Obstacle avoidance control method and apparatus for automatic cleaning device, and storage medium and device

Abstract

Provided are an obstacle avoidance control method and apparatus for an automatic cleaning device, and a storage medium and a device. The method comprises: acquiring operating data of at least one cleaning assembly that is collected during an operating process of an automatic cleaning device (101); on the basis of the operating data of the cleaning assembly, determining a current operating face material corresponding to the current position of the automatic cleaning device (102); and according to an obstacle avoidance strategy corresponding to the current operating face material, performing obstacle avoidance control on the automatic cleaning device (103). In an operating process of the automatic cleaning device, the operating data of the cleaning assembly is utilized to identify the current operating face material corresponding to the automatic cleaning device, so as to realize adaptive obstacle avoidance strategy selection for different operating face materials, thereby reducing the phenomena of misidentification and missing identification of obstacles by the automatic cleaning device, and helping to improve the cleaning efficiency and the cleaning quality of the automatic cleaning device.

Description

Obstacle avoidance control method and device, storage medium, and device for automatic cleaning equipment

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on August 11, 2023, with application number 202311016505.2 and application name “Obstacle avoidance control method and device, storage medium, and equipment for automatic cleaning equipment”, the entire contents of which are incorporated by reference into the application. Technical Field

[0002] The present application relates to the technical field of sweeping robots, and in particular to an obstacle avoidance control method and device, storage medium, and equipment for automatic cleaning equipment. Background Art

[0003] As people's living standards continue to improve, robot vacuums are becoming an increasingly important tool for household cleaning. However, existing robot vacuums typically use sensors such as lasers or infrared to detect their working surface and determine whether they need to avoid obstacles. However, relying solely on these sensors can sometimes lead to malfunctions or misjudgments, causing the robot vacuum to collide with obstacles or fail to complete a clean.

[0004] Contents of this application

[0005] In view of this, the present application provides an obstacle avoidance control method and device, storage medium, and equipment for automatic cleaning equipment, which can adaptively select obstacle avoidance strategies for different work surface materials, reduce the occurrence of misidentification and missed identification of obstacles by automatic cleaning equipment, and help improve the cleaning efficiency and cleaning quality of automatic cleaning equipment.

[0006] According to one aspect of the present application, there is provided an obstacle avoidance control method for an automatic cleaning device, the method comprising:

[0007] Acquiring operating data of at least one cleaning component collected during operation of the automatic cleaning device;

[0008] Determining a current working surface material corresponding to a current position of the automatic cleaning device based on the working data of the cleaning component;

[0009] Obstacle avoidance control is performed on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0010] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component includes:

[0011] In the preset current intervals corresponding to different working surface materials, the preset current interval into which the driving current data of the cleaning component falls is determined as the hit current interval, and the current working surface material is determined based on the working surface material corresponding to the hit current interval.

[0012] Optionally, the working surface material includes: a first fabric material and a second fabric material, wherein a first height value of fabric fibers in the first fabric material protruding from the working surface is greater than a second height value of fabric fibers in the second fabric material protruding from the working surface.

[0013] Optionally, the obstacle avoidance strategy includes an obstacle avoidance reference parameter type, the obstacle avoidance reference parameter type of the first fabric material does not include a preset sensor data type, the obstacle avoidance reference data type of the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

[0014] Optionally, determining the current working surface material based on the working surface material corresponding to the interval includes:

[0015] Counting the target intervals with the largest number among the first number of hit current intervals identified continuously;

[0016] The current working surface material is determined based on the working surface material corresponding to the target interval.

[0017] Optionally, determining the current working surface material based on the working surface material corresponding to the hit current interval includes:

[0018] Determining a currently identified material corresponding to the current position based on the working surface material corresponding to the hit current interval, and determining a historical working surface material corresponding to the current position based on historical cleaning data of the automatic cleaning device;

[0019] If the historical working surface material is consistent with the current working surface material, the currently identified material is determined as the current working surface material;

[0020] If the historical working surface material is inconsistent with the current working surface material, the material identification strategy setting data of the automatic cleaning device is obtained, and the current working surface material is determined according to the material identification strategy setting data, the current identification material and the historical working surface material.

[0021] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component includes:

[0022] Inputting the driving current data of the cleaning component into a pre-trained material classification model to construct current characteristic data of the driving current data of the cleaning component through the material classification model, and performing material prediction on the current characteristic data to obtain the current working surface material corresponding to the current position of the automatic cleaning device;

[0023] The current characteristic data of the driving current data of the cleaning component is constructed by using the currently input driving current data of the cleaning component and the driving current data of the third number of cleaning components input before the currently input driving current data of the cleaning component.

[0024] Optionally, after obtaining the current working surface material corresponding to the current position of the automatic cleaning device, the method further includes:

[0025] Displaying the working surface material identification information corresponding to the automatic cleaning device, wherein the working surface material identification information includes the working surface materials identified by the automatic cleaning device at different positions;

[0026] In response to a working surface material correction instruction at any target position in the working surface material identification information, correcting the working surface material at the target position;

[0027] In the historical cleaning data of the automatic cleaning device, the historical cleaning component current corresponding to the target position is obtained, and based on the historical cleaning component current and the corrected working surface material, the material classification model is updated and trained.

[0028] Optionally, before determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component, the method further includes:

[0029] detecting whether the automatic cleaning device enters the fabric material area;

[0030] When it is detected that the automatic cleaning device enters the fabric material area, the step of determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component is performed.

