Method for controlling robot cleaning and robot

Abstract

The present invention provides a method for controlling robot cleaning, comprising: generating an edge path based on a known map, the edge path including edge path points, the edge path points having boundary attributes; receiving an edge cleaning task, navigating to a cleaning area according to the known map; obtaining the boundary attributes of the edge path points of the cleaning area; and executing a corresponding cleaning strategy according to the boundary attributes of the edge path points. The technical solution of the present invention enables the robot to execute a corresponding cleaning strategy based on the boundary attributes of the edge path points, and can effectively complete the edge cleaning function without collision. It can achieve detailed cleaning of solid walls with excellent cleaning effects. In addition, the edge cleaning function has excellent adaptability to environmental changes, and can complete high-quality edge cleaning in different environments, greatly improving the robot's edge performance and benefiting the robot's robustness and customer experience.

Description

Technical Field

[0001] The present invention generally relates to the field of robotics technology, and more particularly to a method for controlling robot cleaning, a robot, and a computer-readable storage medium. Background Art

[0002] In recent years, with the development of artificial intelligence technology, cleaning robots have been widely used in various fields, reducing the labor burden for humans. Most existing cleaning robots use infrared sensors or contact sensors. When a wall is detected, they perform exploratory edge cleaning. This collision-resistant method is well-suited for household cleaning robots, but it has not been widely adopted in large commercial robots. At the same time, this method does not pre-plan an effective edge path based on a global map. Once the working environment changes, the robot's edge function is easily affected. For example, it may collide with obstacles, creating danger, or even stray outside the cleaning area and be unable to return. At the same time, repeated cleaning may occur, reducing the robot's work efficiency and affecting the normal operation of the robot.

[0003] The contents of the background technology section are merely the technologies known to the inventors and do not necessarily represent the existing technologies in this field. Summary of the Invention

[0004] In view of one or more problems existing in the prior art, the present invention provides a method for controlling a cleaning robot, comprising:

[0005] Generate an edge path based on a known map, wherein the edge path includes edge path points, and the edge path points have boundary attributes;

[0006] Receiving a border cleaning task and navigating to the cleaning area according to the known map;

[0007] Obtaining boundary attributes of path points along the edge of the cleaning area; and

[0008] Execute corresponding cleaning strategies according to the boundary attributes of the edge path points.

[0009] According to one aspect of the present invention, the step of generating an edge path based on a known map includes: performing image region segmentation on the known map, extracting boundary information of the segmented area contour, processing the boundary information, and generating edge path points with boundary attributes.

[0010] According to one aspect of the present invention, the step of processing the boundary information to generate edge path points with boundary attributes includes: processing the boundary information based on the map attributes of the known map to generate initial edge path points, matching the initial edge path points with the known map to generate edge path points with boundary attributes, and then generating an edge path.

[0011] According to one aspect of the present invention, the boundary attributes of the edge path points include physical wall boundaries and virtual area boundaries; the cleaning strategies include path tracking cleaning strategies and wall-adhering cleaning strategies.

[0012] According to one aspect of the present invention, the step of executing a corresponding cleaning strategy according to the boundary attributes of the edge path points includes:

[0013] Determine whether the boundary attribute of the path point along the edge of the cleaning area is a solid wall boundary;

[0014] If the boundary attribute of the path points along the edge of the cleaning area is not a solid wall boundary, the path tracking cleaning strategy is executed.

[0015] According to one aspect of the present invention, the step of executing a corresponding cleaning strategy based on the boundary attributes of the edge path points also includes: if the boundary attribute of the edge path points of the cleaning area is a solid wall boundary, determining whether the robot detects a solid wall, and executing a corresponding cleaning strategy based on the detection result.

[0016] According to one aspect of the present invention, if the step of executing the corresponding cleaning strategy according to the boundary attributes of the path points along the edge also includes: if it is determined that the robot detects a solid wall, executing the wall cleaning strategy; otherwise, executing the path tracking cleaning strategy.

[0017] According to one aspect of the present invention, the step of executing the wall cleaning strategy includes: controlling the robot to maintain cleaning within a preset distance range from the physical wall according to the shape change of the physical wall.

