Cleaning method, cleaning apparatus, cleaning device, and storage medium

Abstract

A cleaning method comprising: (01) determining a target cleaning area; (02) generating a cleaning trajectory within the target cleaning area in response to a path planning command; and (03) performing a cleaning operation along the cleaning trajectory. The present application further discloses a cleaning apparatus, a cleaning device, and a storage medium.

Description

Technical Field

[0001] This application claims the priority and rights of patent applications with patent application numbers 202210504138.X, 202210597028.2, 202210613623.0, and 202210608104.5, which were filed with the China National Intellectual Property Administration on May 10, 2022, May 30, 2022, and May 31, 2022, and incorporates the full texts of these by reference herein.

[0002] This application relates to the field of cleaning technology, and particularly to cleaning methods, cleaning devices, cleaning apparatuses, and storage media.

Background Art

[0003] With the advent of the smart era, various smart devices bring great convenience to people. Smart cleaning devices can reduce people's burden of housework. However, at present, it is difficult for the cleaning strategy of cleaning devices to reach a high overall room cleaning coverage rate, and there is a situation where the cleaning effect is not ideal in many aspects such as map construction, path planning, setting of cleaning parameters, and dynamic scenes. For example, in dynamic scenes, people walking, pets moving, doors opening and closing, furniture moving, etc. of In some cases, the cleaning device may not be able to recognize dynamic obstacles, resulting in cleaning omissions.

Summary of the Invention

Problems to be Solved by the Invention

[0004] Embodiments of the present invention provide a cleaning method, a cleaning device, a cleaning apparatus, and a storage media.

Means for Solving the Problems

[0005] The cleaning method in the embodiments of the present invention is used in a cleaning device, and the cleaning method includes: determining a target cleaning area; and generating a cleaning trajectory within the target cleaning area in response to a path planning command. The process includes the step of performing a cleaning operation along the aforementioned cleaning trajectory.

[0006] In some embodiments, the step of determining the target cleaning area is: After activating the cleaning device, if it is recognized that the cleaning device was activated in a non-charging position, the method includes the step of determining the target cleaning area of ​​the cleaning device.

[0007] In some embodiments, the step of determining the target cleaning area of ​​the cleaning device is: The method includes the step of recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and if the first cleaning target exists, determining the area where the first cleaning target is located as the target cleaning area.

[0008] In some embodiments, the step of determining the target cleaning area of ​​the cleaning device is: The steps include obtaining a semantic map of all scenes constructed by the cleaning device, The method includes the step of determining the target cleaning area using the semantic map.

[0009] In some embodiments, the step of determining the target cleaning area using the semantic map is: The method includes the step of determining the room of a predetermined type as the target cleaning area if the semantic map determines that the cleaning device is located in a room of a predetermined type.

[0010] In some embodiments, the step of determining the target cleaning area using the semantic map is: The method includes the step of determining the area where the second cleaning target is located as the target cleaning area if the semantic map determines that the cleaning device is not present in a room of a predetermined type and that a second cleaning target exists within an area at a predetermined distance from the cleaning device.

[0011] In some embodiments, the step of determining the target cleaning area using the semantic map is: The method includes the step of determining the area at a predetermined distance from the cleaning device as the target cleaning area if the semantic map determines that the cleaning device is not present in a room of a predetermined type and that there is no second cleaning target within an area at a predetermined distance from the cleaning device.

[0012] In some embodiments, before determining the target cleaning area by the semantic map, the cleaning method is performed The further step includes recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and confirming that if the first cleaning target does not exist, the semantic map is used to determine the target cleaning area.

[0013] In some embodiments, the step of performing a cleaning operation along the cleaning trajectory is: The cleaning method includes cleaning the target cleaning area by cleaning along the edges and then cleaning in a curved shape, and after completion, returning to the charging position and charging.

[0014] In some embodiments, before performing the cleaning operation along the cleaning trajectory, the cleaning method The step further includes providing voice instructions on how to clean the cleaning device for the target cleaning area.

[0015] In some embodiments, the first cleaning target includes one of the following: dirt, small granular debris, and hair-like debris.

[0016] In some embodiments, the second cleaning target is a home appliance or furniture.

[0017] In some embodiments, the step of generating a cleaning trajectory within the target cleaning area in response to a path planning command includes: responding to the path planning command to determine the current cleaning state of the mop and the starting and ending points corresponding to the path planning command; determining a cleaning trajectory from the starting point to the ending point based on a geographical situation map, a cleaning situation map, and the cleaning state.

[0018] In some embodiments, the step of determining the current cleaning state of the mop includes: when the current cleaning stage of the cleaning device is the starting stage after self-cleaning at the water station, determining that the current cleaning state of the mop is clean; when the current cleaning stage of the cleaning device is the stage of moving from the currently cleaned area to the area waiting for cleaning or the stage of returning to the water station to wash the mop, determining that the current cleaning state of the mop is dirty.

[0019] In some embodiments, the step of determining a cleaning trajectory from the starting point to the ending point based on a geographical situation map, a cleaning situation map, and the cleaning state includes: determining an area without obstacles based on the geographical situation map; determining a cleaning trajectory from the starting point to the ending point according to a predetermined passing strategy corresponding to the cleaning state based on the area without obstacles and the cleaning situation map.

[0020] In some embodiments, the step of determining a cleaning trajectory from the starting point to the ending point according to a predetermined passing strategy corresponding to the cleaning state based on the area without obstacles and the cleaning situation map includes: based on the fact that the cleaning state is clean, determining an area that has been cleaned from the cleaning situation map; Based on the area without obstacles and the area that has been cleaned, determining all areas without obstacles and that have been cleaned between the starting point and the ending point; Determining that at least one continuous movement trajectory can be formed between the starting point, all areas without obstacles and that have been cleaned, and the ending point, and determining the shortest movement trajectory in the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point, including.

[0021] In some embodiments, according to the predetermined passage strategy corresponding to the cleaning state by the area without obstacles and the cleaning status map, the step of determining the cleaning trajectory from the starting point to the ending point is: Based on the fact that the cleaning state is dirty, determining all areas waiting to be cleaned from the cleaning status map; Based on the area without obstacles and all areas waiting to be cleaned, determining all areas without obstacles and waiting to be cleaned between the starting point and the ending point; Determining that at least one continuous movement trajectory can be formed between the starting point, all areas without obstacles and waiting to be cleaned, and the ending point, and determining the shortest movement trajectory in the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point, including.

[0022] In some embodiments, the cleaning method is: Determining that the continuous movement trajectory cannot be formed, and further including the step of determining the cleaning trajectory from the starting point to the ending point based on the area without obstacles.

[0023] In some embodiments, before responding to the route planning command, Further including the step of dividing the target cleaning area into a plurality of areas and determining the cleaning order of each area.

[0024] In some embodiments, the step of determining the starting point and the ending point corresponding to the route planning command is: The process includes determining the start and end points corresponding to the route planning command based on the current cleaning stage of the cleaning device and the cleaning sequence of each area.

[0025] In some embodiments, the cleaning method is The steps include marking obstacles within the target cleaning area, avoiding the obstacles within the target cleaning area, and performing a cleaning operation. The steps include detecting the state of obstacles within the target cleaning area and identifying the obstacles whose state has changed, The process further includes the step of performing a cleaning operation at the location of the obstacle whose state has changed.

[0026] In some embodiments, the step of marking obstacles within the target cleaning area is: The process includes the step of marking the location, type, and shape of obstacles within the target cleaning area, wherein the type includes dynamic obstacles.

[0027] In some embodiments, the step of detecting the state of obstacles within the target cleaning area and identifying obstacles whose state has changed is: A step of detecting the position and shape of the dynamic obstacle within the target cleaning area, The process includes the step of determining dynamic obstacles whose state has changed based on dynamic obstacles whose position or shape has changed.

[0028] In some embodiments, the cleaning operation includes a first cleaning operation and a second cleaning operation, where the first cleaning trajectory determined by performing the first cleaning operation is a closed loop, and the second cleaning trajectory determined by performing the second cleaning operation can fill the target cleaning area.

[0029] In some embodiments, the step of determining the target cleaning area is: The process includes the steps of performing the first cleaning operation and determining the target cleaning area based on the cleaning trajectory of the first cleaning operation.

[0030] In some embodiments, the step of avoiding the obstacles within the target cleaning area and performing the cleaning operation is: The steps include: performing a second cleaning operation within the aforementioned target cleaning area; The method includes the steps of: when it is determined that the aforementioned obstacle has been encountered, performing a first cleaning operation, and continuing to perform a second cleaning operation after avoiding the obstacle.

[0031] In some embodiments, the step of performing a cleaning operation along the cleaning trajectory is: A step of monitoring the amount of dust collected in the dust box of the cleaning device, A step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold, wherein the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device. The step of performing the cleaning operation by driving and operating the cleaning device in the target operating mode.

[0032] In some embodiments, the step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold is: The steps include detecting that the amount of dust collected is greater than the predetermined dust amount threshold, and determining that the cleaning device will be controlled to operate the target operating mode of the cleaning function with a first cleaning intensity and a first cleaning area, or The process includes detecting that the amount of dust collected is not greater than the predetermined dust amount threshold, and determining that the cleaning device should be controlled to operate the cleaning function in a target operating mode with a second cleaning intensity and a second cleaning area, wherein the second cleaning intensity is lower than the first cleaning intensity and the second cleaning area is smaller than the first cleaning area.

[0033] In some embodiments, the step of detecting that the amount of dust collected is greater than the predetermined dust amount threshold and determining to control the cleaning device to operate the target operating mode of the cleaning function at a first cleaning intensity and a first cleaning area is: The steps include determining that the amount of dust collected is greater than the predetermined dust amount threshold, and recording the location of the cleaning device, The method further includes marking an area within a predetermined range from the aforementioned location as a high-cleaning area, and controlling the cleaning device to operate the cleaning function in the high-cleaning area with a first cleaning intensity and a first cleaning area.

[0034] In some embodiments, the step of driving and operating the cleaning device in the target operating mode is: The steps include determining at least one of the following: the rotation speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions, which represent the target operating mode; The process includes the step of driving the cleaning device and operating the cleaning function with at least one of the following: the rotational speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions, wherein the travel interval is used to reflect the distance between two adjacent travel routes of the cleaning device.

[0035] In some embodiments, the step of driving the cleaning device and operating the cleaning function at the travel interval is: The steps include determining the initial interval between two adjacent travel routes of the current cleaning device, The steps include adjusting the initial interval to a target interval where the distance is smaller than the initial interval, The step includes driving the cleaning device and operating the cleaning function so that the distance between two adjacent travel routes becomes the target interval.

[0036] In some embodiments, the step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold is: The step of detecting that the amount of dust collected is greater than the predetermined dust amount threshold and activating the imaging device of the cleaning device, The steps include: using the aforementioned imaging device to collect area images in the direction of travel of the cleaning device; The process includes determining the target operating mode of the cleaning device based on the recognition results of the area image and the relationship between the amount of dust collected and a predetermined dust threshold.

[0037] In some embodiments, after the step of using the imaging device to collect area images in the direction of travel of the cleaning device, A step of using a predetermined image detection model to recognize an area object feature in the area image, which includes at least one of size features, color features, and contour features; The method further includes the step of determining the recognition result of the area image based on the area object features, wherein the recognition result is used to reflect the objects awaiting cleaning that are present in the area where the cleaning device is currently located.

[0038] In some embodiments, the step of monitoring the amount of dust collected in the dust box of the cleaning device is: The procedure includes the steps of monitoring the amount of dust collected at the dust box inlet over a predetermined period, or monitoring the weight change of the dust box over a predetermined period.

[0039] The cleaning device in the embodiment of the present invention is A location planning module used to determine the target cleaning area, A trajectory planning module used to generate a cleaning trajectory within the target cleaning area in response to a route planning command, The system includes a cleaning module used to perform a cleaning operation along the aforementioned cleaning trajectory.

[0040] The cleaning device in an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable by the processor, and when the processor executes the program, the cleaning method is realized.

[0041] In embodiments of the present invention, the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the cleaning method is implemented.

[0042] Additional aspects and advantages of the present invention are partially shown in the following description, partially become apparent from the following description, or are understood through the implementation of the present invention. [Brief explanation of the drawing]

[0043] The above and / or additional aspects and advantages of the present invention will become apparent and readily apparent from the following description of embodiments in combination with the drawings.

[0044] [Figure 1] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 2] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 3] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 4] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 5] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 6] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 7] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 8] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 9] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 10] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 11] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 12] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 13] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 14] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 15] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 16] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 17] This is a schematic diagram of a scene in an embodiment of the present invention. [Figure 18] This is a schematic diagram of the cleaning method process in an embodiment of the present invention. [Figure 19] This is a schematic diagram of a cleaning device module according to an embodiment of the present invention. [Figure 20] This is a schematic diagram of a cleaning device module according to an embodiment of the present invention. [Figure 21] This is a schematic diagram of a cleaning device module according to an embodiment of the present invention. [Figure 22] This is a schematic diagram of a cleaning device in an embodiment of the present invention. [Modes for carrying out the invention]

[0045] To further clarify the object, technical proposal and advantages of the present invention, the technical proposal of the present invention will be clearly and completely described below with reference to the accompanying drawings, and obviously, the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments that can be obtained by those skilled in the art without creative effort based on the embodiments of the present invention are included within the scope of protection of the present invention.

[0046] In this specification, any reference to terms such as “one embodiment,” “several embodiments,” “example,” “specific example,” or “several examples” means that the specific features, structures, materials, or properties described in the applicable embodiment or example are included in at least one embodiment or example of the present invention. Furthermore, the terms “first,” “second,” and “third” are used for descriptive purposes only and do not indicate or suggest relative importance. Exemplary expressions of the above terms in this specification do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or properties described can be combined in appropriate ways in any embodiment or example. Furthermore, a person skilled in the art can combine different embodiments or examples and features of different embodiments or examples described herein, provided they do not conflict with each other.

[0047] Embodiments of the present invention will be described in further detail below with reference to the attached drawings and examples. The following examples are for illustrative purposes only and do not limit the scope of the present invention.

[0048] Referring to Figure 1, embodiments of the present invention disclose a cleaning method used in a cleaning device, and the cleaning method is 01. Steps to determine the target cleaning area, 02. In response to a route planning command, a step of generating a cleaning trajectory within the target cleaning area, 03. Includes the step of performing a cleaning operation along a cleaning trajectory.

[0049] In actual dynamic application scenarios, such as when people walk, pets move, doors open and close, or furniture is moved, the execution terminal for the embodiment of the present invention may be a cleaning device such as a cleaning robot, an automatic floor cleaning machine, a robot that combines cleaning and mopping, an automatic cleaning machine, a smart vacuum cleaner, or a robotic vacuum cleaner.

[0050] Furthermore, when performing a cleaning task, the cleaning device first determines the target cleaning area for the cleaning task within the clean scene, and when determining the target cleaning area, it detects obstacles. toIf an obstacle is encountered, the device will avoid the detected obstacle and mark it. In the subsequent cleaning process, if an obstacle detected when determining the target cleaning area is a dynamic obstacle and its position moves, the cleaning device will re-clean that area.

[0051] Figure 2 is an exemplary flowchart for determining the target cleaning area according to some embodiments of this specification. In some embodiments, step 01 in Figure 1 is the below described This can be performed based on step 011.

[0052] Step 011 In After activating the cleaning device, if it is detected that the cleaning device was activated in a non-charging position, the target cleaning area of ​​the cleaning device is determined.

