Robot-based swimming pool cleaning method and apparatus, and robot
Patent Information
- Application Number
- PCT/CN2025/144757
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-02-21
- Filing Date
- 2025-12-23
- Publication Date
- 2026-08-27
Smart Images
Figure CN2025144757_27082026_PF_FP_ABST
Abstract
Description
A robot-based swimming pool cleaning method, device, and robot
[0001] Cross-references to related applications
[0002] This application claims priority to Chinese Patent Application No. 202510196854X, filed on February 21, 2025, entitled "A Robot-Based Pool Cleaning Method, Apparatus and Robot", the entire contents of which are incorporated herein by reference. Technical Field
[0003] This application relates to the field of machine control technology, specifically to a robot-based method, apparatus, and robot for cleaning swimming pools. Background Technology
[0004] Existing pool cleaning robots consist of a shell, two tracks, two adjustable-speed motors, an adsorption motor, and a filter. The motors on the robot drive the blades to rotate, causing the sediment at the bottom of the cleaning robot to flow through the filter with the water and be discharged from the top. At the same time, a reverse adsorption force is formed, which can clean the sediment at the bottom of the pool, or allow it to be adsorbed onto the pool wall through different float ratios.
[0005] When cleaning a swimming pool, the robot usually moves to one side of the pool wall, then turns around and returns along a route parallel to the original path. When it reaches the other boundary of the pool, it turns again. However, the shape of the pool varies greatly, and this path may not be able to cover all areas, resulting in cleaning blind spots and failure to complete the designated task. In some cases, when there are large obstacles in the work area, the pool cleaning robot cannot automatically avoid or report them, leading to work failure. Summary of the Invention
[0006] In view of this, this application provides a robot-based swimming pool cleaning method, apparatus and robot to solve the problems of blind spots in swimming pool cleaning and the inability to automatically avoid obstacles during operation, which leads to operation failure.
[0007] In a first aspect, this application provides a robot-based pool cleaning method applied to a robot equipped with a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment surrounding the robot, and the robot pose acquisition device is used to determine the robot's pose. The method includes: the robot entering the water and acquiring a first entry position; iteratively performing a map building operation until the robot returns to the first entry position during the map building operation, thus completing the pool map; the map building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall, wherein the target pool wall satisfies the following conditions: the robot has not walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest; during the robot's walking along the direction parallel to the target pool wall, constructing a pool map based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory; and the robot cleaning the pool based on the completed pool map.
[0008] The robot-based pool cleaning method provided in this application involves a robot entering the water and acquiring its first entry position. It iteratively performs a map-building operation until the robot returns to the first entry position during its movement through the map-building operation, thus completing the pool map. The map-building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall. The target pool wall satisfies the following conditions: the robot has not previously walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest. During the robot's movement along the target pool wall, a pool map is constructed based on the surrounding pool environment scanned by a sonar device and the robot's walking trajectory. The robot then cleans the pool based on the constructed pool map. This method enables the robot to clean based on the sonar-built pool map and automatically avoid obstacles during cleaning. It can comprehensively cover all corners of the pool, avoiding cleaning blind spots, improving cleaning efficiency, and promptly avoiding various obstacles in the pool, ensuring the success of the cleaning operation.
[0009] In one optional implementation, the robot stores a pool map set, which includes multiple pre-recorded pool maps. The robot is equipped with a camera device. Before the robot enters the water, the method further includes: acquiring a first image captured by the camera device; determining whether a pool exists in the first image; if a pool exists in the first image, identifying all pool edges and determining whether all pool edges can form a closed curve; if all pool edges can form a closed curve, acquiring the attribute information of the pool and matching the attribute information of the pool with each pool map in the pool map set, wherein the attribute information of the pool includes at least geometric information and obstacle information; if no match is found with any pool map in the pool map set, the robot enters the water, acquires a first entry position, and iteratively performs a map building operation until the robot is again at the first entry position during the map building operation, thus completing the construction of the pool map.
[0010] In an optional implementation, if all pool edges do not form closed curves, the method further includes: identifying a first direction of the pool edges that are not fully displayed in the first image, and recording the position of the intersection point between the pool edges and the edges of the first image; rotating the robot to the first direction by a preset angle, and controlling the camera device to capture a second image; obtaining the pool edges displayed in the first direction from the second image based on the position of the intersection point, and stitching the pool edges displayed in the first direction to the first image based on the position of the intersection point to obtain an image in which all pool edges form closed curves, and then performing the step of obtaining the attribute information of the pool.
[0011] In one optional implementation, the robot is equipped with a camera device. The robot cleans the pool based on a constructed pool map, or, if the pool's attribute information matches any pool map in the pool map set, it cleans the pool based on the matched pool map. This includes: the robot walking and cleaning along a preset path, recording the current robot walking direction, and capturing a third image through the camera device; identifying whether there is first pool debris in the third image; if there is first pool debris, marking the location of the first debris on the pool map, rotating based on the direction pointing to the first pool debris, walking to the marked location of the first debris, cleaning the debris, and accumulating the number of first pool debris cleaning operations; the robot returning to the location where the third image was captured, and controlling the camera device to capture the image again, determining whether there is still first pool debris at the location of the first debris; if there is still first pool debris at the location of the first debris, and the accumulated number of first pool debris cleaning operations reaches a preset operation threshold, then marking the location of the first pool debris on the pool map; the robot walking and cleaning along a preset path based on the location of the captured third image and the recorded current robot walking direction.
