Automatic pool cleaning equipment and control method thereof
By using image sensors on the automatic pool cleaning device to identify obstacles and adjust the movement route, the problem that the equipment is difficult to avoid obstacles during cleaning operations is solved, and a more efficient and safe cleaning process is achieved.
Patent Information
- Application Number
- CN202510121342.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-23
- Publication Date
- 2025-05-30
AI Technical Summary
When performing cleaning operations, existing pool automatic cleaning equipment is difficult to accurately identify and avoid obstacles, resulting in unnecessary collisions, traps, falls and failures, affecting the life of the equipment and cleaning efficiency.
By assembling an image sensor on the pool automatic cleaning device, obtaining real-time images and determining the location information and type of obstacles, and then adjusting the movement route of the device to avoid non-cleaning objects or continue to move forward to clean the cleanable objects.
It realizes accurate identification and handling of obstacles by automatic pool cleaning equipment, reduces unnecessary collisions and traps, extends the equipment life, and improves cleaning efficiency and user experience.
Smart Images
Figure CN120066018A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure 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, an automatic pool cleaning device can be used for automatic cleaning or auxiliary cleaning. For example, the automatic pool cleaning device can be designed to move on the bottom, wall, and / or water surface of the pool while operating its cleaning mechanism to filter the pool water and absorb dirt. Summary of the Invention
[0003] Disclosed is a method for controlling an automatic pool cleaning device, including: controlling the automatic pool cleaning device to perform a cleaning operation in a pool; during the cleaning operation, acquiring a real-time image of the front scene of the automatic pool cleaning device; determining the position information and type of an obstacle in front of the automatic pool cleaning device based on the real-time image; and controlling the movement of the automatic pool cleaning device according to the position information and type of the obstacle.
[0004] In one or more embodiments, controlling the movement of the automatic pool cleaning device includes: when the type of the obstacle indicates that the obstacle is a non-cleaning object, adjusting the movement route of the automatic pool cleaning device based on the position information of the obstacle to avoid the obstacle.
[0005] In one or more embodiments, controlling the movement of the automatic pool cleaning device includes: when the type of the obstacle indicates that the obstacle is a cleanable object, controlling the automatic pool cleaning device to continue moving forward based on the position information of the obstacle to clean the obstacle.
[0006] In one or more embodiments, controlling the automatic pool cleaning device to continue moving forward based on the position information of the obstacle to clean the obstacle includes: determining whether the obstacle is in a specific area, the specific area including an area where the automatic pool cleaning device may be stuck or fall; and
[0007] When the obstacle is not in the specific area, controlling the automatic pool cleaning device to move forward towards the obstacle to clean the obstacle.
[0008] In one or more embodiments, determining whether the obstacle is in a specific area includes: determining whether the obstacle is located in the specific area based on the real-time image.
[0009] In one or more embodiments, determining whether the obstacle is in a specific area includes: determining whether the obstacle is in a specific area based on the position information of the obstacle and the map information of the pool.
[0010] In one or more embodiments, controlling the pool automatic cleaning device to continue moving forward includes at least one of the following: controlling the pool automatic cleaning device to move forward after turning; and controlling the pool automatic cleaning device to move forward along the historical movement route.
[0011] In one or more embodiments, controlling the pool automatic cleaning device to continue moving forward based on the position information of the obstacle to clean the obstacle includes: determining whether the obstacle will cause the pool automatic cleaning device to be blocked or malfunction; and in the case of determining that the obstacle will not cause the pool automatic cleaning device to be blocked or malfunction, controlling the pool automatic cleaning device to continue moving forward towards the obstacle to clean the obstacle.
[0012] In one or more embodiments, determining whether the obstacle will cause the pool automatic cleaning device to be blocked or malfunction includes: determining whether the obstacle will cause the pool automatic cleaning device to be blocked or malfunction based on the volume or size of the obstacle and the current amount of garbage stored in the garbage basket of the pool automatic cleaning device.
