Charging station

Abstract

Charging station, characterized in that the charging station comprises a charging station body (11) and a marking component (2), wherein the marking component (2) is used to indicate a position of the charging station (10) so that a robotic lawnmower can dock with the charging station for charging, wherein the marking component (2) comprises a first marking component (20, 211), wherein a plurality of first marking components (20, 211) are provided, which are arranged on the same side surface of the charging station body (11), wherein a marking pattern is formed by the first marking components (20, 211) on a surface of the charging station body (11), wherein the minimum inner diameter in the marking pattern is greater than or equal to a first preset threshold value, and wherein the first preset threshold value is 3 cm.

Description

Technical area

[0001] Embodiments of the present application relate to the technical field of garden tools, in particular to a charging station. Technical background

[0002] Robotic lawn mowers can mow lawns, etc., automatically, reducing the time spent on manual labor. Robotic lawn mowers can follow input instructions to return to a charging station without human intervention, reducing user burden and saving time.

[0003] Most existing technologies for returning robotic lawn mowers to their charging stations are based on methods such as GPS positioning, guide wire guidance, or virtual boundary patrol. For example, in indoor deployment scenarios, robotic lawn mowers typically use infrared or ultrasonic induction technology to return to the charging station, or map-based virtual boundary guidance to return to the charging station. When returning to the charging station using infrared or ultrasonic induction technology, there is a high probability of false contact, and such a return is severely affected by ambient noise.

[0004] In outdoor deployment scenarios, robotic lawnmowers typically return precisely to the charging station based on GPS positioning and the electromagnetic guide wires in front of the charging station, which serve to assist with guidance. This GPS-based return to the charging station not only places high demands on signal strength and accuracy, but also requires the installation of supporting electromagnetic guide wires in a base plate of the charging station, which also incurs certain material and transportation costs.

[0005] In summary, it is expensive, difficult and less stable for existing robotic lawnmowers to automatically return to the charging station. Content of the invention

[0006] To solve the above-mentioned problems, embodiments of the present application provide a charging station to at least partially solve the above-mentioned problems.

[0007] One or more embodiments of the present application provide a charging station. The charging station comprises a charging station body and a marking component, wherein the marking component is used to indicate a position of the charging station so that a robotic lawnmower can dock with the charging station for charging. The marking component comprises a first marking component, wherein a plurality of first marking components are provided, which are arranged on the same side surface of the charging station body, wherein a marking pattern is formed by the first marking components on a surface of the charging station body, wherein the minimum inner diameter in the marking pattern is greater than or equal to a first preset threshold, and wherein the first preset threshold is 3 cm.

[0008] According to one or more embodiments of the present application, a marking pattern formed by the first marking components on a surface of the charging column body is a rectangular pattern.

[0009] According to one or more embodiments of the present application, four first marking components are provided, wherein adjacent ones of the first marking components are spaced apart from one another by a predetermined distance.

[0010] According to one or more embodiments of the present application, the minimum distance between the marking components is greater than or equal to a second preset threshold, wherein the second preset threshold is 3 cm.

[0011] According to one or more embodiments of the present application, the four first marking components are located at four corner points of a rectangular area.

[0012] According to one or more embodiments of the present application, the first marking components comprise a first group of first marking components located on an upper part of the side surface of the charging station, and a second group of first marking components located on a lower part of the charging station. The upper part of the side surface of the charging station is a part above a horizontal center line of the side surface of the charging station, and the lower part of the side surface of the charging station is a part below the horizontal center line of the side surface of the charging station.

[0013] According to one or more embodiments of the present application, the charging station further comprises a charging structure. The charging structure is located in a rectangular area surrounded by the four first marking components.

[0014] According to one or more embodiments of the present application, at least one of the first marking components is located below the loading structure, wherein at least one of the first marking components is located above the loading structure.

[0015] According to one or more embodiments of the present application, the marking component further comprises a second marking component, wherein the second marking component is located on the charging structure.

[0016] According to one or more embodiments of the present application, the second marking component is arranged at an overhanging end of the loading structure, wherein the second marking component is arranged on a front end surface of the loading structure.

[0017] According to one or more embodiments of the present application, the marking component is a reflective component or a luminous element.

[0018] One or more embodiments provide a charging station, wherein a plurality of feature markings are preset on the charging station, wherein a distribution area of ​​at least two of the plurality of feature markings differs from a distribution area of ​​the remaining feature markings, wherein the feature markings are used for image recognition by the robotic lawnmower so that the robotic lawnmower can dock onto the charging station for charging.

[0019] According to a further aspect of the present application, a charging station is provided, wherein a marking component is provided on the charging station, which is used to indicate a position of the charging station so that the robotic lawnmower can dock to the charging station for charging.

[0020] According to a further aspect of the present application, a charging station system is provided which comprises a charging station according to one of the above-mentioned aspects and a marking device, wherein a fourth marking component is provided on the marking device, wherein the fourth marking component is used to assist in determining the position of the charging station.

[0021] According to a further aspect of the present application, a method for returning to a charging station is provided, the method being used to guide a robotic lawnmower back to a charging station, the robotic lawnmower being equipped with an image capture device, feature markers being distributed on the charging station, the method comprising: acquiring available image frames captured by the image capture device of the robotic lawnmower in a front region of the charging station, the number of feature markers detected in the image frames being greater than or equal to N and N being a positive integer greater than or equal to 3;Determining a relative pose of the robotic lawnmower relative to the charging station based on two-dimensional coordinates of the detected feature markers in the image frames, three-dimensional coordinates of the feature markers in a world coordinate system, and imaging parameters of the image capture device; and driving the robotic lawnmower based on the relative pose so that it returns to the charging station.

[0022] According to a further aspect of the present application, a device for returning to a charging station is provided, the device being used to guide a robotic lawnmower back to a charging station, the robotic lawnmower being equipped with an image capture device, feature markers being distributed on the charging station, the device comprising: an acquisition module used to acquire available image frames captured by the image capture device of the robotic lawnmower in a front region of the charging station, the number of feature markers detected in the image frames being greater than or equal to N and N being a positive integer greater than or equal to 3;a determination module used to determine a relative pose of the robotic lawnmower relative to the charging station based on two-dimensional coordinates of the detected feature markers in the image frames, three-dimensional coordinates of the feature markers in a world coordinate system, and imaging parameters of the image capture device; and a drive module used to drive the robotic lawnmower to return to the charging station based on the relative pose.

[0023] According to a further aspect of the present application, a robotic lawnmower is provided, wherein the robotic lawnmower is equipped with an image capturing device, wherein the robotic lawnmower comprises a control unit, wherein the control unit is used to carry out the method described above.

[0024] According to a further aspect of the present application, a computer storage medium is provided, wherein a computer program is stored on the computer storage medium, wherein the computer program, when executed by a processor, implements the method described above.

[0025] In this method, by detecting the two-dimensional coordinates of the feature markers using the available image frames captured by the image capture device in the front area of ​​the charging station, and then combining them with the three-dimensional coordinates of the feature markers in the world coordinate system and the imaging parameters of the image capture device, the relative pose between the robotic lawnmower and the charging station can be accurately determined, and the robotic lawnmower can be accurately guided back to the charging station based on the relative pose. In this way, the use of feature markers for positioning ensures positioning accuracy, and the visual image cannot be disturbed by noise from other electromagnetic waves and signals in the environment, thus ensuring accuracy and reliability.There's also no need to lay additional guide wires. At the same time, the lack of GPS positioning errors is overcome, and the accuracy of the return to the charging station is fully ensured.

[0026] Furthermore, in the embodiments of the present application, it is only necessary to provide a marker component on the charging station. The lawnmower can obtain pose information from the feature markers distributed in the marker component through its own image recognition, so that relative pose information between the charging station and the lawnmower can be determined to perform path planning, allowing the lawnmower to return to the charging station for recharging. The costs are low. Since only feature markers need to be attached to the charging station, the structure is simple and easy to assemble and disassemble. Illustrations

[0027] The following drawings serve only to schematically illustrate and explain the present application, but are not intended to limit the scope of the present application. Herein: Fig. 1A is a schematic flow diagram of steps of a method for returning to a charging station in a first embodiment of the present application; Fig. 1B is a schematic view of a distribution of feature marks in the first embodiment of the present application; Fig. 1C is a schematic view of another distribution of feature markings in the first embodiment of the present application; Fig. 1D is a schematic view of a front portion of a charging station in the first embodiment of the present application; Fig. 1E is a schematic flowchart of the substeps of step S102 in the first embodiment of the present application; Fig. 2 is a structural block diagram of a device for returning to a charging station provided by a second embodiment of the present application; Fig. 3A is a schematic view of a distribution of marking components at a charging station according to an exemplary embodiment of the present application; Fig. 3B is a schematic view of a distribution of marking components at a charging station according to an exemplary embodiment of the present application; Fig. 4 is a schematic view of a distribution of marking components at a charging station according to an exemplary embodiment of the present application; Fig. 5 is an exploded view of a marking component according to an exemplary embodiment of the present application; Fig. 6 is a schematic structural view of a reflective element of a marking component of a charging station according to an exemplary embodiment of the present application; Fig. 7 a schematic view of a charging station system according to an exemplary embodiment of the present application. List of reference symbols:

[0028] 10-charging post; 11-charging post body; 111-mounting slot; 12-top cover; 13-bottom plate; 2-marking component; 20-feature marking; 211-first marking component; 212-second marking component; 213-third marking component; 214-fourth marking component; 22-reflective element; 221-transparent portion; 222-reflective portion; 23-mounting plate; 3-charging structure; 41-first distribution surface; 42-second distribution surface; 43-third distribution surface; 44-fourth distribution surface; 50-marking device. Description of embodiments

[0029] To enable a person skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application is described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Of course, the described embodiments represent a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by a person skilled in the art from the embodiments of the present application without inventive steps fall within the scope of the application.

