Positioning method of swimming pool cleaning robot and swimming pool cleaning robot

Abstract

The invention discloses a positioning method of a swimming pool cleaning robot and the swimming pool cleaning robot, the robot is controlled to enter a mapping mode, and in the mapping mode, the robot obtains at least one piece of image information of the edge of a swimming pool and position information corresponding to the image information; the robot is controlled to enter an operation mode, and in the operation mode, the robot obtains current image information; and matching the current image information with the at least one piece of image information, and if the matching succeeds, acquiring the current position information based on the position information corresponding to the image information in the at least one piece of image information matched with the current image information. According to the invention, the current image information obtained in the operation mode is matched with the image information retained in the mapping mode in a sliding manner, so that positioning by using a single feature is avoided, and the positioning precision is improved.

Description

Technical Field

[0001] This invention relates to the field of underwater equipment technology, and in particular to a positioning method for a pool cleaning robot and the pool cleaning robot itself. Background Technology

[0002] Currently, with the widespread use of swimming pools, automated pool cleaning robots are gradually becoming one of the important cleaning equipment. Traditional pool cleaning robots mostly rely on timed or random movement for cleaning, which can easily lead to uneven cleaning or low efficiency. In addition, when pool cleaning robots work underwater, poor ambient light, water surface reflection, and complex underwater currents can all significantly affect the positioning capabilities of the robot's sensors, resulting in low positioning accuracy and an inability to accurately determine the robot's position in the pool, thus affecting the cleaning effect.

[0003] Traditional positioning technologies commonly include GPS, LiDAR, and acoustic positioning. However, GPS signals have difficulty propagating underwater, making them unsuitable for the positioning needs of pool cleaning robots. While LiDAR and other technologies offer high accuracy, they are expensive and susceptible to underwater reflections, leading to unstable measurements. Acoustic positioning, though applicable to underwater environments, suffers from high equipment complexity and cost, and is easily affected by noise and interference, limiting its widespread application. Therefore, existing pool cleaning robots often face problems such as inaccurate positioning, insufficient cleaning coverage, and low efficiency in practical use. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a positioning method for a pool cleaning robot and a pool cleaning robot, thereby solving the positioning problem of a pool cleaning robot in an underwater environment.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for locating a pool cleaning robot, comprising the following steps: S1. Control the robot to enter the mapping mode. In the mapping mode, the robot acquires at least one image of the edge of the pool and the position information corresponding to the image. S2. Control the robot to enter the operation mode. In the operation mode, the robot acquires the current image information. S3. Match the current image information with at least one image information. If the match is successful, obtain the current location information based on the location information corresponding to the image information in the at least one image information that matches the current image information.

[0006] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is as follows: A swimming pool cleaning robot, wherein the robot performs the positioning method of the swimming pool cleaning robot.

[0007] The beneficial effects of the present invention include at least the following: providing a positioning method for a pool cleaning robot and a pool cleaning robot, wherein in mapping mode the robot is controlled to acquire at least one image information of the pool edge as a positioning reference; if the robot acquires current image information in operation mode and the image information can be successfully matched with the above image information, then the current position information is acquired according to the position information corresponding to the above image information, and the robot positioning is completed. That is, the current image information acquired in operation mode is used to perform sliding matching with the image information retained in mapping mode, avoiding the use of a single feature for positioning and improving positioning accuracy. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating a positioning method for a pool cleaning robot according to an embodiment of the present invention. Detailed Implementation

[0009] To explain in detail the technical content, objectives, and effects of the present invention, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0010] In the description of this application, it should be understood that the terms "upper," "lower," "inner," "outer," "top," and "bottom," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or regarding the vertical, perpendicular, or gravitational direction of the component itself. These terms are used only for the convenience of describing this application and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0011] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this application. Terms such as “part” or “component” appearing herein can refer to a single part or a combination of multiple parts. Terms such as “installation,” “setup,” and “connection” appearing herein should be interpreted broadly; for example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can indicate that one component is directly attached to another component or that one component is attached to another component via an intermediate component; they can refer to the internal connection of two elements. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. A feature described in one embodiment herein may be applied alone or in combination with other features to another embodiment, unless that feature is not applicable in that other embodiment or is otherwise stated.

[0012] Please refer to Figure 1 A method for locating a pool cleaning robot, comprising the following steps: S1. Control the robot to enter the mapping mode. In the mapping mode, the robot acquires at least one image of the edge of the pool and the position information corresponding to the image. S2. Control the robot to enter the operation mode. In the operation mode, the robot acquires the current image information. S3. Match the current image information with at least one image information. If the match is successful, obtain the current location information based on the location information corresponding to the image information in the at least one image information that matches the current image information.

