameras 40 in which lens dirt has been detected, the robot 20 determines a movement route that optimizes movement efficiency when moving sequentially to the multiple cameras 40. Then, the robot 20 guides the worker 50 sequentially to the installation locations of the multiple cameras 40 in which lens dirt has been detected, according to the movement route. The configurations of the server 10 and the robot 20 constituting the work support system will be described in detail below.

[0020] Fig. 2 is a diagram showing a hardware configuration of the server 10 shown in Fig. 1. Referring to Fig. 2, the server 10 includes a CPU (Central Processing Unit) 61, a RAM (Random Access Memory) 62, a ROM (Read Only Memory) 63, a communication device 64, and a storage device 65. The CPU 61, the RAM 62, the ROM 63, the communication device 64, and the storage device 65 can exchange various data through a communication bus 66.

[0021] The CPU 61 loads a program stored in the ROM 63 into the RAM 62 and executes it. The program stored in the ROM 63 describes various processes to be executed in the server 10. The communication device 64 is an input / output device for exchanging various data and signals with the camera 40 and the robot 20 using a known wireless or wired communication method.

[0022] The memory device 65 is a storage for storing various information, and stores information on each camera 40 that is the subject of cleaning management by the worker 50, information on the robot 20 that is the subject of management, etc. The memory device 65 does not store position information on the cameras 40 and the robot 20. In this embodiment, the position information of the cameras 40 and the robot 20 is stored in the robot 20. The memory device 65 is, for example, a hard disk drive (HDD: Hard Disk Drive) or a solid state drive (SSD: Solid State Drive), etc.

[0023] Fig. 3 is a block diagram functionally showing a configuration of server 10. Referring to Fig. 3, server 10 includes an imaging data acquisition unit 71, a dirt detection unit 72, a camera information database (DB) 73, a communication unit 74, and a processing unit 75.

[0024] The imaging data acquisition unit 71 acquires imaging data captured by the cameras 40 from the cameras 40 through the communication unit 74. The imaging data acquisition unit 71 may accumulate the acquired imaging data in an image DB (not shown) for a predetermined period (e.g., one week or one month). The dirt detection unit 72 detects dirt on the lens of the cameras 40 based on the imaging data acquired by the imaging data acquisition unit 71 for each camera 40.

[0025] 4 is a flowchart illustrating an example of the procedure of a dirt detection process executed by the dirt detection unit 72. The process shown in this flowchart is periodically executed for each camera 40. The process for any one of the cameras 40 will be described below.

[0026] 4, the dirt detection unit 72 acquires the imaging data acquired by the imaging data acquisition unit 71 (step S10). Next, the dirt detection unit 72 acquires a corresponding reference image for the camera 40 from the camera information DB 73 (described later) (step S20).

[0027] This reference image is an image for comparing with the imaging data acquired in step S10 to check whether lens dirt is reflected in the imaging data, and is captured in advance for each camera 40 and stored in the camera information DB 73. In order to accurately extract lens dirt by comparing with the imaging data, it is preferable to use a reference image captured in an environment as similar as possible to the imaging data, and a plurality of reference images are prepared that are captured under various seasons, times of day, weather conditions, etc., without lens dirt. Then, the dirt detection unit 72 acquires from the camera information DB 73 a reference image that is close to the conditions when the imaging data acquisition unit 71 acquired the imaging data.

[0028] Next, the dirt detection unit 72 extracts the difference between the imaging data acquired in step S10 and the reference image acquired in step S20 (step S30). More specifically, the dirt detection unit 72 calculates the difference for each pixel between the imaging data and the reference image. Then, the dirt detection unit 72 calculates the average value of the differences for each pixel between the imaging data and the reference image (step S40).

[0029] Next, the dirt detection unit 72 determines whether the average value of the differences between the pixels calculated in step S40 is greater than a predetermined threshold value (step S50). This threshold value determines how much lens dirt is acceptable, and is appropriately set by a prior evaluation test or the like.

