Cleaning tray for cleaning robot, base station and cleaning system

Abstract

The utility model discloses a cleaning tray for a cleaning robot, a base station and a cleaning system. The cleaning tray is provided with features for visual inspection of the cleaning robot; the cleaning tray is used for assisting in cleaning a cleaning module of the cleaning robot. In this way, the detection cost of the cleaning tray is effectively reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cleaning, in particular to a cleaning tray, a base station and a cleaning system for a cleaning robot. BACKGROUND

[0002] A cleaning robot is usually used with a base station. The base station is mainly used for self-cleaning of cleaning components on the cleaning robot or charging service for the main machine. The base station has a cleaning tray. The cleaning tray is a kind of accessory for cleaning the base station, and is usually used to collect dirt and dust that the cleaning robot may bring when charging or on standby in the base station. The cleaning tray is usually detachable, which facilitates regular cleaning of the cleaning tray and keeps the base station clean.

[0003] After the cleaning tray is disassembled and cleaned, the base station bottom will be dirty if the cleaning tray is not put back on the base station, which is not easy to clean. Therefore, the related art adds in-situ detection of the cleaning tray, which is usually detected by using in-situ switches or Hall devices in the base station. UTILITY MODEL CONTENT

[0004] The cleaning tray, the base station and the cleaning system for the cleaning robot provided by the present application can effectively reduce the detection cost of the cleaning tray.

[0005] To solve the above technical problems, one technical solution adopted by the present application is to provide a cleaning tray for a cleaning robot, the cleaning tray being provided with a feature for visual detection of the cleaning robot; wherein the cleaning tray is used to assist in cleaning a cleaning module of the cleaning robot.

[0006] The feature is a coding pattern or is composed of multiple layers of colors on the cleaning tray.

[0007] The cleaning tray has a side wall, and the feature is arranged on the side wall.

[0008] The cleaning tray is a first type of tray, a second type of tray or a third type of tray; the first type of tray is suitable for a cleaning robot with a fan-shaped flat mop; the second type of tray is suitable for a cleaning robot with a disc mop; and the third type of tray is suitable for a cleaning robot with a roller mop.

[0009] To solve the above technical problems, another technical solution adopted by the present application is to provide a base station for a cleaning robot, the base station comprising: a base station body; a base; and a cleaning tray, the cleaning tray being provided with a feature for visual detection of the cleaning robot, wherein the cleaning tray is detachably arranged on the base, and the cleaning tray is used to assist in cleaning a cleaning module of the cleaning robot.

[0010] The base is provided with a support table corresponding to the cleaning tray.

[0011] The support table has a first color layer, the cleaning tray has a second color layer, and the first color layer and the second color layer have different colors.

[0012] The cleaning tray has a side wall, and the feature is arranged on the side wall.

[0013] To solve the above technical problems, another technical solution adopted by the present application is to provide a cleaning system, which comprises a cleaning robot, a base station, and a cleaning module.

[0014] The perception system comprises an image acquisition assembly configured to acquire the feature on the cleaning tray in the base station.

[0015] The cleaning tray, the base station, and the cleaning system provided by the present application have the feature arranged on the cleaning tray for visual detection by the cleaning robot. The cleaning robot can use image recognition technology to identify whether the feature exists in the image of the base station corresponding to the cleaning robot, so as to complete detection of the cleaning tray according to the identification result. Compared with the detection method using in-place switches or Hall devices in the base station, the cleaning tray detection cost is effectively reduced without additional electronic devices. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0017] Figure 1 is a structural schematic diagram of an embodiment of the cleaning tray provided by the present application;

[0018] Figure 2 is a structural schematic diagram of another embodiment of the cleaning tray provided by the present application;

[0019] Figure 3 is a structural schematic diagram of another embodiment of the cleaning tray provided by the present application;

[0020] Figure 4 is a structural schematic diagram of an embodiment of the base station provided by the present application;

[0021] Figure 5 is a structural schematic diagram of an embodiment of the base station provided by the present application;

[0022] Figure 6 is a structural schematic diagram of an embodiment of the base station provided by the present application; Figure 5a schematic diagram of an explosion;

[0023] Figure 7 is a structural schematic diagram of an embodiment of the cleaning system provided in the present application;

[0024] Figure 8 is a flow schematic diagram of an embodiment of the detection method of the cleaning tray provided in the present application;

[0025] Figure 9 is a flow schematic diagram of another embodiment of the detection method of the cleaning tray provided in the present application;

[0026] Figure 10 is a flow schematic diagram of another embodiment of the detection method of the cleaning tray provided in the present application;

[0027] Figure 11 is a flow schematic diagram of another embodiment of the detection method of the cleaning tray provided in the present application;

[0028] Figure 12 is a flow schematic diagram of another embodiment of the detection method of the cleaning tray provided in the present application;

[0029] Figure 13 is a structural schematic diagram of an embodiment of the cleaning robot provided in the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0031] In this document, reference to“an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. Those skilled in the art will understand that the embodiments described herein can be combined with other embodiments.

[0032] The cleaning robot is usually matched with a base station. The base station is mainly used for self-cleaning of the cleaning element on the cleaning robot or charging service for the main machine. The base station has a cleaning tray. The cleaning tray is a kind of accessory for cleaning the base station, and is usually used to collect dirt and dust that the cleaning robot may bring when charging or waiting in the base station. The cleaning tray is usually detachable, which facilitates regular cleaning of the cleaning tray and keeps the base station clean.