[0013] There is also disclosed a pool automatic cleaning device, including: an image sensor configured to acquire a real-time image of the front scene of the pool automatic cleaning device; and a controller configured to execute the method as described above. Description of the Drawings
[0014] Figure 1 Schematically shows an example of the pool automatic cleaning device in the embodiments of the present disclosure.
[0015] Figure 2 Schematically shows an example of the method for controlling the pool automatic cleaning device in the embodiments of the present disclosure.
[0016] Figure 3 Schematically shows an example of the real-time image in the method for controlling the pool automatic cleaning device in the embodiments of the present disclosure.
[0017] Figure 4 Schematically shows an example of the execution process of the method for controlling the pool automatic cleaning device in the embodiments of the present disclosure.
[0018] Figure 5 Schematically shows an example of another real-time image in the method for controlling the pool automatic cleaning device in the embodiments of the present disclosure.
[0019] Figure 6 An example of the execution process of the method for controlling a pool automatic cleaning device in an embodiment of the present disclosure is schematically shown.
[0020] Figure 7 An example of the execution process of the method for controlling a pool automatic cleaning device in an embodiment of the present disclosure is schematically shown.
[0021] Figure 8 An example of the execution process of the method for controlling a pool automatic cleaning device in an embodiment of the present disclosure is schematically shown. Detailed implementation manners
[0022] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the drawings, the same or equivalent parts are given the same reference numerals, and their descriptions are not repeated.
[0023] During the process of the pool automatic cleaning device performing a cleaning operation in the pool or on the water surface, it is necessary to avoid obstacles. For example, the pool automatic cleaning device can be configured to, in the case of colliding with an obstacle, attempt to clean or cross the obstacle, and after the attempt fails, change the route, such as turning around in the opposite direction.
[0024] However, the pool automatic cleaning device may become easily damaged after long-term collisions. In the case of encountering an obstacle with a large volume or a light mass, it may be difficult to trigger a collision reaction, resulting in the pool automatic cleaning device pushing the obstacle to move.
[0025] In addition, the pool automatic cleaning device may also be trapped due to colliding with certain obstacles, such as being suspended and unable to move forward due to colliding with certain obstacles, or may be entangled by certain obstacles (such as linear obstacles such as cables) and unable to break free, or may be sucked or stuck by facilities such as drainage outlets in the pool.
[0026] In addition, the pool automatic cleaning device may also make a wrong judgment due to the influence of obstacles and continue to move forward, resulting in falling from a pool area such as a platform.
[0027] In addition, the pool automatic cleaning device may also malfunction due to obstacles. For example, in the case where the obstacle is cleanable garbage, the rolling brush of the pool automatic cleaning device may be entangled by the garbage (such as hair, etc.), or the transition device or garbage basket in the pool automatic cleaning device may be quickly (such as instantaneously) filled or blocked due to excessive dirt, resulting in the pool automatic cleaning device malfunctioning.
[0028] In an embodiment of the present disclosure, a camera sensor is assembled on the automatic pool cleaning device to obtain a real-time image of the front scene of the automatic pool cleaning device during the process of the automatic pool cleaning device performing a cleaning operation in the pool or on the water surface, and to determine the position information and type of an obstacle in front of the automatic pool cleaning device based on the obtained real-time image, and then to control the movement of the automatic pool cleaning device according to the determined position information and type of the obstacle.
[0029] Thereby, the automatic pool cleaning device in the embodiment of the present disclosure can accurately identify the position and type of obstacles in the pool, avoid or reduce unnecessary collisions, avoid or reduce jamming or falling, which is beneficial to extending the service life of the device, improving the cleaning efficiency and user experience.
[0030] Figure 1 Schematically shown is an exemplary automatic pool cleaning device 100 in an embodiment of the present disclosure, hereinafter also simply referred to as "device 100".
[0031] Device 100 may be configured with a housing, a water inlet, a water outlet, a water pump, a filtering device, a driving mechanism, etc. Among them, the driving mechanism may include, for example, power mechanisms such as motors and water pumps, and traveling mechanisms such as traveling wheels, crawlers, water spray nozzles, and propellers driven by the power mechanisms. For example, device 100 may use its driving mechanism to move on the pool bottom, pool wall or water surface, and at the same time suck the pool water together with the garbage in the water into the device through the water pump, and then discharge the filtered pool water from the water outlet into the pool.
