Self-moving device and boundary map acquisition method

Abstract

The invention provides a self-moving device and a boundary map obtaining method. The self-moving device comprises a control module, and a visual positioning module and a storage module are both in signal connection with the control module; the control module is configured to receive the positioning information and the image information, obtain a first virtual boundary of the working area based on the positioning information, and obtain a boundary attribute of the area boundary based on the image information; the control module is further configured to perform offset adjustment on the first virtual boundary based on the boundary attribute to obtain second virtual boundaries and a boundary map defined by the second virtual boundaries; the control module is further configured to control the self-moving device to run along the virtual boundary, so that the task execution module executes the work task in the area boundary of the work area. According to the self-moving equipment provided by the invention, boundary attributes do not need to be manually set, the whole working area is more accurately covered, missing areas are reduced, the time for identifying the boundary attributes on site and adjusting the operation mode is shortened, and the operation efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of self-moving device technology, and more particularly to a self-moving device and a method for acquiring boundary maps. Background Technology

[0002] With the rapid development of robotics technology, some robots can move autonomously within their designated activity areas to perform tasks. Correspondingly, such robots can be called self-moving devices. Currently, common self-moving devices include robotic vacuum cleaners, intelligent lawnmowers, and automatic snowplows.

[0003] Existing self-moving devices, such as lawnmowers, require users to identify and set the attributes of map boundaries in real time and adjust the operating parameters of the lawnmower during the mapping process. However, during parameter adjustment, missed mowing may occur, affecting the mowing effect. Summary of the Invention

[0004] In view of this, the purpose of this application is to propose a method for acquiring self-moving devices and boundary maps, which helps to improve the quality and safety of operations while reducing human intervention.

[0005] To achieve one of the aforementioned objectives, this application provides a self-moving device, comprising:

[0006] The visual positioning module is used to acquire positioning information and image information of the work area boundary;

[0007] A storage module is used to store a map of the work area;

[0008] The task execution module is used to execute work tasks;

[0009] The self-moving device also includes:

[0010] The control module, the visual positioning module and the storage module are both signal-connected to the control module;

[0011] The control module is configured to receive the positioning information and the image information, obtain the first virtual boundary of the working area based on the positioning information, and obtain the boundary attributes of the area boundary based on the image information.

[0012] The control module is further configured to offset and adjust the first virtual boundary based on the boundary attributes to obtain a second virtual boundary and a boundary map formed by the second virtual boundary.

[0013] The control module is also configured to control the self-moving device to run along the second virtual boundary, so that the task execution module performs work tasks within the area boundary of the work area.

[0014] As a further improvement to the embodiments of this application, the boundary attributes include safe boundaries and dangerous boundaries, wherein the safe boundary is a region boundary that the mobile device can cross, and the dangerous boundary is a region boundary that the mobile device cannot cross.

[0015] The control module is further configured to overlay the boundary attributes onto the first virtual boundary to form a safe boundary segment and a dangerous boundary segment, respectively.

[0016] As a further improvement to the embodiments of this application, the offset adjustment of the first virtual boundary based on the boundary attribute includes:

[0017] The safe boundary segment is offset outward from the area boundary by a first distance, and the dangerous boundary segment is offset inward from the area boundary by a second distance to obtain the second virtual boundary, and the boundary map is constructed based on the second virtual boundary.

[0018] As a further improvement to the embodiments of this application, the control module is further configured to obtain the boundary category of the region boundary based on the image information;

[0019] The control module adjusts the offset of the first virtual boundary based on the boundary attributes and the boundary category.

[0020] As a further improvement to the embodiments of this application, under the same boundary attributes, the offset adjustment distances corresponding to different boundary categories may be the same or different.

[0021] As a further improvement to the embodiments of this application, the region boundary includes at least one boundary type, which includes at least a sub-region boundary, an island boundary formed in the sub-region boundary, and a channel boundary for connecting multiple sub-region boundaries;

[0022] The control module is configured to offset the first virtual boundary based on the boundary type and / or boundary category of the region boundary, and in conjunction with the boundary attributes.

[0023] To achieve one of the aforementioned objectives, this application also provides a method for obtaining a boundary map, comprising:

[0024] Acquire the location information and image information of the work area's boundary;

[0025] The first virtual boundary of the region is obtained based on the positioning information, and the boundary attributes of the region are obtained based on the image information.

[0026] Based on the boundary attributes, the offset of the first virtual boundary is adjusted to obtain a second virtual boundary and a boundary map enclosed by the second virtual boundary, wherein the second virtual boundary is used to delineate the operating area of ​​the self-moving device.

