Swimming pool overwater map creating method and swimming pool cleaning equipment

Abstract

The invention relates to the technical field of swimming pool cleaning equipment, and provides a method for creating a water map of a swimming pool. The method comprises the following steps: generating an instruction for creating an overwater map; based on the instruction, position information of a swimming pool robot floating on the water surface is obtained; obtaining swimming pool boundary information collected by the swimming pool robot through a laser radar or an image sensor; and on the basis of the position information and the swimming pool boundary information, a water map of the swimming pool is generated, convenience is provided for water work of the swimming pool cleaning equipment, the working efficiency of the swimming pool cleaning equipment is improved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of robotics, and in particular to a method for creating a swimming pool water map and a swimming pool cleaning device. Background Art

[0002] At present, most pool cleaning robots cannot clean the water surface. The few pool cleaning robots that can clean the water surface generally adopt a random walking mode to clean the water surface without the concept of positioning and mapping. This implementation method is not smart enough, has low cleaning efficiency, low coverage, and poor user experience.

[0003] Or the sensors used in map construction may not measure accurately and may be easily affected by the environment, resulting in map construction failure or large errors, making the map unusable directly. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a method and device for creating a swimming pool water map to solve the problem in the prior art that there is no water map of the swimming pool or the map is inaccurate.

[0005] According to a first aspect of an embodiment of the present application, a method for creating a swimming pool water map is provided, comprising:

[0006] Generate instructions for creating a water map;

[0007] Based on the instruction, obtaining position information of the swimming pool robot floating on the water surface;

[0008] Acquiring the swimming pool boundary information collected by the swimming pool robot through a laser radar or an image sensor;

[0009] A water map of the swimming pool is generated based on the location information and the swimming pool boundary information.

[0010] Furthermore, it also includes determining whether the swimming pool boundary of the water map is closed. If not, controlling the swimming pool cleaning robot to collect the unclosed area of ​​the boundary to generate a final water map.

[0011] Furthermore, the position information or the swimming pool boundary information is calibrated by an IMU on the swimming pool robot.

[0012] Further, controlling the swimming pool cleaning robot to collect the unclosed area of ​​the boundary includes controlling the swimming pool cleaning robot to move toward the unclosed area.

[0013] Furthermore, the unclosed area includes at least two areas; and controlling the swimming pool robot to move toward the unclosed area includes: determining a target boundary unclosed area that is closest to the swimming pool robot; and controlling the swimming pool robot to move to the target boundary unclosed area.

[0014] Furthermore, the boundary information includes obstacle information on the water surface.

[0015] Furthermore, the method also includes, after generating the water map of the swimming pool, in response to receiving a command to summon a robot, the command including target position information; based on the target position information and the water map, controlling the swimming pool robot to move to the target position.

[0016] Furthermore, the method also includes, after generating the water map of the swimming pool, in response to receiving a swimming pool cleaning instruction, controlling the swimming pool robot to clean the swimming pool and recording the cleaned area in the water map; in response to receiving a cleaning pause instruction, recording the target position and target posture of the swimming pool robot at the current moment in the water map; in response to receiving a continue cleaning instruction, controlling the swimming pool robot to move to the target position and adjust to the target posture; planning a cleaning path in the water map, and controlling the swimming pool robot to clean the swimming pool along the cleaning path.

[0017] Furthermore, after creating the above-water map of the swimming pool, the method also includes: obtaining an underwater map of the swimming pool, the underwater map having an underwater coordinate system origin; obtaining a displacement between the underwater coordinate system origin and the coordinate system origin of the above-water map; moving the underwater coordinate system origin based on the displacement, or moving the coordinate system origin of the above-water map to align the moved underwater coordinate system origin with the coordinate system origin of the above-water map; in response to determining that there is a non-overlapping area at the boundary of the underwater map and the above-water map after the alignment operation is performed, determining that the non-overlapping area is a swimming pool step area.

[0018] According to a second aspect of an embodiment of the present application, a swimming pool cleaning device is provided, which is equipped with a laser radar or a camera. The swimming pool boundary information collected by the swimming pool robot is obtained through the laser radar or the camera, and combined with the position information of the swimming pool robot, it is used to generate a water map of the swimming pool.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the embodiments of the present application generate instructions for creating a water map; based on the instructions, obtain the position information of the pool robot floating on the water surface; obtain the pool boundary information collected by the pool robot through a laser radar or an image sensor; and generate the pool water map based on the position information and the pool boundary information. This solves the technical problem that the current pool robot has no pool water map to refer to when working on the water surface, realizes autonomous water surface mapping, provides convenience for the pool robot's work on the water surface, improves the pool robot's work efficiency, and enhances the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart of a method for creating a swimming pool water map provided in an embodiment of the present application.