[0032] As Figure 1 shown, in device 100, an image sensor 110 and a controller 120 are also configured.
[0033] The image sensor 110 may include one or more image sensors such as a monocular camera and a binocular camera. For example, the image sensor 110 may be configured at the front of the device 100 to obtain a real-time image of the front scene of the device 100 (for example, Figure 1 the shaded area in) during the process of the device 100 performing a cleaning operation in the pool or on the water surface.
[0034] The controller 120 may include any one or more circuits and / or modules having data processing capabilities and / or instruction execution capabilities and suitable for the device 100, such as a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), etc. For example, the controller 120 may include an application specific integrated circuit or a custom processor such as a tensor processing unit (TPU), a brain processing unit (BPU), a deep learning processing unit (DPU), a neural network processing unit (NPU). For example, the controller 120 may further include circuits and / or modules for accelerating operations, such as an array of multiply-accumulate units.
[0035] The controller 120 may be configured to perform data processing and / or control related to the cleaning operation and / or other functions of the device 100 according to programs stored in the memory of the device 100 and / or signals and / or instructions from the control panel or control terminal of the device 100 and / or sensed data from one or more sensors of the device 100, such as the image sensor 110. For example, the controller 120 may be configured to analyze and / or process real-time images from the image sensor 110, and control the operation of one or more other components of the device 100, such as the drive mechanism, the traveling mechanism, etc., according to the analysis and / or processing results of the real-time images.
[0036] Figure 2 Schematically shows an exemplary method 200 that can be used to control the device 100 in an embodiment of the present disclosure. The method 200 may be executed, for example, by the controller 120 of the device 100 in combination with other components of the device 100 (e.g., the image sensor 110), and may include steps 210, 220, 230, and 240.
[0037] In step 210, the device 100 may be controlled to perform a cleaning operation in a pool.
[0038] During the process of the device 100 performing the cleaning operation, step 220 may be executed to obtain a real-time image of the scene in front of the device 100.
[0039] Depending on the configuration of the image sensor 110, the real-time image obtained in step 220 may include one or more two-dimensional images (e.g., two-dimensional video) and / or one or more three-dimensional images (e.g., three-dimensional video).
[0040] Then, step 230 may be executed to determine the position information and type of obstacles in front of the device 100 based on the real-time image obtained in step 220.
[0041] In step 230, any suitable method or model such as convolutional neural network, object detection, semantic segmentation, instance segmentation, etc. can be adopted to determine the position information and type of the obstacle in front of device 100 from the acquired real-time image.
[0042] For example, the determined type of the obstacle can indicate that the obstacle in front of device 100 is a non-cleaning object such as a cable in a pool, a step, a drain, a ladder, etc., or can indicate that the obstacle in front of device 100 is a cleanable object such as a leaf, a branch, a small stone. Additionally, the determined type of the obstacle can also indicate whether the obstacle in front of device 100 is a cleanable object with a small quantity or a large total volume / area, or a cleanable object with a large quantity or a large total volume / area.
[0043] Then, in step 240, device 100 is controlled to move according to the position information and type, etc. of the obstacle determined in step 230.
[0044] For example Figure 3 As shown, in the case where the type of the obstacle 310 determined from the real-time image 300 indicates that the obstacle 310 is a non-cleaning object such as a ladder, in step 240, the movement route of device 100 can be adjusted based on the position information of the obstacle 240 to avoid the obstacle 310. For example Figure 4 as shown, the movement route of device 100 can be adjusted such that device 100 turns, for example, near the obstacle 310, and then changes to move along the route shown by the solid arrow in Figure 4 instead of moving along the route shown by the dashed arrow in Figure 4 (i.e., the previously determined historical movement route).