[0027] As a further improvement to the embodiments of this application, the boundary attributes include safe boundaries and dangerous boundaries, wherein the safe boundary is a region boundary that the mobile device can cross, and the dangerous boundary is a region boundary that the mobile device cannot cross.

[0028] The adjustment of the first virtual boundary offset based on the boundary attribute includes:

[0029] The boundary attributes are superimposed onto the first virtual boundary to form safe boundary segments and dangerous boundary segments, respectively.

[0030] The safety boundary segment is offset outward by a first distance to obtain an outward expansion boundary, and the danger boundary segment is offset inward by a second distance to obtain an inward contraction boundary;

[0031] The second virtual boundary is obtained by fitting the outward expansion boundary and the inward contraction boundary, and the second virtual boundary is smoothed to obtain a boundary map formed by the second virtual boundary.

[0032] As a further improvement to the embodiments of this application, the method further includes: before acquiring the location information and image information of the region boundary of the working area, determining the boundary type of the region boundary; wherein, the boundary type includes at least a sub-region boundary, an island boundary formed in the sub-region boundary, and a channel boundary for connecting multiple sub-region boundaries;

[0033] The step of adjusting the offset of the first virtual boundary based on the boundary attributes includes: adjusting the offset of the first virtual boundary based on the boundary type of the region boundary and in combination with the boundary attributes.

[0034] As a further improvement to the embodiments of this application, obtaining the first virtual boundary of the region boundary based on the positioning information includes:

[0035] Control the self-moving device to run along the boundary of the region;

[0036] Confirm whether the self-moving device has returned to the vicinity of the starting point. If yes, prompt the user that the acquisition of the first virtual boundary has ended; if no, prompt for manual takeover.

[0037] Obtain the first virtual boundary.

[0038] The self-moving device provided in this application acquires positioning and image information of the area boundary through a visual positioning module. It can obtain first virtual boundary information for initially characterizing the work area boundary, and further obtain the boundary attributes of the area boundary based on the image information. This eliminates the need for manual setting of the virtual boundary attributes, improving the intelligence level of the self-moving device. Simultaneously, it can further adjust the first virtual boundary based on the acquired boundary attributes to obtain a second virtual boundary, enabling the self-moving device to operate within the safe range defined by the second virtual boundary. Controlling the self-moving device to run along the second virtual boundary can more accurately cover the entire work area, reducing missed areas and decreasing the time spent on-site identifying boundary attributes and adjusting operating modes, thus improving work efficiency. Attached Figure Description

[0039] Figure 1 A schematic diagram of the structure of a self-moving device provided for some embodiments of this application;

[0040] Figure 2 A schematic diagram of the functional modules of a self-moving device provided in some embodiments of this application;

[0041] Figure 3 This is a schematic diagram of the first virtual boundary in some embodiments of this application;

[0042] Figure 4 This is a schematic diagram of the second virtual boundary in some embodiments of this application;

[0043] Figure 5 This is a schematic diagram of various boundary types for the region boundary in other embodiments of this application;

[0044] Figure 6 This is a flowchart illustrating a method for obtaining a boundary map provided in some other embodiments of this application.

[0045] Figure label:

[0046] 100. Self-moving device; 11. Control module; 12. Task execution module; 13. Visual positioning module; 14. Storage module;

[0047] 200. Working area; 20. First virtual boundary; 21. Safe boundary segment; 22. Dangerous boundary segment; 23. Sub-area boundary; 24. Island boundary; 25. Passage boundary; 26. Second virtual boundary. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0049] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0050] Self-moving devices are robots that integrate all necessary components, such as sensor systems, positioning modules, control modules, power supplies, and propulsion systems. They can independently complete specific tasks without requiring user input or control during automatic operation. Examples of self-moving devices include automatic vacuum cleaners, intelligent lawnmowers, and automatic trimmers. These devices automatically move across the ground or surfaces in their work area to perform tasks such as cleaning, mowing, or snow removal.

[0051] In the field of self-moving equipment, accurate positioning and environmental mapping are key technologies for achieving efficient and safe operation. Taking lawnmowers as an example, related technologies rely on users to identify and set the attributes of map boundaries during the mapping process. This allows the lawnmower to control its movement along the mapped boundaries and adjust the spacing along the boundaries based on these attributes, effectively cutting grass near the work area boundaries. The lawnmower's control module receives boundary attribute information of the work area and adjusts the operating mode accordingly. While these technologies achieve basic boundary recognition and lawnmower control, they still have the following drawbacks: The need for manual identification of boundary attributes and setting of map boundaries based on these attributes increases the user's burden and may lead to reduced efficiency and safety due to human error. Furthermore, the need to continuously adjust operating parameters during the lawnmower's movement along the map boundaries may result in missed cuts, affecting mowing results. Additionally, the dynamic identification of boundary attributes requires real-time processing of large amounts of sensor data and rapid decision-making, demanding high computing power and potentially increasing equipment costs, thus limiting its market competitiveness.

