Cleaning device, cleaning system, and cleaning program
The cleaning device addresses incomplete cleaning by analyzing floor images to stop when dirt is spread, preventing dirt spread and ensuring effective cleaning.
Patent Information
- Application Number
- JP2023081047
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-16
- Publication Date
- 2024-11-28
- Estimated Expiration
- 2043-05-16
AI Technical Summary
Conventional cleaning systems inaccurately determine cleaning completion, potentially spreading dirt like food, drink, or animal excrement due to incomplete cleaning.
A cleaning device equipped with a self-position estimating unit, cleaning effect determining section, and control unit that analyzes floor images before and after cleaning to determine cleaning effectiveness, stopping cleaning if dirt is spread.
Prevents the spread of dirt by allowing the device to stop cleaning when dirt is worsened, ensuring thorough and effective cleaning.
Smart Images

Figure 2024165145000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a cleaning device, a cleaning system, and a cleaning program. [Background technology]
[0002] In recent years, cleaning robots that autonomously move and clean floors have been used. These cleaning robots are used to clean various areas, such as homes, offices, and public facilities (e.g., train stations).
[0003] For example, International Publication No. 2022 / 009391 (Patent Document 1) discloses a cleaning system comprising: a first autonomous robot suitable for cleaning relatively large areas; an imaging means for photographing the entire cleaning area while the first autonomous robot cleans the cleaning area in accordance with cleaning instruction information created based on layout information of the cleaning area; a generation means for generating uncleaned area information that identifies areas within the cleaning area that have not actually been cleaned by the first autonomous robot by analyzing the imaging data generated by the imaging means; and an instruction means for instructing the first autonomous robot to clean areas that have not actually been cleaned, which are identified from the uncleaned area information. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] International Publication No. 2022 / 009391 Summary of the Invention [Problem to be solved by the invention]
[0005] In conventional cleaning systems, such as the cleaning system described in Patent Document 1, cleaning is considered complete when the cleaning robot passes through the cleaning area. However, depending on the type of soiling material, such as food, drink, vomit, or animal waste, the cleaning robot's passage may actually spread the dirt.
[0006] An object of the present disclosure is to provide a cleaning device, cleaning system, and cleaning program that can choose not to clean if the device itself is spreading dirt. [Means for solving the problem]
[0007] The cleaning device (10) according to the first aspect of the present disclosure includes a self-position estimation unit (50) that estimates a position of the cleaning device itself, a control unit (58, 60) that controls the cleaning device to clean a floor surface within a cleaning area (14) while autonomously traveling based on the position estimated by the self-position estimation unit, and a cleaning effect determination unit (54) that determines cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, and the control unit controls the cleaning device (10) to stop traveling of the cleaning device itself and to cease cleaning in the small area being determined when the cleaning effect determination unit determines that the dirt on the floor surface has worsened.
[0008] A cleaning system (100) according to a second aspect of the present disclosure is a cleaning system (100) comprising a cleaning device and a cleaning assistance device (12) communicatively connected to the cleaning device and assigning a cleaning task of cleaning a specific cleaning area to the cleaning device, wherein the cleaning device comprises a self-position estimation unit that estimates a position of the cleaning device, a control unit that controls the cleaning device to clean the floor surface within the cleaning area while autonomously traveling based on the position estimated by the self-position estimation unit, and a cleaning effect determination unit that determines the cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, and when the cleaning effect determination unit determines that the dirt on the floor surface has worsened, the control unit controls the cleaning device to stop traveling and cancel cleaning in the small area to be determined.
[0009] A cleaning program according to a third aspect of the present disclosure is a cleaning program that causes at least one processor (32) to estimate a position of the device itself, control the device to clean the floor surface within a cleaning area while autonomously traveling based on the estimated position, determine the cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, and, if it is determined that the dirt on the floor surface has worsened, control the device to stop traveling of the device and abort cleaning in the small area to be determined. Effect of the Invention
[0010] According to the present disclosure, a cleaning device, cleaning system, and cleaning program are provided that can select not to clean if the device itself is spreading dirt. [Brief description of the drawings]
[0011] [Figure 1] 1 is a schematic diagram showing an example of a configuration of a cleaning system according to a first embodiment of the present disclosure. [Diagram 2] 1 is a block diagram showing an example of a hardware configuration of a cleaning device according to a first embodiment of the present disclosure. [Diagram 3] 1 is a functional block diagram showing an example of a functional configuration of a cleaning system according to a first embodiment of the present disclosure. FIG. [Figure 4] 5 is a flowchart showing an example of the flow of a cleaning program according to the first embodiment of the present disclosure. [Diagram 5] 6 is a flowchart showing an example of the flow of a "cleaning effect determination process" according to the first embodiment. [Figure 6] 10 is a flowchart showing an example of the flow of a cleaning program according to a second embodiment of the present disclosure. [Figure 7] 13 is a flowchart showing an example of the flow of a "dirt detection process" according to the second embodiment. [Figure 8] 1A and 1B are schematic diagrams showing an example of stain detection. [Figure 9] 6(A) to 6(C) are schematic diagrams showing another example of stain detection. [Figure 10] 13(A) and 13(B) are schematic diagrams showing another example of stain detection. [Figure 11] 13 is a flowchart showing an example of the flow of a “cleaning effect determination process” according to a third embodiment of the present disclosure. [Figure 12] 13 is a flowchart showing an example of the flow of an "additional dirt detection process" according to the third embodiment. [Figure 13] 13 is a flowchart showing an example of the flow of a cleaning program according to a fourth embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0012] An embodiment of the present invention will now be described in detail with reference to the drawings.
[0013] [First embodiment] <Cleaning System> First, the cleaning system of the present disclosure will be described with reference to FIG. As shown in Fig. 1, the cleaning system 100 includes a cleaning device 10, which is an autonomous robot, and a cleaning assistant device 12 communicatively connected to the cleaning device 10. The cleaning system 100 may include a plurality of cleaning devices 10. In this example, three cleaning devices 10, cleaning devices 101, 102, and 103, are illustrated. When there is no need to distinguish between the cleaning devices 101, 102, and 103, they will be collectively referred to as the cleaning device 10.
[0014] The cleaning support device 12 generates cleaning work details (hereinafter referred to as "cleaning tasks") for each cleaning area 141, 142, 143, and assigns the cleaning tasks to the cleaning devices 101, 102, 103. Here, the tasks of cleaning the cleaning areas 141, 142, 143 are assigned to each of the cleaning devices 101, 102, 103. When there is no need to distinguish between the cleaning areas 141, 142, 143, they are collectively referred to as the cleaning area 14. The cleaning device 10 is placed in the cleaning area 14 to be cleaned, and cleans the floor surface of the cleaning area 14 while autonomously traveling within the cleaning area 14.