[0030] To facilitate explanation and understanding, before describing the procedure for returning to a charging station, the structure and working scenario of a robotic lawnmower are described as follows:

[0031] In the present embodiment, the robotic lawn mower may be an automatic lawn mower including some main parts such as a main body, an image sensing device (also referred to as a visual sensing device), a navigation position estimation device, a visual position estimation device, and an autonomous movement device.

[0032] The main body includes a housing and a lawn mower blade assembly, etc. The lawn mower blade assembly is configured to mow grass in lawns to an appropriate height. The autonomous movement device includes a drive wheel, a drive motor, and a motor controller, etc. The motor controller is connected to the drive motor to control the rotation of the drive motor and then drive the drive wheel to move, thereby enabling forward and backward movement, steering, and the like of the robotic lawn mower.

[0033] The image capture device may include a video camera, a camera, and the like. Image capture devices with different structures may have different imaging parameters. Imaging parameters include, for example, aperture, focal length, optical axis, etc.

[0034] The navigation position estimation device is used to position the robotic lawnmower and then drive the robotic lawnmower to move depending on a positioning result.

[0035] The visual position estimation device can be used to process the image frames captured by the image capture device and then estimate a relative position of the robotic lawnmower relative to the charging station based on the image frames, in order to navigate and drive the robotic lawnmower to move based on the relative pose. It should be noted that the visual position estimation device can be an independent chip with computing power or a common chip shared with other devices, which is not limited.

[0036] As in Fig. 1B and Fig. 1C, is attached to a charging station (reference numeral 10 in Fig. 1B) Q Feature markings (reference numeral 20 in Fig. 1B), where Q is greater than or equal to 2 and is a positive integer. The feature markings may be any suitable pattern, shape, or structure, etc., that can be used for marking, but this is not limited to. The feature markings may be, for example, triangular protrusions or dots, rectangular patterns, two-dimensional codes or line segments, arcs, etc. Further examples are omitted here.

[0037] In order to improve the accuracy of relative pose positioning, for each coordinate axis of the world coordinate system, the maximum projection distance of the Q feature markers onto each of the coordinate axes is preferably greater than or equal to a distance threshold (the distance threshold can be determined according to the required positioning detection accuracy). This makes the feature markers on the same distribution plane more scattered on a distribution plane where these feature markers are located, with the distance between the feature markers being larger, which contributes to improving the detection efficiency and accuracy of relative pose positioning. The reason is that: In a Fig. In the coordinate system shown in Figure 1B, a Z-axis represents the forward direction of the robotic lawnmower. In a conventional relatively flat ground environment, docking the robotic lawnmower with a charging station relies more heavily on the transformation of a yaw angle (i.e., a rotation angle around a Y-axis). That is, the larger the lateral distance between the feature markers on the charging station, the larger the absolute distance of the position change of the feature markers distributed on an imaging plane when the relative pose of the robotic lawnmower relative to the charging station changes, thereby increasing the anti-interference ability. The same applies to a pitch angle (i.e., a rotation angle around an X-axis).

[0038] Preferably, as in Fig. 1C, a distribution plane of at least two of the Q feature marks differs from a distribution plane of the remaining feature marks. This means that the multiple feature marks provided on the charging station are located on at least two different distribution planes, thereby realizing differentiation of the feature marks in a Z-axis direction. After comparative experiments, it was found that a charging station A in which all feature marks are located on the same distribution plane has weaker anti-noise capability than a charging station B in which at least two feature marks are located on a different distribution plane than the remaining feature marks. In the same number of tests, charging station A is either unable to calculate the relative pose or has a worse accuracy of the calculated relative pose than that of charging station B.

[0039] By optimizing the distribution of the feature markers distributed on the charging station, the anti-interference and anti-sensitivity capabilities in detecting the relative pose of the robotic lawnmower can be improved. However, it should be noted that the distribution method exemplified in the embodiments of the present application is a preferred method. In further embodiments, the feature markers may use other distribution methods as long as the relative pose can be calculated. First embodiment

[0040] The following describes an implementation process of the procedure for returning to a charging station: As in Fig. Figure 1A shows a flowchart of steps in a method for returning to a charging station. In this embodiment, the method includes the following steps: Step S102: Acquiring available image frames captured by the image capture device of the robotic lawnmower in a front area of ​​the charging column.

[0041] In this embodiment, the image capture device captures image frames of the surroundings during a movement of the robotic lawnmower, with multiple image frames at different times forming an image frame sequence, which can also be referred to as a video. Since the pose of the robotic lawnmower varies at different times, the content contained in the image frames also varies, with some image frames possibly containing feature markers and some image frames possibly not containing feature markers.

[0042] The available image frames can be image frames captured in the front area of ​​the charging station and containing a sufficient number of feature markers. These image frames can be used to resolve the relative pose of the robotic lawnmower, which is why these image frames are considered the available image frames. Containing a sufficient number of feature markers can be considered as follows: The number of feature markers detected in the image frames is greater than or equal to N, where N is a positive integer greater than or equal to 3.

[0043] As in Fig. As shown in Figure 1D, the front area of ​​the charging station includes a sector area corresponding to the charging station, the sector area being located in front of the charging station, and a radius of the sector area taking a value greater than 0 and less than M, where M is a positive integer. The value of M can be determined depending on the imaging parameters of the image capture device, the sizes of the feature marks, etc., which is not limited.

[0044] In one example, the front area of ​​the charging station may be a sector area with a radius of 2 meters and an angle of 120°. Of course, in other examples, the shape, dimensions, etc. of the front area of ​​the charging station may be selected accordingly, but this is not limited.

[0045] Optionally, in this embodiment, as in Fig. 1E, step S102 is implemented by the following substeps to ensure that the robotic lawnmower can move reliably and accurately to the charging station in any position:

[0046] Substep S1021: Acquiring a navigation pose of the robotic lawnmower at a current time.

[0047] For example, in a normal working mode scenario, a navigation estimation device of the robotic lawnmower may locate a navigation pose of the robotic lawnmower when the robotic lawnmower receives an instruction to return to the charging station.

[0048] Substep S1022: Determine whether the robotic lawnmower is in the front area of ​​the charging station, depending on the navigation pose and a preset pose of the charging station.

[0049] Based on the pose of the charging station, the front area of ​​the charging station can be determined; then, based on position information in the navigation pose, it can be determined whether the robotic lawnmower is located in the front area of ​​the charging station.

[0050] If the robotic lawnmower is located in the front area of ​​the charging column, this indicates that a distance between the charging column and the robotic lawnmower is sufficient to detect clear feature markers of a suitable size, in which case sub-step S1023 can be executed; otherwise, the robotic lawnmower must first be driven to move to the front area of ​​the charging column so that sub-step S1025 can be executed.

[0051] Substep S1023: Determine whether the available image frames are present in an image frame sequence captured by the image capture device when the robotic lawnmower is in the front area of ​​the charging station.

[0052] In an executable implementation, a trained robot learning model is used to perform image recognition on each image frame in the image frame sequence to detect feature markers and determine whether the image frames are available image frames based on the number of detected feature markers.

[0053] Taking N as an example, if the number of detected feature markers is greater than or equal to 3, the image frames are the available image frames. Substep S1024 can be executed; otherwise, substep S1026 can be executed.

[0054] Substep S1024: Use the existing available image frames as the purchased available image frames if there are available image frames.

[0055] Step S104 may be executed after acquiring the available image frames.

[0056] Substep S1025: Driving the robotic lawnmower to move to the front of the charging column based on the navigation pose if the robotic lawnmower is not in the front of the charging column; and returning to the step of acquiring a navigation pose of the robotic lawnmower at a current time to continue execution.