[0022] FIG2(A) is a schematic diagram of a global map with an unclosed boundary provided in an embodiment of the present application.

[0023] FIG2(B) is a schematic diagram of another global map with an unclosed boundary provided in an embodiment of the present application.

[0024] Figure 3 It is a flowchart of a method for controlling a swimming pool robot to move to an unclosed boundary area in a global map provided in an embodiment of the present application.

[0025] Figure 4 It is a flow chart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0026] Figure 5 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0027] Figure 6 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0028] Figure 7 This is a flow chart of yet another method for creating a swimming pool water map provided in an embodiment of the present application.

[0029] Figure 8 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0030] Fig. 9 It is a schematic diagram of a swimming pool water map creation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0032] A method and device for creating a swimming pool water map according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0033] As mentioned above, most of the current pool cleaning robots cannot clean the water surface. The few pool cleaning robots that can clean the water surface generally adopt a random walking mode to clean the water surface without the concept of positioning and mapping. This implementation method is not smart enough, has low cleaning efficiency, low coverage, and poor user experience.

[0034] In view of this, the embodiment of the present application provides a method for creating a swimming pool water map, by generating an instruction for creating a water map; based on the instruction, obtaining the position information of a swimming pool robot floating on the water surface; obtaining the swimming pool boundary information collected by the swimming pool robot through a laser radar or an image sensor; and generating the swimming pool water map based on the position information and the swimming pool boundary information. This solves the technical problem that there is no swimming pool water map to refer to when the swimming pool robot is working on the water surface, realizes autonomous water surface mapping, provides convenience for the swimming pool robot's work on the water surface, improves the working efficiency of the swimming pool robot, and enhances the user experience.

[0035] Secondly, compared with traditional ultrasonic ranging sensor mapping, the lidar or image sensor used in the present invention has significant advantages in accuracy, resolution, anti-interference ability, real-time and speed. Regardless of the case of single mapping, the boundary map can be established more accurately, and when a single map scan fails to cover the entire map, it is only necessary to move forward to the unclosed area and measure again to obtain the global map. It has more advantages than ultrasonic sensors in terms of accuracy and ease of operation.

[0036] Figure 1 FIG. 1 is a flow chart of a method for creating a swimming pool water map provided in an embodiment of the present application. Figure 1 As shown, the method includes the following contents:

[0037] Generate instructions for creating a water map; based on the instructions, obtain position information of a pool robot floating on the water surface; obtain pool boundary information collected by the pool robot through a laser radar or an image sensor; and generate a water map of the pool based on the position information and the pool boundary information.

[0038] In the above method, the method for creating a swimming pool water map can be executed by a terminal. Further, the method for creating a swimming pool water map can be executed in a swimming pool robot associated application in the terminal. The instruction to create a water map can be sent by a user, or it can be triggered by the terminal itself when a preset condition is met.

[0039] Furthermore, after receiving the command to create a water map, the terminal obtains the position information of the pool robot floating on the water surface; obtains the pool boundary information collected by the pool robot through a laser radar or an image sensor; and generates a water map of the pool based on the position information and the pool boundary information. Specifically, after the robot floats to the water surface, the sensor carried by the pool robot is activated according to the position information of the pool robot to scan the surrounding environment. The sensor includes at least part of the pool boundary information, and the pool boundary information can be the position information of the pool wall. The sensor uses a laser radar or an image sensor.

[0040] For the position information of the swimming pool robot, the initial position of the swimming pool robot can be obtained, the initial position can be determined as the origin of the coordinate system, and a global map can be generated based on the origin of the coordinate system and the first information of the sensor. In the above steps, the initial position of the swimming pool robot can be the position of the swimming pool robot when the swimming pool robot obtains sensor information through the sensor it carries. The initial position of the swimming pool robot can also be obtained as the coordinate information of the world coordinate system, and a global map can be generated based on the coordinate information and the swimming pool boundary information. Therefore, generating a global map can be to use the initial position of the swimming pool robot as the origin of the coordinate system, obtain the relative position information about the pool wall detected by the sensor, and convert each position information into coordinates in the coordinate system, thereby obtaining a global map. Alternatively, the coordinate system is a world coordinate system, and the swimming pool robot can obtain coordinate information through a positioning device such as GPS, thereby obtaining a global map.

