Control methods for pool cleaning robots

Abstract

This disclosure provides a control method for a swimming pool cleaning robot, relating to the field of robotics. The method includes: operating along a pool bottom covering cleaning path; acquiring first image information of a target area via a vision sensor; moving to the target area if the first image information indicates the presence of an object to be cleaned; and adjusting the cleaning parameters of the swimming pool cleaning robot to target cleaning parameters after reaching the target area, so that the swimming pool cleaning robot can clean the target area. This method can improve cleaning efficiency and cleaning effect.

Description

Technical Field

[0001] This disclosure relates to the field of robotics, and more particularly to a control method for a pool cleaning robot. Background Technology

[0002] In the field of pool cleaning technology, pool cleaning robots typically employ a uniform movement speed and fixed pump pressure when cleaning pools. While this achieves some level of pool cleaning, it also leads to a waste of the robot's power resources, thus affecting its cleaning efficiency. Summary of the Invention

[0003] This disclosure provides a control method for a pool cleaning robot.

[0004] According to a first aspect of this disclosure, a control method for a pool cleaning robot is provided, comprising:

[0005] Operate according to the cleaning path covering the bottom of the pool; First image information of the target area is acquired using a visual sensor; If the first image information indicates that there is something to be cleaned in the target area, proceed to the target area; After reaching the target area, the cleaning parameters of the pool cleaning robot are adjusted to the target cleaning parameters so that the pool cleaning robot can clean the target area.

[0006] According to a second aspect of this disclosure, a control device for a pool cleaning robot is provided, comprising: The configuration module is used to operate according to the cleaning path covering the bottom of the pool; The first acquisition module is used to acquire first image information of the target area through a visual sensor; The first operating module is configured to run to the target area when the first image information indicates that there is something to be cleaned in the target area; The cleaning module is used to adjust the cleaning parameters of the pool cleaning robot to the target cleaning parameters after it runs to the target area, so that the pool cleaning robot can clean the target area.

[0007] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0008] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0009] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0010] In this embodiment, the robot operates according to a cleaning path covering the pool bottom; it acquires first image information of the target area using a visual sensor; when the first image information indicates the presence of objects to be cleaned within the target area, the robot moves to that area; and upon reaching the target area, it adjusts the cleaning parameters of the pool cleaning robot to the target cleaning parameters, enabling the robot to clean the target area. This coupled control of visual recognition and cleaning parameters not only achieves efficient pool cleaning but also reduces waste of robot power resources, thereby effectively improving cleaning efficiency and effectiveness.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A flowchart illustrating a control method for a pool cleaning robot provided in an embodiment of this disclosure; Figure 2 A flowchart illustrating another control method for a pool cleaning robot provided in this embodiment of the present disclosure; Figure 3 This is a schematic diagram of the control device for a pool cleaning robot provided in an embodiment of the present disclosure. Detailed Implementation

[0013] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0014] As is known from the background art, pool cleaning robots typically employ uniform movement speed and constant pump pressure during cleaning or full coverage processes. This not only wastes the robot's power resources but also results in low cleaning efficiency. Therefore, this disclosure provides a control method, apparatus, and device for a pool cleaning robot. It achieves efficient collaborative pool cleaning through the coupled control of visual recognition and pump pressure control. Furthermore, a memory persistence mechanism maintains a high-pressure cleaning state for a preset duration after the visual sensor confirms the disappearance of the object to be cleaned. This not only reduces the waste of the robot's power resources but also effectively improves cleaning efficiency and cleaning effect.

[0015] The control method of the pool cleaning robot according to an embodiment of the present disclosure is described below with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart illustrating a control method for a pool cleaning robot provided in an embodiment of this disclosure. It can be applied to a pool cleaning robot, or to a device for controlling a pool cleaning robot. Figure 1 As shown, the method includes the following steps: Step 101: Follow the cleaning path for covering the bottom of the pool.

[0017] In this embodiment of the disclosure, the basic working state of the pool cleaning robot can be established first. For example, the pool bottom coverage cleaning path of the pool cleaning robot can be planned by a preset pool bottom coverage path planning algorithm to ensure that the robot can systematically traverse the entire area of ​​the pool bottom and avoid omissions and repeated cleaning.

[0018] Step 102: Acquire first image information of the target area using a visual sensor.

