Self-cleaning control method and cleaning system of manipulator

Abstract

The embodiment of the invention discloses a self-cleaning control method of a manipulator and a cleaning system. Self-moving cleaning equipment comprises the manipulator and an image acquisition module, the self-cleaning control method of the mechanical arm comprises the steps that a first task for a target task area is determined, the first task comprises moving a to-be-moved object in the target task area, and in the process of executing the first task, the to-be-moved object is moved through the mechanical arm according to the type of the to-be-moved object existing in an image collected by an image collection module; and triggering the manipulator to perform self-cleaning based on the object type of the to-be-moved object. The mechanical arm moves the to-be-moved object according to the type in the cleaning process, the mechanical arm cleans the to-be-moved object according to the type in a clean state as far as possible through classification arrangement and triggering of self-cleaning, dirt crossing and dirt accumulation are avoided, and therefore it is avoided that dirt which does not exist originally appears on the arranged object, and the cleaning efficiency is improved. And the comprehensive cleaning and tidying effects are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of automatic cleaning technology, and in particular to a self-cleaning control method and a cleaning system for a robot. Background Art

[0002] With the continuous development of electronic technology, various forms of smart homes have begun to appear in people's lives, providing users with convenience in many aspects and improving their quality of life. For example, self-propelled cleaning devices can free people from a large part of their time spent on housework, allowing them to have more time to experience the richness of life.

[0003] The floor cleaning component installed at the bottom of the self-moving cleaning equipment can clean small garbage and dirt on the ground covered with various materials. The manipulator installed on the self-moving cleaning component can sort out larger garbage or other scattered objects. The floor cleaning component and the manipulator can comprehensively realize the comprehensive cleaning and sorting of the ground.

[0004] The inventors found that when using existing self-propelled cleaning equipment to comprehensively clean and organize the ground, dirt appeared on the objects after organization that was not originally there, and the comprehensive cleaning and organization effect was poor. Summary of the Invention

[0005] The present invention provides a self-cleaning control method and a cleaning system for a manipulator, so as to solve the technical problem that the existing self-moving cleaning equipment performs comprehensive cleaning and tidying of the ground, but the objects after tidying appear dirty and non-existent, resulting in poor comprehensive cleaning and tidying effects.

[0006] In a first aspect, an embodiment of the present invention provides a self-cleaning control method for a manipulator, wherein the self-cleaning control method for the manipulator is used for a self-moving cleaning device, wherein the self-moving cleaning device includes a manipulator and an image acquisition module; the self-cleaning control method for the manipulator includes:

[0007] Determining a first task for the target task area, the first task comprising moving the object to be moved in the target task area to a corresponding target placement area;

[0008] During the execution of the first task, the object to be moved is moved by the manipulator according to the type of the object to be moved present in the image captured by the image capture module;

[0009] Trigger the robot to self-clean based on the object type being moved.

[0010] Wherein, in the process of performing the first task, moving the object to be moved by the manipulator according to the object type of the object to be moved in the image captured by the image capture module includes:

[0011] During the execution of the first task, obtaining images captured by the image acquisition module;

[0012] Identify the object to be moved and its type in the image;

[0013] When the object to be moved meets a preset first moving condition, the object to be moved is moved by the manipulator.

[0014] Wherein, when the object to be moved meets the preset first movement condition, moving the object to be moved by the manipulator includes one or more of the following combination methods:

[0015] When the object to be moved is of the same type as the object to be moved in the previous move, the object to be moved is moved by the manipulator;

[0016] When a preset number of objects to be moved have not been moved after the previous movement of the objects to be moved, the objects to be moved are moved by the manipulator;

[0017] When a first preset time has passed since the last movement of the object to be moved, the object to be moved is moved by the manipulator;

[0018] When the cleaning area after the object to be moved is moved the last time reaches the first preset area, the object to be moved is moved to the corresponding target placement area by the robot.

[0019] The self-cleaning control method of the manipulator further includes:

[0020] Recording objects to be moved that do not meet the preset first movement condition;

[0021] After completing the supplementary cleaning judgment for all objects to be moved, the recorded objects to be moved are moved by the manipulator according to the recorded object type. The supplementary cleaning judgment includes judging whether each object to be moved meets the first movement condition.

[0022] Wherein, in the process of performing the first task, moving the object to be moved by the manipulator according to the object type of the object to be moved in the image captured by the image capture module includes:

[0023] Collect images of the target task area to obtain an image set covering the target task area;

[0024] Perform image processing on the images in the image set to obtain the objects to be moved and the corresponding object types in the target task area;

[0025] During the execution of the first task, the objects to be moved are classified and moved by the manipulator according to the object type. The classified movement includes moving objects to be moved of the same object type.

[0026] In the process of executing the first task, the objects to be moved are classified by object type by the manipulator, including:

[0027] Classify and sort the objects to be moved according to their type and the order in which they are grasped, to obtain a subset of objects corresponding to each object type that includes the movement order;

[0028] According to the order of the object subsets, move the objects to be moved in each object subset;

[0029] The movement sequence includes a preset movement sequence and / or a movement sequence determined according to the degree of dirtiness of each object type.

[0030] Among them, triggering the manipulator to perform self-cleaning based on the type of the object to be moved includes:

[0031] After all objects to be moved are moved, the robot is triggered to perform self-cleaning;

[0032] During the self-cleaning process, the movement of the robot is controlled to cooperate with the self-cleaning of the robot.

[0033] Among them, triggering the manipulator to perform self-cleaning based on the type of the object to be moved includes:

[0034] Upon completion of movement of an object of one type to be moved, triggering the manipulator to perform self-cleaning; and / or

[0035] When the movement of an object to be moved of a type of object with a degree of dirtiness exceeding a preset threshold is completed, the manipulator is triggered to perform self-cleaning.

[0036] Among them, the target task area includes an area determined by a map pre-stored in the self-mobile cleaning device or a temporarily selected area sent by the control terminal; the temporarily selected area is determined according to the received area selection operation, and the area selection operation is used to determine one or more sub-areas from the map pre-stored in the self-mobile cleaning device.