[0012] In one optional implementation, if there is still first pool trash at the first trash location, but the accumulated number of first pool trash cleaning operations has not reached the preset operation count threshold, then the process returns to the steps of controlling the robot to rotate and walk to the marked trash location based on the direction pointing to the first pool trash to clean the trash, and accumulating the number of first pool trash cleaning operations, until there is no first pool trash at the first trash location, or the accumulated number of first pool trash cleaning operations reaches the preset operation count threshold.
[0013] In one alternative implementation, the cleaned areas are marked on the pool map as the robot cleans based on the pool map.
[0014] In one optional implementation, before the robot walks along a preset path and performs cleaning, the method further includes: acquiring the pool environment around the robot scanned by a sonar device at the current location; acquiring the current robot pose determined by a robot pose acquisition device; comparing the pool environment around the robot scanned by the sonar device with the pool environment corresponding to the current robot pose on a pool map to determine whether the current robot pose is accurate; if the current robot pose is determined to be accurate, then performing the steps of the robot walking along the preset path and performing cleaning.
[0015] In one optional implementation, the cleaning device installed on the robot is used to clean the pool in real time during the robot's movement. The method further includes: controlling the cleaning device to clean and marking the cleaned areas while the robot is walking and building a pool map; and after the pool map is built, the robot cleans the pool based on the unmarked areas in the completed pool map.
[0016] In one optional implementation, during the robot's movement along a direction parallel to the target pool wall, the method further includes: recording the current robot's walking direction and capturing a fourth image via a camera device; identifying whether second pool debris exists in the fourth image; if second pool debris exists, marking the location of the second debris on the pool map, and controlling the robot to rotate and walk to the marked location of the second debris based on the direction pointing to the second pool debris to perform debris cleaning, and accumulating the number of second pool debris cleaning operations; the robot returning to the location where the fourth image was captured, and controlling the camera device to capture the image again to determine whether second pool debris still exists; if second pool debris still exists at the location of the fourth debris, and the accumulated number of second pool debris cleaning operations reaches a preset operation threshold, then marking the location of the second pool debris on the constructed pool map; the robot, based on the location where the fourth image was captured and the recorded current robot walking direction, controlling the robot to walk along a direction parallel to the target pool wall and controlling the cleaning device to perform cleaning.
[0017] Secondly, this application provides a robot-based pool cleaning device applied to a robot. The robot is equipped with a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The device includes: a pool map building module, used for the robot to enter the water and obtain a first entry position, iteratively performing a map building operation until the robot is back at the first entry position during the map building operation, thus completing the pool map. The map building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall, wherein the target pool wall satisfies the following conditions: the robot has not walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest; during the robot's walking along the direction parallel to the target pool wall, constructing a pool map based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory; and a pool cleaning module, used for the robot to clean the pool based on the completed pool map.
[0018] Thirdly, this application provides a robot, which includes a controller, a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The controller includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the robot-based pool cleaning method of the first aspect or any corresponding embodiment described above. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0020] Figure 1 is a schematic flowchart of a robot-based pool cleaning method according to an embodiment of this application;
[0021] Figure 2 is a flowchart illustrating the construction of a swimming pool map according to an embodiment of this application;
[0022] Figure 3 is a flowchart illustrating another robot-based pool cleaning method according to an embodiment of this application;
[0023] Figure 4 is an example diagram of the robot's operation logic before entering the water according to an embodiment of this application;
[0024] Figure 5 is a flowchart illustrating the cleaning process based on a pool map according to an embodiment of this application;
[0025] Figure 6 is a schematic diagram of the structure of a robot according to an embodiment of this application;
[0026] Figure 7 is a structural block diagram of a robot-based pool cleaning device according to an embodiment of this application;
[0027] Figure 8 is a schematic diagram of the hardware structure of the controller according to an embodiment of this application. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0029] According to an embodiment of this application, a robot-based pool cleaning method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0030] This embodiment provides a robot-based pool cleaning method, applied to a robot including the robot itself and a control panel. The user can observe the robot's operating status and control its movement, rotation, and stopping via the control panel. The robot is equipped with a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device scans the pool environment around the robot, and the robot pose acquisition device determines the robot's pose. This embodiment uses a sonar device capable of 360-degree wake-up scanning to scan and acquire the pool environment around the robot. Through multiple movements and multi-point scans, a complete map is built. The choice of the robot pose acquisition device is not limited; for example, a gyroscope, GPS, or radar can be selected. Devices such as a gyroscope are used to determine the robot's posture in the pool. Taking a gyroscope as an example, the robot's posture and direction of movement can be confirmed by the gyroscope, and then the robot's movement distance and trajectory can be determined by the encoder. The robot can also walk by the cooperation of motors, gears and tracks. Two dedicated DC motors and servo motors can be set up to facilitate the robot's turning, forward and backward movements. The cleaning device can include a water pump motor and a filter screen. The water pump motor pumps water, giving the robot a downward pressure. The water pumping action of the water pump motor allows the water at the bottom of the machine to flow through the filter screen, achieving the purpose of filtering dirt from the bottom of the pool. This is only an example and is not limited. Figure 1 is a flowchart of a robot-based pool cleaning method according to an embodiment of this application. As shown in Figure 1, the process includes the following steps:
[0031] In step S101, the robot enters the water and obtains the first entry position. Iteratively, the map building operation is performed until the robot returns to the first entry position while walking through the map building operation, and the pool map is completed.
