Cleaning path planning method and cleaning robot

Abstract

The invention discloses a cleaning path planning method, and the method comprises the steps: obtaining overhead visual image data which is used for representing space image data located above a plane where a to-be-planned path is located and in a plane parallel to the plane, identifying a visual occlusion area and a visual non-occlusion area in the overhead visual image data, determining a minimum circumscribed polygon of the visual occlusion area based on the identified visual occlusion area, and determining a minimum circumscribed polygon of the visual occlusion area in the visual non-occlusion area adjacent to the minimum circumscribed polygon, and selecting one side with the longest side length of the minimum circumscribed polygon as an observation reference side for guiding a coverage path, and planning a cleaning path for the visual occlusion area by taking the observation reference side as an access side. The cleaning efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of cleaning robots, and in particular to a cleaning path planning method. Background Art

[0002] Cleaning path planning is one of the effective ways for cleaning robots to ensure cleaning efficiency and cleaning results.

[0003] Existing cleaning path planning is based on machine vision positioning of images captured by a front image acquisition device installed in front of the cleaning robot. Due to the limitations of the field of view of the front image acquisition device, the efficiency and accuracy of cleaning path planning are unsatisfactory. Summary of the Invention

[0004] The present invention provides a cleaning path planning method to improve the efficiency and accuracy of the cleaning planning path.

[0005] A first aspect of the present invention provides a cleaning path planning method, the method comprising:

[0006] Obtaining overhead visual image data, wherein the overhead visual image data is used to represent spatial image data located above the plane where the path to be planned is located and in a plane parallel to the plane.

[0007] Identify visually blocked areas and visually unblocked areas in the overhead visual image data,

[0008] Based on the identified visual occlusion area, determine the minimum circumscribed polygon of the visual occlusion area,

[0009] In the visually unobstructed area adjacent to the minimum circumscribed polygon, the longest side of the minimum circumscribed polygon is selected as the observation reference side for guiding the coverage path.

[0010] The observation reference edge is used as the entry and exit edge to plan the cleaning path for the visually blocked area.

[0011] As a possible implementation manner, the acquiring of overhead visual image data includes:

[0012] The top image acquisition device located on the top of the cleaning robot acquires spatial image data in a plane above the carrying surface on which the cleaning robot is located and parallel to the carrying surface;

[0013] The step of selecting the longest side of the minimum circumscribed polygon as the observation reference side for guiding the coverage path includes:

[0014] The longest side of the minimum circumscribed polygon is extended by a set distance threshold toward the visually unobstructed area adjacent to the minimum circumscribed polygon to obtain an extended side as an observation reference side.

[0015] As a possible implementation method, the planning of a cleaning path for the visually blocked area using the observation reference edge as the entry and exit edge includes:

[0016] A bow-shaped path is planned in the visual occlusion area in a direction perpendicular to the observation reference edge, so that the visual occlusion area is covered by the bow-shaped path, wherein the straight path in the bow-shaped path is perpendicular to the observation reference edge, and the rotation path used to connect two adjacent straight paths in the bow-shaped path is parallel to or coincides with the observation reference edge.

[0017] As a possible implementation, planning a bow-shaped path in the visually blocked area includes:

[0018] When it is detected that there is no feasible area in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge, and the bow-shaped path is readjusted at the observation reference edge.

[0019] As a possible implementation manner, determining the minimum circumscribed polygon of the visually blocked area based on the identified visually blocked area includes:

[0020] Determining a minimum bounding rectangle of the identified visually blocked area;

[0021] The step of selecting the longest side of the minimum circumscribed polygon as the observation reference side for guiding the coverage path includes:

[0022] The two longest sides of the minimum circumscribed rectangle are used as the two observation reference sides.

[0023] As a possible implementation, planning a bow-shaped path in the visually blocked area includes:

[0024] Plan a bow-shaped straight path in the visual occlusion area in a direction perpendicular to the first of the two observation reference edges until the current straight path reaches the second of the two observation reference edges, and plan a bow-shaped rotation path at the second observation reference edge.

[0025] At the end point of the bow-shaped rotation path planned at the current second observation reference side, the next bow-shaped straight path is planned in the visual occlusion area in a direction perpendicular to the second observation reference side until the current straight path reaches the first observation reference side, and a bow-shaped rotation path is planned at the first observation reference side.