[0037] In a second aspect, embodiments of the present application provide a cleaning system for a base station. The cleaning system includes a water tank, a first cleaning area, and a second cleaning area. The first cleaning area and the second cleaning area are connected and share a drainage channel. The water tank is used to supply water for cleaning in the first cleaning area and the second cleaning area.

[0038] The first cleaning area is provided with a first cleaning component, and the second cleaning area is provided with a second cleaning component; the first cleaning component is used to clean the cleaning component of the self-moving cleaning equipment located in the first cleaning area, and the second cleaning component is used to clean the robot to be cleaned located in the second cleaning area, and the robot to be cleaned is the robot of the self-moving cleaning equipment.

[0039] In the aforementioned manipulator self-cleaning control method and cleaning system, the self-moving cleaning device includes a manipulator and an image acquisition module; the manipulator self-cleaning control method includes: determining a first task for a target task area, the first task including moving an object to be moved in the target task area; in the process of executing the first task, moving the object to be moved by the manipulator according to the object type of the object to be moved present in the image captured by the image acquisition module; and triggering the manipulator to self-clean based on the object type of the object to be moved. During the cleaning process, the manipulator moves the moving objects according to their type. By classifying and sorting the movement and triggering self-cleaning, the manipulator treats the moving objects as cleanly as possible and cleans them by type, avoiding cross-contamination and accumulation of dirt, thereby preventing the appearance of dirt that was not originally present on the sorted objects, and improving the overall cleaning and sorting effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0041] Figure 1 A flow chart of the method for self-cleaning control of a manipulator provided in an embodiment of the present application.

[0042] Figure 2 This is a schematic diagram of the overall structure of the self-moving cleaning device provided in an embodiment of the present application.

[0043] Figure 3 A schematic diagram of the distribution of objects to be cleaned provided in an embodiment of the present application.

[0044] Figure 4 and Figure 5 Schematic diagram of the process of moving the object to be moved to obtain an image during the cleaning process.

[0045] Figure 6 This is a schematic diagram of the global patrol process.

[0046] Figure 7 Schematic diagram of the process of moving the object to be moved after obtaining an image covering the target task area.

[0047] Figure 8 A schematic diagram of the structure of a base station provided in an embodiment of the present application.

[0048] Figure 9 This is a schematic diagram of a self-moving cleaning device using a robotic arm to extend the gripper into the second cleaning area for self-cleaning.

[0049] Figure 10 This is a schematic diagram of the self-moving cleaning device disassembling the gripping head to the second cleaning area for self-cleaning.

[0050] Figure 11 Schematic diagram of the hardware structure of the self-moving cleaning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] To make the objectives, technical solutions, and advantages of this application more apparent, embodiments of the present application will be further described in detail below with reference to the accompanying drawings. It will be understood that the specific embodiments described herein are intended to illustrate the present invention, not to limit it. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all of the components.

[0052] It should be noted that due to space limitations, this application specification does not enumerate all optional implementation methods. After reading this application specification, those skilled in the art should be able to understand that as long as the technical features do not contradict each other, any combination of technical features can constitute an optional implementation method.

[0053] Each embodiment is described in detail below.

[0054] Existing self-mobile cleaning equipment can free people from a large part of their time in housework, so that they can have more time to experience the richness of life.

[0055] The floor cleaning component installed at the bottom of the self-moving cleaning equipment can clean small garbage and dirt on the ground covered with various materials. The manipulator installed on the self-moving cleaning component can sort out larger garbage or other scattered objects. The floor cleaning component and the manipulator can comprehensively realize the comprehensive cleaning and sorting of the ground.

[0056] The inventors found that when using existing self-propelled cleaning equipment to comprehensively clean and organize the ground, dirt appeared on the objects after organization that was not originally there, and the comprehensive cleaning and organization effect was poor.

[0057] The inventors further analyzed the process of implementing comprehensive floor cleaning and sorting by existing self-propelled cleaning equipment using floor cleaning components and manipulators and found that when self-propelled cleaning equipment uses manipulators to sort large garbage or other scattered objects, the floor cleaning components are usually the primary cleaning targets for small garbage and dirt, with cleaning efficiency as the main principle. The sorting of large garbage or other scattered objects is quite random. This random processing causes the manipulator to come into contact with large garbage or other scattered objects without restraint, resulting in the possibility that heavily contaminated large garbage may cross-contaminate other, more clean scattered objects through the manipulator. Furthermore, as the number of objects contacted by the manipulator increases, the manipulator itself may become more contaminated. Direct contact between the manipulator and scattered objects may also cause contamination of the scattered objects.

[0058] In order to solve the technical problem that dirt that did not originally exist appears on the objects after being sorted, and the overall cleaning and sorting effect is poor, the inventor, based on the above analysis of the cleaning process of the self-moving cleaning device, proposes a self-cleaning control method and cleaning system for the manipulator in the embodiment of the present application. The self-moving cleaning device includes a manipulator and an image acquisition module; the self-cleaning control method of the manipulator includes: determining a first task for the target task area, the first task includes moving the object to be moved in the target task area, and in the process of executing the first task, moving the object to be moved by the manipulator according to the type of the object to be moved in the image captured by the image acquisition module; triggering the manipulator to perform self-cleaning based on the object type of the object to be moved. During the cleaning process, the manipulator moves the moving objects according to their type. By classifying and sorting and triggering self-cleaning, the manipulator treats the moving objects as clean as possible and cleans them according to their type, avoiding cross-contamination and accumulation of dirt, thereby avoiding dirt that did not originally exist on the objects after being sorted, and improving the overall cleaning and sorting effect.

[0059] The self-propelled cleaning device may include a body, a processor, one or more cleaning components, one or more sensors, etc. The body may be round, square, or other shapes. For example, the front portion of the body may be round, and the rear portion may be square. The cleaning components may be round, square, multi-branched, or other shapes (such as semicircular, arc-shaped, triangular, or other special shapes). A round shape facilitates the cleaning component's rotational cleaning, while shapes other than round facilitate cleaning corners. The cleaning components may include a side brush, a center sweeper (also known as a floor brush or roller brush), and a rag tray (also known as a mop tray). The side brush collects foreign matter, causing it to move toward the center of the bottom of the self-propelled cleaning device and collect it at the bottom of the self-propelled cleaning device. The center sweeper sweeps foreign matter from the bottom of the self-propelled cleaning device and allows it to enter the dust collection box through the suction port. The rag tray is used for mopping or mopping the floor, and is provided with a rag. The self-propelled cleaning device is provided with a water tank, and water in the tank flows through a hole to the rag, wetting the rag, which is then used for mopping the floor.