[0057] If the navigation position obtained by the navigation position estimation device determines that the robotic lawnmower is not in the front area of ​​the charging station, the navigation position estimation device can instruct the robotic lawnmower to move based on the navigation pose; then, execution returns to sub-step S1021. This process is repeated until the robotic lawnmower moves to the front area of ​​the charging station. Thus, the robotic lawnmower only enters a return-to-the-charging-station mode when it enters the front area of ​​the charging station and a sufficient number of feature markers can be detected.

[0058] Substep S1026: Adjusting at least one of the position and the pose of the robotic lawnmower and acquiring a new image frame sequence if the available image frames are not present, and returning to the step of determining whether the available image frames are present in the image frame sequence acquired by the image acquisition device to continue the execution.

[0059] For example, when adjusting at least one of the position and the pose of the robotic lawnmower, the robotic lawnmower is set to a new navigation pose, wherein the robotic lawnmower is located outside the front area of ​​the charging column when it assumes the new navigation pose; depending on the new navigation pose, the robotic lawnmower is driven to move to the front area of ​​the charging column, wherein during the movement of the robotic lawnmower, the image capture device captures a plurality of image frames to form the image frame sequence.

[0060] For example, if the robotic lawnmower enters the front of the charging column but no image frame is available, the robotic lawnmower may be driven to leave the front of the charging column, then move back into the front of the charging column at a different angle, then captures image frames, and return to the step of determining whether the available image frames are present in the image frame sequence captured by the image capture device.

[0061] For example, if the robotic lawnmower stays in the front area of ​​the charging station for 5 seconds and detects insufficient markers on the charging station, the robotic lawnmower can randomly choose a direction to exit the front area of ​​the charging station, re-enter this area at a different angle, and detect markers on the charging station again. This process is repeated until sufficient markers are detected, and then it switches to return-to-the-charging-station mode.

[0062] Step S104 may be performed when available image frames are obtained.

[0063] Step S104: Determining a relative pose of the robotic lawnmower relative to the charging station depending on two-dimensional coordinates of the detected feature markers in the image frames, three-dimensional coordinates of the feature markers in a world coordinate system and imaging parameters of the image acquisition device.

[0064] When the robot is in the return-to-charging station mode, the visual position estimation device continuously updates the relative pose of the robotic lawnmower and the charging station by detecting and matching the image frames, and then guides the robotic lawnmower to arrive at the charging station and complete docking with the charging station.

[0065] The detection of the image frames can be carried out by recognizing the image frames using a trained neural network model to detect feature markings in the image frames and determining two-dimensional coordinates of the feature markings in the image frames.

[0066] For different feature labels, different neural network models can be trained to detect the feature labels in the image frames.

[0067] Based on the two-dimensional coordinates of the detected feature markers in the image frames, the three-dimensional coordinates of the feature markers in the world coordinate system, and the imaging parameters of the image acquisition device, a relative pose at the current time is determined.For example, a process for calculating the relative pose is as follows: Based on the two-dimensional coordinates and the imaging parameters of the image sensing device, the two-dimensional coordinates can be converted into three-dimensional coordinates in a coordinate system of the image sensing device; then, depending on the three-dimensional coordinates of the feature markers in the coordinate system of the image sensing device and their three-dimensional coordinates in the world coordinate system, a mapping relationship between the coordinate system of the image sensing device and the world coordinate system can be determined, where the mapping relationship is the relative pose.

[0068] Step S106: Driving the robotic lawnmower depending on the relative pose so that it returns to the charging station.

[0069] The pose of the robotic lawnmower can be adjusted based on the relative pose so that the robotic lawnmower faces the charging station, thereby realizing the robotic lawnmower's return to the charging station.

[0070] From the above-described process, it can be seen that the ability of the robotic lawnmower to quickly and accurately return to the charging station is greatly influenced by the accuracy of detecting the two-dimensional coordinates of the feature markers in the image frames. Since the image frames are captured while the robotic lawnmower is moving, they are inevitably affected by motion blur. In this embodiment, in the case where the image capture device captures the image frames and the ambient light intensity is fixed, the exposure time of the image frames is positively correlated with a relative distance, where the relative distance is a distance between the robotic lawnmower and the charging station.

[0071] Under normal circumstances, for example, the exposure time of the image capture device is determined based on the ambient light intensity. The brighter the ambient light, the shorter the exposure time; and the shorter the exposure time, the less motion blur occurs.

[0072] If, during an actual operation of the robotic lawnmower, the feature markers in the image frames captured at a distance of more than X meters (X is a positive integer and can be determined as needed) are missed during detection due to blur or other reasons, the problem of missing detection can be resolved by rotating the robotic lawnmower or moving it closer to the charging station. Since the robotic lawnmower is comparatively far from the charging station at this time, missing feature markers in the image frames or a low accuracy of the aligned two-dimensional coordinates have less of an impact on navigation accuracy and can be compensated for by subsequently adjusting the image frames.

[0073] When the distance between the robotic lawnmower and the charging station is less than or equal to Y (Y is a positive integer and less than X), the comparatively close distance between the two can easily lead to excessive movement deviation of the robotic lawnmower and inaccurate return to the charging station if the feature markers are missed due to motion blur during detection or the accuracy of the two-dimensional coordinates is insufficient. To avoid this problem and at the same time ensure that the brightness of the captured image frames meets the detection requirements, under the same light intensity, the exposure time of the image capture device is reduced with increasing distance until the distance reaches a distance threshold. This sufficiently reduces the motion blur.

[0074] For example, in one example, the exposure time remains constant when the light intensity and distance are the same. If the light intensity remains unchanged but the distance decreases by z, the exposure time T decreases by a * z ms. Here, a can be adjusted appropriately as needed. If the light intensity changes, the exposure time T increases or decreases accordingly. Light intensity and distance have independent effects on the exposure time.

[0075] In addition, research has shown that, under the influence of the characteristics of the image capture device, when the ambient light intensity remains unchanged, the shorter the exposure time, the lower the scene restoration degree by the image frames, and the corresponding image frames appear darker overall. However, after experimental comparison, it was found that the adverse effect of a reduced restoration degree by the image frames on the accuracy of returning to the charging station is much smaller than the adverse effect of motion blur on the accuracy of returning to the charging station, so at a shorter distance, an appropriate reduction in the exposure time contributes to improving accuracy.

[0076] To further improve the accuracy, data enhancement technology can optionally be used for image frames with a low restoration level to improve the accuracy of feature detection and avoid missed detection, thus improving robustness.

[0077] In this embodiment, by recognizing the two-dimensional coordinates of the feature markers using the available image frames captured by the image capture device in the front area of ​​the charging station, and then combining them with the three-dimensional coordinates of the feature markers in the world coordinate system and the imaging parameters of the image capture device, the relative pose between the robotic lawnmower and the charging station can be accurately determined, and the robotic lawnmower can thus be accurately guided back to the charging station depending on the relative pose. In this way, the use of the feature markers for positioning ensures positioning accuracy, and the visual image cannot be disturbed by noise from other electromagnetic waves and signals in the environment, thus ensuring accuracy and reliability.There's also no need to lay additional guide wires. At the same time, the lack of GPS positioning errors is overcome, and the accuracy of the return to the charging station is fully ensured.

[0078] In this way, based on the image frames captured by the image capture device in combination with a navigation position estimation device with low accuracy requirements, it is possible for the robotic lawnmower, located at any position in the working area, to return precisely to the charging station from any direction and be charged there.

[0079] When approaching the charging station, stable docking and stable charging can be achieved by taking advantage of the property that visual information such as image frames becomes more accurate with decreasing distance. In particular, in this embodiment, the distribution of feature markers has better robustness and better resistance to detection sensitivity. The problem of motion blur, which is difficult to handle with the visual solution itself, is also solved by adjusting the exposure time depending on the distance. Second embodiment

[0080] With reference to Fig. 2 shows a structural block diagram of a device for returning to a charging station according to a second embodiment.

[0081] The device is used to guide a robotic lawnmower back to a charging station, the robotic lawnmower being equipped with an image capture device, with feature markers being distributed on the charging station, the device comprising: an acquisition module 202 used to acquire available image frames captured by the image capture device of the robotic lawnmower in a front area of ​​the charging station, wherein the number of feature markers detected in the image frames is greater than or equal to N and N is a positive integer greater than or equal to 3; a determination module 204 used to determine a relative pose of the robotic lawnmower relative to the charging station depending on two-dimensional coordinates of the detected feature markers in the image frames, three-dimensional coordinates of the feature markers in a world coordinate system, and imaging parameters of the image capture device; and a drive module 206 used to drive the robotic lawnmower to return to the charging station depending on the relative pose.

[0082] Optionally, the front area of ​​the charging station comprises a sector area corresponding to the charging station, wherein the sector area is located in front of the charging station and a radius of the sector area takes a value greater than 0 and less than M, where M is a positive integer.

