Automatic pool cleaning device and control method thereof

Abstract

Disclosed are an automatic pool cleaning device and a control method thereof. The method comprises: obtaining at least one frame of real-time image of a scene in front of the automatic pool cleaning device during the process of the automatic pool cleaning device moving on the bottom of a pool; obtaining real-time information of a target object in the scene from the at least one frame of real-time image; and controlling the movement of the automatic pool cleaning device on the bottom of the pool according to the real-time information.

Description

Technical Field

[0001] The present invention relates to an automatic pool cleaning device and a control method thereof in the field of automatic cleaning. Background Art

[0002] For pool facilities such as swimming pools, automatic pool cleaning equipment can be used for automatic cleaning or auxiliary cleaning. For example, the automatic pool cleaning equipment can be designed to move on the bottom, wall and / or water surface of the pool while running its cleaning mechanism to filter pool water and absorb dirt. Summary of the invention

[0003] Disclosed is a control method for an automatic pool cleaning device, comprising: obtaining at least one frame of real-time image of a scene in front of the automatic pool cleaning device during the process of the automatic pool cleaning device moving on the pool bottom; obtaining real-time information of a target object in the scene from the at least one frame of real-time image; and controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information.

[0004] In one or more embodiments, the real-time information includes at least one of the following: the type of the target; the location of the target; the size of the target; the deviation angle of the center point of the target relative to the current orientation of the automatic pool cleaning device; and the distance between the target and the automatic pool cleaning device.

[0005] In one or more embodiments, the center point of the target object includes one of the center point of the circumscribed circle of the target object's contour, the center point of the inscribed circle of the target object's contour, the point on the target object closest to the automatic pool cleaning device, the center point of a line between two points on the target object's contour, or a point on the axis of symmetry of the target object, wherein the two points on the contour include the point on the contour farthest from the automatic pool cleaning device.

[0006] In one or more embodiments, when the type of the target object indicates that the target object is cleanable garbage, controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information includes: controlling the automatic pool cleaning device to move toward the target object based on the position of the target object.

[0007] In one or more embodiments, controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information includes: controlling the automatic pool cleaning device to move toward the center point of the target object based on the center point of the target object.

[0008] In one or more embodiments, when the type of the target object indicates that the target object is cleanable garbage, controlling the movement of the automatic pool cleaning device on the pool bottom based on the real-time information also includes: tracking the target object during the movement toward the target object; and when the target object disappears, controlling the automatic pool cleaning device to continue moving forward a preset distance or a preset time to clean the target object.

[0009] In one or more embodiments, controlling the automatic pool cleaning device to continue moving forward a preset distance or a preset duration includes: in a case where the target object disappears, controlling the automatic pool cleaning device to rotate in an attempt to find the target object; in a case where the target object is found by rotating, controlling the automatic pool cleaning device to move toward the target object; and in a case where the target object is still not found by rotating, controlling the automatic pool cleaning device to continue moving forward the preset distance or a preset duration in the direction before rotating.

[0010] In one or more embodiments, the preset distance or the preset duration depends on at least one of the size of the blind spot of the automatic pool cleaning device and the position of the sewage suction port at the bottom of the automatic pool cleaning device.

[0011] In one or more embodiments, when the type of the target object indicates that the target object is an uncleanable obstacle, controlling the movement of the automatic pool cleaning device on the pool bottom based on the real-time information includes: determining whether the automatic pool cleaning device will collide with the target object if it continues to move forward based on at least one of the size of the target object, the position of the target object, and the deviation angle of the center point of the target object relative to the current orientation of the automatic pool cleaning device; and controlling the automatic pool cleaning device to continue moving forward if it is determined that the automatic pool cleaning device will not collide with the target if it continues to move forward.

[0012] In one or more embodiments, the target object includes a preset target object, and the distance between the preset target object and the automatic pool cleaning device is within a preset range.

[0013] In one or more embodiments, the at least one frame of real-time image is acquired by a monocular camera.

[0014] Also disclosed is an automatic pool cleaning device, comprising: an image sensor configured to acquire at least one frame of real-time image of a scene in front of the automatic pool cleaning device as the automatic pool cleaning device moves on the bottom of a pool; and a controller configured to execute the control method as described above.