[0041] Further, in response to the closure of the boundary of the global map, the global map is determined to be a water map of the swimming pool.

[0042] In the above steps, if the boundary of the global map generated by the sampling method is closed, it can be considered that the water map of the swimming pool has been created, and the global map is directly determined as the water map of the swimming pool.

[0043] That is to say, if the range of the sensor carried by the pool robot is sufficient and there are no obstacles on the water surface of the pool, the pool robot or the sensor carried by it can obtain a global map with closed boundaries after scanning one circle at the initial position.

[0044] Further, in response to the border of the global map not being closed, the swimming pool robot is controlled to move to the border-unclosed area in the global map.

[0045] In the above steps, if the boundaries of the global map generated by the sampling method are not closed, it can be considered that the water map of the swimming pool has not been created yet, and further map construction is required. Specifically, when the range of the sensor carried by the swimming pool robot is insufficient, or the water surface of the swimming pool includes obstacles, it can only obtain a global map containing part of the swimming pool boundary information at the initial position. At this time, the boundaries of the obtained global map are not closed.

[0046] In the above steps, when it is determined that the boundary of the global map is not closed, the swimming pool robot can be controlled to move to the unclosed boundary area in the global map to obtain boundary information of the unclosed area to generate the final water map.

[0047] For example, as shown in Figure 2(A), the box in the figure is a schematic diagram of the swimming pool boundary, where the swimming pool boundary is the part of the swimming pool wall on the water surface. The swimming pool robot is located on the swimming pool surface. Due to the limited range of the sensor it carries, the swimming pool robot cannot obtain information about the left side of the swimming pool boundary after scanning in situ. It can only obtain a global map as shown in the lower figure in Figure 2(A).

[0048] Alternatively, as shown in FIG2(B), the box in the figure is a schematic diagram of the swimming pool boundary, the swimming pool robot is located on the swimming pool surface, and there are obstacles on the water surface. Due to the occlusion of the obstacles, even if the range of the sensor carried by the swimming pool robot is sufficient, a global map as shown in the lower figure in FIG2(B) will be obtained.

[0049] It should be noted that the above only provides examples of global maps with partially unclosed boundaries. In actual use, global maps with unclosed boundaries may include other situations, which are not limited here.

[0050] In addition, when there are multiple areas on the boundary of the global map that are not closed, a corresponding movement method is proposed, as follows:

[0051] like Figure 3 As shown, the method comprises the following steps:

[0052] In step S301, the target boundary unclosed area closest to the swimming pool robot is determined.

[0053] In step S302, the swimming pool robot is controlled to move to the target boundary unclosed area.

[0054] Specifically, when the unclosed border area includes at least two areas, the target unclosed border area that is closest to the current distance of the pool robot can be first determined, and then the pool robot can be controlled to move to the target unclosed border area to perform water mapping on the area until the boundary of the area is closed. Next, if the remaining unclosed border area still includes multiple areas, the pool robot can continue to determine the target unclosed border area that is closest to the current distance of the pool robot from the remaining multiple areas, and control the pool robot to move to the target unclosed border area again until the water mapping of all unclosed border areas is completed.

[0055] Furthermore, when controlling the swimming pool robot to move to the unclosed boundary area in the global map, the swimming pool robot can be controlled to use the sensors it carries to obtain information while moving, and then use the obtained sensor information to generate a local map, and superimpose the local map on the global map to obtain an updated global map. Among them, the terminal can autonomously calculate and plan the driving path of the swimming pool robot so that the swimming pool robot moves to the unclosed boundary area, or the user can operate in the terminal to manually control the swimming pool robot to move to the unclosed boundary area, which is not limited here.

[0056] In the embodiment of the present application, when the boundary of the updated global map is still not closed, the swimming pool robot can continue to be controlled to move to the area of ​​the global map where the boundary is not closed, and continue to obtain sensor information during the movement, regenerate a local map based on the obtained sensor information, and overlay the local map on the global map to obtain an updated global map again, until the boundary of the updated global map is closed. At this time, the updated global map when the boundary is closed can be determined as the water map of the swimming pool.