[0031] Optionally, the method further includes:

[0032] When it is detected that the automatic cleaning device enters a fabric material area, generating a predicted fabric area corresponding to the current position based on the current position of the automatic cleaning device and historical driving current data of the cleaning component corresponding to the current position;

[0033] Planning a cleaning path of the automatic cleaning device within the predicted fabric area.

[0034] Optionally, the detecting whether the automatic cleaning device enters a fabric material area includes:

[0035] Acquire visual data collected during the operation of automatic cleaning equipment;

[0036] Performing fabric fiber data analysis on the visual data to determine whether the automatic cleaning device has entered a fabric material area, wherein the fabric fiber data includes the length and / or density of fabric fibers.

[0037] Optionally, the working data of the cleaning component includes cleaning component pressure data; and determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component includes:

[0038] In the preset pressure intervals corresponding to different working surface materials, the preset pressure interval where the cleaning component pressure data is located is determined as the hit pressure interval, and the current working surface material is determined based on the working surface material corresponding to the hit pressure interval.

[0039] According to another aspect of the present application, an obstacle avoidance control device for an automatic cleaning device is provided, the device comprising:

[0040] A data acquisition module, configured to acquire operating data of at least one cleaning component collected during operation of the automatic cleaning device;

[0041] a material recognition module for determining a current working surface material corresponding to a current position of the automatic cleaning device based on working data of the cleaning component;

[0042] The obstacle avoidance control module is used to perform obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0043] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and the material identification module is further configured to:

[0044] In the preset current intervals corresponding to different working surface materials, the preset current interval into which the driving current data of the cleaning component falls is determined as the hit current interval, and the current working surface material is determined based on the working surface material corresponding to the hit current interval.

[0045] Optionally, the working surface material includes: a first fabric material and a second fabric material, wherein a first height value of fabric fibers in the first fabric material protruding from the working surface is greater than a second height value of fabric fibers in the second fabric material protruding from the working surface.

[0046] Optionally, the obstacle avoidance strategy includes an obstacle avoidance reference parameter type, the obstacle avoidance reference parameter type of the first fabric material does not include a preset sensor data type, the obstacle avoidance reference data type of the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

[0047] Optionally, the material identification module is further configured to:

[0048] Counting the target intervals with the largest number among the first number of hit current intervals identified continuously;

[0049] The current working surface material is determined based on the working surface material corresponding to the target interval.

[0050] Optionally, the material identification module is further configured to:

[0051] Determining a currently identified material corresponding to the current position based on the working surface material corresponding to the hit current interval, and determining a historical working surface material corresponding to the current position based on historical cleaning data of the automatic cleaning device;

[0052] If the historical working surface material is consistent with the current working surface material, the currently identified material is determined as the current working surface material;

[0053] If the historical working surface material is inconsistent with the current working surface material, the material identification strategy setting data of the automatic cleaning device is obtained, and the current working surface material is determined according to the material identification strategy setting data, the current identification material and the historical working surface material.

[0054] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and the material identification module is further configured to:

[0055] Inputting the driving current data of the cleaning component into a pre-trained material classification model to construct current characteristic data of the driving current data of the cleaning component through the material classification model, and performing material prediction on the current characteristic data to obtain the current working surface material corresponding to the current position of the automatic cleaning device;

[0056] The current characteristic data of the driving current data of the cleaning component is constructed by using the currently input driving current data of the cleaning component and the driving current data of the third number of cleaning components input before the currently input driving current data of the cleaning component.

[0057] Optionally, the material identification module is further configured to:

[0058] Displaying the working surface material identification information corresponding to the automatic cleaning device, wherein the working surface material identification information includes the working surface materials identified by the automatic cleaning device at different positions;

[0059] In response to a working surface material correction instruction at any target position in the working surface material identification information, correcting the working surface material at the target position;

[0060] In the historical cleaning data of the automatic cleaning device, the historical cleaning component current corresponding to the target position is obtained, and based on the historical cleaning component current and the corrected working surface material, the material classification model is updated and trained.

[0061] Optionally, the material identification module is further configured to:

[0062] detecting whether the automatic cleaning device enters the fabric material area;

[0063] When it is detected that the automatic cleaning device enters the fabric material area, the step of determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component is performed.

[0064] Optionally, the device further includes a path planning module, configured to:

[0065] When it is detected that the automatic cleaning device enters a fabric material area, generating a predicted fabric area corresponding to the current position based on the current position of the automatic cleaning device and historical driving current data of the cleaning component corresponding to the current position;

[0066] Planning a cleaning path of the automatic cleaning device within the predicted fabric area.

[0067] Optionally, the data acquisition module is further used to obtain visual data collected during the operation of the automatic cleaning device;

[0068] The material recognition module is also used to: obtain visual data collected during the operation of the automatic cleaning device; perform fabric fiber data analysis on the visual data to determine whether the automatic cleaning device has entered the fabric material area, wherein the fabric fiber data includes the length and / or density of the fabric fibers.

[0069] Optionally, the working data of the cleaning component includes pressure data of the cleaning component; and the material identification module is further configured to:

[0070] In the preset pressure intervals corresponding to different working surface materials, the preset pressure interval where the cleaning component pressure data is located is determined as the hit pressure interval, and the current working surface material is determined based on the working surface material corresponding to the hit pressure interval.

[0071] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the obstacle avoidance control method of the automatic cleaning device is implemented.

[0072] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the obstacle avoidance control method for the automatic cleaning device when executing the program.