[0018] According to one aspect of the present invention, the further method includes: detecting whether there is an obstacle, and if there is an obstacle, controlling the robot to perform an obstacle avoidance operation.

[0019] According to one aspect of the present invention, the step of controlling the robot to perform an obstacle avoidance operation includes: when the robot executes a path tracking cleaning strategy, the robot performs a local planning obstacle avoidance operation.

[0020] According to one aspect of the present invention, the step of controlling the robot to perform obstacle avoidance operations also includes: when the robot executes a wall-sticking cleaning strategy, controlling the robot to perform a wall-sticking obstacle avoidance operation, and determining whether it deviates from the preset distance range during the wall-sticking obstacle avoidance process; if deviated, controlling the robot to perform a local planned obstacle avoidance operation.

[0021] According to one aspect of the present invention, it also includes: during the entire edge cleaning process, if it is detected that the robot deviates from the cleaning area, the robot is controlled to execute a path tracking cleaning strategy and navigate to the cleaning area according to the known map.

[0022] The present invention also provides a robot, comprising:

[0023] The main body has a walking mechanism;

[0024] a sensor mounted on the main body and configured to detect the surrounding environment of the robot;

[0025] Cleaning brush for sweeping;

[0026] The processor is coupled to the walking mechanism and the sensor, and is configured to execute the method described above.

[0027] According to one aspect of the present invention, the sensor includes one or more of a laser radar, an odometer, and a visual sensor.

[0028] The present invention also provides a computer-readable storage medium, comprising computer-executable instructions and a map stored thereon, wherein the executable instructions implement the method described above when executed by a processor.

[0029] By adopting the technical solution of the present invention, the robot can execute the corresponding cleaning strategy based on the boundary attributes of the edge path points, and can better complete the edge cleaning function without collision. It can achieve detailed cleaning of solid walls with good cleaning effect. In addition, the edge cleaning function has very good adaptability to environmental changes, and can complete high-quality edge cleaning in different environments, which greatly improves the robot's edge performance and is conducive to improving the robot's robustness and customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0031] Figure 1 A flow chart of a method for controlling a robot to clean is shown according to an embodiment of the present invention;

[0032] Figure 2A schematic diagram of a process for generating an edge path based on a known map according to a preferred embodiment of the present invention is shown;

[0033] Figure 3 A schematic diagram showing a path point according to a preferred embodiment of the present invention;

[0034] Figure 4 A flowchart showing a robot performing an edge cleaning task according to an embodiment of the present invention is shown; and

[0035] Figure 5 A schematic diagram of a robot according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0036] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0037] In the description of the present invention, it should be understood that the terms "center," "longitudinal," "transverse," "length," "width," "thickness," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," "clockwise," "counterclockwise," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended solely for the purpose of facilitating the description of the present invention and simplifying the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features referred to. Thus, features designated "first" or "second" may explicitly or implicitly include one or more of the designated features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0038] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, removable, or integral connections; mechanical, electrical, or intercommunication connections; direct or indirect connections through an intermediary; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0039] In the present invention, unless otherwise expressly specified or limited, a first feature being "above" or "below" a second feature may include the first and second features being in direct contact, or may also include the first and second features not being in direct contact but being in contact via another feature between them. Furthermore, a first feature being "above," "above," and "above" a second feature may include the first feature being directly above or diagonally above the second feature, or may simply mean that the first feature is at a higher level than the second feature. A first feature being "below," "below," and "below" a second feature may include the first feature being directly above or diagonally above the second feature, or may simply mean that the first feature is at a lower level than the second feature.

[0040] The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numbers and / or reference letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides examples of various specific processes and materials, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0041] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0042] The present invention provides a method for controlling robot cleaning, so that the robot can achieve effective collision-free edge cleaning. The method 10 is described in detail below with reference to the accompanying drawings.