[0032] The map building operation includes: when the robot detects the target pool wall, controlling the robot to walk along a direction parallel to the target pool wall, wherein the target pool wall meets the following conditions: the robot has not walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest; during the robot's walking along the direction parallel to the target pool wall, a pool map is built based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory.
[0033] As shown in Figure 2, the robot in this embodiment enters the pool and prepares to walk and build a pool map. At this time, the robot's first entry position can be obtained in advance through the gyroscope. The robot can obtain the distance between the robot and the relative pool wall based on different rotation directions of the current position through the sonar device. Then, the specific rotation direction of the robot is determined through the gyroscope data. Then, the distance between the robot and the relative pool wall based on different rotation directions of the current position can be obtained. Generally, the vertical distance between the robot's position and the relative pool wall is the shortest. Therefore, the pool wall with the shortest vertical distance to the robot's position and which the robot has not yet walked on can be selected as the target pool wall.
[0034] In this embodiment, after the robot rotates its direction to be parallel to the target pool wall, it can be controlled to walk along a direction parallel to the target pool wall. For example, if the pool wall is a straight line, the robot's trajectory is also a straight line, meaning the two straight lines are parallel. This is just an example. During the robot's movement, the sonar device has its own rotating mechanism (360-degree rotation scanning) to scan the pool environment (including but not limited to the edge of the pool wall and pool obstacles), thereby constructing a pool map. The robot's walking trajectory can also be depicted in the pool map. Different colors can be used to distinguish between the pool wall and the robot's walking trajectory, so as to realize the effect of connecting personal devices such as mobile phones and computers with robot control using Internet technology, allowing users to clearly obtain the robot's operating status. Among them, the walking... The trajectory can be determined by calculating the robot's walking distance and direction. The walking distance is calculated by judging the number of motor rotations before and after movement between two points. When the walking motor is running, there is a signal line FG. The motor shaft will output four rising pulses for each rotation. The MCU will count these pulses, and the robot's walking count value will change. The walking distance is obtained by multiplying the change in the counter by a ratio, which is determined by the reduction ratio and the gear transmission ratio in the structure. The robot repeats the above steps of rotating the robot's direction to be parallel to the target pool wall, walking in a direction parallel to the target pool wall, and building a pool map using the sonar device, until the robot's position in the map building process is equal to the first entry position, then the pool map construction is completed.
[0035] In step S102, the robot cleans the pool based on the completed pool map.
[0036] After constructing the pool map, the robot in this embodiment can walk along a preset planned path. During the robot's movement, the pool can be cleaned using a cleaning device.
[0037] The robot-based pool cleaning method provided in this application involves a robot entering the water and acquiring its first entry position. It iteratively performs a map-building operation until the robot returns to the first entry position during its movement through the map-building operation, thus completing the pool map. The map-building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall. The target pool wall satisfies the following conditions: the robot has not previously walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest. During the robot's movement along the target pool wall, a pool map is constructed based on the surrounding pool environment scanned by a sonar device and the robot's walking trajectory. The robot then cleans the pool based on the constructed pool map. This method enables the robot to clean based on the sonar-built pool map and automatically avoid obstacles during cleaning. It can comprehensively cover all corners of the pool, avoiding cleaning blind spots, improving cleaning efficiency, and promptly avoiding various obstacles in the pool, ensuring the success of the cleaning operation.
[0038] This embodiment provides a robot-based pool cleaning method applied to a robot. Figure 3 is a flowchart of the robot-based pool cleaning method according to an embodiment of this application. As shown in Figure 3, the process includes the following steps:
[0039] Step S301: Before entering the water, the robot acquires a first image captured by the camera device and determines whether a swimming pool exists in the first image. If a swimming pool exists in the first image, all pool edges are identified, and it is determined whether all pool edges can form a closed curve. If all pool edges can form a closed curve, the attribute information of the pool is acquired, and the attribute information of the pool is matched with each pool map in the pool map set. The attribute information of the pool includes at least geometric information and obstacle information. If the matching with each pool map in the pool map set fails, the robot enters the water and acquires the first entry position. The map building operation is iteratively performed until the robot is back at the first entry position during the map building operation, thus completing the construction of the pool map.
[0040] The robot stores a set of pool maps, which includes multiple pre-recorded pool maps, and is equipped with a camera device.
[0041] As shown in Figure 4, before entering the water, the robot in this embodiment can use a camera device to capture a first image, and then analyze the first image to identify whether a swimming pool exists in the first image. If the swimming pool is not present in the first image, the robot can rotate or walk at a suitable angle until the captured image includes the swimming pool. After the swimming pool is included in the captured first image, all the edges of the swimming pool can be identified, and it can be determined whether all the edges can form a closed curve (indicating whether the swimming pool in the image is complete). If all the edges can form a closed curve, it means that the swimming pool in the image is complete, and the attribute information of the swimming pool in the image can be identified and analyzed. The attribute information includes, but is not limited to, the geometric information of the swimming pool (including size, etc.). The robot matches the determined pool attributes (size and shape) with each pool map in its stored pool map set (including but not limited to matching pool size, shape, and obstacle information). These pool maps can be historically constructed maps by the robot or user-created maps, as an example only. If the robot fails to match any of the pool maps in the set, it enters a mapless cleaning process, i.e., executes the aforementioned pool map construction implementation. If it successfully matches any pool map in the set, the robot performs the pool cleaning operation based on the matched map.