[0045] For example Figure 5 As shown, in the case where the type of the obstacle 510 determined from the real-time image 500 indicates that the obstacle 510 is a cleanable object such as a leaf, in step 240, device 100 can be controlled to continue moving forward based on the position information of the obstacle 510 to clean the obstacle 510. For example Figure 6 as shown, device 100 can be controlled to continue moving along the route shown by the solid arrow in Figure 6 (i.e., the previously determined historical movement route) to pass by the obstacle 510 and clean it.
[0046] Thereby, device 100 can accurately identify the position and type of the obstacle in the pool, thus avoiding or reducing unnecessary collisions and avoiding or reducing the occurrence of situations such as jamming and falling.
[0047] In the case where the type of the obstacle 510 indicates that the obstacle 510 is a cleanable object such as a leaf, in step 240, it can be further determined whether the obstacle 510 is in a specific area that may cause the device 100 to get stuck (for example, unable to move forward due to suspension, or being stuck and unable to break free, or being sucked by a drain, etc.) or fall (for example, falling from a platform), such as the edge of a platform or a pool drain.
[0048] For example, based on the real-time image obtained in step 220, it can be determined whether the obstacle 510 is located in the above-mentioned specific area by any suitable method or model such as convolutional neural network, object detection, semantic segmentation, instance segmentation, etc. It can also be determined whether the obstacle 510 is in the above-mentioned specific area based on the position information of the obstacle 510 determined in step 230 and the map information of the pool.
[0049] In the case where it is determined that the obstacle 510 is not in the above-mentioned specific area, in step 240, the device 100 can be controlled to continue moving forward along the previously determined historical movement route towards the obstacle 510 in order to clean the obstacle 510.
[0050] In the case where it is determined that the obstacle 510 is in a specific area such as the platform edge 700, as Figure 7 shown, in step 240, the movement route of the device 100 can be adjusted so that the device 100 turns, for example, near the obstacle 510 or at the obstacle 510 or near the platform edge 700, and then changes to move along the route shown by the solid arrow in Figure 7 instead of moving along the route shown by the dashed arrow in the original Figure 7 (i.e., the previously determined historical movement route) to prevent the device 100 from falling from the platform.
[0051] In addition, in the case where the type of the obstacle 510 indicates that the obstacle 510 is a cleanable object such as a leaf, in step 240, it can also be further determined whether the obstacle 510 will cause the device 100 to be blocked or malfunction, for example, an excessive amount of the obstacle 510 may cause the trash basket of the device 100 to be instantly filled or blocked.
[0052] For example, in step 240, any suitable method or model such as a convolutional neural network, object detection, semantic segmentation, instance segmentation, etc. can be adopted to determine other features such as the volume, size, shape, etc. of the obstacle 510 based on the acquired real-time image. Then, based on information such as the volume or size of the obstacle 510, and the current amount of garbage stored in the trash basket of the device 100 (for example, it can be determined according to the sensing data of the capacity sensor in the trash basket and the rated capacity of the trash basket based on the configuration of the device 100), it can be determined whether the obstacle 510 will cause the device 100 to be blocked or malfunction.
[0053] When it is determined that the obstacle 510 will not cause the device 100 to be blocked or malfunction, in step 240, the device can be controlled to continue moving towards the obstacle 510 for cleaning the obstacle 510.
[0054] When it is determined that the obstacle 510 may cause the device 100 to be blocked or malfunction, as Figure 8 shown, in step 240, the moving route of the device 100 can be adjusted so that the device 100 turns, for example, near the obstacle 510, and then changes to move along the route shown by the solid arrow in Figure 8 , instead of moving along the route shown by the dashed arrow in Figure 8 (i.e., the previously determined historical moving route), to prevent the device 100 from being blocked or malfunctioning.
[0055] In method 200, during the process of controlling the device 100 to perform a cleaning operation, a real-time image of the front scene of the device 100 is acquired, and the movement of the control device 100 is controlled according to the position information and type of the obstacle in front of the device 100 determined from the real-time image, so that the device 100 can accurately identify the position and type of the obstacle in the pool, avoid or reduce unnecessary collisions, avoid or reduce the occurrence of situations such as jamming, falling, and blockage, which is beneficial to extending the service life of the device and improving the cleaning efficiency and user experience.