[0030] If it is determined in step S50 that the average value of the differences between the pixels is greater than the threshold value (YES in step S50), the dirt detection unit 72 determines that lens dirt has occurred in the camera 40 corresponding to the imaging data acquired in step S10 (step S60). Note that if it is determined in step S50 that the average value of the differences between the pixels is equal to or less than the threshold value (NO in step S50), the process of step S60 is not executed, and it is determined that no lens dirt has occurred.

[0031] 3, the camera information DB 73 stores information on each camera 40 that is the target of cleaning management by the worker 50. The camera information DB 73 also stores the detection result of the lens dirt of each camera 40 by the dirt detection unit 72.

[0032] Fig. 5 is a diagram showing an example of a data structure of camera information stored in camera information DB 73. Referring to Fig. 5, camera information 80 includes information such as "Building No.", "Floor No.", "Camera No.", "Reference Image", "Stain Information", and "Detection Date and Time".

[0033] This work support system manages multiple cameras installed in multiple buildings, and "Building No." indicates the identification number of the building managed by the work support system. "Floor No." indicates the floor in each building.

[0034] "Camera No." indicates an identification number of each camera 40. The camera 40 is identified in the work support system by this camera No. As described above, the "reference image" is imaging data captured when the lens is clean, and is prepared and stored in advance for each camera 40. Note that, as described above, the reference image may include multiple images captured for each camera 40 under various seasons, times of day, weather conditions, etc.

[0035] "Dirt information" indicates the result of detection of lens dirt by dirt detection unit 72. Dirt information "present" indicates that lens dirt has been detected by dirt detection unit 72. Note that, as described below, after the lens cleaning work is performed by worker 50, the dirt information "present" is maintained until it is determined that no lens dirt has occurred by a dirt detection process performed again by dirt detection unit 72.

[0036] The "detection date and time" indicates the date and time when the dirt on the lens was detected by the dirt detection unit 72. Note that in this example, if the dirt detection unit 72 performs the dirt detection process again and determines that there is no dirt on the lens, the information on the detection date and time is deleted.

[0037] Although the camera information DB 73 stores information for identifying each camera 40 (building number, floor number, camera number), it does not store position information of the camera 40. The position information of the camera 40 is managed in the robot 20 together with map information of the floor 30 (floor map).

[0038] 3, the communication unit 74 receives imaging data from each camera 40, and outputs the received imaging data to the imaging data acquisition unit 71. The communication unit 74 is also configured to be able to communicate with the robot 20, and exchanges various signals with the robot 20.

[0039] The processing unit 75 executes various processes other than the dirt detection process by the dirt detection unit 72. For example, in response to an inquiry received from the robot 20 through the communication unit 74, the processing unit 75 searches for cameras 40 on which lens dirt has been detected by the dirt detection unit 72 on floors patrolled by the robot 20 according to the "dirt information" in the camera information DB 73. Then, the processing unit 75 transmits camera information (floor number, camera number, etc.) specifying the camera 40 on which lens dirt has been detected to the robot 20 through the communication unit 74.

[0040] Furthermore, when the processing unit 75 receives work completion information indicating the completion of the cleaning work of the camera 40 by the worker 50 from the robot 20 through the communication unit 74, the processing unit 75 outputs an instruction to the dirt detection unit 72 to execute the dirt detection process again based on the imaging data acquired from the camera 40 for which the cleaning work has been completed. Then, the processing unit 75 controls the communication unit 74 to transmit the determination result of the dirt detection again by the dirt detection unit 72 to the robot 20. Note that, when the dirt detection unit 72 determines that there is no dirt on the lens, the processing unit 75 rewrites the dirt information for the camera 40 in the camera information DB 73 from "present" to "absent."

[0041] Fig. 6 is a diagram showing a hardware configuration of the robot 20 shown in Fig. 1. Referring to Fig. 6, the robot 20 includes a CPU 101, a RAM 102, a ROM 103, a communication device 104, a storage device 105, a driving device 106, a battery 107, an I / F device 108, and a camera 109. The CPU 101, the RAM 102, the ROM 103, the communication device 104, the storage device 105, the driving device 106, the battery 107, the I / F device 108, and the camera 109 can exchange various types of data through a communication bus 110.