[0042] Before entering the water, the robot of this application first uses a camera device to photograph and identify the swimming pool, and then compares the identified swimming pool information with its own stored pool map set. If it fails to match any of the maps in the pool map set, it enters a mapless cleaning process. If it successfully matches a swimming pool map, it can directly clean based on the successfully matched swimming pool map, which broadens the robot's application scenarios and ensures that the robot can complete the cleaning operation efficiently and stably.
[0043] In one optional implementation, if it is determined that all pool edges do not form closed curves, the robot identifies a first direction of the pool edge that is not fully displayed in the first image and records the position of the intersection point between the pool edge and the edge of the first image; the robot rotates to the first direction by a preset angle and controls the camera device to capture a second image; based on the position of the intersection point, the pool edge corresponding to the first direction displayed is obtained from the second image, and the pool edge corresponding to the first direction displayed is stitched into the first image based on the position of the intersection point to obtain an image in which all pool edges form closed curves, and then the step of obtaining the attribute information of the pool is performed.
[0044] In this embodiment, the robot identifies the captured first image and finds that all pool edges do not form closed curves, meaning that a certain pool edge is not fully displayed in the first image. It then determines the first direction of the pool edge not fully displayed in the first image and records the position of the intersection point between the pool edge and the edge of the first image. For example, if the first image is captured and calculations show that the pool edge on the left is complete, but the pool edge on the right is incomplete, meaning the right side of the pool intersects with the right edge of the image, the position of the intersection point between the right pool edge and the right side of the image can be recorded. Then, the robot rotates a preset angle in the first direction and controls the camera device to capture a second image. Simultaneously, the position of the intersection point in the second image is determined. Finally, based on the position of the intersection point, the pool edge corresponding to the first direction displayed in the second image is stitched into the first image to obtain an image where all pool edges form closed curves (the pool is complete). For example, if the robot rotates 1 degree to the right to obtain the second image, the intersection point position information is incorporated into the second image. The pool edge to the right of the intersection point is a newly added pool edge. This newly added pool edge is added to the image specifically storing the pool edges (which can be the first image) to obtain an image of the complete pool. This is merely an example.
[0045] After determining that the pool is not fully displayed in the first image, this application records the position of the intersection point between the pool edge and the edge of the first image. Based on the direction of the identified incomplete pool edge, the robot rotates by a preset angle in the corresponding direction to capture a second image. Then, based on the position of the intersection point, the pool edge displayed in the first direction in the second image is stitched into the first image to obtain a complete image of the pool. This ensures that the pool image acquired by the robot is complete and avoids pool map matching errors due to missing images, which could affect subsequent pool operations.
[0046] In step S302, the robot enters the water and obtains the first entry position. Iteratively, it performs map building operations until the robot returns to the first entry position while walking through the map building operations, thus completing the construction of the pool map.
[0047] The map building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall, wherein the target pool wall meets the following conditions: the robot has not walked along a direction parallel to the target pool wall before, and the vertical distance between the target pool wall and the robot's position is the shortest; during the robot's walking along the direction parallel to the target pool wall, a pool map is built based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory. For details, please refer to step S101 of the embodiment shown in Figure 1, which will not be repeated here.
[0048] In step S303, the robot cleans the pool based on the completed pool map.
[0049] Specifically, the robot is equipped with a camera device. The robot conducts pool cleaning based on the completed pool map. Or, if the attribute information of the pool successfully matches any pool map in the pool map set, the robot conducts pool cleaning based on the successfully matched pool map, including: the robot walks along a preset path and conducts cleaning, records the current walking direction of the robot, and acquires a third image through the camera device; identifies whether there is any first pool garbage in the third image. If there is any first pool garbage, marks the position of the first garbage on the pool map, rotates based on the direction pointing to the first pool garbage, walks to the marked position of the first garbage for garbage cleaning, and accumulates the operation times of the first pool garbage cleaning operation; the robot returns to the position where the third image was taken, controls the camera device to take an image again, and determines whether there is still any first pool garbage at the position of the first garbage; if there is still any first pool garbage at the position of the first garbage, and the accumulated operation times of the first pool garbage cleaning operation reach the preset operation times threshold, marks the position of the first pool garbage on the pool map; the robot walks along a preset path and conducts cleaning based on the position where the third image was taken and the recorded current walking direction of the robot.