[0056] The basic principles of the present disclosure have been described above in conjunction with the embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. Additionally, the foregoing details are only for illustrative and easy-to-understand purposes, rather than limitations, and the foregoing details do not limit the present disclosure to necessarily adopt the foregoing details to implement.
[0057] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. In different embodiments, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any appropriate manner.
[0058] In addition, words such as "comprising", "including", and "having" in this text are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The terms "or" and "and" used herein refer to the term "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The term "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.
[0059] It should also be noted that in the devices, equipment, and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.
[0060] In this text, modifiers without quantifiers such as "first", "second", etc. are intended to be used to distinguish different elements / components / circuits / modules / devices / steps, rather than to emphasize order, positional relationship, importance level, priority level, etc. In contrast, modifiers with quantifiers such as "the first one", "the second one", etc. can be used to emphasize the order, positional relationship, importance level, priority level, etc. of different elements / components / circuits / modules / devices / steps.
[0061] The above description is given for purposes 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 method for controlling an automatic pool cleaning device, comprising: Controlling the automatic pool cleaning device to perform cleaning operations in the pool; During the cleaning operation, a real-time image of a scene in front of the automatic pool cleaning device is obtained; Determine the location information and type of the obstacle in front of the automatic pool cleaning device based on the real-time image; as well as The automatic pool cleaning device is controlled to move according to the location information and type of the obstacle.
2. The method of claim 1, wherein: Controlling the movement of the automatic pool cleaning device includes: In the case where the type of the obstacle indicates that the obstacle is a non-cleaning object, the moving route of the automatic pool cleaning device is adjusted based on the position information of the obstacle so as to avoid the obstacle.
3. The method according to claim 1 or 2, wherein: Controlling the movement of the automatic pool cleaning device includes: In the case where the type of the obstacle indicates that the obstacle is a cleanable object, the automatic pool cleaning device is controlled to continue moving forward based on the position information of the obstacle so as to clean the obstacle.
4. The method of claim 3, wherein: Controlling the automatic pool cleaning device to continue moving forward based on the position information of the obstacle so as to clean the obstacle includes: Determining whether the obstacle is in a specific area, wherein the specific area includes an area that may cause the automatic pool cleaning device to get stuck or fall; and When the obstacle is not in the specific area, the automatic pool cleaning device is controlled to continue moving toward the obstacle so as to clean the obstacle.
5. The method of claim 4, wherein: Determining whether the obstacle is in a specific area includes: It is determined whether the obstacle is located in the specific area based on the real-time image.
6. The method of claim 4, wherein: Determining whether the obstacle is in a specific area includes: It is determined whether the obstacle is in a specific area based on the position information of the obstacle and the map information of the pool.
7. The method of claim 3, wherein: Controlling the automatic pool cleaning device to continue to move forward includes at least one of the following: controlling the automatic pool cleaning device to move forward after turning; and The automatic pool cleaning device is controlled to move along the historical moving route.
8. The method of claim 3, wherein: Controlling the automatic pool cleaning device to continue moving forward based on the position information of the obstacle so as to clean the obstacle includes: determining whether the obstruction will cause the automatic pool cleaning device to become blocked or malfunction; and When it is determined that the obstacle will not cause the automatic pool cleaning device to be blocked or malfunction, the automatic pool cleaning device is controlled to continue to move toward the obstacle so as to clean the obstacle.
9. The method of claim 8, wherein: Determining whether the obstacle will cause the automatic pool cleaning device to become blocked or malfunction includes: Whether the obstacle will cause the automatic pool cleaning device to be blocked or malfunction is determined based on the volume or size of the obstacle and the current amount of garbage stored in the garbage basket of the automatic pool cleaning device.
10. An automatic pool cleaning device, comprising: An image sensor configured to acquire a real-time image of a scene in front of the automatic pool cleaning device; as well as A controller configured to execute the method according to any one of claims 1 to 9.