[0033] After disassembling and cleaning the cleaning tray, forgetting to put the cleaning tray back on the base station will make the bottom of the base station dirty and difficult to clean. Therefore, the related technology adds in-situ detection of the cleaning tray, which is usually achieved by using in-situ switches or Hall devices in the base station.

[0034] Therefore, the present application proposes to set a feature for visual detection of the cleaning robot on the cleaning tray, which can facilitate the cleaning robot to identify whether the feature exists in the image of the base station corresponding to the cleaning robot by using image recognition technology, so as to complete the detection of the cleaning tray according to the identification result. Compared with the detection method of using in-situ switches or Hall devices in the base station, no additional electronic devices are needed, which effectively reduces the detection cost of the cleaning tray. Further, the technology of detecting the cleaning tray by using image recognition on the cleaning robot side can be added on the basis of using in-situ switches or Hall devices in the base station. For details, refer to any of the following embodiments.

[0035] Referring to Figure 1 , Figure 1 is a structural schematic diagram of an embodiment of the cleaning tray for the cleaning robot provided by the present application. The cleaning tray 10 is provided with a feature 11 for visual detection of the cleaning robot.

[0036] In some embodiments, the cleaning robot can detect whether the cleaning tray 10 is located in the base station by detecting the feature 11.

[0037] In some embodiments, the feature 11 can be sprayed on the cleaning tray 10 in the form of a coating.

[0038] In some embodiments, the feature 11 can be embedded on the cleaning tray 10 in the form of a module structure.

[0039] In some embodiments, the feature 11 can be provided on the cleaning tray 10 in the form of adhesion.

[0040] In some embodiments, the feature 11 is a code pattern.

[0041] In some embodiments, the feature 11 is composed of multiple layers of colors on the cleaning tray 10.

[0042] In the embodiment, the feature 11 is arranged on the cleaning tray 10 for visual detection of the cleaning robot, which can facilitate the cleaning robot to identify whether the feature 11 exists in the image of the corresponding base station of the cleaning robot by using image recognition technology, so as to complete the detection of the cleaning tray 10 according to the identification result. Compared with the detection mode of using in-place switches or Hall devices in the base station, the corresponding electronic devices do not need to be additionally increased, and the detection cost of the cleaning tray 10 is effectively reduced.

[0043] Referring to Figure 2 , the cleaning tray 10 has a side wall 12, and the feature 11 is arranged on the side wall 12.

[0044] In some embodiments, the cleaning robot has different mop forms, and therefore, the structure form for cleaning the mop on the base station is also different.

[0045] Exemplarily, the mop cleaning mode of the cleaning robot with a fan-shaped flat mop is that the cleaning piece in the cleaning tank moves back and forth left and right to scrape the mop back and forth left and right.

[0046] The mop cleaning mode of the cleaning robot with a disc-shaped mop is that the mop rotates to realize rotary scraping on the cleaning rib of the cleaning tank.

[0047] The mop cleaning mode of the cleaning robot with a roller-shaped mop is that the roller rotates, and the scraping strip scrapes the outer periphery of the roller.

[0048] Therefore, the cleaning tray 10 also has different types. For example, the first type of tray can be adapted to the cleaning robot with a fan-shaped flat mop; the second type of tray can be adapted to the cleaning robot with a disc-shaped mop; and the third type of tray can be adapted to the cleaning robot with a roller-shaped mop.

[0049] In some embodiments, when the cleaning tray 10 is correctly placed in the base station, the feature 11 is directed to one side of the access area of the cleaning robot of the base station. When the image acquisition assembly on the cleaning robot is also directed to this direction, the feature 11 can exist in the acquired image.

[0050] In the embodiment, the feature 11 is arranged on the cleaning tray 10, which can facilitate the cleaning robot to identify whether the feature 11 exists in the image of the corresponding base station of the cleaning robot by using image recognition technology, so as to complete the detection of the cleaning tray 10 according to the identification result. Compared with the detection mode of using in-place switches or Hall devices in the base station, the corresponding electronic devices do not need to be additionally increased, and the detection cost of the cleaning tray 10 is effectively reduced.

[0051] Further, the feature 11 is arranged on the side wall 12 of the cleaning tray 10, which can improve the probability of the feature 11 being acquired by the cleaning robot.

[0052] Referring to Figure 3 The cleaning tray 10 is provided with a plurality of features 11 for visual detection by the cleaning robot, as shown in Figure 3 In some embodiments, the features 11 are code patterns, i.e., the cleaning tray 10 is provided with a plurality of code patterns for visual detection by the cleaning robot.

[0053] In the present embodiment, the plurality of features 11 provided on the cleaning tray 10 can facilitate the cleaning robot to identify, by using image recognition technology, whether the features 11 exist in the image of the corresponding base station of the cleaning robot, so as to complete the detection of the cleaning tray 10 according to the identification result. Compared with the detection mode using in-place switches or Hall devices in the base station, no additional electronic devices are needed, which effectively reduces the detection cost of the cleaning tray 10.

[0054] Further, the plurality of features 11 can provide more image detection targets, effectively avoiding the problem that a single feature 11 is contaminated and cannot be identified.

[0055] Referring to Figure 4 , Figure 5 and Figure 6 , the base station 100 comprises a base station body 30, a base 20 and a cleaning tray 10.

[0056] The cleaning tray 10 is provided with features 11 for visual detection by the cleaning robot, wherein the cleaning tray 10 is detachably arranged with the base 20. The cleaning tray 10 is used to assist in cleaning the cleaning module of the cleaning robot.