[0060] Foreign objects that can be cleaned by the self-moving cleaning device include but are not limited to dust, hair, pet feces, etc. Sensors may include lidar sensors (such as triangulation sensors, TOF sensors, etc.), infrared sensors, line laser sensors, edge sensors, visual sensors (such as cameras, etc.), posture sensors, etc. The sensors are used to detect various status information of the self-moving cleaning device itself or its surroundings. For example, a line laser sensor is used to detect obstacle information representing one or more obstacles. The processor can control the self-moving cleaning device based on the status information detected by the sensor. Among the sensors, the sensor used to detect obstacle information is defined as a ranging sensor. Different types of ranging sensors can emit specific signals (such as laser signals, infrared signals) and receive the reflection signal of the specific signal from the obstacle. Then, based on the time difference between emission and reception and the direction of emission, the relative position relationship between the obstacle and itself is determined to complete the ranging. The specific number and type of ranging sensors are not limited.

[0061] Please refer to Figure 1 , which is a flow chart of the method for the self-cleaning control method of the manipulator provided in the embodiment of the present application. The self-cleaning control method of the manipulator is exemplarily as follows Figure 2 The self-moving cleaning device 10 shown is implemented, and the self-moving cleaning device 10 includes a manipulator 14 and an image acquisition module; Figure 2 The self-propelled cleaning device 10 in the figure shows the image acquisition module 11 described above. The image acquisition module 11 can be equipped with a fill light 12 to provide fill light for the image acquisition of the image acquisition module 11 in low light conditions. In addition, a side brush 13 is shown. The image acquisition module 11 is located on the front side of the self-propelled cleaning device 10, and a floor cleaning component is located at the bottom of the self-propelled cleaning device 10. It should be understood that Figure 2 The self-moving cleaning device 10 may also include other cleaning components and various sensors to comprehensively implement the established cleaning functions, which are not specifically described here.

[0062] The manipulator 14 in the embodiment of the present application may include a main skeleton, a gripping head 141, a drive motor, a controller and related sensors, etc. The controller is used to control the movement of the manipulator 14 through the drive motor, and the related sensors monitor the position, speed, strength and other parameters of the manipulator 14 in real time and feed back to the controller to improve the accuracy and stability of the controller's control of the manipulator 14. The specific structure of the manipulator 14 can refer to the existing technology and will not be repeated in this embodiment.

[0063] like Figure 1 As shown, the self-cleaning control method of the manipulator includes but is not limited to steps S110 to S130:

[0064] Step S110: determining a first task for the target task area, where the first task includes moving an object to be moved in the target task area.

[0065] The self-mobile cleaning device, in response to a user's control command or a preset timed first task, begins executing operations related to the first task in a target task area. The target task area includes an area determined by a map stored in the self-mobile cleaning device or a temporarily selected area transmitted by a control terminal; the temporarily selected area is determined based on a received area selection operation, which is used to determine one or more sub-areas from the map stored in the self-mobile cleaning device.

[0066] In a specific application scenario, for example, the first task involves the user determining a target task area based on the impact range of indoor activities, and then performing a preset area selection operation on the control terminal of the self-mobile cleaning device (e.g., a mobile phone with a control application installed), and determining one or more sub-areas based on the displayed map pre-stored by the self-mobile cleaning device. For example, in a case where the overall indoor cleaning state is good, and only the children's activity area has many objects placed in a messy manner due to children's activities, the user can perform an area selection operation when the control terminal passes by, determine one or more sub-areas covering the children's activity area on the displayed map pre-stored by the self-mobile cleaning device, and then instruct the self-mobile cleaning device to move the objects to be moved in the sub-areas to the corresponding target placement areas.

[0067] The first task may be, for example, a preset timed first task or the user specifies that the self-mobile cleaning device performs global cleaning of the room according to the map based on the indoor cleaning status. At this time, the target task area includes all areas determined by the map pre-stored by the self-mobile cleaning device. The first task includes moving the object to be moved in the target task area to the corresponding target placement area, and also includes cleaning the target task area.

[0068] Step S120: During the execution of the first task, the object to be moved is moved by the manipulator according to the object type of the object to be moved present in the image captured by the image capture module.

[0069] Step S130: triggering the robot arm to perform self-cleaning based on the type of the object to be moved.

[0070] In the embodiment of the present application, considering that in the process of implementing the self-cleaning control method of the manipulator, the object to be moved and the self-cleaning of the manipulator may be moved alternately according to the type of object, and the process of triggering the self-cleaning of the manipulator is highly related to the process of moving the object to be moved, the specific implementation process of step S120 and step S130 is comprehensively described here.

[0071] The self-moving cleaning device responds to the user's control instruction or the preset timed first task and starts to perform the first task on the target task area. Because of the presence of the manipulator, the self-moving cleaning device can not only clean the small garbage and dirt on the ground through the ground cleaning component at the bottom, but also organize larger objects through the manipulator, such as books, shoes, toys, etc. In the embodiment of the present application, objects scattered on the ground that are not in their original storage position are defined as objects to be moved. The manipulator can specifically organize larger objects by grabbing, pushing, etc. The process of organizing a single larger object, such as the process of returning the object to its original storage position or trash can (i.e., the target placement area) by grabbing or pushing, can refer to the existing related technology and will not be explained in detail here.

[0072] In an embodiment of the present application, the process of moving the object to be moved to the corresponding target placement area is controlled as a whole, that is, according to the type of object to be moved in the image captured by the image acquisition module, the object to be moved to the corresponding target placement area by a robotic arm, and overall, objects to be moved of the same type are moved in one stage as much as possible.