[0073] Through the above-mentioned technical solution, the obstacle avoidance control method and device, storage medium, and equipment for automatic cleaning equipment provided in this application, compared with the existing method of indiscriminate obstacle avoidance control when the automatic cleaning equipment works on working surfaces of different materials, sets corresponding obstacle avoidance strategies for adaptability to different working surface materials. Therefore, during the operation of the automatic cleaning equipment, the working data of the cleaning component is used to identify the current working surface material corresponding to the automatic cleaning equipment, so that obstacle avoidance control can be performed according to the obstacle avoidance strategy that is adapted to the current working surface material, so as to realize adaptive obstacle avoidance strategy selection for different working surface materials, reduce the occurrence of misidentification and missed identification of obstacles by the automatic cleaning equipment, help improve the cleaning efficiency and cleaning quality of the automatic cleaning equipment, improve the user experience, and enhance product competitiveness.

[0074] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0076] FIG1 is a schematic flow chart showing an obstacle avoidance control method for an automatic cleaning device provided in an embodiment of the present application;

[0077] FIG2 is a flow chart showing another obstacle avoidance control method for an automatic cleaning device provided in an embodiment of the present application;

[0078] FIG3 is a flow chart showing another obstacle avoidance control method for an automatic cleaning device provided in an embodiment of the present application;

[0079] FIG4 shows a schematic structural diagram of an obstacle avoidance control device for an automatic cleaning device provided in an embodiment of the present application;

[0080] FIG5 shows a schematic diagram of the device structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0081] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0082] In this embodiment, an obstacle avoidance control method for an automatic cleaning device is provided, as shown in FIG1 , the method comprising:

[0083] Step 101: Acquire operating data of at least one cleaning component collected during the operation of the automatic cleaning device.

[0084] The automatic cleaning device in the embodiment of the present application can be a sweeping robot. During operation, the automatic cleaning device will continuously collect working data of the cleaning components through its own various sensors, and then use the collected working data of the cleaning components to identify the material of the current position of the automatic cleaning device, and select an obstacle avoidance strategy based on the material of the working surface currently being cleaned, so that the automatic cleaning device can automatically select the obstacle avoidance strategy suitable for the working surface currently being cleaned, reduce the occurrence of the automatic cleaning device missing or misjudging obstacles, and thus improve cleaning efficiency and accuracy.

[0085] Step 102: Determine the material of the current working surface corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component.

[0086] In this embodiment, the working data of the cleaning component may include the driving current data of the cleaning component, the pressure data of the cleaning component, etc. The cleaning component may specifically include a roller brush (main brush), a side brush, and a mopping module. Specifically, the working data of one type of cleaning component may be selected for working surface material identification, or the working data of multiple types of cleaning components may be combined for working surface material identification. When combining the working data of multiple types of cleaning components for material identification, when the material identification results corresponding to the working data of different types of cleaning components are consistent, the current working surface material can be directly determined, and when the material identification results corresponding to the working data of different types of cleaning components are inconsistent, different results can be scored to obtain the final material identification result, for example, scoring different material identification results based on preset scoring weights, or determining the scoring weights of the working data of different types of cleaning components based on the user's evaluation of historical working surface material identification results. In specific application scenarios, a current detection sensor can be installed on the main brush motor circuit to collect the working current of the main brush motor. For example, the sensor can be set at the reverse connection of the main brush motor circuit. A pressure sensor can also be set on the bristles of the main brush to collect the contact pressure of the main brush on the cleaning work surface. Visual data can also be collected through a camera or laser sensor on the automatic cleaning equipment, so as to use computer vision technology to determine the material of the working surface.

[0087] In an embodiment of the present application, the problem that an automatic cleaning device is difficult to adapt to different types of fabrics in setting obstacle avoidance strategies is taken as an example. Optionally, when the working data of the cleaning component includes driving current data of the cleaning component, step 102 includes: determining, within the preset current intervals corresponding to different working surface materials, the preset current interval into which the driving current data of the cleaning component falls as a hit current interval, and determining the current working surface material based on the working surface material corresponding to the hit current interval; wherein the working surface materials include: a first fabric material and a second fabric material, wherein a first height value of the fabric fibers protruding from the working surface in the first fabric material is greater than a second height value of the fabric fibers protruding from the working surface in the second fabric material. The obstacle avoidance strategy includes an obstacle avoidance reference parameter type, the obstacle avoidance reference parameter type of the first fabric material does not include a preset sensor data type, the obstacle avoidance reference data type of the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

[0088] In this embodiment, using carpet as an example, driving current data of the cleaning component of the automatic cleaning device operating on different types of carpet is collected and analyzed in advance. Preset current ranges for the main brush current corresponding to different types of carpet are set. The preset current ranges corresponding to different types of carpet are then used to distinguish the material type of the working surface of the automatic cleaning device. Specifically, carpets can be divided into long-pile and short-pile types based on the fiber length cutoff value. It should be noted that during operation of the automatic cleaning device, the power of the main brush motor adaptively changes with the friction between the main brush and the working surface, allowing the main brush of the automatic cleaning device to maintain a certain rotational speed. As the friction between the main brush and the working surface increases, the main brush motor drives the main brush with greater power. Therefore, changes in the main brush current indirectly reflect changes in the friction between the main brush and the working surface. Different types of carpets also generate different degrees of friction with the main brush. The embodiment of the present application utilizes this characteristic to determine the material of the working surface by collecting driving current data of the cleaning component. In a specific application scenario, the driving current data of the cleaning component collected when the automatic cleaning device is working on a long-haired carpet (first fabric material) and the driving current data of the cleaning component collected when working on a short-haired carpet (second fabric material) can be collected in advance, and the two can be analyzed to establish the current intervals of the main brush current corresponding to the long-haired carpet and the short-haired carpet, that is, the preset current intervals. During the operation of the automatic cleaning device, the driving current data of the cleaning component is collected in real time, and the preset current interval in which the driving current data of the cleaning component is located is determined, so that the type of carpet on the working surface currently being cleaned by the automatic cleaning device can be determined. For example, if the driving current data of the cleaning component belongs to the preset current interval corresponding to the long-haired carpet, then it can be determined that the automatic cleaning device is currently cleaning the long-haired carpet.