[0043] Figure 1 FIG. 1 is a flow chart of a method 10 for controlling robot cleaning according to an embodiment of the present invention. Figure 4 FIG. 4 shows a flow chart of a robot performing a side cleaning task according to an embodiment of the present invention. Figure 1 As shown, the method 10 includes steps S11-S14: in step S11, an edge path is generated based on a known map, wherein the edge path includes edge path points, and the edge path points have boundary attributes; in step S12, an edge cleaning task is received and navigation is performed to the cleaning area based on the known map; in step S13, the boundary attributes of the edge path points in the cleaning area are obtained; and in step S14, a corresponding cleaning strategy is executed based on the boundary attributes of the edge path points. The following describes each step of the method 10 in detail.

[0044] In step S11, an edge path is generated based on a known map, wherein the edge path includes edge path points, and the edge path points have boundary attributes.

[0045] According to a preferred embodiment of the present invention, the known map may be a map formed by the robot mapping its working environment. The following briefly describes the mapping process of the known map.

[0046] According to a preferred embodiment of the present invention, the robot is equipped with an acquisition sensor and a modeling processor. The acquisition sensor includes but is not limited to a laser radar, an infrared sensor, a binocular vision sensor, and an ultrasonic sensor, etc. The acquisition sensor is configured to collect data of the working environment of the robot, and the modeling processor is configured to create a map based on the data collected by the acquisition sensor. In the process of creating a map, the robot can generate different map layers through different modeling processors, such as a static layer, a dynamic obstacle layer, an ultrasonic layer, a visual layer, etc., and these layers can be integrated to generate a positioning map, that is, the known map. The robot can use the known map to perform positioning, navigation, and path planning (such as an edge path). How to generate an edge path based on a known map is described in detail below.

[0047] Figure 2 FIG. 1 shows a schematic diagram of a process for generating an edge path based on a known map according to a preferred embodiment of the present invention. Figure 3 A schematic diagram of a path point according to a preferred embodiment of the present invention is shown in FIG. Figure 2 As shown, step S11 includes sub-steps S111-S114, which are described in detail below.

[0048] In sub-step S111, the image region of the known map is segmented to obtain several sub-regions. For example, the image region can be segmented based on map elements such as walls, doors, partitions, etc. to obtain different rooms or different regions. In addition, the sub-regions can also be segmented based on non-physical map elements. For example, the user can divide a large space into different sub-regions according to function. It should be understood that the main purpose of performing image region segmentation on a known map is to divide the region so that the robot can perform zoned cleaning with greater targeting and higher efficiency. The present invention does not limit how to perform image region segmentation on a known map. Optionally, for example, each room can be divided into a sub-region.

[0049] In sub-step S112, the contour boundary information of the plurality of sub-regions is extracted and processed based on the map attributes of the known map to generate initial path points along the edges. After being divided into multiple sub-regions, the boundary information of each sub-region can be obtained based on the map data, and multiple boundary points can be obtained on its boundaries. Adjacent boundary points can be spaced apart by a preset distance, for example, to serve as path points along the edges. Alternatively, the boundary points can be offset by a certain distance (e.g., 10 cm or 20 cm) toward the interior of the sub-region, and the offset points can be used as path points along the edges.

[0050] In sub-step S113, the edge path points are matched with the known map to generate edge path points with boundary attributes. The boundary attributes of the edge path points include, for example, physical wall boundaries and virtual area boundaries. The boundary point attributes can be obtained from the map data.

[0051] In sub-step S114, the edge path points with boundary attributes are connected and optimized to generate a final edge path. The optimization process may include, for example, encrypting the path points. When the interval between adjacent edge path points exceeds a threshold, additional edge path points may be added to improve control accuracy.

[0052] It should be noted that the physical wall is a wall that physically exists in the real life environment (refer to Figure 3 The virtual area is an area manually defined to limit the robot's activities, such as doors, prohibited areas, elevator entrances, or areas that do not need to be cleaned (see Figure 3 According to one embodiment of the present invention, the path point located at the boundary of the physical wall (refer to Figure 3 The solid circle in the figure has the property of a solid wall boundary and is located at the path point at the boundary of the virtual area (refer to Figure 3 The hollow circle in ) has a virtual area boundary attribute, which can be recorded in the map data.

[0053] The above embodiment describes how to generate an edge path based on a known map. The following describes how the robot can perform edge cleaning based on the edge path.

[0054] In step S12, a side cleaning task is received, and navigation is performed to the cleaning area according to the known map.