[0026] Return to the step of planning a bow-shaped straight path in the visual occlusion area in a direction perpendicular to the first observation reference side of the two observation reference sides until the visual occlusion area is covered by the bow-shaped path.

[0027] As a possible implementation manner, the length of the rotation path is determined according to the maximum size of a cleaning component of the cleaning robot that contacts the area to be cleaned.

[0028] As a possible implementation, the straight path planning further includes:

[0029] In the event that a non-feasible area is detected in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge where the current straight path starts, and a bow-shaped turning path is planned at the current observation reference edge. The turning path is parallel to or coincides with the current observation reference edge, and the length of the turning path is adjusted to a length that allows the next straight path starting from the current observation reference edge to bypass the non-feasible area in the current straight path;

[0030] According to the direction perpendicular to the current observation reference edge, a bow-shaped next straight path starting from the current observation reference edge is planned in the visual occlusion area until the next straight path reaches the other observation reference edge, and a bow-shaped turning path is planned at the other observation reference edge. The turning path is parallel to or coincides with the other observation reference edge, and the length of the turning path is adjusted to cover the area between the next straight path starting from the other observation reference edge and the next straight path starting from the current observation reference edge, and to reach a length where there is no feasible area in the current straight path.

[0031] A second aspect of the present application provides a cleaning robot, which includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the cleaning path planning method.

[0032] As a possible implementation, the top of the cleaning robot includes an image acquisition device.

[0033] The cleaning path planning method provided by the present invention plans the path of the visual occlusion area based on the visual occlusion area identified by the overhead visual image data, which not only avoids the field of view limitation of the front image acquisition device, but also solves the problem of generating a cleaning planning path when the overhead visual positioning fails due to occlusion, reduces long-term occlusion situations to ensure positioning stability, and avoids excessive repeated paths by using the observation reference edge as the entry and exit edge, which is beneficial to improving cleaning efficiency, reducing continuous visual occlusion each time the cleaning path is switched, and improving positioning stability. In this way, the cleaning operation of the cleaning robot is more adaptable and the number of missed cleaning areas is effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1A flow chart of the cleaning path planning method according to an embodiment of the present application.

[0035] Figure 2 This is a schematic diagram of the cleaning path planning of this embodiment.

[0036] Figure 3 A schematic diagram of the identified visually blocked area and the visually unblocked area.

[0037] Figure 4 A schematic diagram of the minimum bounding rectangle of a visually occluded area.

[0038] Figure 5 A schematic diagram of generating an observation reference edge in this embodiment.

[0039] Figure 6 This is a schematic diagram of the bow-shaped path planning in this embodiment.

[0040] Figure 7 This is another schematic diagram of the bow-shaped path planning in this embodiment.

[0041] Figure 8 This is a schematic diagram of a cleaning path planning device according to an embodiment of the present application.

[0042] Figure 9 This is another schematic diagram of the cleaning path planning device according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical means and advantages of this application more clear, this application is further described in detail below with reference to the accompanying drawings.

[0044] The applicant's research found that the cleaning path planning of the cleaning robot is based on the visual image data of its carrying surface collected by the front image acquisition device. Since there are various obstacles distributed on the carrying surface, such as various furniture, household items, etc., this not only leads to fragmented cleaning path planning, resulting in low cleaning efficiency, but also makes it almost impossible to plan cleaning paths for carrying surfaces located under beds, tables, etc., and thus difficult to perform effective cleaning.

[0045] In view of this, an embodiment of the present application provides a cleaning path planning method, which uses overhead visual image data to plan the cleaning path, thereby improving the planning efficiency and accuracy of the cleaning path.

[0046] See also Figure 1 As shown, Figure 1 A flow chart of the cleaning path planning method according to an embodiment of the present application.

[0047] The method includes:

[0048] Step 101: Obtain overhead visual image data, wherein the overhead visual image data is used to represent spatial image data located above the plane where the path to be planned is located and in a plane parallel to the plane.

[0049] As an example, the overhead image acquisition device located on the top of the cleaning robot collects spatial image data in a plane above the supporting surface of the cleaning robot and parallel to the supporting surface. In this way, the overhead visual image data is equivalent to an overhead view of the spatial environment where the cleaning robot is located; it should be understood that the overhead visual image data can be collected in real time, for example, in real time during the cleaning process, or it can be collected non-real time, for example, pre-collected and stored in the cleaning robot body. This application does not impose any restrictions on this.