[0053] In this embodiment, the entity that performs the submitted cleaning method may be a cleaning device or a cleaning apparatus. To more clearly explain the cleaning method submitted in this invention, the following embodiment will provide an illustrative explanation using a cleaning apparatus in which the entity that performs the cleaning method is a cleaning device.

[0054] In this embodiment, the cleaning device is activated in a non-charged position when the user moves the cleaning device to a certain position and activates it manually, at which point the cleaning device enters localized cleaning mode.

[0055] Specifically, after activating the cleaning device, the cleaning system first recognizes whether the activated position of the cleaning device is the non-charging position. More precisely, when the cleaning device is activated, the position recognition component in the cleaning device is also activated accordingly. The position recognition component can detect whether the cleaning device is in the charging position, and the cleaning system can determine whether the activated position of the cleaning device is the non-charging position based on the recognition result of the position recognition component.

[0056] Furthermore, if the cleaning device determines that the cleaning device is to be activated in a non-charging position, that is, if the cleaning device is to be moved to a certain location and activated manually, the cleaning device needs to determine the target cleaning area where the cleaning device needs to be cleaned.

[0057] Specifically, if the cleaning device determines that the cleaning device is activated in a non-charged position, it will appear as being in localized cleaning mode. At this point, the user's cleaning intention can be determined to clean a certain area. Therefore, the cleaning device needs to determine the target cleaning area and, in subsequent steps, perform cleaning accurately according to the user's cleaning intention.

[0058] Specifically, the cleaning device is equipped with a detection component used to detect conditions near the location where the cleaning device is situated. The cleaning device stores a semantic map of all scenes, and the cleaning device can analyze the user's cleaning intentions based on the detection results of the detection component and / or the semantic map. Furthermore, the cleaning device determines the target cleaning area based on the user's cleaning intentions.

[0059] In this embodiment, the cleaning device first determines whether the cleaning device is in a state where it can be activated in a non-charged position. If the cleaning device is in a state where it can be activated in a non-charged position, it determines the area the user wants to clean (i.e., the target cleaning area), and then controls the cleaning device to clean the area the user wants to clean. In this embodiment of the present invention, when the cleaning device determines that the cleaning device is in a state where it can be activated in a non-charged position, it can automatically analyze the user's cleaning intention and determine the area the user wants to clean. This allows the cleaning area of ​​the cleaning device to better match the user's requirements and improve user satisfaction. Furthermore, by controlling the cleaning device to clean only the area the user wants to clean, the cleaning efficiency of the cleaning device is improved.

[0060] Referring to Figure 2, in some embodiments, step 01 is: 012. A step of recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, 013, if a first cleaning target exists, further includes the step of determining the area where the first cleaning target is located as the target cleaning area.

[0061] In this embodiment, the predetermined distance refers to the distance that the sensing component of the cleaning device can recognize, and may be a custom distance. It is understood that the custom distance must be within the range that the sensing component of the cleaning device can recognize, and the first cleaning target is the cleaning Difficult It refers to dirt or grime.

[0062] Specifically, the process of determining the target cleaning area of ​​a cleaning device involves the cleaning device first recognizing whether a first cleaning target exists in an area at a predetermined distance from the cleaning device. More specifically, if the cleaning device is equipped with a sensing component that can be used to detect conditions near the location where the cleaning device is located, the cleaning device can recognize conditions near the location where the cleaning device is located using the sensing component, that is, it can recognize whether the first cleaning target exists near the cleaning device.

[0063] For example, the above detection component may be, but is not limited to, one type of AI (image) recognition device, camera, or video camera.

[0064] Furthermore, when the cleaning device determines that a first cleaning target exists within an area at a predetermined distance from the cleaning device, the cleaning device determines the area where the first cleaning target is located as the user's desired cleaning area, that is, determines the area where the first cleaning target is located as the target cleaning area.

[0065] Specifically, when the cleaning device recognizes that a first cleaning target exists within an area at a predetermined distance from the cleaning device, the user's cleaning intention is to clean the first cleaning target. At this time, the cleaning device determines the area where the first cleaning target is located as the target cleaning area. In the subsequent step, the cleaning device simply controls the cleaning device to clean the area where the first cleaning target is located, so that the cleaning area of ​​the cleaning device better matches the user's requirements.

[0066] In this embodiment, when the cleaning device recognizes that a first cleaning target exists within an area at a predetermined distance from the cleaning device, it determines the area where the first cleaning target is located as the target cleaning area, that is, it determines the area where the first cleaning target is located as the user's desired cleaning area. Then, in the subsequent steps, the cleaning device simply controls the cleaning device to clean the area where the first cleaning target is located, and the cleaning area of ​​the cleaning device better matches the user's requirements, improving the cleaning efficiency of the cleaning device and increasing user satisfaction.

[0067] Referring to Figure 3, in some embodiments, step 01 is: 014. Steps to obtain a semantic map of all scenes constructed by the cleaning device, 015, including the step of determining the target cleaning area using a semantic map.

[0068] In this embodiment, the semantic map refers to the semantic map of all scenes constructed after the cleaning device has performed cleaning on all scenes, where "all scenes" refers to the scenes of all rooms in the user's house. Specifically, the semantic map includes the type of room and the location and type of items such as home appliances and furniture.

[0069] Specifically, the process for determining the target cleaning area of ​​a cleaning device involves the cleaning device first acquiring a semantic map constructed after cleaning all scenes. More precisely, after the cleaning device cleans all rooms in the user's house for the first time, it constructs a semantic map of all scenes in the user's house. After each subsequent cleaning, it updates this semantic map according to the actual situation and stores the updated semantic map in the cleaning device's memory unit. The cleaning device can then acquire the semantic map from this memory unit. Furthermore, the cleaning device acquires the updated semantic map after the most recent cleaning, thus ensuring the accuracy of the target cleaning area determined by the semantic map in subsequent steps.

[0070] Furthermore, the cleaning device determines the target cleaning area using the semantic map, that is, it determines the area the user wants to clean using the semantic map. Specifically, the semantic map determines the room type where the cleaning device is currently located, and the cleaning device but The system can determine whether furniture or appliances are present at the current location, analyze the user's cleaning intentions based on that information, and determine the area the user wants to clean based on their cleaning intentions. Therefore, the cleaning device can determine the target cleaning area using the above-mentioned semantic map.

[0071] In this embodiment, when it is determined that the cleaning device is in a state where it is activated in a non-charged position, that is, when the cleaning device activates local cleaning mode, the cleaning device can acquire the semantic map constructed by the cleaning device, and the cleaning device butBy analyzing the situation near the current location, i.e., analyzing the user's cleaning intention, and determining the target cleaning area based on the user's intention, the area cleaned by the cleaning device in the subsequent step will be guaranteed to be the area the user wants to clean. This ensures that the cleaning area of ​​the cleaning device better matches the user's requirements, improves the cleaning efficiency of the cleaning device, and increases user satisfaction.

[0072] Referring to Figure 4, in some embodiments, step 015 teeth, 0151, if the semantic map determines that the cleaning device is located in a room of a predetermined type, the step of determining the room of a predetermined type as the target cleaning area.

[0073] In this embodiment, the above-mentioned predetermined type of room refers to a room that is difficult to clean or easily gets dirty, such as a toilet or kitchen.

[0074] Specifically, the process of determining the target cleaning area using a semantic map involves the cleaning device first analyzing whether the room type at its current location is a predetermined room type using the semantic map.

[0075] Furthermore, if the cleaning device determines that the room type at its current location is a predetermined room type, the cleaning device will identify that room as the user's desired cleaning area, that is, it will identify that room as the target cleaning area.

[0076] Specifically, if the cleaning device analyzes the room type at its current location using the semantic map described above, and determines that it is a predetermined room type, then the user's cleaning intention is to clean a room of the predetermined type. At this point, the cleaning device identifies the predetermined room type (i.e., the room where the cleaning device is currently located) as the target cleaning area. In the subsequent steps, the cleaning device simply controls itself to clean the predetermined room, thereby ensuring that the cleaning area of ​​the cleaning device better matches the user's requirements.

[0077] In this embodiment, if the cleaning device analyzes the current location of the cleaning device using the semantic map, it determines that the room of that predetermined type is the area the user wants to clean, i.e., determines that the room of that predetermined type is the target cleaning area. Then, in the subsequent steps, the cleaning device simply controls the cleaning device to clean the room of that predetermined type, so that the cleaning area of ​​the cleaning device better matches the user's requirements, improving the cleaning efficiency of the cleaning device and increasing user satisfaction.

[0078] Referring to Figure 5, in some embodiments, step 015 is: 0152, if a semantic map determines that a cleaning device is not present in a room of a predetermined type and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, the step of determining the area where the second cleaning target is located as the target cleaning area.

[0079] In this embodiment, the second cleaning target refers to household appliances or furniture in the user's room that are likely to interrupt the cleaning process of the cleaning device, such as a bed, tea table, and washing machine.

[0080] Specifically, the process of determining the target cleaning area using a semantic map involves the cleaning device analyzing whether a second cleaning target exists within a predetermined distance from the cleaning device if the semantic map indicates that the room type at the cleaning device's current location is not a predetermined room type. In more specific terms, the semantic map clarifies the second cleaning target. to By doing so, the cleaning device does not need to call the detection component of the cleaning device to detect the situation near the cleaning device, and can determine whether a second cleaning target exists within an area at a predetermined distance from the cleaning device using a semantic map.

[0081] Furthermore, when the cleaning device analyzes, based on the semantic map, that a second cleaning target exists within an area at a predetermined distance from the cleaning device, the cleaning device determines the area where the second cleaning target is located as the user's desired cleaning area, that is, determines the area where the second cleaning target is located as the target cleaning area.

[0082] Specifically, if the cleaning device analyzes, using the semantic map described above, that the room type at the current location of the cleaning device is not a predetermined room type, and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, then the user's cleaning intention is to clean the area where the second cleaning target is located. At this point, the cleaning device determines the area where the second cleaning target is located as the target cleaning area. In the subsequent steps, the cleaning device simply controls the cleaning device to clean the area where the second cleaning target is located, thereby making the cleaning area of ​​the cleaning device more in line with the user's requirements.

[0083] In this embodiment, if the cleaning device analyzes using the semantic map that the current location of the cleaning device is not a predetermined type of room, and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, the cleaning device determines the area where the second cleaning target is located as the user's desired cleaning area, that is, it determines the area where the second cleaning target is located as the target cleaning area. Then, in the subsequent steps, the cleaning device simply controls the cleaning device to clean the area where the second cleaning target is located, and the cleaning area of ​​the cleaning device better matches the user's requirements, improving the cleaning efficiency of the cleaning device and increasing user satisfaction.

[0084] Referring to Figure 6, in some embodiments, step 015 is: 0153, if the semantic map determines that a cleaning device is not present in a room of a predetermined type and that there is no second cleaning target within an area at a predetermined distance from the cleaning device, the step of determining the area at a predetermined distance from the cleaning device as the target cleaning area.

[0085] In this embodiment, the process of determining the target cleaning area using a semantic map involves the cleaning device first analyzing, using the semantic map, whether the room type at the current location of the cleaning device is a predetermined room type, and whether a second cleaning target exists within an area at a predetermined distance from the cleaning device.

[0086] Specifically, according to the semantic map described above, the cleaning device determines that the room type at its current location is not a predetermined room type, and that a second cleaning target exists within a predetermined distance from the cleaning device. do not In this analysis, the cleaning device determines an area at a predetermined distance from the cleaning device as the user's desired cleaning area, that is, it determines the area at a predetermined distance from the cleaning device as the target cleaning area.

[0087] Specifically, if the cleaning device analyzes, using the semantic map described above, that the room type at the current location of the cleaning device is not a predetermined room type, and that there is no second cleaning target within a predetermined distance from the cleaning device, then the user's cleaning intention is to clean the area at a predetermined distance from the cleaning device. At this point, the cleaning device determines the area at a predetermined distance from the cleaning device as the target cleaning area. In the subsequent step, the cleaning device simply controls the cleaning device to clean the area at a predetermined distance from the cleaning device, thereby making the cleaning area of ​​the cleaning device more in line with the user's requirements.

[0088] In this embodiment, if the cleaning device analyzes using the semantic map that the current location of the cleaning device is not a predetermined type of room and that there is no second cleaning target within a predetermined distance from the cleaning device, the cleaning device determines the area within a predetermined distance from the cleaning device as the user's desired cleaning area, i.e., determines the area within a predetermined distance from the cleaning device as the target cleaning area. Then, in the subsequent steps, the cleaning device simply controls the cleaning device to clean the area within a predetermined distance from the cleaning device, thereby making the cleaning area of ​​the cleaning device more in line with the user's requirements, improving the cleaning efficiency of the cleaning device, and increasing user satisfaction.

[0089] Referring to Figure 7, in some embodiments, step 01 is performed before step 015. 016, a step of recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, 017. If there is no first cleaning target, the step of confirming that a step is performed to determine the target cleaning area using a semantic map is performed.

[0090] In this embodiment, before determining the target cleaning area using the semantic map, the cleaning device also needs to recognize whether a first cleaning target exists in an area at a predetermined distance from the cleaning device. Specifically, the cleaning device may be equipped with a detection component that can be used to detect conditions near the location of the cleaning device, and the cleaning device can recognize conditions near the location of the cleaning device using this detection component, that is, it recognizes whether the first cleaning target exists near the cleaning device.

[0091] Furthermore, when the cleaning device determines that the first cleaning target does not exist within an area at a predetermined distance from the cleaning device, it determines that the cleaning device can perform the step of determining the target cleaning area using the semantic map.

[0092] Specifically, when the cleaning device recognizes that the first cleaning target does not exist within an area at a predetermined distance from the cleaning device, the user's cleaning intention is not to clean dirt or trash near the cleaning device. At this point, the cleaning device can perform steps such as analyzing the user's specific cleaning intention using the semantic map to determine whether to clean a predetermined type of room, clean near the second cleaning target, or clean an area near the cleaning device.

[0093] In this embodiment, before the cleaning device performs the step of determining the target cleaning area of ​​the cleaning device using the semantic map, it is also necessary to recognize whether a first target cleaning area exists within an area at a predetermined distance from the cleaning device. This allows for a more accurate determination of the user's cleaning intention, and by determining a more accurate target cleaning area, the cleaning area of ​​the cleaning device better matches the user's requirements, improving the cleaning efficiency of the cleaning device and enhancing the user experience.

[0094] In some embodiments, step 03 is, 031, the step of cleaning the target cleaning area using a cleaning method that involves cleaning along the edges and then cleaning in a curved shape, and after completion, returning to the charging position and charging.

[0095] In this embodiment, the cleaning device controls the cleaning device to clean the target cleaning area, and the cleaning device controls the cleaning device to clean the boundary of the target cleaning area along the edge, and then clean the area of ​​the target cleaning area in a curved shape.

[0096] Specifically, since the above target cleaning area is the area that users want to focus on cleaning, the cleaning device needs to employ edge-following and curved cleaning methods, which will ensure that the required cleaning effect can be achieved.

[0097] Furthermore, after the cleaning device confirms that it has completed cleaning the target cleaning area, it controls the cleaning device to return to the charging position and recharge. Specifically, the cleaning device can determine whether it has completed cleaning the target cleaning area based on the cleaning time of the cleaning device, and it can, but is not limited to, detecting the cleaning status near the cleaning device using the sensing component of the cleaning device to determine whether it has completed cleaning the target cleaning area.

