A method for a cleaning robot to build an environmental map

Abstract

The application provides a method for a cleaning robot to establish an environment map, which comprises: obtaining an environment map constructed by the cleaning robot; screening a mirror reflection area from a non-obstacle area according to whether the contour of the non-obstacle area conforms to a preset shape and whether the non-obstacle area is passable; and deleting the mirror reflection area on the environment map. In the application, the mirror reflection area can be identified while the environment map is established, and the mirror reflection area is deleted from the environment map when it is identified, which effectively avoids the interference of the mirror reflection area on the environment map, improves the mapping accuracy of the environment map, guarantees the credibility of the environment map, improves the accuracy of the cleaning robot in navigation and cleaning planning according to the environment map, and improves the cleaning efficiency of the cleaning robot.

Description

Technical Field

[0001] This application relates to the field of robotics, and in particular to a method for a cleaning robot to create an environmental map. Background Technology

[0002] As people's living standards improve, cleaning robots are being used more and more widely in people's daily lives. Currently, cleaning robots first create an environmental map corresponding to the target area. After the map is created, they clean the target area, navigating and planning the cleaning process based on the environmental map.

[0003] In existing technologies, cleaning robots primarily create environmental maps by performing laser scanning on target areas. Specifically, the cleaning robot is equipped with a laser emitter and a laser receiver. During map creation, the robot controls the laser emitter to emit laser signals to scan the target area. During the scanning process, the robot uses the laser receiver's reception of the laser signals to detect whether each location within the target area is passable and whether there are any obstacles. Upon successful detection, the results are displayed on the environmental map in real time.

[0004] However, as Figure 1 As shown, when the laser signal emitted by the laser emitter scans a translucent obstacle D (such as a mirror), the laser signal cannot be perpendicular to the obstacle D and will be reflected by the obstacle D. This reflection prevents the laser receiver from receiving the laser signal. When the laser receiver cannot receive the laser signal, the cleaning robot mistakenly assumes the area behind the translucent obstacle D is passable, thus incorrectly creating a mirrored reflection area on the environmental map. The existence of this mirrored reflection area reduces the accuracy of the environmental map, interferes with the cleaning robot's navigation and cleaning planning, and reduces the cleaning efficiency of the robot. Summary of the Invention

[0005] The purpose of this application is to provide a method for a cleaning robot to create an environmental map, which can identify areas of mirror reflection.

[0006] This application provides a method for a cleaning robot to create an environmental map, applicable to cleaning robots, including:

[0007] Obtain the environmental map constructed by the cleaning robot, the environmental map including obstacle-free areas, obstacle areas, and unexplored areas;

[0008] Based on whether the outline of the obstacle-free area conforms to a preset shape and whether the obstacle-free area is passable, a mirror reflection area is selected from the obstacle-free area, wherein the mirror reflection area is the area generated when the cleaning robot scans a light-transmitting obstacle;

[0009] The specular reflection area is deleted from the environment map.

[0010] In one embodiment, the step of selecting specular reflection areas from the barrier-free area based on whether the outline of the barrier-free area conforms to a preset shape and whether the barrier-free area is passable includes:

[0011] From the unobstructed area, candidate feature regions that are directly connected to the unexplored area are selected;

[0012] Determine whether the contour features of the candidate feature region conform to the contour features of a preset shape;

[0013] Determine whether the passability features of the candidate feature region meet the preset passability features;

[0014] If the contour features of the candidate feature region conform to the preset shape features, and the passability features of the candidate feature region conform to the preset passability features, then the candidate feature region is determined to be the specular reflection region.

[0015] In one embodiment, determining whether the contour features of the candidate feature region conform to the contour features of a preset shape includes:

[0016] Extract the boundary points between the candidate feature regions and the unexplored regions;

[0017] The intersection points are fitted to form feature lines; wherein, the feature lines include several sub-lines;

[0018] Based on the feature lines, determine whether the outline shape of the candidate feature region is a preset shape; wherein, the preset shape is radiating or fan-shaped.

[0019] If the contour shape of the candidate feature region is the preset shape, then the contour features of the candidate feature region are considered to conform to the contour features of the preset shape.

[0020] In one embodiment, before fitting the boundary points to form feature lines, the method for the cleaning robot to build an environmental map further includes:

[0021] Determine whether the number of points at the boundary is less than a preset threshold.

[0022] If the number of points at the boundary points is less than the preset point threshold, the candidate feature region is deleted.

[0023] If the number of points at the boundary is not less than the preset point threshold, the step of fitting the boundary points is performed.

[0024] In one embodiment, determining whether the contour shape of the candidate feature region is a preset shape based on the feature lines includes:

[0025] Determine the number and type of sub-lines contained in the feature line;

[0026] If the feature line includes two sub-lines of type straight line and one sub-line of type curve, then the outline shape of the candidate feature region is a fan-shaped shape;

[0027] If the number of sub-lines of type straight line included in the feature line is greater than a preset threshold, then the outline shape of the candidate feature region is scattering.