[0015] In one or more embodiments, the image sensor includes a monocular camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 An example of an automatic pool cleaning device according to an embodiment of the present disclosure is schematically shown.

[0017] Figure 2 An example of a control method of an automatic pool cleaning device according to an embodiment of the present disclosure is schematically shown.

[0018] Figure 3 An example of an execution environment of the control method according to an embodiment of the present disclosure is schematically shown.

[0019] Figure 4 An example of a real-time image during the execution of the control method according to an embodiment of the present disclosure is schematically shown.

[0020] Figure 5 An example of a target object during the execution of the control method according to an embodiment of the present disclosure is schematically shown.

[0021] Figure 6 An example of determining the distance between a target object and an automatic pool cleaning device during the execution of the control method according to an embodiment of the present disclosure is schematically shown.

[0022] Figure 7 An example of an execution process of the control method according to an embodiment of the present disclosure is schematically shown.

[0023] Figure 8 An example of a blind area of ​​vision during the execution of the control method according to an embodiment of the present disclosure is schematically shown.

[0024] Fig. 9 Another example of the execution process of the control method according to the embodiment of the present disclosure is schematically shown.

[0025] Fig.10 Another example of the execution process of the control method according to the embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0026] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In the accompanying drawings, the same or corresponding parts are given the same symbols, and their description will not be repeated.

[0027] The automatic pool cleaning device may be equipped with a sensor such as an ultrasonic sensor to sense surrounding obstacles while the automatic pool cleaning device is traveling in the pool or on the water surface, thereby allowing the automatic pool cleaning device to avoid obstacles in the pool or on the water surface or to attempt to cross the obstacles. However, the automatic pool cleaning device may also avoid garbage that actually needs to be cleaned in the pool or on the water surface or collide with actual obstacles that cannot be cleaned multiple times, thereby reducing the cleaning efficiency and the life of the device.

[0028] The technical solution in the embodiments of the present disclosure enables the automatic pool cleaning device to identify the type of obstacles and perform cleaning operations more intelligently according to the type of obstacles.

[0029] Figure 1 An exemplary automatic pool cleaning device 100 in an embodiment of the present disclosure is schematically shown, which is also referred to as “device 100 ” hereinafter.

[0030] The device 100 may be configured with a housing, a water inlet, a water outlet, a water pump, a filtering device, and a driving mechanism, etc., wherein the driving mechanism may include, for example, a power mechanism such as a motor, a water pump, and a traveling mechanism such as a traveling wheel, a crawler, a water nozzle, a propeller, etc. driven by the power mechanism. For example, the device 100 may use its driving mechanism to move on the bottom, wall, or surface of a pool, while the pool water and the garbage in the water are sucked into the device from the water inlet through the water pump, and then the pool water filtered by the filtering device is discharged from the water outlet into the pool.

[0031] like Figure 1 As shown, in the device 100 , an image sensor 120 and a controller 110 are also configured.

[0032] The image sensor 120 may include an image sensor such as a monocular camera or a binocular camera. For example, the image sensor 120 may be disposed in front of the device 100, or may be configured to at least face the front of the device 100, so as to obtain a scene in front of the device 100 (e.g., Figure 1 The live image of the .

[0033] The controller 110 may include one or more circuits and / or modules such as a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), etc., which have data processing capabilities and / or instruction execution capabilities and are suitable for the device 100. For example, the controller 110 may include a dedicated integrated circuit or a custom processor such as a tensor processing unit (TPU), a brain processing unit (BPU), a deep learning processor (DPU), and a neural network processor (NPU). For example, the controller 110 may also include circuits and / or modules for accelerating operations such as a multiplication and addition unit array.

[0034] The controller 110 can be configured to perform data processing and / or control related to the cleaning operation and / or other functions of the device 100 according to a program stored in the memory of the device 100 and / or signals and / or instructions from a control panel or control terminal of the device 100 and / or sensing data from one or more sensors of the device 100 such as the image sensor 120, etc.