[0089] Optionally, when the working data of the cleaning component includes cleaning component pressure data; step 102 includes: in the preset pressure intervals corresponding to different working surface materials, determining the preset pressure interval in which the cleaning component pressure data is located as the hit pressure interval, and determining the current working surface material based on the working surface material corresponding to the hit pressure interval.

[0090] In this embodiment, similar to the principle of detecting the working surface material through the driving current data of the cleaning component mentioned above, when the automatic cleaning device moves on different types of carpets, the contact pressure between the main brush and the carpet is also different. For example, the contact pressure of short-hair carpets is greater than that of long-hair carpets. In specific application scenarios, it is also possible to pre-collect the cleaning component pressure data collected when the automatic cleaning device is working on long-hair carpets and the cleaning component pressure data collected when the automatic cleaning device is working on short-hair carpets, and analyze the two to establish the pressure range of the main brush contact pressure corresponding to long-hair carpets and short-hair carpets, respectively, that is, the preset pressure range. During the operation of the automatic cleaning device, the cleaning component pressure data is collected in real time, and the preset pressure range in which the cleaning component pressure data is located is determined, so that the type of carpet on the working surface currently being cleaned by the automatic cleaning device can be determined. For example, if the cleaning component pressure data belongs to the preset pressure range corresponding to short-hair carpets, then it can be determined that the automatic cleaning device is currently cleaning short-hair carpets.

[0091] Optionally, when the working data of the cleaning component includes visual data; step 102 also includes: analyzing the fabric fiber data corresponding to the current position of the automatic cleaning device based on the visual data to determine the fabric type of the current working surface, wherein the fabric fiber data includes the length and / or density of the fabric fibers.

[0092] In this embodiment, visual data collection devices such as cameras and laser sensors installed on the automatic cleaning device can also be used to collect visual data when the automatic cleaning device is operating on long-pile carpets and short-pile carpets. The visual data collected can be used to analyze the fiber length and density of the long-pile and short-pile carpets, thereby summarizing the characteristics of the fiber length and density of the long-pile and short-pile carpets. During the operation of the automatic cleaning device, visual data is collected in real time and feature analysis is performed on the visual data to determine the type of carpet on the surface currently being cleaned by the automatic cleaning device.

[0093] Furthermore, to avoid similar cleaning component drive current data characteristics, cleaning component pressure data characteristics, and main brush visual data characteristics between other working surface materials and carpet materials, an existing material detection algorithm can be used during the operation of the automatic cleaning device to detect the material of the working surface on which the automatic cleaning device is located. Upon detecting that the automatic cleaning device has entered a fabric material area, the aforementioned method is executed to distinguish between long-hair and short-hair carpets, thereby improving recognition accuracy. Optionally, the method further includes: detecting whether the automatic cleaning device has entered a fabric material area; and upon detecting that the automatic cleaning device has entered a fabric material area, executing step 102 above.

[0094] Step 103 : performing obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0095] Finally, after identifying the current working surface material of the automatic cleaning device, the obstacle avoidance strategy corresponding to the current working surface material is found from among the pre-set obstacle avoidance strategies for different materials, and the automatic cleaning device is then controlled to avoid obstacles according to this obstacle avoidance strategy. This allows for adaptive obstacle avoidance strategy selection for different working surface materials, reducing the occurrence of misidentification and missed obstacle recognition by the automatic cleaning device. For example, if the robot detects that the current carpet is long-pile, it will determine that the resistance state is high. If the sensor data from the sensor (e.g., a line laser sensor) whose sensing range includes the portion above the fibers of the short-pile carpet is still used for obstacle avoidance, it may easily lead to misidentification of obstacles and missed detection. Therefore, these sensors are pre-set as default sensors, and their data is ignored and not used as a basis for subsequent obstacle avoidance. If the robot detects that the current carpet is short-pile, it will determine that the resistance state is low, and the aforementioned sensor data is retained normally, thus achieving a strategy that can properly avoid obstacles even on short-pile carpets.

[0096] By applying the technical solution of this embodiment, during the operation of the automatic cleaning device, the working data of the cleaning component collected by the automatic cleaning device is used to identify the current working surface material of the automatic cleaning device at its current position, so that the automatic cleaning device is controlled to avoid obstacles according to the obstacle avoidance strategy corresponding to the current working surface material. Compared with the prior art method in which the automatic cleaning device performs indiscriminate obstacle avoidance control when working on working surfaces of different materials, the present application adaptively sets corresponding obstacle avoidance strategies for different working surface materials, so that during the operation of the automatic cleaning device, the working data of the cleaning component is used to identify the current working surface material corresponding to the automatic cleaning device, so that obstacle avoidance control is performed according to the obstacle avoidance strategy adapted to the current working surface material, so as to realize the selection of adaptive obstacle avoidance strategies for different working surface materials, reduce the occurrence of misidentification and missed identification of obstacles by the automatic cleaning device, help improve the cleaning efficiency and cleaning quality of the automatic cleaning device, improve the user experience, and enhance product competitiveness.