[0028] In one embodiment, determining whether the accessibility features of a candidate feature region meet preset accessibility features includes:

[0029] Determine whether the cleaning robot can travel from the target point to the candidate feature region; where the target point is the location where the cleaning robot can scan the candidate feature region;

[0030] If the cleaning robot cannot travel from the target point to the candidate feature area, it is considered that the drivability features of the candidate feature area meet the preset drivability features.

[0031] In one embodiment, determining whether a cleaning robot can travel from a target point to a candidate feature region includes:

[0032] Plan the travel path starting from the target point and control the cleaning robot to travel to the candidate feature area according to the travel path;

[0033] If the cleaning robot collides during its journey, an obstacle feature point is marked at the point of collision;

[0034] For each obstacle feature point marked, the robot replans its path around the marked obstacle feature point and continues to the candidate feature area. When it is unable to replan its path, it indicates that the cleaning robot cannot travel from the target point to the candidate feature area.

[0035] In one embodiment, the method for a cleaning robot to create an environmental map further includes:

[0036] The area containing the feature points of the obstacle is marked as a light-transmitting obstacle area;

[0037] Identify the region type of areas with light-transmitting obstacles;

[0038] Mark the area type of the light-transmitting obstacle area on the environment map.

[0039] In one embodiment, identifying the region type of the light-transmitting obstacle region includes:

[0040] Determine whether the cleaning robot can enter the candidate feature area from the target unobstructed area; where the target unobstructed area is the area where the target point is located;

[0041] If the cleaning robot cannot enter the candidate feature area from the target unobstructed area, the area type of the light-transmitting obstacle area is the light-transmitting glass area.

[0042] In one embodiment, the method for a cleaning robot to create an environmental map further includes:

[0043] If the cleaning robot can enter the candidate feature area from the target unobstructed area, determine whether the cleaning robot can scan the target unobstructed area within the candidate feature area;

[0044] If the cleaning robot can scan the target unobstructed area within the candidate feature area, then the area type of the light-transmitting obstacle area is the light-transmitting glass area.

[0045] If the cleaning robot cannot scan the target obstacle-free area within the candidate feature area, the area type of the light-transmitting obstacle area is a mirror area.

[0046] This application's solution can identify specular reflection areas while building an environmental map, and remove these areas from the map upon identification. This effectively avoids interference from specular reflection areas, improves the accuracy of the environmental map, and ensures its reliability. Furthermore, while maintaining the accuracy of the environmental map, it also improves the accuracy of the cleaning robot's navigation and cleaning planning based on the environmental map, thereby increasing the cleaning efficiency of the robot.

[0047] In addition, this application can identify mirror reflection areas based on map information and accessibility information without adding hardware, resulting in low identification costs. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly described below.

[0049] Figure 1 This is a schematic diagram of a laser emitter scanning onto a mirror surface according to an embodiment of this application;

[0050] Figure 2 This is a schematic diagram showing the connections of various components within a cleaning robot according to an embodiment of this application;

[0051] Figure 3 This is a schematic diagram showing the connections of various devices within a control unit according to an embodiment of this application;

[0052] Figure 4 A schematic diagram of the environmental map provided in the first embodiment of this application;

[0053] Figure 5 A schematic diagram of the environmental map provided in the second embodiment of this application;

[0054] Figure 6 A flowchart illustrating a method for creating an environmental map using a cleaning robot according to an embodiment of this application;

[0055] Figure 7 This is a flowchart illustrating a process for determining whether the contour features of a candidate feature region conform to a preset shape, according to an embodiment of this application.

[0056] Figure 8 A schematic diagram of a travel path provided in one embodiment of this application;

[0057] Figure 9 A schematic diagram of the environmental map provided in the third embodiment of this application;

[0058] Figure 10 A flowchart illustrating the process of identifying the region type of a light-transmitting obstacle area according to an embodiment of this application;

[0059] Figure 11 A schematic diagram of the environmental map provided in the fourth embodiment of this application;

[0060] Figure 12 A schematic diagram of the environmental map provided in the fifth embodiment of this application;

[0061] Figure 13 A schematic diagram of the environmental map provided in the sixth embodiment of this application;

[0062] Figure 14 This is a schematic diagram of the environmental map provided in the seventh embodiment of this application.

[0063] Icon labels:

[0064] 1-Control unit; 10-Bus; 11-Processor; 12-Memory; 2-Laser sensor; 21-Laser emitter; 22-Laser receiver; 100-Cleaning robot. Detailed Implementation

[0065] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0066] Similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0067] Please refer to Figure 2 This is a schematic diagram showing the connections of various components within a cleaning robot 100 according to an embodiment of this application. Please refer to... Figure 3 This is a schematic diagram showing the connections of various devices within the control unit 1 provided in an embodiment of this application. For example... Figure 2 As shown, the cleaning robot 100 includes a control unit 1 and a laser sensor 2, among other devices. The laser sensor 2 includes a laser emitter 21 and a laser receiver 22. The control unit 1 is connected to both the laser emitter 21 and the laser receiver 22. The laser emitter 21 emits laser signals under the control of the control unit 1, and the laser receiver 22 receives laser signals. The control unit 1 monitors the laser signal received by the laser receiver 22. The control unit 1 also executes the method for establishing an environmental map using the cleaning robot 100 provided in the following embodiments of this application. Figure 3 As shown, in this embodiment, the control unit 1 includes at least one processor 11 and a memory 12. Figure 2 Taking a processor 11 as an example. The processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11, and the instructions are executed by the processor 11.