[0050] As shown in FIG. 5, in the embodiment of the present application, a walking path can be pre-planned for the robot, such as a "square inside a square" or "bow" shape. For example only, when the robot walks along the preset planned path and conducts pool cleaning, it can record the walking path and the current walking direction A1 of the robot in real time, and can simultaneously acquire a third image through the camera device, and identify whether there is any first pool garbage in the third image. If it is determined that there is any first pool garbage in the third image, the first garbage position of the first pool garbage can be marked on the pool map, then it can rotate based on the direction A2 pointing to the first pool garbage, and walk to the first garbage position for garbage cleaning. At this time, the operation times of the first pool garbage cleaning operation can be accumulated. After the cleaning is completed, the robot can return to the position where the third image was taken, control the camera device to take an image again, and then determine whether there is still any first pool garbage at the position of the first garbage, and determine whether the accumulated operation times of the first pool garbage cleaning operation reach the preset operation times threshold. Among them, the preset operation times threshold can be set according to actual requirements. For example, the operation times threshold is 3 times; if it is recognized that there is still any first pool garbage at the position of the first garbage, and the accumulated operation times of the first pool garbage cleaning operation reach the preset operation times threshold, indicating that the pool garbage is stubborn garbage, a mark indicating stubborn garbage here can be marked on the pool map. Finally, the robot continues to walk along the preset planned path and conduct pool cleaning based on the position where the third image was taken and the recorded current walking direction of the robot.
[0051] This application uses a camera device to identify a location with trash in the pool, then focuses on cleaning that area to ensure effective removal. After cleaning, the robot returns to its original position to reassess whether trash remains and whether the cleaning frequency has reached a threshold. If trash is still present and the cleaning frequency has reached the threshold, a marker indicating stubborn trash is added to the pool map. This facilitates more targeted cleaning measures to maintain the pool's cleanliness. The robot then continues its planned path-following and cleaning tasks, avoiding meaningless repetitive cleaning and improving its cleaning efficiency.
[0052] In one optional implementation, if there is still first pool trash at the first trash location, but the accumulated number of first pool trash cleaning operations has not reached the preset operation count threshold, then the process returns to the steps of controlling the robot to rotate and walk to the marked trash location based on the direction pointing to the first pool trash to clean the trash, and accumulating the number of first pool trash cleaning operations, until there is no first pool trash at the first trash location, or the accumulated number of first pool trash cleaning operations reaches the preset operation count threshold.
[0053] In this embodiment, the robot returns to the location where the third image was taken and takes another image. If it finds that there is still first pool trash at the first trash location and the accumulated number of first pool trash cleaning operations has not reached the preset operation threshold, the robot can rotate to the direction pointing to the first pool trash and walk to the marked trash location to clean it, and accumulate the first pool trash cleaning operation count. After cleaning, the robot returns to the location where the third image was taken, determines whether there is still first pool trash at the first trash location, and whether the accumulated number of first pool trash cleaning operations has reached the preset operation threshold, and repeats the above steps until there is no first pool trash at the first trash location, or the accumulated number of first pool trash cleaning operations reaches the preset operation threshold.
[0054] In one alternative implementation, the cleaned areas are marked on the pool map as the robot cleans based on the pool map.
[0055] In this embodiment of the application, the uncleaned areas and cleaned areas in the pool map can be distinguished by different colors. For example, the entire pool map can be represented in black, and the edges of the pool walls can be depicted in white. During the cleaning process based on the pool map, the robot can mark the cleaned areas with green markers. When the areas circled in white turn green, it means that the entire pool has been cleaned. This is just an example.
[0056] This application marks the uncleaned and cleaned areas separately on the pool map, ensuring a clearer distinction between cleaned and uncleaned areas, avoiding repeated cleaning and missed areas, and improving cleaning efficiency.
[0057] In one optional implementation, before the robot walks along a preset path and performs cleaning, the pool environment around the robot is acquired by the sonar device at the current location; the current robot pose is acquired by the robot pose acquisition device; the pool environment around the robot scanned by the sonar device is compared with the pool environment corresponding to the current robot pose on the pool map to determine whether the current robot pose is accurate; if the current robot pose is determined to be accurate, the steps of the robot walking along the preset path and performing cleaning are executed.
[0058] Before entering the water, the robot in this embodiment acquires an image of the pool using a camera device. Generally, the robot enters the water in a straight line and determines its position after entering the water based on its position in the pool image. Then, it performs pool cleaning operations based on its current position. However, a series of special situations may occur, such as multiple positions corresponding to similar pool environments, which may lead to inaccurate pose determination. Therefore, before the robot performs the cleaning task, the robot can acquire the pool environment around the robot scanned by a sonar device at its current position, as well as the current pose of the robot determined by a pose acquisition device. The pool environment around the robot scanned by the sonar device is compared with the pool environment corresponding to the current pose of the robot on the pool map to determine whether the current pose of the robot is accurate. If the robot pose is inaccurate, the robot can be controlled to perform appropriate walking, rotating, and other operations until the current pose of the robot is accurate. Only after the current pose of the robot is confirmed to be accurate will the robot perform the cleaning steps according to the preset path.
[0059] In one alternative implementation, the cleaning device installed on the robot is used to clean the pool in real time while the robot is walking. During the process of the robot walking and building a pool map, the cleaning device is controlled to clean and mark the cleaned areas. After the pool map is built, the robot cleans the pool based on the unmarked areas in the completed pool map.
[0060] In the process of walking and building a pool map, the robot in this application embodiment can control the cleaning device to clean in real time. That is, wherever the robot goes, the cleaning device will clean it, and the cleaned areas can be marked. This means that the pool map includes not only the pool environment map and the robot's movement trajectory, but also the areas cleaned by the robot during the mapping process. After the pool map is built, the robot can clean the pool only based on the unmarked areas in the completed pool map.