[0073] In one optional implementation, the self-moving cleaning device obtains type parameters of the objects to be moved before executing the first task. The type parameters are sent by the control terminal or read from a preset storage space. That is, the self-moving cleaning device can use the type parameters entered by the user at the control terminal, or pre-stored type parameters, as a reference for movement based on object type after identifying the objects to be moved. The type parameters can include how the objects to be moved are classified by type and the order in which different object types should be moved. Generally speaking, objects with similar or similar usage attributes or general cleanliness levels are classified into the same object type. For example, clothes, socks, and towels can be classified into the same object type; fruit peels and used paper towels can also be classified into the same object type. The movement order can be to prioritize clean objects, which is equivalent to moving dirty objects last, returning to the base station for cleaning by the robot arm, and then concluding all cleaning operations. This ensures that a clean robot arm will be available to move clean objects the next time the first task is executed. Alternatively, the self-moving cleaning device can prioritize dirty objects, which is equivalent to moving clean objects last, returning directly to the base station, and concluding all cleaning operations. This allows dirty objects to be moved directly the next time the first task is executed.

[0074] In a specific implementation, there are multiple object type classification methods, and different types of classification methods correspond to different levels of classification precision. Each first task corresponds to one object type classification method. For example, in a relatively rough classification method, object types include: clothing (including clothes, socks, towels), footwear (shoes), toys, and sundries (paper towels); in a more refined classification method, object types include specific clothing styles, shoe styles, toy types, paper towel brands, etc. An exemplary cleaning order, for example, first grabs clothing, then grabs footwear, then grabs toys, and finally grabs sundries.

[0075] The self-propelled cleaning device detects moving objects, including image detection based on images captured by an image acquisition module and detection by sensors within the self-propelled cleaning device. If the image acquisition module and sensors are calibrated within the self-propelled cleaning device based on the same coordinate system, the moving objects identified in the images can be mapped and processed within the sensor's detection results, and the robotic arm can be controlled to move them by grasping and / or pushing. Specifically, the process of identifying moving objects from images can be implemented using a pre-trained image recognition model.

[0076] In an optional implementation, the image captured by the image acquisition module can be obtained during the execution of the first task for identification, and the object type can be moved based on the identification result, that is, during the execution of the first task, the object to be moved is moved by the manipulator according to the type of the object to be moved in the image captured by the image acquisition module, including: during the execution of the first task, the image captured by the image acquisition module is obtained; the object to be moved and its object type are identified in the image; and when the object to be moved meets the preset first movement condition, the object to be moved is moved by the manipulator, that is, when the object to be moved meets the preset first movement condition, the object to be moved is moved to the corresponding target placement area by the manipulator.

[0077] In a specific implementation, the first movement condition includes one or more of: the object to be moved is the same type as the object to be moved last time, a preset number of objects to be moved have not moved since the last time the object to be moved was moved, a first preset time has passed since the last time the object to be moved was moved, and a cleaning area after the last time the object to be moved was moved has reached a first preset area. That is, when the object to be moved meets the preset first movement condition, the object to be moved by the manipulator includes one or more of the following combined methods: when the object to be moved is the same type as the object to be moved last time, the object to be moved is moved by the manipulator; when a preset number of objects to be moved have not moved since the last time the object to be moved was moved, the object to be moved is moved by the manipulator; when a first preset time has passed since the last time the object to be moved was moved, the object to be moved is moved by the manipulator; when the cleaning area after the last time the object to be moved was moved has reached a first preset area, the object to be moved to the corresponding target placement area by the manipulator.

[0078] In a specific application scenario, when the self-moving cleaning device performs the first task, it identifies the objects to be moved in real time. After identifying the objects to be moved, it first determines the object type and compares it with the object type of the last object to be moved. If the object types are the same, the robot arm is controlled to move the object to be moved to the corresponding target placement area; if the object types are different, the object to be moved is skipped and the first task is continued. Considering that the distribution positions of the objects to be moved have a certain degree of randomness, in order to avoid a large number of objects to be moved not moving, it can be determined whether to move based on other states in the first movement condition, such as if the number of objects to be grabbed of different categories reaches 3 within 10 minutes, or if the cleaning area exceeds 50 square meters and different categories of objects to be grabbed are identified. This ensures a balance between classified movement and overall cleaning efficiency. It should be understood that the corresponding positions of the objects to be moved that have not been moved because they do not meet the first movement condition need to be recorded. After the self-cleaning of the ground based on the ground cleaning module is completed, the corresponding positions are returned to complete the movement of all objects to be moved. That is, the self-cleaning control method of the manipulator also includes: recording objects to be moved that do not meet the preset first moving condition; after completing the supplementary cleaning judgment of all objects to be moved, according to the object type of the recorded objects to be moved, the recorded objects to be moved are moved by the manipulator, and the supplementary cleaning judgment includes judging whether each object to be moved meets the first moving condition.

[0079] If the first task itself only includes moving the objects to be moved in the target task area, then after completing a round of movement based on the first movement condition described above, continue to move the unmoved objects to be moved, thereby ensuring the thorough execution of the first task.

[0080] The above moving process can be further referenced Figure 4 and Figure 5 ,exist Figure 3 There are 5 objects to be moved in the target task area shown, of which 3 are clothes (i.e., patterned clothes 151, striped clothes 154, and solid-color clothes 155) and 2 are food residues (i.e., banana peels 152 and apple cores 153). The base station 20 is located in the lower left corner of the target task area, and the self-mobile cleaning device 10 is parked at the base station 20. There is also a square trash can on the left side of the target task area. If the image captured by the image acquisition module is obtained during the execution of the first task and the object type is recognized and moved based on the recognition result, then the object type is identified in the target task area. Figure 3 The moving process of the five objects to be moved is as shown in Figure 4 and Figure 5 shown.