[0052] Based on this, this application provides a method for acquiring self-moving devices and boundary maps to solve the above-mentioned technical problems.

[0053] refer to Figure 1 , Figure 2 and Figure 3 As shown, some embodiments of this application provide a self-moving device 100, which includes a visual positioning module 13, a storage module 14, a task execution module 12, and a control module 11. The visual positioning module 13 is used to acquire positioning information and image information of the boundary of the working area 200, the storage module 14 is used to store a map of the working area 200, the task execution module 12 is used to execute work tasks, and the control module 11 is signal-connected to the visual positioning module 13 and the storage module 14 respectively.

[0054] The control module 11 is configured to: receive positioning information and image information; obtain a first virtual boundary 20 of the work area 200 based on the positioning information; and obtain the boundary attributes of the area boundary of the work area based on the image information; adjust the first virtual boundary 20 based on the boundary attributes to obtain a second virtual boundary 26 and a virtual boundary map formed by the second virtual boundary 26; and control the self-moving device 100 to run along the second virtual boundary 26 so that the task execution module can perform work tasks within the work area 200.

[0055] The self-moving device 100 provided in this embodiment acquires positioning information and image information of the area boundary through the visual positioning module 13 to automatically identify the first virtual boundary 20 of the working area 200. The control module 11 can further obtain the boundary attributes of the area boundary based on the image information, and adjust the first virtual boundary 20 based on the boundary attributes of the area boundary to obtain a second virtual boundary 26, so as to limit or guide the operating range of the self-moving device 100. With this setting, on the one hand, the boundary attributes of the area boundary can be automatically obtained through image information, avoiding the abnormal setting of the virtual boundary caused by manual identification / setting of the boundary attributes of the area boundary; on the other hand, by controlling the self-moving device 100 to run along the second virtual boundary 26, the self-moving device 100 can more accurately cover the entire working area 200 and reduce the omission of area boundary cutting.

[0056] Specifically, the boundary of the work area 200 refers to the edge of the physical area within the work area 200 where work actually needs to be carried out. The boundary is typically defined by physical features such as walls, fences, building edges, or natural terrain. The visual positioning module 13 includes a camera that can capture images of the environment surrounding the boundary in real time. Through image processing technology, it extracts key features from the captured images, such as corners and edges. Using the extracted features, the visual positioning module 13 can construct a two-dimensional or three-dimensional map of the work area, i.e., obtain an initial boundary map. This initial boundary map includes at least a first virtual boundary 20 of the work area boundary, providing spatial information for the movement of the self-moving device 100 within the work area 200. The self-moving device 100 determines its position in the environment by matching the currently captured image information with features on the acquired initial boundary map, and then through the visual positioning module 13.

[0057] During the initial boundary map construction process, the initial boundary map may include mutually mapped SLAM (Simultaneous Localization and Mapping) maps and coordinate maps; wherein, the first virtual boundary 20 is obtained by fitting the boundary SLAM map and boundary coordinate map of the boundary region. Further, in a preferred embodiment of this application, the SLAM map is a visual SLAM map acquired through a visual sensor (such as a camera). The visual positioning module 13 integrates SLAM technology, enabling the self-moving device 100 to autonomously navigate and build maps in unknown environments. The visual positioning module 13 also integrates AI (artificial intelligence) algorithms, which can improve the accuracy of feature recognition, especially in complex or blurry visual environments. Thus, the visual positioning module 13 can provide the self-moving device 100 with the necessary spatial perception capabilities, enabling the self-moving device 100 to achieve autonomous positioning and path planning under complex environmental conditions. Through SLAM technology and AI algorithms, accurate perception of the environment, intelligent boundary adjustment, and efficient and safe operation can be achieved.

[0058] Specifically, the control module 11 extracts the visual features of the region boundary based on the image information collected by the visual positioning module 13, classifies the region boundary according to different boundary attributes, and overlays the identified boundary attribute information onto the first virtual boundary 20 of the initial boundary map, so that the first virtual boundary 20 includes not only the corresponding position information and visual information of the region boundary, but also the boundary attribute information.

[0059] Specifically, based on the boundary attributes, the control module 11 offsets and adjusts the first virtual boundary 20 of the initial boundary map to obtain a second virtual boundary 26 and a boundary map enclosed by the second virtual boundary 26. The second virtual boundary 26 reflects the safe distance calculated based on the boundary attributes and provides runtime constraints and guidance for operations along the edge.

