Automatic pool cleaning device, control method and computer storage medium thereof

Abstract

The invention provides an automatic pool cleaning device, a control method and a computer storage medium thereof. The control method comprises the steps that the automatic pool cleaning device is controlled to move in a pool; acquiring an environment image acquired by image acquisition equipment in the moving process of the automatic pool cleaning device; when the collected environment image is recognized and it is recognized that an obstacle exists in the environment image, obstacle information of the obstacle is obtained; and controlling the movement of the automatic pool cleaning device according to the obstacle information.

Description

Technical Field

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

[0002] When a pool cleaning robot cleans a pool, it usually needs to clean the bottom, the walls, and the water surface of the pool. During such cleaning processes, the pool cleaning robot is very likely to encounter various types of objects, such as dirt (such as branches, leaves, paper scraps, etc.) and obstacles (such as steps, railings, stone piers, toys, etc.). Obtaining information about the objects (such as the distance and size of the objects) is crucial for the pool cleaning robot to take appropriate actions (such as obstacle avoidance, obstacle crossing, cleaning path adjustment, etc.). Summary of the Invention

[0003] According to one aspect of the present disclosure, there is provided a control method for an automatic pool cleaning device, including: controlling the automatic pool cleaning device to move in a pool; obtaining an environmental image during the movement of the automatic pool cleaning device collected by an image acquisition device; in the case where the collected environmental image is recognized and an obstacle is recognized in the environmental image, obtaining obstacle information of the obstacle; and controlling the movement of the automatic pool cleaning device according to the obstacle information.

[0004] Further, the obstacle information includes the height of the obstacle, and wherein, the controlling the movement of the automatic pool cleaning device according to the obstacle information includes: if the height of the obstacle is less than a first preset height, controlling the automatic pool cleaning device to continue moving along the current movement path to cross the obstacle; if the height of the obstacle is greater than or equal to the first preset height, controlling the automatic pool cleaning device to turn to avoid the obstacle.

[0005] Further, when controlling the automatic pool cleaning device to continue moving along the current movement path, the method further includes: when moving to the position where the obstacle is located or at a predetermined distance from the obstacle, controlling the automatic pool cleaning device to increase the pump power to cross the obstacle.

[0006] Further, the obstacle information further includes the width of the obstacle, and the controlling the automatic pool cleaning device to turn includes: in the case where the height of the obstacle is greater than or equal to the first preset height, controlling the turning angle and / or the distance of the automatic pool cleaning device after turning based on the width of the obstacle.

[0007] Further, controlling the turning of the automatic pool cleaning device includes: after the automatic pool cleaning device turns to avoid the obstacle, controlling the automatic pool cleaning device to return to the current movement path and continue moving forward.

[0008] Further, the obstacle information includes the category and size of the obstacle. Controlling the movement of the automatic pool cleaning device according to the obstacle information includes: when the obstacle belongs to a preset category of obstacles, controlling the automatic pool cleaning device to turn and move to the next movement path; when the obstacle does not belong to the preset category of obstacles, controlling the automatic pool cleaning device to cross or avoid the obstacle according to the size of the obstacle.

[0009] Further, the preset category of obstacles includes at least one of a pool wall and a cliff.

[0010] Further, it further includes: determining whether the obstacle belongs to the preset category of obstacles through semantic recognition, or determining whether the obstacle belongs to the preset category of obstacles based on the size of the obstacle.

[0011] Further, the obstacle information includes the position, category, and size of the obstacle. Adjusting the movement path of the automatic pool cleaning device according to the obstacle information includes: based on the position of the obstacle, determining whether the obstacle is located on the current movement path of the automatic pool cleaning device. If so, controlling the automatic pool cleaning device to cross or avoid the obstacle based on the category and / or size of the obstacle.

[0012] Further, the image acquisition device includes a binocular vision sensor or a monocular vision sensor.

[0013] According to another aspect of the present disclosure, an automatic pool cleaning device is provided, including an image acquisition device and a controller. The image acquisition device is used to acquire the environmental image during the movement of the automatic pool cleaning device; the controller is used to execute the control method described in any one of the present applications.

[0014] According to another aspect of the present disclosure, a computer storage medium is provided. A computer program is stored in the storage medium, and when the computer program is executed by a processor, the control method described in any one of the present applications is implemented.