[0068] In existing technology, before cleaning a target area, the cleaning robot 100 first establishes an environmental map corresponding to the target area. After successful establishment, it cleans the target area according to the environmental map. Specifically, the environmental map is established by the control unit 1 first controlling the laser emitter 21 to emit laser signals to scan the target area. During the scanning process, the control unit 1 monitors the laser receiver 22's reception of the laser signals in real time, and detects whether each sub-area within the target area is passable, and whether there are obstacles within the target area, based on the monitoring results; for example... Figure 4 As shown, if a sub-region within the target area is detected to be passable, this region is marked as obstacle-free region A on the map; the color of obstacle-free region A is white. If an obstacle is detected within the target area, the area containing the obstacle is marked as obstacle region B on the map; the color of obstacle region B is black. Additionally, as... Figure 4As shown, there are also gray areas on the environmental map. In the prior art, gray areas are called unexplored areas C. Unexplored areas C are areas in the target area that have not been scanned by laser. As the environmental map is gradually built, the above-mentioned unexplored areas C will be gradually scanned by laser and then gradually updated to obstacle-free areas A or obstacle areas B. When the entire target area is scanned, the environmental map is successfully built.

[0069] However, in reality, such as Figure 1 As shown, when the laser emitter 21 scans and detects a light-transmitting obstacle D within the target area, the obstacle D reflects the laser signal emitted by the laser emitter 21. This reflection causes the laser receiver 22 to be unable to receive the laser signal. When the laser receiver 22 cannot receive the laser signal, the control unit 1 mistakenly assumes that the laser signal is propagating in the direction shown by the dotted line in the figure, and therefore mistakenly believes that the area behind the light-transmitting obstacle D is a passable area. Figure 5 As shown, when the control unit 1 mistakenly believes that the area behind the light-transmitting obstacle D is a passable area, it will incorrectly mark an obstacle-free area A on the environmental map. However, the obstacle-free area A is actually a specular reflection area E formed by the cleaning robot 100 after scanning the light-transmitting obstacle. Although a specular reflection area E is generated on the environmental map, the cleaning robot 100 cannot actually pass through the specular reflection area E.

[0070] It can be seen that in the prior art, when the cleaning robot 100 is building an environmental map, if the laser scan detects light-transmitting obstacles such as mirrors, a mirror reflection area will be incorrectly generated on the environmental map. The existence of the mirror reflection area reduces the accuracy of the environmental map. To solve this problem, this application provides a method for the cleaning robot 100 to build an environmental map. The working principle of this method will be explained in detail below.

[0071] Please refer to Figure 6 This is a flowchart illustrating a method for a cleaning robot 100 to create an environmental map according to an embodiment of this application. The method includes steps S210-S230, and the specific principles of this method will be explained in detail below.

[0072] Step S210: Obtain the environmental map constructed by the cleaning robot 100. The environmental map includes obstacle-free areas, obstacle areas, and unexplored areas.

[0073] Among them, the obstacle-free area is the area without obstacles and not occupied by any obstacles (usually marked in white on the grid map), the obstacle area is the area where the obstacle is located (usually marked in black on the grid map), and the unexplored area is the area in the target area that has not been scanned by the laser (usually marked in gray on the grid map).

[0074] In this step, during the creation of the environmental map, control unit 1 acquires the environmental map in real time. After successful acquisition, control unit 1 can continue to execute the following step S220. Wherein, as Figure 4 and Figure 5 As shown, the environment map includes multiple obstacle-free areas, multiple obstacle areas, and at least one unexplored area.

[0075] Step S220: Based on whether the outline of the obstacle-free area conforms to a preset shape and whether the obstacle-free area is passable, a mirror reflection area is selected from the obstacle-free area. The mirror reflection area is the area generated when the cleaning robot 100 scans a light-transmitting obstacle.

[0076] Among them, light-transmitting obstacles can be mirrors and transparent glass, etc.

[0077] As can be seen from the above description of the prior art, the control unit 1 may incorrectly mark the specular reflection area as an unobstructed area. Therefore, in this step, the specular reflection area can be filtered out from the unobstructed area. Specifically, the control unit 1 can filter out the specular reflection area from the unobstructed area based on the contour features and accessibility features of the unobstructed area. After successful filtering, the control unit 1 can continue to execute the following step S230.

[0078] Step S230: Delete the specular reflection area on the environment map.

[0079] In this step, control unit 1 can remove the specular reflection area from the environment map.

[0080] During the process of establishing the environmental map, the control unit 1 continues to execute the above steps S210-S230 until the environmental map is established.

[0081] This application's solution can identify specular reflection areas while building an environmental map, and remove these areas from the map upon identification. This effectively avoids interference from specular reflection areas, improves the accuracy of the environmental map, and ensures its reliability. Furthermore, while ensuring the accuracy of the environmental map, it also improves the accuracy of the cleaning robot 100 in navigation and cleaning planning based on the environmental map, thereby increasing the cleaning efficiency of the cleaning robot 100.