[0098] In this embodiment, the cleaning device employs edge cleaning and curved cleaning methods to control the cleaning device and perform cleaning on the target cleaning area, thereby ensuring cleaning of the target cleaning area, achieving a cleaning effect, and improving user satisfaction.

[0099] In some embodiments, before step 03, the cleaning method is 04. Further includes the step of presenting a cleaning method for the cleaning device for the target cleaning area via voice.

[0100] In this embodiment, before controlling the cleaning device to clean the target cleaning area, the cleaning device needs to play voice prompts to inform the user of how the cleaning device will control the cleaning device to clean the target cleaning area.

[0101] Specifically, before the cleaning device cleans the target cleaning area, the device plays voice prompts so that the user can understand the area to be cleaned. For example, if the area to be cleaned by the cleaning device is the area where the tea table is located, the device will play the voice prompt "I will soon clean under the tea table," allowing the user to confirm whether the area to be cleaned by the cleaning device is the area the user wants to have cleaned.

[0102] In this embodiment, before controlling the cleaning device to clean the target cleaning area, the cleaning device plays voice prompts for the area to be cleaned. This allows the user to determine whether the area to be cleaned by the cleaning device is the area the user wants to clean. If the area indicated in the played voice prompts is not the area the user wants to clean, the cleaning device can adjust the cleaning area in a timely manner.

[0103] In the above embodiment, the first cleaning target includes one of the following: dirt, small granular debris, and hair-like debris.

[0104] In this embodiment, the first cleaning target may be, but is not limited to, dirt that is difficult to clean, small granular debris that is difficult to clean, and hair-like debris that is difficult to clean.

[0105] In the above embodiment, the second cleaning target is home appliances or furniture.

[0106] In this embodiment, the second cleaning target may be, but is not limited to, home appliances or furniture.

[0107] Note that Figure 2 is merely an illustrative example, and the method for determining the target area is not limited to what is described in the above embodiment.

[0108] Figure 8 is an exemplary flowchart illustrating the generation of a cleaning trajectory according to some embodiments of this specification. In some embodiments, step 02 in Figure 1 can be performed based on steps 021 and 022 in Figure 8.

[0109] 021. In response to the route planning command, the current clean state of the mop and the start and end points corresponding to the route planning command are determined.

[0110] 022. The cleaning trajectory from the starting point to the ending point is determined by the geographical location map, the cleaning status map, and the cleanliness status.

[0111] In possible embodiments, prior to step 021, the target cleaning area is divided into multiple areas and the cleaning order of each area is determined. The control device of the cleaning device divides the cleaning task into multiple serialization subtasks and dispatches the corresponding subtasks according to the serialization order, with each subtask having a corresponding subarea.

[0112] In a possible embodiment, step 021, the step of determining the start and end points corresponding to the route planning command, includes the step of determining the start and end points corresponding to the route planning command based on the current cleaning stage of the cleaning device and the cleaning sequence of each area.

[0113] In a possible embodiment, step 021 involves determining the current cleanliness of the mop. If the current cleaning stage of the cleaning device is the starting stage after self-cleaning in the water station, the steps include confirming that the current clean state of the mop is clean, The process includes determining the current cleanliness of the mop is dirty, if the current cleaning stage of the cleaning device is the stage of moving from an area where cleaning is currently completed to an area awaiting cleaning, or the stage of returning to a water station to wash the mop.

[0114] In a possible embodiment, step 022 involves determining the cleaning trajectory from the starting point to the ending point based on the geographical map, the cleaning status map, and the cleanliness status. The steps include determining areas free of obstacles using the aforementioned geographical map, The process includes the step of determining a cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness, based on the area without obstacles and the cleaning status map.

[0115] In a possible embodiment, the step of determining the cleaning trajectory from the starting point to the ending point according to a predetermined traffic strategy corresponding to the clean state, based on the area without obstacles and the cleaning status map, The method includes the steps of: determining the currently cleaned areas from the cleaning status map based on the clean state being clean; determining all areas from the starting point to the ending point that are free of obstacles and have been cleaned, based on the areas without obstacles and the currently cleaned areas; determining that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0116] In a possible embodiment, the step of determining the cleaning trajectory from the starting point to the ending point according to a predetermined traffic strategy corresponding to the clean state, based on the area without obstacles and the cleaning status map, The method includes the steps of: determining all areas awaiting cleaning from the cleaning status map based on the clean state being dirty; determining all areas awaiting cleaning without obstacles between the starting point and the ending point based on the areas without obstacles and all areas awaiting cleaning; determining that at least one continuous movement trajectory can be formed between the starting point, all areas awaiting cleaning without obstacles, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0117] In a possible embodiment, the method further includes the step of determining that the continuous movement trajectory cannot be constructed and determining the cleaning trajectory from the starting point to the ending point by the area free of obstacles.

[0118] In possible embodiments, prior to step 021, the user activates the cleaning device and performs cleaning by remotely controlling it via an application or remote control, or by directly controlling it with a button on the cleaning device.

[0119] In a possible embodiment, prior to step 021, the method further includes the step in which the control device of the cleaning device performs multilayer map initialization to obtain information on each map of the multilayer map and periodically updates the map information in real time during the cleaning process.

[0120] By using accurate geographical information obtained through multi-layer maps, the cleaning device can adjust its cleaning trajectory based on the geographical location map, cleaning status map, and the cleanliness status. The cleaning trajectory is self-adaptive, adjusting the subsequent cleaning trajectory according to the position and stage of the cleaning device, reducing secondary contamination of the floor surface, and enabling highly efficient cleaning.

[0121] In a possible embodiment, the geographical conditions of each sub-area are determined by the status of the obstacle layer of the raster layer of each sub-area, and the cleanliness of each sub-area is determined by the status of the cleanliness layer of the raster layer of each sub-area.

[0122] When planning cleaning routes, the geographical conditions and cleaning status of areas within the raster layer are determined based on the obstacle layer status and cleaning status layer status of the raster layer.

[0123] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0124] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0125] In possible embodiments, the geographical map and the cleaning status map are updated in real time according to their respective set intervals.

[0126] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0127] The need to update obstacle conditions stems from changes due to moving or temporary obstacles.

[0128] So-called updates can be considered as updates to the attribute values ​​corresponding to layers in a raster map.

[0129] In a possible embodiment, the method is Due to a failure in the cleaning route planning for a sub-area, the cleaning route planning for the next sub-area will be performed.

[0130] If the cleaning route plan for a sub-area fails, and it is determined that the sub-area is inaccessible, the sub-area is ignored, the cleaning sub-task switches to the next sub-area, and the cleaning route for that next sub-area is then replanned. If there is no next sub-area, the cleaning is completed.

[0131] This application as an example to The path planning algorithms used in the cleaning device path planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest path with the least contamination.

[0132] Referring to Figure 9, which shows the cleaning method provided in the present embodiment, the user remotely controls the cleaning device via an application or remote control, or directly controls it via a button on the cleaning device to activate the cleaning device and perform cleaning. The task management module of the cleaning device's control unit prepares to activate cleaning by planning the cleaning path based on the received cleaning command, and the cleaning command contains information such as the cleaning task type and cleaning area. The cleaning task is divided into multiple serialization subtasks, and the corresponding subtasks are transmitted according to the serialization order, with each subtask having a corresponding subarea. Furthermore, the map module of the cleaning device's control unit acquires map information for each layer of the multilayer map by performing multilayer map initialization, and periodically updates the map information in real time during the cleaning process.

[0133] During the path planning process for each sub-area, if the plan is successful, the cleaning of that sub-area is performed according to the planned path. If the plan fails, the plan is re-planned by adjusting the conditions of the map layer being considered. If the plan is successful this time, it is executed. If the plan fails again, the path planning for this sub-area is skipped, and the cleaning subtask is moved to the next sub-area. Ama The system then switches and replans the cleaning route for the next sub-area. If there is no further sub-area, the cleaning is complete.

[0134] The current cleanliness of the mop and the start and end points corresponding to the route planning command are determined by the route planning command. Furthermore, the cleaning trajectory from the start point to the end point is determined by the geographical situation map, the cleaning status map, and the cleanliness status.

[0135] When determining the cleanliness of a mop, if the current cleaning stage of the cleaning device is the departure stage after self-cleaning at the water station, the current cleanliness of the mop is determined to be clean. If the current cleaning stage of the cleaning device is the stage where the mop moves from the area where cleaning is currently completed to the area awaiting cleaning, or the stage where the mop is washed after returning to the water station, the current cleanliness of the mop is determined to be dirty.

[0136] Based on the aforementioned geographical map, areas without obstacles are identified, and based on the aforementioned areas without obstacles and the cleaning status map, a cleaning trajectory from the starting point to the ending point is determined according to a predetermined traffic strategy corresponding to the cleanliness status.

[0137] If the cleanliness is good, the areas that have been cleaned are determined from the cleaning status map, and all areas that are free of obstacles and have been cleaned are determined from the starting point to the ending point based on the areas without obstacles and the areas that have been cleaned. It is determined that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and the shortest movement trajectory among the at least one movement trajectory is determined as the cleaning trajectory from the starting point to the ending point.

[0138] Since the clean state is defined as dirty, all areas awaiting cleaning are determined from the cleaning status map, and all areas without obstacles and awaiting cleaning between the starting point and the ending point are determined by the areas without obstacles and all areas awaiting cleaning. It is determined that at least one continuous movement trajectory can be formed between the starting point, all areas without obstacles and awaiting cleaning, and the ending point, and the shortest movement trajectory among the at least one movement trajectory is determined as the cleaning trajectory from the starting point to the ending point.

[0139] If it is determined that the aforementioned continuous movement trajectory cannot be constructed, the cleaning trajectory from the starting point to the ending point is determined by the area without obstacles.

[0140] Figure 10 shows Layer 1 of the raster map, which stores information on obstacles and restricted areas (considered equivalent to obstacles) in a map that integrates recordings from multiple sensors. As shown in Figure 10, the area types in the layer include obstacles, free areas, and map boundaries.

[0141] Figure 11 shows Layer 2 of the raster map, where cleaning trajectory information from the cleaning device is stored. As shown in Figure 11, the area types in the layer include uncleaned, cleaned, and map boundaries.

[0142] In a possible embodiment, the steps of route planning for the entire cleaning process include: a step in which the cleaning device washes the mop and departs from the water station (hereinafter referred to as step 1); a step in which, during the normal cleaning process, the device moves from a cleaned area to another area awaiting cleaning (hereinafter referred to as step 2); and a step in which cleaning is interrupted or completed and the device needs to return to the water station to wash the mop (hereinafter referred to as step 3).

[0143] At each stage, it is necessary to plan a rational path for the cleaning device to move. In this process, a multi-layer raster map is used, and different planning strategies are adopted depending on the geographical stage in which the cleaning device is located. By ensuring that the equipment preferentially passes through areas cleaned in stage 1 and areas not cleaned in stages 2 and 3, secondary contamination of the floor surface is reduced.

[0144] Figure 12 shows a schematic diagram of an embodiment of route planning, and it can be seen that there are two selectable routes, namely Route 1 and Route 2, for route planning of the cleaning task in the sub-area. Route 2 is used when the cleaning device cleans the starting point and then proceeds to an area that is free of obstacles and already clean. Ta It is preferable to select and pass through an area, and in Route 2, when the cleaning device returns from the end point to the starting point, it is preferable to select and pass through an area that is free of obstacles and does not need to be cleaned.

[0145] During the cleaning process of the cleaning device, a two-layer raster map is maintained in real time. Each layer of the raster map stores one type of environmental feature. Layer 1 stores information on obstacles and restricted areas (considered equivalent to obstacles) from a map that integrates recordings from multiple sensors, while Layer 2 stores information on the cleaning trajectory of the cleaning device. In the path planning of the cleaning device, the robot employs different planning strategies depending on the different cleaning stages. During normal cleaning and navigation to wash the mop, it prioritizes passing through areas that are not to be cleaned, and then proceeds to clean areas after washing the mop. but When cleaning continues, prioritizing the area that has been cleaned will reduce secondary contamination of the floor surface.

[0146] While the embodiments of this application use as an example the target information most commonly considered in application scenarios for cleaning devices, the embodiments of this application are not limited to this, as other layers such as obstacle information, cleaning trajectory information, and user-specific setting information may also be included.

[0147] In this embodiment, the method for acquiring geographical information includes, but is not limited to, raster maps.

[0148] In some embodiments, step 021 is, 0211, If ​​the current cleaning stage of the cleaning device is the starting stage after self-cleaning in the water station, the step is to confirm that the current clean state of the mop is clean, 0212, if the current cleaning stage of the cleaning device is the stage of moving from the currently cleaned area to the area awaiting cleaning, or the stage of returning to the water station to wash the mop, the step of determining that the current clean status of the mop is dirty.

[0149] In possible embodiments, prior to step 0211, the user activates the cleaning device and performs cleaning by remotely controlling it via an application or remote control, or by directly controlling it with a button on the cleaning device.

[0150] In a possible embodiment, in step 0211, the control device of the cleaning device prepares to start cleaning by planning a cleaning path based on the cleaning command received, where the cleaning command includes information such as the cleaning task type and the cleaning area.

[0151] In a possible embodiment, the geographical map of each sub-area is determined by the status of the obstacle layer of the raster layer of each sub-area, and the cleanliness map of each sub-area is determined by the status of the cleanliness layer of the raster layer of each sub-area.

[0152] When planning cleaning routes, the obstacle and cleaning status of areas within a raster layer are determined based on the obstacle layer status and cleaning status of the raster layer.

[0153] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0154] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0155] In a possible embodiment, the current cleanliness status of the mop of the cleaning device, the geographical map of each sub-area, and the cleaning status map are updated in real time according to their respective set intervals.

[0156] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0157] The need to update geographical conditions stems from changes due to movement or temporary obstacles. This so-called update can be considered an update of attribute values ​​corresponding to layers in a raster map.

[0158] This application as an example to The routing algorithms used in the cleaning device routing planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest route with the least contamination.

[0159] In some embodiments, step 021 is, 0213, The step of determining areas without obstacles using the aforementioned geographical map, 0214. The further step is to determine a cleaning trajectory from a starting point to an ending point, according to a predetermined traffic strategy corresponding to the cleanliness, based on an area free of obstacles and a cleaning status map.

[0160] When planning cleaning routes, the obstacle and cleaning status of areas within a raster layer are determined based on the obstacle layer status and cleaning status of the raster layer.

[0161] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0162] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0163] In a possible embodiment, the current cleanliness status of the mop of the cleaning device, the geographical map of each sub-area, and the cleaning status map are updated in real time according to their respective set intervals.

[0164] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0165] The need to update geographical conditions stems from changes due to movement or temporary obstacles.

[0166] So-called updates can be considered as updates to the attribute values ​​corresponding to layers in a raster map.

[0167] This application as an example to The path planning algorithms used in the cleaning device path planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest path with the least contamination.

[0168] In some embodiments, step 02 is, Step a, in response to a route planning command, determine the current clean state of the mop and the start and end points corresponding to the route planning command, and if the current cleaning stage of the cleaning device is the departure stage after self-cleaning at the water station, determine that the current clean state of the mop is clean, and if the current cleaning stage of the cleaning device is the stage of moving from the area where cleaning is currently completed to the area waiting to be cleaned, or the stage of returning to the water station to wash the mop, determine that the current clean state of the mop is dirty, Step b further includes determining areas free of obstacles using a geographical map, and determining a cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness of the areas free of obstacles and a cleaning status map.