[0057] Furthermore, the position information or the swimming pool boundary information is calibrated by an IMU on the swimming pool robot.

[0058] Specifically, when the pool robot is mapping on the water surface, it will inevitably be tilted due to the shaking of the water surface. At this time, the position information or the pool boundary information obtained will be biased. The IMU (inertial measurement unit) can be used to obtain the posture information of the pool robot at different times, and the position information or pool boundary information obtained by the sensor at the corresponding time can be combined to calibrate the map. In other words, the sensor can measure the distance between the robot and the pool wall or other obstacles. Combined with the posture information of the IMU, the boundary map of the pool can be constructed and calibrated. The combination of the IMU and the sensor can significantly improve the accuracy of the position information and the reliability of the boundary information.

[0059] Furthermore, the sensor carried by the swimming pool robot may be a laser radar or an image sensor. The laser radar may be a two-dimensional laser radar or a three-dimensional laser radar.

[0060] When the sensor carried by the swimming pool robot is a two-dimensional laser radar, the boundary information is two-dimensional laser point cloud information of a local boundary, wherein the local boundary at least includes a portion of the boundary in an unclosed area of ​​the boundary.

[0061] When the sensor carried by the swimming pool robot is a three-dimensional laser radar, the boundary information is the three-dimensional laser point cloud information of the local boundary.

[0062] When the sensor carried by the pool robot is an image sensor, the boundary information is the image information of the local boundary. At this time, generating a local map based on the boundary information can be: extracting features from the image information to obtain three-dimensional image feature information of the local boundary; removing the vertical axis information in the three-dimensional image feature information to obtain the mapped image feature information mapped to the two-dimensional plane; and drawing the mapped image feature information to the coordinate system of the global map to obtain the local map.

[0063] That is to say, when the sensor carried by the pool robot is a two-dimensional laser radar or a three-dimensional laser radar, the laser radar can be used to scan the water surface to obtain the contour information of the pool wall. If it is a single-line laser radar, that is, a two-dimensional laser radar, it obtains the two-dimensional contour of the pool, and if it is a multi-line laser radar, that is, a three-dimensional laser radar, it obtains the three-dimensional contour of the pool. When the pool robot moves, it will generate a translation and a rotation, where the translation includes the horizontal coordinate translation and the vertical coordinate translation, and the rotation is used to characterize the movement angle of the pool robot. At this time, the point cloud information obtained by the laser radar carried by the pool robot when scanning the same object will also change accordingly. This change is a posture change that has undergone rotation and translation. The rotation value and translation value can be calculated to obtain the rotation value and translation value of each sampling frame during the movement of the pool robot, and then a local map is generated based on the calculated rotation value and translation value of each sampling frame.

[0064] Among them, the rotation and translation values ​​of each sampling frame can be calculated in combination with the inertial measurement unit (IMU). In one example, the rotation and translation values ​​of each sampling frame with error of the swimming pool robot body can be first calculated by IMU integral calculation, and the moving speed of the swimming pool robot can be obtained. Then the point cloud data of the current frame is used as the observation value, and the normal distribution transform (Normal Distributions Transform, NDT) residual between the point cloud data of the current frame and the point cloud map is calculated. Finally, the information-extended Kalman filter (IEKF) method is used to update the error-bearing rotation and translation values ​​estimated by IMU using the point cloud observation data and NDT residual, so as to obtain more accurate rotation and translation values ​​of each sampling frame. Further, the local map can be generated by fixing the point cloud data of the first frame, and then using the estimated point cloud rotation and translation values ​​of each frame to align the point cloud information of the current frame to the fixed first frame point cloud to form a point cloud map.

[0065] In the embodiment of the present application, when the sensor carried by the swimming pool robot is an image sensor, a feature point extraction algorithm can be used to extract feature information from each frame of the image and calculate the description value of the feature, and the image feature usually includes corner points and edge features. The description value of the feature point is then used to perform feature point matching on the current frame image and the previous frame image, and the relative motion between the two frames of the image is estimated by using the pose estimation algorithm (Perspective-n-Point, PnP) through feature point matching. In this way, the rotation value and translation value of the current swimming pool robot relative to the initial position can be obtained when the swimming pool robot is constantly moving, and then a local map can be generated based on the rotation value and translation value of the robot at each position.