[0055] According to a preferred embodiment of the present invention, the cleaning area may be one or more sub-areas as described above. When the robot receives a task of cleaning along the edge, it may determine its current self-positioning according to a known map (refer to Figure 3 The location of the midpoint A) and navigate to a path point along the edge of the cleaning area that is closest to the current self-positioning according to the known map (reference Figure 3 The edge path point B). The edge path point can be used as the starting point for the robot to perform the edge cleaning task. After arriving at an edge path point, if there are multiple optional travel directions (for example, Figure 3 In the example, starting from point B, the robot can move left or right. A random direction of travel can be selected. It should be understood that the robot's starting point for performing edge cleaning tasks is not limited to the edge path point closest to its current location. The starting point can also be any one of multiple edge path points.

[0056] In step S13, the boundary attributes of the path points along the edge of the cleaning area are obtained.

[0057] According to a preferred embodiment of the present invention, when the robot navigates into the cleaning area, it can obtain boundary attributes of multiple path points along the cleaning area, where the boundary attributes include physical wall boundary attributes and virtual boundary attributes. Specifically, for example, the robot can obtain the boundary attribute of path point B as a physical wall boundary attribute, and the boundary attribute of path point C as a virtual area boundary attribute.

[0058] In step S14, a corresponding cleaning strategy is executed according to the boundary attributes of the edge path points.

[0059] According to a preferred embodiment of the present invention, the cleaning strategy includes a path tracking cleaning strategy and a wall-adhering cleaning strategy. How to execute the corresponding cleaning strategy according to the boundary attributes of the path points along the edge will be described below.

[0060] According to a preferred embodiment of the present invention, referring to Figure 4 , after the robot obtains the boundary attributes of the edge path points in the cleaning area, it is necessary to determine whether the boundary attributes of the edge path points are physical wall boundary attributes. If the boundary attributes of the edge path points are not physical wall boundary attributes, the robot is controlled to execute the path tracking cleaning strategy. In addition, alternatively, after the robot obtains the boundary attributes of the edge path points in the cleaning area, it can also determine whether the boundary attributes of the edge path points are virtual area boundaries. If the boundary attributes of the edge path points are virtual area boundaries, the robot is controlled to execute the path tracking cleaning strategy, that is, the robot is controlled to clean along the planned path. It should be noted that the path tracking cleaning strategy refers to a method in which the robot strictly executes tracking cleaning based on the generated edge path. If an obstacle is encountered during the tracking cleaning process, local planning obstacle avoidance is executed. After returning to the edge path, the robot decides whether to continue to execute the tracking cleaning strategy based on the boundary attributes of the edge path points and the sensor detection results.

[0061] According to another preferred embodiment of the present invention, Figure 4 , if the boundary attribute of the path point along the edge of the cleaning area is a solid wall boundary, it is determined whether the robot has detected the solid wall, and the corresponding cleaning strategy is executed according to the detection result. The present invention does not limit how to determine whether the robot has detected the solid wall. The robot can be determined by its own sensors whether the robot has detected the solid wall, such as by using an airborne laser radar and / or a binocular vision sensor to obtain a more accurate detection result. According to a preferred embodiment of the present invention, if it is determined that the robot has detected a solid wall, the robot is controlled to execute a wall-sticking cleaning strategy; if it is determined that the robot has not detected a solid wall, the robot is controlled to execute a path tracking cleaning strategy.