[0097] Furthermore, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another obstacle avoidance control method for an automatic cleaning device is provided, as shown in FIG2 , the method includes:

[0098] Step 201: Acquire driving current data of a cleaning component collected during operation of the automatic cleaning device.

[0099] Step 202: Within the preset current intervals corresponding to different working surface materials, the preset current interval within which the driving current data of the cleaning component falls is taken as a hit current interval, and the current working surface material is determined based on the working surface material corresponding to the hit current interval; wherein the working surface materials include: a first fabric material and a second fabric material, wherein a first height value of the fabric fibers protruding from the working surface in the first fabric material is greater than a second height value of the fabric fibers protruding from the working surface in the second fabric material. The obstacle avoidance strategy includes an obstacle avoidance reference parameter type, wherein the obstacle avoidance reference parameter type for the first fabric material does not include a preset sensor data type, and the obstacle avoidance reference data type for the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

[0100] In an embodiment of the present application, during operation, the automatic cleaning device can continuously collect driving current data of the cleaning component through a current detection sensor arranged at the main brush motor circuit, and map the driving current data of the cleaning component collected each time to a preset current interval corresponding to different working surface materials, and determine the preset current interval into which the driving current data of the cleaning component collected each time falls, that is, the hit current interval where the driving current data of the cleaning component is located.

[0101] Among them, the working surface material of the preset current range is pre-set to include at least a first fabric material (such as a long-haired carpet) and a second fabric material (such as a short-haired carpet). Since the fabric fibers of long-haired carpets are long, the obstructions detected by the line laser sensor may be fabric fibers. If the automatic cleaning device avoids the fabric fibers when cleaning, it may cause missed cleaning. Therefore, the obstacle avoidance strategy for long-haired carpets can be set to not use the data collected by the line laser sensor as a reference parameter for obstacle avoidance. That is, the obstacle avoidance strategy for long-haired carpets is to ignore the data collected by the line laser sensor and not use the data collected by the line laser sensor as the basis for subsequent obstacle avoidance, while the obstacle avoidance strategy for short-haired carpets is to retain the data collected by the line laser sensor and use the data collected by the line laser sensor as the basis for subsequent obstacle avoidance.

[0102] Furthermore, more fabric types can be set based on the fiber length of the fabric, such as long-pile, medium-long-pile, medium-pile, medium-short-pile, and short-pile. When setting corresponding obstacle avoidance strategies for different carpet types, long-pile carpets can be set to completely ignore line laser sensor data, medium-long-pile, medium-pile, and medium-short-pile carpets can be set to ignore a portion of the line laser sensor data at their respective heights, and short-pile carpets can be set to completely use line laser sensor data. This embodiment of the application only uses the example of dividing carpets into long-pile and short-pile categories for explanation.

[0103] Step 203 : Count the target intervals with the largest number among the first number of hit current intervals identified continuously.

[0104] Step 204: Determine the current working surface material based on the working surface material corresponding to the target interval.

[0105] If the number of the target intervals is greater than or equal to the second number, the working surface material corresponding to the target interval is determined as the current working surface material.

[0106] In this embodiment, since using the driving current data of the cleaning component detected once to determine the carpet type may result in inaccurate identification due to interference, jitter, and other factors, the driving current data of the cleaning component collected several times can be combined for determination. Specifically, based on the current driving current data of the cleaning component and the driving current data of multiple cleaning components collected previously, totaling a first amount of data, the target interval that appears most frequently among the main brush current intervals corresponding to these driving current data of the cleaning components is counted, and the working surface material corresponding to the target interval is determined as the current working surface material corresponding to the current position.

[0107] The real-time identified working surface material can also be further corrected in combination with historical cleaning data. Optionally, step 202 includes: determining the currently identified material corresponding to the current position based on the working surface material corresponding to the hit current interval, and determining the historical working surface material corresponding to the current position based on the historical cleaning data of the automatic cleaning device; if the historical working surface material is consistent with the current working surface material, determining the currently identified material as the current working surface material; if the historical working surface material is inconsistent with the current working surface material, obtaining the material identification strategy setting data of the automatic cleaning device, and determining the current working surface material based on the material identification strategy setting data, the currently identified material, and the historical working surface material.

[0108] Among them, the working surface material corresponding to the hit current interval determined in real time can be used as the current identification material, and then the historical working surface material of the current position can be determined based on the historical cleaning data. If the two are consistent in confirming that the current identification material is accurate, it can be directly used as the current working surface material for obstacle avoidance. If the two are inconsistent, then according to the material identification strategy set by the user or automatically matched, the current identification material and the historical working surface material are combined to determine the final current working surface material. For example, if the material identification strategy is to give priority to historical materials, then the historical working surface material is used as the current working surface material, and the identified material is continuously monitored within a specific period of time to see if it is still inconsistent with the corresponding historical working surface material. If it is still inconsistent within a specific period of time, the current working surface material corresponding to the automatic cleaning equipment is determined as the real-time identified material.