[0083] Optionally, the acquisition module 202 is used to acquire a navigation pose of the robotic lawnmower at a current time; determine, depending on the navigation pose and a preset pose of the charging station, whether the robotic lawnmower is located in the front area of ​​the charging station; determine whether the available image frames are present in the image frame sequence captured by the image capture device if the robotic lawnmower is located in the front area of ​​the charging station; and use the existing available image frames as acquired available image frames if available image frames are present.

[0084] Optionally, the acquisition module 202 is also used to adjust at least one of the position and pose of the robotic lawnmower and acquire a new image frame sequence in the case where the available image frames are not present; and to return to the step of determining whether the available image frames are present in the image frame sequence acquired by the image acquisition device to continue execution.

[0085] Optionally, the acquisition module 202 is used to adjust at least one of the position and the pose of the robotic lawnmower to a new navigation pose, wherein the robotic lawnmower is located outside the front area of ​​the charging station when it assumes the new navigation pose; to drive the robotic lawnmower depending on the new navigation pose such that it moves to the front area of ​​the charging station, wherein during the movement of the robotic lawnmower, the image capture device captures a plurality of image frames to form the image frame sequence.

[0086] Optionally, the acquisition module 202 is also used to drive the robotic lawnmower to move to the front of the charging column depending on the navigation pose when the robotic lawnmower is not in the front area of ​​the charging column; and to return to the step of acquiring a navigation pose of the robotic lawnmower at a current time to continue the execution.

[0087] Optionally, the charging station is provided with Q feature markers, where Q is greater than or equal to 2 and is a positive integer, where for each coordinate axis of the world coordinate system, the maximum distance of the projection of the Q feature markers onto each of the coordinate axes is greater than or equal to a distance threshold.

[0088] Optionally, a distribution level of at least two of the Q feature markers differs from a distribution level of the remaining feature markers.

[0089] Optionally, in the case where the image capture device captures the image frames and the ambient light intensity is fixed, the exposure time of the image frames is positively correlated with a relative distance, where the relative distance is a distance between the robotic lawnmower and the charging station.

[0090] The device can achieve corresponding effects which are achieved by the corresponding method and are therefore not described repeatedly. Third embodiment

[0091] According to one embodiment of the present application, a robotic lawnmower is provided, the robotic lawnmower being equipped with an image capture device comprising a control unit, the control unit being used to execute the method described above. The control unit can implement the operations corresponding to the method described above and achieve corresponding effects, which will not be described repeatedly.

[0092] Optionally, the robotic lawnmower also includes a charging unit. The charging unit is located below the image capture device. This means that the charging unit is closer to the ground than the image capture device. The charging unit is used to dock onto the charging structure of the charging station to charge the robotic lawnmower.

[0093] According to another aspect of the present application, a computer storage medium is provided, wherein a computer program is stored on the computer storage medium, wherein the computer program, when executed by a processor, implements the method described above. The program can implement the operations corresponding to the method described above and achieve corresponding effects, which will not be described repeatedly.

[0094] According to a further aspect of the present application, a charging station 10 is provided, wherein Q feature markings 20 are provided on the charging station 10, wherein a distribution plane of at least two feature markings 20 of the Q feature markings 20 differs from a distribution plane of the remaining feature markings 20, wherein Q is greater than or equal to 2 and is a positive integer.

[0095] In the charging station according to one embodiment, Q feature markers 20 are provided on the charging station 10, wherein a distribution area of ​​at least two feature markers 20 of the Q feature markers 20 differs from a distribution area of ​​the remaining feature markers 20, where Q is greater than or equal to 2 and is a positive integer. In the embodiments of the present application, it is only necessary to provide feature markers 20 on the charging station, and a robotic lawnmower can obtain pose information of the feature markers 20 through its own image recognition, whereby relative pose information between the charging station and the robotic lawnmower can be determined to perform path planning, thus enabling the robotic lawnmower to return to the charging station for recharging. The cost is low. And the structure is simple and easy to assemble or disassemble.dismantle, since only the feature markings 20 need to be provided on the charging station. By having a distribution plane of at least two feature markings 20 of the plurality of feature markings 20 differ from a distribution plane of the remaining feature markings 20, the accuracy of image recognition and the calculation of the relative pose information of the charging station by the robotic lawnmower can be improved.

[0096] As in Fig. 1B and Fig. 1C, is attached to a charging station (reference numeral 10 in Fig. 1B) Q Feature markings 20 (reference numeral 20 in Fig. 1B), where Q is greater than or equal to 2 and is a positive integer. The feature markings 20 may be any suitable pattern, shape, or structure, etc., that can be used for marking, but this is not limited to. The feature markings 20 may be, for example, triangular protrusions or dots, rectangular patterns, two-dimensional codes or line segments, arcs, etc. Further examples are omitted here.

[0097] In order to improve the accuracy of positioning the relative pose, for each coordinate axis of the world coordinate system, the maximum projection distance of the Q feature markers onto each of the coordinate axes is preferably greater than or equal to a distance threshold (the distance threshold can be determined according to the required positioning detection accuracy). As a result, the feature markers 20 are more dispersed on the same distribution plane on a distribution plane where these feature markers are located, with the distance between the feature markers 20 being larger, which contributes to improving the detection efficiency and accuracy in positioning the relative pose. The reason is that in a Fig. In the coordinate system illustrated in Figure 1B, a Z-axis is a forward direction of the robotic lawnmower, and in a conventional relatively flat ground environment, docking the robotic lawnmower with a charging station relies more heavily on the transformation of a yaw angle (i.e., a rotation angle about a Y-axis). That is, the larger a lateral distance between the feature markers 20 on the charging station, the larger the absolute distance of the position change of the feature markers 20 distributed on an imaging plane when the relative pose of the robotic lawnmower relative to the charging station changes, thereby strengthening the anti-interference ability. The same applies to a pitch angle (i.e., a rotation angle about an X-axis).

[0098] Preferably, as in Fig. 1C, a distribution plane of at least two feature marks 20 of the Q feature marks 20 is different from a distribution plane of the remaining feature marks 20. That is, the plurality of feature marks 20 provided on the charging station are located on at least two different distribution planes, thereby realizing differentiation of the feature marks 20 in a Z-axis direction. After comparative experiments, it was found that a charging station A in which all feature marks 20 are located on the same distribution plane has a weaker anti-noise capability than a charging station B in which at least two feature marks 20 are located on a different distribution plane than the remaining feature marks 20.For the same number of tests, charging station A is either unable to calculate the relative pose or has a worse accuracy of the calculated relative pose than that of charging station B.

[0099] By optimizing the distribution of the feature markers 20 distributed on the charging station, the anti-interference and anti-sensitivity capabilities in detecting the relative pose of the robotic lawnmower can be improved. However, it should be noted that the distribution method 20 exemplified in the embodiments of the present application is a preferred method. In further embodiments, the feature markers 20 may use other distribution methods as long as the relative pose can be calculated.

[0100] According to another aspect of the present application, a charging station 10 is provided. To facilitate explanation and understanding, before describing the charging station of this embodiment, the overall structure of the charging station 10 is briefly described as follows:

[0101] The charging station 10 may comprise a charging station main body 1 and a charging assembly 3, wherein the charging station main body 1 comprises an upper cover 12, a charging station body 11 and a base plate 13, wherein the charging assembly 3 is mounted on one side of the charging station body 11, wherein the upper cover 12 is connected to an upper end of the charging station body 11, and wherein the base plate 13 is connected to a lower end of the charging station body 11.

[0102] With reference to Fig. 1A to 7, in the charging station 10 according to this embodiment, it is provided that a plurality of feature markings 20 are preset on the charging station 10, wherein a distribution area of ​​at least two feature markings 20 of the plurality of feature markings 20 differs from a distribution area of ​​the remaining feature markings 20, wherein the feature markings 20 are used for image recognition by the robotic lawnmower, so that the robotic lawnmower can dock to the charging station 10 for charging.

[0103] For example, the feature marker 20 is a marker point. The marker point refers to a point with abstract meaning. The marker point can be an explicit marker point, for example, an endpoint of line segments, a corner point of shapes, a corner point of two-dimensional codes, etc., or an implicit marker point for semantic classes, for example, a center point of the intersection line of different surfaces, semantic information of the marker itself, such as a wrist of a human-shaped marker, a center point of the densest grass of a grass marker, etc. The marker point can be a point on a surface or a convex or concave point on this surface.The feature marker 20 in this embodiment refers to an explicit marker point on the charging station 10, which can be a marker point of the charging station 10 itself, such as endpoints of edges on the surface of the charging station 10, or a marker point designed depending on the requirements of an image recognition algorithm of the robotic lawnmower. For example, marker components 2 with different shapes are provided on the charging station 10, with the feature markers 20 being corner points of the shapes of the marker components 2. This is not limited in this embodiment.