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

[0016] During the process of the automatic pool cleaning device provided by the present application for moving and cleaning the pool, by collecting environmental images and identifying the environmental images, obstacles can be identified and further obstacle information can be obtained, so that the automatic pool cleaning device can take appropriate actions (such as obstacle avoidance, obstacle crossing, cleaning path adjustment, etc.) according to the obstacle information, improving the success rate of obstacle avoidance of the machine and the intelligence of the machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. The drawings in the following description are only exemplary embodiments of the present disclosure.

[0018] Figure 1 is a flowchart of the control method of the automatic pool cleaning device of the present application;

[0019] Figure 2 is a schematic diagram of the forward direction of the automatic pool cleaning device of the present application at the bottom of the pool Figure 1 ;

[0020] Figure 3 is a schematic diagram of the forward direction of the automatic pool cleaning device of the present application at the bottom of the pool Figure 2 ;

[0021] Figure 4 is a schematic diagram of the forward direction of the automatic pool cleaning device of the present application on the pool wall Figure 1 ;

[0022] Figure 5 is a schematic diagram of the forward direction of the automatic pool cleaning device of the present application on the pool wall Figure 2 . DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below in conjunction with the drawings in the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present application fall within the scope of protection of the present application.

[0024] The present application provides a control method for a pool automatic cleaning device and a pool automatic cleaning device. It can be understood that the pool automatic cleaning device can clean a pool. The pool is, for example, a pool-shaped building. The pool-shaped building can be a swimming pool, a water storage tank, a spa pool, a water storage tank, a water storage trough, etc. The pool automatic cleaning device can be a device such as an automatic cleaning device, a pool cleaning robot, etc., which can clean the pool-shaped building. The present application does not limit the specific presentation forms of the pool automatic cleaning device and the pool-shaped building, as long as the principle of the present application can be realized. In the following text, if not otherwise specified, the robot will be used as an example of the pool automatic cleaning device for elaboration, and the swimming pool will be used as an example of the pool or pool-shaped building for elaboration.

[0025] The control method 100 for the pool automatic cleaning device will be described in detail below with reference to the accompanying drawings.

[0026] Figure 1 is a flowchart of the control method 100 for the pool automatic cleaning device of the present application. As Figure 1 shown in the figure, the present application provides a control method for a pool automatic cleaning device, including: in step S101, controlling the pool automatic cleaning device to move in the pool; in step S102, obtaining the environmental image during the movement of the pool automatic cleaning device collected by the image acquisition device; in the case where the collected environmental image is recognized and an obstacle is recognized in the environmental image, in step S103, obtaining the obstacle information of the obstacle; in step S104, controlling the movement of the pool automatic cleaning device according to the obstacle information.

[0027] The above steps will be described in detail below with specific examples.

[0028] In step S101, control the pool automatic cleaning device to move in the pool. The term "in the pool" can refer to the bottom of the pool, the pool wall, or the water surface of the pool. For example, the "movement" referred to in the present application can mean that the robot randomly moves on the bottom of the pool, or the robot moves along a planned path (such as a "bow-shaped" path) on the bottom of the pool. Another example is that the "movement" referred to in the present application can mean that the robot randomly moves on the pool wall, or the robot moves along a planned path (such as a "bow-shaped" path) on the pool wall. The "movement" referred to in the present application can also mean that the robot moves on the water surface, such as moving along the edge of the water surface, randomly moving on the water surface, or "bow-shaped" moving on the water surface. The above description of "movement" is exemplary and is not intended to be an exhaustive list of the robot's movement in the pool.

[0029] Next, proceed to step S102. In step S102, obtain the environmental image during the movement of the pool automatic cleaning device collected by the image acquisition device.

[0030] The image acquisition device includes, for example, a binocular vision sensor or a monocular vision sensor. The vision sensor can focus light through a lens group to form an inverted and reduced real image on the image sensor. The binocular vision sensor mimics the two eyes and captures left and right images through two parallel cameras, and calculates the depth using the parallax. For example, the pixel position difference (parallax) of the same object in the left and right images is inversely proportional to the distance. The larger the parallax, the closer the object; the smaller the parallax, the farther the object. The monocular vision sensor only uses a single camera to capture 2D images. The camera captures single-frame or multi-frame continuous images and detects key points, edges, or semantic information in the images. In this application, if there is no other special description, the binocular vision sensor is abbreviated as the binocular camera, the monocular vision sensor is abbreviated as the monocular camera, and further, the binocular camera and the monocular camera are uniformly abbreviated as the camera.

