Automatic pool cleaning device, control method and computer storage medium

By using underwater image acquisition equipment and image recognition models in the pool cleaning robot, the problem of the pool cleaning robot being unable to recognize the pool wall when the water level is too high is solved, obstacle avoidance operation is achieved, and the smooth completion of the cleaning task is ensured.

CN120704342APending Publication Date: 2025-09-26SHENZHEN AIPER INTELLIGENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510942398.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-08
Publication Date
2025-09-26

AI Technical Summary

Technical Problem

When the water level is too high, the pool cleaning robot cannot recognize the pool wall, causing it to get stuck, affecting cleaning efficiency and user experience.

Method used

Image acquisition equipment is used to collect images under the water surface, and the water surface features are judged through image recognition models to perform obstacle avoidance operations, including retreating, turning or stopping.

Benefits of technology

Effectively identify the edge of the pool to avoid getting stuck and ensure the normal execution of cleaning tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120704342A_ABST
    Figure CN120704342A_ABST
Patent Text Reader

Abstract

The invention provides an automatic pool cleaning device, a control method and a computer storage medium. The automatic pool cleaning device comprises image acquisition equipment, when the automatic pool cleaning device moves on the water surface of a pool, the image acquisition equipment is located under the water surface and can acquire water surface images, and the control method comprises the steps that the automatic pool cleaning device is controlled to conduct movable cleaning on the water surface of the pool; in the moving process, acquiring a water surface image through the image acquisition equipment; and judging whether the water surface image contains a target feature or not, and if not, controlling the automatic pool cleaning device to execute an obstacle avoidance operation, thereby ensuring that the automatic pool cleaning device can normally execute a cleaning task.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of cleaning devices, and in particular to an automatic pool cleaning device, a control method, and a computer storage medium. Background Art

[0002] With the popularity of swimming pools and significant advances in robotics, more and more consumers are turning to automated pool cleaning robots to perform their cleaning tasks. However, when the water level in a pool is too high, the pool robot's sensors may fail to detect the pool wall when they reach the edge while performing cleaning operations. This causes the pool robot to be unable to recognize that it has reached the pool wall, causing it to remain at the pool wall, resulting in a "stuck" phenomenon and unable to continue cleaning until the pool robot's battery runs out, seriously affecting cleaning efficiency and user experience. Summary of the Invention

[0003] In response to the deficiencies of the above-mentioned prior art, the present application provides a control method for an automatic pool cleaning device, wherein the automatic pool cleaning device includes an image acquisition device. When the automatic pool cleaning device moves on the water surface of the pool, the image acquisition device is located below the water surface and can acquire water surface images. The control method includes: controlling the automatic pool cleaning device to move and clean the water surface of the pool; during the movement, acquiring water surface images through the image acquisition device; and determining whether the water surface image contains target features. If not, controlling the automatic pool cleaning device to perform obstacle avoidance operations.

[0004] Furthermore, the controlling of the automatic pool cleaning device to perform an obstacle avoidance operation includes at least one of the following: controlling the automatic pool cleaning device to retreat a predetermined distance or for a predetermined period of time; controlling the automatic pool cleaning device to turn; controlling the automatic pool cleaning device to stop moving forward; controlling the automatic pool cleaning device to move along the extension direction of the pool wall.

[0005] Furthermore, the target feature includes a water ripple feature.

[0006] Furthermore, the determining whether the water surface image contains target features includes: identifying the water ripple features through a pre-trained image recognition model.

[0007] Furthermore, if the image recognition model does not output a recognition result within a predetermined time period, it is determined that the water surface image does not contain the water ripple feature.

[0008] Furthermore, the control method further includes: if the water surface image contains the target feature, controlling the automatic pool cleaning device to continue moving and cleaning the water surface.

[0009] The present application also discloses a non-volatile computer storage medium, in which a computer program is stored. When the computer program is executed by a processor, the control method described in any embodiment of the present application is implemented.

[0010] The present application also discloses an automatic pool cleaning device, which can execute the control method described in any embodiment of the present application.

