Automatic water surface cleaning device and control method thereof

Abstract

The invention discloses a method for controlling an automatic water surface cleaning device. The method comprises the steps that the automatic water surface cleaning device is controlled to advance on the water surface; collecting motion posture data of the automatic water surface cleaning device; collecting image information of an object around the automatic water surface cleaning device; on the basis of the motion posture data and the image information, a correction value of posture change of the automatic water surface cleaning device is obtained; and correcting an error of the motion attitude data based on the correction value of the attitude change.

Description

Technical Field

[0001] This disclosure relates to the field of cleaning, specifically to an automatic water surface cleaning device and its control method. Background Technology

[0002] Automatic water surface cleaning devices are generally used to clean the surface of pools and ponds, for example, to collect and remove trash / debris from the surface of pools such as swimming pools, so as to filter and purify the water in the pool. Summary of the Invention

[0003] According to one aspect of this disclosure, a method for controlling an automatic water surface cleaning device is proposed, comprising: controlling the automatic water surface cleaning device to move on the water surface; acquiring motion posture data of the automatic water surface cleaning device; acquiring image information of objects surrounding the automatic water surface cleaning device; obtaining a correction value for the posture change of the automatic water surface cleaning device based on the motion posture data and the image information; and correcting the error of the motion posture data based on the correction value for the posture change.

[0004] According to at least one embodiment of this disclosure, in the above method, obtaining the correction value of the attitude change of the automatic water surface cleaning device based on the motion posture data and the image information may include: obtaining an estimated value of the attitude change of the automatic water surface cleaning device based on the motion posture data; obtaining a reference value of the attitude change of the automatic water surface cleaning device based on the image information; and obtaining the correction value of the attitude change of the automatic water surface cleaning device based on the estimated value of the attitude change and the reference value of the attitude change.

[0005] According to at least one embodiment of this disclosure, in the above method, the motion posture data includes multi-frame motion posture data with timestamps, the image information includes at least one pair of image frames with timestamps, and the method may further include: inserting at least a portion of the multi-frame motion posture data between the at least one pair of image frames based on timestamp order.

[0006] According to at least one embodiment of the present disclosure, the above method may further include: calculating an estimated value of the attitude change of the automatic water surface cleaning device during the acquisition period of the at least one pair of image frames based on at least a portion of the multi-frame motion attitude data; and obtaining a reference value of the attitude change of the automatic water surface cleaning device during the acquisition period of the at least one pair of image frames based on feature matching between the at least one pair of image frames.

[0007] According to at least one embodiment of this disclosure, the method may further include: obtaining a correction value for the attitude change of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames, based on the difference between the estimated value of the attitude change and the reference value of the attitude change.

[0008] According to at least one embodiment of this disclosure, the method may further include: obtaining a correction value of the attitude change of the automatic water surface cleaning device during an acquisition period including multiple pairs of image frames; and correcting the error of the motion attitude data based on the correction value of the attitude change of the automatic water surface cleaning device during an acquisition period including multiple pairs of image frames.

[0009] According to at least one embodiment of this disclosure, in the above method, the motion attitude data includes at least one of the following: acceleration data collected by the inertial measurement unit equipped with the automatic water surface cleaning device and angular velocity data collected by the inertial measurement unit.

[0010] According to at least one embodiment of this disclosure, in the above method, the image information includes image information collected by an image sensor equipped with the automatic water surface cleaning device, wherein the image sensor includes at least one of the following: a monocular camera, a binocular camera, a depth camera, and a panoramic camera.

[0011] According to another aspect of this disclosure, an automatic water surface cleaning device is also proposed, comprising: a processor configured to cause the automatic water surface cleaning device to perform the above-described method when executing one or more instructions.

[0012] According to at least one embodiment of the present disclosure, the above-mentioned automatic water surface cleaning device further includes at least one of the following: an inertial measurement unit for acquiring motion attitude data of the automatic water surface cleaning device, wherein the motion attitude data includes at least one of acceleration data and angular velocity data; and an image sensor for acquiring image information of surrounding objects during the movement of the automatic water surface cleaning device. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1A-1B The schematic illustration shows the shape of an automatic water surface cleaning device according to an embodiment of the present disclosure.

[0015] Figure 2The illustration schematically shows a portion of the internal structure of the automatic water surface cleaning device according to an embodiment of the present disclosure after the top cover and front cover of the housing have been removed.