[0060] In a preferred embodiment of this application, the adjusted second virtual boundary 26 can also be used to guide the path planning of the lawnmower, ensuring that the lawnmower operates within a safe range while maximizing the mowing coverage area.

[0061] Furthermore, the edge-running in this application includes cross-edge running and / or edge-hugging running. Cross-edge running means that when the lawnmower is performing a mowing task, it can straddle the second virtual boundary 26 to ensure that the grass on both sides of the area boundary is properly mowed. At the same time, the lawnmower straddling the second virtual boundary 26 helps to optimize the mowing path and reduce invalid or repetitive mowing actions.

[0062] Edge-following operation refers to the lawnmower closely adhering to the second virtual boundary 26 when performing mowing tasks, ensuring that the grass near the area boundary is properly cut. It should be noted that the second virtual boundary 26 and boundary map are different for different edge-following operation modes in this application. That is, the control module 11 can adaptively adjust the offset adjustment distance of the first virtual boundary 20 according to the set edge-following operation mode to ensure the coverage of the lawnmower's cutting of the area boundary of the working area. Furthermore, when the edge-following operation mode is selected before the lawnmower runs, the control module 11 can call up the boundary map stored in the lawnmower.

[0063] In a preferred embodiment of this application, when the selected edge-running mode is cross-edge running, after the lawnmower completes the cutting of the area boundary while straddling the second virtual boundary 26, it fits against the second virtual boundary 26 to cut again, ensuring the integrity of the area boundary cutting.

[0064] In another preferred embodiment of this application, the lawnmower selects different running modes along the edge when performing two adjacent work tasks, so as to ensure the integrity and coverage of the area boundary cutting during the multiple work processes of the lawnmower.

[0065] Of course, in other embodiments of this application, the cutting path in the working area can also be planned according to the selected edge running mode, and the cutting integrity of the area boundary can be compensated by the path planning method.

[0066] refer to Figure 4As shown, in some embodiments of this application, boundary attributes include safe boundaries and dangerous boundaries. A safe boundary is the boundary of an area that the self-moving device (lawnmower) can closely adhere to, and the safe operation of the self-moving device will not be affected when it is closely attached to the boundary. A dangerous boundary is an area boundary where danger is likely to occur when the self-moving device is closely attached to the boundary. The control module 11 is also configured to overlay the boundary attributes onto the first virtual boundary 20 to form a safe boundary segment 21 and a dangerous boundary segment 22, respectively.

[0067] The control module 11 overlays the identified boundary attribute information onto the first virtual boundary 20 and specifically marks the safe boundary segment 21 and the dangerous boundary segment 22; then it obtains the second virtual boundary 26 to characterize and guide the lawnmower to run along the area boundary; wherein the second virtual boundary 26 is formed by adjusting the first virtual boundary 20 according to the boundary attributes, such as shrinking or expanding the first virtual boundary 20 based on the boundary attributes.

[0068] Specifically, the safety boundary is the boundary of the area where the lawnmower can operate closely, such as the boundary of a paved path or dirt road between lawns. Crossing the safety boundary will not damage the equipment or cause it to enter an unsafe area. In this application, the safety boundary may also include the following boundaries: lawn edges, the boundary line between lawns and non-mowing areas, along which the equipment can mow; paved area boundaries, such as the edges of paved paths or brick roads, along which the equipment can mow but will not enter the paved area; and natural terrain boundaries, such as slight slopes or mounds, along which the equipment can safely perform mowing operations.

[0069] A hazardous boundary refers to the boundary of an area where a self-moving device is likely to be dangerous when operating in close proximity to the equipment, such as the boundary of water bodies (the edge of a pond or pool), the edge of steps, or a steep slope. Crossing a hazardous boundary may damage the equipment or cause it to go out of control. In this application, hazardous boundaries may also include the following boundaries: water body boundaries, such as the edges of ponds, lakes, and rivers, which the equipment should avoid contact with to prevent falls or damage; cliff or steep slope boundaries, areas with a height difference, which the equipment should avoid approaching to prevent overturning or damage; traffic area boundaries, such as the edges of roads and driveways, which the equipment should avoid entering to prevent traffic accidents; building edges, the perimeter of buildings such as houses and garages, which the equipment should avoid colliding with; and unidentifiable boundaries, such as fuzzy boundaries that are difficult to identify, such as tall grass or dense grass.