[0035] For example, the controller 110 can be configured to analyze and / or process at least one frame of real-time image of the scene in front of the device 100 from the image sensor 120 while the device 100 is moving on the bottom of the pool, and control the operation of one or more other components of the device 100 such as a driving mechanism, a traveling mechanism, etc. based on the results of the analysis and / or processing.

[0036] Figure 2 An exemplary control method 200 that can be used to control the device 100 in an embodiment of the present disclosure is schematically shown, hereinafter referred to as “method 200 ”.

[0037] The method 200 may be performed, for example, by the controller 110 of the device 100 in combination with other components of the device 100 such as the image sensor 120, and may include: step 210, acquiring at least one frame of real-time image of the scene in front of the device 100 during movement of the device 100 on the bottom of the pool; step 220, acquiring real-time information of a target object in the scene in front of the device 100 from the at least one frame of real-time image acquired in step 210; and step 230, controlling the movement of the device 100 on the bottom of the pool according to the real-time information of the target object in the scene in front of the device 100 acquired in step 220.

[0038] Through method 200, the device 100 can identify a target object in the scene in front of the device 100 and obtain real-time information about the target object, and can intelligently control the movement of the device 100 on the pool bottom based on the obtained real-time information, so that the device 100 can avoid unnecessary collisions while ensuring cleaning coverage, which is beneficial to improving cleaning efficiency and extending the service life of the device 100.

[0039] The details of method 200 and an example of the execution process are described below in conjunction with the drawings.

[0040] like Figure 3 As shown, at different positions of the bottom 300 of the pool, there may be targets of various types, sizes and / or shapes, wherein the first target 310 may be, for example, a single cleanable garbage such as leaves or branches, the second target 320 may be, for example, an uncleanable obstacle such as a ladder, and the third target 330 may be, for example, an area where a plurality of scattered cleanable garbage are relatively concentrated, wherein the area may be determined by any suitable method such as clustering, so that a plurality of scattered garbage that are close to each other are identified as a complete area.

[0041] When the device 100 enters the pool (e.g., moves into the pool, or is placed in the pool) and moves on the pool bottom 300, the method 200 may be executed to control the device 100. In addition, the method 200 may also include a step for starting the device 100 to move on the pool bottom 300, which may be executed before step 210. In addition, one or more steps in the method 200 may be repeatedly executed multiple times, and different steps may be executed in series or in parallel.

[0042] When the device 100 moves on the pool bottom 300, at least one frame of real-time image of the scene in front of the device 100 can be acquired by the image sensor 120, for example Figure 4 The real-time image 400 is shown in which images of the first target 310 , the second target 320 , and the third target 330 are captured.

[0043] For example, at least one frame of real-time image such as real-time image 400 may be at least one frame of two-dimensional image acquired by image sensor 120. In another embodiment, for example, when image sensor 120 includes a binocular camera, at least one frame of real-time image such as real-time image 400 may also be at least one frame of three-dimensional image acquired by image sensor 120.

[0044] The real-time image 400 may be processed and analyzed by any suitable method or model such as a convolutional neural network to obtain at least one real-time information about at least one of the first target 310 , the second target 320 , and the third target 330 from the real-time image 400 .

[0045] Real-time information about the target object may include, for example, but is not limited to, the type of the target object, the position of the target object, the size of the target object, the deviation angle of the center point of the target object relative to the current orientation of the device 100, and the distance between the target object and the device 100.

[0046] The type of the object may indicate whether the object is a cleanable garbage or garbage area (eg, the first object 310 and the third object 330 ), or an uncleanable obstacle (eg, the second object 320 ).

[0047] The center point of the target object may include the center point of the circumscribed circle of the target object's outline, the center point of the inscribed circle of the target object's outline, the point on the target object that is closest to the device 100, the center point of the line between two points on the target object's outline (for example, it may include the point on the target object's outline that is farthest from the device 100), a point on the target object's axis of symmetry, or other points that can represent the target object (for example, the geometric center point of an enclosing shape of the target object such as a rectangle or other shape).