[0062] It should be noted that the wall-sticking cleaning strategy refers to the robot being guided by distance detection using sensors (such as lidar, etc.) to achieve real-time control of the robot's posture during movement, and controlling the robot to always maintain a close distance to the wall to perform cleaning tasks based on changes in the wall's contour shape. Specifically, when the boundary attributes of the robot's edge path points are the boundary attributes of a solid wall and the solid wall features currently detected by the sensor are consistent with the map environment feature matching results, that is, the expected consistency between the current cleaning environment and the boundary path attributes is confirmed, the robot executes the wall-sticking cleaning strategy. At this point, the robot will have a certain threshold space relative to the edge path, and no longer needs to strictly track the edge path for cleaning. Instead, it performs wall cleaning within a preset distance range (for example, within 5 cm) based on the detected solid wall. Among them, the solid wall can be a straight wall, a curved wall, a right-angled wall, etc. During the cleaning process, the robot can make real-time motion adjustments according to the changes in the contour shape of the wall, so that the robot can always maintain the preset distance range (for example, within 5 cm) to clean the wall. In combination with the side cleaning tools carried by the robot itself, such as rotating side brushes and other cleaning brushes, it can well achieve the commercial cleaning robot to clean the wall edge without dead angles and details without collision. Moreover, wall cleaning does not rely on positioning, and has high robustness to mapping accuracy, positioning accuracy, and slight changes in the environment. During the wall cleaning process, the edge path will also update the matching of the boundary attributes of the edge path points in real time based on the robot's cleaning position. If the boundary attribute of the edge path point is wall cleaning but no valid solid wall is detected and the matching difference with the map environment is large, the wall cleaning will no longer be performed, and the path tracking cleaning strategy will be directly executed instead.

[0063] It should be understood that during the cleaning process, the robot can obtain its own positioning and the boundary attributes of the edge path points in real time, and execute the corresponding cleaning strategy based on the boundary attributes of the edge path points. If the boundary attributes of the edge path points change, the cleaning strategy can be adjusted in time to obtain better cleaning results until all edge cleaning tasks in the cleaning area are completed. Specifically, for example, the edge path point currently being cleaned by the robot (refer to Figure 3 The boundary attribute of the path point D) is the boundary attribute of the solid wall. The next path point along the edge that the robot needs to clean (reference Figure 3 If the boundary attribute of the path point C) is the virtual area boundary attribute, the robot can switch from the wall cleaning strategy to the path tracking cleaning strategy when it reaches or is about to reach the next path point along the edge that needs to be cleaned. Similarly, if the path point along the edge that the robot is currently cleaning (reference Figure 3 The boundary attribute of the path point C) is the boundary attribute of the virtual area. The next path point along the edge that the robot needs to clean (reference Figure 3 If the boundary attribute of the path point D) is a solid wall boundary attribute, the robot can switch from the path tracking cleaning strategy to the wall cleaning strategy when it reaches or is about to reach the next edge path point that needs to be cleaned.

[0064] Continue to refer Figure 4 To ensure safer, collision-free cleaning, the robot can detect obstacles in real time during the cleaning process. If an obstacle is detected, the robot is controlled to perform an obstacle avoidance maneuver to prevent a collision. The robot can detect obstacles using its own sensors, such as lidar and / or binocular vision sensors. When an obstacle is detected, it can perform an appropriate obstacle avoidance maneuver based on the obstacle's status and cleaning strategy, as described in detail below.

[0065] According to a preferred embodiment of the present invention, when the robot executes the path tracking cleaning strategy, the robot performs a local planning obstacle avoidance operation. Specifically, for example, when a static obstacle is detected, the robot can be controlled to pause cleaning, and the robot's movement speed and / or direction can be adjusted to avoid the obstacle. After the obstacle is eliminated, the robot can be controlled to continue to execute the path tracking cleaning strategy to ensure the safety of the robot. In addition, when a dynamic obstacle is detected, the robot can be controlled to pause cleaning, and based on sensors such as lidar, visual sensors, etc., the movement speed and / or direction of the dynamic obstacle can be detected and predicted, and the robot's movement speed and / or direction can be adjusted in time according to the movement speed and / or direction of the dynamic obstacle to avoid the obstacle. After the obstacle is eliminated, the robot can be controlled to continue to execute the path tracking cleaning strategy to ensure the safety of the robot.

[0066] The above embodiment describes how to control the robot to perform obstacle avoidance when the robot executes the path tracking cleaning strategy. Next, it describes how to control the robot to perform obstacle avoidance when the robot executes the wall cleaning strategy.