[0082] In addition, this application can identify mirror reflection areas based on map information and accessibility information without adding hardware, resulting in low identification costs.

[0083] In one embodiment, such as Figure 5As shown, the specular reflection area is directly connected to the unexplored area and has no outline, with its edges not surrounded by obstacles. Therefore, when filtering specular reflection areas, the control unit 1 can first filter candidate feature areas directly connected to the unexplored area from the obstacle-free area. After successful filtering, it can then determine whether the candidate feature area is a specular reflection area based on its outline features and its accessibility features. Specifically, the control unit 1 determines whether the accessibility features of the candidate feature area conform to a preset accessibility feature and whether the outline features of the candidate feature area conform to a preset shape. If the determination results show that the outline features of the candidate feature area conform to the preset shape and the accessibility features of the candidate feature area conform to the preset accessibility feature, then the candidate feature area is determined to be a specular reflection area. The two determination processes are not sequential; it is possible to determine whether the outline features of the candidate feature area conform to the preset shape first, or whether the accessibility features of the candidate feature area conform to the preset accessibility feature first.

[0084] It is worth noting that if there are multiple candidate feature regions, namely candidate feature region A and candidate feature region B, then it can be determined whether candidate feature region A is a specular reflection region based on the contour features and accessibility features of candidate feature region A; at the same time, it can be determined whether candidate feature region B is a specular reflection region based on the contour features and accessibility features of candidate feature region B.

[0085] In one embodiment, the control unit 1 can be via Figure 7 Steps S310-S330 show the determination of whether the contour features of the candidate feature region conform to the preset contour features.

[0086] Step S310: Extract the boundary points between candidate feature regions and unexplored regions.

[0087] Among them, there is an intersection between the candidate feature region and the unexplored region, and the boundary point is located within the aforementioned intersection region.

[0088] In this step, control unit 1 can extract the boundary points between candidate feature regions and unexplored regions. After successful boundary point extraction, control unit 1 can continue to execute the following step S320.

[0089] Step S320: Fit the intersection points to form feature lines.

[0090] The feature lines include several sub-lines.

[0091] In this step, control unit 1 can perform linear fitting on multiple intersection points, forming feature lines after linear fitting. After the feature lines are formed, control unit 1 can continue to execute the following step S330.

[0092] Step S330: Based on the feature lines, determine whether the outline of the candidate feature region is a preset shape, and determine whether the outline features of the candidate feature region conform to the preset outline features based on the judgment result.

[0093] The preset shape is either scattering or fan-shaped.

[0094] like Figure 5 As shown, the outline of the specular reflection area is generally scattering or fan-shaped. Therefore, in this step, the control unit 1 can determine whether the outline of the candidate feature area is scattering or fan-shaped based on the feature lines. If the determination result shows that the outline of the candidate feature area is scattering or fan-shaped, it can be determined that the outline feature of the candidate feature area conforms to the preset outline feature. If the determination result shows that the outline feature of the candidate feature area is not scattering or fan-shaped, it can be determined that the outline feature of the candidate feature area does not conform to the preset outline feature.

[0095] In one embodiment, the control unit 1 can determine whether the outline of the candidate feature region is scattering or fan-shaped based on the number and type of sub-lines contained in the feature line.

[0096] Specifically, if the feature line includes two sub-lines of type straight lines and one sub-line of type curve, then the outline shape of the candidate feature region can be determined to be fan-shaped. In other words, when the feature line includes two straight lines and one curve, the outline shape of the candidate feature region is fan-shaped.

[0097] If the number of sub-lines of type straight line included in the feature line is greater than the preset threshold N. line Then, the contour shape of the candidate feature region can be determined to be scattering. That is, when the feature line includes multiple straight lines, and the number of these straight lines is greater than a preset threshold N... line At that time, the contour shape of the candidate feature region is scattering.

[0098] In another embodiment, if the feature line includes multiple sub-lines of type straight line, and among the multiple sub-lines of type straight line, there is a predetermined number of sub-lines with a length greater than a predetermined length L. line If the sub-lines are defined, then the contour shape of the candidate feature region can be determined to be scattering. That is, when the feature line includes multiple straight lines, and a predetermined number of these straight lines have a length greater than a predetermined length L... line The straight lines. Where the aforementioned preset number of lines is greater than the aforementioned preset threshold N. line Preset threshold N line Greater than 2; the above-mentioned preset length L line The effective mapping distance L is less than that of laser sensor 2.

[0099] In one embodiment, after executing the above step S310 and extracting the boundary points between the candidate feature region and the unexplored region, the control unit 1 can determine whether the number of boundary points is less than a preset point threshold X. If the determination result shows that the number of boundary points is less than the preset point threshold X, the candidate feature region is deleted. If the determination result shows that the number of boundary points is greater than or equal to the preset point threshold X, then step S320 is continued.

[0100] Specifically, the preset point threshold X can be determined by the following formula (1):

[0101]

[0102] Where L is the effective mapping distance of laser sensor 2, and R is the resolution of the environmental map.

[0103] Preferably, when the effective mapping distance L of the laser sensor 2 is 4m and the resolution R of the environmental map is 0.05m, the preset point threshold X can be 160, and the preset threshold N can be... line It can be 1m, with a preset length L. line It can be 4m.