[0070] refer to Figure 4As shown, in some embodiments of this application, the first virtual boundary 20 is offset and adjusted based on boundary attributes, including: offsetting the safety boundary segment 21 outwards from the working area 200 by a first distance to obtain an outward expansion boundary, offsetting the danger boundary segment 22 inwards from the working area 200 by a second distance to obtain an inward contraction boundary, then fitting the outward expansion boundary and the inward contraction boundary to form a second virtual boundary 26, and constructing a boundary map based on the second virtual boundary 26, the boundary map being formed by the second virtual boundary 26.

[0071] Specifically, the safety boundary segment 21 is a virtual boundary segment formed by extending the portion of the first virtual boundary 20 with the boundary attribute of a safety boundary outwards by a first distance towards the area boundary, so as to ensure that the lawnmower can fully cut the area boundary of the working area when running along the virtual boundary segment; the danger boundary segment 22 is a virtual boundary segment formed by extending the portion of the first virtual boundary 20 with the boundary attribute of a danger boundary inwards by a second distance towards the area boundary, so as to prevent the lawnmower from getting too close to the area boundary that may cause damage or danger to the lawnmower, and ensure the safe operation of the lawnmower; while ensuring that the lawnmower can cover the vicinity of the area boundary, reduce the uncut area in the working area, and maximize the mowing coverage area.

[0072] Specifically, after setting the inner and outer boundaries according to the boundary attributes, the first virtual boundary 20 is offset and adjusted. The adjusted outer and inner boundaries are then fitted and smoothed to obtain the second virtual boundary 26 of the working area, ensuring the continuity and smoothness of the second virtual boundary 26. At the same time, when the lawnmower runs along the boundary map formed by the second virtual boundary 26, the lawnmower can run more smoothly.

[0073] In some embodiments of this application, adjusting the map boundary offset based on boundary attributes further includes:

[0074] The control module 11 obtains the boundary category of the working area boundary based on the image information, and adjusts the offset of the first virtual boundary 20 based on the boundary attributes and the boundary category; and under the same boundary attributes, the offset adjustment distances corresponding to different boundary categories are the same or different, that is, under the same boundary attributes, the first distance or the second distance corresponding to different boundary categories are different.

[0075] Specifically, the first virtual boundary 20 can be further subdivided into more specific boundary categories so that the self-moving device 100 can more accurately identify and adapt to its working environment. For example, based on the material of the boundary, the boundary categories of the safety boundary can further include: paved road boundaries and brick road boundaries, which have a clear, traversable hard surface, allowing the device to operate safely within a certain distance; and muddy road boundaries, which, although traversable, may require consideration of preventing the device from getting stuck in the mud.

[0076] The boundary categories for hazardous boundaries can be further included as follows: sloping soil boundaries, such as the edge of a pond which is sloping soil, may require a larger setback distance to prevent equipment from sliding down; and masonry boundaries, such as the edge of a pond which is masonry, where the risk of equipment running along the boundary is lower and the setback distance can be reduced.

[0077] In some embodiments of this application, the offset adjustment distances corresponding to different boundary categories under the same boundary attributes may be the same or different.

[0078] For example, when categorizing the same boundary attributes into different boundary types based on the boundary material, the material also determines the equipment's crossing strategy. For instance, hard stone slab paths and soft mud paths have different impacts on the equipment's crossing ability. In safe boundaries, the offset distances corresponding to stone slab and brick paths can be the same. However, the outward expansion distance corresponding to mud path boundaries can be relatively small to reduce the risk of equipment getting stuck. In dangerous boundaries, the inward expansion distance corresponding to stone masonry boundaries is smaller, while the inward expansion distance corresponding to sloping mud boundaries is larger to prevent the equipment from sliding down.

[0079] refer to Figure 5 As shown, in some embodiments of this application, the region boundary of the working area 200 includes at least one boundary type, which includes at least a sub-region boundary 23 and an island boundary 24 formed in the sub-region boundary 23. The boundary type may also include a channel boundary 25 for connecting multiple sub-region boundaries 23. The control module 11 is configured to adjust the offset of the first virtual boundary 20 based on the boundary type and / or boundary category of the region boundary, combined with the boundary attributes.

[0080] The control module 11 performs offset adjustments based on at least one of the following: boundary type (e.g., sub-region boundary, island boundary, passage boundary), boundary category (e.g., cobblestone road boundary, mud road boundary), and boundary attributes (e.g., safe boundary or dangerous boundary). Each boundary type can include dangerous boundaries and / or safe boundaries. According to the boundary type and boundary attributes, the control module 11 adjusts the map boundaries corresponding to the region boundaries. For example, it can adjust the dangerous boundaries in passage boundary 25 and island boundary 24 towards the working area, or expand the safe boundaries in sub-region boundary 23 outwards. The adjusted boundaries are used to optimize the lawnmower's edge path planning, ensuring the lawnmower completes its work efficiently and safely.