[0011] Furthermore, the automatic pool cleaning device includes a disturbance generator, which is located in the forward direction of the automatic pool cleaning device and can generate disturbances on the water surface.

[0012] Furthermore, the disturbance generator includes a roller brush or a roller.

[0013] Furthermore, the automatic pool cleaning device includes a fill light, which is used to provide fill light in the forward direction of the automatic pool cleaning device.

[0014] Furthermore, the image acquisition device is configured to acquire water surface images at a predetermined elevation angle.

[0015] The embodiments described in this application have the following beneficial effects:

[0016] The control method of the automatic pool cleaning device of the present application collects water surface images through an image acquisition device during the water surface cleaning process of the automatic pool cleaning device, and determines whether the water surface image contains target features, thereby determining whether the automatic pool cleaning device is close to the edge of the swimming pool. When it is determined that the automatic pool cleaning device has reached the edge of the swimming pool, it can promptly identify and perform obstacle avoidance operations, thereby ensuring that the automatic pool cleaning device can perform the cleaning task normally. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present application, the following briefly introduces the drawings required for describing the embodiments. The drawings described below are only exemplary embodiments of the present application.

[0018] Figure 1 A flow chart showing a method for controlling an automatic pool cleaning device according to an embodiment of the present application is shown;

[0019] Figure 2 A schematic structural diagram of an automatic pool cleaning device according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram showing an automatic pool cleaning device according to an embodiment of the present application moving on the water surface; and

[0021] Figure 4A schematic diagram of a non-volatile computer storage medium according to an embodiment of the present application is shown. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 100-Pool wall, 200-Automatic pool cleaning device, 201-Image acquisition device, 2011-Field of view, 202-Disturbance generator, 300-Non-volatile computer storage medium, 301-Computer program. DETAILED DESCRIPTION

[0024] The technical solutions in this application will be described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other unless there is a conflict.

[0025] This application provides a control method for an automatic pool cleaning device, an automatic pool cleaning device employing the control method, and a computer storage medium. The automatic pool cleaning device of this application is used to clean a pool, the pool comprising a pool bottom, a pool wall 100, and a transition region between the pool bottom and the pool wall 100. The pool is, for example, a pool-shaped structure. The pool-shaped structure may be a swimming pool, a reservoir, a spa pool, a water tank, a water storage tank, or the like. The automatic pool cleaning device may be a device such as an automatic cleaning device or a pool cleaning robot, capable of cleaning the pool-shaped structure. This application does not limit the specific embodiment of the automatic pool cleaning device or the pool-shaped structure; any embodiment is sufficient as long as the principles of this application are implemented. Hereinafter, unless otherwise specified, the robot will be used as an example of the automatic pool cleaning device, and a swimming pool will be used as an example of a pool or pool-shaped structure. Hereinafter, unless otherwise specified, the terms "pool bottom," "pool bottom," and "pool bottom" all refer to the bottom surface of a swimming pool.

[0026] The automatic pool cleaning device and control method of the present application are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 A flow chart of a control method 10 of an automatic pool cleaning device 200 according to an embodiment of the present application is shown. Figure 2 The schematic diagram of the structure of the automatic pool cleaning device 200 of an embodiment of the present application is shown. Figure 2The automatic pool cleaning device 200 may include an image capture device 201. When the automatic pool cleaning device 200 moves on the surface of the pool, the image capture device 201 is located below the water surface and can capture images of the water surface. The automatic pool cleaning device 200 can be a surface cleaning device that only cleans the water surface, or it can be a multifunctional cleaning device that cleans both underwater and on the water surface.

[0028] Figure 2 The front and two side portions (i.e., the left and right sides) of the automatic pool cleaning device 200 are shown. For example, the image acquisition device 201 can be located at the front of the automatic pool cleaning device 200, or at the left front portion or right front portion of the body or housing of the automatic pool cleaning device 200. When the automatic pool cleaning device 200 moves on the surface of the pool, the image acquisition device 201 is located below the water surface. The image acquisition device 201 can have a certain field of view, so that it can capture images of the water surface of the automatic pool cleaning device 200 below the water surface. Alternatively, the image acquisition device 201 can be used to capture or scan the water surface at a certain angle or direction to capture images of the water surface of the automatic pool cleaning device 200.