[0104] In practice, when the laser emitter 21 detects other interfering factors within the target area, candidate feature regions will also be formed on the environmental map. In this embodiment, the candidate feature regions are further filtered based on the number of boundary points, eliminating candidate feature regions formed by interfering factors, thereby further improving the accuracy of identifying specular reflection areas.

[0105] In one embodiment, the control unit 1 can determine whether the passability features of the candidate feature region meet the preset passability features through the following step S410.

[0106] Step S410: Determine whether the cleaning robot 100 can travel from the target point to the candidate feature region.

[0107] The target point is the location of the candidate feature region that the cleaning robot 100 can scan.

[0108] like Figure 5 As shown, the specular reflection area is an area that can be seen from a certain position but cannot be directly entered by the cleaning robot 100. Therefore, in this step, the control unit 1 first finds a target point in the environmental map; when the cleaning robot 100 is located at the target point, the laser emitter 21 can scan the candidate feature area; the fact that the laser emitter 21 can scan the candidate feature area indicates that the cleaning robot 100 can see the candidate feature area.

[0109] After the target point is successfully found, the control unit 1 determines whether the cleaning robot 100 can travel from the target point to the candidate feature area. If the determination result shows that the cleaning robot 100 cannot travel from the target point to the candidate feature area, then the passability characteristics of the candidate feature area are determined to meet the preset passability characteristics; if the determination result shows that the cleaning robot 100 can travel from the target point to the candidate feature area, then the passability characteristics of the candidate feature area are determined to not meet the preset passability characteristics.

[0110] In one embodiment, the control unit 1 can determine whether the cleaning robot 100 can travel from the target point to the candidate feature region in the following manner:

[0111] First, control unit 1 plans a path from the target point to the candidate feature area. This path is a ray that does not pass through obstacles. After successful planning, control unit 1 controls the cleaning robot 100 to travel along the path to the candidate feature area. If control unit 1 detects a collision while the cleaning robot 100 is traveling along the path, it indicates that the cleaning robot 100 is blocked by a light-transmitting obstacle and cannot enter the candidate feature area. In this case, control unit 1 can mark an obstacle feature point at the collision location. After successful marking, control unit 1 can bypass the marked obstacle feature point and replan a path to the candidate feature area. After successful planning, control unit 1 controls the cleaning robot 100 to continue traveling along the replanned path to the candidate feature area. If control unit 1 detects a collision during travel, it marks an obstacle feature point at the collision location. This process is repeated continuously. Each time an obstacle feature point is marked, a new path is planned to bypass the marked obstacle feature point. After successful planning, control unit 1 controls the cleaning robot 100 to travel along the new path. When the cleaning robot 100 is unable to plan a travel path, it indicates that the cleaning robot 100 cannot travel from the target point to the candidate feature area. When the cleaning robot 100 travels to the candidate feature area according to the planned travel path, it indicates that the cleaning robot 100 can travel from the target point to the candidate feature area.

[0112] For example, such as Figure 8As shown, control unit 1 first plans a path to candidate feature region G, starting from target point a. This path is a ray that does not pass through obstacles. After successful planning, control unit 1 controls cleaning robot 100 to travel to candidate feature region G along the aforementioned path. If control unit 1 detects a collision while cleaning robot 100 is traveling along the aforementioned path, it marks an obstacle feature point b1 at the collision location. After successful marking, control unit 1 can bypass the marked obstacle feature point b1 and replan a path to candidate feature region G. After successful planning, control unit 1 controls cleaning robot 100 to continue traveling to candidate feature region G along the replanned path. If control unit 1 detects a collision during travel, it marks an obstacle feature point b2 at the collision location. This process is repeated continuously; for each marked obstacle feature point, a new path is planned, bypassing the marked obstacle feature point. After successful planning, control unit 1 controls cleaning robot 100 to travel along the new path. When the cleaning robot 100 is unable to plan a travel path, it indicates that the cleaning robot 100 cannot travel from the target point to the candidate feature region G. When the cleaning robot 100 travels to the candidate feature region G according to the planned travel path, it indicates that the cleaning robot 100 can travel from the target point to the candidate feature region G.

[0113] As can be seen from the above, in this application, based on the outline shape of the candidate feature region and whether the cleaning robot 100 can enter the candidate feature region from a position where the candidate feature region can be seen, the candidate feature region is identified as a specular reflection region. The identification method is closely combined with the characteristics of the specular reflection region itself, resulting in high identification accuracy and a simple identification method.

[0114] It is worth noting that, such as Figure 9As shown, region M is connected to region K through a light-transmitting barrier D. The length and width of region K exceed the effective mapping distance of laser sensor 2. When the cleaning robot 100 enters region A to establish an environmental map, it cannot establish a complete environmental map of region K through the light-transmitting barrier D; instead, it only establishes a partial map of region K on the environmental map, forming region L. At this time, according to the method in this application, region L will be misjudged as a specular reflection region. In fact, region L is a partial environmental map of region K. However, the cleaning robot 100 itself cannot enter region L or region K. Therefore, misjudging region L as a specular reflection region and deleting it from the environmental map according to the method in this application will not reduce the cleaning effect. Furthermore, when there are other exits that allow the cleaning robot 100 to enter region L or region K, this application can also delete region L after misjudging it as a specular reflection region. Since the cleaning robot 100 will subsequently enter region L to establish an environmental map, deleting region L will not affect the establishment of the environmental map.