[0081] Specifically, the boundary of the work area 200 includes at least one boundary type, which can be a sub-area boundary 23, an island boundary 24, or a passage boundary 25. The sub-area boundary 23 defines the boundaries of different zones within the work area; for example, a lawn may have multiple sub-areas that need to be mowed separately. The island boundary 24 corresponds to an independent area formed within the sub-area boundary, which may be separated from the surrounding area due to terrain or other obstacles. The passage boundary 25 is used to connect multiple sub-areas, allowing the lawnmower to move from one sub-area to another for operation. Optionally, the control module 11 is also responsible for real-time monitoring of the lawnmower's operating status and environmental changes to adaptively adjust the boundary offset strategy. The control module 11 uses AI algorithms for intelligent decision-making, automatically determining how to adjust the boundary map based on the boundary type and boundary attributes. Of course, users can also intervene in the configuration of the control module 11, adjusting the boundary type and offset strategy according to personal preferences or specific needs.

[0082] refer to Figure 6 As shown in the figure, this application also provides a method for obtaining a boundary map, including the following steps:

[0083] Step S1: Obtain the location information and image information of the boundary of the working area 200;

[0084] Step S2: Obtain the first virtual boundary 20 of the working area based on the positioning information, and obtain the boundary attributes of the area boundary based on the image information;

[0085] Step S3: Based on the boundary attributes, the first virtual boundary 20 is offset and adjusted to obtain the second virtual boundary 26 and the boundary map formed by the second virtual boundary 26. The second virtual boundary 26 is used to delineate the operating area of ​​the self-moving device 100 for the self-moving device 100 to run along the edge.

[0086] The boundary map acquisition method of this application automatically identifies the first virtual boundary 20 of the work area 200 by acquiring the location information and image information of the area boundary, obtains the boundary attributes of the area boundary, and adjusts the offset of the first virtual boundary 20 based on the boundary attributes to obtain the second virtual boundary 26, so as to limit or guide the operating range of the self-moving device 100 and control the self-moving device 100 to run along the edge of the second virtual boundary 26, which can more accurately cover the entire work area 200 and reduce the omission of areas.

[0087] Among them, running along the edge includes running across the edge and / or running close to the edge. Running across the edge means that when the lawnmower is performing the mowing task, it can straddle the second virtual boundary 26 to ensure that the grass on both sides of the area boundary is properly mowed. At the same time, running the lawnmower straddles the second virtual boundary 26 helps to optimize the mowing path and reduce invalid or repetitive mowing actions.

[0088] Edge-following operation refers to the lawnmower closely adhering to the second virtual boundary 26 when performing mowing tasks, ensuring that the grass near the area boundary is properly cut. It should be noted that the second virtual boundary 26 and boundary map are different for different edge-following operation modes in this application. That is, the control module 11 can adaptively adjust the offset adjustment distance of the first virtual boundary 20 according to the set edge-following operation mode to ensure the coverage of the lawnmower's cutting of the area boundary of the working area. Furthermore, when the edge-following operation mode is selected before the lawnmower runs, the control module 11 can call up the boundary map stored in the lawnmower.

[0089] In some embodiments of this application, boundary attributes include safe boundaries and dangerous boundaries. A safe boundary is the boundary of an area that the self-moving device (lawnmower) can closely adhere to, and the safe operation of the self-moving device will not be affected when it is closely attached to the boundary. A dangerous boundary is an area boundary where danger is likely to occur when the self-moving device is closely attached to the boundary. Step S3 includes the following steps:

[0090] Step S31: Overlay the boundary attributes onto the first virtual boundary 20 to form a safe boundary segment 21 and a dangerous boundary segment 22 respectively;

[0091] Step S32: Offset the safety boundary segment 21 outward by a first distance to obtain the outward expansion boundary, and offset the danger boundary segment 22 inward by a second distance to obtain the inward contraction boundary;

[0092] Step S33: Fit the outward expansion boundary and the inward contraction boundary to obtain a second virtual boundary 26, and smooth the second virtual boundary 26 to obtain a boundary map enclosed by the second virtual boundary 26. Specifically, the boundary map acquisition method of this application enhances the map by overlaying boundary attribute information onto the first virtual boundary 20 and specifically marking the safe boundary segment 21 and the dangerous boundary segment 22. For the dangerous boundary segment 22, an inward contraction operation increases the distance from the first virtual boundary 20, preventing the device from getting too close to potentially damaging or dangerous locations and maintaining a safe distance. For the safe boundary segment 21, an outward expansion operation ensures that the lawnmower can cover the vicinity of the boundary, reducing uncut areas and maximizing the mowing coverage area.