[0019] In this embodiment of the disclosure, a visual sensor can be used to actively perceive the area in front of the robot, and the existence and location of the object to be cleaned can be identified through image acquisition and real-time analysis. For example, the first image information can not only include the two-dimensional planar coordinates of the object to be cleaned, but also extract its contour, color, texture and other features through visual algorithms.

[0020] Step 103: If the first image information indicates that there is something to be cleaned in the target area, proceed to the target area.

[0021] In this embodiment of the disclosure, the target localization and path replanning mechanism of the robot (pool cleaning robot) can be triggered based on the visual recognition result (first image information). Once it is confirmed that there is an object to be cleaned, the robot can move towards the target area. The target area can be the area in front of the robot.

[0022] Step 104: After running to the target area, adjust the cleaning parameters of the pool cleaning robot to the target cleaning parameters so that the pool cleaning robot can clean the target area.

[0023] In some possible implementations, the cleaning parameters include at least one of pump pressure and operating speed.

[0024] In this embodiment of the disclosure, after the robot reaches the target area, the cleaning parameters of the pool cleaning robot can be set as the target cleaning parameters. For example, the cleaning parameters may include at least one of pump pressure and operating speed. Thus, by adjusting the pump pressure, operating speed, etc., a stronger water flow and a slower operating speed can be achieved to clean the stains.

[0025] In this embodiment, the robot operates according to a cleaning path covering the pool bottom; it acquires first image information of the target area using a visual sensor; when the first image information indicates the presence of objects to be cleaned within the target area, the robot moves to that area; and upon reaching the target area, it adjusts the cleaning parameters of the pool cleaning robot to the target cleaning parameters, enabling the robot to clean the target area. This coupled control of visual recognition and cleaning parameters not only achieves efficient pool cleaning but also reduces waste of robot power resources, thereby effectively improving cleaning efficiency and effectiveness.

[0026] In some possible implementations, when the cleaning parameters include pump pressure, adjusting the cleaning parameters of the pool cleaning robot to the target cleaning parameters includes: Based on the first image information, feature information of the object to be cleaned is extracted; wherein, the novel feature includes at least one of area feature, gray level distribution, and morphological feature. Based on the characteristic information, the cleaning difficulty level of the object to be cleaned is determined; different pump pressure values ​​correspond to different cleaning difficulty levels. After reaching the target area, the target pump pressure value is dynamically calculated based on the cleaning difficulty level; Adjust the pump pressure of the pool cleaning robot from the initial pump pressure value to the target pump pressure value.

[0027] In this embodiment, feature information of the object to be cleaned can also be extracted based on the first image information. For example, its area, grayscale distribution, and morphology can be extracted using image processing techniques. These features can be used to assess the cleaning difficulty level, with different levels corresponding to different pump pressure values. When the pool cleaning robot reaches the target area, it dynamically calculates the target pump pressure value suitable for the current cleaning task based on the preset mapping relationship between the difficulty level and the pump pressure value, and smoothly adjusts the pump pressure from the initial value to the target value. As an example, image processing techniques (such as OpenCV) can be used to process the first image information to extract the area features, grayscale distribution, and morphological features of the object to be cleaned. The area features can be obtained, for example, by counting the number of pixels after binarizing the image; the grayscale distribution can be analyzed using image histograms; and the morphological features can be analyzed by examining the object's boundaries, connectivity, and shape regularity (e.g., using the ratio of area to perimeter or aspect ratio to reflect complexity). Then, the area, grayscale distribution, and morphological features can be normalized and assigned corresponding weights (e.g., area weight 0.5, grayscale distribution weight 0.3, morphological feature weight 0.2), and the cleaning difficulty level can be calculated using a weighted summation formula. Then, based on the cleaning difficulty level, a linear mapping formula can be used to convert the difficulty level into a corresponding target pump pressure value, and the pump pressure value of the pool cleaning robot can be adjusted from the initial pump pressure value to the target pump pressure value. The linear mapping formula could be, for example: Ptarget =a× D level + b. Among them, Ptarget Indicates the target pump pressure value; D level This indicates the cleaning difficulty level; 'a' is a proportional coefficient, representing the increase in pump pressure for each increase of 1 in the cleaning difficulty level, for example, 1.75; 'b' is a constant, representing the baseline pump pressure when the difficulty level is 0. This allows for precise control of the cleaning effect, ensuring cleaning quality while avoiding excessive resource consumption, thereby further improving cleaning efficiency.