[0081] Figure 4The process diagram in the figure is defined as the first state, the second state, the third state, the fourth state, the fifth state and the sixth state in sequence according to the directions indicated by the arrows. Figure 5 The schematic diagram in is defined as the seventh state. The self-mobile cleaning device 10 determines the first task, and after determining the bow-shaped path R1 according to the map of the target task area, it starts to move along the bow-shaped path from the base station 20 to perform the relevant task actions. The first state is the state before starting to perform the first task. The bow-shaped path R1 is illustrated in the first state. The method of determining the bow-shaped path R1 based on the target task area can refer to the relevant technology and will not be explained in detail here. The self-mobile cleaning device 10 collects images through the image acquisition module during the movement and identifies the objects to be moved in the target task area. When the self-mobile cleaning device 10 moves to the vicinity of the patterned clothing 151 (as shown in the second state), the patterned clothing 151 will be first identified from the image. The self-mobile cleaning device 10 directly moves the patterned clothing 151 to the designated area (such as the storage corner or the dirty clothes basket T1 in the lower right corner of the target task area). At this time, the layout of the objects to be moved is as shown in the third state. After moving the patterned clothing 151, the self-moving cleaning device 10 continues to move along the bow-shaped path R1, and will successively identify banana peels 152 and apple cores 153 from the image during the movement. The object types of banana peels 152 and apple cores 153 are different from the object type (clothing) of the most recently moved object (patterned clothing 151), and do not meet the first movement condition. At this time, even if the self-moving cleaning device 10 passes by banana peels 152 and apple cores 153 as shown in the fourth state, it still does not move banana peels 152 and apple cores 153, but can record the positions of banana peels 152 and apple cores 153. The self-moving cleaning device 10 continues to move along the bow-shaped path R1, and will successively identify striped clothing 154 and solid-color clothing 155. Corresponding to the fifth and sixth states, the striped clothing 154 and solid-color clothing 155 are moved to the designated area in sequence. When it is determined that the target task area has been cleaned and the unmoved objects to be moved have been recorded, the self-mobile cleaning device 10 can directly move the unmoved objects to be moved according to the object type. Figure 4 After the sixth state shown, there is only one type of object to be moved in the target task area, and it can be moved to the trash can T2 at a time. Figure 5 As shown in the seventh state, the first task of the target task area is completed, and the self-moving cleaning device 10 can return to the base station to self-clean the manipulator. It should be understood that if there are multiple types of objects to be moved, they need to be moved according to the object type during the supplementary movement.

[0082] In another optional implementation, a global patrol can be performed first to collect images for identification through the image acquisition module, and the objects to be moved and their object types can be moved based on the identification results of all objects to be moved in the target task area. That is, in the process of executing the first task, the objects to be moved are moved by the manipulator according to the types of objects to be moved in the images collected by the image acquisition module, including: performing image acquisition on the target task area to obtain an image set covering the target task area; performing image processing on the images in the image set to obtain each object to be moved and the corresponding object type in the target task area; in the process of executing the first task, the objects to be moved are classified by object type and moved by the manipulator, and the classified movement includes moving objects to be moved of the same object type. Specifically, in the process of executing the first task, in the process of moving the objects to be moved by the manipulator according to the object type, the cleaning path of the objects to be moved can be determined first, that is, the cleaning path of the objects to be moved is determined first according to the object type of the objects to be moved, and objects to be moved of the same object type are continuously distributed in the cleaning path. Then, in the process of executing the first task according to the cleaning path, the objects to be moved are moved in sequence by the manipulator according to the objects to be moved distributed in the cleaning path.

[0083] In a specific application scenario, after the self-mobile cleaning device determines the first task, it first conducts a global inspection of the target task area corresponding to the first task. The main purpose of the global inspection is to collect information about the objects to be moved (including location information and object type) through the image acquisition module and sensors. Suppose that 5 pieces of clothing, 3 pairs of shoes, 2 toys, and 10 paper towels are identified. If the user chooses coarse movement, only large object types will be distinguished, such as treating all clothing as a single category and moving them. Of course, specific objects to be moved may have corresponding target placement areas, and the object type can only determine the order of movement. If all objects to be moved have been determined in advance, the robot arm can be controlled to move according to the pre-set order corresponding to the object type during the specific movement process, such as moving according to major categories such as clothing, shoes, toys, and miscellaneous items. At the data processing level, this is equivalent to sorting the objects to be moved according to the object type and the order of grasping them, obtaining object subsets corresponding to each object type including the movement order; then, according to the sorting of the object subsets, the objects to be moved in each object subset are moved.

[0084] The above moving process can be further referenced Figure 6 and Figure 7 ,exist Figure 3There are 5 objects to be moved in the target task area shown, of which 3 are clothes (i.e., patterned clothes 151, striped clothes 154, and solid-color clothes 155) and 2 are food residues (i.e., banana peels 152 and apple cores 153). The base station 20 is located in the lower left corner of the target task area, and the self-mobile cleaning device 10 is parked at the base station 20. There is also a trash can T2 on the left side of the target task area. If a global patrol is first performed by collecting images through the image acquisition module for recognition, and the movement is performed based on the recognition results of all objects to be moved and their object types in the target task area, then the objects to be moved in the target task area will be moved. Figure 3 The moving process of the five objects to be moved is as shown in Figure 7 As shown. The self-mobile cleaning device 10 determines the first task, that is, starts to move from the base station 20, collects images through the image acquisition module during the movement, and does not perform task-related actions until an image set covering the target task area is obtained. The specific global patrol process can be referred to Figure 6 , considering that the images collected by the image acquisition module each time can cover a larger range, and the goal of the global patrol is to obtain an image set covering the target task area, the route of the global patrol is as follows Figure 6 As shown in the patrol route R2 in the figure, the images can be distributed relatively sparsely. The image acquisition module has a certain depth and breadth of image acquisition capabilities. After moving according to the patrol route R2, an image set covering the target task area can be obtained, thereby completing the full recognition of the objects to be moved, and determining the specific movement process when moving according to the object type based on the recognition results.

[0085] Figure 7 The process diagram in the figure is defined as the eighth state, the ninth state, the tenth state, the eleventh state, the twelfth state and the thirteenth state in sequence according to the directions indicated by the arrows. The eighth state is the state before starting to move all the identified objects to be moved. The first state shows that the self-mobile cleaning device 10 has determined the moving order of each object to be moved before moving, that is, moving the patterned clothing 151, the striped clothing 154, the solid color clothing 155, the apple core 153 and the banana peel 152 in sequence, that is, moving in the order indicated by the dotted arrows in the first state. It should be noted that the order indicated by the dotted arrows in the first state is only the moving order and does not represent the moving path of the self-mobile cleaning device 10. Based on the image set, the information of all the objects to be moved in the target task area (including object type and position information) can be obtained. At this time, the self-mobile cleaning device 10 can move and start to perform the first task-related cleaning action. During the movement, the objects to be moved are classified by object type through the manipulator. The classified movement includes moving objects to be moved with the same object type.