[0061] The robot in this application performs cleaning simultaneously while walking and building a map, avoiding the waste of time that would otherwise be spent building the map first and then cleaning, effectively shortening the overall cleaning time, accurately locating uncleaned areas, and improving cleaning efficiency.
[0062] In one optional implementation, as the robot walks along a direction parallel to the target pool wall, the current robot direction is recorded, and a fourth image is captured via a camera. The presence of second pool debris in the fourth image is identified. If second pool debris is present, its location is marked on the pool map. Based on the direction pointing to the second pool debris, the robot is controlled to rotate and walk to the marked location to clean the debris, and the number of cleaning operations is accumulated. The robot returns to the location where the fourth image was captured and the camera is controlled to capture another image to determine if second pool debris still exists. If second pool debris still exists at the fourth location, and the accumulated number of cleaning operations reaches a preset threshold, the location of the second pool debris is marked on the constructed pool map. Based on the location of the captured fourth image and the recorded current robot direction, the robot is controlled to walk along a direction parallel to the target pool wall and the cleaning device is controlled to clean.
[0063] In the process of building a map, the robot in this embodiment can not only perform basic cleaning tasks, but also focus on cleaning up pool debris. It can also mark the debris that cannot be cleaned up after multiple cleanings on the pool map, thereby improving the completeness of the constructed pool map. In the cleaning process after the pool map is completed, the cleaning of stubborn debris can be ignored (stubborn debris can be cleaned manually), thereby improving cleaning efficiency.
[0064] In this embodiment of the application, the robot can record its walking path and current direction in real time during pool mapping and cleaning. Simultaneously, it can capture a fourth image via a camera and identify whether second pool debris exists in the fourth image. If second pool debris is detected in the fourth image, its location is marked on the pool map. The robot then rotates based on the direction pointing to the second pool debris and walks to that location to clean it. The number of second pool debris cleaning operations is accumulated. After cleaning, the robot returns to the location where the fourth image was captured and controls the camera to capture another image, then re-identifies the second pool debris. The system checks whether there is still second pool debris at the location and whether the accumulated cleaning operations for the second pool debris have reached a preset threshold. This preset threshold can be set according to actual needs, for example, a threshold of 3 operations. If second pool debris is detected at the location of the second debris, and the accumulated cleaning operations for the second pool debris have reached the preset threshold, it indicates that the pool debris is stubborn. A marker indicating stubborn debris can be added to the pool map. Finally, based on the location of the captured fourth image and the recorded current robot direction, the robot continues to move parallel to the target pool wall and controls the cleaning device to perform cleaning. For detailed explanations, please refer to the above embodiment; further details will not be repeated here.
[0065] This embodiment also provides a robot, as shown in Figure 6. The robot includes a controller, a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The controller includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the above-described robot-based pool cleaning method. For detailed description, please refer to the above embodiment, which will not be repeated here.
[0066] This embodiment also provides a robot-based pool cleaning device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0067] This embodiment provides a robot-based pool cleaning device applied to a robot equipped with a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device scans the pool environment around the robot, and the robot pose acquisition device determines the robot's pose. As shown in Figure 7, it includes: a pool map building module 701, used for the robot to enter the water and obtain the first entry position, iteratively performing map building operations until the robot is back at the first entry position during the map building operation, thus completing the pool map. The map building operation includes: when the robot detects a target pool wall, controlling the robot to walk along a direction parallel to the target pool wall, wherein the target pool wall meets the following conditions: the robot has not walked along a direction parallel to the target pool wall, and the vertical distance between the target pool wall and the robot's position is the shortest; during the robot's walking along the direction parallel to the target pool wall, a pool map is built based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory; and a pool cleaning module 702, used for the robot to clean the pool based on the completed pool map.
[0068] In some optional implementations, the robot stores a pool map set, which includes multiple pre-recorded pool maps. The robot is equipped with a camera device. Before the robot enters the water, the robot-based pool cleaning device further includes: a pool recognition module, used to acquire a first image captured by the camera device and determine whether a pool exists in the first image; a pool integrity judgment module, used to identify all pool edges if a pool exists in the first image and determine whether all pool edges can form a closed curve; a pool comparison module, used to acquire the pool's attribute information if all pool edges can form a closed curve, and match the pool's attribute information with each pool map in the pool map set, the pool's attribute information including at least geometric information and obstacle information; and a map building execution module, used to execute the robot entering the water if no match is found with any pool map in the pool map set, and to acquire a first entry position, iteratively executing the map building operation until the robot is back at the first entry position during the map building operation, thus completing the pool map construction step.
[0069] In some optional implementations, if all pool edges do not form closed curves, the robot-based pool cleaning device further includes: an intersection position recognition module, used to identify a first direction of the pool edge that is not fully displayed in the first image, and record the position of the intersection point between the pool edge and the edge of the first image; a second image capturing module, used to rotate the robot to the first direction by a preset angle and control the camera device to capture a second image; and a pool stitching module, used to obtain the pool edge displayed in the first direction from the second image based on the position of the intersection point, and stitch the pool edge displayed in the first direction into the first image based on the position of the intersection point to obtain an image in which all pool edges form closed curves, and then perform the step of obtaining the attribute information of the pool.