[0057] Further, the base 20 is provided with a support table 21 corresponding to the cleaning tray 10.

[0058] Further, the support table 21 has a first color layer, and the cleaning tray 10 has a second color layer, the colors of the first color layer and the second color layer being different. In some embodiments, the first color layer of the support table 21 is arranged on the surface of the support table 21. The second color layer of the cleaning tray 10 is arranged on the surface of the cleaning tray 10.

[0059] In some embodiments, the cleaning tray 10 has an upper surface and a lower surface, and the second color layer of the cleaning tray 10 can be arranged on the upper surface. When the cleaning tray 10 is arranged in the base station, the lower surface of the cleaning tray 10 faces the support table 21.

[0060] In some embodiments, the second color layer can be white, and the first color layer can be black.

[0061] In some embodiments, the second color layer can be black, and the first color layer can be white.

[0062] In other embodiments, the colors of the first color layer and the second color layer can be any two different colors, as long as they can be visually distinguished.

[0063] In some embodiments, the support table 21 and the base 20 can be integrally arranged.

[0064] In some embodiments, the support table 21 and the base 20 can be detachably arranged.

[0065] Further, the cleaning tray 10 has a side wall, and the feature 11 is arranged on the side wall.

[0066] Further, the base 20 includes a cleaning area and an access area 23; the cleaning tray 10 is detachably arranged in the cleaning area. The access area 23 is usually arranged in the form of a slope with a certain slope. The access area 23 is provided with anti-skid structures 24 corresponding to the drive wheels of the cleaning robot, the anti-skid structures 24 protrude from the upper surface of the access area 23 and act on the drive wheels, which can prevent the cleaning robot from slipping when getting on the seat.

[0067] In some embodiments, the base station 100 can be a dust collection base station with a base 20. The dust collection base station includes a base station body 30 and a base 20 connected to the base station body 30. In some embodiments, the base station body 30 and the base 20 are integrally formed, and in other embodiments, the base station body 30 and the base 20 are detachably connected to reduce the packaging volume. The base station body 30 is mainly used for function modules related to dust collection functions, and the base 20 is used to carry the cleaning robot, which is usually in the form of a slope with a certain slope. The base 20 is provided with anti-skid structures 24 corresponding to the drive wheels of the cleaning robot, the anti-skid structures 24 protrude from the upper surface of the base 20 and act on the drive wheels, which can prevent the cleaning robot from slipping when getting on the seat.

[0068] In some embodiments, the base station 100 can be a cleaning base station. In addition to including a base station body 30 and a base 20 connected to the base station body 30, the cleaning base station also includes guide wheels. The guide wheels are provided in multiple numbers and are used to contact the cleaning robot to guide and limit the movement of the cleaning robot, guiding the cleaning robot to dock at the accurate position of the cleaning base station.

[0069] With the cleaning robot as a reference, the guide wheels can be arranged on the left and right sides of the cleaning robot to guide the cleaning robot to get on and off the seat. In this case, the guide wheels can be arranged on the base 20 or on the base station body 30. The guide wheels can also be arranged above the cleaning robot to limit the cleaning robot in the vertical direction.

[0070] With the cleaning base station corresponding to the disc type mop as an example, the cleaning base station further comprises a cleaning tray 10 and a support table 21 for carrying the cleaning tray 10 and detachably connected with the cleaning tray 10. The support table 21 is arranged on the base 20 and can be detachably connected with the base 20 or integrally formed with the base 20. The cleaning tray 10 has a concave cleaning groove and a convex cleaning rib, the cleaning rib is provided with protruding convex parts and a water scraping rib, and the bottom wall of the cleaning groove and the cleaning rib are both provided with water leakage holes. The cleaning tray 10 is further provided with a water inlet, and clean water enters the cleaning tray through the water inlet. The support table 21 is further provided with a water guide opening in communication with the water inlet and a sewage discharge pipe in communication with the sewage collection area, the water guide opening is in communication with the clean water tank, and the sewage discharge pipe is in communication with the sewage tank.

[0071] When the cleaning robot is docked with the cleaning base station, the mop of the cleaning robot is located above the cleaning groove, when the mop is cleaned, the clean water pump sends the clean water in the clean water tank to the water guide opening and then to the water inlet, so that the clean water enters the cleaning tray 10. The cleaning robot controls the mop to rotate, and in the process of rotating the mop, the convex parts and the water scraping rib on the cleaning rib continuously scrape the mop to remove dirt on the mop and reduce the water content of the mop. The sewage generated in the process of cleaning the mop enters the sewage collection area of the support table 21 through the water leakage holes, and the sewage pump pumps the sewage in the sewage collection area into the sewage discharge pipe and finally into the sewage tank.

[0072] In order to prevent liquid from overflowing due to blockage, a water fullness detection structure such as an electrode can also be arranged in the cleaning tray 10, when the water level in the cleaning tray 10 rises to a water fullness prompt value, the clean water pump stops working, and the cleaning robot synchronously prompts the user of water fullness. Of course, water fullness detection can also be performed by other ways such as float detection, current detection, etc.

[0073] In the embodiment, the feature 11 is arranged on the cleaning tray 10, which can facilitate the cleaning robot to identify whether the feature 11 exists in the image of the cleaning robot corresponding base station by using image recognition technology, so as to complete the detection of the cleaning tray 10 according to the identification result. Compared with the detection mode of using in-place switches or Hall devices in the base station 100, no additional electronic devices are needed, and the detection cost of the cleaning tray 10 is effectively reduced.