[0029] It is understandable that the automatic pool cleaning device 200, due to the need to clean the water surface, usually uses a non-streamlined setting on the side used to collect garbage to increase its contact area with the garbage. During the process of the automatic pool cleaning device 200 moving on the water surface, due to the setting of the non-streamlined structure, the automatic pool cleaning device 200 will generate certain water surface disturbances (including water surface ripples, water surface waves, etc.). When the automatic pool cleaning device 200 is blocked by an obstacle, the automatic pool cleaning device 200 stops moving on the water surface, and at least part of the water surface disturbance will disappear. Therefore, the image acquisition device 201 is used to capture the water surface image, and by judging whether the captured water surface image contains the water surface disturbance, it can be confirmed whether the automatic pool cleaning device 200 needs to avoid obstacles. In addition, the above description of the image acquisition device 201 is only exemplary. In actual applications, those skilled in the art can selectively set the image acquisition device 201 according to actual conditions, as long as the technical principles of the present application can be implemented.

[0030] Furthermore, the automatic pool cleaning device 200 may include a disturbance generator 202 . The disturbance generator 202 is located in the forward direction of the automatic pool cleaning device 200 , and the disturbance generator 202 can generate disturbances on the water surface.

[0031] For example, the automatic pool cleaning device 200 may be provided with a disturbance generator 202, which may be positioned in the direction of travel of the automatic pool cleaning device 200. For example, the disturbance generator 202 may be positioned at the bottom of the automatic pool cleaning device 200 (e.g., at a side of the bottom, or in the middle of the front end of the bottom, etc.), or when the automatic pool cleaning device 200 is cleaning the water surface, the disturbance generator 202 may be completely submerged in the water surface, or at least a portion of the disturbance generator 202 may be positioned below the water surface. The position of the disturbance generator 202 is primarily determined to facilitate the disturbance of the water surface by the disturbance generator 202 when the automatic pool cleaning device 200 is moving on the water surface. The disturbance may be, for example, ripples or waves on the water surface.

[0032] Exemplarily, the disturbance generator 202 may include a roller brush, a roller, or a cleaning roller. For example, the roller brush can rotate to not only clean dirt and impurities in the water but also create disturbances on the water surface. The roller can rotate to create disturbances such as ripples or waves on the water surface. The cleaning roller includes a generally elongated cage-like structure. When the automatic pool cleaning device 200 is located on the water surface for cleaning, the rotating cleaning roller not only guides surface debris into the automatic pool cleaning device 200 but also creates ripples or waves on the water surface.

[0033] Furthermore, the automatic pool cleaning device 200 may include a fill light, and the fill light is used to provide fill light in the forward direction of the automatic pool cleaning device 200 .

[0034] For example, the automatic pool cleaning device 200 can be equipped with a fill light that provides additional illumination in the direction of travel of the automatic pool cleaning device 200. In low-light environments, the fill light can provide additional illumination, ensuring that the image capture device 201 can capture images of the water surface. Furthermore, the fill light can enhance the visibility of ripples or rippling on the water surface.

[0035] The following combination Figure 1 The control method 10 of the automatic pool cleaning device 200 of the present application is described in detail. Figure 1 FIG. 1 is a flow chart showing a control method 10 of an automatic pool cleaning device 200 according to an embodiment of the present application. Figure 1 As shown, the control method 10 includes: in step S11, controlling the automatic pool cleaning device to move and clean the water surface of the pool; in step S12, during the movement, collecting a water surface image through the image acquisition device; in step S13, determining whether the water surface image contains a target feature; if not, entering step S14, controlling the automatic pool cleaning device to perform an obstacle avoidance operation. Figure 1 Steps S11 to S14 in the control method 10 will be described.