[0093] After the boundary map is generated, the self-moving device 100 can use the boundary map to start running along the second virtual boundary 26 and perform its work tasks. During task execution, single-frame images captured by the camera are segmented using a deep learning network to generate a segmentation map, which is then fused with the depth map to generate a single-frame raster map. As the self-moving device 100 moves, multiple frames of raster maps are stitched together to form a local map, improving the stability of recognition and the coverage of the map. The local map classifies and merges the information in the single-frame raster map, dividing areas according to traffic strategies, such as living obstacles, non-living obstacles, crossable areas, and passable areas. The lawnmower calculates its travel path based on the division of different areas. For living and non-living obstacles, the lawnmower avoids crossing the boundary; for crossable areas, the terrain and width are considered to determine the optimal travel path to reduce grass left behind. Within passable areas, the lawnmower combines the global map and its own positioning information to generate a travel path, ensuring that it does not cross the boundary when mowing along the boundary. Additionally, for areas that can be crossed, the driving path can be determined by reducing the area of ​​these areas on the map, allowing the lawnmower to travel closer to the boundary and reducing the possibility of leaving grass behind. For dangerous boundaries or areas that the user specifies should not be crossed, the area of ​​these areas can be expanded to ensure that the lawnmower maintains a safe distance and avoids approaching or entering them. By adjusting the area area on the lawnmower's map, an optimized driving path can be generated, allowing the lawnmower to work more accurately along the actual mowing boundaries.

[0094] refer to Figure 5 As shown, in some embodiments of this application, the method for obtaining the boundary map further includes:

[0095] Before step S1, the boundary type of the region boundary is determined; wherein, the boundary type includes at least sub-region boundary 23, island boundary 24 formed in sub-region boundary 23, and channel boundary 25 used to connect multiple sub-region boundaries 23;

[0096] Step S3, "Adjusting the offset of the first virtual boundary 20 based on boundary attributes", includes: adjusting the offset of the first virtual boundary 20 based on the boundary type of the region boundary and in combination with the boundary attributes.

[0097] Specifically, before controlling the self-moving device 100 to run along the edge, the user specifies the boundary type of the first virtual boundary 20. For example, when building a single-area boundary map, the user specifies the boundary type as sub-area boundary 23 on the APP, controls the lawnmower to run along the boundary, and builds the initial boundary map of that area. Before entering the next sub-area map, the user specifies the boundary type as channel boundary 25 and builds the initial boundary map of the channel. After entering the next sub-area, the user switches to sub-area boundary 23, controls the lawnmower to run along the boundary, and builds the corresponding initial boundary map. During the single-area mapping process, boundary attributes are automatically matched based on AI algorithms and SLAM technology. Each boundary type can include dangerous boundaries and / or safe boundaries. Boundary attributes can be identified using AI algorithms and superimposed onto the first virtual boundary 20 obtained through SLAM technology. Individual image frames are processed to identify features such as the height and category of obstacles or area boundaries. By analyzing multiple consecutive image frames, the identification results are stitched together to form a local map. Multi-frame recognition helps improve the stability and accuracy of environmental recognition. The machine combines local and global maps with its own location information to determine the accurate attributes of the boundaries. Of course, users can preset boundary rules, allowing the self-moving device 100 to automatically execute these rules and adjust them according to actual conditions. Thus, the self-moving device 100 can determine boundary attributes and achieve highly automated mapping and lawn mowing operations accordingly.

[0098] In some embodiments of this application, step S2, "obtaining the first virtual boundary 20 of the work area boundary based on positioning information," includes the following steps:

[0099] Step S21: Control the self-moving device 100 to run along the area boundary;

[0100] Step S22: Confirm whether the self-moving device 100 has returned to the vicinity of the starting point. If yes, prompt the user that the acquisition of the first virtual boundary has ended; if no, prompt for manual takeover.

[0101] Step S23: Obtain the first virtual boundary.

[0102] The automatic confirmation and user interaction stages in the mapping process are designed to ensure the accuracy and completeness of the mapping, and to allow for manual intervention when necessary to ensure the smooth progress of the operation.

[0103] It should be noted that "a certain body" or "a certain part" can be a portion of the corresponding "component," meaning that "a certain body" or "a certain part" is integrally formed and manufactured with the "other parts of the component"; or it can be an independent component that can be separated from the "other parts of the component," meaning that "a certain body" or "a certain part" can be manufactured independently and then combined with the "other parts of the component" to form a whole. The expression of "a certain body" or "a certain part" in this application is only one embodiment for ease of reading, and is not intended to limit the scope of protection of this application. Any technical solution that includes the above features and has the same function should be understood as an equivalent technical solution of this application.