[0015] In the cleaning system 100 of the present disclosure, the cleaning device 10 captures images of the floor surface before and after cleaning while autonomously traveling within the cleaning area 14, and judges the cleaning effect by comparing the images of the floor surface before and after cleaning. If the dirt on the floor surface worsens, the cleaning device 10 presumes that the device itself is spreading the dirt, and selects not to perform any more cleaning.
[0016] In this embodiment, an example in which the cleaning support device 12 generates a task will be described, but the cleaning device 10 may have a task generation function. If the cleaning device 10 has a task generation function, the cleaning support device 12 may be omitted.
[0017] (Hardware configuration) Next, an example of a hardware configuration of the cleaning device 10 will be described with reference to FIG. 2, the cleaning device 10 includes a control unit 20. The control unit 20 can be configured as a computer, and includes a processor 32, a read only memory (ROM) 34, a random access memory (RAM) 36, a storage 38, an input / output interface (I / F) 40, and a communication interface (I / F). The processor 32, the ROM 34, the RAM 36, the storage 38, the input / output interface 40, and the communication interface 42 are each connected to each other via an internal bus 44 so as to be able to communicate with each other.
[0018] The processor 32 may be configured, for example, by a CPU (Central Processing Unit), and executes various programs and controls each part. Specifically, the processor 32 reads various programs stored in the ROM 34 or the storage 38, and executes the programs using the RAM 36 as a working area. The processor 32 controls each part constituting the cleaning device 10 and performs various arithmetic processing according to the programs.
[0019] The ROM 34 stores various programs and various data. The RAM 36 temporarily stores programs or data as a working area. The storage 38 can be configured with a recording medium such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory.
[0020] The storage 38 may store various programs including an operating system and various data necessary for operating the cleaning device 10. In this embodiment, the ROM 34 or the storage 38 stores a "cleaning program" (to be described later) and various data necessary for executing a cleaning task.
[0021] The communication interface 42 may be capable of transmitting and receiving predetermined data by wireless communication based on a wireless communication standard such as Wi-Fi (registered trademark) or Bluetooth (registered trademark). The communication interface 42 allows the control unit 20 of the cleaning device 10 to communicate with other electronic devices, such as the cleaning assistant device 12 and other cleaning devices 10, via a network.
[0022] As shown in FIG. 2, the travel device 22, the cleaning tool 24, the camera 26, the display 28, and the reporting device 30 are connected to the input / output interface 40 of the control unit 20 so as to transmit and receive data to and from the control unit 20.
[0023] The traveling device 22 includes a plurality of wheels 22A disposed on the front and rear bottom of the cleaning device 10. At least some of the wheels 22A are rotated by a driving means such as a motor (not shown), and the traveling direction is changed by a steering means capable of controlling the orientation of at least some of the wheels 22A, thereby realizing autonomous traveling of the cleaning device 10.
[0024] The cleaning tool 24 is provided at an appropriate location on the cleaning device 10 and is a device that enables cleaning of the floor surface while the cleaning device 10 is autonomously traveling. The cleaning tool 24 includes at least a vacuum cleaner capable of sucking up dust on the floor surface. The cleaning tool 24 may further include a cloth capable of wiping, such as wet wiping or dry wiping. The cleaning tool 24 may include a robot arm to which a predetermined cleaning tool can be attached or which can hold the cleaning tool. The cleaning tool 24 may also include a dust sensor 24A built in.
[0025] Each cleaning device 10 may be equipped with multiple different types of cleaning tools 24. In this case, different cleaning tools 24 may be used depending on the type of dirt. Furthermore, each of the multiple cleaning devices 10 may be equipped with the same type of cleaning tool 24, or may be equipped with different types of cleaning tools 24. When each cleaning device 10 is equipped with different types of cleaning tools 24, cleaning can be easily performed using the most suitable cleaning means by, for example, changing the cleaning device 10 that performs cleaning according to the type of dirt.
[0026] The camera 26 is a device that captures images of the surroundings and floor surface of the cleaning device 10. The cleaning device 10 estimates its own position from the surrounding conditions captured by the camera 26. The cleaning device 10 also captures images of the floor surface before and after cleaning. For example, the cameras 26 may be installed in front and behind the cleaning device 10 to capture images of the floor surface before and after cleaning. For example, the camera 26 installed in the front of the cleaning device 10 captures an image of the floor surface before cleaning in front of the cleaning device 10 (for example, see the diagram of the cleaning device 102 in FIG. 1). Then, after passing through the floor surface and cleaning it, the camera 26 installed in the rear of the cleaning device 10 captures an image of the floor surface after cleaning behind the cleaning device 10 (for example, see the diagram of the cleaning device 103 in FIG. 1).
[0027] A two-dimensional camera using an imaging element such as a CCD (Charge Coupled Device) sensor or a CMOS (Complementary Metal Oxide Semiconductor) sensor can be used as the camera 26. Also, a three-dimensional camera such as a stereo camera, a structured light, or a camera with a depth sensor such as a ToF (Time of Flight) sensor can be used as the camera 26.
[0028] Although the camera 26 is exemplified here, an object detection means other than a camera may be used to estimate the self-position of the cleaning device 10 and detect dirt, which will be described later. For example, instead of or in addition to the camera 26, a radar (e.g., a millimeter wave sensor) or LiDAR (Laser Imaging Detection and Ranging) that detects the distance and direction to objects around the vehicle, a sonar that detects objects around the vehicle by sound waves, or a GPS (Global Positioning System) can be used. Also, a digital map such as a GIS (Geographic Information System) can be used to estimate the self-position.
[0029] The display 28 is a device for displaying various kinds of information to the user, etc. For example, messages to people in the vicinity can be displayed on the display 28. The display 28 may be installed at any position on the cleaning device 10. As the display 28, a well-known display device such as a liquid crystal display (LCD) or an organic electro-luminescent display (OELD) can be used.
[0030] The notification device 30 is a device for notifying people in the vicinity of the various pieces of information by emitting a sound or turning on a lamp. The notification device 30 may be installed at any position of the cleaning device 10. The notification device 30 may be provided with a speaker for outputting sound, a lamp for outputting light, or the like.
[0031] Although detailed description will be omitted, the cleaning support device 12 is, for example, a server device arranged in the cloud. The cleaning support device 12 can be configured as a cloud server capable of providing XaaS (X as a Service). The cleaning support device 12 includes a control device, a storage device, and a communication interface. The control device of the cleaning support device 12 can be configured as a computer, similar to the control unit 20 of the cleaning device 10.