[0048] For example, Figure 5 As shown, the center point P1 of the first target 310 can be the center of the circumscribed circle of the contour of the first target 310, and can be used to represent the first target 310; the center point P2 of the second target 320 can be the center of the circumscribed circle of the contour of the second target 320, and can be used to represent the second target 320; the center point P3 of the third target 330 can be the center of the circumscribed circle of the contour of the third target 330, and can be used to represent the third target 330.

[0049] The location of the center point of the target object may be represented by any suitable form of data under any system.

[0050] For example, for the center point P1 of the first target 310 , the two-dimensional coordinate data of the point P1 in the two-dimensional image coordinate system of the real-time image 400 may be determined, and the three-dimensional coordinate data of the point P1 in the three-dimensional image coordinate system of the real-time image 400 may also be determined.

[0051] For example, for the center point P1 of the first target object 310, the device 100 can also be taken as the origin and the current orientation of the device 100 as the axis, and then the distance D1 from the point P1 to the device 100 and the angle A1 from the axis can be determined by using the real-time sensing values ​​of the real-time image 400 and / or other sensors of the device 100 (for example, an ultrasonic ranging sensor, etc.), and the tuple (D1, A1) of the determined distance D1 and angle A1 can be used as data representing the position of the center point P1 of the first target object 310.

[0052] The deviation angle of the center point of the target object relative to the current orientation of the device 100 may be measured in any suitable manner and may be represented by any suitable form of data.

[0053] For example, when all targets captured in the real-time image are at a basically consistent field of view distance relative to the device 100, the perpendicular distance from the center point of the target to the axis corresponding to the current orientation of the device 100 can be used to measure and represent the deviation angle of the center point of the target relative to the current orientation of the device 100.

[0054] For example, the angle between the center point of the target object and the line connecting the device 100 and the current orientation of the device 100 can also be used to measure and represent the deviation angle of the center point of the target object relative to the current orientation of the device 100. Figure 5 As shown, the deviation angle of the center point P1 of the first target object 310 relative to the current orientation of the device 100 can be expressed as angle A1, the deviation angle of the center point P2 of the second target object 320 relative to the current orientation of the device 100 can be expressed as angle A2, and the deviation angle of the center point P3 of the third target object 330 relative to the current orientation of the device 100 can be expressed as angle A3.

[0055] After the real-time information of the target object in the scene in front of the device 100 is acquired from the real-time image 400 , the movement of the device 100 on the pool bottom 300 may be controlled according to the acquired real-time information.

[0056] For example, if the first target 310 is within a preset range from the device 100, or the first target 310 includes a preset target (e.g., a preset type of target) within the preset range from the device 100, the movement of the device 100 on the pool bottom 300 can be controlled based on real-time information about the first target 310.

[0057] For example, Figure 5As shown, among the first target 310, the second target 320, and the third target 330 captured by the real-time image 400, the distance D2 between the first target 310 and the device 100 is smaller than the distance D2 between the second target 320 and the device 100 and the distance D3 between the third target 330 and the device 100; or Figure 6 As shown, among the first target 310, the second target 320, and the third target 330 captured by the real-time image 400, the distance between the center point P1 of the first target 310 and the center point C of the lower edge of the real-time image 400 is smaller than the distance between the center point P2 of the second target 320 and point C and the distance between the center point P3 of the third target 330 and point C. Accordingly, the first target 310 is closest to the device 100. Therefore, the first target 310 closest to the device 100 can be selected from the first target 310, the second target 320, and the third target 330 captured by the real-time image 400, and the movement of the device 100 on the pool bottom 300 can be controlled according to the real-time information of the first target 310.

[0058] When the type of the selected object indicates that the object is cleanable garbage, the device 100 can be controlled to move toward the object based on the position of the object. For example, the device 100 can be controlled to move toward the center of the object based on the center of the object.

[0059] For example, Figure 7 As shown, when the first target object 310 is selected, if the current orientation of the device 100 ( Figure 7 The dotted arrow in the figure does not point to the center point P1 of the first target object 310, then according to the point P1 relative to Figure 7 The deviation angle A1 of the dotted arrow in the figure is used to control the rotation of the device 100, so that the orientation of the device 100 after the rotation is ( Figure 7 ) points to the center point P1 of the first target object 310. Then, the device 100 may be controlled to move toward the center point P1 of the first target object 310 so as to clean the first target object 310.