[0031] The term "environmental image" refers to the image collected by the robot at the current position through the camera. The collected image can include the image in the direction of the robot's head, the image in the direction of the robot's tail, the image in the lateral direction of the robot, or can also include the image of a predetermined angle (such as 180 degrees, 360 degrees) surrounding the robot. The collected environmental image can include the environmental information of the robot in the pool (such as the environment of the pool bottom and / or the pool wall), and can also include the environmental information of the water surface. There can be obstacles (such as steps, railings, stone piers, toys, etc.), dirt (such as branches, leaves, paper scraps, etc.) in the collected environmental image.

[0032] It should be noted that in step S102, the robot collects the environmental image while moving. The robot can collect the environmental image in a certain direction multiple times at a predetermined time interval through the camera, or the robot can also collect the environmental image in a certain direction once, as long as the technical principle of this application can be realized.

[0033] In the case where the collected environmental image is recognized and an obstacle is recognized in the environmental image, proceed to step S103. In step S103, obtain the obstacle information of the obstacle.

[0034] "Obstacle" may be a fixed facility of the pool, such as: the pool wall or the pool bottom or the drain / suction port fixedly installed on the pool bottom or the pool wall, underwater lights, steps / ramps, stone piers, stone columns, cables, water pipes, etc.; the underwater "obstacle" may also be the remains of human activities, such as toys, floating objects, jewelry, coins, goggles, diving equipment. The term "obstacle information" may include: the category of the obstacle, the size of the obstacle (such as: height, width), the orientation of the obstacle, etc.

[0035] The robot can pre-collect a large number of images containing various obstacles in the underwater environment and perform deep learning on the large number of collected images. Through deep learning, an artificial intelligence recognition model of the environmental image can be established. The trained model can be pre-stored in the robot. The trained model can output the orientation, distance, size, category, etc. of the obstacle. For example, the robot collects a large number of image data containing obstacles in the underwater environment for training, enabling the robot to accurately identify obstacles such as stones, pipes, steps, railings, etc. in the pool through the camera. The robot uses a convolutional neural network for deep learning.

[0036] The robot uses binocular vision ranging through binocular cameras to obtain obstacle information, such as the position, size, category, etc. of the obstacle. For example, the robot obtains binocular images of the same scene through two cameras, then calculates the disparity between the same obstacle feature points in the binocular images and uses triangulation to calculate the depth of the obstacle.

[0037] The above description of the recognition of the environmental image and the acquisition of obstacle information is only exemplary and is not intended to be an exhaustive list.

[0038] Next, enter step S104. In step S104, according to the obstacle information, control the movement of the pool automatic cleaning device.

[0039] Figure 2 Shows a schematic diagram of the forward direction of the pool automatic cleaning device of the present application at the pool bottom. Figure 3 Shows another schematic diagram of the forward direction of the pool automatic cleaning device of the present application at the pool bottom. As Figure 2 and Figure 3 shown, the robot moves along the path indicated by the arrow at the pool bottom. Figure 4 Shows a schematic diagram of the forward direction of the pool automatic cleaning device of the present application on the pool wall. Figure 5 Shows another schematic diagram of the forward direction of the pool automatic cleaning device of the present application on the pool wall.

[0040] The obstacle information includes the height of the obstacle. Among them, controlling the movement of the automatic pool cleaning device according to the obstacle information includes: if the height of the obstacle is less than a first preset height, controlling the automatic pool cleaning device to continue moving along the current movement path to cross the obstacle; if the height of the obstacle is greater than or equal to the first preset height, controlling the automatic pool cleaning device to turn to avoid the obstacle.

[0041] Specifically, the height of the obstacle is used as the obstacle information for exemplary illustration. The robot identifies that the height of the obstacle is relatively low (for example, less than the first preset height) through the acquisition of the obstacle information. The robot can choose to continue moving forward along the original path (i.e., the current path) and cross the obstacle. As Figure 2 and Figure 4 shown, the robot moves along the path indicated by the arrow (for example, moves along the bottom of the pool as shown in Figure 2 shown, and moves along the pool wall as shown in Figure 4 shown). And if the robot identifies that the height of the obstacle on the path indicated by the arrow is relatively low, the robot can continue to move along the path indicated by the arrow, thereby crossing the obstacle. Among them, the height of the obstacle can refer to the maximum height of the obstacle. For example, the floor lights or wall lights in the swimming pool are generally arc-shaped structures, and the vertex of the arc corresponds to the maximum height of the floor light or wall light. If the maximum height is less than the preset height, it means that the robot can cross the arc vertex of the floor light or wall light, that is, the robot can directly cross the obstacle.