[0169] vinegarIn step b, the cleanliness status is determined to be clean, the areas that have been cleaned are determined from the cleaning status map, all areas that are free of obstacles and have been cleaned are determined from the starting point to the ending point based on the areas without obstacles and the areas that have been cleaned, it is determined that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and the shortest movement trajectory among the at least one movement trajectory is determined as the cleaning trajectory from the starting point to the ending point.

[0170] vinegar In step b, since the clean state is dirty, all areas awaiting cleaning are determined from the cleaning status map, and all areas without obstacles and awaiting cleaning between the starting point and the ending point are determined by the areas without obstacles and all areas awaiting cleaning, and it is determined that at least one continuous movement trajectory can be formed between the starting point, all areas without obstacles and awaiting cleaning, and the ending point, and the shortest movement trajectory among the at least one movement trajectory is determined as the cleaning trajectory from the starting point to the ending point.

[0171] vinegar Before step a, the user activates the cleaning device and performs cleaning by remotely controlling it via an application or remote control, or by directly controlling it with a button on the cleaning device.

[0172] vinegar In step a, the control device of the cleaning device prepares to start cleaning by planning the cleaning path based on the received cleaning command, and here the cleaning command contains information such as the cleaning task type and cleaning area.

[0173] before The geographical conditions map for each sub-area is determined by the status of the obstacle layer in the raster layer of each sub-area, and the cleaning status map for each sub-area is determined by the status of the cleaning status layer in the raster layer of each sub-area.

[0174] When planning cleaning routes, the obstacle and cleaning status of areas within a raster layer are determined based on the obstacle layer status and cleaning status of the raster layer.

[0175] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0176] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0177] before The current cleanliness status of the cleaning device's mop, the geographical location map of each sub-area, and the cleaning status map are updated in real time according to their respective setting cycles.

[0178] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0179] The need to update geographical conditions stems from changes due to movement or temporary obstacles.

[0180] So-called updates can be considered as updates to the attribute values ​​corresponding to layers in a raster map.

[0181] This application as an example to The path planning algorithms used in the cleaning device path planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest path with the least contamination.

[0182] In some embodiments, step 02 is, Step c, in response to a route planning command, the current clean state of the mop and the start and end points corresponding to the route planning command are determined, and if the current cleaning stage of the cleaning device is the departure stage after self-cleaning at the water station, the current clean state of the mop is determined to be clean, and if the current cleaning stage of the cleaning device is the stage of moving from the area where cleaning is currently completed to the area awaiting cleaning, or the stage of returning to the water station to wash the mop, the current clean state of the mop is determined to be dirty, Step d further includes determining areas free of obstacles using a geographical map, and determining a cleaning trajectory from the starting point to the ending point according to a predetermined traffic strategy corresponding to the cleanliness of the areas free of obstacles and a cleaning status map.

[0183] vinegar Step d includes the steps of determining the currently cleaned areas from the cleaning status map based on the cleanliness status being clean, determining all areas between the starting point and the ending point that are free of obstacles and have been cleaned, based on the areas without obstacles and the currently cleaned areas, and determining that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0184] vinegarStep d includes the steps of: determining all areas awaiting cleaning from the cleaning status map, based on the clean state being dirty; determining all areas awaiting cleaning without obstacles between the starting point and the ending point, based on the areas without obstacles and all areas awaiting cleaning; determining that at least one continuous movement trajectory can be formed between the starting point, all areas awaiting cleaning without obstacles, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0185] before The method further includes the step of determining that the continuous movement trajectory cannot be constructed and determining the cleaning trajectory from the starting point to the ending point using areas free of obstacles.

[0186] vinegar Before step c, the user activates the cleaning device and performs cleaning by remotely controlling it via an application or remote control, or by directly controlling it with a button on the cleaning device.

[0187] vinegar In step c, the control device of the cleaning device prepares to start cleaning by planning the cleaning path based on the received cleaning command, and here the cleaning command contains information such as the cleaning task type and cleaning area.

[0188] before The geographical conditions map for each sub-area is determined by the status of the obstacle layer in the raster layer of each sub-area, and the cleaning status map for each sub-area is determined by the status of the cleaning status layer in the raster layer of each sub-area.

[0189] When planning cleaning routes, the obstacle and cleaning status of areas within a raster layer are determined based on the obstacle layer status and cleaning status of the raster layer.

[0190] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0191] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0192] before The current cleanliness status of the cleaning device's mop, the geographical location map of each sub-area, and the cleaning status map are updated in real time according to their respective setting cycles.

[0193] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0194] The need to update geographical conditions stems from changes due to movement or temporary obstacles.

[0195] So-called updates can be considered as updates to the attribute values ​​corresponding to layers in a raster map.

[0196] This application as an example to The path planning algorithms used in the cleaning device path planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest path with the least contamination.

[0197] In some embodiments, step 02 is, Step e, in response to a route planning command, the current clean state of the mop and the start and end points corresponding to the route planning command are determined, and if the current cleaning stage of the cleaning device is the departure stage after self-cleaning at the water station, the current clean state of the mop is determined to be clean, and if the current cleaning stage of the cleaning device is the stage of moving from the area where cleaning is currently completed to the area awaiting cleaning, or the stage of returning to the water station to wash the mop, the current clean state of the mop is determined to be dirty, Step f further includes determining areas free of obstacles using a geographical map, and determining a cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness of the areas free of obstacles and a cleaning status map.

[0198] vinegar Step e further includes the step of dividing the target cleaning area into multiple areas and determining the cleaning order for each area before responding to the route planning command.

[0199] before The step of determining the start and end points corresponding to the route planning command includes determining the start and end points corresponding to the route planning command based on the current cleaning stage of the cleaning device and the cleaning sequence of each area.

[0200] vinegar Step f includes the steps of determining the currently cleaned areas from the cleaning status map based on the cleanliness status being clean, determining all areas between the starting point and the ending point that are free of obstacles and have been cleaned, based on the areas without obstacles and the currently cleaned areas, and determining that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0201] vinegarStep f includes the steps of: determining all areas awaiting cleaning from the cleaning status map, based on the clean state being dirty; determining all areas awaiting cleaning without obstacles between the starting point and the ending point, based on the areas without obstacles and all areas awaiting cleaning; determining that at least one continuous movement trajectory can be formed between the starting point, all areas awaiting cleaning without obstacles, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0202] before The method further includes the step of determining that the continuous movement trajectory cannot be constructed and determining the cleaning trajectory from the starting point to the ending point using areas free of obstacles.

[0203] vinegar Before step e, the user activates the cleaning device and performs cleaning by remotely controlling it via an application or remote control, or by directly controlling it with a button on the cleaning device.

[0204] vinegar In step e, the control device of the cleaning device prepares to start cleaning by planning the cleaning path based on the received cleaning command, and here the cleaning command contains information such as the cleaning task type and cleaning area.

[0205] before The geographical conditions map for each sub-area is determined by the status of the obstacle layer in the raster layer of each sub-area, and the cleaning status map for each sub-area is determined by the status of the cleaning status layer in the raster layer of each sub-area.

[0206] When planning cleaning routes, the obstacle and cleaning status of areas within a raster layer are determined based on the obstacle layer status and cleaning status of the raster layer.

[0207] At the stage immediately after the cleaning device's mop has been washed, the device will prioritize passing through areas that are free of obstacles and have already been cleaned, based on the obstacle layer status and cleaning status layer status. At the normal cleaning stage, or at the interruption or completion stage, when there is a high probability that the cleaning device's mop is dirty, the device will prioritize passing through uncleaned areas, based on the obstacle layer status and cleaning status layer status.

[0208] When planning the route, the location of the cleaning device at each stage should be carefully considered, and different planning strategies should be adopted at different stages to achieve greater efficiency and avoid secondary contamination.

[0209] before The current cleanliness status of the cleaning device's mop, the geographical location map of each sub-area, and the cleaning status map are updated in real time according to their respective setting cycles.

[0210] The real-time update cycles for the geographical location map and cleaning status map can be set to different cycles or to the same cycle, depending on the user's needs.

[0211] The need to update geographical conditions stems from changes due to movement or temporary obstacles.

[0212] So-called updates can be considered as updates to the attribute values ​​corresponding to layers in a raster map.

[0213] This application as an example to The path planning algorithms used in the cleaning device path planning process include, but are not limited to, DijkStra, A*, and JPS. The objective is to find the shortest path with the least contamination.

[0214] In summary, by responding to a route planning command, the current cleanliness of the mop and the start and end points corresponding to the route planning command are determined, and the cleaning trajectory from the start to the end point is determined based on the geographical situation map, the cleaning status map, and the cleanliness status. In the process of the cleaning task of the cleaning device, the route is rationally planned to minimize secondary contamination of the road surface and improve the cleaning effect.

[0215] Note that Figure 8-12 is merely an illustrative example, and the method for generating the cleaning trajectory is not limited to what is described in the above embodiment.

[0216] Figure 13 is an illustrative flowchart of a cleaning method according to some embodiments of this specification. In some embodiments, the cleaning method is 01. Steps to determine the target cleaning area, 05. The steps include marking obstacles within the target cleaning area, avoiding the obstacles within the target cleaning area, and performing the cleaning operation. 06. A step to detect the state of obstacles within the target cleaning area and identify the obstacles whose state has changed, 07. Further includes the step of performing a cleaning operation at the location of the obstacle whose state has changed.

[0217] In actual dynamic application scenarios, such as people walking, pets moving, doors opening and closing, and furniture moving, the execution terminal for the embodiment of the present invention may be, but is not limited to, a cleaning device, an automatic cleaning machine, a smart vacuum cleaner, or a robotic vacuum cleaner. The following description will use a cleaning device as the execution terminal.

[0218] Regarding step 01, when performing a cleaning task, the cleaning device first determines the target cleaning area within the cleaning scene. If an obstacle is encountered when determining the target cleaning area, the device avoids the detected obstacle and marks it. In the subsequent cleaning process, if the obstacle detected when determining the target cleaning area is a dynamic obstacle and its position moves, the cleaning device re-cleans that area.

[0219] Regarding step 05, the cleaning device itself has the functions of target recognition, target segmentation, and target tracking. These functions allow the robot to mark obstacles in the target cleaning area when performing the cleaning task. After marking the current obstacles, it saves them in the collection of obstacles, and then cleans the remaining target cleaning area while avoiding the current obstacles.

[0220] Regarding step 06, during each cleaning process, the cleaning device detects the condition of nearby obstacles in real time. If it detects a change in the condition of an obstacle, it marks the changed obstacle so that it can be checked during the next cleaning.

[0221] Regarding step 07, the cleaning device can perform steps 01 through 06 sequentially in a single cleaning task until the current target cleaning area is cleaned. After the current cleaning task is completed, step 07 is executed to remove the collection of obstacles. Traverse and check. The system checks if the state of any obstacles in the group has changed, and if any obstacles have changed state, it moves to the location of the changed obstacle and performs a cleaning operation.

[0222] Furthermore, in the current cleaning task, the cleaning device immediately moves to the location of an obstacle and performs the cleaning operation after detecting a change in the state of that obstacle. For example, after avoiding the current obstacle, the cleaning device can immediately detect a change in the state of the obstacle and immediately clean the obstacle at its original position, eliminating the need to perform additional cleaning at that location after the entire room has been cleaned.

[0223] The cleaning method of this embodiment allows for the detection of movable obstacles within the target cleaning area during the cleaning process, and for determining whether the state of the dynamic obstacles has changed. By moving to the location of the obstacle whose state has changed and performing the cleaning operation, it is possible to effectively prevent cleaning omissions due to object movement and improve the coverage rate of automatic cleaning of dynamic scenes.

[0224] What I understand is that the step of marking obstacles within the target cleaning area is, This includes a step of marking the location, type, and shape of obstacles within the target cleaning area.

[0225] Furthermore, when the cleaning device encounters an obstacle, it first marks the location of the obstacle within the target cleaning area, and then, based on the visual sensing device and radar device installed on the cleaning device, it can acquire the type and shape of the obstacle. Obstacle types are divided into static obstacles and dynamic obstacles, and this embodiment of the present invention mainly focuses on the impact of dynamic obstacles on the cleaning coverage rate. There are many subcategories within the category of dynamic obstacles, such as furniture, pets, shoes, socks, doors, and trash cans.

[0226] Specifically, the type includes both dynamic and static obstacles, and is used to determine whether or not the obstacle needs to be detected. The position of static obstacles generally does not change, and once their position is determined, the area they cover is not part of the target cleaning area. Therefore, static obstacles are also marked during the marking process, but the robot does not need to detect the state of static obstacles, saving computational power.

[0227] Obstacle types are generally collected and processed by a visual sensing device, which may be an RGB camera. In this case, the cleaning device collects RGB image data of obstacles along the route, marks the location of the obstacles, and outputs the type of data of the obstacles currently being collected by a target recognition method. Dynamic obstacles refer to obstacles whose position is constantly moving or whose shape changes in the scene, while static obstacles refer to obstacles whose position is constantly unchanged in the scene, such as walls and pillars.

[0228] Obstacle shapes are generally collected and processed by radar devices, which may be rotary laser lidar devices. Rotary laser lidar devices can collect point cloud information of obstacles, and this point cloud information includes the 3D shape of the obstacle. In some cases, obstacle information requires a combination of visual sensing devices and laser devices to comprehensively determine the type and shape of the obstacle. For example, in the case of pets, changes in their movement can affect the range of the area where cleaning is required.

[0229] Specifically, the embodiment of the present invention constructs a target recognition method and employs a general deep learning-based target detection model as its foundation, such as a Convolutional Neural Network (CNN), R-CNN, Fast R-CNN, or YOLO network model. The target recognition algorithm trains the target detection model by constructing various training sets in the field of household cleaning, and the labels in the training sets include types of obstacles commonly found in household scenes, such as furniture, people, pets, shoes, chairs, power lines, socks, doors, and trash cans. By fetching real-time depth features of obstacles and training, the target recognition method in the embodiment of the present invention can ultimately output the type of obstacle using visual data.

[0230] Furthermore, the door, which is an obstacle, needs to be processed comprehensively by combining information obtained from the visual sensing device and the laser device. The visual sensing device detects whether the door is open or closed, and the laser device determines whether the opening size of the door is suitable for the passage of the cleaning device, thereby obtaining the door's position and state. Here, an open door indicates that the cleaning device can enter, and a closed door indicates that the cleaning device cannot enter. Doors are specifically highlighted among the obstacles because the opening and closing of doors affects the range of the target cleaning area. Therefore, if the cleaning device recognizes that the state of the door has changed from closed to open in step 06, it needs to move to the door's position and repeat the process of determining the target cleaning area from step 01.

[0231] The cleaning method of this embodiment allows the location, type, and shape of obstacles within the target cleaning area to be marked during the cleaning process, and the marked obstacles can be stored in an obstacle collection. Not all obstacle types in the obstacle collection are known; if the state of some obstacles changes during subsequent detection, those obstacle types can be marked in the obstacle collection as dynamic obstacles. By marking dynamic obstacles, the method of this embodiment allows the cleaning device to handle the location of dynamic obstacles in dynamic scenes and avoid missed cleaning areas.

[0232] What I understand is that the steps to detect the state of obstacles within the target cleaning area and identify obstacles whose state has changed are as follows: A step of detecting the location and shape of dynamic obstacles within the target cleaning area, The process includes the step of determining dynamic obstacles whose state has changed based on dynamic obstacles whose position or shape has changed.