[0032] (Functional configuration) Next, the functional configuration of the cleaning device 10 will be described with reference to FIG. The cleaning device 10 includes a self-location estimation unit 50, a dirt detection unit 52, a cleaning effectiveness determination unit 54, a cleaning feasibility determination unit 56, a travel control unit 58, a cleaning control unit 60, and a report control unit 62. Of the functional units exemplified above, the cleaning device 10 of the present disclosure has the self-location estimation unit 50, the cleaning effectiveness determination unit 54, and the cleaning control unit 60 as essential components. Note that units other than the self-location estimation unit 50, the dirt detection unit 52, the cleaning effectiveness determination unit 54, and the cleaning feasibility determination unit 56 may be collectively referred to as the "control unit."
[0033] The self-position estimation unit 50 is a functional unit that estimates the position of the cleaning device 10 itself. In this embodiment, the self-position is estimated from the surrounding situation captured by the camera 26 and map information of the cleaning area 14. The self-position estimation unit 50 can also detect the traveling speed of the cleaning device 10 from the change in the position of the cleaning device over time.
[0034] The dirt detection unit 52 is a functional unit that detects dirt on the floor surface of a portion of the cleaning area 14 before cleaning and detects the type and state of the dirt. In this embodiment, the dirt detection unit 52 detects dirt on the floor surface of the cleaning area 14 before cleaning by comparing an image of the floor surface of the cleaning area 14 without dirt that has been captured in advance with an image of the floor surface of the cleaning area 14 captured immediately before cleaning.
[0035] The cleaning effect determination unit 54 is a functional unit that, after cleaning, determines the cleaning effect for a portion of an area within the cleaning area 14 based on images of the floor surface before and after cleaning. In this embodiment, the cleaning effect determination unit 54 compares an image of the floor surface of the cleaning area 14 taken before cleaning with an image of the floor surface of the cleaning area 14 taken after cleaning, and determines the cleaning effect based on whether the dirt on the floor surface has worsened.
[0036] The cleaning feasibility determination unit 56 is a functional unit that determines, before cleaning, whether or not it is possible to clean the floor surface of a portion of the cleaning area 14. The cleaning feasibility determination unit 56 calculates the cleanability of the dirt detected by the dirt detection unit 52, and determines whether or not the cleaning device 10 can clean the dirt based on the calculated cleanability.
[0037] The travel control unit 58 is a functional unit that controls the traveling device 22 based on the position of the device itself estimated by the self-position estimation unit 50 to cause the cleaning device 10 to travel autonomously. The cleaning control unit 60 is a functional unit that controls the position of the cleaning tool 24 and the like to clean the floor surface within the cleaning area 14. In this embodiment, when the cleaning effect determination unit 54 determines that the dirt on the floor surface has worsened, the cleaning device 10 is controlled to stop traveling in the small area to be determined and to stop cleaning.
[0038] In this embodiment, the operation modes include a "cleaning mode" in which the cleaning device 10 performs cleaning while traveling autonomously, and a "non-cleaning mode" in which the cleaning device 10 performs autonomous traveling without cleaning. The cleaning control unit 60 transitions the operation mode from the non-cleaning mode to the cleaning mode when cleaning starts. In addition, the cleaning control unit 60 transitions the operation mode from the cleaning mode to the non-cleaning mode when the cleaning effect determination unit 54 determines that the dirt on the floor surface has worsened. In the cleaning mode, the travel control unit 58 and the cleaning control unit 60 cooperate to control the cleaning device 10.
[0039] The notification control unit 62 is a functional unit that notifies various information to the outside when, for example, a cleaning task is stopped. The notification control unit 62 controls the notification device 30 to notify people in the vicinity of the various information. The notification control unit 62 also causes the various information to be transmitted to the cleaning support device 12 or other cleaning devices 10 via the communication interface 42.
[0040] The cleaning support device 12 also includes a task generation unit 66 and a dirt information accumulation unit 68. The task generation unit 66 is a functional unit that generates tasks to be executed by each cleaning device 10, specifically, cleaning tasks including the details of the cleaning work. The cleaning task may include information such as the cleaning area to be cleaned, the target cleaning level, and the cleaning tool 24 to be used. The dirt information accumulation unit 68 is a functional unit that stores the dirt information transmitted from each cleaning device 10 in a storage device in association with the position on the map of the cleaning area 14.
[0041] The respective functional units of the cleaning device 10 are realized by the processor 32 of the control unit 20 executing a "cleaning program" which will be described next.
[0042] <Cleaning Program> Next, the "cleaning program" will be described with reference to FIG. The "cleaning program" is executed by the processor 32 of the control unit 20. The "cleaning program" is started when the cleaning device 10 receives a cleaning task from the cleaning support device 12. Here, the cleaning area 14 is divided into a number of small areas, and the cleaning effect is determined for each small area.
[0043] First, in step S100, processor 32 switches the operation mode of cleaning device 10 to a cleaning mode for cleaning the floor surface. Next, in step S102, processor 32 moves cleaning device 10 to the next small area. At the start of cleaning, it is moved to the small area where cleaning will start. Cleaning device 10 acquires surrounding images from camera 26, and moves to a desired position while estimating its own position from the surrounding images.
[0044] Next, in step S104, processor 32 causes camera 26 to capture an image of the floor surface in a small area before cleaning in front of cleaning device 10, obtains an image of the floor surface before cleaning, and stores the obtained image in RAM 36. Next, in step S114, processor 32 causes cleaning device 10 to travel and clean the small area. Next, in step S116, processor 32 causes camera 26 to capture an image of the floor surface in a small area after cleaning behind cleaning device 10, obtains an image of the floor surface after cleaning, and stores the obtained image in RAM 36.
[0045] Next, in step S118, the processor 32 executes a "cleaning effect determination process" for determining the cleaning effect in the cleaned small area.
[0046] Here, the "cleaning effect determination process" will be described with reference to FIG. First, in step S200, the processor 32 acquires an image of the floor surface before cleaning from the RAM 36. Next, in step S202, the processor 32 acquires an image of the floor surface after cleaning from the RAM 36. Next, in step S204, the processor 32 compares the images of the floor surface before and after cleaning. Here, the images of the floor surface before and after cleaning are converted into images seen from above (Top View) so that the images can be compared regardless of from which angle they were captured, and the two converted images are compared.
[0047] Next, in step S206, processor 32 determines whether or not cleaning has caused dirt on the floor surface to increase compared to before cleaning. For example, a difference image is extracted by subtracting the image of the floor surface before cleaning from the image of the floor surface after cleaning, and if new dirt is added as the difference image, it can be determined that the dirt has increased.
[0048] In addition to the scattering of dust, dirt may spread when tire marks are left behind by the cleaning device 10 as it moves through the cleaning area 14. For example, the heavy cleaning device 10 passing over carpet or flooring may cause severe wear and tear that cannot be restored even after a certain period of time.