[0104] The image capture device of the robotic lawnmower captures available image frames in the front area of ​​the charging station 10 and detects the preset feature markers 20 on the surface of the charging station 10 from the image frames using the preset detection algorithm. The preset feature markers 20 are marker points on the charging station 10 that are preset using the preset detection algorithm. Depending on the two-dimensional coordinates of the detected feature markers 20 in the image frames, the three-dimensional coordinates of the feature markers 20 in the world coordinate system, and the imaging parameters of the image capture device, a relative pose of the robotic lawnmower relative to the charging station 10 is determined. Depending on the relative pose, the robotic lawnmower is driven to return to the charging station 10.

[0105] With reference to Fig. 1C, a plurality of feature markings 20 are provided on the charging station 10, wherein a distribution area of ​​at least two of the plurality of feature markings 20 differs from a distribution area of ​​the remaining feature markings 20. That is, the plurality of feature markings 20 provided on the charging station 10 are located on at least two different distribution areas, thereby realizing a differentiation of the feature markings 20 in a Z-axis direction. After comparative experiments, it was determined that a charging station 10A in which all feature markings 20 are located on the same distribution area has a weaker anti-noise capability than a charging station 10B in which at least two feature markings 20 are located on a different distribution area than the remaining feature markings 20.For the same number of tests, charging station 10A is either unable to calculate the relative pose or has a worse accuracy of the calculated relative pose than that of charging station 10B.

[0106] In this embodiment, it is only necessary to provide feature markers 20 on the charging station 10. A robotic lawnmower can obtain pose information of the feature markers 20 through its own image recognition, thereby determining relative pose information between the charging station 10 and the robotic lawnmower to perform path planning, allowing the robotic lawnmower to return to the charging station for recharging. The cost is low. Furthermore, the structure is simple and easy to assemble and disassemble, since only the feature markers 20 need to be provided on the surface of the charging station 10.By having a distribution area of ​​at least two feature markings 20 of the plurality of feature markings 20 differ from a distribution area of ​​the remaining feature markings 20, the accuracy of the image recognition and the calculation of the relative pose of the charging station 10 by the robotic lawnmower can be improved.

[0107] With reference to Fig. 3, in a specific implementation, it is provided that a marking component 2 is provided on the surface of the charging station 10, wherein the marking component 2 comprises a first marking component 211 and a second marking component 212, wherein the first marking component 211 and the second marking component 212 are located on different distribution surfaces of the charging station 10, wherein at least two feature markings 20 are distributed on the marking component 2.

[0108] For example, the number of first marking components 211 and second marking components 212 can be greater than or equal to 1 and a positive integer. The marking component 2 can have different shapes, for example, rectangular, triangular, circular, or L-shaped. Marking components 2 of the same shape or marking components 2 of different shapes can be used as the first marking component 211 and the second marking component 212. For example, four L-shaped marking components 2 can be used as the first marking component 211, and a stripe-shaped marking component 2 can be used as the second marking component 212, which is not limited in this embodiment. Each marking component 2 can have a single shape or a combination of several different shapes.The marking component 2 may be flat, such as a sticker, or three-dimensional, such as a reflective plastic assembly.

[0109] The number of feature markers 20 on each marker component 2 can be greater than or equal to 2 and is a positive integer. The distribution positions of the feature markers 20 on the marker components 2 of different shapes are different and can be preset based on the image recognition algorithm of the robotic lawnmower. For example, the feature markers 20 on a rectangular marker component 2 can be provided at at least two of the four corner points, and the feature markers 20 on an L-shaped marker component 2 can be provided at at least two of the four end points, etc.

[0110] In this specific implementation, the marking component 2 enables the feature markers 20 to have more selectable distribution positions on the charging station 10, with a larger number of feature markers 20 that can be provided, thereby improving the accuracy of the image recognition calculations by the robotic lawnmower. Furthermore, by providing the marking component 2, the position and number of feature distributions can be adjusted based on the image recognition algorithm used by the robotic lawnmower or the hardware specifications, enabling adaptation to more robot products.

[0111] In a specific implementation, the first marking component 211 is located on a first distribution surface 41 of the charging station 10, wherein the second marking component 212 is located on a second distribution surface 42 of the charging station 10. An angle is formed between a normal of the first distribution surface 41 and a normal of the second distribution surface 42, and the angle is not equal to 0 degrees; alternatively, the normal of the first distribution surface 41 is parallel to the normal of the second distribution surface 42, and the first distribution surface 41 and the second distribution surface 42 are spaced apart from each other in the normal direction. For example, with reference to Fig. 3A and Fig. 3B, the first distribution surface 41 may be a first side surface of the charging column 10 on which a charging structure 3 is provided, wherein the second distribution surface 42 may be a side of the charging column 10 adjacent to the first side surface, or a side surface, an upper surface, or a lower surface of the charging structure 3; the normals of the two (the dashed lines in the figures) form an angle A, wherein the angle A is not equal to 0 degrees, so that the first distribution surface 41 and the second distribution surface 42 are different distribution surfaces.Alternatively, the first distribution surface 41 may be the first side surface of the charging column 10 on which the charging structure 3 is provided, and the second distribution surface 42 may be a side of the charging column 10 opposite the first side surface or a front end surface of the charging structure 3; the normals of the two (the dashed lines in the figures) are parallel to each other, but they are spaced apart from each other in the normal direction. The first distribution surface 41 and the second distribution surface 42 are thus different distribution surfaces. In this specific implementation, by determining a positional relationship between the distribution surfaces on which the first marking component 211 and the second marking component 212 are respectively located, it can be determined that the first marking component 211 and the second marking component 212 are located on different distribution surfaces.

[0112] In a specific implementation, the first distribution surface 41 and the second distribution surface 42 may include flat surfaces and curved surfaces. For example, the first distribution surface 41 and the second distribution surface 42 may be side surfaces of the charging station 10 or edges where the two side surfaces intersect, or the like. Note that when the marker component 2 is provided on a curved surface, the normal to the position of the marker component 2 serves as the normal to the distribution surface of the marker component 2. When multiple feature markers 20 are simultaneously detected on distribution surfaces with large curvature differences, the accuracy of the finally calculated relative pose information of the charging station 10 and the robotic lawnmower is higher.

[0113] In a specific implementation, the charging station 10 comprises the charging station body 11 and the charging structure 3, wherein the charging structure 3 is mounted on a first side surface of the charging station body 11, wherein the second marking component 212 is provided on the charging structure 3, and wherein the first marking component 211 is provided on the first side surface of the charging station body 11 on which the charging structure 3 is mounted.

[0114] For example, one end of the charging structure 3 is mounted on the first side surface of the charging column body 11, and the other end of the charging structure 3 protrudes from the charging column body 11. The charging structure 3 is used to connect to a charging port of the robotic lawnmower to charge the robotic lawnmower. The second marking component 212 is provided on the charging structure 3, and the first marking component 211 is provided on the first side surface of the charging column body 1, on which the charging structure 3 is mounted.For example, four L-shaped marking components 2 can be used as the first marking component 211, and a strip-shaped marking component 2 can be used as the second marking component 212. The strip-shaped marking component is mounted on one end of the charging structure 3 that protrudes from the charging column body 11. The four L-shaped marking components are mounted on the first side surface of the charging column body 11 on which the charging structure 3 is mounted. Depending on the projection positions of the marking components 2 on the first side surface of the charging column body 11 on which the charging structure 3 is mounted, the four L-shaped marking components 2 surround the strip-shaped marking component 2, thereby realizing both the aesthetics and the functionality of the feature markings 20.

[0115] In this specific implementation, by providing the second marking component 212 on the charging structure 3 and the first marking component 211 on a side of the charging column body 1 on which the charging structure 3 is mounted, the structural characteristics of the charging column 10 itself are utilized, so that the first marking component 211 and the second marking component 212 are located on different distribution surfaces. There is no need to separately install a protruding flat surface or curved surface. The structure is simple, and costs can be saved.

[0116] In a specific implementation, the charging column 10 comprises the charging column body 11 and the charging structure 3, wherein the charging structure 3 is mounted on a first side surface of the charging column body 11, wherein the marking component 2 further comprises a third marking component 213, wherein the first marking component 211 is provided on the first side surface, and wherein the third marking component 213 is provided on at least one of the other side surfaces or edges of the charging column body 11 except the first side surface.

[0117] For example, the first marking component 211 and the third marking component 213 may be distributed on the first side surface of the charging column 10 and each side surface adjacent to the first side surface; alternatively, they may be distributed on the first side surface and a side surface opposite the first side surface; alternatively, they may be distributed on the first side surface and each edge (an edge is an intersection point of two adjacent side surfaces in an outer peripheral surface); alternatively, they may be distributed on the first side surface, each edge, and each side surface adjacent to the first side surface; alternatively, they may be distributed on each surface of the outer peripheral surface and an edge, etc. It should be noted that the edge here may refer to a facet, where the facet may be a flat surface or a curved surface.