[0016] Figure 3 The illustration schematically shows the flow of a control method for an automatic water surface cleaning device according to an embodiment of the present disclosure.

[0017] Figure 4 The illustration shows a diagram of image frames and motion posture data acquired by an automatic water surface cleaning device.

[0018] Figure 5 A schematic block diagram of an automatic water surface cleaning device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0019] The detailed description that follows, taken in conjunction with the accompanying drawings, is intended as a description of various configurations and not as representing only configurations in which the concepts described herein can be practiced. The detailed description includes specific details and is intended to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts can be practiced without these specific details.

[0020] In the description of this disclosure, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," "one side," "the other side," "front end," "rear end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0021] Furthermore, terms such as "first," "second," and "third," which relate to sequence, 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. Therefore, a feature defined with terms such as "first," "second," and "third," which relate to sequence, may explicitly or implicitly include at least one of those features. In the description of this disclosure, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0022] Furthermore, dimensions may be exaggerated in the accompanying drawings for clarity and are not drawn to scale. Throughout the drawings, the same reference numerals generally refer to the same elements.

[0023] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings.

[0024] Figure 1A-1B The diagram schematically illustrates the external appearance of an automatic water surface cleaning device 10 according to an embodiment of the present disclosure. This automatic water surface cleaning device 10 can perform cleaning operations on the surface of a pool as needed, for example, to remove garbage, debris, etc. from the water surface. Figure 1A-1B As shown, the automatic water surface cleaning device 10 may include a housing 110, which is generally boat-shaped, wherein the housing 110 includes a front end 120 located near the direction of travel of the automatic water surface cleaning device and a rear end 130 located away from the direction of travel of the automatic water surface cleaning device.

[0025] As an example, such as Figure 1A and Figure 1B As further shown, the automatic water surface cleaning device 10 also includes flow channels 140 symmetrically arranged on both sides of the housing 110 and a propulsion device 150 disposed in the flow channels 140. As an example, the propulsion device 150 may include a propeller driven by a motor. According to embodiments of this disclosure, the automatic water surface cleaning device 10 can perform various actions such as forward, backward, and turning on the water surface under the drive of the propulsion device, in order to clean up various garbage and debris floating on the water surface, such as fallen leaves.

[0026] like Figure 1A-1B As shown, a water inlet 160 is provided at the front end of the housing 110 of the automatic water surface cleaning device 10, and drain outlets are provided at the rear end and bottom of the housing 110, respectively. Figure 1B The drain outlet 180 at its rear end is schematically shown.

[0027] Figure 1A As further shown, the automatic water surface cleaning device 10 includes a rotatable component 170 disposed at its front end, which can rotate in a first direction or a second direction to guide debris into the inlet 160.

[0028] According to embodiments of this disclosure, the automatic water surface cleaning device may further include: a filter device, at least partially located within the housing, the filter device being capable of filtering water flowing into its interior through the inlet, trapping debris carried in the water within the filter device, and discharging the filtered water through the at least one outlet.

[0029] Figure 2 The illustration schematically shows a portion of the internal structure of the automatic water surface cleaning device 20 according to an embodiment of the present disclosure after the top cover and front cover of the housing have been removed. Figure 2As shown, the automatic water surface cleaning device 20 may include a removable filter device 21, which is at least partially located inside the housing. When the automatic water surface cleaning device moves on the water surface, the water flow in front of it can enter the filter device 21 through the inlet, thereby trapping the debris carried in the water flow inside the filter device 21, and the filtered water can be discharged into the water tank.

[0030] As an example, such as Figure 2 As further shown, the automatic water surface cleaning device also includes buoyancy mechanisms 220 and 230 symmetrically arranged on both sides of the filter device 21. These buoyancy mechanisms provide buoyancy for the automatic water surface cleaning device to remain suspended on the water surface. For example, the buoyancy mechanisms 220 and 230 can take the form of airbags or air chambers. The magnitude of the buoyancy provided by the buoyancy mechanisms 220 and 230 can be adjusted by controlling a buoyancy adjustment mechanism such as an air pump through the control unit of the automatic water surface cleaning device 20. For example, the control unit can be a control circuit such as a microprocessor, digital signal processor (DSP), or microcontroller.