[0060] In the process of controlling the device to move toward the first target object 310, the first target object 310 may be tracked. Figure 8As shown, when the first target object 310 disappears from the current field of view 810 of the image sensor 120 and enters the current blind spot 820 of the image sensor 120, the device 100 can be controlled to continue to move forward a preset distance or a preset time to ensure that the first target object 310 can be cleaned, wherein the preset distance or the preset time can be determined, for example, based on the size of the blind spot of the image sensor 120 of the device 100, and further, the preset distance or the preset time can also be determined, for example, based on the position of the sewage suction port at the bottom of the device 100.

[0061] For example, affected by the resistance in the pool and the fluctuation of water flow, the device 100 may produce a large deviation even if it moves in a straight line. In the case where the first target 310 disappears from the current field of view 810 of the image sensor 120 and enters the current blind spot 820 of the image sensor 120, the device 100 can be controlled to rotate first and try to find the disappeared first target 310. In the case where the first target 310 is found by rotation, the device 100 can be controlled to move toward the first target 310. In the case where the first target 310 is still not found by rotation, the device 100 can be controlled to continue to move forward for a preset distance or a preset time in the direction before rotation. In this way, the device 100 can find the first target 310 more accurately and clean it.

[0062] In the case where the type of the selected target object indicates that the target object is an uncleanable obstacle, it can be determined whether the device 100 will collide with the target object if it continues to move forward in the current orientation according to at least one of the size of the target object, the position of the target object, and the deviation angle of the center point of the target object relative to the current orientation of the device 100. If it is determined that the target object will not be collided, the device 100 can be controlled to continue to move forward in the current orientation, otherwise, for example, the device 100 can be controlled to continue to move forward after rotating a certain angle, so that the device 100 can avoid the target object.

[0063] For example, Fig. 9 As shown, when the second target 320 is selected, the real-time distance D2 between the device 100 and the second target 320 can be determined according to the size of the second target 320. Then, for example, when the distance D2 reaches a predetermined value (for example, 50 cm, 1 m, or any other suitable value), the current orientation ( Fig. 9 The deviation angle A2 of the dashed arrow in the figure.

[0064] For example, when the deviation angle A2 is greater than a predetermined angle threshold (for example, it can be predetermined according to the body width of the device 100), as shown in FIG. Fig. 9As shown, it can be determined that the device 100 is in the current orientation ( Fig. 9 The dashed arrow in the figure) will not collide with the second target object 320, and the device 100 can be controlled to move in the direction according to the current direction ( Fig. 9 Continue forward by clicking the dashed arrow in the figure.

[0065] For example, when the deviation angle A2 is less than or equal to the predetermined angle threshold, Fig.10 As shown, it can be determined that the device 100 is in the current orientation ( Fig.10 If the device 100 continues to move forward, it will collide with the second target object 320. Therefore, the device 100 can be controlled to change its direction, and then the device can be controlled as follows: Fig.10 Continue along the new route indicated by the solid arrow in the figure to avoid colliding with the second target object 320.

[0066] As described above, through method 200, the device 100 can identify the target object in the scene in front of the device 100 and obtain real-time information about the target object, and can intelligently control the movement of the device 100 on the pool bottom based on the real-time information obtained, so that the device 100 can avoid unnecessary collisions while ensuring cleaning coverage, which is beneficial to improving cleaning efficiency and extending the service life of the device 100.

[0067] The basic principle of the present disclosure is described above in combination with the embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the aforementioned details are only for the purpose of illustration and ease of understanding, not limitation, and the aforementioned details do not limit the present disclosure to being implemented by adopting the aforementioned details.

[0068] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. In different embodiments, these devices, apparatuses, equipment, and systems may be connected, arranged, or configured in any appropriate manner.

[0069] In addition, words such as "including", "comprising", "having" and the like are open-ended words, meaning "including but not limited to", and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably therewith.