[0233] In the embodiments of the present invention, mainly the detection of dynamic obstacles is performed, and the states of the obstacles include the existing state and the non-existing state. In particular, in the case of a door, the existing state corresponds to the closed state, and the non-existing state corresponds to the open state. When the cleaning device executes a cleaning task in the target cleaning area, it collects the states of the obstacles within the sensing areas of its visual sensing device and radar device in real time. The change in the state of the obstacle includes a change in position or a change in shape. These two changes cause the obstacle to move from its original position, and there is a possibility that the state of the obstacle changes from the existing state to the non-existing state. When the state of the obstacle disappears, the cleaning device can re-clean the area occupied by the obstacle.

[0234] It can be understood that the cleaning operation includes a first cleaning operation and a second cleaning operation. Here, the first cleaning trajectory determined by executing the first cleaning operation is a closed loop, and the second cleaning trajectory determined by executing the second cleaning operation can fill the target cleaning area.

[0235] In addition, the first cleaning operation may be a cleaning operation along the edge. Specifically, it includes cleaning along the wall or along the edge of the obstacle. Starting from the starting point and finally returning to the starting point, the cleaning trajectory forms a closed loop. The second cleaning operation may be a zigzag cleaning operation. Specifically, the cleaning device starts from the origin position, enters the target cleaning area, starts running in the positive direction. When the cleaning device reaches the rightmost end of the cleaning area, it changes direction and runs in the opposite direction. When the cleaning device reaches the leftmost end of the cleaning area, it changes direction and runs in the positive direction. Finally, when the zigzag cleaning operation ends, the formed second cleaning trajectory fills the first cleaning trajectory formed by the cleaning operation along the edge.

[0236] Referring to FIG. 14, it can be understood that when the drawing shows an ideal state without obstacles, the first cleaning operation is a cleaning along the edge, and the first cleaning trajectory and the second cleaning trajectory finally formed when the second cleaning operation is a zigzag cleaning.

[0237] What I understand is that the step of determining the target cleaning area is, The process includes the steps of performing a first cleaning operation and determining a target cleaning area based on the cleaning trajectory of the first cleaning operation.

[0238] The cleaning device performs a first cleaning action, cleaning around the walls of the environment and acquiring a target cleaning area. This target cleaning area becomes a map created during this cleaning task, and the positions of subsequent obstacles are saved to the map in coordinate format. For example, the cleaning device cleans along the edges of a rectangular room and acquires a rectangular target cleaning area.

[0239] What can be understood is that the steps of avoiding obstacles and performing cleaning actions within the target cleaning area are: The steps include performing a second cleaning operation within the target cleaning area, The system includes the steps of: performing a first cleaning action when it is determined that an obstacle has been encountered, and continuing to perform a second cleaning action after avoiding the obstacle.

[0240] After confirming the target cleaning area, the cleaning device performs a bow-shaped cleaning motion within the target area. If it encounters an obstacle, it cleans along the edge of the obstacle in a counterclockwise direction, and then continues the bow-shaped cleaning motion. After repeatedly performing the first and second cleaning motions, it is finally possible to clean all areas within the target cleaning area except those covered by obstacles.

[0241] What can be understood is that the step of performing a cleaning operation at the location of an obstacle whose state has changed involves three situations: the first situation, the second situation, and the third situation.

[0242] In the first scenario, the obstacle is removed, and a second cleaning operation is performed in the area occupied by the obstacle. Specifically, by performing additional cleaning in response to real-time changes in the obstacle through a curved cleaning pattern, the entire room does not need to be cleaned again, thus improving cleaning efficiency.

[0243] In the second scenario, the obstacle moves slightly, and the first cleaning operation is performed in the area occupied by the obstacle. If the position of the obstacle moves only slightly, the area originally covered by the obstacle is not completely exposed. At this time, the first cleaning operation is performed, and the exposed area is cleaned additionally.

[0244] In the third scenario, if the original obstacle has been removed but another obstacle exists, then the first and second cleaning operations must be combined. For example, first, the boundary of the new obstacle is determined by cleaning along the edge, and then the area between the original boundary and the current boundary is cleaned in a curved pattern to clean the uncleaned target area.

[0245] Furthermore, a second cleaning operation is performed in the area occupied by the obstacle whose state has changed.

[0246] What can be understood is an obstacle to When an encounter occurs, the present invention uses a path planning algorithm based on the first and second cleaning operations to optimize the first and second cleaning trajectories, thereby avoiding repeated cleaning as much as possible.

[0247] For example, the operating process by which a cleaning device performs a cleaning method includes the following:

[0248] Step 201: The cleaning device cleans along the edges of the target cleaning area.

[0249] Step 202: The cleaning device performs a bow-shaped cleaning within the target cleaning area, removing obstacles. to When encountered, clean along the edges.

[0250] In steps 203, 201, and 202, the movable obstacle oi is recorded in obstacle set 0.

[0251] Movable obstacles can be divided into three situations. a. If the obstacle is visible to the laser lidar, record the location and point cloud information of the obstacle. b. If it is an obstacle recognized by the RGB camera, record the position and type of the obstacle. c. If it is the door of the room, record the opening and closing state of the room door.

[0252] Step 204: Repeat Step 202 and Step 203 until the cleaning of the target cleaning area is completed.

[0253] Step 205: Obstacle collection 0 Traverse and check. , detect whether there is an obstacle, and the detection method is as follows.

[0254] e. If it is an obstacle detected by the laser radar, check whether there is point cloud information.

[0255] f. If it is an obstacle detected by the RGB camera, check whether the position of the obstacle moves.

[0256] Step 206: If there is no obstacle detected in Step 205, perform a single figure-eight-shaped cleaning on the area occupied by the obstacle.

[0257] In addition, in the above operation process, the cleaning task is divided into two times. The first cleaning is the conventional normal cleaning, but it is necessary to mark the position and state of the dynamic obstacles. The second cleaning is to inspect and perform additional cleaning on the area where the movable obstacles are located. By the above method, not only can the efficiency of the first cleaning and the obstacle avoidance success rate be improved, but also the coverage rate of the second cleaning can be improved.

[0258] Note that FIGS. 13-14 are merely illustrative explanations, and the method for generating the cleaning trajectory is not limited to the content described in the above embodiments.

[0259] FIG. 15 is an exemplary flowchart for performing a cleaning operation according to some embodiments of the present specification. In some embodiments, Step 03 in FIG. 1 can be executed based on Steps 032-034 in FIG. 15.

[0260] 032. Monitor the amount of dust collected in the dust box of the cleaning device.

[0261] 034. Based on the relationship between the amount of dust collected and a predetermined dust amount threshold, the target operating mode of the cleaning device is determined, and here the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device.

[0262] 035. The cleaning operation is performed by driving and operating the cleaning device in the target operating mode.

[0263] Furthermore, this invention is used to represent the cleaning function of an operating mode by adjusting the width of adjacent cleaning paths of the cleaning device, the number of cleaning cycles for adjacent cleaning paths, and the motor rotation speed in accordance with the current level of soiling in the cleaning area.

[0264] For example, the more the current area is determined to be dirty, the faster the dust collection motor's rotation speed is increased. And / or, the more the current area is determined to be dirty, the narrower the width of the adjacent cleaning path is determined to be, the wider the overlapping area of ​​the paths is determined to be, and the better the cleaning effect. And / or, the more the current area is determined to be dirty, the more the adjacent paths are cleaned repeatedly multiple times, further improving the cleaning effect.

[0265] Specifically, in this application, if the dust collection volume in the dust box is detected to be greater than a predetermined dust volume threshold, the current cleaning area of ​​the cleaning device is recognized as a dirty area. Furthermore, it is necessary to adjust the cleaning device and operate it in a target operating mode with high cleaning intensity and a large cleaning area. If the dust collection volume in the dust box is detected to be less than a predetermined dust volume threshold, the current cleaning area of ​​the cleaning device is recognized as a non-dirty area. Furthermore, it is necessary to adjust the cleaning device and operate it in a target operating mode with medium-low cleaning intensity and a small cleaning area.

[0266] Furthermore, this invention is not specifically limited to a predetermined dust amount threshold. For example, it may be 5g, 10g, or other values.

[0267] Furthermore, this invention allows the cleaning function to be operated according to the target operating mode by determining a target operating mode used to represent the cleaning intensity and cleaning area, and then driving the cleaning device.

[0268] For example, the rotation speed of the dust collection motor of the cleaning device is controlled according to the degree of dirt on the floor surface. What can be understood is that the rotation speed of the dust collection motor is set lower for areas with a light degree of dirt, and the degree of dirt... but For areas with heavy loads, the rotation speed of the dust collection motor is set higher. This method not only ensures effective cleaning but also reduces power consumption and extends the operating time of the cleaning device.

[0269] Alternatively, this invention can also control the overlap width of the cleaning device's travel route and the number of back-and-forth cleaning cycles depending on the degree of soiling of the floor surface. This method can enhance the cleaning effect and further improve cleaning. Quality of guarantee do.

[0270] In one configuration, it is sufficient to simply run the general cleaning intensity and cleaning area mode on areas where the degree of floor soiling is not severe. This ensures both cleaning effectiveness and cleaning efficiency.

[0271] In this embodiment, the amount of dust collected in the dust box of the cleaning device is monitored, and the target operating mode of the cleaning device is determined based on the relationship between the amount of dust collected and a predetermined dust threshold. Here, the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device, and the operation of the cleaning device is driven in the target operating mode. By applying the technical proposal of this application, the cleaning intensity and cleaning area of ​​the cleaning device can be adjusted in accordance with the detected amount of dust collected in the dust box of the cleaning device. This makes it possible to operate the robot with high-intensity cleaning in dirty areas and with low-intensity cleaning in normal areas. Furthermore, it is possible to guarantee the cleaning effect on dirty areas and avoid the problem of low cleaning efficiency in specific areas that occurs when cleaning is always performed with the same cleaning intensity and cleaning area, which exists in related technologies.

[0272] Selectively, in possible embodiments of the present application, step 033 is, 0331, The step of detecting that the amount of dust collected is greater than a predetermined dust amount threshold and determining that the cleaning device will be controlled to operate the target operating mode of the cleaning function at a first cleaning intensity and a first cleaning area, or, 0332, the step of detecting that the amount of dust collected is not greater than a predetermined dust amount threshold and determining that the cleaning device will be controlled to operate the target operating mode of the cleaning function at a second cleaning intensity and a second cleaning area, wherein the second cleaning intensity is lower than the first cleaning intensity and the second cleaning area is smaller than the first cleaning area.

[0273] First, the cleaning intensity in this application can correspond to various cleaning operation parameters. For example, it can include the rotational speed of the dust collection motor of the cleaning device. It can be understood that the higher the rotational speed of the dust collection motor, the higher the cleaning intensity of the cleaning device.

[0274] Alternatively, cleaning intensity may include the number of times the cleaning device is cleaned. It is understood that the more times the cleaning is repeated, the higher the cleaning intensity of the cleaning device. Alternatively, cleaning intensity may include the interval between travels along the cleaning path of the cleaning device. It is understood that the shorter the travel interval, the higher the cleaning intensity of the cleaning device.

[0275] Furthermore, the cleaning area of ​​the cleaning device can be controlled based on the degree of dirtiness on the floor surface. Essentially, the more dirty the floor surface, the larger the predetermined cleaning area becomes, and for areas where the floor surface is not heavily soiled, it is sufficient to simply set the area for general cleaning.

[0276] To illustrate with an example, if the predetermined dust amount threshold is 5g, and the cleaning device monitors the dust box and determines that the current dust amount is greater than 5g, then the current cleaning area can be determined to be a floor surface soiling area, and that area is recognized as a high-cleaning area. Furthermore, the present invention allows for the selection of a target operating mode that operates the cleaning function with high cleaning intensity (i.e., a first cleaning intensity) and a large cleaning area (i.e., a first cleaning area) by a predetermined control strategy.

[0277] Here, high cleaning strength and large The target operating mode corresponding to the cleaning area is a dust collection motor rotation speed of 500. rotate The rotation speed can reach one minute, the distance between two adjacent travel routes can be 1 cm, the number of cleaning repetitions can be 5, and the cleaning area can be 1 square meter. Then, after the subsequent cleaning device selects the target operating mode, it operates the cleaning function according to the rotation speed of the dust collection motor, travel interval, cleaning area, and number of cleaning repetitions represented by the target operating mode.

[0278] For example, if the predetermined dust amount threshold is 5g, and the cleaning device monitors the dust box and determines that the current dust collection amount is less than 5g (e.g., 3g), it can determine that the current cleaning area is a floor surface with a moderate level of dirt, and recognize that area as a medium cleaning area. Furthermore, the present invention allows for the selection of a target operating mode in which the cleaning function operates with a medium cleaning intensity (i.e., a second cleaning intensity) and a medium cleaning area (i.e., a second cleaning area) through a predetermined control strategy.

[0279] Here, the target operating mode corresponding to the medium cleaning intensity and medium cleaning area is a dust collection motor rotation speed of 300. rotate The rotation speed can reach 1 minute, the distance between two adjacent travel routes is 2 cm, the number of cleaning repetitions is 3, and the cleaning area is 0.8 square meters. Then, after the subsequent cleaning device selects the target operating mode, it operates the cleaning function according to the rotation speed of the dust collection motor, travel interval, cleaning area, and number of cleaning repetitions represented by the target operating mode.

[0280] To give another example of selectability, for instance, if the predetermined dust amount threshold is 5g, and the cleaning device monitors the dust box and determines that the current dust collection amount is less than 5g (e.g., 0.5g), it can determine that the current cleaning area is a clean area and recognize that area as a low-cleaning area. Furthermore, the present invention uses a predetermined control strategy to enable low cleaning intensity (i.e., second cleaning intensity) and small A target operating mode can be selected to operate the cleaning function in the cleaning area (i.e., the second cleaning area).

[0281] Here, low cleaning strength and small The target operating mode corresponding to the cleaning area is a dust collection motor rotation speed of 100. rotateThe rotation speed can reach 1 minute, the distance between two adjacent travel routes is 5 cm, the number of cleaning repetitions is 1, and the cleaning area is 0.3 square meters. Then, after the subsequent cleaning device selects the target operating mode, it operates the cleaning function according to the rotation speed of the dust collection motor, travel interval, cleaning area, and number of cleaning repetitions represented by the target operating mode.

[0282] In a possible embodiment of the present application, the step of detecting that the amount of dust collected is greater than a predetermined dust threshold and determining to control the cleaning device to operate a target operating mode of the cleaning function at a first cleaning intensity and a first cleaning area is: The dust collection amount is determined to be greater than the predetermined dust amount threshold, and the location of the cleaning device is recorded. The method further includes the steps of marking an area within a predetermined range from the current location as a high-cleaning area, controlling the cleaning device within the high-cleaning area, and operating the cleaning function at a first cleaning intensity and a first cleaning area.

[0283] In one configuration, the present invention ensures that when the cleaning device monitors the dust box and determines that the current amount of collected dust is greater than a predetermined dust amount threshold, the operating range in which the cleaning function operates with a first cleaning intensity and a first cleaning area acts on the dirty area. Therefore, the present invention first needs to determine the location of the dirty area.