[0028] In a further possible implementation, adjusting the pump pressure of the pool cleaning robot from an initial pump pressure to a target pump pressure includes: The pump pressure of the pool cleaning robot is increased from the initial pump pressure to the target pump pressure at a preset rate.

[0029] The initial pump pressure value can be a set baseline operating parameter for the pool cleaning robot. The pool cleaning robot can perform cleaning according to the initial pump pressure value, which can be maintained at a low level to ensure energy efficiency and motion stability during the robot's regular cruise.

[0030] In this embodiment, the pump pressure can be adjusted gradually, smoothly increasing from an initial value to a target value at a preset rate. For example, the specific value of the preset rate can be dynamically adjusted based on factors such as the adhesion strength of the stain, the area of ​​the target region, and the robot's movement speed. As an example, for stains with high adhesion strength, the preset rate can be set relatively low to ensure sufficient water penetration and loosening of the stain; for stains with low adhesion strength, the preset rate can be appropriately increased to accelerate cleaning efficiency. This gradual adjustment method not only effectively avoids mechanical shock to the pump motor and piping system caused by sudden changes in pump pressure, reducing equipment wear and extending service life, but also helps the water flow gradually act on the stain surface, significantly improving the cleaning effect. Furthermore, adjusting the pump pressure according to the preset rate can prevent violent disturbance and turbidity of the pool water due to sudden increases in water pressure, ensuring the recognition accuracy of the visual sensor and maintaining the movement stability of the cleaning robot itself, making the overall cleaning process more controllable, efficient, and energy-saving.

[0031] In some possible implementations, the vision sensor includes at least one RGB camera positioned in the direction of the pool cleaning robot's movement.

[0032] In this embodiment of the disclosure, the visual sensor is designed to employ at least one RGB camera (Red Green Blue Camera), which can be installed at least in the forward direction of the pool cleaning robot so that the robot can acquire image information of the target area in front in real time during movement, thereby providing accurate data support for subsequent stain detection and cleaning path planning.

[0033] In some possible implementations, before adjusting the pump pressure of the pool cleaning robot from an initial pump pressure to a target pump pressure, the following steps are included: Acquire multi-dimensional feature information of the target area; the multi-dimensional feature information includes: real-time multi-angle image features acquired through visual sensors and historical cleaning data stored by the pool cleaning robot; Multi-angle image features are fused to determine the three-dimensional position and adhesion strength information of the object to be cleaned; Based on real-time multi-angle image features, historical cleaning data, and adhesion strength information, the target pump pressure value is determined through a fusion analysis model.

[0034] In this embodiment, multiple vision sensors mounted on a pool cleaning robot can acquire multi-dimensional feature information of the target area from different angles. This multi-dimensional feature information includes not only multi-angle image features but also historical cleaning data stored by the pool cleaning robot. The multi-dimensional feature information may include, for example, the color, shape, and size of stains, providing three-dimensional spatial information of the stains through multi-angle imaging. Historical cleaning data records the cleaning effects and pump pressure values ​​used under similar conditions (such as stain type, water temperature, and water quality), providing a reference for the current cleaning task and helping to predict the pump pressure setting for the current task. Then, an image processing algorithm can be used to fuse the real-time multi-angle image features acquired from different angles to generate three-dimensional position information and adhesion strength information of the object to be cleaned in the target area. Subsequently, a fusion analysis model can be used to comprehensively consider real-time multi-angle image features, historical cleaning data, and adhesion strength information to calculate the target pump pressure value most suitable for the current cleaning task. For example, the fusion analysis model is implemented using a machine learning algorithm. In this way, the pump pressure can be dynamically adjusted according to the specific conditions of the target area, achieving efficient and precise cleaning operations. This not only improves the cleaning effect but also optimizes energy utilization efficiency and extends the service life of the equipment.

[0035] In some possible implementations, the target pump pressure value is determined through a fusion analysis model, including: The first weight is obtained by geometric analysis of real-time multi-angle image features through fusion analysis model, the second weight is obtained by trend analysis of historical cleaning data, and the third weight is obtained by intensity analysis of adhesion strength information. The target pump pressure value is calculated based on the first weight, the second weight, and the third weight.