[0086] exist Figure 7In the moving process shown, the order of movement of the object types is to move the clothes first and then move the food residues. This moving order can be a pre-set moving order or a moving order determined according to the degree of dirtiness (the object types with lower dirtiness are moved first and then the object types with higher dirtiness are moved). As shown in the ninth state, the self-moving cleaning device 10 first moves to the position of the patterned clothes 151; the state after moving the patterned clothes 151 to the lower right corner of the target task area is the tenth state, and the self-moving cleaning device 10 continues to move to the vicinity of the striped clothes 154 in sequence, and the state at this time is the eleventh state; the state after moving the striped clothes 154 to the lower right corner of the target task area is the twelfth state, and then the solid-color clothes 155 are continued to be moved, thus completing the movement of the object type of clothes. The movement of the object type of food residues can be completed subsequently, and the state after all the moves are completed is the thirteenth state. It should be noted that the self-moving cleaning device 10 can trigger the self-cleaning of the manipulator after moving one type of object; it can also trigger the self-cleaning of the manipulator after moving a certain type of object whose dirtiness exceeds a preset threshold. That is, when pressing Figure 7 During the process shown in the figure, when the robot performs the first task in the target task area, the robot may trigger the self-cleaning of the robot only after moving the food residue because the clothes are relatively clean (that is, the self-cleaning of the robot is triggered only once when the first task is performed); or the self-cleaning of the robot may be triggered each time the movement of one type of object is completed, regardless of the object type (that is, the self-cleaning of the robot is triggered twice when the first task is performed).

[0087] For multiple objects to be moved corresponding to the same object type, the movement order can be generated from large to small in quantity, or from large to small in volume, or according to the minimum movement path required for the self-moving cleaning device to sort out all obstacles.

[0088] Please refer to further Figure 3, there are 5 objects to be moved in the target task area, 3 of which are clothes and 2 are food residues. If the existing technology is used, the manipulator randomly moves the objects to be moved, and it is possible that the manipulator first contacts the food residue and then contacts the clothes. This cleaning method may even cause difficult-to-handle contamination to the clothes. According to the implementation method of the embodiment of the present application, if the object to be moved and the corresponding object type are determined according to the image captured by the image acquisition module during the execution of the first task, pay attention to judge whether to move one by one, and the self-moving cleaning device starts to execute the first task from the lower left corner. The self-moving cleaning device will first identify the 1 piece of clothing below, then identify the 2 pieces of food residue in the middle, and finally identify the 2 pieces of clothing above. According to the method of focusing on the processing as much as possible according to the object type described above, based on the first movement condition, the self-moving cleaning device will not move the 2 pieces of food residue until the first task on the ground is completed (correspondingly, the 3 pieces of clothing will be moved to the target placement area), and then process the 2 pieces of food residue. If a global inspection is performed first, three pieces of clothing and two pieces of food residue will be found. A cleaning path will be generated based on their locations: the three pieces of clothing will be moved first (to the laundry basket T1), followed by the two pieces of food residue (to the trash can T2); or the two pieces of food residue will be moved first, followed by the three pieces of clothing. This categorized movement, combined with the cleaning steps for the robot described later, avoids cross-contamination caused by the movement of different types of objects, improving the cleaning effect.

[0089] Exemplarily, in the process of executing the first task, the objects to be moved are classified by object type by the manipulator, including one or more of the following combined methods: in the process of executing the first task, the objects to be moved are classified by object type by the manipulator according to the degree of dirtiness corresponding to the object type; in the process of executing the first task, the objects to be moved are classified by object type by the manipulator according to a preset movement sequence, and the preset movement sequence is a movement sequence set for the object type. For example, based on Figure 3First, a global inspection is carried out, and 3 pieces of clothing and 2 pieces of food residue are found. At this time, according to the degree of dirtiness, the robot can move the object type with a lower degree of dirtiness (clothing) first, and then move the object type with a higher degree of dirtiness (food residue); of course, the object type with a higher degree of dirtiness (food residue) can also be moved first, and then the object type with a lower degree of dirtiness (clothing). In the specific implementation process, if the preset movement order is followed, there is no need to consider the degree of dirtiness of different object types, and the two object types (clothing and food residue) can be moved directly according to the movement order of the two object types. The process of triggering the robot to perform self-cleaning based on the object type to be moved can include: triggering the robot to perform self-cleaning when completing the movement of an object type to be moved; and / or triggering the robot to perform self-cleaning when completing the movement of an object type to be moved whose dirtiness exceeds a preset threshold. If the object type with a lower degree of dirtiness is moved first, the self-cleaning of the robot arm can be triggered after all the objects to be moved are moved, or the self-cleaning of the robot arm can be triggered after each object type to be moved is moved; if the object type with a higher degree of dirtiness is moved first, the self-cleaning of the robot arm can be triggered after each object type to be moved is moved; or based on the dirtiness of the object type, if the dirtiness exceeds the preset threshold, the self-cleaning of the robot arm can be directly triggered regardless of the object type to be moved subsequently, so as to avoid contamination of the objects to be moved subsequently.

[0090] In an optional implementation, during the execution of the first task, the object to be moved is moved to the corresponding target placement area by the manipulator according to the object type of the object to be moved in the image captured by the image acquisition module, which may include: counting the number of objects to be moved that have been moved; based on the counting of the number of objects to be moved that have been moved, the self-cleaning control method of the manipulator also includes: when the number of objects to be moved that have been moved meets the preset first cleaning condition, pausing the first task and returning to the base station to clean the manipulator.