[0284] Specifically, it is necessary to first record the current location of the cleaning device. For example, the coordinate point is the center point of bedroom A. Furthermore, an area within a predetermined range (e.g., within a radius of 50 cm) from the said center point can be marked as a high-cleaning area. Then, the cleaning function is operated in the said high-cleaning area (i.e., the area within a radius of 50 cm with the center point of bedroom A as the origin) with a first cleaning intensity and a first cleaning area. This ensures that the target operating mode of the cleaning device acts on the dirty area.

[0285] Furthermore, this application does not specifically limit the specified range; for example, the radius may be 50 cm, or it may be 100 cm. stomach.

[0286] Selectively, in possible embodiments of the present application ,eye The cleaning device is driven and operated in standard operating mode. runi In that case, A step of determining at least one of the following, which represents the target operating mode: the rotation speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions. The step of driving a cleaning device and operating a cleaning function with at least one of the following: rotational speed of the dust collection motor, travel interval, cleaning area, and number of cleaning repetitions, wherein the travel interval is used to reflect the distance between two adjacent travel routes of the cleaning device.

[0287] Furthermore, this invention is used to represent the cleaning function of an operating mode by adjusting the width of adjacent cleaning paths of the cleaning device, the number of cleaning cycles for adjacent cleaning paths, and the rotation speed of the motor (one or more of these) in accordance with the current level of soiling in the cleaning area.

[0288] For example, the more the current area is determined to be dirty, the faster the dust collection motor's rotation speed is increased. And / or, the more the current area is determined to be dirty, the narrower the width of the adjacent cleaning path is determined to be, the wider the overlapping area of ​​the paths becomes, and the better the cleaning effect. And / or, the more the current area is determined to be dirty, the more the adjacent paths can be cleaned repeatedly multiple times, further improving the cleaning effect.

[0289] Specifically, in this application, if the dust collection volume of the dust box is detected to be greater than a predetermined dust volume threshold, the current cleaning area of ​​the cleaning device is recognized as a dirty area. Furthermore, it is necessary to drive the cleaning device and operate it in a target operating mode with high cleaning intensity and a large cleaning area. If the dust collection volume of the dust box is detected to be less than a predetermined dust volume threshold, the current cleaning area of ​​the cleaning device is recognized as a non-dirty area. Furthermore, it is necessary to drive the cleaning device and operate it in a target operating mode with medium-low cleaning intensity and a small cleaning area.

[0290] For example, when it is detected that the amount of collected dust is greater than a predetermined dust amount threshold 1, it can be determined that the cleaning device will be controlled to operate in a target mode of the cleaning function with a first cleaning intensity and a first cleaning area.

[0291] When it is detected that the amount of collected dust is not greater than a predetermined dust amount threshold 1 but not less than a predetermined dust amount threshold 2, it can be determined that the cleaning device should be controlled to operate the target operating mode of the cleaning function with a second cleaning intensity and a second cleaning area. When it is detected that the amount of collected dust is not greater than a predetermined dust amount threshold 3, it can be determined that the cleaning device should be controlled to operate the target operating mode of the cleaning function with a third cleaning intensity and a third cleaning area.

[0292] What can be understood here is that the predetermined dust amount threshold 1 is greater than the predetermined dust amount threshold 2, and the predetermined dust amount threshold 2 is greater than the predetermined dust amount threshold 3. The specific numerical values ​​can be set according to the actual situation, and this application is not limited thereto.

[0293] The steps of selectively driving the cleaning device and operating the cleaning function at travel intervals are: Once the initial interval between two adjacent travel routes of the current cleaning device is determined, The initial interval is adjusted to a target interval with a smaller distance, The procedure specifically includes the step of driving a cleaning device and operating the cleaning function such that the distance between two adjacent travel routes is a target interval.

[0294] Figure 16 shows the initial interval between two adjacent travel routes of the cleaning device in the initial operating mode. It can be seen that it follows a normal curved travel pattern. Furthermore, the initial interval between each pair of adjacent travel routes is large. This is why the cleaning device's cleaning of The overlapping area becomes smaller, and as a result, the cleaning intensity is not high.

[0295] To address the above problem, as shown in Figure 17, the present invention allows the initial interval to be adjusted to a target interval with a small distance, thereby reducing the initial interval between each of two adjacent travel routes when the cleaning device travels in a bow-shaped pattern. Furthermore, it achieves the objective of increasing the overlapping area of ​​cleaning and strengthening the cleaning intensity.

[0296] Selectively, in possible embodiments of the present application, in step 033, 0333, The step of detecting that the amount of dust collected is greater than a predetermined dust amount threshold and activating the imaging device of the cleaning device, 0334, further includes the step of using a camera to collect area images in the direction of travel of the cleaning device.

[0297] Based on the recognition results of the area image and the relationship between the amount of dust collected and the predetermined dust amount threshold, the target operating mode of the cleaning device is determined.

[0298] Furthermore, in order to determine a target operating mode that better matches the soiled area, the present invention may also use a camera to collect area images in the direction of travel of the cleaning device, and then use the recognition results of the area images to supplement and determine the target operating mode of the cleaning device.

[0299] What can be understood is that by recognizing the area image, the type of object waiting to be cleaned (e.g., dust or oil stains) present in the area where the cleaning device is currently located can be determined. Based on this, different target operating modes with different cleaning intensity and cleaning area can be selected depending on the type of object waiting to be cleaned.

[0300] Selectively, after using a camera to collect area images in the direction of travel of the cleaning device, Using a predetermined image detection model, the area object features in the area image are recognized, and the area object features include at least one of size features, color features, and contour features. A step of determining the recognition result of an area image based on area characteristics, further comprising the step of using the recognition result to reflect the objects awaiting cleaning that are present in the area where the cleaning device is currently located.

[0301] Specifically, this invention allows a robot to capture images of an area in the forward direction of travel using an image acquisition device installed on the robot, obtain an area image, and input that area into a pre-generated image detection model to determine the object features present in the area image. Subsequently, from a predetermined set of object features, it selects an object waiting to be cleaned that matches the object features.

[0302] Here, this application does not specifically limit the image detection model. For example, it could be a Convolutional Neural Network (CNN). A Convolutional Neural Network is a type of Feedforward Neural Network that includes computation and has a deep structure, and is one of the representative algorithms of deep learning. Convolutional Neural Networks have the capability of representation learning and can classify input information in a way that is invariant to translation according to their hierarchical structure. Thanks to the powerful feature representation ability of CNNs (Convolutional Neural Networks) for images, remarkable results have been obtained in fields such as image classification, target detection, and semantic segmentation.

[0303] Furthermore, the present invention uses a CNN neural network model to fetch feature information of objects awaiting cleaning (i.e., area object features) present in the area image, and identifies the object awaiting cleaning to which it belongs by identifying features in the area image (for example, size features, color features, contour features, texture features, etc., corresponding to the object awaiting cleaning).

[0304] Specifically, in the embodiment of the present invention, the area image is input to a predetermined convolutional neural network model, and the output of the fully connected layer (FC), which is the final layer of the convolutional neural network model, can be used as the identification result of feature data corresponding to the area object features of the area image.

[0305] Selectively, in possible embodiments of the present application, in step 032, 0321, the procedure includes the step of monitoring the amount of dust collected at the dust box inlet over a predetermined period, or the step of monitoring the change in the weight of the dust box over a predetermined period.

[0306] First, this application does not specifically limit the prescribed period; for example, it could be one minute or thirty seconds. Specifically, the cleaning device determines the severity of the dirt by observing whether the weight of the dust box continues to increase over a certain period, with a larger increase indicating more severe soiling.

[0307] As one example, as shown in Figure 18, there is a schematic diagram of the process for operating the cleaning method of the cleaning device submitted in this application, where, The steps include monitoring the amount of dust collected in the dust box of the cleaning device, determining a target operating mode for the cleaning device based on the relationship between the amount of dust collected and a predetermined dust threshold, wherein the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device, and driving the operation of the cleaning device in the target operating mode.

[0308] Here, by applying the technical means of the present invention, the cleaning intensity and cleaning area of ​​the cleaning device can be adjusted in accordance with the amount of dust collected in the dust box of the cleaning device detected. This makes it possible to operate the robot with high-intensity cleaning in dirty areas and with low-intensity cleaning in normal areas. Furthermore, it is possible to guarantee the cleaning effect in dirty areas and avoid the problem of inefficient cleaning in specific areas that occurs when cleaning is always performed with the same cleaning intensity and area, which is present in related technologies.

[0309] Figure 19 shows a schematic block diagram of a cleaning device in an embodiment of the present invention, and the cleaning device 1000 is, The position planning module 1002 was used to determine the target cleaning area. A trajectory planning module 1003 used to generate a cleaning trajectory within the target cleaning area in response to a route planning command. It includes a first cleaning module 1004 used to perform a cleaning operation along the aforementioned cleaning trajectory.

[0310] In some embodiments, the position planning module 1002 is used to determine the target cleaning area of ​​the cleaning device if, after activating the cleaning device, it recognizes that the cleaning device is activated in a non-charging position.

[0311] In this embodiment, the cleaning device is activated in a non-charged position when the user moves the cleaning device to a certain position and activates it manually, at which point the cleaning device enters localized cleaning mode.

[0312] Specifically, after activating the cleaning device, the position planning module 1002 first recognizes whether the activation position of the cleaning device is a non-charging position. More precisely, after the cleaning device enters an activated state, the position recognition component in the cleaning device is also activated accordingly. The position recognition component can detect whether the cleaning device is in a charging position, and the position planning module 1002 can determine whether the activation position of the cleaning device is a non-charging position based on the recognition result of the position recognition component.

[0313] Furthermore, if the position planning module 1002 determines that the cleaning device will be activated in a non-charging position, that is, if the cleaning device is moved to a certain location and activated manually, the position planning module 1002 needs to determine the target cleaning area that the cleaning device needs to clean. but be.

[0314] Specifically, if the position planning module 1002 determines that the cleaning device is activated in a non-charging position, it indicates that the cleaning device is in localized cleaning mode. At this point, the user's cleaning intention can be determined to clean a certain area. Therefore, the position planning module 1002 needs to determine the target cleaning area and, in subsequent steps, accurately clean according to the user's cleaning intention.

[0315] Specifically, the cleaning device is equipped with a detection component used to detect conditions near the location where the cleaning device is situated. The cleaning device stores a semantic map of all scenes, and the location planning module 1002 can analyze the user's cleaning intentions based on the detection results of the detection component and / or the semantic map. Furthermore, the module determines the target cleaning area of ​​the cleaning device based on the user's cleaning intentions.

[0316] In this embodiment, the position planning module 1002 first determines whether the cleaning device is in a state where it is activated in a non-charging position, and if the cleaning device is in a state where it is activated in a non-charging position, it determines the user's desired cleaning area (i.e., the target cleaning area). In this embodiment of the present invention, when the position planning module 1002 determines that the cleaning device is in a state where it is activated in a non-charging position, it can automatically analyze the user's cleaning intention and determine the user's desired cleaning area.

[0317] In the above embodiment, the position planning module 1002 is used to recognize whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and if a first cleaning target exists, to determine the area where the first cleaning target is located as the target cleaning area.

[0318] In this embodiment, the predetermined distance refers to the distance that the sensing component of the cleaning device can recognize, and may be a custom distance. It is understood that the custom distance must be within the range that the sensing component of the cleaning device can recognize, and the first cleaning target is cleaning Difficult It refers to dirt or grime.

[0319] Specifically, the process of determining the target cleaning area of ​​the cleaning device involves the position planning module 1002 first recognizing whether a first cleaning target exists in an area at a predetermined distance from the cleaning device. More specifically, the cleaning device is equipped with a detection component which can be used to detect conditions near the location of the cleaning device. The position planning module 1002 can recognize conditions near the location of the cleaning device using this detection component, that is, it recognizes whether the first cleaning target exists near the cleaning device.

[0320] For example, the above detection component may be, but is not limited to, one type of AI (image) recognition device, camera, or video camera.

[0321] Furthermore, when the position planning module 1002 determines that a first cleaning target exists within an area at a predetermined distance from the cleaning device, the position planning module 1002 determines the area where the first cleaning target is located as the user's desired cleaning area, that is, determines the area where the first cleaning target is located as the target cleaning area.

[0322] Specifically, when the position planning module 1002 recognizes that a first cleaning target exists within an area at a predetermined distance from the cleaning device, the user's cleaning intention is to clean the first cleaning target. At this time, the position planning module 1002 determines the area where the first cleaning target is located as the target cleaning area. In the subsequent steps, the cleaning device controls only the cleaning device and cleans the area where the first cleaning target is located, so that the cleaning area of ​​the cleaning device better matches the user's requirements.

[0323] In this embodiment, when the position planning module 1002 recognizes that a first cleaning target exists within an area at a predetermined distance from the cleaning device, it determines the area where the first cleaning target is located as the target cleaning area, that is, it determines the area where the first cleaning target is located as the user's desired cleaning area.

[0324] In the above embodiment, the cleaning device 1000 of the cleaning device includes an acquisition module, which is used to acquire semantic maps of all scenes constructed by the cleaning device, and the position planning module 1002 is used to determine the target cleaning area using the semantic map.

[0325] In this embodiment, the semantic map refers to the semantic map of all scenes constructed after the cleaning device has performed cleaning on all scenes, where "all scenes" refers to the scenes of all rooms in the user's house. Specifically, the semantic map includes the type of room and the location and type of items such as home appliances and furniture.

[0326] Specifically, the process for determining the target cleaning area of ​​the cleaning device involves first acquiring the semantic map constructed by the cleaning device after it has cleaned all scenes using the acquisition module. More precisely, after the cleaning device has cleaned all rooms in the user's house for the first time, it constructs a semantic map of all scenes in the user's house. After each subsequent cleaning, it updates this semantic map according to the actual situation and stores the updated semantic map in the cleaning device's memory unit. The acquisition module can acquire this semantic map from the memory unit. Furthermore, the acquisition module acquires the updated semantic map after the most recent cleaning, and in the subsequent steps, the position planning module 1002 ensures the accuracy of the target cleaning area determined by this semantic map.

[0327] Furthermore, the location planning module 1002 determines the target cleaning area using the semantic map, that is, it determines the area the user wants to clean using the semantic map. Specifically, the semantic map determines the room type of the location where the cleaning device is currently located, and the cleaning device but The system can determine whether furniture or appliances are present at the current location, analyze the user's cleaning intentions based on that information, and determine the user's desired cleaning area based on those intentions. Therefore, the location planning module 1002 can determine the target cleaning area using the semantic map described above.

[0328] In this embodiment, when it is determined that the cleaning device is in a state where it is activated in a non-charging position, that is, when the cleaning device activates local cleaning mode, the acquisition module can acquire the semantic map constructed by the cleaning device, and the position planning module 1002 uses the semantic map to determine the cleaning device butBy analyzing the situation near the current location, i.e., analyzing the user's cleaning intention, determining the target cleaning area based on the user's intention, and ensuring in subsequent steps that the area cleaned by the cleaning device is the area the user wants to clean, the cleaning area of ​​the cleaning device will better match the user's requirements, improving the cleaning efficiency of the cleaning device and increasing user satisfaction.

[0329] In the above embodiment, the location planning module 1002 is used to determine a room of a predetermined type as the target cleaning area when the cleaning device is determined to be in a room of a predetermined type by the semantic map.

[0330] In this embodiment, the above-mentioned predetermined type of room refers to a room that is difficult to clean or easily gets dirty, such as a toilet or kitchen.