[0036] In this embodiment of the disclosure, the fusion analysis model can determine the target pump pressure value by integrating multiple feature information. For example, the fusion analysis model can perform geometric analysis on real-time multi-angle image features to assess the shape, size, and three-dimensional location of stains. These geometric features help understand the physical distribution of stains, thereby determining the difficulty of cleaning. For instance, large-area, irregularly shaped stains may require higher pump pressures for effective cleaning. Based on the results of the geometric analysis, the fusion analysis model can assign a weight value (i.e., a first weight) to represent the importance of the geometric features in determining the target pump pressure value. The magnitude of the weight value can reflect the complexity and cleaning difficulty of the stain. The fusion analysis model can also perform trend analysis on historical cleaning data to evaluate the pump pressure values ​​used in similar past cleaning tasks and their effectiveness; historical cleaning data can provide information to help predict the pump pressure setting for the current task. For example, if historical cleaning data shows that a certain type of stain is effectively cleaned at a specific pump pressure, the system can refer to this trend to adjust the current pump pressure setting. Based on the results of the trend analysis, the fusion analysis model can assign a weight value (i.e., a second weight) to represent the importance of historical cleaning data in determining the target pump pressure value. The fusion analysis model can also perform strength analysis on adhesion strength information to assess the degree of adhesion between stains and the pool wall. Adhesion strength information reflects the stubbornness of stains and is used to determine the pump pressure value required for cleaning. For example, stains with high adhesion strength may require higher pump pressure for effective removal. Based on the results of the strength analysis, the fusion analysis model can assign a weight value (i.e., a third weight) to indicate the importance of adhesion strength information in determining the target pump pressure value.

[0037] Subsequently, the fusion analysis model can comprehensively calculate the optimal target pump pressure value for the current cleaning task based on the first, second, and third weights. As an example, the target pump pressure value can be calculated by combining geometric analysis results, the first weight, historical data trend values, the second weight, adhesion strength values, and the third weight. In this way, the fusion analysis model can dynamically adjust the target pump pressure value according to the specific conditions of the target area, achieving efficient and precise cleaning operations. This not only improves cleaning effectiveness but also optimizes energy utilization efficiency and extends equipment lifespan.

[0038] In further possible implementations, it also includes: During the cleaning process of the target area, the pump's operating parameters are acquired in real time; these parameters include at least one of the following: operating current and suction inlet flow rate. Determine whether the material to be cleaned has been effectively removed based on the pump's operating parameters; If the material to be cleaned is not effectively removed, increase the target pump pressure or extend the cleaning time.

[0039] In this embodiment, during the cleaning of the target area, pump operating parameters, such as operating current and inlet flow rate, can be monitored in real time. Based on these parameters, it can be determined whether the material to be cleaned has been effectively removed. For example, if an abnormal increase in operating current and a decrease in inlet flow rate are detected, it may mean that the material has not been effectively removed. In this case, the target pump pressure can be increased to enhance suction, or the cleaning time can be extended to ensure thorough removal of the material from the target area. Thus, this dynamic adjustment mechanism can further improve cleaning efficiency and avoid resource waste.

[0040] In some possible implementations, where the cleaning parameters include operating speed, adjusting the cleaning parameters of the pool cleaning robot to target cleaning parameters includes: During the cleaning process of the target area, the operating speed of the pool cleaning robot is adjusted to the target operating speed.

[0041] In this embodiment, when cleaning the target area, the operating speed of the pool cleaning robot can be reduced to allow it to stay in the target area for a longer time, enabling the pump pressure adjustment to be more effective and thus more efficiently removing dirt and improving cleaning quality. Simultaneously, the coordinated adjustment of operating speed and pump pressure can also prevent incomplete cleaning caused by excessively fast movement, as well as resource waste or equipment overload due to excessively high or low pump pressure, achieving a balanced optimization of cleaning efficiency and equipment performance.

[0042] In some possible implementations, adjusting the operating speed of the pool cleaning robot to a target operating speed includes: Based on the first image information, determine the distribution characteristics of the object to be cleaned; wherein, the distribution characteristics include at least one of coverage area and distribution density; Determine the target running speed based on the distribution characteristics; When cleaning the target area, adjust the operating speed of the pool cleaning robot to the target operating speed.