[0036] In step S11, the automatic pool cleaning device is controlled to move and clean the water surface of the pool.

[0037] For example, a robot performs cleaning operations in a pool, which may include a variety of working modes, such as: pool bottom cleaning mode, pool wall cleaning mode, waterline cleaning mode and water surface cleaning mode. The water surface cleaning mode is also called the surface boat mode. In this mode, the robot floats on the water surface, and impurities (such as branches, leaves, soil, etc.) on the water surface are sucked into the robot through a water pump, for example, through a water suction port on the water surface. When the impurities pass through the trash basket, they are retained in the trash basket, and the water is discharged, thereby achieving the purpose of cleaning the water surface. The present application is mainly directed to the water surface cleaning mode. It is understandable that, under certain circumstances or under the premise that the conditions are met, the technical principles described in this application can also be applied to the other cleaning modes described above. In the pool bottom cleaning mode, the robot moves on the bottom surface of the pool, and impurities on the bottom surface of the pool are sucked into the robot through a water pump, thereby achieving the purpose of cleaning the bottom of the pool. The pool wall cleaning mode is also known as the wall climbing mode. This mode mainly uses the adsorption principle of the water pump to attach the robot to the pool wall 100 and move on the pool wall 100 to clean the pool wall 100. The waterline cleaning mode can be understood as the robot moving upward along the pool wall 100 to the waterline and moving along the waterline to clean the waterline.

[0038] For example, a control system can be used to control a robot to move and clean the surface of a pool. The control system may include, for example, a sensing module, a control module, and an execution module. The sensing module may include, for example, a distance sensor, a pressure sensor, an image sensor, etc. The sensing module can be used to monitor the water flow in the pool, the distribution of dirt, and the robot's motion in real time. The control module may be composed of a control chip and related circuits. The control module can be used to receive sensor data, process signals, and generate corresponding control commands based on a preset control strategy. The execution module may include, for example, a motor drive system and a cleaning mechanism. The motor drive system can adjust the motor speed and direction according to the control commands, controlling the robot's movement speed and path. The cleaning mechanism (e.g., a water pump, a sewage suction port, a trash basket, etc.) can clean, absorb, and filter dirt during the robot's movement.

[0039] It is understandable that the above description of the robot moving and cleaning on the surface of the pool is only exemplary. Those skilled in the art can set up the robot to move and clean on the surface of the pool according to actual conditions, as long as the technical principles of this application can be implemented.

[0040] Next, the process proceeds to step S12. In step S12, during the movement, the image acquisition device acquires a water surface image.

[0041] For example, the robot can be controlled to move along the path described above. During this movement, image acquisition device 201 can be used to capture water surface image information of the pool. This water surface image can be understood as an image of the water surface including the interface between water and air. Image acquisition device 201 can be, for example, a camera or a webcam. Image acquisition device 201 can be, for example, a monocular camera or a binocular camera. The water surface image captured by image acquisition device 201 can be multi-dimensional, for example, including static two-dimensional image data, or can include multiple attributes such as color, texture, contour, and spatial relationships.

[0042] Furthermore, the image acquisition device 201 can be configured to capture images of the water surface at a predetermined elevation angle. For example, during the robot's mobile cleaning of the water surface, the image acquisition device 201 is located below the water surface. Placing the image acquisition device 201 below the water surface helps reduce interference caused by reflections from the water surface when it is located above the water surface. Because the image acquisition device 201 is located below the water surface, the image acquisition device 201 uses a predetermined elevation angle to capture images of the water surface, which can increase the area of ​​the water surface image that includes the water surface, thereby improving the accuracy of identifying target features. By capturing water surface images at a predetermined elevation angle, detailed features of the water surface, such as the shape, size, and distribution of water surface ripples, can be clearly captured, thereby improving the accuracy of judging the water surface condition. In some embodiments, the predetermined elevation angle can be set within a range of 0.5 degrees to 30 degrees. This application does not specifically limit the reading of the predetermined elevation angle. Those skilled in the art can set the predetermined elevation angle according to actual needs, as long as the technical principles of this application can be implemented. It can be understood that the above description of the water surface image acquisition method is only exemplary, and those skilled in the art can set the water surface image acquisition method according to actual conditions as long as the technical principles of this application can be implemented.