[0115] In one embodiment, such as Figure 8 As shown, obstacle feature point b1 is a feature point marked on the environmental map by the control unit 1 after the cleaning robot 100 is blocked by a light-transmitting obstacle; in this case, the area where the obstacle feature point is located can be considered the area where the light-transmitting obstacle is located. Therefore, in this embodiment, the area where the above-mentioned obstacle feature point is located is marked as the light-transmitting obstacle area. After successful marking, the control unit 1 can identify the area type of the light-transmitting obstacle area; after successful identification, the area type of the light-transmitting obstacle is marked on the environmental map. For example, as... Figure 8 As shown, obstacle feature points b1, b2...b can be identified. n The area is marked as a light-transmitting obstacle area.

[0116] The region type of the light-transmitting obstacle region is determined by the type of light-transmitting obstacle contained within it. If the light-transmitting obstacle region contains a mirror, then the region type of the light-transmitting obstacle region is a mirror region; if the light-transmitting obstacle region contains light-transmitting glass, then the region type of the light-transmitting obstacle region is a light-transmitting glass region.

[0117] Specifically, control unit 1 can be accessed via Figure 10 Steps S510-S520, as shown, identify the region type of the light-transmitting obstacle area:

[0118] Step S510: Determine whether the cleaning robot 100 can enter the candidate feature area from the target obstacle-free area.

[0119] The target unobstructed area is the area where the target point is located; as can be seen from the above description, the target unobstructed area and the candidate feature area are connected by light-transmitting obstacles.

[0120] In this step, the control unit 1 first determines whether the cleaning robot 100 can enter the candidate feature area from the target unobstructed area. If the determination result shows that the cleaning robot 100 cannot enter the candidate feature area from the target unobstructed area, the area type of the light-transmitting obstacle area can be directly determined to be a light-transmitting glass area. If the candidate feature area overlaps with a map area on the environmental map, and there is a connecting exit between the map area and the target unobstructed area, the cleaning robot 100 can enter the candidate feature area from the target unobstructed area.

[0121] For example, such as Figure 8 As shown, the control unit 1 can determine whether the cleaning robot 100 can enter the candidate feature area G from the target unobstructed area F; if the determination result shows that the cleaning robot 100 cannot enter the candidate feature area G from the target unobstructed area F, the area type of the light-transmitting obstacle area D can be directly determined to be a light-transmitting glass area.

[0122] Step S520: If the cleaning robot 100 can enter the candidate feature area from the target obstacle-free area, determine whether the cleaning robot 100 can scan the target obstacle-free area in the candidate feature area.

[0123] In this step, if the cleaning robot 100 can enter the candidate feature area from the target unobstructed area, the control unit 1 can further determine whether the laser emitter 21 can scan the target unobstructed area when the cleaning robot 100 enters the candidate feature area. If the determination result shows that the laser emitter 21 can scan the target unobstructed area when the cleaning robot 100 enters the candidate feature area, the area type of the light-transmitting obstacle area can be determined to be a light-transmitting glass area; if the determination result shows that the laser emitter 21 cannot scan the target unobstructed area when the cleaning robot 100 enters the candidate feature area, the area type of the light-transmitting obstacle area can be determined to be a mirror area.

[0124] The specific reasons are as follows:

[0125] (1) When the cleaning robot 100 is located at the target point, the laser emitter 21 can scan the candidate feature area, indicating that the cleaning robot 100 can see the candidate feature area in the target unobstructed area; when the cleaning robot 100 enters the candidate feature area, the laser emitter 21 can scan the target unobstructed area, indicating that the cleaning robot 100 can see the target unobstructed area in the candidate feature area; in this case, the light-transmitting obstacle contained in the light-transmitting obstacle area can only be light-transmitting glass with double-sided light transmission, because only when the light-transmitting obstacle is light-transmitting glass can the cleaning robot 100 see the candidate feature area in the target unobstructed area and see the target unobstructed area in the candidate feature area.

[0126] (2) When the cleaning robot 100 is located at the target point, the laser emitter 21 can scan the candidate feature area, indicating that the cleaning robot 100 can see the candidate feature area within the target obstacle-free area; when the cleaning robot 100 enters the candidate feature area, the laser emitter 21 cannot scan the target obstacle-free area, indicating that the cleaning robot 100 cannot see the target obstacle-free area within the candidate feature area. In this case, the translucent obstacle included in the translucent obstacle area can only be a mirror with one-sided light transmission, because only when the translucent obstacle is a mirror can the cleaning robot 100 see the candidate feature area within the target obstacle-free area, and at the same time cannot see the target obstacle-free area within the candidate feature area.