[0331] Specifically, the process of determining the target cleaning area using a semantic map involves the location planning module 1002 first analyzing whether the room type at the current location of the cleaning device is a predetermined room type using the semantic map.

[0332] Furthermore, if the location planning module 1002 determines that the room type at the current location of the cleaning device is a predetermined room type, the location planning module 1002 determines that room as the user's desired cleaning area, that is, determines that room as the target cleaning area.

[0333] Specifically, when the location planning module 1002 analyzes the semantic map described above to determine that the room type at the current location of the cleaning device is a predetermined room type, it indicates that the user's cleaning intention is to clean a room of the predetermined type. At this point, the cleaning device determines the room of the predetermined type (i.e., the room at the current location of the cleaning device) as the target cleaning area.

[0334] In this embodiment, if the location planning module 1002 analyzes that the current location of the cleaning device is a predetermined type of room using the semantic map, it determines that predetermined type of room as the user's desired cleaning area, that is, it determines that predetermined type of room as the target cleaning area.

[0335] In the above embodiment, if the location planning module 1002 determines, based on the semantic map, that a cleaning device is not present in a room of a predetermined type and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, it further determines the area where the second cleaning target is located as the target cleaning area.

[0336] In this embodiment, the second cleaning target refers to household appliances or furniture in the user's room that are likely to interrupt the cleaning process of the cleaning device, such as a bed, tea table, and washing machine.

[0337] Specifically, the process of determining the target cleaning area using a semantic map involves the position planning module 1002 analyzing whether the second cleaning target exists within an area at a predetermined distance from the cleaning device if the semantic map determines that the room type at the cleaning device's current location is not a predetermined room type. In other words, the semantic map clearly identifies the second cleaning target, eliminating the need for the position planning module 1002 to call the cleaning device's detection component to detect the situation near the cleaning device. The semantic map can then determine whether the second cleaning target exists within an area at a predetermined distance from the cleaning device.

[0338] Furthermore, when the position planning module 1002 analyzes that a second cleaning target exists within an area at a predetermined distance from the cleaning device using the semantic map, the position planning module 1002 determines the area where the second cleaning target is located as the user's desired cleaning area, that is, determines the area where the second cleaning target is located as the target cleaning area.

[0339] Specifically, if the position planning module 1002 analyzes using the semantic map that the room type at the current location of the cleaning device is not a predetermined room type, and that a second cleaning target exists within a predetermined distance from the cleaning device, then the user's cleaning intention is to clean the area where the second cleaning target is located. At this point, the cleaning device determines the area where the second cleaning target is located as the target cleaning area. In the subsequent step, the first cleaning module 1004 controls only the cleaning device and performs cleaning in the area where the second cleaning target is located, so that the cleaning area of ​​the cleaning device better matches the user's requirements.

[0340] In this embodiment, if the position planning module 1002 analyzes using the semantic map that the current location of the cleaning device is not a predetermined type of room and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, it determines the area where the second cleaning target is located as the user's desired cleaning area, that is, it determines the area where the second cleaning target is located as the target cleaning area. Then, in the subsequent steps, the first cleaning module 1004 controls only the cleaning device and cleans the area where the second cleaning target is located, so that the cleaning area of ​​the cleaning device is more in line with the user's requirements, the cleaning efficiency of the cleaning device is improved, and user satisfaction is increased.

[0341] In the above embodiment, if the location planning module 1002 determines, based on the semantic map, that the cleaning device is not present in a room of a predetermined type and that there is no second cleaning target within an area at a predetermined distance from the cleaning device, it further determines the area at a predetermined distance from the cleaning device as the target cleaning area.

[0342] In this embodiment, the process of determining the target cleaning area using a semantic map involves the position planning module 1002 first analyzing whether the room type at the current location of the cleaning device is a predetermined room type, and whether a second cleaning target exists within an area at a predetermined distance from the cleaning device, using the semantic map.

[0343] Specifically, if the location planning module 1002 analyzes, based on the semantic map, that the room type at the current location of the cleaning device is not a predetermined room type, and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, the location planning module 1002 determines the area at a predetermined distance from the cleaning device as the user's desired cleaning area, that is, determines the area at a predetermined distance from the cleaning device as the target cleaning area.

[0344] Specifically, if the position planning module 1002 analyzes using the semantic map that the room type at the current location of the cleaning device is not a predetermined room type, and that there is no second cleaning target within a predetermined distance from the cleaning device, then the user's cleaning intention is to clean the area at a predetermined distance from the cleaning device. At this point, the cleaning device determines the area at a predetermined distance from the cleaning device as the target cleaning area. In the subsequent step, the first cleaning module 1004 controls only the cleaning device and cleans the area at a predetermined distance from the cleaning device, thereby making the cleaning area of ​​the cleaning device more in line with the user's requirements.

[0345] In this embodiment, if the position planning module 1002 analyzes using the semantic map that the current location of the cleaning device is not a predetermined type of room and that there is no second cleaning target within a predetermined distance from the cleaning device, it determines the area within a predetermined distance from the cleaning device as the user's desired cleaning area, that is, it determines the area within a predetermined distance from the cleaning device as the target cleaning area. Then, in the subsequent step, the first cleaning module 1004 controls only the cleaning device and cleans the area within a predetermined distance from the cleaning device, thereby making the cleaning area of ​​the cleaning device more in line with the user's requirements, improving the cleaning efficiency of the cleaning device, and increasing user satisfaction.

[0346] In the above embodiment, the position planning module 1002 further confirms that it recognizes whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and if the first cleaning target does not exist, it determines the target cleaning area using a semantic map.

[0347] In this embodiment, before determining the target cleaning area using the semantic map, the location planning module 1002 also needs to recognize whether a first cleaning target exists in an area at a predetermined distance from the cleaning device. Specifically, the cleaning device may be equipped with a detection component that can be used to detect conditions near the location of the cleaning device, and the location planning module 1002 can recognize conditions near the location of the cleaning device using this detection component, that is, it recognizes whether the first cleaning target exists near the cleaning device.

[0348] Furthermore, when the position planning module 1002 determines that the first cleaning target does not exist within an area at a predetermined distance from the cleaning device, the position planning module 1002 determines that it can perform the step of determining the target cleaning area using the semantic map.

[0349] Specifically, when the location planning module 1002 recognizes that the first cleaning target does not exist within an area at a predetermined distance from the cleaning device, the user's cleaning intention is not to clean dirt or trash near the cleaning device. At this time, the location planning module 1002 can perform steps such as analyzing the user's specific cleaning intention using the semantic map to determine whether to clean a predetermined type of room, clean near the second cleaning target, or clean an area near the cleaning device.

[0350] In this embodiment, the position planning module 1002 also needs to take the step of recognizing whether the first target cleaning area exists within an area at a predetermined distance from the cleaning device, before determining the target cleaning area of ​​the cleaning device using the semantic map. This allows for a more accurate determination of the user's cleaning intentions, and by determining a more accurate target cleaning area, the cleaning area of ​​the cleaning device better matches the user's requirements, improving the cleaning efficiency of the cleaning device and enhancing the user experience.

[0351] In this embodiment, the first cleaning module 1004 cleans along the edges and then moves in a curved shape. to By controlling the cleaning device using a cleaning method, cleaning is performed on the target cleaning area, thereby ensuring the cleanliness of the target cleaning area, achieving the required cleaning effect, and improving user satisfaction.

[0352] In the above embodiment, the first cleaning module 1004 is further used to provide a voice prompt indicating the cleaning method of the cleaning device for the target cleaning area.

[0353] In this embodiment, before controlling the cleaning device and cleaning the target cleaning area, the first cleaning module 1004 needs to play voice prompts to inform the user of how the first cleaning module 1004 will control the cleaning device and clean the target cleaning area.

[0354] Specifically, before the cleaning device cleans the target cleaning area, the first cleaning module 1004 plays voice prompts so that the user can understand the area to be cleaned. For example, if the area to be cleaned by the cleaning device is the area where the tea table is located, the first cleaning module 1004 plays voice prompts such as "I will soon be cleaning under the tea table," allowing the user to confirm whether the area to be cleaned by the cleaning device is the area the user wants to have cleaned.

[0355] In this embodiment, before controlling the cleaning device to clean the target cleaning area, the first cleaning module 1004 plays voice prompt information for the area to be cleaned. This allows the user to determine whether the area to be cleaned by the cleaning device is the area the user wishes to clean, and if the area for which the voice prompt information is played is not the area the user wishes to clean, the cleaning device can adjust the cleaning area in a timely manner.

[0356] Based on a similar technical concept, the trajectory planning module 1003 of the cleaning device in this embodiment of the present invention is In response to a route planning command, the current clean state of the mop and the start and end points corresponding to the route planning command are determined, This is used to determine the cleaning trajectory from the starting point to the ending point, based on the geographical conditions map, the cleaning status map, and the cleanliness status.

[0357] In a possible embodiment, trajectory planning module 1003 、 in particular, This is used to determine the current cleanliness of the mop if the current cleaning stage of the cleaning device is the departure stage after self-cleaning at the water station, and to determine the current cleanliness of the mop if the current cleaning stage of the cleaning device is the stage of moving from the area where cleaning is currently completed to the area awaiting cleaning, or the stage of returning to the water station to wash the mop.

[0358] In a possible embodiment, trajectory planning module 1003 、 in particular, The aforementioned geographical map is used to identify areas without obstacles, and the aforementioned areas without obstacles and the cleaning status map are used to determine a cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness.

[0359] In a possible embodiment, the step of determining the cleaning trajectory from the starting point to the ending point according to a predetermined traffic strategy corresponding to the clean state, based on the area without obstacles and the cleaning status map, The method includes the steps of: determining all currently cleaned areas from the cleaning status map based on the cleanliness status; determining all areas between the starting point and the ending point that are free of obstacles and have been cleaned, based on the areas without obstacles and the areas that have been cleaned; determining that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0360] In a possible embodiment, the step of determining the cleaning trajectory from the starting point to the ending point according to a predetermined traffic strategy corresponding to the clean state, based on the area without obstacles and the cleaning status map, The method includes the steps of determining all areas awaiting cleaning from the cleaning status map, given that the clean state is dirty; determining all areas awaiting cleaning without obstacles between the starting point and the ending point, based on the areas without obstacles and all areas awaiting cleaning; determining that at least one continuous movement trajectory can be formed between the starting point, all areas awaiting cleaning without obstacles, and the ending point; and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

[0361] In a possible embodiment, the trajectory planning module 1003 is It is further used to determine that it is not possible to construct the aforementioned continuous movement trajectory, and to determine the cleaning trajectory from the starting point to the ending point using the area without obstacles.

[0362] In a possible embodiment, the cleaning device is The system further includes a division module used to divide a target cleaning area into multiple areas and determine the cleaning order of each area before responding to a route planning command.

[0363] In possible embodiments, the divided module, specifically, The current cleaning stage of the cleaning device and the cleaning sequence of each area are used to determine the start and end points corresponding to the route planning command.

[0364] Referring to Figure 20, the cleaning device in the embodiment of the present invention is A second cleaning module 1005 is used to mark obstacles within a target cleaning area, avoid obstacles within the target cleaning area, and perform cleaning operations. A dynamic detection module 1006 is used to detect the state of obstacles within a target cleaning area and to identify obstacles whose state has changed. The system further includes a third cleaning module 1007 used to perform a cleaning operation at the location of an obstacle whose state has changed.

[0365] The cleaning device of the embodiment of the present invention allows the position planning module to be cleaned. 1002 First, the target cleaning area requiring cleaning is determined, and the second cleaning module 1005 can perform cleaning operations within the target cleaning area, while simultaneously avoiding and marking obstacles. The dynamic detection module 1006 can detect movable obstacles within the target cleaning area, and when there are movable objects in the scene, situations where a user has carried an object, or situations where a door has been opened or closed, the third cleaning module 1007 is used to move the executing entity to the location of the obstacle whose state has changed and to perform cleaning operations, thereby avoiding missed cleaning spots due to object movement and improving the coverage rate of automatic cleaning in dynamic scenes.

[0366] What can be understood is that in the second cleaning module 1005, the step of marking obstacles within the target cleaning area is, This includes a step of marking the location, type, and shape of obstacles within the target cleaning area.

[0367] Furthermore, in order to realize the cleaning device of the embodiment of the present invention, the cleaning device must be equipped with at least an RGB camera, a laser lidar, a high-performance GPU, an AI chip, and memory. For example, high-resolution cameras are installed at 90-degree intervals at the edge positions of the cleaning device and used to capture the visual scene in real time. A high-performance GPU is installed inside the cleaning device and used to fetch features from the visual scene images captured in real time and for image recognition. An AI chip is installed inside the high-performance GPU and an objective recognition algorithm is integrated into the chip. Memory is installed inside the cleaning device and used to store a map of the target cleaning area and a set of obstacles.

[0368] GPUs can enable obstacle state management, AI recognition, and navigation planning functions.

[0369] Specifically, RGB cameras can recognize low obstacles such as socks and power lines, while laser lidars can recognize taller obstacles such as furniture and trash cans.

[0370] What can be understood is that in the dynamic detection module 1006, the step of detecting the state of obstacles within the target cleaning area and identifying the obstacles whose state has changed is: A step of detecting the location and shape of obstacles within the target cleaning area, The process includes the step of determining an obstacle whose state has changed based on an obstacle whose position or shape has changed.

[0371] What can be understood is that the cleaning operation includes a first cleaning operation and a second cleaning operation, where the first cleaning trajectory determined by performing the first cleaning operation is a closed loop, and the second cleaning trajectory determined by performing the second cleaning operation is a closed loop. Traverse and check It is used for the purpose of [doing something].

[0372] What I can understand is the location planning module. 1002 The step of determining the target cleaning area is: The process includes the steps of performing a first cleaning operation and determining a target cleaning area based on the cleaning trajectory of the first cleaning operation.

[0373] What can be understood is that in the third cleaning module 1007, the step of avoiding obstacles and performing a cleaning operation within the target cleaning area is: The steps include performing a second cleaning operation within the target cleaning area, The system includes the steps of: performing a first cleaning action when it is determined that an obstacle has been encountered, and continuing to perform a second cleaning action after avoiding the obstacle.

[0374] In another embodiment of this application, as shown in Figure 21 , the The cleaning module 1004 is, A unit 10041 that monitors the amount of dust collected in the dust box of the cleaning device is set to monitor the amount of dust collected, Based on the relationship between the amount of dust collected and a predetermined dust amount threshold, the target operating mode of the cleaning device is determined, and here, the target operating mode is determined by a unit 10042 which determines an operating mode used to change the cleaning intensity and cleaning area of ​​the cleaning device. The system further includes a drive unit 10043 which is set to drive and operate the cleaning device in the target operating mode.

[0375] In this application, the amount of dust collected in the dust box of the cleaning device is monitored, and the target operating mode of the cleaning device is determined based on the relationship between the amount of dust collected and a predetermined dust amount threshold. Here, the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device, and the operation of the cleaning device is driven in the target operating mode. By applying the technical means of this application, the cleaning intensity and cleaning area of ​​the cleaning device can be adjusted in accordance with the detected amount of dust collected in the dust box of the cleaning device. This makes it possible to operate the robot with high-intensity cleaning in dirty areas and with low-intensity cleaning in normal areas. Furthermore, it is possible to guarantee the cleaning effect on dirty areas and avoid the problem of low cleaning efficiency in specific areas that occurs when cleaning is always performed with the same cleaning intensity and cleaning area, which exists in related technologies.