[0074] Referring to Figure 7 , Figure 7is a structural schematic diagram of an embodiment of the cleaning system provided in the present application. The cleaning system 1000 comprises a cleaning robot 200 and a base station 100, the base station 100 being the base station 100 in any embodiment of the present application. The perception system of the cleaning robot 200 comprises an image acquisition assembly, which is used to acquire features on the cleaning tray in the base station.

[0075] In some embodiments, the cleaning robot comprises a perception system, a walking mechanism, a cleaning module, and a button module.

[0076] Referring to Figure 8 , Figure 8 is a flowchart of an embodiment of the method for detecting the cleaning tray provided in the present application. The method comprises:

[0077] Step 81: acquiring a first image of the base station corresponding to the cleaning robot.

[0078] In some embodiments, the cleaning robot can keep the pose alignment with the base station through infrared or other means during the process of returning to the base station. In this way, the base station can appear in the field of view of the image acquisition assembly of the cleaning robot.

[0079] In this case, the cleaning robot can acquire the first image of the base station corresponding to the cleaning robot by using the image acquisition assembly.

[0080] In the present embodiment, the cleaning tray is provided with features for visual detection by the cleaning robot.

[0081] Step 82: identifying whether the features exist in the first image.

[0082] In some embodiments, the features are coded patterns.

[0083] In some embodiments, the features are composed of multiple layers of colors on the cleaning tray.

[0084] In some embodiments, when the features are coded patterns, the coded patterns can be one-dimensional codes or two-dimensional codes.

[0085] In other embodiments, multiple coded patterns can be provided on the cleaning tray. Providing multiple coded patterns on the cleaning tray can effectively avoid the phenomenon that a single coded pattern is contaminated and cannot be recognized. That is, multiple features can be provided on the cleaning tray.

[0086] In some embodiments, image recognition technology can be used to identify whether the features exist in the first image. If the features exist, step 83 is performed. If the features do not exist, step 84 is performed.

[0087] In some embodiments, the following situations can cause the features not to exist in the first image.

[0088] The first kind: the feature on the cleaning tray is contaminated and cannot be recognized.

[0089] The second kind: the cleaning tray is not in the base station.

[0090] The third kind: the cleaning robot is too far away from the base station, and the image recognition technology cannot recognize the feature from the first image.

[0091] Step 83: determine that the base station has a cleaning tray.

[0092] In step 83, after determining that the base station has a cleaning tray, the cleaning robot can enter the base station and rely on the cleaning tray to clean the mop of the cleaning robot.

[0093] In some embodiments, after determining that the base station has a cleaning tray, the pose angle of the feature is calculated; and a tray adjustment reminder is performed in response to the pose angle not being within a preset range. Since the feature is arranged on the cleaning tray, the pose angle of the feature can be equivalent to the pose of the cleaning tray. If the pose angle of the feature is not within the preset range, a tray adjustment reminder is performed. If the pose angle of the feature is within the preset range, the cleaning robot can perform the next operation. In some embodiments, the feature can be a coded pattern.

[0094] In an application scenario, after detecting that the base station has a cleaning tray, it cannot be determined whether the tray in the base station is correctly placed. Therefore, it is necessary to further detect whether the cleaning tray is correctly placed. If it is detected that the cleaning tray is correctly placed, the next cleaning operation can be performed. If it is detected that the cleaning tray is not correctly placed, a tray adjustment reminder can be performed. For example, the adjustment reminder can be performed by the cleaning robot through voice broadcasting. For example, the adjustment reminder can be performed by the cleaning robot through the on-off or flicker of the corresponding indicator light. For example, the cleaning robot interacts with the base station to send a corresponding instruction to the base station. The instruction is used to instruct the base station to perform a tray adjustment reminder. For example, the base station performs an adjustment reminder through voice broadcasting. For example, the base station performs an adjustment reminder through the on-off or flicker of the corresponding indicator light.

[0095] Step 84: acquire a second image of the base station, and use the second image to detect the cleaning tray.

[0096] In some embodiments, when it is detected in the first image that the feature does not exist, the cleaning robot can be controlled to move so that the distance between the cleaning robot and the base station becomes shorter, and then the image acquisition component on the cleaning robot is used to acquire a second image of the base station at the current position again, and the second image is used to detect the cleaning tray.

[0097] In some embodiments, the use of the second image to detect the cleaning tray can also be achieved by recognizing the feature in the second image. When it is recognized that the feature exists in the second image, it is determined that the base station has a cleaning tray.

[0098] In other embodiments, the feature can carry corresponding text information. The text information can be obtained by identifying the feature. The text information can be used to represent identity information of the cleaning tray, such as a cleaning tray ID. For example, each cleaning robot can correspond to several cleaning trays, and whether the feature corresponding to the cleaning tray corresponds to the cleaning robot can be determined by identifying the feature. If it does not correspond, it is determined that the cleaning tray in the base station does not meet the requirements, and a replacement reminder can be performed. If it corresponds, it is determined that the cleaning tray in the base station meets the requirements, and the next operation can be performed. For example, the cleaning robot enters the base station and completes cleaning on the cleaning tray. In some embodiments, the feature can be a coded pattern that can carry corresponding text information.

[0099] In any embodiment of the present application, the image acquisition component on the cleaning robot can acquire a color image or a gray image.

[0100] In the present embodiment, a feature for visual detection of the cleaning robot is arranged on the cleaning tray. Whether the feature exists in the image of the base station corresponding to the cleaning robot is identified by using the image recognition technology of the cleaning robot. In this way, the detection of the cleaning tray is completed according to the identification result. Compared with the detection method using in-place switches or Hall devices in the base station, no additional electronic devices are needed, and the detection cost of the cleaning tray is effectively reduced.