[0043] In this embodiment of the disclosure, the operating speed of the pool cleaning robot can be dynamically adjusted according to the distribution characteristics (such as coverage area and distribution density) of the object to be cleaned. For example, the distribution characteristics are inversely proportional to the target operating speed; the larger the coverage area or the higher the distribution density, the slower the pool cleaning robot needs to clean. At least one of the coverage area and distribution density of the object to be cleaned can be determined based on the first image information, and then the target operating speed can be determined based on the coverage area and distribution density. For example, a weighted normalization formula can be used to determine the target operating speed, assuming an initial speed of 10 cm / s, a maximum coverage area of ​​100 cm², and a maximum distribution density of 1.0 cm. -², each with a weight of 0.5. If the current coverage area is 50 cm², the distribution density is 0.2 cm. - ², the normalized coverage area is 0.5, and the distribution density is 0.2. Substituting into the following formula, the target velocity is calculated to be approximately 6.5 cm / s.

[0044]

[0045] in, Vtarget It is the target speed; Vinitial It is the initial velocity; w 1 and w 2 is the weighting coefficient; S is the coverage area; Smax It is the maximum coverage area; D It is the distribution density. Dmax It is the maximum distribution density; It is a constant; Vmax That is the maximum speed; Vmin That is the minimum speed.

[0046] When cleaning the target area, the pool cleaning robot's operating speed is adjusted to the target speed. Understandably, the initial operating speed was higher than the target speed, for example, it could be a pre-set initial speed. In this way, by dynamically adjusting the strategy, the cleaning path and dwell time can be optimized, improving cleaning quality, reducing unnecessary repetitive work, thereby increasing overall cleaning efficiency and reducing energy consumption.

[0047] In some possible implementations, it also includes: Second image information of the target area is acquired using a visual sensor; If the second image information indicates that there is no object to be cleaned in the target area, the pump pressure is maintained at the target pump pressure for a preset time and the cleaning path covering the bottom of the pool continues to be run. Adjust the pump pressure from the target pump pressure to the initial pump pressure.

[0048] In this embodiment, after pressurized cleaning is completed, the vision sensor can re-capture images of the target area, i.e., second image information. Analyzing the second image information can determine whether the object to be cleaned in the target area has been removed. The second image information serves as an objective basis for cleaning assessment, providing closed-loop feedback for subsequent decisions. If the second image information indicates that there is no object to be cleaned in the target area, i.e., visual confirmation that the stain has disappeared, the high-pressure state (pump pressure value is the target pump pressure value) can be maintained for a preset duration. This memory-based maintenance mechanism effectively prevents stain escape and cleaning interruption, thereby further ensuring the thorough removal of stubborn stains with high adhesion strength. Simultaneously, the robot can continue to operate along the bottom-covering cleaning path to avoid work stoppages and achieve synergistic optimization of efficient coverage and focused cleaning. After completing the cleaning of the target area and after the preset memory-based maintenance period, the robot can reduce the pump pressure value back to the initial pump pressure value to save energy. In this way, the pressure callback mechanism can form a complete control loop for the robot, ensuring the continuity of the overall cleaning process and the stability of system operation. Through the coupled control of visual recognition and pump pressure control, not only can efficient coordination of pool cleaning be achieved, but also the waste of robot power resources can be reduced, thereby effectively improving cleaning efficiency and cleaning effect. Moreover, through the memory persistence mechanism, after the visual sensor confirms that the object to be cleaned has disappeared, the high-pressure cleaning state can be maintained for a preset time, thereby further improving cleaning efficiency and cleaning effect.

[0049] In some possible implementations, if the second image information indicates that there is no object to be cleaned in the target area, the method further includes: Obtain the current location information of the pool cleaning robot; If the distance between the current location and the target area is less than a preset distance, the auxiliary cleaning mode is triggered; The corners and edges of the target area are cleaned using an auxiliary cleaning device.

[0050] When the auxiliary cleaning device is used to clean the corners of the target area, the pool cleaning robot remains in its current position.