[0049] If the stain has spread (YES in step S206), the process proceeds to step S208. In step S208, processor 32 determines that the stain has worsened and ends the routine. On the other hand, if the stain has not spread (NO in step S206), the process ends the routine without determining that the stain has worsened.
[0050] Returning now to the explanation of Fig. 4, next, in step S120, processor 32 determines whether or not cleaning has worsened the condition of the floor surface in the small area. If it is determined that the condition has worsened in the above-mentioned "cleaning effect determination process", it is assumed that the condition of the floor surface has worsened. If the condition of the floor surface has not worsened (NO in step S120), the process proceeds to step S122. On the other hand, if the condition of the floor surface has worsened (YES in step S120), the process proceeds to step S126.
[0051] If the condition of the floor surface has not deteriorated, in step S122, processor 32 determines whether or not there is a next small area. If there is a next small area (YES in step S122), the process returns to step S102 and repeats the procedure of steps S102 to S122. That is, processor 32 causes cleaning device 10 to continue cleaning. If there is no next small area (NO in step S122), in the following step S124, processor 32 transmits a cleaning task completion notification to cleaning support device 12 and ends the routine.
[0052] If the condition of the floor surface has worsened, in step S126, processor 32 transitions the operation mode of cleaning device 10 to a non-cleaning mode in which floor surface cleaning is not performed. That is, processor 32 causes cleaning device 10 to stop cleaning. In the following step S128, processor 32 performs a "task stop process" for when a cleaning task is stopped midway, and ends the routine.
[0053] The "task cancellation process" may include stopping the movement of the cleaning device 10, notifying the surroundings, etc. Methods for notifying the surroundings include sounding a sound or turning on a lamp. The processor 32 may also send a notification of the cancellation of the cleaning task to the cleaning support device 12.
[0054] As described above, in the first embodiment, the cleaning area 14 is divided into a number of small areas, and the cleaning effect is judged for each small area. Therefore, even if the cleaning device 10 is spreading dirt, it is possible to detect that the condition of the floor surface in a small area has worsened compared to before cleaning.
[0055] Furthermore, in the first embodiment, if a deterioration in the condition of the floor surface is detected in a small area, the cleaning device 10 is caused to stop cleaning in that small area, so that cleaning can be stopped before dirt spreads over a wide area within the cleaning area.
[0056] [Second embodiment] In the second embodiment, a "dirt detection process" is executed before cleaning to determine whether the dirt is cleanable or not. If the dirt is uncleanable, cleaning is stopped before cleaning the small area. Since the other configurations are the same as those of the first embodiment, the description of the common parts will be omitted and only the differences will be described.
[0057] Next, the "cleaning program" according to the second embodiment will be described with reference to FIG. The "cleaning program" according to the second embodiment is similar to the "cleaning program" according to the first embodiment shown in FIG. 4, except that steps S106 to S110 are added.
[0058] First, in step S100, the processor 32 shifts the operation mode of the cleaning device 10 to a cleaning mode for cleaning the floor surface. Next, in step S102, the processor 32 moves the cleaning device 10 to the next small area. Next, in step S104, the processor 32 causes the camera 26 to capture an image of the floor surface in the small area before cleaning in front of the cleaning device 10, obtains an image of the floor surface before cleaning, and stores the obtained image in the RAM 36.
[0059] Next, in step S106, processor 32 executes a "dirt detection process" to detect dirt on the floor surface before cleaning. The "dirt detection process" will be described in detail later. Next, in step S108, processor 32 calculates the cleanability of the dirt detected in step S106. Next, in step S110, processor 32 determines whether cleaning device 10 is capable of cleaning based on the cleanability calculated in step S108. If cleaning is possible (YES in step S110), the process proceeds to step S114. On the other hand, if cleaning is not possible (NO in step S110), the process proceeds to step S126.
[0060] Next, in step S114, processor 32 causes cleaning device 10 to travel and clean the small area. Next, in step S116, processor 32 causes camera 26 to capture an image of the floor surface of the cleaned small area behind cleaning device 10, obtains an image of the floor surface after cleaning, and stores the obtained image in RAM 36.
[0061] Next, in step S118, processor 32 executes a "cleaning effect determination process" to determine the cleaning effect in the cleaned small area. Next, in step S120, processor 32 determines whether the condition of the floor surface in the small area has worsened due to cleaning. If the condition of the floor surface has not worsened, the process proceeds to step S122. On the other hand, if the condition of the floor surface has worsened, the process proceeds to step S126.
[0062] If the condition of the floor surface has not deteriorated, in step S122, the processor 32 determines whether or not there is a next small area. If there is a next small area, the process returns to step S102, and the procedures of steps S102 to S122 are repeated. If there is no next small area, in the following step S124, the processor 32 transmits a cleaning task completion notification to the cleaning support device 12, and ends the routine.
[0063] If the condition of the floor surface has deteriorated, or if it is determined before cleaning that cleaning is impossible, in step S126, the processor 32 transitions the operation mode of the cleaning device 10 to a non-cleaning mode in which the floor surface is not cleaned. In the following step S128, the processor 32 performs a task cancellation process and ends the routine.
[0064] 6, if it is determined in step S110 that cleaning is impossible before cleaning, the mode is switched to the non-cleaning mode, but as shown by the dotted arrow, the uncleanable small area may be skipped and the cleaning device 10 may move to the next small area. In this case, it is preferable to find a route that bypasses the uncleanable small area and move the cleaning device 10 to the next small area via the bypass route.
[0065] (Dirt detection process) Now, the "dirt detection process" in step S106 in Fig. 6 will be described with reference to Fig. 7. First, in step S300, processor 32 acquires a reference image stored in advance. The reference image is an image of a corresponding small area captured in a clean state. Next, in step S302, processor 32 acquires an image of the floor surface before cleaning from RAM 36. Next, in step S304, processor 32 converts the image into an image seen from above and compares the image of the floor surface before cleaning with the reference image.
[0066] Next, in step S306, processor 32 determines whether or not there is dirt. Processor 32 also determines the type of dirt. Here, the type of dirt refers to the type of substance that constitutes the dirt (hereinafter referred to as "dirty substance"). Types of dirty substances include dust, paper scraps, sand, mud, shoe prints, rainwater, food, drink, vomit, animal excrement, etc.
[0067] The type of dirt, i.e., the class of dirt, is determined by image recognition techniques that utilize the characteristics of the dirt (e.g., color, area, shape, whether it is liquid or solid, etc.). For example, if it is a three-dimensional object, it is determined to be solid, and if it is not a three-dimensional object, it is determined to be liquid. Specifically, for an image that is similar to a reference image of food scattered on the floor, the dirt is determined to be food.