[0101] Further, the image recognition technology for detecting the cleaning tray can be added to the cleaning robot on the basis of the detection using in-place switches or Hall devices in the base station.

[0102] Referring to Figure 9 , Figure 9 is a flowchart of another embodiment of the detection method of the cleaning tray provided by the present application. The method comprises:

[0103] Step 91: acquiring a first image of the base station corresponding to the cleaning robot.

[0104] Step 92: identifying whether the feature exists in the first image.

[0105] If the feature exists, step 93 is performed. If the feature does not exist, step 94 is performed.

[0106] Step 93: determining that the base station has a cleaning tray.

[0107] Step 94: acquiring a second image corresponding to the base station; wherein the acquisition distance of the second image is less than the acquisition distance of the first image.

[0108] In some embodiments, the distance between the image acquisition component and the base station can be shortened by adjusting the focal length of the image acquisition component, so that the second image corresponding to the base station is acquired by the image acquisition component after the focal length is adjusted.

[0109] In some embodiments, the distance between the image acquisition component on the cleaning robot and the base station can be shortened by moving the cleaning robot, so that the second image corresponding to the base station is acquired by the image acquisition component after the distance is shortened.

[0110] Step 95: detecting the state of the cleaning tray in the base station based on the second image.

[0111] In some embodiments, the state of the cleaning tray in the base station is detected based on the second image.

[0112] In this application, the state of the cleaning tray can be defined as a first state, a second state and a third state. The first state is used to represent that there is no cleaning tray in the base station. The second state is used to represent that the cleaning tray is not placed correctly. The third state is used to represent that the cleaning tray is placed correctly.

[0113] For example, if no feature is detected in the second image, it can be considered that there is no cleaning tray in the base station, and the state of the cleaning tray is determined to be the first state.

[0114] If a feature is detected in the second image, it can be considered that there is a cleaning tray in the base station, and the state of the cleaning tray needs to be further determined. For example, the posture angle of the feature is used to determine whether the cleaning tray is placed correctly. If the cleaning tray is placed correctly, the state of the cleaning tray is determined to be the third state. If the cleaning tray is not placed correctly, the state of the cleaning tray is determined to be the second state.

[0115] In some embodiments, the type of the cleaning tray in the base station is detected based on the second image.

[0116] For example, because the cleaning robot has different cleaning methods, the corresponding cleaning tray types are also different. Therefore, when the cleaning tray is placed in the base station, there may be a type placement error, which causes the cleaning robot to be unable to perform cleaning operations. Therefore, when it is determined that there is a cleaning tray in the base station, the type of the cleaning tray can be determined.

[0117] For example, the cleaning robot can recognize the type of the cleaning tray by recognizing the text information represented by the feature. For example, when the feature is detected in the second image or the first image, the text information represented by the feature is recognized synchronously. The type of the cleaning tray is extracted from the text information.

[0118] In some embodiments, the state and type of the cleaning tray in the base station are detected based on the second image.

[0119] Step 96: determining the detection result of the cleaning tray based on the state and / or the type.

[0120] In some embodiments, the detection result of the cleaning tray is determined based on the state.

[0121] For example, when the state of the cleaning tray is the first state, the detection result is that there is no cleaning tray in the base station.

[0122] When the state of the cleaning tray is the second state, the detection result is that the cleaning tray is not placed correctly in the base station.

[0123] When the state of the cleaning tray is the third state, the detection result is that the cleaning tray is placed correctly in the base station.

[0124] In some embodiments, the detection result of the cleaning tray is determined based on the type.

[0125] For example, the type of the cleaning tray is matched with the type of the cleaning robot. If they do not match, the detection result is that the type of the cleaning tray is not consistent. If they match, the detection result is that the type of the cleaning tray is consistent.

[0126] In some embodiments, the detection result of the cleaning tray is determined based on the state and the type.

[0127] In this embodiment, a feature for visual detection of the cleaning robot is arranged on the cleaning tray. The image recognition technology of the cleaning robot is used to identify whether the feature exists in the image of the base station corresponding to the cleaning robot. In this way, the detection of the cleaning tray is completed according to the identification result. Compared with the detection method using in-place switches or Hall devices in the base station, no additional electronic devices are needed, and the detection cost of the cleaning tray is effectively reduced.

[0128] Further, on the basis of the detection using in-place switches or Hall devices in the base station, the image recognition technology for detecting the cleaning tray can be added on the side of the cleaning robot.

[0129] Further, when the feature cannot be identified, the state and / or the type of the cleaning tray in the base station are further detected, which can improve the accuracy of the in-place detection of the cleaning tray, and the adaptability between the cleaning tray and the cleaning robot can be determined according to the type of the cleaning tray, so as to avoid the phenomenon that the cleaning tray and the cleaning robot do not match.

[0130] Referring to Figure 10 , Figure 10 FIG. 1 is a flowchart of another embodiment of the detection method of the cleaning tray provided in the present application. The method comprises:

[0131] Step 101: obtaining a first image of a base station corresponding to a cleaning robot.

[0132] Step 102: identifying whether the feature exists in the first image.

[0133] Step 103: determining that the cleaning tray exists in the base station.

[0134] Step 104: acquiring a second image corresponding to the robot of the base station; wherein the acquisition distance of the second image is less than that of the first image.

[0135] Steps 101 to 104 have the same or similar technical solutions as any embodiment of the present application, and will not be repeated here.