[0031] although Figure 1A-Figure 2 The illustration schematically shows the overall shape and a portion of the internal structure of an automatic water surface cleaning device according to an embodiment of the present disclosure. It should be understood that this is merely illustrative and does not constitute any limitation on the principles of the present disclosure.

[0032] According to embodiments of this disclosure, the automatic water surface cleaning device may also be equipped with various sensors to perform various operations such as detecting the surrounding environment, determining a travel route, and / or performing cleaning tasks. For example, as an example, the automatic water surface cleaning device according to embodiments of this disclosure may be equipped with an image sensor for acquiring image information of objects around the automatic water surface cleaning device.

[0033] As an example, the image sensor described above may include at least one of the following: a monocular camera, a binocular camera, a depth camera, or a panoramic camera.

[0034] According to embodiments of this disclosure, the automatic surface cleaning device may also be equipped with an inertial measurement unit (IMU) for acquiring motion attitude data of the automatic surface cleaning device, wherein the motion attitude data includes at least one of acceleration data and angular velocity data, thereby acquiring attitude data of the automatic surface cleaning device such as pitch angle, yaw angle and / or roll angle.

[0035] As an example, the IMU may include a (three-axis) gyroscope and a (three-axis) accelerometer, wherein the (three-axis) accelerometer is used to detect the acceleration signals of the automatic water surface cleaning device in each axis direction in three-dimensional space, and the (three-axis) gyroscope is used to detect the angular velocity signals of the automatic water surface cleaning device relative to each axis of the reference coordinate system in three-dimensional space; based on the detected angular velocity and acceleration of the automatic water surface cleaning device in three-dimensional space, the attitude of the automatic water surface cleaning device in three-dimensional space can be calculated, thereby realizing accurate measurement and control when operating in the pool area.

[0036] To improve the cleaning efficiency and quality of automatic water surface cleaning devices, the device can be controlled to travel along a set route based on the motion attitude data collected by the IMU equipped with it. This allows for obstacle avoidance and cleaning operations during the process, achieving comprehensive cleaning of pools such as swimming pools.

[0037] However, due to the nature of the IMU itself, the motion attitude data it acquires (e.g., acceleration values ​​and / or angular velocity values) contains errors such as zero bias and noise. As the operating time of the automatic water surface cleaning device increases, the errors will gradually accumulate, resulting in inaccurate attitude data such as pitch angle, yaw angle and / or roll angle calculated based on the motion attitude data. This affects the precise control of the automatic water surface cleaning device. For example, it reduces or even degrades the accuracy of mapping the working area environment, affects the positioning and navigation accuracy of the automatic water surface cleaning device, and may also reduce the cleaning efficiency and quality of the pool.

[0038] Therefore, according to the embodiments of this disclosure, it is proposed to correct the attitude estimation of the automatic water surface cleaning device based on data collected by multiple types of sensors to compensate for the shortcomings of a single sensor. On the one hand, this can enhance the robustness of water surface environment perception, improve perception capability and anti-interference capability. On the other hand, during the movement of the automatic water surface cleaning device, image information collected by image sensors can be used to dynamically correct the motion attitude data collected by the IMU in order to obtain accurate and stable attitude data, thereby controlling the operation of the automatic water surface cleaning device accordingly. This improves the positioning and navigation accuracy of the automatic water surface cleaning device, enhances the mapping accuracy of the work area, and improves the operation quality and efficiency of the automatic water surface cleaning device.

[0039] Figure 3 The illustration schematically depicts the flow of a control method for an automatic water surface cleaning device according to an embodiment of the present disclosure. For example... Figure 3As shown, the method 300 may include: S310, controlling the automatic water surface cleaning device to move on the water surface; S320, acquiring motion posture data of the automatic water surface cleaning device and acquiring image information of objects around the automatic water surface cleaning device; S330, obtaining a correction value for the posture change of the automatic water surface cleaning device based on the motion posture data and the image information; and S340, correcting the error of the motion posture data based on the correction value for the posture change.

[0040] According to embodiments of this disclosure, obtaining a correction value for the attitude change of the automatic water surface cleaning device based on motion posture data and image information may include: obtaining an estimated value for the attitude change of the automatic water surface cleaning device based on the motion posture data; obtaining a reference value for the attitude change of the automatic water surface cleaning device based on the image information; and obtaining a correction value for the attitude change of the automatic water surface cleaning device based on the estimated value and the reference value.

[0041] The control method for an automatic water surface cleaning device according to embodiments of this disclosure will be described in detail below with reference to specific examples.