[0051] In this embodiment, after the visual sensor confirms that the main stains in the target area have been removed (i.e., the second image information indicates that there is no object to be cleaned in the target area), the current position information of the cleaning robot can be obtained, for example, through the robot's built-in positioning system, to ensure that the robot can accurately determine its relative position to the target area. Then, the distance between the current position information and the target area can be calculated to determine whether the distance is less than a preset distance. The specific value of the preset distance can be determined based on the effective working range and cleaning efficiency of the auxiliary cleaning device. For example, if the distance between the current position information and the target area is less than the preset distance, it means that the robot is within the effective coverage range of the auxiliary cleaning device (e.g., a robotic arm), and the auxiliary cleaning mode can be triggered for auxiliary cleaning. When the distance between the current position and the target area is less than the preset distance, the auxiliary cleaning mode can be triggered. For example, the auxiliary cleaning mode can be a robotic arm cleaning mode. The cleaning mode of the robotic arm can include actions such as extension, rotation, and cleaning, which can accurately clean corner areas and stubborn stains; the cleaning head of the auxiliary cleaning device (such as a robotic arm) can be equipped with a brush, a nozzle, or other cleaning tools to adapt to different cleaning needs. Once the assisted cleaning mode is triggered, the assisted cleaning device extends to the corners of the target area to perform auxiliary cleaning. Understandably, the cleaning actions of the assisted cleaning device can be adjusted based on preset programs or real-time feedback to ensure cleaning effectiveness. For example, for stubborn stains, the assisted cleaning device can increase cleaning intensity or adjust the angle of the cleaning tools. Understandably, during the assisted cleaning process, the pool cleaning robot remains in its current position. In this way, not only can main stains be effectively removed, but the assisted cleaning device can also precisely clean corners and stubborn stains, ensuring comprehensive and efficient pool cleaning, thereby further improving the cleaning effect.

[0052] In some possible implementations, auxiliary cleaning devices are used to perform auxiliary cleaning of the corner areas of the target area, including: Increase the pump pressure from the target pump pressure to the working pressure of the auxiliary cleaning device; wherein the working pressure of the auxiliary cleaning device is greater than the target pump pressure. Control the auxiliary cleaning device to extend and position it in the corner area, and maintain the pump pressure value at the working pressure value of the auxiliary cleaning device for a preset duration; After the auxiliary cleaning device has completed the cleaning process, the pump pressure will be restored to the initial pump pressure value.

[0053] In this embodiment, when the auxiliary cleaning device is used to clean the corner areas of the target area, the pump pressure can be increased from the current target pump pressure to a higher working pressure value before the auxiliary cleaning device begins cleaning. Furthermore, the auxiliary cleaning device can be controlled to extend from its initial position and precisely position itself at the corner of the target area. After reaching the corner area, the pump pressure can be maintained at the working pressure value for a preset duration. After the auxiliary cleaning device completes the cleaning process, the pump pressure can be restored to its initial value. Thus, the auxiliary cleaning function can effectively handle stubborn stains in corner areas, ensuring comprehensive and efficient pool cleaning. This not only further improves the cleaning effect but also optimizes energy utilization efficiency.

[0054] In some possible implementations, maintaining the pump pressure value at the target pump pressure value for a preset duration includes: The target area is monitored using a visual sensor while maintaining the pump pressure. If an object to be cleaned is detected in the target area within the preset time, the preset time is extended and the pump pressure is maintained at the target pump pressure value.

[0055] In this embodiment, after the pump pressure is adjusted to the target pump pressure, this pump pressure can be maintained for a preset duration. During the maintenance of the pump pressure, the vision sensor can continuously monitor the target area and acquire image information of the target area in real time to confirm whether there are still unremoved stains in the target area. For example, the vision sensor can use image analysis algorithms to identify whether there are items to be cleaned in the target area. If stains are still detected in the target area within the preset duration, it can be determined that these stains may require a longer cleaning time. In this case, the preset duration can be automatically extended, and the pump pressure can continue to be maintained at the target pump pressure. In this way, the cleaning time can be intelligently adjusted to further ensure that the stains in the target area are thoroughly removed, thereby not only improving the cleaning effect but also avoiding the problem of stain residue caused by insufficient cleaning time.

[0056] To make the methods provided in this disclosure clearer, the following examples will be used for illustration.

[0057] In this embodiment, the pool cleaning robot can run a cleaning path covering the pool bottom and set an initial water pump pressure; when it detects trash ahead, it continues the original path and increases the pump pressure; when it detects that the trash has disappeared (entered a blind zone), it continues the original path, runs at high pump pressure for N seconds, and then restores the pump pressure to the initial value. Combined with... Figure 2 Specific implementations of this method may include: 1. Run the cleaning path to cover the bottom of the pool and set the initial water pump pressure (initial pump pressure value). 2. Once trash (items to be cleaned) is detected ahead (target area), continue along the existing path (cleaning path covering the bottom of the pool). 3. When the pump reaches the identified waste location (target area) along the prescribed path, increase the pump pressure (e.g., adjust to the target pump pressure value); 3. If the garbage is detected to have disappeared (entered a blind zone), continue the original path and maintain high pump pressure for N seconds. After that, restore the pump pressure to the initial value (initial pump pressure value).