[0013] It is understandable that mapping mode and operation mode correspond to different working stages of the robot. The main task of mapping mode is to acquire and generate a map of the current working environment, for example, by acquiring image information of the pool edge through its image acquisition module (such as a camera). Simultaneously, it can also acquire positional information corresponding to these images, such as recording the robot's position in space through sensors like ranging sensors, IMUs (Inertial Measurement Units), or odometry. Operation mode is the cleaning work stage that the robot enters after mapping is completed, used for cleaning tasks. When needed, the robot in operation mode acquires current image information (i.e., an image of the robot's current location) and matches these images with images saved in mapping mode. If a match is successful, the robot can determine its current position in the pool based on the matched image position information, ensuring that the robot knows its position during work and performs efficient cleaning work according to the shape of the pool. In other words, this application utilizes sliding matching between the current image information acquired in operation mode and the image information retained in mapping mode to avoid relying on a single feature for localization and improve localization accuracy.

[0014] In some implementations, the pool cleaning robot walks along the edge of the pool in both the mapping mode and the operation mode. The robot can achieve this by using an edge-following algorithm. Specifically, a PID (Proportional-Integral-Derivative) control algorithm is used to adjust the robot's trajectory in real time. Based on the distance between the robot and the pool edge measured by sensors, the PID controller can output correction commands to adjust the robot's direction and speed to maintain a preset distance. Alternatively, image processing algorithms can be used: if a camera is used to capture edge images, image processing algorithms (such as edge detection, feature point matching, etc.) can help identify the contour of the pool edge and keep the robot walking along the detected edge. Using a feature point matching algorithm, the robot can continuously adjust its position to maintain a certain distance from the edge. Alternatively, path planning and trajectory tracking algorithms can be used. Based on the edge data perceived by sensors, the robot can plan a trajectory along the edge according to a preset walking distance. The trajectory tracking algorithm calculates the deviation between the robot's current position and the target position, thereby correcting the robot's walking path to fit the pool edge.

[0015] Specifically, walking along the edge of the pool includes walking at a preset distance from the edge of the pool. The preset distance can be a fixed value or a preset range, preferably 20-40cm, and more preferably 20cm, 30cm or 40cm.

[0016] In some implementations, step S1 further includes generating a map of the swimming pool based on the at least one image information and the location information corresponding to the image information. Specifically, the steps are as follows: First, data is collected using sensors. Image acquisition modules are used to obtain image information of the pool's edge, which is then used to record the pool's shape, features, and boundaries. Then, position information is acquired using sensors such as ranging sensors (e.g., laser, ultrasonic sensors), IMU (Inertial Measurement Unit), GPS, or odometry to obtain the robot's motion trajectory and position information. The position information is used to mark the robot's spatial location during image acquisition; image and position information are then fused. Finally, while acquiring image information, positional information corresponding to each image is also collected, and the image and positional information are synchronized and fused. The acquired image information is associated with the corresponding positional information (e.g., the robot's coordinates in the pool or its distance from the pool edge). Each image has its corresponding positional information, forming an image-positional information mapping. Simultaneously, pose estimation is performed: using positional information (such as IMU and odometry data), the robot's specific pose (position and orientation) at each image acquisition moment is calculated, thus facilitating the projection of each image onto the overall map of the pool, completing map construction.

[0017] Specifically, the current location information includes the robot's location information on the map. By combining the current location information with a pre-generated pool map, the robot can determine its specific location in the pool in real time. Combining known map data and real-time location information, the robot can quickly match corresponding image information based on its location, thereby completing the localization process and improving localization efficiency.

[0018] In some implementations, the current image information and the at least one image information both include multiple stitched image information; since a single image may not be able to cover a sufficiently large area, especially when the edge of the pool is complex or the features are not obvious, stitching multiple images together can obtain a wider range of environmental information and improve positioning accuracy.