[0068] If there is dirt (YES in step S306), the process proceeds to step S308. In step S308, processor 32 records the location of the dirt. On the other hand, if there is no dirt (NO in step S306), there is no need to record the location of the dirt, so step S308 is skipped and the process proceeds to step S310. Next, in step S310, the dirt detection result is output and the routine ends. If dirt is detected, the dirt detection result includes the presence or absence of dirt, the position of the dirt, the type of dirt, etc. The dirt detection result is transmitted to cleaning support device 12, for example, by being included in a notification of completion or cancellation of the cleaning task.
[0069] Here, a specific example of stain detection will be given. (Example 1) Fig. 8(A) shows a reference image 80B. The reference image 80B is an image of a stain-free carpet. Fig. 8(B) shows an image 80A of the floor surface before cleaning. A stain 82 caused by a drink being spilled on the carpet is reflected in the image 80A of the floor surface before cleaning. In this case, by obtaining a difference image between the reference image 80B and the image 80A of the floor surface before cleaning, the stain 82 is detected as a change from the reference image 80B.
[0070] (Example 2) FIG. 9(A) shows a reference image 80B1 taken in a first time period, and FIG. 9(B) shows a reference image 80B2 taken in a second time period. The storage 38 of the cleaning device 10 stores the reference image 80B for each time period in advance. FIG. 9(C) shows an image 80A of the floor surface before cleaning taken in a second time period. A shadow 84 caused by sunlight or lighting is projected on the reference image 80B2 taken in the second time period and the image 80A of the floor surface before cleaning. In this case, the reference image 80B2 taken in the same time period is compared with the image 80A of the floor surface before cleaning so that the shadow 84 is not erroneously detected as dirt. By obtaining a difference image between the two images, only dirt 82 is detected.
[0071] (Example 3) Fig. 10(A) shows a reference image 80B. Fig. 10(B) shows an image 80A of the floor surface before cleaning. A shadow 86 of a person is projected onto the image 80A of the floor surface before cleaning by sunlight or lighting. In the shadow 86 of a person or a moving object such as a curtain, the boundary between the shadow 86 and the surrounding area moves over time. In this case, the reference image 80B is compared with images 80A of the floor surface before cleaning taken at multiple times to prevent the shadow 86 from being erroneously detected as dirt. If the difference image between the two images changes over time, the difference image is determined to be a shadow 86 and is excluded from dirt.
[0072] Although the above describes an example in which shadows or human figures are identified and eliminated during image comparison, the influence of shadows or human figures can be eliminated by other methods. For example, images may be captured from a position or angle where shadows or human figures are not projected. Furthermore, the image capture area may be illuminated by a light source so that shadows or human figures are not projected during image capture.
[0073] In addition, the position of the surrounding light source such as sunlight or lighting may be identified to estimate the direction and shape of the shadow or human figure, and the estimated shadow or human figure may be removed by image processing. In addition, if the shadow of the cleaning device is projected when the image is captured by the camera 26 installed at the rear of the cleaning device 10, the cleaning device 10 may move back by one area and capture the image with the camera 26 installed at the front of the cleaning device 10.
[0074] (Cleanability) Here, the calculation of the cleanability in step S108 in Fig. 6 and the criteria for determining whether or not cleaning is possible in step S110 in Fig. 6 will be described. In the second embodiment, the cleanability is calculated for dirt detected in the dirt detection process before cleaning. The cleanability is calculated based on the result of class determination of the dirt substance.
[0075] In this embodiment, the degree of cleanability is determined in advance according to the class of the soiling substance, for example, "possible" for dust and scraps of paper, "somewhat difficult" for sand, mud, shoe marks, and rainwater, and "difficult" for food, drink, vomit, and animal waste. The determination of whether or not cleaning is possible is made by a threshold determination for the calculated degree of cleanability, for example, determining that a degree of cleanability of "somewhat difficult" or more is possible. In this case, food, drink, vomit, and animal waste are determined to have a degree of cleanability of "difficult" and cannot be cleaned. The degree of cleanability may be expressed as a numerical value, such as "possible / 80% or more," "somewhat difficult / 50% to less than 80%," or "difficult / less than 50%."
[0076] (Cleaning effectiveness judgment process) Here, the "cleaning effect determination process" in the second embodiment will be described. The flow of the "cleaning effect determination process" is the same as that of the first embodiment shown in Fig. 5. However, when comparing images in step S204 and determining whether dirt has expanded in step S206, the dirt detection result obtained in the "dirt detection process" in step S106 in Fig. 6 can be taken into consideration.
[0077] In step S204, processor 32 acquires the dirt detection result and compares the images of the floor surface before and after cleaning. In step S206, processor 32 considers the dirt detection result and determines whether the area of the dirt detected before cleaning has expanded due to cleaning. For example, if an area having the same color as the dirt detected by the dirt detection process expands around the dirt, it can be determined that the dirt has expanded. Also, if the shape of the dirt detected by the dirt detection process changes, it can be determined that the dirt has expanded by being stepped on.
[0078] As described above, in the second embodiment, it is possible to obtain the same effects as in the first embodiment.
[0079] Furthermore, in the second embodiment, dirt is detected before cleaning, and it is determined whether the detected dirt can be cleaned or not, and the cleaning device 10 is caused to stop cleaning in that small area, thereby preventing the dirt from spreading within the cleaning area in advance.
[0080] In the second embodiment, the presence or absence of dirt, the location of the dirt, and the type of dirt are detected before cleaning, so dirt can be cleaned reliably. In addition, in dirt detection, false detection of dirt can be prevented by excluding shadows of objects and people.
[0081] Furthermore, in the second embodiment, the result of detection of dirt is taken into consideration in determining the cleaning effect, so that it is possible to more accurately determine whether dirt is spreading.
[0082] In this embodiment, the processor 32 performs a dirt detection process, calculates the degree of cleanability, and determines whether cleaning is possible before cleaning. Instead of or in addition to this, the processor 32 may perform a dirt detection process, calculate the degree of cleanability, and determine whether cleaning is possible before the floor surface condition deteriorates and the process proceeds to step S126. Then, even if the floor surface condition deteriorates, the processor 32 may cause the cleaning device 10 to clean the same area again if it is determined that cleaning is possible.
[0083] [Third embodiment] In the second embodiment, the "cleaning effect determination process" was performed taking into consideration the dirt detection results obtained in the "dirt detection process". In contrast, in the third embodiment, if the dirt detection results are taken into consideration and the shape of the dirt has changed, the dirt may have been crushed, so the "crush detection process" is executed. Since the other configurations are the same as in the second embodiment, a description of the common parts will be omitted and only the differences will be described.