[0118] It should be noted that in this implementation, the surface on which the first marking component 211 is located is the above-mentioned first distribution surface 41 and the surface on which the third marking component 213 is located is the above-mentioned second distribution surface 42, that an angle is formed between the normal of the first distribution surface 41 of the first marking component 211 and a normal of the second distribution surface 42 of the third marking component 213, and that the angle is not equal to 0 degrees.

[0119] This specific implementation ensures that the robotic lawnmower detects and recognizes a larger number of feature markers 20 in all directions, which in turn leads to more robust effects of the image recognition algorithm. For example, by providing the feature marker 20 on each side surface adjacent to the first side surface, the robotic lawnmower can detect the feature markers 20 even when the offset angle between the robotic lawnmower and the first side surface is relatively large. The pose of the robotic lawnmower is then adjusted, and a return to the charging station is realized to perform charging there.

[0120] With reference to Fig. 4, in a specific implementation, the marking component 2 is projected onto a surface of the charging station body 11 on which the marking component 2 is located to form a marking pattern, wherein the minimum inner diameter in the marking pattern is greater than or equal to a first preset threshold, and wherein the first preset threshold is 3 cm. By way of example, the marking component 2 is projected onto the side surface of the charging station body 11 on which the marking component 2 is located to form the marking pattern, i.e., the shape of the marking component 2, wherein the minimum inner diameter in the marking pattern is greater than or equal to the first preset threshold, which means that a width at any point in the marking pattern is greater than or equal to the first preset threshold.For example, the width of a rectangle in a rectangular marking component 2 is the minimum inner diameter; the height of a triangle in a triangular marking component 2 is the minimum inner diameter; and the width of an L-shape in an L-shaped marking component 2 (width a in . Fig. 4) is the minimum inner diameter. The first preset threshold can be determined depending on the size of the working area and the size of the docking area of ​​the robotic lawnmower so that the robotic lawnmower can detect the charging column body 11 within the working area, wherein the first preset threshold can be set to 3 cm.

[0121] In this specific implementation, by setting the minimum inner diameter of the shape of the marking component 2 greater than or equal to the first preset threshold, the dimensions of the marking component 2 can be controlled to meet the image recognition requirements of the robotic lawnmower. This prevents the feature markers 20 from being accurately recognized due to an excessively small dimension of the marking component 2, or increases in cost due to an excessively large dimension of the marking component 2, and compromises the aesthetics of the charging station 10.

[0122] In a specific implementation, the minimum distance between the marking components 2 located on the same distribution surface on the charging station body 11 is greater than or equal to a second preset threshold, wherein the second preset threshold is 3 cm. By way of example, with reference to Fig. 4, the minimum distance between the marking components 2 located on the same surface of the charging station body 11 is denoted as b. The second preset threshold can be determined depending on the size of the working area and the size of a docking area of ​​the robotic lawnmower, so that the robotic lawnmower can detect the charging station body 11 within the working area and detect the feature markings 20 within the docking area. For example, the second preset threshold is set to 3 cm.In this specific implementation, by setting the minimum distance between adjacent marking components 2 on the same distribution area greater than or equal to the second preset threshold, the distance between the marking components 2 can be controlled to meet the image recognition requirements of the robotic lawnmower, thereby improving the accuracy of image recognition by the robotic lawnmower.

[0123] It should be noted that in this specific implementation, the minimum distance between adjacent marking components 2 on the same distribution area is controlled greater than or equal to the second preset threshold instead of the maximum distance, which can eliminate the influence of the dimension of the marking component 2 on the distance between the adjacent marking components 2 and at the same time ensure that both the dimension of the marking component 2 and the distance between the adjacent marking components 2 meet the image recognition requirements of the robotic lawnmower.

[0124] In a specific implementation, the marking component 2 is a reflective assembly or a luminous assembly. The robotic lawnmower and the charging station 10 are typically used outdoors. In poor weather conditions or insufficient lighting due to nighttime, etc., the image capture device of the robotic lawnmower cannot accurately capture the feature markings 20 on the charging station 10. In this specific implementation, by embodying the marking component 2 as a reflective assembly or a luminous assembly, the feature markings 20 on the charging station 10 are more conspicuous and easier to detect, thereby improving the detection accuracy of the robotic lawnmower.

[0125] In a specific implementation, the reflective assembly comprises a reflective element 22 and a mounting plate 23, wherein the reflective element 22 comprises a light-transmitting portion 221 and a reflective portion 222. In Part I of Fig. Figure 6 shows an enlarged view of a subsection of the reflective section 222. The surface of the subsection may consist of three squares perpendicular to each other and sharing a common vertex. The reflective section 222 comprises multiple subsections. The reflective section 222 of the reflective element 22 is fixedly connected to the mounting plate 23, and the reflective assembly is connected to one side of the charging post body 11.

[0126] With reference to Fig. 5 and Fig. 6, for example, the connection of the reflective assembly to the charging station body 11 can be achieved by ultrasonic welding, snapping, or gluing, etc. The reflective portion 222 of the reflective element 22 is connected to the mounting plate 23 by ultrasonic welding. The reflective element 22 can be made of a transparent plastic, and the reflective element 22 can be integrally formed by injection molding. The surface of the charging station body 11 is provided with a mounting slot 111. When the reflective assembly is mounted in the mounting slot 111 of the charging station body 11, a surface of the reflective element 22 facing away from the charging station body 11 is the translucent portion 221. The translucent portion 221 can be a transparent, glossy surface, and light can pass through the translucent portion 211 into the reflective portion 222 to reflect the light.A surface of the reflective element 22 facing the charging column body 11 is the reflective portion 222. The reflective portion 222 may include a plurality of subsections, the plurality of subsections being evenly distributed in parallel, two adjacent subsections sharing one surface, an edge length of the subsections being adjustable in a range of 0.5 mm to 1 mm, so that the subsections are smaller and arranged more densely, whereby when illuminated, the reflected light is more uniform and it is not easy to generate glare, the outline of the marking component 2 is clearer and easier to recognize.

[0127] In this specific implementation, by providing the marking component 2 as a reflective assembly, the structure is simple and easy to assemble, and the marking component 2 is easier to recognize on the charging column body 11.

[0128] In a specific implementation, the surface of the marking component 2 differs in color and / or texture from the surface of the charging station body 11. In particular, the image capture device of the robotic lawnmower can capture the feature markings 20 on the charging station 10 more quickly and accurately by adjusting the texture and / or color of the surface of the marking component 2 to differ from the texture and / or color of the surface of the charging station body 11. Preferably, the greater the difference in texture and color between the surface of the marking component 2 and the surface of the charging station 10, the easier it is to detect the feature markings 20.

[0129] According to a further aspect of the present application, a charging station 10 is provided, wherein a marking component 2 is provided on the charging station 10, wherein the marking component 2 is used to indicate a position of the charging station 10 so that the robotic lawnmower can dock onto the charging station 10 for charging.

[0130] For example, it may be one or more marking components 2. At least one feature marking 20 may be distributed on the marking component 2. The feature marking 20 may be a corner point of the shape of the marking component 2 or the like. The marking component 2 may have different shapes, for example, rectangular, triangular, or circular, etc. As the first marking component 211 and the second marking component 212, marking components 2 of the same shape or marking components 2 of different shapes may be used. For example, four L-shaped marking components 2 may be used as the first marking component 211, and a strip-shaped marking component 2 may be used as the second marking component 212, which is not limited in this embodiment.Each marking component 2 can have a single shape or a combination of several different shapes. The marking component 2 can be flat, like a sticker, or three-dimensional, like plastic. The marking component 2 can be a reflective or luminous assembly, making the feature marking 20 on the charging post 10 more conspicuous and easier to recognize. Even in poor weather conditions or insufficient lighting due to nighttime, etc., the image capture device of the robotic lawnmower can accurately capture the feature markings 20 on the charging post 10, thereby improving the recognition accuracy of the robotic lawnmower.

[0131] The image capture device of the robotic lawnmower captures available image frames in the front area of ​​the charging station 10 and detects the preset feature markers 20 on the surface of the charging station 10 from the image frames using the preset detection algorithm. The preset feature markers 20 are marker points on the charging station 10 that are preset using the preset detection algorithm. Depending on the two-dimensional coordinates of the detected feature markers 20 in the image frames, the three-dimensional coordinates of the feature markers 20 in the world coordinate system, and the imaging parameters of the image capture device, a relative pose of the robotic lawnmower relative to the charging station 10 is determined. Depending on the relative pose, the robotic lawnmower is driven to return to the charging station 10.