[0067] According to a preferred embodiment of the present invention, when the robot executes the wall cleaning strategy, the robot is controlled to perform a wall obstacle avoidance operation. It should be noted that wall obstacle avoidance means that the robot continues to avoid obstacles in a manner similar to wall cleaning. Specifically, if the robot detects a solid wall during the wall cleaning process and there is a difference between the matching of the solid wall features and the map environment features, such as movable objects such as tables and chairs placed next to the wall, the robot will perform a wall obstacle avoidance operation within a certain preset distance range (for example, 5cm to 10cm) based on the detection results until it returns to the expected solid wall to perform wall cleaning. If during the wall cleaning process, there are dynamic obstacles or large static obstacles that interfere with the robot, causing the robot to deviate seriously from the expected edge path, the robot will make a decision based on its own position and sensor detection results, execute a local planning obstacle avoidance process, and quickly return to the vicinity of the uncleaved edge path that is not occupied by obstacles, and then decide again whether to continue to execute the wall cleaning strategy based on the boundary attributes of the edge path points and the detection matching results.

[0068] Specifically, for example, when a static obstacle is detected, the robot can be controlled to avoid the static obstacle within a certain preset distance range (e.g., 5cm to 10cm). After avoiding the obstacle, the robot is controlled to continue to perform the wall-cleaning strategy. When a dynamic obstacle is detected, the movement speed and / or direction of the dynamic obstacle can be detected and predicted based on sensors such as lidar, visual sensors, etc., and the movement speed and / or direction of the robot can be adjusted in time according to the movement speed and / or direction of the dynamic obstacle. The robot is controlled to avoid the dynamic obstacle within a certain preset distance range (e.g., 10cm to 20cm) and avoid the dynamic obstacle. After avoiding the obstacle, the robot is controlled to continue to perform the wall-cleaning strategy. During the wall-avoidance operation, the robot can be controlled to pause cleaning. The lidar can be used to detect in real time whether the robot deviates from the preset distance range. If it deviates, the robot is controlled to perform a locally planned obstacle avoidance operation to prevent the robot from colliding with the solid wall during the cleaning process, causing damage, adversely affecting the normal operation of the robot, and even reducing the service life of the robot.

[0069] According to a preferred embodiment of the present invention, it is also necessary to determine whether the expected path point has been reached, and the expected path point is the path point that the robot wants to reach, such as the next path point that needs to be cleaned or the last path point that needs to be cleaned in the current cleaning area. After the robot reaches a certain expected path point, it is necessary to determine whether the cleaning task of the path point is completed. After determining that the cleaning task of the path point is completed, the path point is lit. When the robot reaches the last path point in the current cleaning area, it is necessary to determine whether the cleaning task of the entire area is completed. For example, it can be determined whether there are still path points that need to be cleaned but are not lit. If so, navigate to the corresponding path point and continue cleaning until all the path points that need to be cleaned are all lit. When the robot completes the cleaning task, it can notify the user through the APP or voice module that the cleaning task is completed.

[0070] According to a preferred embodiment of the present invention, during the entire edge cleaning process of the robot, it is also necessary to control the robot to detect in real time whether it is outside the cleaning area. If it is detected that the robot deviates outside the cleaning area, the robot is controlled to execute a path tracking cleaning strategy and navigate to the cleaning area according to the known map.

[0071] The present invention also relates to a machine 20, Figure 5 A schematic diagram of a robot 20 according to an embodiment of the present invention is shown. Figure 5 As shown, the robot 20 includes:

[0072] A main body 21 having a walking mechanism 210;

[0073] a sensor 22 mounted on the main body 21 and configured to detect the surrounding environment of the robot 20;

[0074] a cleaning brush 30 for cleaning; and

[0075] A processor is coupled to the walking mechanism and the sensor 22 and configured to execute the method 10 described above.

[0076] According to a preferred embodiment of the present invention, the sensor 22 includes one or more of a laser radar 221 , an odometer 222 , and a visual sensor 223 .

[0077] According to a preferred embodiment of the present invention, the walking mechanism 210 is provided with at least two groups of driving wheels 211. Optionally, the robot may further include at least two groups of driven wheels, one group of driving wheels corresponding to one group of driven wheels, wherein at least one group of driven wheels is used as a left driven wheel, and at the same time, at least one group of driven wheels is used as a right driven wheel, and the left driven wheel and the right driven wheel are used to assist the left driving wheel and the right driving wheel in driving the robot to move, so as to reduce the load pressure of the driving wheel 211.