[0376] In another embodiment of this application, the unit 10042 for determining the operating mode is: The system detects that the amount of dust collected is greater than the predetermined dust amount threshold, and determines that it will control the cleaning device to operate the target operating mode of the cleaning function at a first cleaning intensity and a first cleaning area, or The system detects that the amount of dust collected is not greater than the predetermined dust amount threshold, and determines that it will control the cleaning device to operate the target operating mode of the cleaning function with a second cleaning intensity and a second cleaning area, where the second cleaning intensity is lower than the first cleaning intensity and the second cleaning area is smaller than the first cleaning area.

[0377] In another embodiment of this application, the unit 10042 for determining the operating mode is: The amount of dust collected is determined to be greater than the predetermined dust amount threshold, and the location of the cleaning device is recorded. The system is configured to mark an area within a predetermined range from the aforementioned location as a high-cleaning area, and to control the cleaning device to operate the cleaning function within the high-cleaning area with a first cleaning intensity and a first cleaning area.

[0378] In another embodiment of this application, the unit 10042 for determining the operating mode is: Determine at least one of the following: the rotation speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions, which represent the aforementioned target operating mode. The step of driving the cleaning device and operating the cleaning function with at least one of the following: the rotation speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions, wherein the travel interval is used to reflect the distance between two adjacent travel routes of the cleaning device.

[0379] In another embodiment of this application, the unit 10042 for determining the operating mode is: To determine the initial interval between two adjacent travel routes of the current cleaning device, Adjusting the initial interval to a target interval smaller than the initial interval, The cleaning device is driven and the cleaning function is operated such that the distance between two adjacent travel routes is the target interval.

[0380] In another embodiment of this application, the unit 10042 for determining the operating mode is: The system detects that the amount of dust collected is greater than the predetermined dust amount threshold, and activates the imaging device of the cleaning device. Using the aforementioned imaging device, area images are collected in the direction of travel of the cleaning device. Based on the recognition results of the area image and the relationship between the amount of dust collected and a predetermined dust threshold, the target operating mode of the cleaning device is determined and set.

[0381] In another embodiment of this application, the unit 10042 for determining the operating mode is: Using a predetermined image detection model, the area object features in the area image are recognized, and the area object features include at least one of the following: size features, color features, and contour features. Based on the area object features, the recognition result of the area image is determined, wherein the recognition result is used to reflect the objects awaiting cleaning in the area where the cleaning device is currently located.

[0382] In another embodiment of this application, the dust collection unit 10041 monitors the amount of dust collected. The system is configured to monitor the amount of dust collected at the dust box inlet during a predetermined period, or to monitor the change in the weight of the dust box during a predetermined period.

[0383] Figure 22 is a block diagram of the logic structure of a cleaning device as shown in an exemplary embodiment. For example, the cleaning device 1100 may be a cleaning device equipped with a drying function, such as a dryer or washing machine.

[0384] The cleaning device includes a memory 1102 for storing a program or command, and a processor 1104 that executes the program or command stored in the memory 1102 to realize the steps of the cleaning method to which the above embodiment of the present invention is presented. Therefore, it has all the beneficial technical effects of the cleaning method to which the above embodiment of the present invention is presented, and a detailed explanation is omitted here.

[0385] The present invention provides a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, the above embodiment of the present invention realizes the cleaning method to which the present invention is provided. Therefore, the readable storage medium has all the beneficial technical effects of the cleaning method to which the above embodiment of the present invention is provided, and a detailed explanation is omitted here.

[0386] Optionally, the above instructions are executed by the processor of the cleaning device to complete other steps relating to the above exemplary embodiment. For example, the non-temporary computing device readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Claims

1. A cleaning method used in a cleaning device, Steps to determine the target cleaning area, The steps include generating a cleaning trajectory within the target cleaning area in response to a route planning command, The step includes performing a cleaning operation along the aforementioned cleaning trajectory, The step to determine the target cleaning area is: A cleaning method characterized by including the step of determining the target cleaning area of ​​the cleaning device if, after activating the cleaning device, it is recognized that the cleaning device was activated in a non-charging position.

2. The step of determining the target cleaning area of ​​the cleaning device is: The cleaning method according to claim 1, characterized in that it includes the step of recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and if the first cleaning target exists, determining the area where the first cleaning target is located as the target cleaning area.

3. The step of determining the target cleaning area of ​​the cleaning device is: The steps include obtaining a semantic map of all scenes constructed by the cleaning device, The cleaning method according to claim 1, characterized by comprising the step of determining the target cleaning area using the semantic map.

4. The step of determining the target cleaning area using the semantic map is as follows: The cleaning method according to claim 3, characterized in that, if the semantic map determines that the cleaning device is in a room of a predetermined type, the method includes the step of determining the room of a predetermined type as the target cleaning area.

5. The step of determining the target cleaning area using the semantic map is as follows: The cleaning method according to claim 3, characterized in that, if the semantic map determines that the cleaning device is not present in a room of a predetermined type and that a second cleaning target exists within an area at a predetermined distance from the cleaning device, the method includes the step of determining the area where the second cleaning target is located as the target cleaning area.

6. The step of determining the target cleaning area using the semantic map is as follows: The cleaning method according to claim 3, characterized in that, if the semantic map determines that the cleaning device is not present in a room of a predetermined type and that there is no second cleaning target within an area at a predetermined distance from the cleaning device, the method includes the step of determining the area at a predetermined distance from the cleaning device as the target cleaning area.

7. Before determining the target cleaning area using the aforementioned semantic map, The cleaning method according to claim 3, further comprising the step of recognizing whether a first cleaning target exists within an area at a predetermined distance from the cleaning device, and confirming that if the first cleaning target does not exist, the step of determining the target cleaning area using the semantic map is performed.

8. The step of performing a cleaning operation along the aforementioned cleaning trajectory is: The cleaning method according to any one of claims 1 to 7, characterized in that it includes the step of cleaning the target cleaning area using a cleaning method that involves cleaning along the edges and then cleaning in a curved shape, and after completion, returning to the charging position and performing charging.

9. Before performing the cleaning operation along the aforementioned cleaning trajectory, The cleaning method according to any one of claims 1 to 7, further comprising the step of verbally instructing the cleaning device on the cleaning method for the target cleaning area.

10. The cleaning method according to claim 2 or 7, characterized in that the first cleaning target includes one of the following: dirt, small granular debris, and hair-like debris.

11. The cleaning method according to claim 5 or 6, characterized in that the second cleaning target is a home appliance or furniture.

12. The step of generating a cleaning trajectory within the target cleaning area in response to a route planning command is: The steps include: determining the current clean state of the mop and the start and end points corresponding to the route planning command in response to the route planning command; The cleaning method according to claim 1, characterized by comprising the step of determining the cleaning trajectory from the starting point to the ending point based on a geographical map, a cleaning status map, and the cleanliness status.

13. The steps to determine the current cleanliness of the mop are: If the current cleaning stage of the cleaning device is the starting stage after self-cleaning in the water station, the steps include confirming that the current clean state of the mop is clean, The cleaning method according to claim 12, characterized in that, if the current cleaning stage of the cleaning device is the stage of moving from an area where cleaning has been completed to an area awaiting cleaning, or the stage of returning to a water station to wash the mop, the current clean state of the mop is determined to be dirty.

14. The step of determining the cleaning trajectory from the starting point to the ending point based on the geographical conditions map, the cleaning status map, and the cleanliness status is as follows: The steps include determining areas free of obstacles using the aforementioned geographical map, The cleaning method according to claim 12, comprising the step of determining a cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the clean state, based on the area without obstacles and the cleaning status map.

15. The step of determining the cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness state, based on the area without obstacles and the cleaning status map, is as follows: Based on the cleanliness status, the steps include determining the areas that have been cleaned so far from the cleaning status map, A step of determining all areas between the starting point and the ending point that are free of obstacles and have been cleaned, based on the areas without obstacles and the areas that have already been cleaned. The cleaning method according to claim 14, characterized by comprising the step of determining that at least one continuous movement trajectory can be formed between the starting point, all areas that are free of obstacles and have been cleaned, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

16. The step of determining the cleaning trajectory from the starting point to the ending point in accordance with a predetermined traffic strategy corresponding to the cleanliness state, based on the area without obstacles and the cleaning status map, is as follows: Based on the clean state being dirty, the step of determining all areas awaiting cleaning from the cleaning status map, Based on the areas without obstacles and all areas awaiting cleaning, the steps include determining all areas between the starting point and the ending point that are free of obstacles and awaiting cleaning, The cleaning method according to claim 14, characterized by comprising the steps of determining that at least one continuous movement trajectory can be formed between the starting point, all areas free of obstacles and awaiting cleaning, and the ending point, and determining the shortest movement trajectory among the at least one movement trajectory as the cleaning trajectory from the starting point to the ending point.

17. The aforementioned cleaning method is The cleaning method according to claim 15 or 16, further comprising the step of determining that the continuous movement trajectory cannot be constructed and determining a cleaning trajectory from the starting point to the ending point based on the area free of obstacles.

18. Before responding to a route planning command, The cleaning method according to any one of claims 12 to 16, further comprising the step of dividing the target cleaning area into a plurality of areas and determining the cleaning order for each area.

19. The step of determining the start and end points corresponding to the aforementioned route planning command is: The cleaning method according to claim 18, further comprising the step of determining the start and end points corresponding to the route planning command based on the current cleaning stage of the cleaning device and the cleaning sequence of each area.

20. The aforementioned cleaning method is The steps include marking obstacles within the target cleaning area, avoiding the obstacles within the target cleaning area, and performing a cleaning operation. The steps include detecting the state of obstacles within the target cleaning area and identifying the obstacles whose state has changed, The cleaning method according to claim 1, further comprising the step of performing a cleaning operation at the location of the obstacle whose state has changed.

21. The step of marking obstacles within the target cleaning area is: The cleaning method according to claim 20, comprising the step of marking the location, type and shape of obstacles within the target cleaning area, wherein the type includes dynamic obstacles.

22. The step of detecting the state of obstacles within the target cleaning area and identifying obstacles whose state has changed is as follows: A step of detecting the position and shape of the dynamic obstacle within the target cleaning area, The cleaning method according to claim 21, further comprising the step of determining a dynamic obstacle whose state has changed based on a dynamic obstacle whose position or shape has changed.

23. The cleaning method according to any one of claims 20 to 22, wherein the cleaning operation includes a first cleaning operation and a second cleaning operation, wherein the first cleaning trajectory determined by performing the first cleaning operation is a closed loop, and the second cleaning trajectory determined by performing the second cleaning operation can fill the target cleaning area.

24. The step to determine the target cleaning area is: The cleaning method according to claim 23, further comprising the steps of performing the first cleaning operation and determining the target cleaning area based on the cleaning trajectory of the first cleaning operation.

25. The step of avoiding the obstacles and performing the cleaning operation within the target cleaning area is: The steps include: performing a second cleaning operation within the aforementioned target cleaning area; The cleaning method according to claim 23, characterized in that it includes the step of performing a first cleaning operation when it is determined that the aforementioned obstacle has been encountered, and continuing to perform a second cleaning operation after avoiding the aforementioned obstacle.

26. The step of performing a cleaning operation along the aforementioned cleaning trajectory is: A step of monitoring the amount of dust collected in the dust box of the cleaning device, A step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold, wherein the target operating mode is used to change the cleaning intensity and cleaning area of ​​the cleaning device. The cleaning method according to claim 1, characterized by comprising the step of performing the cleaning operation by driving and operating the cleaning device in the target operating mode.

27. The step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold is as follows: The steps include detecting that the amount of dust collected is greater than the predetermined dust amount threshold, and determining that the cleaning device will be controlled to operate the target operating mode of the cleaning function with a first cleaning intensity and a first cleaning area, or The cleaning method according to claim 26, comprising the step of detecting that the amount of dust collected is not greater than the predetermined dust amount threshold, and determining that the cleaning device is controlled to operate the target operating mode of the cleaning function with a second cleaning intensity and a second cleaning area, wherein the second cleaning intensity is lower than the first cleaning intensity, and the second cleaning area is smaller than the first cleaning area.

28. The step of detecting that the amount of dust collected is greater than the predetermined dust amount threshold and determining that the cleaning device will be controlled to operate the target operating mode of the cleaning function with a first cleaning intensity and a first cleaning area is: The steps include determining that the amount of dust collected is greater than the predetermined dust amount threshold, and recording the location of the cleaning device, The cleaning method according to claim 27, further comprising the steps of marking an area within a predetermined range from the aforementioned location as a high-cleaning area, and controlling the cleaning device to operate the cleaning function in the high-cleaning area with a first cleaning intensity and a first cleaning area.

29. The step of driving and operating the cleaning device in the target operating mode is: The steps include determining at least one of the following: the rotation speed of the dust collection motor, the travel interval, the cleaning area, and the number of cleaning repetitions, which represent the target operating mode; The cleaning method according to 26 or 27, comprising the step of driving the cleaning device and operating the cleaning function with at least one of the rotational speed of the dust collection motor, travel interval, cleaning area, and number of cleaning repetitions, wherein the travel interval is used to reflect the distance between two adjacent travel routes of the cleaning device.

30. The step of driving the cleaning device and operating the cleaning function at the travel interval is: The steps include determining the initial interval between two adjacent travel routes of the current cleaning device, The steps include adjusting the initial interval to a target interval where the distance is smaller than the initial interval, The cleaning method according to claim 29, characterized by comprising the step of driving the cleaning device and operating the cleaning function so that the distance between two adjacent travel routes becomes the target interval.

31. The step of determining the target operating mode of the cleaning device based on the relationship between the amount of dust collected and a predetermined dust amount threshold is as follows: The step of detecting that the amount of dust collected is greater than the predetermined dust amount threshold and activating the imaging device of the cleaning device, The steps include: using the aforementioned imaging device to collect area images in the direction of travel of the cleaning device; The cleaning method according to claim 26, comprising the step of determining a target operating mode for the cleaning device based on the recognition result of the area image and the relationship between the amount of dust collected and a predetermined dust amount threshold.

32. After the step of collecting area images in the direction of travel of the cleaning device using the aforementioned imaging device, A step of using a predetermined image detection model to recognize an area object feature in the area image, which includes at least one of size features, color features, and contour features; The cleaning method according to claim 31, further comprising the step of determining the recognition result of the area image based on the area object features, wherein the recognition result is used to reflect the objects awaiting cleaning that are present in the area where the cleaning device is currently located.

33. The step of monitoring the amount of dust collected in the dust box of the cleaning device is: The cleaning method according to claim 26, characterized by including the step of monitoring the amount of dust collected at the inlet of the dust box during a predetermined period, or the step of monitoring the weight change of the dust box during a predetermined period.

34. A location planning module used to determine the target cleaning area, A trajectory planning module used to generate a cleaning trajectory within the target cleaning area in response to a route planning command, A cleaning module used to perform a cleaning operation along the aforementioned cleaning trajectory, Determining the target cleaning area is A cleaning device characterized by including the step of determining the target cleaning area of ​​the cleaning device if, after activating the cleaning device, it is recognized that the cleaning device was activated in a non-charged position.

35. A cleaning device comprising memory, a processor, and a computer program stored in memory and executable by the processor, wherein when the processor executes the program, the cleaning method described in any one of claims 1 to 7 is realized.

36. A computer-readable storage medium characterized in that a computer program is stored on it, and when the computer program is executed by a processor, the cleaning method described in any one of claims 1 to 7 is realized.

Images