[0042] According to embodiments of this disclosure, when the automatic water surface cleaning device is controlled to move on the surface of the pool, its equipped IMU can be used to collect motion attitude data in real time. For example, it can collect acceleration values ​​and angular velocity values ​​of the three axes of the reference coordinate system XYZ in three-dimensional space, wherein the collected motion attitude data is timestamped.

[0043] Furthermore, when the automatic water surface cleaning device is moving on the water surface, it can use its equipped image sensor (e.g., grayscale image sensor or RGB image sensor) to acquire image information of objects around the automatic water surface cleaning device, such as image information of various fixed objects and moving objects (such as floating objects) around the automatic water surface cleaning device, wherein the image information is timestamped; as an example, fixed objects may include, but are not limited to, facilities such as pool walls, ladders, and platforms in the water; moving objects may include, but are not limited to, floating garbage and debris, such as leaves, life rings, and water toys.

[0044] As an example, the IMU acquires motion posture data more frequently than the image sensor acquires image information; in other words, there can be multiple frames of motion posture data with different timestamps between a pair of acquired image information.

[0045] like Figure 4As shown, during the movement of the automatic water surface cleaning device, as an example, image information of the surrounding environment can be collected in real time using, for example, an image sensor equipped with the automatic water surface cleaning device, during the turning process. For example, at time t1, an image frame f1 containing the surrounding environment information is acquired; as the automatic water surface cleaning device continues to move, at time t2, an image frame f2 containing the surrounding environment information is acquired.

[0046] Furthermore, as mentioned above, during the movement of the automatic water surface cleaning device, its IMU collects motion attitude data in real time, such as acceleration values ​​along the XYZ axes. and angular velocity value

[0047] Considering that the frequency of IMU acquiring motion attitude data is much higher than the frequency of image sensor acquiring image information, that is to say, Figure 4 As shown, between time t1 and t2, the IMU acquires multiple frames of motion attitude data. As an example, the number of frames of motion attitude data between time t1 and t2 depends on the ratio of the frequency at which the IMU equipped with the automatic water surface cleaning device acquires motion attitude data to the frequency at which its image sensor acquires image information.

[0048] According to embodiments of this disclosure, the acquired motion posture data includes multi-frame motion posture data with timestamps, the image information includes at least one pair of image frames with timestamps, and the method may further include: inserting at least a portion of the multi-frame motion posture data between the at least one pair of image frames based on timestamp order.

[0049] According to embodiments of this disclosure, a reference value for the attitude change of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames can be obtained based on feature matching between at least one pair of image frames acquired by an image sensor.

[0050] For example, during the movement of an automatic water surface cleaning device, an image sensor acquires image frames by collecting image information of the surrounding environment. Feature points are extracted from the image frames, for example, identical points are extracted from at least two image frames, and feature matching is performed on them; then, the attitude change and / or trajectory of the image sensor is estimated based on these matched points; given that the relative installation position of the image sensor and the automatic water surface cleaning device is determined, the attitude change and / or trajectory of the automatic water surface cleaning device can be determined based on the estimated attitude change and / or trajectory of the image sensor.

[0051] In other words, based on feature matching between at least one pair of image frames, a reference value for the attitude change of the automatic water surface cleaning device during the acquisition period of the at least one pair of image frames can be obtained.

[0052] As an example, when the automatic water cleaning device moves along the pool wall, it acquires real-time information about its surrounding environment, for example, by using an image sensor to capture image frames of the surrounding environment. Thus, objects in the surrounding environment (such as wall lamps, escalators, and other fixed structures on the pool wall) appear in the acquired image frames. As another example, based on feature matching of a pair of image frames, by identifying the correspondence between the feature points of at least one identical object (e.g., a wall lamp or escalator on the pool wall) in the pair of image frames, the attitude change of the image sensor during the acquisition period of the pair of image frames can be calculated. This allows the acquisition of the attitude change of the automatic water cleaning device, which can then be used as a reference value for the attitude change of the automatic water cleaning device during the acquisition period of the at least one pair of image frames.

[0053] Furthermore, according to embodiments of this disclosure, based on the order of timestamps, multiple frames of motion attitude data can be inserted between the at least one pair of image frames; thereby, an estimate of the attitude change of the automatic water surface cleaning device during the acquisition period of the at least one pair of image frames can be calculated based on at least a portion of the multiple frames of motion attitude data.