[0070] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0071] In this document, modifiers such as "first", "second", etc. without quantifiers are intended to distinguish different elements / components / circuits / modules / devices / steps, and are not used to emphasize the order, positional relationship, importance, priority, etc. In contrast, modifiers such as "first", "second", etc. with quantifiers can be used to emphasize the order, positional relationship, importance, priority, etc. of different elements / components / circuits / modules / devices / steps.

[0072] The above description is given for the purpose of illustration and description. This description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A control method for an automatic pool cleaning device, characterized in that: The control method comprises: During the process of the automatic pool cleaning device moving on the bottom of the pool, acquiring at least one frame of real-time image of the scene in front of the automatic pool cleaning device; Acquire real-time information of a target object in the scene from the at least one frame of real-time image; Controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information, The real-time information includes at least one of the following: the type of the target; the location of the target; the size of the target; the deviation angle of the center point of the target relative to the current orientation of the automatic pool cleaning device; the distance between the target and the automatic pool cleaning device, The center point of the target object includes the center point of the circumscribed circle of the target object's contour, the center point of the inscribed circle of the target object's contour, the point on the target object closest to the automatic pool cleaning device, the center point of the line between two points on the target object's contour, or a point on the axis of symmetry of the target object, wherein the two points on the contour include the point on the contour farthest from the automatic pool cleaning device.

2. The control method as claimed in claim 1, characterized in that: In the case where the type of the target object indicates that the target object is cleanable garbage, the target object includes a single cleanable garbage and / or an area where a plurality of dispersed cleanable garbage are located, and controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information includes: The automatic pool cleaning device is controlled to move toward the target object based on the position of the target object.

3. The control method according to claim 1, characterized in that: Controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information includes: The automatic pool cleaning device is controlled to move toward the position of the center point of the target object based on the position of the center point of the target object.

4. The control method according to claim 1, characterized in that: In the case where the type of the target object indicates that the target object is cleanable garbage, the target object includes an area where a single cleanable garbage and / or a plurality of dispersed cleanable garbage are located, and controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information further includes: tracking the target object while moving toward the target object; When the target object disappears, the automatic pool cleaning device is controlled to continue moving forward for a preset distance or a preset time to clean the target object.

5. The control method according to claim 4, characterized in that: Controlling the automatic pool cleaning device to continue moving forward by a preset distance or for a preset duration includes: When the target object disappears, controlling the automatic pool cleaning device to rotate to try to find the target object; When the target object is found by rotating, controlling the automatic pool cleaning device to move toward the target object; In the case that the target object is still not found after the rotation, the automatic pool cleaning device is controlled to continue moving forward by the preset distance or the preset time according to the orientation before the rotation.

6. The control method according to claim 4, characterized in that: The preset distance or the preset duration depends on at least one of the size of the blind spot of the automatic pool cleaning device and the position of the sewage suction port at the bottom of the automatic pool cleaning device.

7. The control method according to claim 1, characterized in that: In the case where the type of the target object indicates that the target object is an uncleanable obstacle, controlling the movement of the automatic pool cleaning device on the pool bottom according to the real-time information includes: determining whether the automatic pool cleaning device will collide with the target object if it continues to move forward based on at least one of the size of the target object, the position of the target object, and the deviation angle of the center point of the target object relative to the current orientation of the automatic pool cleaning device; When it is determined that the automatic pool cleaning device will not collide with the target object if it continues to move forward, the automatic pool cleaning device is controlled to continue to move forward.

8. The control method according to claim 1, characterized in that: The target object includes a preset target object, and the distance between the preset target object and the automatic pool cleaning device is within a preset range.

9. The control method according to any one of claims 1 to 8, characterized in that: The at least one frame of real-time image is acquired by a monocular camera.

10. An automatic pool cleaning device, characterized in that: The automatic pool cleaning device comprises: An image sensor is configured to obtain at least one frame of real-time image of a scene in front of the automatic pool cleaning device during the process of the automatic pool cleaning device moving on the bottom of the pool; A controller configured to execute the control method according to any one of claims 1 to 9.

11. The automatic pool cleaning device according to claim 10, characterized in that: The image sensor includes a monocular camera.

Images