[0058] During the process of adjusting the pump pressure, the pump pressure is gradually increased after reaching the location of the waste; the waste is identified by a vision sensor, which can be one or more RGB cameras or different vision sensors.

[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0060] According to embodiments of this disclosure, a control device for a pool cleaning robot is also provided. For example, Figure 3 This is a schematic diagram of the structure of a control device for a swimming pool cleaning robot provided in an embodiment of the present disclosure. The control device 300 for the swimming pool cleaning robot includes: The setting module 310 is used to operate according to the cleaning path covering the bottom of the pool; The first acquisition module 320 is used to acquire first image information of the target area through a visual sensor; The first running module 330 is used to run to the target area when the first image information indicates that there is something to be cleaned in the target area; The cleaning module 340 is used to adjust the cleaning parameters of the pool cleaning robot to the target cleaning parameters after running to the target area, so that the pool cleaning robot can clean the target area.

[0061] Furthermore, the cleaning parameters include at least one of pump pressure and operating speed.

[0062] Furthermore, the cleaning module 340 is used for: Based on the first image information, feature information of the object to be cleaned is extracted; wherein, the feature information includes at least one of area features, grayscale distribution, and morphological features; Based on the aforementioned feature information, the cleaning difficulty level of the object to be cleaned is determined; wherein, different pump pressure values ​​correspond to different cleaning difficulty levels. After reaching the target area, the target pump pressure value is dynamically calculated based on the cleaning difficulty level; Adjust the pump pressure of the pool cleaning robot from the initial pump pressure to the target pump pressure.

[0063] Furthermore, the cleaning module 340 is also used for: During the cleaning process of the target area, the operating speed of the pool cleaning robot is adjusted to the target operating speed.

[0064] Furthermore, the cleaning module 340 is also used for: Based on the first image information, the distribution characteristics of the object to be cleaned are determined; wherein, the distribution characteristics include at least one of coverage area and distribution density; Based on the distribution characteristics, the target running speed is determined; When cleaning the target area, the operating speed of the pool cleaning robot is adjusted to the target operating speed.

[0065] Furthermore, it also includes: The parameter acquisition module is used to acquire pump operating parameters in real time during the cleaning process of the target area; wherein the pump operating parameters include at least one of the operating current and the suction inlet flow rate. The suction determination module is used to determine whether the object to be cleaned has been effectively suctioned out based on the pump body operating parameters; The booster module is used to increase the target pump pressure or extend the cleaning time if the object to be cleaned is not effectively removed.

[0066] Furthermore, it also includes: The second acquisition module is used to acquire second image information of the target area through the visual sensor; The second operation module is used to maintain the pump pressure value at the target pump pressure value for a preset duration when the second image information indicates that there is no object to be cleaned in the target area, and to continue to operate according to the bottom cleaning path. An adjustment module is used to adjust the pump pressure value from the target pump pressure value to the initial pump pressure value.

[0067] Furthermore, it also includes: The location acquisition module is used to acquire the current location information of the pool cleaning robot; The auxiliary cleaning module is used to trigger an auxiliary cleaning mode when the distance between the current location information and the target area is less than a preset distance; An auxiliary cleaning module is used to perform auxiliary cleaning of the corner areas of the target area using an auxiliary cleaning device; wherein, when the corner areas of the target area are being cleaned using the auxiliary cleaning device, the pool cleaning robot maintains its current position.

[0068] Furthermore, the auxiliary cleaning module is used for: The pump pressure is increased from the target pump pressure to the working pressure of the auxiliary cleaning device; wherein the working pressure of the auxiliary cleaning device is greater than the target pump pressure. The auxiliary cleaning device is controlled to extend and position itself to the corner area, and the pump pressure is maintained at the working pressure value of the auxiliary cleaning device for the preset duration. After the auxiliary cleaning device has completed the cleaning process, the pump pressure value will be restored to the initial pump pressure value.

[0069] Furthermore, the second operating module is used for: The target area is monitored by the visual sensor while maintaining the pump pressure value; If an object to be cleaned is detected in the target area within the preset time period, the preset time period is extended and the pump pressure value is maintained at the target pump pressure value.

[0070] It should be noted that the description of the features of the control device of the pool cleaning robot in the corresponding embodiment can be found in the relevant description of the control method of the pool cleaning robot in the corresponding embodiment, and will not be repeated here.