[0104] It should be noted that some embodiments of this application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that in the above embodiments and still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result.

[0105] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; under the concept of this application, the above embodiments or technical features of different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0106] The embodiments described herein are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments described herein should be included within the protection scope of this application.

Claims

1. A self-moving device, comprising: The visual positioning module is used to acquire positioning information and image information of the work area boundary; A storage module is used to store a map of the work area; The task execution module is used to execute work tasks; The self-moving device is characterized in that it further includes: The control module, the visual positioning module and the storage module are both signal-connected to the control module; The control module is configured to receive the positioning information and the image information, obtain the first virtual boundary of the working area based on the positioning information, and obtain the boundary attributes of the area boundary based on the image information. The control module is further configured to offset and adjust the first virtual boundary based on the boundary attributes to obtain a second virtual boundary and a boundary map formed by the second virtual boundary. The control module is also configured to control the self-moving device to run along the second virtual boundary, so that the task execution module performs work tasks within the area boundary of the work area.

2. The self-moving device according to claim 1, characterized in that, The boundary attributes include safe boundaries and dangerous boundaries. The safe boundary is a region boundary that the mobile device can cross, and the dangerous boundary is a region boundary that the mobile device cannot cross. The control module is further configured to overlay the boundary attributes onto the first virtual boundary to form a safe boundary segment and a dangerous boundary segment, respectively.

3. The self-moving device according to claim 2, characterized in that, The offset adjustment of the first virtual boundary based on the boundary attributes includes: The safe boundary segment is offset outward from the area boundary by a first distance, and the dangerous boundary segment is offset inward from the area boundary by a second distance to obtain the second virtual boundary, and the boundary map is constructed based on the second virtual boundary.

4. The self-moving device according to claim 1, characterized in that, The control module is also configured to obtain the boundary category of the region boundary based on the image information; The control module adjusts the offset of the first virtual boundary based on the boundary attributes and the boundary category.

5. The self-moving device according to claim 4, characterized in that, Under the same boundary attribute, the offset adjustment distances corresponding to different boundary categories may be the same or different.

6. The self-moving device according to claim 1 or 4, characterized in that, The region boundary includes at least one boundary type, which includes at least a sub-region boundary, an island boundary formed in the sub-region boundary, and a channel boundary for connecting multiple sub-region boundaries; The control module is configured to offset the first virtual boundary based on the boundary type and / or boundary category of the region boundary, and in conjunction with the boundary attributes.

7. A method for obtaining a boundary map, characterized in that, include: Acquire the location information and image information of the work area's boundary; The first virtual boundary of the region is obtained based on the positioning information, and the boundary attributes of the region are obtained based on the image information. Based on the boundary attributes, the first virtual boundary is offset and adjusted to obtain a second virtual boundary and a boundary map formed by the second virtual boundary, wherein the second virtual boundary is used to delineate the operating area of ​​the self-moving device.

8. The method for obtaining a boundary map according to claim 7, characterized in that, The boundary attributes include safe boundaries and dangerous boundaries. The safe boundary is a region boundary that the mobile device can cross, and the dangerous boundary is a region boundary that the mobile device cannot cross. The offset adjustment of the first virtual boundary based on the boundary attribute includes: The boundary attributes are superimposed onto the first virtual boundary to form safe boundary segments and dangerous boundary segments, respectively. The safety boundary segment is offset outward by a first distance to obtain an outward expansion boundary, and the danger boundary segment is offset inward by a second distance to obtain an inward contraction boundary. The second virtual boundary is obtained by fitting the outward expansion boundary and the inward contraction boundary, and the second virtual boundary is smoothed to obtain a boundary map formed by the second virtual boundary.

9. The method for obtaining a boundary map according to claim 7, characterized in that, The method further includes: before acquiring the location information and image information of the area boundary of the working area, determining the boundary type of the area boundary; wherein, the boundary type includes at least a sub-area boundary, an island boundary formed in the sub-area boundary, and a channel boundary for connecting multiple sub-area boundaries; The step of offsetting the first virtual boundary based on the boundary attributes includes: offsetting the first virtual boundary based on the boundary type of the region boundary and in combination with the boundary attributes.

10. The method for obtaining a boundary map according to claim 7, characterized in that, The first virtual boundary obtained based on the positioning information includes: Control the self-moving device to run along the boundary of the region; Confirm whether the self-moving device has returned to the vicinity of the starting point. If yes, prompt the user that the acquisition of the first virtual boundary has ended; if no, prompt for manual takeover. Obtain the first virtual boundary.

Images