[0042] The CPU 101 loads a program stored in the ROM 103 into the RAM 102 and executes it. The program stored in the ROM 103 describes various processes to be executed by the robot 20. The communication device 104 is an input / output device for exchanging various data and signals with the server 10 using a known wireless or wired communication method.

[0043] The storage device 105 is a storage for storing various information, and stores information on the robot 20, information on the building in which the robot 20 is installed (hereinafter also referred to as "building information"), position information and movement history (trajectory) of the robot 20, etc. The storage device 105 is, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0044] The information on the robot 20 includes, for example, ID information for identifying the robot 20 in the server 10. The building information includes map information (floor map) within the building, movement route information, position information of each camera 40 installed in the building, etc. The position information on the robot 20 is information indicating the current position of the robot 20.

[0045] The driving device 106 generates a driving force for the robot 20 to move. The driving device 106 includes, for example, wheels for the robot 20 to move and a motor for driving the wheels. The motor can be operated by receiving a supply of electric power from a battery 107. The battery 107 is a rechargeable secondary battery, and supplies electric power charged by a power supply device (not shown) to the driving device 106.

[0046] The I / F device 108 is an interface device for receiving input from the operator 50 and outputting notifications to the operator 50. The I / F device 108 is configured, for example, with a touch panel display. The camera 109 is an imaging device capable of continuously capturing images of the surroundings of the robot 20, and is, for example, a digital video camera.

[0047] Fig. 7 is a block diagram functionally showing the configuration of the robot 20. Referring to Fig. 7, the robot 20 includes an imaging unit 111, a current position estimation unit 112, a building information DB 113, a communication unit 114, a processing unit 115, a movement path setting unit 116, a user I / F unit 117, a movement control unit 118, and a driving unit 119.

[0048] 6, and continuously captures images of the surroundings of the robot 20 and outputs the captured images to the current position estimation unit 112. In addition, the imaging unit 111 captures an image of the camera 40 that has completed cleaning work in response to a work completion input from the user I / F unit 117 by the worker 50, and outputs the captured image of the camera 40 to the processing unit 115.

[0049] The current position estimation unit 112 acquires the image captured by the imaging unit 111, and acquires map information (floor map) of the floor 30 on which the robot 20 is patrolling from the building information DB 113. Then, the current position estimation unit 112 estimates the current position of the robot 20 from the image captured by the imaging unit 111 and the floor map of the floor 30, and outputs position information indicating the current position of the robot 20 to the processing unit 115.

[0050] The building information DB 113 stores various information about the building in which the robot 20 is deployed. Specifically, the building information DB 113 stores map information (floor map) of the floor 30 on which the robot 20 patrols, position information indicating the installation positions of each camera 40, and the like. The building information DB 113 also stores movement route information including routes that are blocked on the floor 30 due to construction or the like and the construction schedule, etc.

[0051] The communication unit 114 is configured to be able to communicate with the server 10, and exchanges various signals with the server 10. Specifically, the communication unit 114 transmits an inquiry about the camera 40 in which lens dirt has been detected to the server 10 in response to an inquiry input from the user I / F unit 117 by the worker 50. Then, when a camera 40 in which lens dirt has been detected is present, the communication unit 114 receives information about the camera 40 in which lens dirt has been detected (camera information) from the server 10.

[0052] In addition, in response to work completion input by worker 50 from user I / F unit 117, communication unit 114 transmits work completion information indicating that the cleaning work of camera 40 has been completed to server 10, and receives from server 10 the determination result of the re-dirt detection process executed in server 10 in response to the work completion information.

[0053] The movement path setting unit 116 sets an optimal movement path for the robot 20 to move to the installation position of the camera 40 to be cleaned based on the camera information from the server 10. In particular, when the camera information acquired from the server 10 includes multiple cameras 40 to be cleaned, the movement path setting unit 116 sets a movement route that optimizes movement efficiency when moving sequentially from the current position to the multiple cameras 40. The movement path setting unit 116 sets, for example, a movement route with the shortest total movement distance or total movement time as the optimal movement route from multiple movement paths that can move sequentially from the current position to the multiple cameras 40.