[0084] (Cleaning effectiveness judgment process) Here, the "cleaning effect determination process" in the third embodiment will be described with reference to Fig. 11. First, in step S400, the processor 32 acquires an image of the floor surface before cleaning from the RAM 36. Next, in step S402, the processor 32 acquires an image of the floor surface after cleaning from the RAM 36. Next, in step S404, the processor 32 acquires the dirt detection result and compares the images of the floor surface before and after cleaning.
[0085] Next, in step S406, processor 32 considers the dirt detection result and determines whether the shape of the dirt on the floor surface has changed from before cleaning. If the shape of the dirt has changed (YES in step S406), the process proceeds to step S408. On the other hand, if the shape of the dirt has not changed (NO in step S406), the routine ends without making a worsening determination. Next, in step S408, processor 32 executes a "crush detection process" to detect the crushing of dirt.
[0086] Here, the "crushing detection process" will be described with reference to FIG. First, in step S500, the processor 32 calculates the friction coefficient μ of the floor surface in the small area being cleaned, and stores it in the RAM 36. The friction coefficient of the floor surface can be calculated from the travel speed of the cleaning device 10. For example, when dirt containing oil is crushed, the floor surface becomes slippery, the travel speed increases, and the friction coefficient decreases. Also, when sticky dirt is crushed, the friction of the floor surface increases, the travel speed decreases, and the friction coefficient increases.
[0087] Next, in step S502, processor 32 compares the friction coefficient of the small area being cleaned with the previous friction coefficient to determine whether the friction coefficient of the floor surface has changed. The previous friction coefficient can be, for example, the friction coefficient of the immediately preceding small area or the average value of the friction coefficients of the small areas that have already been cleaned. If the friction coefficient has changed (YES in step S502), it is assumed that dirt has been crushed, and the process proceeds to step S504. On the other hand, if the friction coefficient has not changed (NO in step S502), it is assumed that dirt has not been crushed, and the routine ends.
[0088] Next, in step S504, processor 32 moves cleaning device 10 back along the path traveled to the position where the crush occurred. Next, in step S506, processor 32 causes camera 26 to capture an image of the floor surface at the position where the crush occurred, obtains an image of the floor surface, and stores the obtained image in RAM 36. Next, in step S508, processor 32 performs class determination of the soiling material from the captured image, calculates the cleanability based on the result of the class determination, and ends the routine. That is, the type of the crushed soil is identified, and the cleanability is calculated according to the type of soiling.
[0089] Returning now to the description of Fig. 11, next, in step S410, processor 32 determines whether dirt has been trampled on. If there is a change in the friction coefficient, it is determined that dirt has been trampled on. If dirt has not been trampled on (NO in step S410), the routine is terminated without making a deterioration determination. On the other hand, if dirt has been trampled on (YES in step S410), the process proceeds to step S412.
[0090] Next, in step S412, processor 32 determines whether cleaning device 10 can clean based on the cleanability calculated in the "trampling detection process." If cleaning is possible (YES in step S412), the routine ends without making a deterioration determination. For example, if the stepped-on substance is "paper waste," it is presumed to have been cleaned even if the shape of the stain has changed from before cleaning. On the other hand, if cleaning is not possible (NO in step S412), the process proceeds to step S414. In step S414, processor 32 makes a deterioration determination and ends the routine.
[0091] As described above, in the third embodiment, it is possible to obtain the same effects as in the first and second embodiments.
[0092] In the third embodiment, the dirt detected in the "dirt detection process" is detected as being crushed when the shape of the dirt changes. If the dirt is crushed, the system returns to the position where the dirt was crushed and identifies the type of dirt, allowing the system to deal with the dirt crushing more appropriately.
[0093] In addition, in the third embodiment, the type of dirt that has been crushed is identified and it is judged whether cleaning is possible again, so the deterioration judgment can be performed more carefully. This reduces the number of cases where cleaning is stopped, and improves cleaning efficiency compared to the case where the deterioration judgment is performed uniformly when the dirt has spread.
[0094] [Fourth embodiment] In the first embodiment, if the cleaning effect is not worsened as a result of the cleaning effect judgment, the cleaning of that small area is completed and the cleaning proceeds to the next small area. In contrast, in the fourth embodiment, the detection value of the dust sensor is further acquired, and if dust is floating around, the cleaning is not completed and the cleaning of that small area is restarted. Since the configuration other than this is the same as the first embodiment, only the differences will be described.
[0095] The "cleaning program" according to the fourth embodiment will be described with reference to Fig. 13. The "cleaning program" according to the fourth embodiment has the same flow as the "cleaning program" shown in Fig. 4, except for the inclusion of steps S130 and S132. For this reason, the same reference numerals are used for the common parts, and the description thereof will be omitted.
[0096] In step S120, processor 32 determines whether the condition of the floor surface in the small area has worsened as a result of cleaning. If the condition of the floor surface has not worsened (NO in step S120), the process proceeds to step S130. On the other hand, if the condition of the floor surface has worsened (YES in step S120), the process proceeds to step S126.
[0097] If the condition of the floor surface has not deteriorated, the detection value of the dust sensor 24A is obtained in step S130. Next, in step S132, it is determined whether the detection value of the dust sensor 24A is equal to or less than the allowable value. If the detection value of the dust sensor 24A is equal to or less than the allowable value (YES in step S132), the process proceeds to step S122. On the other hand, if the detection value of the dust sensor 24A exceeds the allowable value (NO in step S132), the process returns to step S114 and the cleaning is repeated.
[0098] After cleaning, the floor surface is clean, but if there is dust floating in the air, the dust will fall onto the floor surface and make the floor surface dirty. In this case, the processor 32 determines that cleaning is incomplete and causes the cleaning device 10 to continue cleaning. Alternatively or in addition to this, the processor 32 may send to the cleaning support device 12 the detection value of the dust sensor or information indicating that re-cleaning is necessary.
[0099] As described above, the fourth embodiment can provide the same effects as the first embodiment. In addition, in the fourth embodiment, cleaning continues until the detection value of the dust sensor falls below the allowable value, so that the floor surface can be substantially cleaned.
[0100] [Fifth embodiment] The fifth embodiment is a process performed on the cleaning support device 12 side. In the second embodiment, the presence or absence of dirt, the position of the dirt, and the type of dirt are transmitted to the cleaning support device 12 as dirt detection results. The dirt detection results may also include captured images of the floor and wall surfaces. The presence or absence of dirt, the position of the dirt, and the type of dirt are plotted on a map such as a bird's-eye view of the cleaning area 14 and stored in the dirt information accumulation unit 68 of the cleaning support device 12. In this way, dirt information for each cleaning area 14 is accumulated.