[0136] Step 105: acquiring feature points corresponding to the tray area in the second image.

[0137] In some embodiments, the feature extraction method can be used to acquire the feature points corresponding to the tray area in the second image.

[0138] Exemplarily, edge extraction can be performed on the second image, the image area corresponding to the tray area in the second image is extracted, and then the corresponding feature points are further extracted from the image area.

[0139] Step 106: detecting the state of the cleaning tray according to the feature points.

[0140] In some embodiments, the feature points are compared with the preset feature points; the preset feature points are obtained when the tray area has the cleaning tray; and the state of the cleaning tray is determined according to the comparison result.

[0141] Exemplarily, because there is a difference between the images when the cleaning tray exists in the base station and when the cleaning tray does not exist in the base station, one of the images can be used as a reference to extract the preset feature points as a comparison basis. For example, the image of the base station with the cleaning tray is collected, and the preset feature points are extracted from the image. These feature points represent the corresponding feature information when the cleaning tray exists in the base station.

[0142] The comparison method can be a similarity comparison method. When the similarity is higher than a first similarity threshold, the state of the cleaning tray is determined to be a third state. When the similarity is lower than the first similarity threshold and higher than a second similarity threshold, the state of the cleaning tray is determined to be a second state. When the similarity is lower than the second similarity threshold, the state of the cleaning tray is determined to be a first state.

[0143] In some embodiments, the feature points are compared with the preset feature points; the preset feature points are obtained when the tray area does not have the cleaning tray; and the state of the cleaning tray is determined according to the comparison result.

[0144] Exemplarily, there is a difference between the images when the cleaning tray exists in the base station and when the cleaning tray does not exist in the base station. Therefore, one of the images can be taken as a reference, and then a preset feature point is extracted therefrom as a comparison basis. For example, an image in which the cleaning tray does not exist in the base station is collected, and a preset feature point is extracted from the image. The feature points represent corresponding feature information when the cleaning tray does not exist in the base station.

[0145] The comparison manner can be in a similarity comparison manner. When the similarity is higher than a third similarity threshold, it is determined that the state of the cleaning tray is the first state. When the similarity is lower than the third similarity threshold and higher than a fourth similarity threshold, it is determined that the state of the cleaning tray is the second state. When the similarity is lower than the fourth similarity threshold, it is determined that the state of the cleaning tray is the third state.

[0146] Step 107: determining a detection result of the cleaning tray based on the state.

[0147] Exemplarily, when the state of the cleaning tray is the first state, the detection result is that the cleaning tray does not exist in the base station.

[0148] When the state of the cleaning tray is the second state, the detection result is that the cleaning tray is not correctly placed in the base station.

[0149] When the state of the cleaning tray is the third state, the detection result is that the cleaning tray is correctly placed in the base station.

[0150] In this embodiment, a feature for visual detection of the cleaning robot is arranged on the cleaning tray. Whether the feature exists in an image of the base station corresponding to the cleaning robot is identified by using an image recognition technology of the cleaning robot. The detection of the cleaning tray is completed according to the identification result. Compared with a detection manner in which an in-place switch or a Hall device is used in the base station, no additional electronic device needs to be added, and the detection cost of the cleaning tray is effectively reduced.

[0151] Further, on the basis of the detection of the base station by using the in-place switch or the Hall device, the technology of detecting the cleaning tray by using the image recognition on the cleaning robot side can also be added.

[0152] Further, when the feature cannot be identified, the state of the cleaning tray in the base station is further detected by using the feature point, so that the in-place detection accuracy of the cleaning tray can be improved.

[0153] Referring to Figure 11 , Figure 11 is a flowchart of another embodiment of the detection method of the cleaning tray provided in the application. The method comprises:

[0154] Step 111: acquiring a first image of a base station corresponding to a cleaning robot.

[0155] Step 112: identifying whether the feature exists in the first image.

[0156] Step 113: determining that the cleaning tray is in the base station.

[0157] Step 114: obtaining a second image corresponding to the base station; wherein the collection distance of the second image is less than that of the first image.

[0158] Steps 111 to 114 have the same or similar technical solutions as any embodiment of the present application, and will not be repeated here.

[0159] Step 115: obtaining a pixel value corresponding to the tray area in the second image.

[0160] Step 116: detecting the state of the cleaning tray according to the pixel value.

[0161] In some embodiments, the color of the cleaning tray and the color of the support table below the cleaning tray are set to different colors. Therefore, the state of the cleaning tray can be detected by using the pixel value. For example, the pixel value corresponding to the color of the cleaning tray is A, and the pixel value corresponding to the color of the support table below the cleaning tray is B, and the state of the cleaning tray can be detected by the pixel value.

[0162] For example, the pixel value B corresponding to the tray area in the second image is identified, and the state of the cleaning tray is the first state. The pixel value A corresponding to the tray area in the second image is identified, and the state of the cleaning tray is the third state, and the detection result is that the cleaning tray is correctly placed in the base station.

[0163] In some embodiments, the image can also be processed by gray scale, and the state of the cleaning tray can be detected according to the corresponding gray scale value.

[0164] For example, the average gray scale value in the tray area is obtained according to the pixel value. For example, the color of the cleaning tray surface is black, and the color of the support table is white.

[0165] Wherein, in response to the average gray scale value being greater than a first threshold value, the state of the cleaning tray is determined to be the first state; the first state is used to represent that there is no cleaning tray in the base station.

[0166] When the average gray scale value is greater than the first threshold value, it means that in the second image, there are more support tables below the cleaning tray in the tray area.