[0127] For example, such as Figure 11 As shown, H and I are two adjacent regions, with region H containing a light-transmitting obstacle region D. When the control unit 1 identifies the region type of the light-transmitting obstacle region D:

[0128] (1) If the cleaning robot 100 enters region H first when building an environmental map, and the control unit 1 detects a candidate feature region in region H, the candidate feature region overlaps with region I. After detecting the candidate feature region, the control unit 1 will further determine whether the candidate feature region is a specular reflection region. The determination method is to determine whether the outline shape of the candidate feature region is a preset shape, and whether the cleaning robot 100 can enter the candidate feature region from a target point in region H. When determining whether the cleaning robot 100 can enter the candidate feature region from a target point in region H, the control unit 1 will mark the light-transmitting obstacle region D on the environmental map. When the marking is successful and the cleaning robot 100 enters region I to build an environmental map, the control unit 1 can determine whether the cleaning robot 100 can see region H in region I. If the determination result shows that the cleaning robot 100 can see region H in region I, then the region type of the light-transmitting obstacle region D is a light-transmitting glass region; if the determination result shows that the cleaning robot 100 cannot see region H in region I, then the region type of the light-transmitting obstacle is a mirror region.

[0129] (2) If the cleaning robot 100 enters area I and then area H when building the environmental map; the cleaning robot 100 does not detect the candidate feature area while in area I, and also does not see area H while in area I; upon entering area H, the cleaning robot 100 detects the candidate feature area, which overlaps with area I. After detecting the candidate feature area, the control unit 1 will further determine whether the candidate feature area is a specular reflection area. The determination method is to determine whether the outline shape of the candidate feature area is a preset shape, and whether the cleaning robot 100 can enter the candidate feature area from a target point in area H. When determining whether the cleaning robot 100 can enter the candidate feature area from a target point in area H, the control unit 1 will mark the light-transmitting obstacle area D on the environmental map. Since the cleaning robot 100 does not see area H when entering area I, and the cleaning robot 100 can also enter area H from area I, in this case, after the cleaning robot 100 marks the light-transmitting obstacle area D, it can be directly determined that the area type of the light-transmitting obstacle area D is a specular area.

[0130] It is worth noting that if the cleaning robot 100 does not mark the light-transmitting obstacle area D in this embodiment, it means that a feasible exit has been added near the light-transmitting obstacle area D, and the cleaning robot 100 can enter the I area from the H area through the aforementioned feasible exit.

[0131] In one embodiment, the control unit 1 can determine whether the cleaning robot 100 can see the I region within the H region, and whether the cleaning robot 100 can see the H region within the I region, in the following manner:

[0132] like Figure 12 As shown, when the cleaning robot 100 establishes an environmental map, it first moves to point c within area I. After successful movement, point c is marked as a reference point. Following successful marking, the laser emitter 21 is controlled at point c to perform a laser scan. During the scan, the control unit 1 updates the obstacle-free area and obstacle area on the environmental map based on the laser signal received by the laser receiver 22. Simultaneously, the laser marker information of point c is added to the newly updated obstacle-free area. For example... Figure 13 As shown, when the cleaning robot 100 moves to point b within area J, it marks point b as a reference point. After successful marking, the control unit 1 updates the obstacle-free area and obstacle area on the environmental map. Simultaneously, it adds the laser marker information of point b to the newly updated obstacle-free area. Figure 14 As shown, when the cleaning robot 100 moves to point a within area H, it marks point a as a reference point. After successful marking, the control unit 1 updates the obstacle-free area and obstacle area on the environmental map, and simultaneously adds the laser marking information of point a to the newly updated obstacle-free area. Figure 14 As shown, there are unobstructed areas marked with laser markers (c) around point b on the environmental map, and there are also unobstructed areas marked with laser markers (c) around point c. This indicates that cleaning robot 100 can see point c from point b, and cleaning robot 100 can see point b from point c. Furthermore, this shows that cleaning robot 100 can see and scan area I when it is in area J, and cleaning robot 100 can see and scan area J when it is in area I. Figure 14 As shown, there is an unobstructed area marked with laser marker a around point b on the environmental map, indicating that the cleaning robot 100 can see point c from point b. Furthermore, this shows that the cleaning robot 100 can see and scan area I from area H. Figure 14 As shown, there is no obstacle-free area marked with laser information b around point c on the environmental map, indicating that the cleaning robot 100 cannot see point a from point c. Furthermore, it indicates that the cleaning robot 100 cannot see or scan area H from area I.

[0133] It is worth noting that when actually creating an environmental map, there may be multiple reference points within regions I, H, and J. When selecting a target point from region H, it can be chosen from among the reference points within region H. For example, since cleaning robot 100 can see point c in region I from point a, it means that cleaning robot 100 can see region I from point a, so point a can be used as the target point.

[0134] As can be seen from the above, this application can identify the region type of the light-transmitting obstacle area. After successful identification, the region type of the light-transmitting obstacle area will be marked on the environmental map, which increases the semantic information of the environmental map and improves the intelligence of the environmental map.

[0135] Those skilled in the art will understand that if a cleaning robot, when mapping a scene with transparent glass or mirrors or other light-transmitting obstacles, fails to display mirror reflection areas at the light-transmitting obstacles, and if the map at the light-transmitting obstacles is consistent with the actual map, and the cleaning robot engages in continuous collision probing actions against the light-transmitting obstacles during the map-building process, then the cleaning robot can be considered to have applied the solution disclosed in this application and is infringing.