[0043] After the water surface image is collected, the process proceeds to step S13. In step S13, it is determined whether the water surface image contains a target feature. If it is determined that the water surface image does not contain a target feature, the process proceeds to step S14, where the automatic pool cleaning device is controlled to perform an obstacle avoidance operation.

[0044] For example, after capturing the water surface image in step S12, it is determined whether the image contains the target feature. For example, an intelligent visual algorithm or image processing technology can be used to perform pixel-level analysis on the water surface image to identify whether the target feature exists in the water surface image. The target feature can be, for example, water ripples, ripple patterns, or other iconic features.

[0045] The target features may include water ripple features. Water ripple features specifically include the shape, size, spacing, frequency, and propagation direction of the ripples on the water surface. By identifying the water ripple features, it can be determined whether the robot is performing normal cleaning operations. Figure 3 Schematic diagram showing an automatic pool cleaning device according to an embodiment of the present application moving on the water surface. Figure 3 For example, if the robot performs a cleaning task on the water surface and gradually approaches the pool wall 100, if there is no water ripple feature or ripple feature in the water surface image captured by the image acquisition device 201, it indicates that the robot may be too close to the pool wall 100 or has already touched the pool wall 100. At this time, the following situation may occur: when the image acquisition device 201 captures images obliquely upward at the predetermined elevation angle, the field of view 2011 of the image acquisition device 201 is blocked by the pool wall 100 and the water ripples on the water surface cannot be captured (such as Figure 3 As shown). In some embodiments, the target feature may include a specific graphic projection feature or a light projection feature, and a graphic projection unit or a light projection unit may be provided on the automatic pool cleaning device. The projection unit may perform specific graphic / light projection in the forward direction of the cleaning device, and the image acquisition device 201 may be used to identify whether the projection exists in the water surface image. Similarly, it may be possible to judge whether there is an obstacle in front of the automatic pool cleaning device. At this time, the control system may be used to adjust the movement direction of the robot, such as turning left or right, or first retreating and then adjusting the direction, so as to free the robot, or avoid the robot from colliding with or getting stuck in the pool wall 100. The technical concept will be further described below with reference to specific examples. It will be understood that the "normal cleaning operation" mentioned above means that the robot is not trapped by obstacles such as the pool wall 100, and therefore, the robot can continue to move and clean on the water surface.

[0046] Furthermore, the determining whether the water surface image contains target features includes: identifying the water ripple features through a pre-trained image recognition model.

[0047] For example, water ripple features can be identified using a pre-trained image recognition model. Specifically, the image recognition model is trained based on a large amount of water surface image data containing features such as different water ripple shapes, sizes, spacing, and frequencies. After the training is completed and the image recognition model is obtained, the water surface image collected in step S12 can be input into the image recognition model. The image recognition model can pre-process the water surface image (for example, scaling, format conversion, image denoising, etc.), and then perform feature extraction and calculation on the pre-processed water surface image to determine whether the water surface image contains water ripple features.

[0048] Furthermore, if the image recognition model does not output a recognition result within a predetermined time period, it is determined that the water surface image does not contain the water ripple feature.

[0049] For example, if the image recognition model does not output a recognition result within a predetermined time (for example, within 3-15 seconds, preferably 5 seconds), it can be determined that the water ripple feature in the water surface image is not obvious or missing. Specifically, the image recognition model first pre-processes the water surface image and then extracts the feature. If no recognition result is output within the specified time, it indicates that the water ripple feature in the water surface image is unclear or does not exist. From this, it can be further determined that the robot is close to or against an obstacle (such as the pool wall 100), making it impossible for the robot's image acquisition device 201 to capture the target feature of the water surface (such as the water ripple feature) at the predetermined elevation angle, or the robot is "trapped" by the obstacle, causing the robot to be unable to move forward. Therefore, the robot does not generate corresponding target features on the water surface or the generated target features are small.