[0091] According to the different object types corresponding to the possible pollution generated in the manipulator, the upper limit of the number of objects that the manipulator can move can be set for different object types or the total object types. When the upper limit is reached, it is deemed that the manipulator may bring pollution to the next object to be moved. At this time, the self-mobile cleaning device needs to suspend the first task and return to the base station to clean the manipulator. In the embodiment of the present application, the condition that triggers the suspension of the first task and returns to the base station to clean the manipulator is defined as the first cleaning condition. For example, the cumulative movement of debris reaches 5 pieces, the cumulative movement of clothes reaches 10 pieces, etc. The specific time to return to the base station can be determined by combining the mop cleaning time. When it is close to the next mop cleaning time, it can directly return to the base station to clean the mop and the manipulator at the same time; or it can wait until the next mop cleaning time and then return to the base station to clean the mop and the manipulator at the same time.

[0092] In a specific implementation, triggering the robot to self-clean based on the type of object being moved involves: triggering the robot to self-clean after all objects have been moved; and controlling the robot's movement during the self-cleaning process to coordinate with the robot's self-cleaning. Specifically, after the self-mobile cleaning device returns to or approaches the base station, and the robot is in a designated cleaning position within the base station, control of the robot's movement, such as controlling the rotation of the gripper, begins to coordinate with the base station's cleaning of the robot, improving cleaning effectiveness.

[0093] Generally speaking, a first task is determined for the target task area. This first task involves moving the objects to be moved within the target task area. During the execution of the first task, the robot moves the objects based on their type within the images captured by the image acquisition module. The robot triggers self-cleaning based on the type of the objects to be moved. During the cleaning process, the robot moves the objects by type. By classifying and sorting the objects and triggering self-cleaning, the robot cleans the objects by type as cleanly as possible, avoiding cross-contamination and accumulation of dirt. This prevents the appearance of dirt that was not originally present on the sorted objects, thus improving the overall cleaning and sorting effect.

[0094] The present application provides a cleaning system, such as Figure 8As shown, the cleaning system is used for a base station 20, and the cleaning system includes a water tank (not shown in the figure), a first cleaning area 21 and a second cleaning area 22. The first cleaning area 21 and the second cleaning area 22 are connected and share a drainage channel. The water tank is used to supply water for cleaning in the first cleaning area 21 and the second cleaning area 22; the first cleaning area 21 is provided with a first cleaning component, and the second cleaning area 22 is provided with a second cleaning component; the first cleaning component is used to clean the cleaning component of the self-moving cleaning equipment located in the first cleaning area 21, and the second cleaning component is used to clean the manipulator to be cleaned located in the second cleaning area 22, which is the manipulator of the self-moving cleaning equipment. In a specific implementation, the second cleaning component includes a spray head, which is connected to the water tank via a clean water pump and a water supply pipe. The clean water pump is used to pressurize the water transported to the spray head through the water supply pipe, thereby increasing the flow rate of the water sprayed from the spray head and improving the cleaning effect of the manipulator to be cleaned.

[0095] The base station 20 determines that the self-mobile cleaning device returns to the base station or extends the manipulator into the base station (the self-mobile cleaning device maintains the connection state of the manipulator and extends the manipulator into the second cleaning area 22 (the state at this time is as shown in FIG). Figure 9 As shown), or the manipulator (or only the gripping head) is temporarily disassembled to the second cleaning area 22 (the state at this time is as shown Figure 10 When the robot arm of the self-moving cleaning device is self-cleaning, the second cleaning assembly begins cleaning the robot arm. During the self-cleaning of the robot arm, the robot arm is located in the second cleaning area 22. In addition to the spray head connected to the clean water pump described above, the second cleaning assembly may also include a motor-driven brush, etc. Different second cleaning assemblies can clean the robot arm in different ways.

[0096] When the cleaning system can provide multiple cleaning methods, during the cleaning process of the robot, the base station controls different second cleaning components to clean the robot according to the preset cleaning methods and corresponding cleaning sequences for the preset cleaning time.

[0097] In one optional implementation, the cleaning method includes one or more of cold water cleaning, hot water cleaning, cleaning liquid cleaning, and drying. For example, a typical base station water tank has a water capacity of approximately 4L and is equipped with, for example, one shower head with a water flow rate of 6ml / s, a cleaning time of 70s, and a total cleaning water volume of 100ml. If there are n shower heads, the shower head water flow rate = 6ml / s * n.

[0098] In an exemplary cleaning scheme, the clean water pump operates at a 70% duty cycle, discharging water for 8 seconds (8 seconds for cold water cleaning). The clean water pump flows water into the heating module for heating, and heats for 7 seconds. Cleaning liquid is discharged for 2 seconds. The cleaning liquid and heated clean water are mixed and then flow into the spray head for spraying (hot water cleaning + cleaning liquid cleaning). The spray head discharges water at a flow rate of 6ml / s to spray the gripper head. At the same time, the gripper head rotates, or the spray head rotates, to clean the gripper head in all directions. At the same time, after 3 seconds or at the same time, the sewage pump is turned on and pumps for 5 seconds. During the cleaning process, the gripper head rotates at a speed of 160r / min to achieve thorough cleaning and drying of the gripper head. In the specific implementation process, the robot arm can be dried after each cleaning, or it can be dried only after the first cleaning task. The drying can be hot air drying or cold air drying. The gripper head can rotate during the drying process to achieve drying at all angles.

[0099] The cleaning of the manipulator can be carried out simultaneously with the cleaning of the cleaning components of the self-moving cleaning equipment (such as the middle sweep mentioned above). At this time, the water supply from the water tank to the first cleaning area 21 and the second cleaning area 22 can be achieved through the shared water supply pipe of the tee pipe, or through two independent water supply pipes. Accordingly, if it is achieved through the shared water supply pipe of the tee pipe, a valve is set on the water supply pipe so that only the second cleaning area 22 or the first cleaning area 21 is supplied with water when only the manipulator or the cleaning components need to be cleaned. After the self-cleaning of the manipulator is completed, the sewage in the first cleaning area 21 and the second cleaning area 22 can be collected into the sewage tank through the drainage channel shared by the first cleaning area 21 and the second cleaning area 22, and the necessary treatment such as filtration of the sewage is completed in the process of collecting the sewage.