[0054] The user I / F unit 117 corresponds to the I / F device 108 shown in FIG. 6, and accepts various instructions input by the worker 50. Specifically, the user I / F unit 117 can accept an instruction (first instruction) to inquire of the server 10 about the camera 40 in which lens dirt has been detected, an instruction (second instruction) to transmit work completion information indicating that the cleaning work of the camera 40 has been completed to the server 10, and the like, in response to the operation of the I / F device 108 by the worker 50. In addition, the user I / F unit 117 notifies the worker 50 (for example, displays on a display) of information on the camera 40 to be cleaned, which is indicated by the camera information received from the server 10, and a determination result of re-detection of dirt, etc., received from the server 10 in response to the above-mentioned work completion information.

[0055] The movement control unit 118 executes control for the actual movement of the robot 20 in accordance with the movement command from the processing unit 115. The movement control unit 118 controls the driving unit 119 in accordance with the movement command so that the robot 20 travels at a predetermined movement speed in a direction in accordance with the movement command.

[0056] The driving unit 119 generates a driving force for the robot 20 to move. The driving unit 119 includes, for example, wheels for the robot 20 to move and a motor for driving the wheels. The driving unit 119 (motor) can be operated by receiving a supply of electric power from the battery 107 shown in FIG. 6.

[0057] Processing unit 115 executes overall processing in robot 20. When processing unit 115 receives an instruction (first instruction) from user I / F unit 117 to inquire of server 10 about camera 40 in which lens dirt has been detected, processing unit 115 transmits the received instruction to server 10 via communication unit 114. Then, when communication unit 114 receives camera information from server 10 in response to the above instruction, processing unit 115 outputs information about camera 40 to be cleaned, which is indicated by the received camera information, to user I / F unit 117.

[0058] Furthermore, when the processing unit 115 receives camera information from the server 10, it acquires the current position of the robot 20 from the current position estimation unit 112, and outputs an instruction to the movement path setting unit 116 to calculate a movement path from the current position to the camera 40 to be cleaned. Then, when the movement path is set, the processing unit 115 outputs an instruction to the movement control unit 118 to make the robot 20 travel according to the movement path.

[0059] Furthermore, when the processing unit 115 receives a notification from the user I / F unit 117 that the cleaning of the camera 40 by the worker 50 has been completed, the processing unit 115 outputs an instruction to the imaging unit 111 to capture an image of the camera 40. Then, the processing unit 115 attaches the image of the camera 40 captured by the imaging unit 111 to work completion information of the camera 40, and transmits the image to the server 10 via the communication unit 114. When the communication unit 114 receives a determination result of the dirt detection process again from the server 10 in response to the work completion information, the processing unit 115 outputs the received determination result to the user I / F unit 117.

[0060] 8 and 9 are flowcharts for explaining an example of the flow of processing in the server 10 and the robot 20 together with the operation of the worker 50. Referring to Fig. 8, the server 10 acquires image data captured by the cameras 40 installed on the floor 30 from each camera 40 (step S110). Note that acquisition of image data from the cameras 40 is basically performed continuously, and the image data is accumulated in an image DB (not shown) for a predetermined period (for example, one week or one month).

[0061] Next, the server 10 executes a dirt detection process for detecting dirt on the lens of the camera 40 based on the imaging data acquired in step S110 for each camera 40 (step S120). This dirt detection process is executed according to the flowchart shown in FIG.

[0062] Then, server 10 stores the detection result of the lens dirt by the dirt detection process in camera information DB 73 as "dirt information" for each camera 40 (FIG. 5). The process from step S110 to step S130 is executed periodically for each camera 40.

[0063] Meanwhile, the worker 50 inputs an instruction (first instruction) from the I / F device 108 of the robot 20 to inquire about the camera 40 on which lens dirt has been detected by the dirt detection process in the server 10 (step S310). In response, the robot 20 inquires of the center (server 10) about the presence or absence of a camera 40 on which lens dirt has been detected (step S210).