[0109] Optionally, the following solution can be implemented after step 203: determine whether the number of occurrences of the target interval has reached a second number, for example, whether more than 7 of the driving current data of the cleaning component collected 10 times fall into the preset current interval of the same material. If so, then the working surface material corresponding to the target interval with the largest number of occurrences can be determined as the current working surface material corresponding to the automatic cleaning device. If the number of the target intervals is less than the second number, then based on the historical cleaning data of the automatic cleaning device, the historical working surface material corresponding to the current position is determined, and when the target interval is consistent with the preset current interval corresponding to the historical working surface material, the working surface material corresponding to the target interval is determined as the current working surface material.

[0110] In this embodiment, in order to reduce the inaccurate recognition phenomenon caused by the unstable main brush current due to external interference, the current working surface material can be further judged in combination with historical data. Specifically, if the target interval that appears the most times in the first number of main brush current intervals continuously identified above does not reach the second number, it is possible to further find out what material the current position identified by the automatic cleaning device in the previous cleaning process is, in the historical cleaning records of the automatic cleaning device, that is, to determine the historical working surface material, and thus judge whether the target interval is consistent with the preset current interval corresponding to the historical working surface material. If they are consistent, it can also be considered that the working surface material corresponding to the target interval is the current working surface material. This allows the automatic cleaning device to have an anti-shake effect on the judgment of the carpet material, thereby improving the stability of the judgment.

[0111] Step 205 : performing obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0112] In this embodiment, if the current working surface is determined to be a long-pile carpet, the data collected by the line laser sensor is ignored during the subsequent obstacle avoidance control process. However, if the current working surface is determined to be a short-pile carpet, the data collected by the line laser sensor is used for reference during the subsequent obstacle avoidance control process. This allows the robot vacuum to effectively distinguish between long-pile and short-pile carpets by detecting the main brush current and make appropriate obstacle avoidance decisions, thereby improving the robot vacuum's cleaning efficiency and adaptability.

[0113] In the embodiment of the present application, the material classification model can be pre-trained to predict the material of the working surface, and the model can be continuously iterated and optimized during the operation of the automatic cleaning device to gradually improve the recognition accuracy. As shown in Figure 3, the method includes:

[0114] Step 301: Acquire driving current data of a cleaning component collected during operation of the automatic cleaning device.

[0115] In step 302, the driving current data of the cleaning component is input into a pre-trained material classification model to construct current characteristic data of the driving current data of the cleaning component through the material classification model, and perform material prediction on the current characteristic data to obtain the current working surface material corresponding to the current position of the automatic cleaning device; wherein, the current characteristic data of the driving current data of the cleaning component is constructed using the driving current data of the currently input cleaning component and the driving current data of a third number of cleaning components input before the currently input driving current data of the cleaning component.

[0116] Step 303: performing obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0117] In this embodiment, a material classification model is pre-trained based on driving current data samples of cleaning components of different working surface materials. The driving current data samples of the cleaning components can specifically be driving current data of the cleaning components collected in advance when the automatic cleaning device is working on a long-haired carpet, and driving current data of the cleaning components collected when working on a short-haired carpet. Each driving current data sample of the cleaning component includes the third number of continuously collected driving current data of the cleaning component and the corresponding long-haired carpet label or short-haired carpet label. During the operation of the automatic cleaning device, the driving current data of the cleaning component is collected in real time, and the driving current data of the cleaning component is input into the material classification model. The material classification model first constructs corresponding current characteristic data (or fills it with a zero vector) based on the currently input driving current data of the cleaning component and the third number of driving current data of the cleaning component that were continuously input before, and then predicts the current characteristic data to determine the current working surface material, thereby performing obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy of the current working surface material.

[0118] Step 304 : Displaying the working surface material identification information corresponding to the automatic cleaning device, wherein the working surface material identification information includes the working surface materials identified by the automatic cleaning device at different positions.

[0119] Step 305 : In response to the working surface material correction instruction at any target position in the working surface material identification information, correct the working surface material at the target position.

[0120] Step 306 : Obtain the historical cleaning component current corresponding to the target position from the historical cleaning data of the automatic cleaning device, and update and train the material classification model based on the historical cleaning component current and the corrected working surface material.

[0121] In this embodiment, during or after the operation of the automatic cleaning device, the user can view the working surface material identification information identified by the automatic cleaning device through an application associated with the automatic cleaning device. Specifically, it can be a cleaning area map with each working surface material area marked on the map. After the user views the working surface material identification information through the application, the user can correct the displayed working surface material identification information. Furthermore, based on the corrected working surface material and the historical driving current data of the cleaning component at the corresponding position, a new sample can be constructed, and the new sample can be used to update and train the model to improve the accuracy of the model.

[0122] It should be noted that the embodiments shown in Figures 2 and 3 can also be applied to the situation where the pressure data of the cleaning component is used to realize the working surface material recognition and obstacle avoidance strategy selection of the automatic cleaning equipment. The specific scheme is similar to the above-mentioned scheme implemented using the driving current data of the cleaning component, and will not be repeated here.

[0123] In an embodiment of the present application, optionally, it also includes: when it is detected that the automatic cleaning device enters a fabric material area, generating a fabric prediction area corresponding to the current position based on the current position of the automatic cleaning device and the historical driving current data of the cleaning component corresponding to the current position; and planning the cleaning path of the automatic cleaning device within the fabric prediction area.