[0100] Figure 11 This is a schematic diagram of the structure of a self-moving cleaning device provided in an embodiment of the present application. Figure 11 As shown, the self-moving cleaning device includes a processor 310 and a memory 320. The self-moving cleaning device may also include an input device 330, an output device 340, and a communication device 350. The number of processors 310 in the self-moving cleaning device may be one or more. Figure 11 In the figure, a processor 310 is used as an example; the processor 310, the memory 320, the input device 330, the output device 340 and the communication device 350 in the self-mobile cleaning device can be connected via a bus or other means. Figure 11 The bus connection is taken as an example.

[0101] Memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the self-cleaning control method for the manipulator in the embodiments of the present application. Processor 310 executes the software programs, instructions, and modules stored in memory 320 to execute various functional applications and data processing of the self-mobile cleaning device, thereby implementing the self-cleaning control method for the manipulator described above.

[0102] The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the data storage area may store data created according to the use of the self-mobile cleaning device, etc. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include a memory remotely arranged relative to the processor 310, and these remote memories may be connected to the self-mobile cleaning device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0103] The input device 330 may be used to receive network configuration information. The output device 340 may include a display device such as a display screen.

[0104] The above-mentioned self-moving cleaning device can be used to execute the self-cleaning control method of any robot arm and has corresponding functions and beneficial effects.

[0105] An embodiment of the present invention also provides a storage medium containing computer-executable instructions. When the computer-executable instructions are executed by a computer processor, they are used to perform relevant operations in the self-cleaning control method of the manipulator provided in any embodiment of the present application, and have corresponding functions and beneficial effects.

[0106] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products.

[0107] Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0108] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0109] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0111] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the concept of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A self-cleaning control method for a robot, used for a self-moving cleaning device, characterized in that: The self-moving cleaning device includes a manipulator and an image acquisition module; the self-cleaning control method of the manipulator includes: Determining a first task for a target task area, wherein the first task includes moving an object to be moved in the target task area; During the execution of the first task, the object to be moved is moved by the manipulator according to the type of the object to be moved present in the image captured by the image acquisition module; The robot is triggered to perform self-cleaning based on the object type of the object to be moved.

2. The self-cleaning control method of the manipulator according to claim 1, characterized in that: In the process of performing the first task, moving the object to be moved by the manipulator according to the object type of the object to be moved present in the image captured by the image capture module includes: During the execution of the first task, acquiring images captured by the image acquisition module; Identifying the object to be moved and the type of the object in the image; When the object to be moved meets a preset first movement condition, the object to be moved is moved by the manipulator.

3. The self-cleaning control method of the manipulator according to claim 2, characterized in that: When the object to be moved meets a preset first movement condition, moving the object to be moved by the manipulator includes one or more of the following combination methods: In a case where the object to be moved is of the same type as the object to be moved in a previous move, moving the object to be moved by the manipulator; When a preset number of objects to be moved have not been moved after the previous movement of the objects to be moved, moving the objects to be moved by the manipulator; When a first preset time has passed since the last movement of the object to be moved, the object to be moved is moved by the manipulator; When the cleaning area after the object to be moved is moved the last time reaches a first preset area, the object to be moved is moved to a corresponding target placement area by the robot.

4. The self-cleaning control method of the manipulator according to claim 3, characterized in that: Also includes: Recording objects to be moved that do not meet the preset first movement condition; After completing the supplementary cleaning judgment for all objects to be moved, the recorded objects to be moved are moved by the robot arm according to the recorded object type of the objects to be moved. The supplementary cleaning judgment includes judging whether each object to be moved meets the first movement condition.

5. The self-cleaning control method of the manipulator according to claim 1, characterized in that: In the process of performing the first task, moving the object to be moved by the manipulator according to the object type of the object to be moved present in the image captured by the image capture module includes: Capturing images of the target task area to obtain an image set covering the target task area; Performing image processing on the images in the image set to obtain each object to be moved and the corresponding object type in the target task area; During the execution of the first task, the objects to be moved are classified and moved by the manipulator according to the object types, and the classified movement includes moving objects to be moved of the same object type.

6. The self-cleaning control method of the manipulator according to claim 5, characterized in that: In the process of performing the first task, moving the object to be moved by the manipulator according to the object type classification includes: Classify and sort the objects to be moved according to their type and the order in which they are grasped, to obtain a subset of objects corresponding to each object type that includes the movement order; According to the order of the object subsets, move the objects to be moved in each object subset; The movement sequence includes a preset movement sequence and / or a movement sequence determined according to the degree of dirtiness of each object type.

7. The self-cleaning control method of the manipulator according to claim 5, characterized in that: The triggering of the manipulator to perform self-cleaning based on the type of the object to be moved includes: After all objects to be moved have been moved, the manipulator is triggered to perform self-cleaning; During the self-cleaning process, the movement of the manipulator is controlled to cooperate with the self-cleaning of the manipulator.

8. The self-cleaning control method of the manipulator according to claim 5, characterized in that: The triggering of the manipulator to perform self-cleaning based on the type of the object to be moved includes: Upon completion of movement of an object of one type to be moved, triggering the manipulator to perform self-cleaning; and / or When the movement of an object to be moved of a type of object with a degree of dirtiness exceeding a preset threshold is completed, the manipulator is triggered to perform self-cleaning.

9. The self-cleaning control method of a manipulator according to any one of claims 1 to 8, characterized in that: The target task area includes an area determined by a map pre-stored by the self-mobile cleaning device or a temporarily selected area sent by a control terminal; the temporarily selected area is determined according to a received area selection operation, and the area selection operation is used to determine one or more sub-areas from the map pre-stored by the self-mobile cleaning device.

10. Cleaning system, characterized in that, Used in a base station, the cleaning system includes a water tank, a first cleaning area and a second cleaning area, the first cleaning area and the second cleaning area are connected and share a drainage channel, the water tank is used to supply water for cleaning in the first cleaning area and cleaning in the second cleaning area; The first cleaning area is provided with a first cleaning component, and the second cleaning area is provided with a second cleaning component; the first cleaning component is used to clean the cleaning component of the self-moving cleaning equipment located in the first cleaning area, and the second cleaning component is used to clean the robot to be cleaned located in the second cleaning area, and the robot to be cleaned is the robot of the self-moving cleaning equipment.

Images