[0167] Wherein, in response to the average gray scale value being less than the first threshold value and greater than a second threshold value, the state of the cleaning tray is determined to be the second state; the second state is used to represent that the cleaning tray is not correctly placed.

[0168] When the average gray value is less than the first threshold value and greater than the second threshold value, it indicates that there are more cleaning trays in the tray area in the second image, but the cleaning trays are not placed correctly.

[0169] When the average gray value is less than the second threshold value, it indicates that there are almost all cleaning trays in the tray area in the second image, indicating that the cleaning trays are placed correctly.

[0170] When the average gray value is less than the second threshold value, it indicates that there are almost all cleaning trays in the tray area in the second image, indicating that the cleaning trays are placed correctly.

[0171] In some embodiments, the judgment basis of the average gray value can be set according to the color of the cleaning tray and the color of the support table below the cleaning tray. For example, the surface color of the cleaning tray is white, and the color of the support table is black.

[0172] For example, the average gray value in the tray area is obtained according to the pixel value. The surface color of the cleaning tray is white, and the color of the support table is black.

[0173] When the average gray value is greater than the third threshold value, it indicates that there are almost all cleaning trays in the tray area in the second image, indicating that the cleaning trays are placed correctly.

[0174] When the average gray value is greater than the third threshold value, it indicates that there are almost all cleaning trays in the tray area in the second image, indicating that the cleaning trays are placed correctly.

[0175] When the average gray value is less than the third threshold value and greater than the fourth threshold value, it indicates that there are more cleaning trays in the tray area in the second image, but the cleaning trays are not placed correctly.

[0176] When the average gray value is less than the third threshold value and greater than the fourth threshold value, it indicates that there are more cleaning trays in the tray area in the second image, but the cleaning trays are not placed correctly.

[0177] When the average gray value is less than the fourth threshold value, it indicates that there are more cleaning trays below the support table in the tray area in the second image.

[0178] When the average gray value is less than the fourth threshold value, it indicates that there are more cleaning trays below the support table in the tray area in the second image.

[0179] Step 117: determining the detection result of the cleaning tray based on the state.

[0180] In the embodiment, features for visual detection of the cleaning robot are arranged on the cleaning tray. Whether the features exist in the image of the base station corresponding to the cleaning robot is identified by using image recognition technology of the cleaning robot. The detection of the cleaning tray is completed according to the identification result. Compared with the detection mode of using in-place switches or Hall devices in the base station, the corresponding electronic devices do not need to be additionally added, and the detection cost of the cleaning tray is effectively reduced.

[0181] Further, on the basis of the detection of the base station using in-place switches or Hall devices, the technology of detecting the cleaning tray by using image recognition on the cleaning robot side can be added.

[0182] Further, when the features cannot be identified, the state of the cleaning tray in the base station is further detected by the color difference between the cleaning tray and the base support table, so that the in-place detection accuracy of the cleaning tray can be improved.

[0183] Reference Figure 12 , Figure 12 is a flowchart of another embodiment of the detection method of the cleaning tray provided by the present application. The method comprises:

[0184] Step 121: acquiring a first image of a base station corresponding to a cleaning robot.

[0185] Step 122: identifying whether the features exist in the first image.

[0186] Step 123: determining that the base station has a cleaning tray.

[0187] Step 124: acquiring a second image corresponding to the base station robot; wherein the acquisition distance of the second image is less than the acquisition distance of the first image.

[0188] Steps 121 to 124 have the same or similar technical solutions as any embodiment of the present application, and will not be repeated here.

[0189] Step 125: detecting the state and / or type of the cleaning tray in the base station corresponding to the second image by using a neural network model.

[0190] In some embodiments, the neural network model can be trained in advance by using images of the base station with the cleaning tray and / or images of the base station without the cleaning tray, to obtain the neural network model that can detect the state and / or type of the cleaning tray in the base station corresponding to the second image.

[0191] In some embodiments, the neural network model can detect the state and / or type of the cleaning tray corresponding to the second image in the base station. As can be defined as the state of the cleaning tray as a first state, a second state and a third state. Among them, the first state is used to represent that there is no cleaning tray in the base station. The second state is used to represent that the cleaning tray is not placed correctly. The third state is used to represent that the cleaning tray is placed correctly.

[0192] Step 126: Determine the detection result of the cleaning tray based on the state and / or type.

[0193] In an application scenario, the cleaning robot is a sweeping robot. The cleaning tray is provided with a coded pattern for visual detection. The application of the technical solution of the present application to the sweeping robot is as follows:

[0194] During the process of returning to the base station, the sweeping robot keeps the posture aligned with the base station through infrared and other means. Therefore, the calculated inclination angle of the tray relative to the sweeping robot can be equivalent to the angle of the cleaning tray relative to the base station. When the sweeping robot is close to the base station, the camera (image acquisition component) on the sweeping robot acquires an image inside the base station. Then in the image, the features of the coded pattern are searched. If the searched features of the coded pattern are the same as the pre-set features, it is considered that the coded pattern and the cleaning tray are in the base station.

[0195] If the coded pattern exists, the corner points corresponding to the coded pattern need to be extracted from the image. Since the structural parameters of the coded pattern are known, according to the pixel relationship between the corner points and the actual distance between the corner points in the space, an equation set related to the posture angle of the coded pattern can be constructed. By solving the equation set, the posture angle of the coded pattern relative to the sweeping robot can be obtained. Since the sweeping robot and the base station have been aligned, the posture angle can be considered as the relative posture angle of the cleaning tray and the base station. If the posture angle exceeds the normal range, it means that the cleaning tray is installed with a skew, and an alarm needs to be given to remind the user to adjust. If the posture angle is normal, the sweeping robot returns to charging normally.