[0054] As an example, the motion attitude data includes at least one of the following: acceleration data (e.g., acceleration values ​​about the XYZ axes) and angular velocity data (e.g., angular velocity values ​​about the XYZ axes) acquired by the IMU equipped with the automatic surface cleaning device. Based on the acceleration and angular velocity data acquired by the IMU, attitude data such as the pitch angle, yaw angle, and / or roll angle of the automatic surface cleaning device can be calculated, thereby obtaining an estimate of the attitude change of the automatic surface cleaning device during the acquisition period of at least one pair of image frames.

[0055] According to embodiments of this disclosure, after obtaining reference values ​​and estimated values ​​of the attitude change of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames, a correction value of the attitude change of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames can be obtained based on the difference between the estimated value of the attitude change and the reference value of the attitude change.

[0056] Therefore, the errors in the motion attitude data acquired by the IMU can be corrected based on the obtained correction values ​​of attitude changes.

[0057] According to embodiments of this disclosure, in order to improve the stability and accuracy of error correction for motion posture data, correction values ​​for the posture changes of the automatic water surface cleaning device within a predetermined time period including multiple image frames can be obtained. For example, multiple image frames can be acquired within the predetermined time period, and feature matching can be performed on the multiple image frames to identify at least one feature point of the same object in the multiple image frames. Based on the feature matching in the multiple image frames, the posture change of the image sensor during the predetermined time period can be calculated, thereby obtaining the posture change of the automatic water surface cleaning device during the predetermined time period. This serves as a reference value for the posture change of the automatic water surface cleaning device during the predetermined time period, so as to constrain the motion posture data acquired by the IMU during the predetermined time period and eliminate unreasonable data values ​​in the motion posture data acquired by the IMU due to interference from various factors.

[0058] In addition, multiple frames of motion attitude data can be acquired within the predetermined time period, and the attitude change of the automatic water surface cleaning device during the predetermined time period can be calculated based on the multiple frames of motion attitude data. This calculation serves as an estimate of the attitude change of the automatic water surface cleaning device during the predetermined time period. Furthermore, the estimated attitude change can be used to further constrain the attitude calculation based on image frames to make it converge and avoid divergence, thereby improving the stability of the attitude correction of the automatic water surface cleaning device.

[0059] Therefore, based on the data collected by the image sensor and IMU, the attitude changes of different types of sensors within a predetermined time period are obtained, and then the reference value and estimated value of the attitude change of the automatic water surface cleaning device within the predetermined time period are obtained. The difference between the two is used as the correction value for the attitude estimation obtained based on the motion attitude data collected by the IMU. This value is then applied to the subsequent IMU attitude estimation to achieve dynamic correction of the attitude of the automatic water surface cleaning device.

[0060] According to another aspect of this disclosure, an automatic water surface cleaning device is also proposed. For example... Figure 5 As shown, the automatic water surface cleaning device 500 includes a processor 510 configured to cause the automatic water surface cleaning device to perform the above-described method when executing one or more instructions.

[0061] According to embodiments of this disclosure, such as Figure 5 As shown, the automatic water surface cleaning device 500 further includes at least one of the following: an image sensor 520 for acquiring image information of surrounding objects during the movement of the automatic water surface cleaning device; and an inertial measurement unit 530 for acquiring motion attitude data of the automatic water surface cleaning device, wherein the motion attitude data includes at least one of acceleration data and angular velocity data.

[0062] As an example, processor 510 includes, but is not limited to, control units such as central processing unit (CPU), microprocessor (MPU), graphics processor (GPU) or digital signal processor (DSP); it can perform preprocessing such as denoising and image enhancement on image information acquired by image sensor, and perform operations such as feature extraction, feature matching and feature fusion based on the preprocessed image information, thereby calculating the attitude change of the automatic water surface cleaning device based on the acquired image information.

[0063] As an example, the image sensor 520 includes, but is not limited to, at least one of the following: a monocular camera, a binocular camera, a depth camera, and a panoramic camera.

[0064] In addition, the image sensor 520 may also include a grayscale camera or an RGB camera.

[0065] Equipped with an image sensor, the automatic water surface cleaning device can acquire image information about the surrounding environment. For example, it can acquire still images and / or video frames of surrounding objects, thereby obtaining information about the objects such as edges, textures, sizes, and colors.