[0050] Step 102: Identify the visually blocked area and the visually unblocked area in the overhead visual image data.

[0051] As an example, based on the overhead visual image data, feature extraction is performed, and the visually blocked area and the visually unblocked area in the overhead visual image data are identified according to the extracted features.

[0052] As another example, a trained artificial intelligence model, such as a neural network model, is used to identify visually occluded areas and visually unoccluded areas in overhead visual image data.

[0053] Step 103: Based on the identified visual occlusion area, determine the minimum circumscribed polygon of the visual occlusion area.

[0054] As an example, there may be multiple visual occlusion areas. For each visual occlusion area, the minimum circumscribed polygon of the visual occlusion area is determined.

[0055] To reduce complexity, the minimum enclosing polygon may be a minimum enclosing rectangle.

[0056] Step 104: In the visually unobstructed area adjacent to the minimum circumscribed polygon, select one of the longest sides of the minimum circumscribed polygon as an observation reference side for guiding the coverage planning path.

[0057] As an example, one of the longest sides of the minimum circumscribed polygon is extended by a set distance threshold toward the unobstructed visual area adjacent to the minimum circumscribed polygon to obtain an extended edge, which serves as an observation reference edge. The distance threshold can be determined based on the body size of the cleaning robot.

[0058] There may be multiple observation reference sides. For example, when the minimum circumscribed polygon is a minimum circumscribed rectangle, the two longest sides of the minimum circumscribed rectangle are respectively used as observation reference sides.

[0059] Step 105 : Planning a cleaning path for the visually blocked area using the observed reference edge as the entry and exit edge.

[0060] As an example, a bow-shaped path is planned in the visual occlusion area in a direction perpendicular to the observation reference edge, so that the visual occlusion area is covered by the bow-shaped path, wherein the straight path in the bow-shaped path is perpendicular to the observation reference edge, and the rotation path used to connect two adjacent straight paths in the bow-shaped path is parallel to or coincides with the observation reference edge.

[0061] For example, if the visual occlusion area is the minimum circumscribed rectangle, a bow-shaped straight path can be planned in the visual occlusion area in a direction perpendicular to the first of the two observation reference edges until the current straight path reaches the second of the two observation reference edges, and a bow-shaped rotation path can be planned at the second observation reference edge.

[0062] At the end point of the bow-shaped rotation path planned at the current second observation reference side, the next bow-shaped straight path is planned in the visual occlusion area in a direction perpendicular to the second observation reference side until the current straight path reaches the first observation reference side, and a bow-shaped rotation path is planned at the first observation reference side.

[0063] Return to the step of planning a bow-shaped straight path in the visual occlusion area in a direction perpendicular to the first observation reference edge of the two observation reference edges until the visual occlusion area is covered by the bow-shaped path, so that the planned path is formed within the two observation reference edges.

[0064] Furthermore, when it is detected that there is no feasible area in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge, and the bow-shaped path is readjusted at the observation reference edge.

[0065] For example, in the case where the visual occlusion area is a minimum bounding rectangle, if it is detected that there is an infeasible area in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge where the current straight path starts. A bow-shaped turning path is planned at the current observation reference edge. The turning path is parallel to or coincides with the current observation reference edge, and the length of the turning path is adjusted to a length that allows the next straight path starting from the current observation reference edge to bypass the infeasible area in the current straight path.

[0066] According to the direction perpendicular to the current observation reference edge, a bow-shaped next straight path starting from the current observation reference edge is planned within the visual occlusion area until the next straight path reaches the other observation reference edge, and a bow-shaped turning path is planned at the other observation reference edge. The turning path is parallel to or coincides with the other observation reference edge, and the length of the turning path is adjusted to cover the area between the next straight path starting from the other observation reference edge and the next straight path starting from the current observation reference edge, and to reach the length where there is no feasible area in the current straight path. In this way, the planned path covers the feasible area within the two observation reference edges.

[0067] The cleaning path planning method provided in the embodiment of the present application plans the cleaning path for the visually blocked area in the overhead visual image data, so that the path planning can also be performed on the blocked area above the plane where the planned path is located, which is beneficial to increasing the cleaning range and avoiding missing the cleaning area. By observing the reference edge for path planning, the cleaning robot can enter the blocked area in the shortest way, which is beneficial to improving the cleaning efficiency.