[0101] According to the map stored in the dirt information storage unit 68, it is possible to store locations that are easily soiled for each cleaning area 14. For example, areas near the entrances and exits of rooms are more likely to become soiled than other areas. Therefore, the cleaning support device 12 can generate the next cleaning task taking into account the locations that are easily soiled. In addition, by providing the cleaning device 10 with dirt information about the cleaning area 14 together with the cleaning task, cleaning of the cleaning area 14 becomes easier.
[0102] Furthermore, as a result of the accumulation of dirt information, information on dirt, damage, and deterioration over time is also accumulated. Examples of dirt, damage, and deterioration over time include cases where dirt cannot be completely removed and leaves stains, where scratches and ruts remain, where the carpet surface becomes frayed due to friction, and where the floor surface becomes sunburned due to sunlight. If dirt information continues for a certain period of time for the same position in the cleaning area 14, it is estimated that dirt, damage, and deterioration over time have occurred. For this reason, information indicating the need for maintenance such as replacing carpets and wallpaper, i.e., maintenance information for the facilities equipped in the cleaning area, may be generated and transmitted to an administrator or another cleaning device 10.
[0103] <Modification> The configurations of the cleaning device, cleaning system, and cleaning program described in the above embodiment are merely examples, and it goes without saying that the configurations may be changed without departing from the spirit of the present invention.
[0104] The control unit and the method described in the present disclosure may be realized by a special-purpose computer having a processor programmed to execute one or more functions embodied in a computer program. Alternatively, the device and the method described in the present disclosure may be realized by a special-purpose computer having a processor configured by a dedicated hardware logic circuit. Alternatively, the device and the method described in the present disclosure may be realized by one or more special-purpose computers configured by a combination of a processor that executes a computer program and one or more hardware logic circuits. In addition, the computer program may be stored in a computer-readable non-transitory tangible recording medium as instructions executed by the computer.
[0105] [Note] The features of the present invention are as follows. (Appendix 1) A cleaning device (10) comprising a self-position estimation unit (50) that estimates a position of the device itself, a control unit (58, 60) that controls the device itself to clean a floor surface within a cleaning area (14) while traveling autonomously based on the position estimated by the self-position estimation unit, and a cleaning effect determination unit (54) that determines cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, wherein, when the cleaning effect determination unit determines that the dirt on the floor surface has worsened, the control unit controls the device to stop traveling in the small area to be determined and to cease cleaning. (Appendix 2) The cleaning device according to claim 1, wherein the cleaning effect assessment unit assesses that the dirt on the floor surface has worsened if the dirt on the floor surface in the small area to be assessed has increased compared to before cleaning. (Appendix 3) The cleaning device according to claim 1 or 2, further comprising a notification device (30) for notifying an outside party that cleaning is to be stopped, and when cleaning is to be stopped, the control unit activates the notification device to notify an outside party that cleaning is to be stopped. (Appendix 4) The cleaning device according to any one of Appendix 1 to Appendix 3, further comprising a dirt detection unit (52) that detects dirt on the floor surface of the small area to be cleaned before cleaning, the dirt detection unit identifying the presence or absence of dirt, the position of the dirt, and the type of dirt from an image of the floor surface of the small area to be cleaned. (Appendix 5) The cleaning device according to claim 4, wherein the dirt detection unit detects dirt on the floor surface of the small area to be cleaned by comparing an image of the clean floor surface of the small area to be cleaned with an image of the floor surface immediately before cleaning. (Appendix 6) The cleaning device according to claim 4 or 5, wherein the dirt detection unit detects dirt on the floor surface of the small area to be cleaned by excluding shadows of objects and people projected onto the floor surface from dirt on the floor surface. (Appendix 7) The cleaning device according to any one of Supplementary Note 4 to Supplementary Note 6, further comprising a cleaning feasibility determination unit (56) which determines whether or not a floor surface of a small area to be cleaned can be cleaned before cleaning, wherein the cleaning feasibility determination unit calculates a degree of cleanability of the small area to be cleaned from the type of dirt identified by the dirt detection unit, and determines that cleaning of the small area to be cleaned is impossible if the calculated degree of cleanability is equal to or less than a predetermined threshold, and the control unit controls to stop cleaning of the small area to be cleaned that is determined by the determination unit to be impossible to clean. (Appendix 8) The cleaning device according to claim 7, wherein the cleaning feasibility determination unit calculates a degree of cleanability corresponding to the type of dirt identified by the dirt detection unit based on a predetermined relationship between the type of dirt and the degree of cleanability. (Appendix 9) The cleaning device according to any one of Appendix 4 to Appendix 8, wherein the cleaning effect assessment unit assesses that the dirt on the floor surface has worsened if the range of dirt in the small area to be assessed has expanded from the position of dirt identified by the dirt detection unit compared to before cleaning. (Appendix 10) The cleaning device according to any one of claims 4 to 8, wherein the cleaning effect determination unit determines that the dirt on the floor surface has worsened when it detects that uncleanable dirt has been trampled on. (Appendix 11) The cleaning device described in Appendix 10, wherein the cleaning effect assessment unit detects whether the dirt has been trampled on based on a change in the friction coefficient of the floor surface when the shape of the dirt in the small area to be assessed differs from that before cleaning based on the position of the dirt identified by the dirt detection unit. (Appendix 12) The cleaning device described in Appendix 10, wherein the cleaning effectiveness determination unit identifies the type of the crushed dirt from the image of the crushed dirt, and if the cleanability corresponding to the identified type of dirt is below a threshold, determines that the crushed dirt is an uncleanable dirt. (Appendix 13) The cleaning device according to claim 1, further comprising a dust sensor (24A) for detecting dust in the air, and the control unit controls the device to repeatedly clean the small area to be judged until the detection value detected by the dust sensor becomes equal to or less than a predetermined allowable value, regardless of the judgment result of the cleaning effect judgment unit. (Appendix 14) A cleaning system (100) comprising a cleaning device and a cleaning assistance device (12) communicatively connected to the cleaning device and assigning a cleaning task of cleaning a specific cleaning area to the cleaning device, wherein the cleaning device comprises a self-position estimation unit that estimates a position of the cleaning device, a control unit that controls the cleaning device to clean the floor surface within the cleaning area while autonomously traveling based on the position estimated by the self-position estimation unit, and a cleaning effect determination unit that determines cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, and when the cleaning effect determination unit determines that the dirt on the floor surface has worsened, the control unit controls the cleaning device to stop traveling in the small area to be determined and to cease cleaning. (Appendix 15) The cleaning system described in Appendix 14, wherein the cleaning device further includes a dirt detection unit that detects dirt on the floor surface of the small area to be cleaned before cleaning, and the cleaning device transmits dirt information for each small area of the cleaning area detected by the dirt detection unit to the cleaning support device, and the cleaning support device accumulates the dirt information received from the cleaning device in a dirt information accumulation unit (68) for each small area of the cleaning area. (Appendix 16) The cleaning system described in Appendix 15, wherein the cleaning support device generates at least one of the cleaning task and maintenance information for equipment in the cleaning area based on the dirt information accumulated in the dirt information accumulation unit. (Appendix 17) A cleaning program that causes at least one processor (32) to estimate its own position, control the device to clean the floor surface within a cleaning area while autonomously traveling based on the estimated position, judge the cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning, and control the device to stop traveling of the device and cancel cleaning in the small area to be judged if it is judged that the dirt on the floor surface has worsened. [Explanation of symbols]
[0106] 10 cleaning device, 12 cleaning support device, 14 cleaning area, 50 self-location estimation unit, 52 dirt detection unit, 54 cleaning effect determination unit, 56 cleaning feasibility determination unit, 58 travel control unit, 60 cleaning control unit, 62 report control unit
Claims
1. A self-position estimation unit (50) that estimates the position of the own device; a control unit (58, 60) that controls the device so that the device cleans a floor surface within a cleaning area (14) while autonomously traveling based on the position estimated by the self-position estimation unit; a cleaning effect determination unit (54) for determining cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning; Equipped with When the cleaning effect determination unit determines that the dirt on the floor surface has worsened, the control unit controls the device to stop traveling in the small area to be determined and to stop cleaning. Cleaning device (10).