[0042] When the automatic pool cleaning device continues to move along the current movement path, the control method 100 further includes: when moving to the position where the obstacle is located or at a predetermined distance from the obstacle, controlling the automatic pool cleaning device to increase the pump power to cross the obstacle.

[0043] In the case where the robot chooses to continue moving forward along the original path and cross the obstacle, in order to cross the obstacle smoothly, the robot needs to increase the pump power to provide additional thrust and speed for the robot, so as to facilitate the robot to cross the obstacle smoothly. The robot can increase the pump power at a predetermined distance from the obstacle so that the robot can obtain additional thrust and speed when driving to the position of the obstacle. The robot can also increase the pump power when moving to the position of the obstacle.

[0044] The robot identifies that the height of the obstacle is relatively high (for example, greater than or equal to the first preset height) through the acquisition of the obstacle information. The robot can turn and drive along the turning direction to avoid the obstacle, or the robot can re-plan the path, and the re-planned path can enable the robot to avoid the obstacle. As Figure 3 and Figure 5As shown, the robot moves along the path indicated by the straight arrow (for example, moves along the bottom of the pool as shown in Figure 3 , moves along the pool wall as shown in Figure 5 ). And if the robot recognizes that the height of the obstacle on the path indicated by the straight arrow is relatively high, the robot can turn (as indicated by the curved arrows in Figure 3 and Figure 5 ) and move along the curved arrow to avoid the obstacle. In practice, if the obstacle is directly in front of the robot, the robot can adjust the path to the left or right. After avoiding the obstacle, the robot returns to the predetermined path or a random path; if the obstacle is in the upper right front of the robot, the robot can adjust the path to the left. After avoiding the obstacle, the robot returns to the predetermined path or a random path; if the obstacle is in the upper left front of the robot, the robot can adjust the path to the right. After avoiding the obstacle, the robot returns to the predetermined path or a random path.

[0045] The first preset height can be a height threshold preset by the robot according to its own obstacle-crossing ability, such as a height value preset by the robot at the time of factory. The first preset height can also be preset by the user.

[0046] The turning of the automatic pool cleaning device may include: after the automatic pool cleaning device turns and avoids the obstacle, controlling the automatic pool cleaning device to return to the current moving path and continue to travel.

[0047] Specifically, as described above with reference to Figure 3 and Figure 5 , after the robot bypasses the obstacle, it can continue to return to the original path and continue to travel. In other words, after the robot turns and avoids the obstacle, the robot can be controlled to continue cleaning the original cleaning path, so that the cleaning path is not changed due to the previous obstacle avoidance action.

[0048] As described above with reference to Figure 2 and Figure 4 , the robot moves along the original path and crosses the obstacle. During the process of crossing the obstacle, the robot needs to maintain a stable posture to avoid rolling or capsizing. If the shape or position of the obstacle requires the robot to adjust the driving direction during the process of crossing the obstacle, the robot can also appropriately adjust the driving direction (for example, appropriately adjust the turning angle of the robot with respect to the obstacle) to cross the obstacle more smoothly. For example, if the obstacle is a slope, the robot can adjust the driving direction so that the driving direction of the robot is consistent or substantially consistent with the direction of the slope, so as to more easily cross the obstacle without rolling or capsizing.

[0049] The obstacle information may further include the width of the obstacle. Controlling the turning of the automatic pool cleaning device includes: when the height of the obstacle is greater than or equal to the first preset height, controlling the turning angle and / or the distance of movement after turning of the automatic pool cleaning device based on the width of the obstacle.