[0066] Various aspects of this disclosure have been presented above with reference to various apparatuses and methods. These apparatuses and methods are illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively, “elements”). These elements can be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented in hardware or software depends on the specific application and the design constraints on the overall system.

[0067] Therefore, in one or more example embodiments, the described functionality can be implemented using hardware, software, or any combination thereof. If implemented in software, these functions can be stored or encoded as one or more instructions or code on a computer-readable medium. A computer-readable medium includes a computer storage medium. The storage medium can be any available medium accessible by a computer.

[0068] It should be understood that the specific order or hierarchy of blocks in the disclosed process / flowchart is illustrative of the exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of blocks in the process / flowchart can be rearranged. Furthermore, some blocks can be combined or omitted. The appended method claims present elements of various blocks in a sample order and are not intended to limit one to the specific order or hierarchy presented.

[0069] The foregoing description is provided to enable those skilled in the art to practice the various aspects described herein. Unless otherwise stated, references to elements in the singular form are not intended to mean "one and only one," but rather "one or more." The term "exemplary" as used herein means "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects. Unless otherwise stated, the term "some" means one or more. Combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C.

[0070] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "setting," "connection," "linking," "fixing," and "coupling," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communicative connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0071] Obviously, the embodiments described above are merely some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features, all of which are within the patent protection scope of this application.

Claims

1. A method for controlling an automatic water surface cleaning device, comprising: Control the automatic water surface cleaning device to move on the water surface; Collect motion posture data of the automatic water surface cleaning device; Collect image information of objects around the automatic water surface cleaning device; Based on the motion posture data and the image information, the correction value for the posture change of the automatic water surface cleaning device is obtained; as well as Based on the correction value of the posture change, the error of the motion posture data is corrected.

2. The method according to claim 1, wherein, Based on the motion posture data and the image information, obtaining the correction values ​​for the posture changes of the automatic water surface cleaning device includes: Based on the motion posture data, an estimated value for the posture change of the automatic water surface cleaning device is obtained; Based on the image information, a reference value is obtained regarding the attitude change of the automatic water surface cleaning device; and Based on the estimated value of the attitude change and the reference value of the attitude change, the correction value of the attitude change of the automatic water surface cleaning device is obtained.

3. The method according to claim 2, wherein, The motion pose data includes multi-frame motion pose data with timestamps, the image information includes at least one pair of image frames with timestamps, and the method further includes: At least a portion of the multi-frame motion pose data is inserted between at least one pair of image frames based on timestamp order.

4. The method according to claim 3, further comprising: Based on at least a portion of the multi-frame motion attitude data, the estimated values ​​of the attitude changes of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames are calculated. as well as Based on feature matching between the at least one pair of image frames, a reference value is obtained for the attitude change of the automatic water surface cleaning device during the acquisition period of the at least one pair of image frames.

5. The method according to claim 4, further comprising: Based on the difference between the estimated value of the attitude change and the reference value of the attitude change, the correction value of the attitude change of the automatic water surface cleaning device during the acquisition period of at least one pair of image frames is obtained.

6. The method according to any one of claims 3-5, further comprising: Obtain the correction value of the attitude change of the automatic water surface cleaning device during the acquisition period including multiple pairs of image frames; as well as The error in the motion posture data is corrected based on the correction value of the posture change of the automatic water surface cleaning device during the acquisition period including multiple pairs of image frames.

7. The method according to any one of claims 1-6, wherein, The motion posture data includes at least one of the following: The automatic water surface cleaning device is equipped with an inertial measurement unit that collects acceleration data and angular velocity data.

8. The method according to any one of claims 1-7, wherein, The image information includes image information collected by the image sensor equipped with the automatic water surface cleaning device, wherein the image sensor includes at least one of the following: Monocular camera, binocular camera, depth camera, panoramic camera.

9. An automatic water surface cleaning device, comprising: The processor is configured to, when executing one or more instructions, cause the automatic water surface cleaning device to perform the method according to any one of claims 1-8.

10. The automatic water surface cleaning device according to claim 9, further comprising at least one of the following: An inertial measurement unit collects motion attitude data of an automatic water surface cleaning device, wherein the motion attitude data includes at least one of acceleration data and angular velocity data; and An image sensor is used to collect image information of surrounding objects as the automatic water surface cleaning device moves.

Images