[0064] When the server 10 receives an inquiry from the robot 20 about the camera 40 in which the lens dirt has been detected, the server 10 searches the camera information DB 73 and transmits the camera information (floor number, camera number, etc.) of the camera 40 whose "dirt information" is "present" to the robot 20 (step S140). Note that the camera information may include information on multiple cameras 40.

[0065] When the robot 20 receives the camera information from the server 10, the robot 20 searches for an optimal movement route to the camera 40 (which may be multiple) to be cleaned, which is indicated in the camera information (step S220). More specifically, based on the movement route information, which includes map information of the floor 30, position information of the camera 40, routes that are blocked due to construction or the like, and the construction schedule, etc., stored in the building information DB 113, a movement route that optimizes movement efficiency when moving sequentially from the current position to the camera 40 to be cleaned is searched for. Then, of the multiple movement routes that can be used to move from the current position to the camera 40, the movement route with the shortest total movement distance or total movement time, for example, is set as the optimal movement route.

[0066] 9, the robot 20 moves to the installation position of the camera 40 to be cleaned (step S230) according to the movement route set as a result of the search in step S220 (FIG. 8). That is, the robot 20 moves to the installation position of the camera 40 to be cleaned, thereby guiding the operator 50 to the installation position of the camera 40 to be cleaned.

[0067] The worker 50 moves following the robot 20 (step S320). Then, when the worker 50 reaches the installation position of the camera 40 to be cleaned together with the robot 20, the worker 50 performs the work of cleaning the lens of the camera 40 (step S330).

[0068] When the cleaning work of the camera 40 is completed, the worker 50 inputs an instruction (second instruction) to the I / F device 108 of the robot 20 to transmit work completion information indicating that the cleaning work of the camera 40 has been completed to the server 10 (step S340). Then, the robot 20 transmits the work completion information of the camera 40 for which the cleaning work has been completed to the center (server 10) (step S240).

[0069] When the server 10 receives the task completion information of the camera 40 from the robot 20, it acquires imaging data from the camera 40 (step S150). Next, the server 10 executes a dirt detection process to detect lens dirt based on the imaging data acquired in step S150 (step S160). This lens dirt detection process is also executed according to the flowchart shown in FIG. 4. Then, the server 10 transmits the detection result executed in step S160 to the robot 20 (step S170).

[0070] In response to sending the work completion information to the server 10 in step S240, the robot 20 receives from the server 10 the detection result of lens dirt on the camera 40 for which the cleaning work has been completed, and notifies the worker 50 by displaying the detection result on the I / F device 108 (step S250).

[0071] If this detection result indicates NG (YES in step S350), that is, if it is determined that the lens is still dirty, worker 50 returns to step S330 and performs the cleaning work on the lens of camera 40 again.

[0072] If the detection result of the dirt on the lens of the camera 40 received from the server 10 in step S250 indicates OK, the robot 20 determines whether there is another camera 40 to be cleaned (step S260). If there is another camera 40 to be cleaned (YES in step S260), the robot 20 returns to step S230 and moves to the installation position of the next camera 40 to be cleaned, following the movement route set as a result of the search in step S220.

[0073] For the worker 50, if the lens dirt detection result in step S350 indicates OK (NO in step S350), and if there are other cameras 40 to be cleaned (YES in step S360), the process returns to step S320, and the worker 50 follows the robot 20 to move to the installation position of the next camera 40.

[0074] As described above, in this work support system, the robot 20 is used to guide the worker 50 to the installation position of the camera 40 where the lens dirt has been detected. The robot 20 acquires camera information specifying the camera 40 where the lens dirt has been detected from the server 10 according to an inquiry instruction by the worker 50, and guides the worker 50 to the installation position of the camera 40 specified by the acquired camera information. As a result, even if the worker 50 does not know information inside the building (such as the movement route and information on construction work on the route), he or she can move to the installation position of the camera 40 where the lens dirt has been detected (the camera to be cleaned) by moving following the robot 20. Therefore, according to this work support system, the worker 50 can quickly move to the installation position of the camera 40 and clean the lens of the camera 40.