[0071] Embodiments of this disclosure also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0072] Embodiments of this disclosure also provide a computer-readable storage medium storing a computer program configured to perform the steps in any of the above method embodiments when executed.

[0073] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0074] Embodiments of this disclosure also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0075] Embodiments of this disclosure also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0076] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0077] The control method for a swimming pool cleaning robot provided in this disclosure has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this disclosure. The descriptions of the embodiments above are only for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make several improvements and modifications to this disclosure without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this disclosure.

Claims

1. A control method for a swimming pool cleaning robot, characterized in that, include: Operate according to the cleaning path covering the bottom of the pool; First image information of the target area is acquired using a visual sensor; If the first image information indicates that there is something to be cleaned in the target area, proceed to the target area; After reaching the target area, the cleaning parameters of the pool cleaning robot are adjusted to the target cleaning parameters so that the pool cleaning robot can clean the target area.

2. The method according to claim 1, characterized in that, The cleaning parameters include at least one of pump pressure and operating speed.

3. The method according to claim 2, characterized in that, When the cleaning parameters include pump pressure, adjusting the cleaning parameters of the pool cleaning robot to the target cleaning parameters includes: Based on the first image information, feature information of the object to be cleaned is extracted; wherein, the feature information includes at least one of area features, grayscale distribution, and morphological features; Based on the aforementioned feature information, the cleaning difficulty level of the object to be cleaned is determined; wherein, different pump pressure values ​​correspond to different cleaning difficulty levels. After reaching the target area, the target pump pressure value is dynamically calculated based on the cleaning difficulty level; Adjust the pump pressure of the pool cleaning robot from the initial pump pressure to the target pump pressure.

4. The method according to claim 2, characterized in that, When the cleaning parameters include operating speed, adjusting the cleaning parameters of the pool cleaning robot to target cleaning parameters includes: During the cleaning process of the target area, the operating speed of the pool cleaning robot is adjusted to the target operating speed.

5. The method according to claim 4, characterized in that, Adjusting the operating speed of the pool cleaning robot to the target operating speed includes: Based on the first image information, the distribution characteristics of the object to be cleaned are determined; wherein, the distribution characteristics include at least one of coverage area and distribution density; Based on the distribution characteristics, the target running speed is determined; When cleaning the target area, the operating speed of the pool cleaning robot is adjusted to the target operating speed.

6. The method according to claim 3, characterized in that, Also includes: During the cleaning process of the target area, the pump's operating parameters are acquired in real time; wherein, the pump's operating parameters include at least one of the operating current and the inlet flow rate. Based on the pump's operating parameters, determine whether the object to be cleaned has been effectively removed; If the object to be cleaned is not effectively removed, increase the target pump pressure or extend the cleaning time.

7. The method according to claim 3, characterized in that, Also includes: The visual sensor acquires second image information of the target area; If the second image information indicates that there is no object to be cleaned in the target area, the pump pressure is maintained at the target pump pressure for a preset duration, and the cleaning path covering the bottom of the pool continues to be followed. Adjust the pump pressure from the target pump pressure to the initial pump pressure.

8. The method according to claim 7, characterized in that, The method further includes, when the second image information indicates that there is no object to be cleaned in the target area: Obtain the current location information of the pool cleaning robot; If the distance between the current location information and the target area is less than a preset distance, the auxiliary cleaning mode is triggered; The corner areas of the target area are cleaned using an auxiliary cleaning device; while the corner areas of the target area are being cleaned using the auxiliary cleaning device, the pool cleaning robot remains in its current position.

9. The method according to claim 8, characterized in that, The auxiliary cleaning process for the corner areas of the target area using an auxiliary cleaning device includes: The pump pressure is increased from the target pump pressure to the working pressure of the auxiliary cleaning device; wherein the working pressure of the auxiliary cleaning device is greater than the target pump pressure. The auxiliary cleaning device is controlled to extend and position itself in the corner area, and the pump pressure is maintained at the working pressure value of the auxiliary cleaning device for the preset duration. After the auxiliary cleaning device has completed the cleaning process, the pump pressure value will be restored to the initial pump pressure value.

10. The method according to claim 7, characterized in that, The duration for which the pump pressure is maintained at the target pump pressure value is preset includes: The target area is monitored by the visual sensor while maintaining the pump pressure value; If an object to be cleaned is detected in the target area within the preset time period, the preset time period is extended and the pump pressure value is maintained at the target pump pressure value.

Images