[0078] According to a preferred embodiment of the present invention, the laser radar 221 can be set at the slit of the robot shell, so that it is easy to emit laser signals to detect surrounding objects. In a specific embodiment, the laser radar 221 includes a photoelectric receiving array and a laser emitting unit array, so that when the laser radar 221 rotates along a set plane, the photoelectric receiving array can form a scanning cylinder, thereby increasing the scanning area, facilitating the acquisition of details of the object shape, and avoiding the situation where the robot equipment bumps into the object. In another specific embodiment, the laser radar 221 only includes a single photoelectric receiving unit and a single laser emitting unit. Then, after the laser radar 221 rotates along the set plane, it can measure the shape of an object in a circle, thereby reducing costs. Optionally, the above-mentioned set plane can be a horizontal plane to facilitate the robot to detect objects during movement. In addition, other set planes, such as a vertical plane, can be selected according to user needs, and the present invention is not limited to this.

[0079] According to a preferred embodiment of the present invention, the odometer 222 uses the rotational speed values ​​of at least two sets of driving wheels 211 to obtain the linear velocity and angular velocity of the robot, substitutes them into the kinematic model of the mobile robot, and deduce the current posture of the robot, that is, the position and heading angle information.

[0080] The present invention also relates to a computer-readable storage medium, comprising computer-executable instructions and a map stored thereon, wherein the executable instructions implement the method 10 described above when executed by a processor.

[0081] According to one embodiment of the present invention, the computer-readable storage medium can be a tangible device that can hold and store the instructions used by the instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. The computer-readable storage medium used here is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by a fiber optic cable), or an electrical signal transmitted by a wire.

[0082] It should be noted that the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0083] The computer program instructions for performing the operation of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, Python, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The computer readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), is personalized by utilizing the state information of the computer readable program instructions, and the electronic circuit can execute the computer readable program instructions, thereby realizing various aspects of the present invention.

[0084] By adopting the technical solution of the present invention, the robot can execute the corresponding cleaning strategy based on the boundary attributes of the edge path points, and can better complete the edge cleaning function without collision. It can achieve detailed cleaning of solid walls with good cleaning effect. In addition, the edge cleaning function has very good adaptability to environmental changes, and can complete high-quality edge cleaning in different environments, which greatly improves the robot's edge performance and is conducive to improving the robot's robustness and customer experience.

[0085] It should be noted that, in the present invention, the robot can work in various environments such as shopping malls, homes, hotels, etc., and is particularly suitable for commercial environments such as shopping malls.

[0086] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for controlling a cleaning robot, comprising: Generate an edge path based on a known map, wherein the edge path includes edge path points, and the edge path points have boundary attributes; Receiving a border cleaning task and navigating to the cleaning area according to the known map; Obtaining boundary attributes of path points along the edge of the cleaning area; and Executing a corresponding cleaning strategy according to the boundary attributes of the edge path points; wherein the boundary attributes of the edge path points include physical wall boundaries and virtual area boundaries; and the cleaning strategies include path tracking cleaning strategies and wall-adhering cleaning strategies; The step of executing a corresponding cleaning strategy according to the boundary attributes of the edge path points includes: Determine whether the boundary attribute of the path point along the edge of the cleaning area is a solid wall boundary; If the boundary attribute of the path point along the edge of the cleaning area is not a solid wall boundary, executing the path tracking cleaning strategy; If the boundary attribute of the path point along the edge of the cleaning area is a solid wall boundary, determining whether the robot detects a solid wall, and executing a corresponding cleaning strategy according to the detection result; If it is determined that the robot detects a solid wall, the wall cleaning strategy is executed; otherwise, the path tracking cleaning strategy is executed.

2. The method according to claim 1, wherein the step of generating a path along the edge based on a known map comprises: Perform image region segmentation on the known map, extract boundary information of the segmented region outline, process the boundary information, and generate path points along the edge with boundary attributes.

3. The method according to claim 2, wherein the step of processing the boundary information to generate path points along the edge with boundary attributes comprises: The boundary information is processed based on the map attributes of the known map to generate initial path points along the edge, and the initial path points along the edge are matched with the known map to generate path points along the edge with boundary attributes, thereby generating an edge path.