[0066] Furthermore, the image sensor can also be combined with the IMU for positioning to generate a local map. In one example, the rotation and translation values ​​of the swimming pool robot body with errors can be first obtained through IMU integration, and the moving speed of the swimming pool robot can be obtained. Then, the line features and point feature information of the swimming pool boundary are obtained from the image collected by the image sensor as observations. The constraint relationship between the point or line features between adjacent frames is used as an observation, and the rotation and translation values ​​with errors are updated using the Multi-State Constraint Kalman Filter (MSCKF) method to obtain a more accurate position and posture of the swimming pool robot. Finally, a local map is generated based on the more accurate position and posture of the swimming pool robot obtained.

[0067] In the embodiment of the present application, when generating a local map, if laser radar or laser radar and IMU fusion are used for positioning, after obtaining the rotation and translation values ​​of the laser radar, the point cloud obtained by the laser radar scanning can be converted into the coordinate transformation relationship. Figure 1 When using an image sensor or an image sensor and IMU fusion for positioning, after obtaining the rotation value and translation value, the point and edge information of the image can be drawn in the world coordinate system according to the coordinate transformation relationship to obtain a grid map.

[0068] like Figure 4 As shown, the method also includes the following steps:

[0069] In response to receiving the instruction to create a water surface obstacle map, the swimming pool robot obtains obstacle information on the water surface.

[0070] Furthermore, a local obstacle map is generated based on the obstacle information on the water surface, and the local obstacle map is superimposed on the global map to obtain a water surface obstacle map.

[0071] In the embodiment of the present application, when receiving the command to create a water surface obstacle map, the terminal can obtain obstacle information on the water surface from the pool robot. The obstacle information on the water surface can be obtained by the pool robot moving around the water surface obstacles. Furthermore, a local obstacle map can be generated based on the obstacle information on the water surface, and the local obstacle map is superimposed on the global map to obtain a water surface obstacle map.

[0072] That is to say, when the pool cleaning robot is cleaning the water surface, it may encounter some large obstacles, such as toy water guns, clothes and other daily necessities. To improve the efficiency of water surface cleaning, these obstacles can be mapped first, and then the cleaning path of the pool robot can be planned with reference to the global map and the water surface obstacle map.

[0073] When creating a water surface obstacle map, the laser radar point cloud or image sensor (such as a camera) carried by the pool robot can be used for intelligent identification, and the position of the obstacle in the machine coordinate system can be obtained according to the corresponding algorithm, and finally transferred to the map. Among them, the positioning and local map generation method during obstacle identification are basically the same as the method described above for constructing a local map of an unclosed boundary area when the pool robot moves to an unclosed boundary area, and will not be repeated here.

[0074] It should be noted that the step of creating a partial obstacle map can be performed after the creation of the swimming pool's water map is completed. In some cases, the step of creating a partial obstacle map can also be performed before the creation of the swimming pool's water map is completed. In this case, after the partial obstacle map is created, the partial obstacle map can be temporarily stored until the swimming pool's water map is created, and then the partial obstacle map can be superimposed on the swimming pool's water map to obtain a water surface obstacle map.

[0075] Figure 5 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0076] like Figure 5 As shown, the method also includes the following contents:

[0077] In response to receiving the summon robot instruction, a summon position is obtained from the summon robot instruction.

[0078] Determine the target location of the summon location in the water map.

[0079] Control the pool robot to move to the target position.

[0080] In an embodiment of the present application, after the water map of the swimming pool is created, if the terminal receives a robot summoning instruction, for example, the user executes a robot summoning operation in the terminal application, the summoning position can be obtained from the robot summoning instruction, and the summoning position is the target position that the user expects the swimming pool robot to reach.

[0081] The summoning instruction can be a user directly clicking a point in the water map as the summoning position, and the position clicked by the user is the target position of the summoning position in the water map. On the other hand, the summoning instruction can also be a voice instruction sent by the user, such as "recall the robot to the center of the swimming pool". At this time, the key information "the center of the swimming pool" in the voice instruction can be extracted, and the center position of the swimming pool water map calculator can be used to finally determine the center position of the water surface map as the target position of the summoning position in the water map.

[0082] In the embodiment of the present application, after the target position is determined, the swimming pool robot can be controlled to move to the target position, thereby realizing the summoning of the swimming pool robot to any position.