[0068] To facilitate understanding of the embodiments of the present application, the following is an example of a cleaning robot planning a cleaning path based on overhead visual image data. It should be understood that the embodiments of the present application are not limited to this specific overhead visual image data, and overhead visual image data in any other spatial environment can be applied to the present application.

[0069] See also Figure 2 As shown, Figure 2 This is a schematic diagram of cleaning path planning in this embodiment. The method includes:

[0070] Step 201, obtaining overhead visual image data,

[0071] As an example, the cleaning robot moves in the environment in advance, and collects overhead visual image data through an overhead image acquisition device installed on its top to construct a base map.

[0072] Step 202: Identify visually blocked areas and visually unblocked areas based on the acquired overhead visual image data.

[0073] See also Figure 3 As shown, Figure 3A schematic diagram of the identified visually obstructed and unobstructed areas. The green area represents the visually obstructed area, including three areas with ranges greater than the set range threshold. The red and yellow areas represent the visually unobstructed areas. For example, the visually unobstructed area is typically the ceiling, which can be understood as an obstacle-free area in overhead visual image data. However, the visually obstructed area, due to the obstruction of the ceiling, can cause unstable positioning results during visual positioning, and can be understood as an unstable positioning area.

[0074] The recognition method may be: based on the overhead visual image data, performing feature extraction, and identifying the visually blocked areas and visually unobstructed areas in the overhead visual image data based on the extracted features; or using a trained artificial intelligence model, such as a neural network model, to identify the visually blocked areas and visually unobstructed areas in the overhead visual image data. This application does not impose any restrictions on this.

[0075] Step 203: Determine the minimum bounding rectangle of the visually blocked area based on the identified visually blocked area.

[0076] As an example, based on the pixel position information of the identified visual occlusion area, the pixel position information of the minimum circumscribed rectangle of the visual occlusion area is calculated.

[0077] See also Figure 4 As shown, Figure 4 FIG2 is a schematic diagram of a minimum bounding rectangle of a visual occlusion area. In the figure, the minimum bounding rectangle of the visual occlusion area can be determined by the pixel position information of the four vertices abcd of the minimum bounding rectangle.

[0078] Step 204: Generate observation reference edge information based on the minimum bounding rectangle.

[0079] As an example, in the feasible area adjacent to the minimum enclosing rectangle, the longest side of the minimum enclosing rectangle is selected as the reference. For example, in the feasible area adjacent to the minimum enclosing rectangle, the long side is selected, that is, among the four rectangular sides, the rectangular sides that fall into the occlusion area are not counted, and the longest rectangular side is selected from the remaining rectangular sides.

[0080] Based on the selected reference, an observation reference edge of the same length as the reference edge is extended perpendicularly toward the feasible region to guide the coverage planning path. The distance threshold for this extension can be determined based on the size of the cleaning robot, for example, its width. In other words, the longest edge of the selected rectangle is translated perpendicularly toward the feasible region by the set distance threshold. Extending the reference edge improves the reliability of path planning and reduces the likelihood of positioning failure.

[0081] See also Figure 5 As shown, Figure 5 A schematic diagram of generating an observation reference edge in this embodiment is shown in FIG. In the figure, the longest rectangular side in the unobstructed visual area is ab, and based on ab, the observation reference edge a1b1 is obtained by expansion.

[0082] The number of observation reference edges can be multiple. Take the two longest sides of the minimum bounding rectangle as the reference, and expand them to the adjacent visual unobstructed area to obtain two observation reference edges, such as Figure 7 Indicated by the blue line.

[0083] Step 205 : Using the observed reference edge as the entry and exit edge, path planning is performed on the video occlusion area.

[0084] As an example, a bow-shaped path is planned within the minimum circumscribed rectangle along a direction perpendicular to the observation reference edge, wherein the straight path in the bow is perpendicular to the observation reference edge, and the rotation path used to connect two adjacent straight paths can be parallel to or coincide with the observation reference edge.