[0070] In some optional implementations, the robot is equipped with a camera device, and the pool cleaning module includes: a third image capturing unit, used for the robot to walk and clean according to a preset path, record the current walking direction of the robot, and capture a third image through the camera device; a trash cleaning unit, used to identify whether there is first pool trash in the third image, and if there is first pool trash, mark the location of the first trash on the pool map, rotate based on the direction pointing to the first pool trash, walk to the marked location of the first trash and clean the trash, and accumulate the number of first pool trash cleaning operations; an image re-capturing unit, used for the robot to return to the location where the third image was captured, and control the camera device to capture the image again, to determine whether there is still first pool trash at the location of the first trash; a trash marking unit, used for marking the location of the first pool trash on the pool map if there is still first pool trash at the location of the first trash and the accumulated number of first pool trash cleaning operations reaches a preset operation threshold; and a robot running unit, used for the robot to walk and clean according to a preset path based on the location where the third image was captured and the recorded current walking direction of the robot.
[0071] In some optional implementations, if there is still first pool trash at the first trash location, but the accumulated number of first pool trash cleaning operations has not reached the preset operation threshold, then the process returns to the steps of controlling the robot to rotate and walk to the marked trash location based on the direction pointing to the first pool trash to clean the trash, and accumulating the number of first pool trash cleaning operations, until there is no first pool trash at the first trash location, or the accumulated number of first pool trash cleaning operations reaches the preset operation threshold.
[0072] In one alternative implementation, a pool marking module is used to mark the cleaned areas on the pool map during the robot's cleaning process based on the pool map.
[0073] In one optional implementation, before the robot walks along a preset path and performs cleaning, the robot-based pool cleaning device further includes: a pool environment acquisition module, used to acquire the pool environment around the robot scanned by the sonar device at the current location; a robot pose acquisition module, used to acquire the current pose of the robot determined by the robot pose acquisition device; an environment comparison module, used to compare the pool environment around the robot scanned by the sonar device with the pool environment corresponding to the current pose of the robot on the pool map, and determine whether the current pose of the robot is accurate; and a cleaning execution module, used to execute the steps of the robot walking along the preset path and performing cleaning if the current pose of the robot is determined to be accurate.
[0074] The cleaning device installed on the robot is used to clean the pool in real time while the robot is walking. The robot-based pool cleaning device also includes: an area marking module, which is used to control the cleaning device to clean and mark the cleaned areas while the robot is walking and building a pool map; and a pool cleaning module, which is used to clean the pool based on the unmarked areas in the completed pool map after the pool map is built.
[0075] In one optional implementation, the robot is equipped with a camera device. As the robot walks along a direction parallel to the target pool wall, the robot-based pool cleaning device further includes: a fourth image capturing module for recording the current robot's walking direction and capturing a fourth image via the camera device; a trash cleaning module for identifying whether second pool trash exists in the fourth image; if second pool trash exists, marking the location of the second trash on the pool map, controlling the robot to rotate and walk to the marked location based on the direction pointing to the second pool trash to perform trash cleaning, and accumulating the number of second pool trash cleaning operations; an image recapture module for the robot to return to the location where the fourth image was captured and controlling the camera device to capture the image again to determine if second pool trash still exists; a trash marking module for marking the location of second pool trash on the constructed pool map if second pool trash still exists at the fourth trash location and the accumulated number of second pool trash cleaning operations reaches a preset operation threshold; and a robot walking module for controlling the robot to walk along a direction parallel to the target pool wall based on the location of the captured fourth image and the recorded current robot walking direction, and controlling the cleaning device to perform cleaning.
[0076] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0077] In this embodiment, the robot-based pool cleaning device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0078] This application also provides a controller having the robot-based pool cleaning device shown in FIG7 above.
[0079] Please refer to Figure 8, which is a schematic diagram of a controller provided in an optional embodiment of this application. As shown in Figure 8, the controller includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processors can process instructions executed within the controller, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple controllers can be connected, each device providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 uses one processor 10 as an example.
[0080] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0081] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.
[0082] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the controller. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0083] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0084] The controller also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means; Figure 8 shows an example of a connection via a bus.
[0085] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the controller, such as a touch screen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touch screen.
[0086] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.
[0087] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.
Claims
1. A robot-based swimming pool cleaning method, characterized in that, Applied to a robot equipped with a sonar device, a cleaning device, and a robot pose acquisition device, the sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The method includes: The robot enters the water and acquires its initial entry position. It iteratively performs map-building operations until the robot returns to the initial entry position while moving through the map-building process, thus completing the construction of the pool map. The map-building operations include: When the robot detects the target pool wall, it is controlled to walk in a direction parallel to the target pool wall, wherein the target pool wall satisfies the following conditions: the robot has not walked in a direction parallel to the target pool wall before, and the vertical distance between the target pool wall and the robot's position is the shortest. As the robot walks along a direction parallel to the target pool wall, a pool map is constructed based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory. The robot cleans the pool based on the constructed pool map.
2. The method according to claim 1, characterized in that, The robot stores a pool map set, which includes multiple pre-recorded pool maps. The robot is equipped with a camera device. Before the robot enters the water, the method further includes: Acquire a first image captured by a camera device, and determine whether a swimming pool exists in the captured first image; If a swimming pool is present in the first captured image, identify all the pool edges and determine whether all the pool edges can form a closed curve. If all pool edges can form closed curves, obtain the attribute information of the pool, and match the attribute information of the pool with each pool map in the pool map set. The attribute information of the pool includes at least geometric information and obstacle information. If no match is found with any of the pool maps in the pool map set, the robot enters the water and obtains the first entry position. The map building operation is then performed iteratively until the robot is once again at the first entry position while walking through the map building operation, thus completing the construction of the pool map.