4. According to the method described in claim 1, during the wall cleaning process, the edge path updates the matching of the boundary attributes of the edge path points in real time based on the robot's cleaning position. If the boundary attribute of the edge path point is for wall cleaning but no valid physical wall is detected and the matching difference with the map environment is large, the wall cleaning will not be executed and the path tracking cleaning strategy will be implemented.

5. The method according to claim 1, wherein the step of executing the wall cleaning strategy comprises: According to the shape change of the solid wall, the robot is controlled to maintain cleaning within a preset distance range from the solid wall.

6. The method according to claim 5, further comprising: Detect whether there is an obstacle, and if there is an obstacle, control the robot to perform obstacle avoidance operations.

7. The method according to claim 6, wherein the step of controlling the robot to perform obstacle avoidance comprises: When the robot executes the path tracking cleaning strategy, the robot performs a local planning obstacle avoidance operation.

8. The method according to claim 7, wherein when the robot executes the path tracking cleaning strategy, the robot performs a local planning obstacle avoidance operation, comprising: When a static obstacle is detected, the robot is controlled to pause cleaning and adjust its movement speed and / or direction to avoid the obstacle. After the obstacle is removed, the robot is controlled to continue executing the path tracking cleaning strategy. When a dynamic obstacle is detected, the robot is controlled to pause cleaning, and the movement speed and / or direction of the dynamic obstacle is detected and predicted based on the sensor, and the movement speed and / or direction of the robot is adjusted in time according to the movement speed and / or direction of the dynamic obstacle to avoid the obstacle. After the obstacle is eliminated, the robot is controlled to continue to execute the path tracking cleaning strategy.

9. The method according to claim 6, wherein the step of controlling the robot to perform obstacle avoidance operation further comprises: When the robot executes the wall cleaning strategy, the robot is controlled to perform a wall obstacle avoidance operation, and it is determined whether it deviates from the preset distance range during the wall obstacle avoidance process. If it deviates, the robot is controlled to perform a local planning obstacle avoidance operation.

10. The method according to claim 9, wherein when a static obstacle is detected, the robot is controlled to avoid the static obstacle within a predetermined distance range, and after avoiding the obstacle, the robot is controlled to continue to perform a wall cleaning strategy; When a dynamic obstacle is detected, the movement speed and / or direction of the dynamic obstacle is detected and predicted based on the sensor, and the movement speed and / or direction of the robot is adjusted in time according to the movement speed and / or direction of the dynamic obstacle. The robot is controlled to be within a certain preset distance range from the dynamic obstacle and to bypass the dynamic obstacle. After bypassing the dynamic obstacle, the robot continues to be controlled to execute the wall cleaning strategy.

11. The method according to claim 10 determines whether the expected path point has been reached, and the expected path point is the next path point to be cleaned or the last path point to be cleaned in the current cleaning area. When the robot reaches the expected path point, it determines whether the cleaning task of the path point is completed. When it is determined that the cleaning task of the path point is completed, the path point is lit; when the robot reaches the last path point to be cleaned in the current cleaning area, it determines whether there are any path points that need to be cleaned but are not lit. If so, it navigates to the corresponding path point and continues cleaning until all the path points to be cleaned are lit; when the robot completes the cleaning task, it notifies the user through the APP or voice module that the cleaning task is completed.

12. The method according to claim 11, further comprising: During the entire edge cleaning process, if it is detected that the robot deviates from the cleaning area, the robot is controlled to execute a path tracking cleaning strategy and navigate into the cleaning area according to the known map.

13. A robot comprising: The main body has a walking mechanism; a sensor mounted on the main body and configured to detect the surrounding environment of the robot; Cleaning brush for sweeping; A processor is coupled to the walking mechanism and the sensor, and is configured to execute the method according to any one of claims 1 to 12.

14. The robot according to claim 13, wherein the sensor comprises one or more of a laser radar, an odometer, and a visual sensor.

15. A computer-readable storage medium comprising computer-executable instructions and a map stored thereon, wherein the executable instructions implement the method according to any one of claims 1 to 12 when executed by a processor.

Images