[0083] That is to say, after the pool robot finishes cleaning, it may be in the middle of the pool or at the bottom of the water, which is inconvenient for users to obtain. When the pool robot needs to be obtained, the user can send a machine summoning command to the terminal application. The machine summoning command includes the location of the pool robot, which is recorded as X. At this time, if the pool robot is at the bottom of the water, it will first float vertically to the surface of the water after receiving the machine summoning command, and then match the collected point cloud with the map point cloud by rotating the laser radar to determine the current position of the robot in the pool water map. Next, a path to X is planned based on the determined current position, and it moves along the path to point X, thereby completing the user summoning.

[0084] Figure 6 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0085] like Figure 6 As shown, the method also includes the following contents:

[0086] In response to receiving the call-to-clean instruction, a call-to-clean area is obtained from the call-to-clean instruction.

[0087] Determine the target area for the summon cleaning area in the water map.

[0088] Control the pool robot to move to the target area and clean the target area.

[0089] In the embodiment of the present application, after the water map of the swimming pool is created, if the terminal receives a call to clean command, the call to clean area can be obtained from the call to clean command, and then the target area of ​​the call to clean area in the water map can be determined. Finally, the swimming pool robot is controlled to move to the target area and clean the target area.

[0090] That is to say, after creating the swimming pool's water map, the user can directly specify a cleaning area in the swimming pool's water map in the terminal application, and the swimming pool robot can autonomously plan a path from the current position to the designated cleaning area, thereby realizing the call for cleaning. Among them, the method for determining the target area, the method for determining the current position of the swimming pool robot, and the path planning method are all the same as Figure 5 The implementation method in the illustrated embodiment is similar and will not be described again here.

[0091] Figure 7 This is a flow chart of yet another method for creating a swimming pool water map provided in an embodiment of the present application.

[0092] like Figure 7 As shown, the method also includes the following contents:

[0093] In response to receiving the swimming pool cleaning instruction, the swimming pool robot is controlled to clean the swimming pool and the cleaned area is recorded in the water map.

[0094] In response to receiving the cleaning pause instruction, the target position and target posture of the swimming pool robot at the current moment are recorded in the water map.

[0095] In response to receiving the continue cleaning instruction, the swimming pool robot is controlled to move to a target position and adjust to a target posture.

[0096] A cleaning path is planned in the area other than the cleaned area in the water map, and the pool robot is controlled to clean the pool along the cleaning path.

[0097] In an embodiment of the present application, after creating an aquatic map of the swimming pool, the swimming pool robot can clean the swimming pool after receiving a swimming pool cleaning instruction and record the cleaned area in the aquatic map. When receiving a cleaning pause instruction, the target position and target posture of the swimming pool robot at the current moment can be recorded in the aquatic map. The cleaning pause instruction can be sent by the user through a terminal application, or it can be automatically generated when the swimming pool robot detects that it is out of water. Furthermore, the current moment can be the moment when the swimming pool robot last cleaned the swimming pool before stopping cleaning the swimming pool.

[0098] In the embodiment of the present application, when the terminal receives the continue cleaning instruction, the pool robot can be controlled to move to the target position and adjust to the target posture. Furthermore, a cleaning path can be planned in the area other than the cleaned area in the water map, and the pool robot can be controlled to clean the pool along the cleaning path.

[0099] That is to say, when the pool robot's task of cleaning the pool is re-executed after an interruption, the pool robot can be repositioned on the water surface and continue to sweep based on the constructed water map. For example, when the user picks up the pool robot and throws it back into the water, the pool robot will disappear on the terminal application and needs to be repositioned. By controlling the robot's rotation to match the current laser point cloud with the map point cloud, the robot's posture (including rotation and translation values) can be obtained. If the repositioning is successful, the robot's position will appear on the terminal application, and the path planning can be re-performed at this time.

[0100] Figure 8 It is a flowchart of another method for creating a swimming pool water map provided in an embodiment of the present application.

[0101] like Figure 8 As shown, the method also includes the following steps:

[0102] Get an underwater map of your pool.

[0103] The underwater map has an origin of an underwater coordinate system.

[0104] Get the displacement between the origin of the underwater coordinate system and the origin of the coordinate system of the water map.