[0085] It should be understood that, in this embodiment, there is no restriction on the starting position of the bow-shaped path on the observation reference edge, that is, the bow-shaped path can start from anywhere on the observation reference edge and end at anywhere on the observation reference edge, as long as the video occlusion area is covered by the planned path. This is beneficial for the cleaning robot to enter the visual occlusion area by the shortest path, thereby improving cleaning efficiency.

[0086] See also Figure 6 As shown, Figure 6 This is a schematic diagram of the bow-shaped path planning in this embodiment. In the figure, a straight bow-shaped path is planned starting from position A of the observation reference edge until it reaches the obstacle. At the obstacle, a roundabout path is planned along the edge of the obstacle, and this process is repeated until the entire video occlusion area within the minimum bounding rectangle is covered by the planned path.

[0087] See also Figure 7 As shown, Figure 7 This is another schematic diagram of the bow-shaped path planning in this embodiment. Starting from position A on observation reference edge b1a1, a straight path in the shape of a bow is planned in a direction perpendicular to observation reference edge b1a1 until reaching observation reference edge c1d1. A rotational path is then planned at observation reference edge c1d1. Finally, a straight path is planned at the endpoint of the rotational path in a direction perpendicular to observation reference edge c1d1.

[0088] If no feasible area is detected on the current straight path, for example, an obstacle is detected, the shortest path is used to return to the starting point of the current straight path, such as Figure 7As shown by the dotted line in , a turning path is then planned. The turning path is parallel to or coincides with the current observation reference edge, and the length of the turning path is adjusted to allow the next straight path starting from the current observation reference edge b1a1 to bypass the length of the infeasible area in the current straight path, as shown in FIG. Figure 7 AB path in, return to the step of planning a bow-shaped straight path from position A of the observation reference edge b1a1 along a direction perpendicular to the observation reference edge b1a1 until reaching the observation reference edge c1d1; at the observation reference edge c1d1, plan a rotation path, which is parallel to or coincides with the current observation reference edge c1d1, and the length of the rotation path is adjusted to ensure that the area between the next straight path starting from the current observation reference edge c1d1 and the straight path starting from the observation reference edge b1a1 is covered, and the length reaches the length of the current straight path where there is no feasible area, as shown in FIG. Figure 7 The CD path in .

[0089] Step 206: The cleaning robot moves along the planned path to perform cleaning operations.

[0090] As an example, the cleaning robot converts the planned path into a planned path in a world coordinate system, and moves according to the planned path to perform a cleaning operation on the carrying surface where the cleaning robot is located.

[0091] Step 207: Determine whether an obstacle is detected during the current movement.

[0092] If so, the shortest path is selected to return to the observed reference edge, and the vehicle is rotated according to the planned rotation path at the observed reference edge to move according to the next planned straight line path.

[0093] Otherwise, return to step 206 until all video occlusion areas are cleaned.

[0094] In this embodiment, the planned path is executed after the planned path is completed. It should be understood that the planned path can also be generated and executed in real time, and the embodiment of the present application does not limit this.

[0095] See also Figure 8 As shown, Figure 8 This is a schematic diagram of a cleaning path planning device according to an embodiment of the present application. The device includes:

[0096] An acquisition module is used to acquire overhead visual image data, wherein the overhead visual image data is used to represent spatial image data located above the plane where the path to be planned is located and in a plane parallel to the plane.

[0097] A recognition module is used to identify visually blocked areas and visually unblocked areas in the overhead visual image data.

[0098] The planning module is used to determine the minimum circumscribed polygon of the visually blocked area based on the identified visually blocked area, and select the longest side of the minimum circumscribed polygon in the visually unobstructed area adjacent to the minimum circumscribed polygon as the observation reference side for guiding the covering path, and use the observation reference side as the entry and exit side to plan the cleaning path for the visually blocked area.

[0099] See also Figure 9 As shown, Figure 9 This is another schematic diagram of a cleaning path planning device according to an embodiment of the present application. The device includes a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the computer program to implement the steps of the cleaning path planning method according to an embodiment of the present application.

[0100] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0101] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0102] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the cleaning path planning method of the embodiment of the present application are implemented.