[0019] Preferably, both the current image information and the at least one image information include processing these image information into a bird's-eye view (BEV) or fusing the image with data from other positioning sensors. Relying solely on image recognition technology may not be effective in a swimming pool environment. The edge of a pool typically lacks obvious feature points, and factors such as water reflection and changes in lighting can interfere with the accuracy of image recognition, leading to inaccurate positioning. Therefore, accurate positioning in a swimming pool environment using only image data is challenging. To overcome these problems, combining data from other sensors becomes an effective solution. Specifically, devices such as ranging sensors (e.g., lidar or ultrasonic sensors) and IMUs (inertial measurement units) can be used to acquire additional information related to position and motion. This data can be combined with image information to form a more accurate environmental perception. For example, using a ranging sensor, a robot can determine its distance from the pool edge in real time; using an IMU, a robot can detect its own posture and direction of movement. This sensor data can be fused with image information to provide a more comprehensive environmental description. The bird's-eye view (BEV) is an image captured by a camera converted into a top-down perspective, similar to a view of the pool from a high vantage point. The advantage of generating BEV images is that it unifies images from multiple angles into a standard, intuitive top-down view, which is highly beneficial for feature point recognition and comparison. By stitching together multiple images and converting them into BEV images, the robot can obtain a complete and easily analyzable image of the pool edge, thereby improving the accuracy of subsequent image matching.

[0020] Furthermore, images that incorporate sensor data can enhance image recognition accuracy. For example, by combining IMU data with images, robots can not only identify edge features through images but also understand their own motion state (such as angular velocity and acceleration) through sensor data, further improving the accuracy and reliability of positioning.

[0021] In some implementations, the current image information includes images captured by the pool cleaning robot as it travels 1 / 10 to 2 / 3 laps around the edge of the pool. This means image data acquired via a camera or other image sensor. In this process, the robot does not need to travel a full lap around the pool to obtain useful image information; traveling only 1 / 10 to 2 / 3 laps is sufficient. Controlling the robot to collect image data without circling the entire pool speeds up localization, mapping, and cleaning.

[0022] A swimming pool cleaning robot performs the aforementioned positioning method. Specifically, the robot includes an image acquisition module for acquiring the current image or at least one image information. The image acquisition module can be one or more of a fisheye camera, panoramic camera, depth camera, vision camera, or laser scanner, used to acquire image information of the robot's surrounding environment.

[0023] In summary, the present invention provides a positioning method and a pool cleaning robot. By matching current image information with pre-generated image information, the robot can accurately determine its specific position in the pool, improving positioning accuracy and ensuring that the robot can effectively perform tasks in complex underwater environments. Furthermore, the robot only needs to travel 1 / 10 to 2 / 3 of a lap along the pool edge to acquire sufficient image information for positioning and mapping, avoiding the need for the robot to travel a full lap around the pool. This significantly reduces mapping and positioning time, improves the efficiency of the entire cleaning task, and accelerates the speed of positioning, mapping, and cleaning. In addition, through multi-source data fusion (such as the combination of IMU, ranging sensors, and image data), high positioning reliability and accuracy can be maintained even under varying ambient lighting conditions or insufficient pool feature points, ensuring that the robot can stably perform cleaning tasks.

[0024] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent modifications made based on the content of the present invention specification and drawings, or direct or indirect applications in related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A positioning method for a swimming pool cleaning robot, characterized in that, Including the following steps: S1. Control the robot to enter the mapping mode. In the mapping mode, the robot acquires at least one image of the edge of the pool and the position information corresponding to the image. S2. Control the robot to enter the operation mode. In the operation mode, the robot acquires the current image information. S3. Match the current image information with at least one image information. If the match is successful, obtain the current location information based on the location information corresponding to the image information in the at least one image information that matches the current image information.

2. The positioning method for the pool cleaning robot according to claim 1, characterized in that, The location information corresponding to the image information includes location information obtained based on data collected by a ranging sensor, IMU, or odometer.

3. The positioning method for the pool cleaning robot according to claim 1, characterized in that, In both the mapping mode and the operation mode, the pool cleaning robot walks along the edge of the pool.

4. The positioning method for the pool cleaning robot according to claim 3, characterized in that, Walking along the edge of the pool includes walking at a preset distance from the edge of the pool.

5. The positioning method for the pool cleaning robot according to claim 1, characterized in that, Step S1 further includes generating a map of the swimming pool based on the at least one image information and the location information corresponding to the image information.

6. The positioning method for the pool cleaning robot according to claim 5, characterized in that, The current location information includes the robot's location information on the map.

7. The positioning method for the pool cleaning robot according to any one of claims 1-6, characterized in that, The current image information and the at least one image information both include multiple spliced ​​image information.

8. The positioning method for the pool cleaning robot according to any one of claims 1-6, characterized in that, The current image information includes images collected by the pool cleaning robot as it travels 1 / 10 to 2 / 3 laps around the edge of the pool.

9. A swimming pool cleaning robot, characterized in that: The robot performs the positioning method of the pool cleaning robot according to any one of claims 1-8.

10. The pool cleaning robot according to claim 9, characterized in that: The robot includes an image acquisition module for acquiring the current image or at least one image information.

Images