[0105] In the above steps, you can first create an underwater map and record the origin of the underwater coordinate system. After the underwater map is created, control the swimming pool robot to move to the initial position for creating the water map, that is, start creating the water map from the origin of the coordinate system of the water map. In this process, the application in the terminal can record the movement trajectory of the swimming pool robot throughout the process, and then obtain and save the displacement between the origin of the underwater coordinate system and the origin of the coordinate system of the water map. It should be noted that the displacement between the origin of the underwater coordinate system and the origin of the coordinate system of the water map can also be determined and saved in other ways, which is not limited here.

[0106] The underwater coordinate system origin is moved based on the displacement, or the coordinate system origin of the surface map is moved, so that the moved underwater coordinate system origin is aligned with the coordinate system origin of the surface map.

[0107] In the above steps, the origin of the underwater coordinate system can be moved by the above displacement amount to align the origin of the underwater coordinate system with the origin of the coordinate system of the surface map. Alternatively, the origin of the coordinate system of the surface map can be moved by the above displacement amount to align the origin of the underwater coordinate system with the origin of the coordinate system of the surface map. For example, if the displacement between the origin of the underwater coordinate system and the origin of the coordinate system of the surface map is (-1, -1), the origin of the coordinate system can be moved from (0, 0) to (-1, -1) in the surface map, so that the origin of the coordinate system of the surface map is moved to the original (-1, -1) position, and the origin of the underwater map and the surface map are now at the same position.

[0108] In response to determining that a non-overlapping area exists between the boundaries of the underwater map and the above-water map after the alignment operation is performed, the non-overlapping area is determined to be a swimming pool step area.

[0109] In the above steps, the underwater map after the origin of the coordinate system is aligned can be compared with the surface map. If there is a non-overlapping area in the swimming pool boundary, it can be determined that the non-overlapping area is the swimming pool step area.

[0110] Furthermore, the non-overlapping area can be determined in the following manner: if the first target point in the underwater map and the second target point in the above-water map have the same horizontal coordinate value, and the vertical coordinate values ​​of the first target point and the second target point are greater than a preset threshold, then the first target point and the second target point can be determined to be non-overlapping points. Also, if the third target point in the underwater map and the fourth target point in the above-water map have the same vertical coordinate value, and the horizontal coordinate values ​​of the third target point and the fourth target point are greater than a preset threshold, then the three target points and the fourth target point can be determined to be non-overlapping points. Finally, the area formed by all the second target points and all the fourth target points in the above-water map is determined to be a non-overlapping area. Among them, the preset threshold can be set according to actual needs and is not limited here.

[0111] That is to say, the method for creating a swimming pool water map provided in the embodiment of the present application can execute the mapping process in the following manner:

[0112] 1) Execute the water mapping command.

[0113] 2) Place the robot on the water surface and allow it to move autonomously.

[0114] 3) Define the first frame pose as the world coordinate system, and define the map generated by the first frame sensor information as the global map.

[0115] 4) For the sensor information at each timestamp, a local two-dimensional grid map is obtained through the sensor information.

[0116] 5) Based on the sensor information, estimate the robot's position information in the world coordinate system at each moment, and use the position information to match (superimpose) the local grid map of the current timestamp into the global map.

[0117] 6) If it is determined that the map building is completed, a new map is obtained.

[0118] Among them, the autonomous movement of the robot in step 2) can be: if a two-dimensional or laser radar is used, the distance information from the edge of the swimming pool obtained by the laser radar can be used to control the robot to reach a relatively central position in the swimming pool. If the map boundary is closed at this time, the map is built; if the map boundary is not closed at this time, the robot will move to the area where the map boundary is missing until the map is completely closed. If an image sensor such as a camera is used to obtain an image, the robot will perform a rotation movement in the swimming pool. After scanning for one week, the map boundary is closed and the map is built. If manual control is used, the map boundary can be closed according to the position of the robot's movement manually, and the map is built.

[0119] The mapping process in step 4) can be that if a two-dimensional laser radar sensor is used, the two-dimensional laser point cloud information can be directly obtained, and the point cloud information is drawn to the world coordinate system, and the obtained swimming pool outline is the local grid map. If a three-dimensional laser radar sensor is used, the three-dimensional point cloud needs to be mapped to a two-dimensional plane by removing the z-axis, and then the mapped two-dimensional point cloud information is drawn to the world coordinate system to obtain a local grid map. If the image information obtained by the camera is used, the point feature and line feature information in the swimming pool environment need to be obtained through the Fast point feature extraction algorithm and the line segment detection algorithm (Line Segment Detector, LSD). The three-dimensional information of the image features is obtained by using the triangulation depth estimation method. Finally, the feature extraction results are mapped to a two-dimensional plane by removing the z-axis, and drawn to the world coordinate system to obtain a local grid map.