[0075] Furthermore, in this work support system, the robot 20, which can move autonomously within the building, has information about the building in which the camera 40 is installed (such as information about the movement route and construction work on the route), so the load on the server 10, which manages multiple buildings and robots 20, can be reduced.

[0076] Furthermore, in this work support system, when the worker 50 completes the cleaning work of the camera 40, the robot 20 transmits work completion information to the server 10 in accordance with the instructions of the worker 50. Then, the server 10 executes the dirt detection process again for the camera 40 indicated by the work completion information, and transmits the detection result to the robot 20. In this way, according to this work support system, the worker 50 who performed the cleaning work can quickly check whether the lens dirt has been eliminated by the cleaning work.

[0077] In addition, in this work support system, when an instruction is given to transmit work completion information to the server 10, the camera 40 where the cleaning work was performed is photographed by the robot 20, and the photograph is transmitted together with the work completion information to the server 10. Therefore, according to this work support system, it is possible to confirm in the server 10 that the cleaning work has actually been performed by the worker 50.

[0078] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The technical scope of the present disclosure is defined by the claims, not by the description of the embodiments described above, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0079] 10 server, 20 robot (mobile robot), 30 floor, 40,109 camera, 50 worker, 61,101 CPU, 62,102 RAM, 63,103 ROM, 64,104 communication device, 65,105 storage device, 66,110 communication bus, 71 imaging data acquisition unit, 72 dirt detection unit, 73 camera information DB, 74,114 communication unit, 75,115 processing unit, 80 camera information, 106 driving unit, 107 battery, 108 I / F device, 111 imaging unit, 112 current position estimation unit, 113 building information DB, 116 movement path setting unit, 117 user I / F unit, 118 movement control unit, 119 driving unit.

Claims

1. A work support system for a worker to clean dirt on a lens of a camera installed in a building, comprising: A server that executes a dirt detection process to detect the lens dirt based on image data captured by the camera; a mobile robot configured to be able to move autonomously within the building, The mobile robot includes: acquiring, from the server, camera information identifying a camera in which lens dirt has been detected by the dirt detection process in accordance with a first instruction from the operator; By moving to the installation position of the camera specified by the acquired camera information, the worker is guided to the installation position of the camera where the lens dirt was detected; After the camera is moved to an installation position specified by the camera information, in accordance with a second instruction from the worker, transmitting work completion information indicating completion of the cleaning work of the lens dirt to the server; The server, When the work completion information is received, the dirt detection process is performed for the camera indicated by the work completion information; Transmitting a result of the dirt detection process to the mobile robot; The mobile robot notifies the worker of the execution result received from the server.

2. The mobile robot is A communication unit that communicates with the server; A storage unit that stores building information including map information within the building, travel route information, and position information of the camera; a control unit for controlling movement of the mobile robot, 2. The work assistance system according to claim 1, wherein the control unit controls movement of the mobile robot so as to move to an installation position of a camera specified by the camera information based on the building information and the camera information acquired from the server by the communication unit.

3. The mobile robot includes an imaging unit, The imaging unit captures an image using a camera specified by the camera information in accordance with the second instruction, The work support system according to claim 1 , wherein the work completion information includes an image captured by the imaging unit in accordance with the second instruction.

4. When a plurality of cameras are identified by the camera information, The mobile robot includes: determining a movement route that optimizes movement efficiency when moving sequentially to the plurality of cameras; The work support system according to claim 1 or 2, further comprising: a step of guiding the worker along the movement route.

Citation Information

Patent Citations

  • Camera maintenance support device, camera maintenance support method and remote monitoring system

    JP2017212596A

  • Robot management apparatus and robot management system

    JP2019049937A

  • Robot control device, robot control method, and robot

    JP2020166353A

  • Work support apparatus and work support method

    JP2020181456A

  • Sensing device and sensing system for defective photographic data

    WO2019146097A1