[0050] It will be understood that the above identification of the target features is merely exemplary, and those skilled in the art may configure the identification method of the target features according to actual circumstances, as long as the technical principles of the present application can be implemented.

[0051] If it is determined that there is no target feature in the water surface image, the process proceeds to step S14 to control the automatic pool cleaning device to perform an obstacle avoidance operation.

[0052] If it is determined that there are no target features (e.g., water ripple features) in the water surface image, the automatic pool cleaning device is controlled to perform an obstacle avoidance operation. For example, the control system can adjust the movement direction or speed of the automatic pool cleaning device to enable the automatic pool cleaning device to avoid obstacles and ensure that the automatic pool cleaning device can continue to perform its cleaning task. Adjusting the movement direction of the automatic pool cleaning device can, for example, involve turning or backing. The obstacles may be, for example, the pool wall 100, pool handrails, decorations, or steps.

[0053] Furthermore, the controlling of the automatic pool cleaning device to perform an obstacle avoidance operation includes at least one of the following: controlling the automatic pool cleaning device to retreat a predetermined distance or for a predetermined period of time; controlling the automatic pool cleaning device to turn; controlling the automatic pool cleaning device to stop moving forward; controlling the automatic pool cleaning device to move along the extension direction of the pool wall 100.

[0054] For example, the control system can control the automatic pool cleaning device 200 to retreat a predetermined distance (e.g., half the length of the body) at a predetermined speed or for a predetermined time (e.g., 5 seconds), so that the automatic pool cleaning device can avoid obstacles (e.g., the pool wall 100) and continue to perform the cleaning task.

[0055] For another example, the control system can be used to control the automatic pool cleaning device 200 to turn left or right at a predetermined speed to change the direction of travel of the automatic pool cleaning device 200, thereby avoiding obstacles (e.g., avoiding the pool wall 100). The turning angle can be a preset angle, or it can be adjusted according to the relative position of the automatic pool cleaning device 200 and the pool wall 100.

[0056] For another example, the control system can be used to control the automatic pool cleaning device 200 to stop moving forward, thereby preventing the automatic pool cleaning device 200 from running out of power. After stopping, the automatic pool cleaning device 200 can perform other operations, such as backing up or turning, according to a preset obstacle avoidance strategy to adjust the position and direction of the automatic pool cleaning device 200 to ensure that it can avoid obstacles.

[0057] For another example, the control system can be used to control the moving direction of the automatic pool cleaning device 200 so that the automatic pool cleaning device 200 moves along the extension direction of the pool wall 100, thereby allowing the automatic pool cleaning device 200 to avoid obstacles and perform wall cleaning.

[0058] It will be understood that the above description of the predetermined distance, predetermined duration and predetermined speed is merely exemplary, and those skilled in the art may set the predetermined distance, predetermined duration and predetermined speed according to actual conditions, as long as the technical principles of the present application can be implemented.

[0059] It can also be understood that the above-mentioned various operations for controlling the automatic pool cleaning device to perform obstacle avoidance can be achieved, for example, by controlling the driving device of the automatic pool cleaning device (such as a water pump, a driving wheel, etc.). Therefore, the above description of various operations is only exemplary. Those skilled in the art can set up the control of the automatic pool cleaning device to perform obstacle avoidance operations according to actual conditions, as long as the technical principles of this application can be implemented.

[0060] Furthermore, the control method may further include: if the water surface image contains the target feature, controlling the automatic pool cleaning device 200 to continue moving and cleaning the water surface.

[0061] For example, if the collected water surface image contains target features (such as water ripples), it indicates that the automatic pool cleaning device 200 is performing a normal cleaning operation. At this time, the automatic pool cleaning device continues to move along the current direction on the water surface to perform the cleaning task.