[0103] As for the apparatus / network-side device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0104] In this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0105] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A cleaning path planning method, characterized in that: The method includes: Obtaining overhead visual image data, wherein the overhead visual image data is used to represent spatial image data located above the plane where the path to be planned is located and in a plane parallel to the plane. Identify visually blocked areas and visually unblocked areas in the overhead visual image data, Based on the identified visual occlusion area, determine the minimum circumscribed polygon of the visual occlusion area, In the visually unobstructed area adjacent to the minimum circumscribed polygon, the longest side of the minimum circumscribed polygon is selected as the observation reference side for guiding the coverage path. The observation reference edge is used as the entry and exit edge to plan the cleaning path for the visually blocked area.

2. The cleaning path planning method according to claim 1, wherein: The acquiring of overhead visual image data comprises: The top image acquisition device located on the top of the cleaning robot acquires spatial image data in a plane above the carrying surface on which the cleaning robot is located and parallel to the carrying surface; The step of selecting the longest side of the minimum circumscribed polygon as the observation reference side for guiding the coverage path includes: The longest side of the minimum circumscribed polygon is extended by a set distance threshold toward the visually unobstructed area adjacent to the minimum circumscribed polygon to obtain an extended side as an observation reference side.

3. The cleaning path planning method according to claim 1 or 2, characterized in that: The planning of a cleaning path for the visually blocked area using the observation reference edge as the entry and exit edge includes: A bow-shaped path is planned in the visual occlusion area in a direction perpendicular to the observation reference edge, so that the visual occlusion area is covered by the bow-shaped path, wherein the straight path in the bow-shaped path is perpendicular to the observation reference edge, and the rotation path used to connect two adjacent straight paths in the bow-shaped path is parallel to or coincides with the observation reference edge.

4. The cleaning path planning method according to claim 3, wherein: Planning a bow-shaped path in the visually blocked area includes: When it is detected that there is no feasible area in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge, and the bow-shaped path is readjusted at the observation reference edge.

5. The cleaning path planning method according to claim 4, characterized in that: The step of determining the minimum circumscribed polygon of the visually blocked area based on the identified visually blocked area includes: Determining a minimum bounding rectangle of the identified visually blocked area; The step of selecting the longest side of the minimum circumscribed polygon as the observation reference side for guiding the coverage path includes: The two longest sides of the minimum circumscribed rectangle are used as the two observation reference sides.

6. The cleaning path planning method according to claim 5, characterized in that: Planning a bow-shaped path in the visually blocked area includes: Plan a bow-shaped straight path in the visual occlusion area in a direction perpendicular to the first of the two observation reference edges until the current straight path reaches the second of the two observation reference edges, and plan a bow-shaped rotation path at the second observation reference edge. At the end point of the bow-shaped rotation path planned at the current second observation reference side, the next bow-shaped straight path is planned in the visual occlusion area in a direction perpendicular to the second observation reference side until the current straight path reaches the first observation reference side, and a bow-shaped rotation path is planned at the first observation reference side. Return to the step of planning a bow-shaped straight path in the visual occlusion area in a direction perpendicular to the first observation reference side of the two observation reference sides until the visual occlusion area is covered by the bow-shaped path.

7. The cleaning path planning method according to claim 6, characterized in that: The length of the rotation path is determined according to the maximum size of a cleaning component of the cleaning robot that contacts the area to be cleaned.

8. The cleaning path planning method according to claim 6, wherein: The planning of the straight path further includes: In the event that a non-feasible area is detected in the current straight path, the current straight path is terminated, and the shortest path is selected to return to the observation reference edge where the current straight path starts, and a bow-shaped turning path is planned at the current observation reference edge. The turning path is parallel to or coincides with the current observation reference edge, and the length of the turning path is adjusted to a length that allows the next straight path starting from the current observation reference edge to bypass the non-feasible area in the current straight path; According to the direction perpendicular to the current observation reference edge, a bow-shaped next straight path starting from the current observation reference edge is planned in the visual occlusion area until the next straight path reaches the other observation reference edge, and a bow-shaped turning path is planned at the other observation reference edge. The turning path is parallel to or coincides with the other observation reference edge, and the length of the turning path is adjusted to cover the area between the next straight path starting from the other observation reference edge and the next straight path starting from the current observation reference edge, and to reach a length where there is no feasible area in the current straight path.

9. A cleaning robot, characterized in that: The cleaning robot includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the cleaning path planning method according to any one of claims 1 to 8.

10. The cleaning robot according to claim 9, wherein: The top of the cleaning robot includes an image acquisition device.

Images