[0136] The apparatuses and methods disclosed in the several embodiments provided in this application can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0137] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0138] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. The aforementioned memory 12 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

Claims

1. A method for a cleaning robot to create an environmental map, applied to a cleaning robot, the method comprising: The method involves obtaining an environmental map constructed by the cleaning robot, the environmental map including obstacle-free areas, obstacle areas, and unexplored areas; characterized in that the method further includes: filtering out specular reflection areas from the obstacle-free areas based on whether the outline of the obstacle-free areas conforms to a preset shape and whether the obstacle-free areas are passable, wherein the specular reflection areas are areas generated when the cleaning robot scans for translucent obstacles; and deleting the specular reflection areas from the environmental map. The step of selecting specular reflection areas from the unobstructed area based on whether the outline of the unobstructed area conforms to a preset shape and whether the unobstructed area is passable includes: selecting candidate feature areas directly connected to the unexplored area from the unobstructed area; determining whether the outline features of the candidate feature areas conform to the outline features of a preset shape; determining whether the passability features of the candidate feature areas conform to preset passability features; if the outline features of the candidate feature areas conform to the preset shape features and the passability features of the candidate feature areas conform to the preset passability features, then the candidate feature areas are determined to be the specular reflection areas; the preset shape is scattering or fan-shaped. Determining whether the traversability characteristics of the candidate feature region meet the preset traversability characteristics includes: determining whether the cleaning robot can travel from the target point to the candidate feature region; wherein, the target point is the location where the cleaning robot can scan the candidate feature region; if the cleaning robot cannot travel from the target point to the candidate feature region, then the traversability characteristics of the candidate feature region are considered to meet the preset traversability characteristics.

2. The method for establishing an environmental map using a cleaning robot according to claim 1, characterized in that, The step of determining whether the contour features of the candidate feature region conform to the contour features of a preset shape includes: extracting the boundary points between the candidate feature region and the unexplored region; fitting the boundary points to form feature lines; wherein the feature lines include several sub-lines; determining whether the contour shape of the candidate feature region is a preset shape based on the feature lines; if the contour shape of the candidate feature region is the preset shape, then the contour features of the candidate feature region are considered to conform to the contour features of the preset shape.

3. The method for establishing an environmental map using a cleaning robot according to claim 2, characterized in that, Before fitting the boundary points to form feature lines, the method for the cleaning robot to build an environmental map further includes: determining whether the number of points at the boundary points is less than a preset point threshold; if the number of points at the boundary points is less than the preset point threshold, deleting the candidate feature region; if the number of points at the boundary points is not less than the preset point threshold, performing the step of fitting the boundary points.

4. The method for establishing an environmental map using a cleaning robot according to claim 2, characterized in that, The step of determining whether the outline shape of the candidate feature region is a preset shape based on the feature lines includes: determining the number and type of sub-lines contained in the feature lines; if the feature lines include two sub-lines of type straight lines and one sub-line of type curve, then the outline shape of the candidate feature region is fan-shaped; if the number of sub-lines of type straight lines contained in the feature lines is greater than a preset threshold, then the outline shape of the candidate feature region is scattering.

5. The method for establishing an environmental map using a cleaning robot according to claim 1, characterized in that, The step of determining whether the cleaning robot can travel from the target point to the candidate feature area includes: planning a travel path starting from the target point, controlling the cleaning robot to travel to the candidate feature area according to the travel path; if the cleaning robot collides during the process, marking an obstacle feature point at the collision point; after marking each obstacle feature point, replanning the travel path around the marked obstacle feature point and continuing to the candidate feature area; when it is impossible to replan the travel path, it indicates that the cleaning robot cannot travel from the target point to the candidate feature area.

6. The method for establishing an environmental map using a cleaning robot according to claim 5, characterized in that, The method for the cleaning robot to establish an environmental map further includes: marking the area where the obstacle feature points are located as a light-transmitting obstacle area; identifying the area type of the light-transmitting obstacle area; and marking the area type of the light-transmitting obstacle area on the environmental map.

7. The method for establishing an environmental map using a cleaning robot according to claim 6, characterized in that, The identification of the region type of the light-transmitting obstacle area includes: determining whether the cleaning robot can enter the candidate feature area from the target obstacle-free area; wherein, the target obstacle-free area is the area where the target point is located; if the cleaning robot cannot enter the candidate feature area from the target obstacle-free area, then the region type of the light-transmitting obstacle area is a light-transmitting glass area.

8. The method for establishing an environmental map using a cleaning robot according to claim 7, characterized in that, The method for establishing an environmental map by the cleaning robot further includes: if the cleaning robot can enter the candidate feature area from the target obstacle-free area, determining whether the cleaning robot can scan the target obstacle-free area within the candidate feature area; if the cleaning robot can scan the target obstacle-free area within the candidate feature area, then the area type of the light-transmitting obstacle area is a light-transmitting glass area; if the cleaning robot cannot scan the target obstacle-free area within the candidate feature area, then the area type of the light-transmitting obstacle area is a mirror area.

Images