[0124] In this embodiment, when it is detected that the automatic cleaning device enters the fabric material area, the historical cleaning data of the automatic cleaning device can be called to find the historical driving current data of the cleaning component that matches the current position of the automatic cleaning device in the historical cleaning data. For example, the driving current data of the cleaning components collected by the automatic cleaning device during the historical cleaning process can be used to construct a material map or a current map in advance, wherein the material map is a map constructed by the automatic cleaning device during the previous cleaning process based on the identified materials of each area, and the current map is a map constructed by the automatic cleaning device during the previous cleaning process based on the driving current data of the cleaning components collected at different positions. Therefore, when it is detected that the automatic cleaning device enters the fabric material area, the carpet area entered by the automatic cleaning device can be obtained in the material map based on the current position of the automatic cleaning device, or the historical driving current data of the cleaning components that are within a certain range from the current position and whose difference with the driving current data of the cleaning components currently collected is within a certain range can be obtained based on the current position of the automatic cleaning device, and the carpet area can be drawn using the historical driving current data of this part of the cleaning components. Finally, the carpet area determined based on the current position and the historical driving current data of its corresponding cleaning component will be used as the above-mentioned fabric prediction area. When the automatic cleaning device is subsequently planning the cleaning path, the fabric prediction area will be used as a reference to plan a more accurate cleaning path, so that the automatic cleaning device can prioritize cleaning the fabric prediction area before entering other material areas, avoiding the need to frequently adjust the obstacle avoidance strategy after repeatedly entering and exiting the carpet area, thereby improving the cleaning efficiency and cleaning quality of the sweeping robot and enhancing the user experience.

[0125] Furthermore, as a specific implementation of the method of FIG1 , an embodiment of the present application provides an obstacle avoidance control device for an automatic cleaning device, as shown in FIG4 , the device comprising:

[0126] A data acquisition module, configured to acquire operating data of at least one cleaning component collected during operation of the automatic cleaning device;

[0127] a material recognition module for determining a current working surface material corresponding to a current position of the automatic cleaning device based on working data of the cleaning component;

[0128] The obstacle avoidance control module is used to perform obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

[0129] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and the material identification module is further configured to:

[0130] In the preset current intervals corresponding to different working surface materials, the preset current interval into which the driving current data of the cleaning component falls is determined as the hit current interval, and the current working surface material is determined based on the working surface material corresponding to the hit current interval.

[0131] Optionally, the working surface material includes: a first fabric material and a second fabric material, wherein a first height value of fabric fibers in the first fabric material protruding from the working surface is greater than a second height value of fabric fibers in the second fabric material protruding from the working surface.

[0132] Optionally, the obstacle avoidance strategy includes an obstacle avoidance reference parameter type, the obstacle avoidance reference parameter type of the first fabric material does not include a preset sensor data type, the obstacle avoidance reference data type of the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

[0133] Optionally, the material identification module is further configured to:

[0134] Counting the target intervals with the largest number among the first number of hit current intervals identified continuously;

[0135] The current working surface material is determined based on the working surface material corresponding to the target interval.

[0136] Optionally, the material identification module is further configured to:

[0137] Determining a currently identified material corresponding to the current position based on the working surface material corresponding to the hit current interval, and determining a historical working surface material corresponding to the current position based on historical cleaning data of the automatic cleaning device;

[0138] If the historical working surface material is consistent with the current working surface material, the currently identified material is determined as the current working surface material;

[0139] If the historical working surface material is inconsistent with the current working surface material, the material identification strategy setting data of the automatic cleaning device is obtained, and the current working surface material is determined according to the material identification strategy setting data, the current identification material and the historical working surface material.

[0140] Optionally, the material identification module is further configured to:

[0141] If the number of target intervals is greater than or equal to the second number, the working surface material corresponding to the target interval is determined as the current working surface material; if the number of target intervals is less than the second number, the historical working surface material corresponding to the current position is determined based on the historical cleaning data of the automatic cleaning equipment, and when the target interval is consistent with the preset current interval corresponding to the historical working surface material, the working surface material corresponding to the target interval is determined as the current working surface material.

[0142] Optionally, the working data of the cleaning component includes driving current data of the cleaning component; and the material identification module is further configured to:

[0143] Inputting the driving current data of the cleaning component into a pre-trained material classification model to construct current characteristic data of the driving current data of the cleaning component through the material classification model, and performing material prediction on the current characteristic data to obtain the current working surface material corresponding to the current position of the automatic cleaning device;

[0144] The current characteristic data of the driving current data of the cleaning component is constructed by using the currently input driving current data of the cleaning component and the driving current data of the third number of cleaning components input before the currently input driving current data of the cleaning component.

[0145] Optionally, the material identification module is further configured to:

[0146] Displaying the working surface material identification information corresponding to the automatic cleaning device, wherein the working surface material identification information includes the working surface materials identified by the automatic cleaning device at different positions;

[0147] In response to a working surface material correction instruction at any target position in the working surface material identification information, correcting the working surface material at the target position;

[0148] In the historical cleaning data of the automatic cleaning device, the historical cleaning component current corresponding to the target position is obtained, and based on the historical cleaning component current and the corrected working surface material, the material classification model is updated and trained.

[0149] Optionally, the material identification module is further configured to:

[0150] detecting whether the automatic cleaning device enters the fabric material area;

[0151] When it is detected that the automatic cleaning device enters the fabric material area, the step of determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component is performed.

[0152] Optionally, the device further includes a path planning module, configured to:

[0153] When it is detected that the automatic cleaning device enters a fabric material area, generating a predicted fabric area corresponding to the current position based on the current position of the automatic cleaning device and historical driving current data of the cleaning component corresponding to the current position;

[0154] Planning a cleaning path of the automatic cleaning device within the predicted fabric area.