[0062] The control method 10 of the automatic pool cleaning device 200 of the present application, during the process of the automatic pool cleaning device performing water surface cleaning, collects a water surface image through the image acquisition device 201, and determines whether the water surface image contains target features, thereby determining whether the automatic pool cleaning device 200 is approaching an obstacle such as the pool wall 100. If it is determined that the automatic pool cleaning device 200 is approaching or reaching an obstacle, it can promptly identify and perform obstacle avoidance operations, thereby ensuring that the automatic pool cleaning device 200 can perform the cleaning task normally.

[0063] The present application also discloses an automatic pool cleaning device 200 , which is capable of executing the control method described above in the present application.

[0064] The present application also discloses a non-volatile computer storage medium 300, Figure 4 FIG. 1 shows a schematic diagram of a non-volatile computer storage medium according to an embodiment of the present application. Figure 4 As shown, the storage medium 300 stores a computer program 301, and when the computer program 301 is executed by the processor, it can implement the control method described above in this application.

[0065] It should be understood that, in this embodiment, the computer storage medium may be located in at least one of the plurality of network servers in the computer network. Alternatively, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0066] It should be noted that the sequence of the above embodiments of the present application is for description only and does not represent the advantages or disadvantages of the embodiments.

[0067] In the description of this specification, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and integrate different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0068] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0069] In this application, unless otherwise specified, directional words such as "up" and "down" are generally used with respect to the directions shown in the drawings, or with respect to the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "left" and "right" are generally used with respect to the left and right shown in the drawings; "inside" and "outside" refer to the inside and outside relative to the outline of each component itself, but the above directional words are not used to limit this application.

[0070] The above is merely an exemplary embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various modifications or substitutions within the technical scope described in this application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for controlling an automatic pool cleaning device, wherein the automatic pool cleaning device includes an image acquisition device. When the automatic pool cleaning device moves on the surface of a pool, the image acquisition device is located below the water surface and can capture images of the water surface. The control method comprises: Controlling the automatic pool cleaning device to move and clean the water surface of the pool; During the movement, collecting water surface images by the image acquisition device; It is determined whether the water surface image contains target features. If not, the automatic pool cleaning device is controlled to perform an obstacle avoidance operation.

2. The control method according to claim 1, wherein: The controlling the automatic pool cleaning device to perform an obstacle avoidance operation includes at least one of the following: Control the automatic pool cleaning device to retreat a predetermined distance or for a predetermined time; control the automatic pool cleaning device to turn; control the automatic pool cleaning device to stop moving forward; control the automatic pool cleaning device to move along the extension direction of the pool wall.

3. The control method according to claim 1, wherein: The target feature includes a water ripple feature.

4. The control method according to claim 3, wherein: The determining whether the water surface image contains target features includes: identifying the water ripple features through a pre-trained image recognition model.

5. The control method according to claim 4, wherein: If the image recognition model does not output a recognition result within a predetermined time period, it is determined that the water surface image does not contain the water ripple feature.

6. The control method according to any one of claims 1 to 3, further comprising: If the water surface image contains the target feature, the automatic pool cleaning device is controlled to continue moving and cleaning the water surface.

7. A non-volatile computer storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the control method according to any one of claims 1 to 6 is implemented.

8. An automatic pool cleaning device, wherein: The automatic pool cleaning device can execute the control method according to any one of claims 1 to 6.

9. The automatic pool cleaning device according to claim 8, wherein: The automatic pool cleaning device includes a disturbance generator, which is located in the forward direction of the automatic pool cleaning device and can generate disturbances on the water surface.

10. The automatic pool cleaning device according to claim 9, wherein: The disturbance generator includes a roller brush or a roller.

11. The automatic pool cleaning device according to claim 8, wherein: The automatic pool cleaning device includes a fill light, which is used to provide fill light in the forward direction of the automatic pool cleaning device.

12. The automatic pool cleaning device according to claim 8, wherein: The image acquisition device is configured to acquire water surface images at a predetermined elevation angle.