2. The cleaning device according to claim 1 , wherein the cleaning effect determiner determines that dirt on the floor surface has worsened when dirt on the floor surface in the small area to be determined has increased compared to before cleaning.
3. The cleaning device further includes a notification device (30) for notifying the outside that cleaning is to be stopped, The cleaning device according to claim 1 , wherein the control unit, when stopping cleaning, activates the notification device to notify an outside party that cleaning is to be stopped.
4. The cleaning device further includes a dirt detection unit (52) for detecting dirt on the floor surface of the small area to be cleaned before cleaning; The cleaning device according to claim 1 , wherein the dirt detection unit identifies the presence or absence of dirt, a position of the dirt, and a type of dirt from an image of the floor surface of the small area to be cleaned.
5. The cleaning device according to claim 4 , wherein the dirt detection unit detects dirt on the floor surface of the small area to be cleaned by comparing an image of the clean floor surface of the small area to be cleaned with an image of the floor surface immediately before cleaning.
6. The cleaning device according to claim 4 , wherein the dirt detection unit detects dirt on the floor surface in the small area to be cleaned by excluding shadows of objects and figures projected onto the floor surface from dirt on the floor surface.
7. The cleaning device further includes a cleaning possibility determination unit (56) for determining whether or not the floor surface of the small area to be cleaned can be cleaned before cleaning, The cleaning possibility determination unit calculates a degree of cleanability of the small area to be cleaned from the type of dirt identified by the dirt detection unit, and determines that cleaning of the small area to be cleaned is impossible if the calculated degree of cleanability is equal to or less than a predetermined threshold value; The control unit controls the cleaning of the small area of the cleaning target determined by the cleaning feasibility determination unit as being impossible to clean to be stopped.
5. The cleaning device of claim 4.
8. The cleaning device according to claim 7 , wherein the cleaning feasibility determination unit calculates a degree of cleanability corresponding to the type of dirt identified by the dirt detection unit, based on a predetermined relationship between the type of dirt and the degree of cleanability.
9. The cleaning device according to claim 4 , wherein the cleaning effect determination unit determines that the dirt on the floor surface has worsened when the range of dirt in the small area to be determined has expanded from the position of the dirt identified by the dirt detection unit compared to before cleaning.
10. The cleaning device according to claim 4 , wherein the cleaning effect determining unit determines that dirt on the floor surface has worsened when it detects that dirt that cannot be cleaned has been trampled on.
11. The cleaning device according to claim 10, wherein the cleaning effect assessment unit detects the crushing of the dirt based on a change in the friction coefficient of the floor surface when the shape of the dirt in the small area to be assessed differs from that before cleaning based on the position of the dirt identified by the dirt detection unit.
12. The cleaning device according to claim 10, wherein the cleaning effect determination unit identifies a type of the crushed dirt from an image of the crushed dirt, and if a degree of cleanability corresponding to the identified type of dirt is equal to or lower than a threshold value, determines that the crushed dirt is an uncleanable dirt.
13. Further comprising a dust sensor (24A) for detecting dust in the air; 2. The cleaning device according to claim 1, wherein the control unit controls the device to repeatedly clean the small area to be judged until the detection value detected by the dust sensor becomes equal to or less than a predetermined tolerance value, regardless of the judgment result of the cleaning effect judgment unit.
14. A cleaning system (100) comprising a cleaning device and a cleaning assistant device (12) communicatively connected to the cleaning device and configured to assign a cleaning task to the cleaning device for cleaning a specific cleaning area, The cleaning device includes: A self-location estimation unit that estimates a location of the device itself; a control unit that controls the device so that the device cleans a floor surface within a cleaning area while autonomously traveling based on the position estimated by the self-position estimation unit; a cleaning effect determination unit that determines cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning; Equipped with When the cleaning effect determination unit determines that the dirt on the floor surface has worsened, the control unit controls the device to stop traveling in the small area to be determined and to stop cleaning. Cleaning system.
15. The cleaning device further includes a dirt detection unit that detects dirt on a floor surface of a small area to be cleaned before cleaning, and the cleaning device transmits dirt information for each small area of the cleaning area detected by the dirt detection unit to the cleaning support device; The cleaning support device accumulates the dirt information received from the cleaning device in a dirt information accumulation unit (68) for each small area of the cleaning area.
15. The cleaning system of claim 14.
16. The cleaning system according to claim 15 , wherein the cleaning support device generates at least one of the cleaning task and maintenance information for equipment included in the cleaning area based on the dirt information stored in the dirt information storage unit.
17. At least one processor (32) Estimate the location of the device itself; and controlling the device so as to clean the floor surface within the cleaning area while autonomously traveling based on the estimated position; determining a cleaning effect for each small area within the cleaning area based on images of the floor surface before and after cleaning; When it is determined that the dirt on the floor surface has worsened, the device is controlled to stop traveling and to stop cleaning in the small area that is the subject of the determination. Cleaning program.
Citation Information
Patent Citations
Movable cleaning device and control method thereof
CN106377209A
Floor processor autonomously moving in environment
JP2020030825A
Vacuum cleaner, vacuum cleaning information system, and program for vacuum cleaner
JP2021192822A
Floor treatment by an autonomous mobile robot
JP2021503334A
Mobile robot and control method of mobile robots
US20220211236A1