[0120] The technical solution provided by the embodiment of the present application solves the problem of the current swimming pool robot having no map on the water surface, and the constructed swimming pool water map can be pushed to the terminal application display. On the basis of the constructed swimming pool water map, the water surface obstacle map can be superimposed and displayed, the water surface call cleaning can be realized, the water surface repositioning and continued sweeping can be realized, and the water map can be compared with the underwater map of the swimming pool to realize the positioning of the swimming pool step area.

[0121] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0122] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0123] Fig. 9 Schematic diagram of a swimming pool water map creation device provided in an embodiment of the present application. Fig. 9 As shown, the device comprises:

[0124] A laser radar or a camera is provided, and the following method can be performed, including:

[0125] Generate instructions for creating a water map;

[0126] Based on the instruction, obtaining position information of the swimming pool robot floating on the water surface;

[0127] Acquiring the swimming pool boundary information collected by the swimming pool robot through a laser radar or an image sensor;

[0128] A water map of the swimming pool is generated based on the location information and the swimming pool boundary information.

[0129] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0130] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for creating a swimming pool water map, characterized in that: The method comprises: Generate instructions for creating a water map; Based on the instruction, obtaining position information of the swimming pool robot floating on the water surface; Acquiring the swimming pool boundary information collected by the swimming pool robot through a laser radar or an image sensor; A water map of the swimming pool is generated based on the location information and the swimming pool boundary information.

2. The method according to claim 1, characterized in that The method also includes determining whether the swimming pool boundary of the water map is closed. If not, controlling the swimming pool cleaning robot to collect the unclosed area of ​​the boundary to generate a final water map.

3. The method according to any one of claims 1 to 2, characterized in that: The position information or the pool boundary information is calibrated by an inertial measurement unit on the pool robot.

4. The method according to claim 2, characterized in that: Controlling the swimming pool cleaning robot to collect the unclosed area of ​​the boundary includes controlling the swimming pool cleaning robot to move toward the unclosed area.

5. The method according to claim 3, characterized in that: The unclosed area includes at least two areas; The controlling the swimming pool robot to move toward the unclosed area comprises: Determine the target boundary unclosed area closest to the swimming pool robot; The swimming pool robot is controlled to move to the target boundary unclosed area.

6. The method according to claim 2, characterized in that The boundary information includes obstacle information on the water surface.

7. The method according to any one of claims 1-2, characterized in that: The method further includes, after generating the water map of the swimming pool, in response to receiving a robot summoning instruction, the instruction including target position information; based on the target position information and the water map, controlling the swimming pool robot to move to the target position.

8. The method according to any one of claims 1-2, characterized in that: The method further comprises, after generating the water map of the swimming pool, In response to receiving a swimming pool cleaning instruction, controlling the swimming pool robot to clean the swimming pool and recording the cleaned area in the water map; In response to receiving a cleaning pause instruction, recording a target position and a target posture of the swimming pool robot at a current moment in the water map; In response to receiving a continue cleaning instruction, controlling the swimming pool robot to move to the target position and adjust to the target posture; A cleaning path is planned in the water map, and the swimming pool robot is controlled to clean the swimming pool along the cleaning path.

9. The method according to any one of claims 1-2, characterized in that: After creating the water map of the swimming pool, the method further includes: Obtaining an underwater map of the swimming pool, wherein the underwater map has an origin of an underwater coordinate system; Obtaining the displacement between the origin of the underwater coordinate system and the origin of the coordinate system of the water map; Moving the origin of the underwater coordinate system based on the displacement, or moving the origin of the coordinate system of the above-water map, so that the moved origin of the underwater coordinate system is aligned with the origin of the coordinate system of the above-water map; In response to determining that a non-overlapping area exists between the boundaries of the underwater map and the above-water map after the alignment operation is performed, the non-overlapping area is determined to be a swimming pool step area.

10. A swimming pool cleaning device, provided with a laser radar or a camera, for executing the method according to claims 1-9.

Images