[0050] The width of the obstacle may include the width of the obstacle in the horizontal direction. When the height of the obstacle is greater than or equal to the first preset height, it is difficult for the robot to directly continue moving along the predetermined path and bypass the obstacle. In other words, the robot needs to turn to avoid the obstacle. The turning angle and / or the distance of movement after turning of the robot can be determined according to the width of the obstacle. If the width of the obstacle is large, the turning angle of the robot is also large, and the distance of movement after turning is also large. On the contrary, if the width of the obstacle is small, the robot can turn a small angle to bypass the obstacle, and correspondingly, the distance of movement after turning is also small.

[0051] The robot can also adjust the movement path according to other information of the obstacle (such as one or more of the category, shape, volume, etc. of the obstacle). The adjustment of the movement path by the robot according to the obstacle information described above is only exemplary and is not intended to exhaustively list the ways for the robot to cross or avoid obstacles in the pool.

[0052] The obstacle information may further include the category and size (such as width, height, etc.) of the obstacle. Controlling the movement of the automatic pool cleaning device according to the obstacle information includes: when the obstacle belongs to the preset category of obstacles, controlling the automatic pool cleaning device to turn and move to the next movement path; when the obstacle does not belong to the preset category of obstacles, controlling the automatic pool cleaning device to cross or avoid the obstacle according to the size of the obstacle. The preset category of obstacles for the automatic pool cleaning device includes at least one of the pool wall and the cliff. The automatic pool cleaning device determines whether the obstacle belongs to the preset category of obstacles through semantic recognition, or determines whether the obstacle belongs to the preset category of obstacles based on the size of the obstacle.

[0053] The obstacle category may include the pool wall, cliff, steps, railing, stone pillar, wall lamp, floor lamp, etc. For the preset category of obstacles (such as wall lamps and floor lamps), their sizes are usually small. The robot can, as described above, choose to continue moving along the predetermined path and cross such obstacles according to the size of the obstacle (such as Figure 2 shown). Even if the sizes of these categories of obstacles are large, the robot can also turn to avoid the obstacle and then return to the predetermined path again (such as Figure 3 shown).

[0054] For some other types of obstacles (such as pool walls, cliffs, steps, railings, etc.), these obstacles usually occupy a large area on the pool wall / pool bottom. Generally, the robot cannot directly cross such obstacles, or even if it crosses such obstacles, the cleaning work of the robot along the predetermined path cannot continue. Therefore, the robot needs to turn and move to the next moving path.

[0055] The term "semantic recognition" may refer to the robot assigning corresponding semantic categories to the pixels in the environmental image. For example, the robot assigns corresponding semantic categories to the pixels in the environmental image, and then performs semantic segmentation on the environmental image. For example, the pixels of the environmental image are classified into categories such as "steps", "railings", "stone pillars", "dirt", etc., so that the robot can understand the environmental image based on the semantic segmentation of the environmental image and identify the category, position, orientation, size, etc. of the obstacle.

[0056] By performing semantic recognition on the environmental image, the robot can determine whether the obstacle in the environmental image belongs to the preset category of obstacles. For example, it determines whether the obstacle belongs to at least one of the pool wall and the cliff. The robot can also, based on the obstacle information obtained in step 103 above, obtain the size of the obstacle, and further determine whether the obstacle belongs to the preset category of obstacles based on the size of the obstacle. For example, if both the height and width of the obstacle exceed a certain threshold, the robot can determine the obstacle as a pool wall.

[0057] Step S014 may further include: based on the position of the obstacle, determining whether the obstacle is located on the current moving path of the pool automatic cleaning device. If so, controlling the pool automatic cleaning device to cross the obstacle or avoid the obstacle based on the category and / or size of the obstacle.

[0058] If the obstacle is located on the current path of the robot, the robot can choose to avoid the obstacle (such as bypassing the obstacle as shown above with reference to Figure 3 ) or cross the obstacle (such as crossing the obstacle as shown above with reference to Figure 2 ) by pre-judging the category and / or size of the obstacle in advance. If the obstacle is not on the current moving path, the robot does not need to adjust the path (i.e., does not need to adjust the moving direction) nor increase the pump power. By judging the position of the obstacle, the robot can avoid unnecessary operations, thereby improving the cleaning efficiency.

[0059] The present application also provides a pool automatic cleaning device, including an image acquisition device and a controller. Wherein, the image acquisition device is used to acquire the environmental image during the movement of the pool automatic cleaning device; the controller is used to execute the control method for the robot to cross the obstacle or avoid the obstacle as described above.