3. The method according to claim 2, characterized in that, If all pool edges do not form closed curves, the method further includes: Identify the first direction of the pool edge that is not fully displayed in the first image, and record the position of the intersection point of the pool edge and the edge of the first image; The robot rotates a preset angle in the first direction and controls the camera device to capture a second image; Based on the position of the intersection point, the pool edge corresponding to the first direction is obtained from the second image, and the pool edge corresponding to the first direction is stitched into the first image based on the position of the intersection point to obtain an image in which all pool edges form a closed curve, and then the step of obtaining the attribute information of the pool is performed.
4. The method according to claim 1 or 2, characterized in that, The robot is equipped with a camera device. The robot cleans the pool based on a constructed pool map, or, if the pool's attribute information matches any pool map in the pool map set, it cleans the pool based on the matched pool map, including: The robot walks and cleans along a preset path, records the current direction of the robot's movement, and captures third-party images through a camera device; The system identifies whether there is first pool trash in the third image. If there is first pool trash, the system marks the location of the first trash on the pool map, rotates based on the direction pointing to the first pool trash, walks to the marked location of the first trash to clean it, and accumulates the number of first pool trash cleaning operations. The robot returns to the location where the third image was taken and controls the camera device to take another image to determine whether the first pool trash still exists at the location of the first trash; If there is still trash at the first trash location, and the cumulative number of first pool trash cleaning operations reaches a preset operation threshold, then the first pool trash location is marked on the pool map. Based on the location of the captured third image and the recorded current robot walking direction, the robot walks and cleans according to a preset path.
5. The method according to claim 4, characterized in that, If there is still trash at the first trash location, but the accumulated number of first pool trash cleaning operations has not reached the preset operation threshold, then return to the steps of controlling the robot to rotate and walk to the marked trash location based on the direction pointing to the first pool trash to clean the trash, and accumulating the number of first pool trash cleaning operations, until there is no more first pool trash at the first trash location, or the accumulated number of first pool trash cleaning operations reaches the preset operation threshold.
6. The method according to claim 4, characterized in that, During the cleaning process, the robot marks the cleaned areas on the pool map.
7. The method according to claim 4, characterized in that, Before the robot moves along the preset path and performs cleaning, the method further includes: Acquire the pool environment around the robot as scanned by the sonar device at the current location; Obtain the current robot pose determined by the machine pose acquisition device; The pool environment around the robot scanned by the sonar device is compared with the pool environment corresponding to the current pose of the robot on the pool map to determine whether the current pose of the robot is accurate. If the robot's current pose is determined to be accurate, then the steps of the robot walking along the preset path and performing cleaning are executed.
8. The method according to claim 1, characterized in that, The cleaning device installed on the robot is used to clean the pool in real time while the robot is moving, and the method further includes: As the robot walks and builds a map of the pool, the cleaning device is controlled to clean and mark the cleaned areas. After the pool map is built, the robot cleans the pool based on the unmarked areas in the completed pool map.
9. The method according to claim 8, characterized in that, The method further includes the following steps during the robot's movement along a direction parallel to the target pool wall: Record the current direction of the robot's movement and acquire a fourth image through a camera device; The system identifies whether there is second pool trash in the fourth image. If there is second pool trash, the system marks the location of the second trash on the pool map and controls the robot to rotate and walk to the marked location of the second trash based on the direction pointing to the second pool trash to clean it up. The system also accumulates the number of second pool trash cleaning operations. The robot returns to the location where the fourth image was taken and controls the camera to take another image to determine if there is still trash in the second pool. If there is still second pool trash at the fourth trash location, and the cumulative number of second pool trash cleaning operations reaches a preset operation threshold, then the second pool trash location will be marked on the constructed pool map. Based on the location of the fourth image and the recorded current robot walking direction, the robot controls itself to walk parallel to the target pool wall and controls the cleaning device to perform cleaning.
10. A robot-based swimming pool cleaning device, characterized in that, This device is applied to a robot equipped with a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The device includes: A pool map building module is used for the robot to enter the water and obtain its first entry position. It iteratively executes map building operations until the robot returns to the first entry position during its movement through the map building operations, thus completing the pool map. The map building operations include: When the robot detects the target pool wall, it is controlled to walk in a direction parallel to the target pool wall, wherein the target pool wall satisfies the following conditions: the robot has not walked in a direction parallel to the target pool wall before, and the vertical distance between the target pool wall and the robot's position is the shortest. As the robot walks along a direction parallel to the target pool wall, a pool map is constructed based on the surrounding pool environment scanned by the sonar device and the robot's walking trajectory. The pool cleaning module is used by the robot to clean the pool based on the constructed pool map.
11. A robot, characterized in that, The robot includes a controller, a sonar device, a cleaning device, and a robot pose acquisition device. The sonar device is used to scan the pool environment around the robot, and the robot pose acquisition device is used to determine the robot's pose. The controller includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the robot-based pool cleaning method according to any one of claims 1 to 8.