[0155] Optionally, the data acquisition module is further used to obtain visual data collected during the operation of the automatic cleaning device;

[0156] The material recognition module is also used to: obtain visual data collected during the operation of the automatic cleaning device; perform fabric fiber data analysis on the visual data to determine whether the automatic cleaning device has entered the fabric material area, wherein the fabric fiber data includes the length and / or density of the fabric fibers.

[0157] Optionally, the working data of the cleaning component includes pressure data of the cleaning component; and the material identification module is further configured to:

[0158] In the preset pressure intervals corresponding to different working surface materials, the preset pressure interval where the cleaning component pressure data is located is determined as the hit pressure interval, and the current working surface material is determined based on the working surface material corresponding to the hit pressure interval.

[0159] It should be noted that for other corresponding descriptions of the functional units involved in the obstacle avoidance control device of an automatic cleaning equipment provided in an embodiment of the present application, reference can be made to the corresponding descriptions in the methods of Figures 1 to 3, and no further details will be given here.

[0160] The embodiment of the present application also provides a computer device, which can be specifically a personal computer, a server, a network device, etc. As shown in Figure 5, the computer device includes a bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store location information. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in each method embodiment are implemented.

[0161] Those skilled in the art will understand that the structure shown in FIG5 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile, and stores a computer program thereon. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0163] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0165] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0166] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An obstacle avoidance control method for an automatic cleaning device, wherein: The method comprises: Acquire working data of at least one cleaning component collected during the working process of the automatic cleaning device; Determining a current working surface material corresponding to a current position of the automatic cleaning device based on the working data of the cleaning component; The automatic cleaning device is controlled to avoid obstacles according to the obstacle avoidance strategy corresponding to the current working surface material.

2. The method according to claim 1, wherein: The working data of the cleaning component includes driving current data of the cleaning component; The determining, based on the working data of the cleaning component, the current working surface material corresponding to the current position of the automatic cleaning device comprises: In the preset current intervals corresponding to different working surface materials, the preset current interval into which the driving current data of the cleaning component falls is taken as the hit current interval, and the current working surface material is determined based on the working surface material corresponding to the hit current interval.

3. The method according to claim 1, wherein: The working surface material includes: a first fabric material and a second fabric material, wherein a first height value of fabric fibers in the first fabric material protruding from the working surface is greater than a second height value of fabric fibers in the second fabric material protruding from the working surface.

4. The method according to claim 3, wherein: The obstacle avoidance strategy includes an obstacle avoidance reference parameter type, the obstacle avoidance reference parameter type corresponding to the first fabric material does not include a preset sensor data type, the obstacle avoidance reference data type corresponding to the second fabric material includes a preset sensor data type, and the sensing range of the preset sensor includes a range above the second height value.

5. The method according to claim 2, wherein: The determining the current working surface material based on the working surface material corresponding to the hit current interval includes: Counting the target intervals with the largest number among the first number of hit current intervals that are continuously identified; The current working surface material is determined based on the working surface material corresponding to the target interval.

6. The method according to claim 2, wherein: The determining the current working surface material based on the working surface material corresponding to the hit current interval includes: Determine the current identified material corresponding to the current position based on the working surface material corresponding to the hit current interval, and determine the historical working surface material corresponding to the current position based on the historical cleaning data of the automatic cleaning device; If the historical working surface material is consistent with the current working surface material, the currently identified material is determined as the current working surface material; If the historical working surface material is inconsistent with the current working surface material, the material identification strategy setting data of the automatic cleaning device is obtained, and the current working surface material is determined according to the material identification strategy setting data, the current identification material and the historical working surface material.

7. The method according to claim 1, wherein: The working data of the cleaning component includes pressure data of the cleaning component; and determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component includes: In the preset pressure intervals corresponding to different working surface materials, the preset pressure interval in which the cleaning component pressure data is located is determined as the hit pressure interval, and the current working surface material is determined based on the working surface material corresponding to the hit pressure interval.

8. The method according to any one of claims 1 to 7, wherein: The cleaning component includes a roller brush.

9. The method according to any one of claims 1 to 7, wherein: Before determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component, the method further includes: Detecting whether the automatic cleaning device enters the fabric material area; When it is detected that the automatic cleaning device enters the fabric material area, the step of determining the current working surface material corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component is performed.

10. The method according to claim 9, wherein: The method further comprises: When it is detected that the automatic cleaning device enters the fabric material area, based on the current position of the automatic cleaning device and the historical driving current data of the cleaning component corresponding to the current position, a predicted fabric area corresponding to the current position is generated; The cleaning path of the automatic cleaning device in the predicted fabric area is planned.

11. The method according to claim 9, wherein: The detecting whether the automatic cleaning device enters the fabric material area includes: Obtain visual data collected during the operation of automatic cleaning equipment; The visual data is subjected to fabric fiber data analysis to determine whether the automatic cleaning device has entered a fabric material area, wherein the fabric fiber data includes the length and / or density of fabric fibers.

12. An obstacle avoidance control device for an automatic cleaning device, wherein: The device comprises: A data acquisition module, used to acquire working data of at least one cleaning component collected during the working process of the automatic cleaning device; A material identification module, used to determine the material of the current working surface corresponding to the current position of the automatic cleaning device based on the working data of the cleaning component; The obstacle avoidance control module is used to perform obstacle avoidance control on the automatic cleaning device according to the obstacle avoidance strategy corresponding to the current working surface material.

13. A storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

14. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 11 is implemented.

Images