[0060] The image acquisition device includes a binocular vision sensor or a monocular vision sensor. The image acquisition device has been described above and will not be elaborated here. The controller is the core component of the robot, responsible for processing the data acquired by the image acquisition device and making decisions and controlling the robot according to preset algorithms and logics. The controller will receive the image data transmitted by the camera and identify the category, position, size, etc. of the obstacles. Based on the detected obstacle information, the controller performs path planning and adjusts the path to cross or avoid the obstacle.

[0061] This embodiment discloses a computer storage medium in which a computer program is stored. When the computer program is executed by a processor, it implements the control method described above.

[0062] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0063] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection 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 can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0064] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0065] In this application, unless otherwise stated, the orientation terms such as "upper" and "lower" generally refer to the directions shown in the drawings, or to the vertical, perpendicular or gravitational directions; similarly, for the convenience of understanding and description, "left" and "right" generally refer to the left and right shown in the drawings; "inner" and "outer" refer to the inner and outer of the contours of the respective components themselves, but the above orientation terms are not used to limit this application.

[0066] As described above, it is only an exemplary embodiment of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope recorded in this application can easily think of various changes or substitutions, and these should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A control method for an automatic pool cleaning device, comprising: Controlling the automatic pool cleaning device to move in the pool; Obtaining environmental images during the movement of the automatic pool cleaning device collected by an image acquisition device; When recognizing the collected environmental images and recognizing that there are obstacles in the environmental images, obtaining obstacle information of the obstacles; Controlling the movement of the automatic pool cleaning device according to the obstacle information.

2. The control method according to claim 1, wherein The obstacle information includes the height of the obstacle. Wherein, the controlling the movement of the automatic pool cleaning device according to the obstacle information includes: If the height of the obstacle is less than a first preset height, controlling the automatic pool cleaning device to continue moving along the current movement path to cross the obstacle; If the height of the obstacle is greater than or equal to the first preset height, controlling the automatic pool cleaning device to turn to avoid the obstacle.

3. The control method according to claim 2, wherein When controlling the automatic pool cleaning device to continue moving along the current movement path, the method further includes: When moving to the position of the obstacle or a predetermined distance from the obstacle, controlling the automatic pool cleaning device to increase the pump power to cross the obstacle.

4. The control method according to claim 2, wherein, The obstacle information further includes the width of the obstacle. The controlling the automatic pool cleaning device to turn includes: When the height of the obstacle is greater than or equal to the first preset height, controlling the turning angle and / or the moving distance after turning of the automatic pool cleaning device based on the width of the obstacle.

5. The control method according to claim 2, wherein the controlling the automatic pool cleaning device to turn includes: After the automatic pool cleaning device turns to avoid the obstacle, controlling the automatic pool cleaning device to return to the current movement path and continue moving forward.

6. The control method according to any one of claims 1-5, wherein the obstacle information includes the category and size of the obstacle. The controlling the movement of the automatic pool cleaning device according to the obstacle information includes: When the obstacle belongs to a preset category of obstacles, controlling the automatic pool cleaning device to turn and move to the next movement path; When the obstacle does not belong to the preset category of obstacles, controlling the automatic pool cleaning device to cross the obstacle or avoid the obstacle according to the size of the obstacle.

7. The control method according to claim 6, wherein, The preset category of obstacles includes at least one of a pool wall and a cliff.

8. The control method according to claim 6, wherein, It further includes: Determining whether the obstacle belongs to the preset category of obstacles by semantic recognition, or determining whether the obstacle belongs to the preset category of obstacles based on the size of the obstacle.

9. The control method according to claim 1, wherein the obstacle information includes the position, category and size of the obstacle. The adjusting the movement of the automatic pool cleaning device according to the obstacle information includes: Based on the position of the obstacle, determine whether the obstacle is located on the current moving path of the automatic pool cleaning device. If so, control the automatic pool cleaning device to cross or avoid the obstacle based on the category and / or size of the obstacle.

10. The control method according to claim 1, wherein, The image acquisition device includes a binocular vision sensor or a monocular vision sensor.

11. An automatic pool cleaning device, comprising an image acquisition device and a controller, wherein, The image acquisition device is used to acquire the environmental image during the movement of the automatic pool cleaning device; The controller is used to execute the control method according to any one of claims 1-10.

12. A computer storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the control method according to any one of claims 1 to 10 is realized.

Images