[0132] In this embodiment, it is only necessary to provide a marker component 2 on the charging station 10. The robotic lawnmower can obtain pose information of the feature markers 20 distributed in the marker component 2 through its own image recognition, so that relative pose information between the charging station 10 and the robotic lawnmower can be determined to perform path planning, thus enabling the robotic lawnmower to return to the charging station for recharging. The costs are low. Since only feature markers 20 need to be attached to the surface of the charging station 10, the structure is simple and easy to assemble and disassemble.

[0133] In a specific implementation, the charging station 10 comprises a charging structure 3, wherein the marking component 2 is provided on the charging structure 3. For example, the charging structure 3 is provided on one side of the charging station 10, wherein the marking component 2 is provided on the charging structure 3. This can be done by a detachable connection, such as by snapping or gluing, etc., or by ultrasonic welding, which is not limited in this embodiment.

[0134] In this specific implementation, the marking component 2 can be arranged only on the charging structure 3, so that it is not necessary to consider the arrangement position of the marking component 2 when designing the dimension of the charging column body 11, thereby reducing the dimension of the charging column body 11 and reducing costs; furthermore, when designing the texture and color of the charging column body 11, it is also not necessary to consider the impact of the marking component 2 on the information acquired by the robotic lawnmower.

[0135] In a specific implementation, the marking component 2 comprises a first marking component 211 and a second marking component 212, wherein the first marking component 211 and the second marking component 212 are located on different distribution surfaces of the charging station 10. For example, the distribution surfaces of the marking component 2 on the charging station 10 may comprise side surfaces and edges, wherein the side surfaces and the edges may be flat surfaces and curved surfaces. With reference to reference Fig. 3A and Fig. 3B, the first marking component 211 is located on a first distribution surface 41 of the charging station 10, and the second marking component 212 is located on a second distribution surface 42 of the charging station 10. An angle is formed between a normal of the first distribution surface 41 and a normal of the second distribution surface 42, and the angle is not equal to 0 degrees; alternatively, the normal of the first distribution surface 41 is parallel to the normal of the second distribution surface 42, and the first distribution surface 41 and the second distribution surface 42 are spaced apart from each other in the normal direction. It should be noted that in the case where the marking component 2 is provided on a curved surface, the normal of the position of the marking component 2 serves as the normal of the distribution surface of the marking component 2.

[0136] In this specific implementation, by providing the first marking component 211 and the second marking component 212 on different distribution areas of the charging station 10, it is possible to allow the distribution areas of the plurality of feature markings 20 to be different. Compared to the feature markings distributed on the same area, this implementation can improve the robustness of the image recognition algorithm of the image capture device, reduce the probability of misrecognition, and improve the accuracy of image recognition and the calculation of the relative pose information of the charging station 10 by the robotic lawnmower.

[0137] The image acquisition device acquires images and detects the first marker component 211 and the second marker component 212 in the images, and then extracts feature markers 20 in the first marker component 211 and the second marker component 212 (typically, endpoints and inflection points of the first marker component 211 and the second marker component 212 are used as feature markers 20).

[0138] A specific algorithm flow is as follows: n feature markers 20 are provided; first, m (m<=n) position coordinates of the feature markers 20 are detected on a two-dimensional image; then, p (p<=m<=n) valid feature markers 20 are matched depending on the parameters of the image capture device and the three-dimensional coordinate positions of the feature markers 20; then, the relative position of a vehicle body and a camera is calculated. When p=m=n, image recognition is considered successful. If the n feature markers 20 are arranged on the same plane, it is assumed that there are four initial feature markers, and each initial feature marker contains a feature marker 20 (i.e., a marker point). Four (n=4) feature markers 20 (marker points) form a rectangle.When problems such as sunlight irradiation, camera surface occlusion, or blurring lead to detection on the two-dimensional image, two feature markers 20 on the left side of the rectangle are offset in the same direction (but the total of four feature markers after the offset of the two feature markers still satisfy the geometric characteristics of the affine transformation). Therefore, there is a probability that the algorithm may still output a pose that should be erroneous based on n=p=4 coordinates after the offset, and this pose may usually be significantly offset.When there are feature markers 20 that are not on the same plane, it is assumed that four feature markers 20 at the endpoints of the rectangle are located on the same distribution surface, and two feature markers 20 included in the second marker component 212 are located on the other distribution surface (distribution surface with four salient points), that is, n = 6; when the feature markers on the side of the rectangle are offset, and the four feature markers 20 in the same plane after the offset satisfy the geometric features of the rectangle after the affine transformation, the algorithm cannot calculate erroneous poses based on the coordinates after the offset due to the presence of the two salient feature markers 20 (because at this time, p < n due to the presence of the salient points), and therefore a highly offset pose cannot be provided.This first marking component 211 and the second marking component 212 are provided on different distribution areas of the charging station 10, which can improve the robustness of the image recognition algorithm of the image capturing device, reduce the probability of misrecognition, and improve the accuracy of image recognition and the calculation of the relative pose information of the charging station 10 by the robotic lawnmower.

[0139] In a specific implementation, the charging column 10 comprises the charging column body 11 and the charging structure 3, wherein the first marking component 211 and the charging structure 3 are mounted on a first side surface of the charging column body 11, ie, the first marking component 211 is provided on a side surface on which the charging structure 3 is mounted.

[0140] A lens of the image capture device of the robotic lawnmower has a limited detection range. When the robotic lawnmower moves in front of the charging station 10 and begins docking with the charging station, the detection range of the lens of the image capture device occupied by the first side surface is larger the closer the robotic lawnmower is to the charging structure of the charging station. By providing the first marking component 211 on the first side surface, the following applies: the closer the robotic lawnmower is to the charging station 10, the more accurately the position of the first marking component 211 is detected, the more accurately the pose of the charging station 10 is determined, the more accurately the pose of the robotic lawnmower is adjusted, and the more accurately the charging structure 3 is docked to the charging port of the robotic lawnmower.

[0141] Furthermore, the charging structure 3 is arranged protruding from the first side surface. During a process from straight contact to full contact between the charging unit of the robotic lawnmower and the charging structure 3, the provision of the first marking component 211 on the first side surface ensures that the robotic lawnmower can still detect the first marking component 21, and the pose of the robotic lawnmower is continuously adjusted depending on the position of the first marking component 211 to ensure that the charging unit of the robotic lawnmower is in full contact with the charging structure 3 and effective charging occurs.

[0142] In a specific implementation, a second marking component 212 is provided on the loading structure 3. The second marking component 212 can be provided on a front face or a side face of the loading structure 3.

[0143] In this implementation, by providing the second marking component 212 on the charging structure 3 and the first marking component 211 on the first side surface of the charging column body 1 on which the charging structure 3 is mounted, the structural characteristics of the charging column 10 itself are utilized, so that the first marking component 211 and the second marking component 212 are located on different distribution surfaces. There is no need to separately set up a protruding flat surface or curved surface. The structure is simple, and costs can be saved.

[0144] In a specific implementation, the second marking component 212 is arranged at an overhanging end of the charging structure 3, and the second marking component 212 is arranged on the front end face. The image capture device faces the front end face of the overhanging end of the charging structure 3 and can fully capture the features of the front end face of the overhanging end of the charging structure 3 when the robotic lawnmower is moving toward the first side face of the charging column 10 and has not yet reached the docking position.Compared to the arrangement of the marking component 2 on the side surface of the charging structure 3, the arrangement of the second marking component 212 on the front end surface of the overhanging end of the charging structure 3 ensures that the robotic lawnmower can acquire all feature markings of the second marking component 212, thereby improving the accuracy of the pose information of the charging structure 3 and enabling returning to the charging station and charging there.

[0145] In a specific implementation, the marking component 2 further comprises a third marking component 213, wherein the third marking component 213 is arranged on a second side surface of the charging column body, the second side surface being connected to the first side. For example, the first marking component 211 and the third marking component 213 may be distributed, respectively, on the first side surface of the charging column 10 and each side surface adjacent to the first side surface; alternatively, they may be distributed, respectively, on the first side surface and each edge (an edge is an intersection point of two adjacent side surfaces in an outer peripheral surface), etc. It should be noted that the edge here may refer to a facet, wherein the facet may be a flat surface or a curved surface.

[0146] It should be noted that in this implementation, the surface on which the first marking component 211 is located is the above-mentioned first distribution surface 41 and the surface on which the third marking component 213 is located is the above-mentioned second distribution surface 42, that an angle is formed between the normal of the first distribution surface 41 of the first marking component 211 and a normal of the second distribution surface 42 of the third marking component 213, and that the angle is not equal to 0 degrees.

[0147] This specific implementation ensures that the robotic lawnmower detects and recognizes a larger number of feature markers 20 in all directions of the charging station 10, which in turn leads to more robust effects of the image recognition algorithm. For example, by providing the third marker component 213 on each side surface adjacent to the first side surface, the robotic lawnmower can detect the feature markers 20 even when the offset angle between the robotic lawnmower and the first side surface is relatively large. The pose of the robotic lawnmower is then adjusted, and a return to the charging station is realized to perform charging there.