[0196] If the coded pattern is not detected, the robot will move forward again to climb the base station base, and take a picture of the cleaning tray at a closer position. Since the support table at the bottom of the cleaning tray has a white color block, and the cleaning tray is all black, the color boundary feature at the tray position can be detected to determine whether the tray is in place. For example, the first method: detecting structural feature points in the image, using ORB, SIFT, etc. If the extracted feature points are similar to the design effect of the cleaning tray bottom support table, it means that the cleaning tray bottom support table is exposed, and the cleaning tray is not in place. The second method: calculating the mean value of the gray value in the specific area of the cleaning tray. If the mean value is greater than the set threshold, it means that the area is white, and the tray is not in place. The third method: using deep learning scheme, collecting more data and manually labeling the two states of the cleaning tray in place and not in place, and training the deep learning model to directly classify the cleaning tray in place / not in place.

[0197] The above two schemes of identifying the coded pattern and detecting the tray position feature can ensure the accuracy of the cleaning tray in place detection.

[0198] In some embodiments, the robot can use any of the above technical solutions, which will not be repeated here.

[0199] In another application scenario, the base station is provided with an in-place switch or Hall device to detect the cleaning tray. Based on this, during the cleaning robot returning to the base station, the cleaning robot first interacts with the base station to know whether the cleaning tray is in the base station. If the base station replies that the cleaning tray cannot be detected, it may be that the in-place switch or Hall device is faulty. In order to reduce the impact of the in-place switch or Hall device failure on the cleaning robot, the cleaning robot can directly use any of the above technical solutions to detect the cleaning tray.

[0200] If the base station replies that the cleaning tray is detected, but there is still a problem that the cleaning tray is not placed correctly or the type is not correct, the cleaning robot can directly use any of the above technical solutions to detect the cleaning tray to detect the type and / or state of the cleaning tray.

[0201] That is, the cleaning tray detection scheme of the present application can be used in cooperation with the scheme of setting an in-place switch or Hall device on the base station to detect the cleaning tray, so as to make up for the defects of using the base station electronic device to detect the cleaning tray.

[0202] Referring to Figure 13 , Figure 13is a structural schematic diagram of an embodiment of the cleaning robot provided in the present application. The cleaning robot 200 comprises a robot main body 201, an image acquisition assembly 202, and a processor 203. The image acquisition assembly 202 is arranged on the robot main body 201. The processor 203 is arranged on the robot main body 201 and is coupled to the image acquisition assembly 202, and is configured to receive images sent by the image acquisition assembly 202 and implement the method provided in any of the above embodiments.

[0203] In summary, the detection method of the cleaning tray, the cleaning robot, and the cleaning system provided in the present application set a feature for visual detection of the cleaning robot on the cleaning tray, and use the image recognition technology of the cleaning robot to identify whether the feature exists in the image of the base station corresponding to the cleaning robot. In this way, the detection of the cleaning tray is completed according to the identification result. Compared with the detection method using in-place switches or Hall devices in the base station, no additional electronic devices are needed, and the detection cost of the cleaning tray is effectively reduced.

[0204] Further, on the basis of the detection using in-place switches or Hall devices in the base station, the technology of detecting the cleaning tray using image recognition on the cleaning robot side can also be added.

[0205] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other manners. For example, the embodiments of the device described above are merely schematic, and the division of the circuit or unit is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0206] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0207] In addition, each functional unit in the various embodiments of the present application can be integrated into one processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0208] The above description is merely an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation according to the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A cleaning tray for a robot, characterized in that, The cleaning tray is provided with a feature for visual detection by the cleaning robot; wherein the cleaning tray is used to assist in cleaning the cleaning module of the cleaning robot.

2. The cleaning tray of claim 1, wherein, The feature is a coded pattern or the feature is composed of multiple layers of color on the cleaning tray.

3. The cleaning tray of claim 1, wherein, The cleaning tray has a side wall, and the feature is arranged on the side wall.

4. The cleaning tray of claim 1, wherein, The cleaning tray is a first type of tray, a second type of tray or a third type of tray; wherein the first type of tray is adapted for a cleaning robot with a fan-shaped flat mop; wherein the second type of tray is adapted for a cleaning robot with a disc-shaped mop; wherein the third type of tray is adapted for a cleaning robot with a roller-type mop.

5. A base station for a cleaning robot, characterized in that, The base station comprises: a base station body; a base; a cleaning tray provided with a feature for visual detection by the cleaning robot, wherein the cleaning tray is detachably arranged on the base, and the cleaning tray is used to assist in cleaning the cleaning module of the cleaning robot.

6. The base station of claim 5, characterized in that, The base is provided with a support table corresponding to the cleaning tray.

7. The base station of claim 6, characterized in that, The support table has a first color layer, and the cleaning tray has a second color layer, and the colors of the first color layer and the second color layer are different.

8. The base station of claim 5, wherein, The cleaning tray has a side wall, and the feature is arranged on the side wall.

9. A cleaning system characterized by, The cleaning system comprises: a cleaning robot comprising a perception system, a walking mechanism, a cleaning module and a key module; a base station as claimed in any one of claims 4-8.

10. The cleaning system of claim 9, wherein, The perception system comprises an image acquisition component for acquiring the feature on the cleaning tray in the base station.

Images