[0148] In a specific implementation, a plurality of marker components 211 are provided, wherein the plurality of marker components 211 are distributed around the charging structure 3. The robotic lawnmower can return from another location to the vicinity of the charging station and then dock with the charging station for charging. If the first marker components 211 are provided in only one orientation of the charging structure 3, the first marker components 211 cannot be correctly detected due to occlusion of the charging structure 3, resulting in pose errors.

[0149] For example, if only two first marking components 211 are provided on the first side surface and both are located below the charging structure 3 (compared to the charging structure 3, the first marking components 211 are closer to the bottom plate 13), during a process from just contact to full contact between the charging unit of the robotic lawnmower and the charging structure 3, the lens of the image pickup device, which is located above the charging structure 3 (compared to the charging structure 3, the lens of the image pickup device is further away from the bottom plate 13) and is hidden by the charging structure 3, cannot correctly detect the first marking components 211 below the charging structure 3.By distributing the plurality of first marking components 211 around the charging structure 3, it can be ensured during the process from straight contact to full contact between the charging unit of the robotic lawnmower and the charging structure 3 that the robotic lawnmower can still detect the first marking components 211 located above the charging structure 3, thereby reducing the pose errors that arise because the first marking components 211 cannot be correctly detected due to an obscuration of the charging structure 3.

[0150] In a further embodiment, the plurality of first marking components 211 may be distributed at intervals around the loading structure 3. With reference to Fig. 4, four first marking components 211 are provided, which are distributed at intervals around the loading structure 3. The feature markings 20 detected by the lens of the image capture device are mainly distributed at the endpoints, center points, or inflection points of the marking components 2. By arranging the plurality of first marking components 211 at intervals from one another, the number of feature markings at the endpoints can be increased.

[0151] In a specific implementation, the plurality of first marking components 211 are not distributed centrally symmetrically. When the image capture device is offset at the placement position of the robotic lawnmower, the non-centrosymmetrical distribution of the plurality of first marking components 211 allows the distribution of the first marking components 211 to correspond to a bias direction of the image capture device, thereby allowing the image capture device to obtain more information about the marking components 2.

[0152] In a specific implementation, the first marking components 211 comprise two stripe structures that are perpendicular to each other and intersect each other. For example, the first marking components 211, as shown in Fig. 4, be L-shaped. By forming the shape of the first marking components 211 as two mutually perpendicular and intersecting stripe structures, multiple scattered feature markers can be distributed with fewer consumables. Second, this implementation has strong structural integrity, a simple structure, and is easy to assemble compared to multiple dot-shaped marking structures.

[0153] According to a further aspect of the present application, a charging station system is provided which comprises a charging station 10 according to one of the above-mentioned aspects and a marking device 50, wherein a fourth marking component 214 is provided on the marking device 50, wherein the fourth marking component 214 is used to assist in determining the position of the charging station 10.

[0154] Optionally, the marking component 2 is provided on a third distribution surface 43 on the charging station 10, wherein the third distribution surface 43 can comprise the first distribution surface 41 and the second distribution surface 42, wherein the fourth marking component 214 is provided on a fourth distribution surface 44 on the marking device 50, wherein an angle is formed between a normal of the third distribution surface 43 and a normal of the fourth distribution surface 44, and wherein the angle is not equal to 0 degrees; alternatively, the normal of the third distribution surface 43 runs parallel to the normal of the fourth distribution surface 44, and the third distribution surface 43 and the fourth distribution surface 44 are spaced from one another in a normal direction.

[0155] For example, the marking device 50, as shown in Fig.7, a specially arranged marking sign, etc. The marking device 50 and the charging station 10 are provided separately in the working area of ​​the robotic lawnmower, wherein the marking component 2, such as a first marking component 211, a second marking component 212, and a third marking component 213, is provided on the charging station 10, wherein a surface on which the marking component 2 is located is the third distribution surface 43, wherein the third distribution surface 43 can comprise the first distribution surface 41 and the second distribution surface 42 in the embodiments described above, wherein the fourth marking component 214 is provided on the marking device 50, wherein a surface on which the fourth marking component 214 is located is the fourth distribution surface 44,wherein an angle B is formed between a normal (the dashed line shown in the figure) of the third distribution surface 43 and a normal (the dashed line shown in the figure) of the fourth distribution surface 44, and wherein the angle B is not equal to 0 degrees; alternatively, the normal of the third distribution surface 43 is parallel to the normal of the fourth distribution surface 44, and the third distribution surface 43 and the fourth distribution surface 44 are spaced apart from each other in a normal direction.

[0156] In this embodiment, by providing the marking components 2 on the charging station 10 or the marking device 50, the distribution areas of the plurality of feature markings 20 are different, thereby improving the accuracy of the image recognition and the calculation of the relative pose information of the charging station 10 by the robotic lawnmower.

[0157] In a specific implementation, the marking device 50 is a position signal receiving device. For example, the position signal receiving device may be a GPS signal receiver. The fourth marking component 214 may be provided on a surface of the position signal receiving device, which may be achieved by a detachable connection, etc. In this implementation, by providing the marking component 2 on the position signal receiving device used together with the charging station 10, the cost of separately providing the marking device 50 can be reduced.

[0158] It should be noted that in the description of the present application, the terms "first" and "second" are used only for the convenience of describing different components or designations and should not be understood to indicate or imply a sequential relationship or relative importance, or to implicitly indicate a number of the technical features involved. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0159] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms used in the description of this application are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of this application.

[0160] It should be noted that although the specific embodiments of the present application have been described in detail with reference to the accompanying drawings, they should not be construed as limiting the scope of the present application. Within the scope described in the claims, various modifications and variations that can be made by one skilled in the art without inventive steps are still within the scope of the present application.

[0161] The examples of the embodiments of the present application are intended merely to concisely illustrate the technical features of the embodiments of the present application so that those skilled in the art can intuitively understand the technical features of the embodiments of the present application. However, they are not intended to be an undue limitation of the embodiments of the present application.

[0162] Finally, it should be noted that the above-described embodiments are used only to illustrate the technical solution of the present application, rather than to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should appreciate that they may still modify the technical solutions of the above individual embodiments or make equivalent substitutions for some technical features thereof. However, these modifications or substitutions do not cause the essence of the respective technical solutions to deviate from the spirit and scope of the technical solutions of the individual embodiments of the present application.

Claims

[1] Charging station, characterized by in that the charging station comprises a charging station body (11) and a marking component (2), wherein the marking component (2) is used to indicate a position of the charging station (10) so that a robotic lawnmower can dock with the charging station for charging, wherein the marking component (2) comprises a first marking component (20, 211), wherein a plurality of first marking components (20, 211) are provided, which are arranged on the same side surface of the charging station body (11), wherein a marking pattern is formed by the first marking components (20, 211) on a surface of the charging station body (11), wherein the minimum inner diameter in the marking pattern is greater than or equal to a first preset threshold value, and wherein the first preset threshold value is 3 cm. [2] Charging station according to claim 1, characterized bythat the marking pattern formed by the first marking components (20, 211) on a surface of the charging column body (11) is a rectangular pattern. [3] Charging station according to claim 1 or 2, characterized by that four first marking components (20, 211) are provided, wherein adjacent ones of the first marking components (20, 211) are spaced apart from one another by a predetermined distance. [4] Charging station according to claim 3, characterized by that the minimum distance between the marking components (2) is greater than or equal to a second preset threshold, wherein the second preset threshold is 3 cm. [5] Charging station according to claim 3, characterized by that the four first marking components (20, 211) are located at four corner points of a rectangular area. [6] Charging station according to one of claims 1 to 5, characterized byin that the first marking components (20, 211) comprise a first group of first marking components (20, 211) located on an upper part of the side surface of the charging column, and a second group of first marking components (20, 211) located on a lower part of the charging column, wherein the upper part of the side surface of the charging column is a part above a horizontal center line of the side surface of the charging column, and the lower part of the side surface of the charging column is a part below the horizontal center line of the side surface of the charging column. [7] Charging station according to claim 5, characterized by that the charging station further comprises a charging structure (3), wherein the charging structure (3) is located in a rectangular area surrounded by the four first marking components (20, 211). [8] Charging station according to claim 7, characterized bythat at least one of the first marking components (20, 211) is located below the loading structure (3) and at least one of the first marking components (20, 211) is located above the loading structure (3). [9] Charging station according to one of claims 7 to 8, characterized by that the marking component (2) further comprises a second marking component (212), wherein the second marking component (212) is located on the loading structure. [10] Charging station according to claim 9, characterized by that the second marking component (20, 212) is arranged at an overhanging end of the loading structure (3) and the second marking component (212) is arranged on a front end face of the loading structure (3). [11] Charging station according to one of claims 1 to 10, characterized by that the marking component (2) is a reflective component or a luminous element.

Images