Robot control method, non-volatile readable storage medium, and robot

Abstract

The application relates to the technical field of cleaning equipment, and discloses a robot control method, a nonvolatile readable storage medium and a robot. The robot control method comprises the following steps: acquiring an environment image collected when a robot performs a cleaning operation, the environment image containing at least one obstacle region; determining a target obstacle type of the obstacle region according to a preset visual semantic model; determining a target movement type of the target obstacle according to the target obstacle type; if the target movement type is a difficult movement type, determining an offset distance of the obstacle region relative to a preset original region; and controlling the cleaning operation of the robot according to the offset distance. The embodiment can pay attention to whether the target obstacle of the difficult movement type is moved, wherein the offset distance is used for representing whether the target obstacle is moved, the cleaning operation of the robot can be controlled according to the offset distance, the corresponding cleaning operation can be adaptively selected, and therefore the cleaning effect can be improved.

Description

Technical Field

[0001] This invention relates to the field of cleaning equipment technology, specifically to a robot control method, a non-volatile readable storage medium, and a robot. Background Technology

[0002] In everyday home environments, the placement of many pieces of furniture is generally fixed. Due to this long-term fixed location, household trash easily gets trapped inside the furniture or accumulates at the edges or corners where the furniture meets the floor. Over time, this accumulated dirt and debris can leave deep marks on the floor when the furniture is moved, and small particles like sand can easily remain in these marks. Since current cleaning robots do not record cleaning information associated with furniture, when the robot uses its normal cleaning mode, it struggles to effectively clean the areas corresponding to these marks, resulting in poor cleaning performance. Summary of the Invention

[0003] One objective of this invention is to provide a robot control method, a non-volatile readable storage medium, and a robot, aiming to solve the technical problem of poor cleaning effect in related technologies.

[0004] In a first aspect, embodiments of the present invention provide a robot control method, comprising:

[0005] Acquire environmental images captured by the robot during cleaning operations, wherein the environmental images contain at least one obstacle area;

[0006] Based on a preset visual semantic model, the target obstacle type in the obstacle area is determined;

[0007] Determine the target movement type of the target obstacle corresponding to the obstacle region based on the target obstacle type;

[0008] If the target movement type is a difficult movement type, then the offset distance of the obstacle area relative to the preset original area is determined, where the original area is the area where the target obstacle was initially placed;

[0009] The robot's cleaning operation is controlled based on the offset distance.

[0010] Optionally, controlling the robot's cleaning operation based on the offset distance includes:

[0011] Determine whether the offset distance is greater than a preset distance threshold;

[0012] If the target cleaning intensity is greater than the target obstacle type, the target cleaning intensity is determined, and the robot is controlled to clean the original area according to the target cleaning intensity, wherein the target cleaning intensity is greater than the cleaning intensity selected by the robot in the normal cleaning mode.

[0013] If the value is less than the target value, the robot is controlled to clean the target obstacle along its edge.

[0014] Optionally, the weight grade is positively correlated with the cleaning intensity, and determining the target cleaning intensity based on the type of target obstacle includes:

[0015] The target weight class is determined based on the type of the target obstacle.

[0016] The cleaning intensity corresponding to the target weight level is determined as the target cleaning intensity.

[0017] Optionally, controlling the robot to clean the original area according to the target cleaning intensity includes:

[0018] Determine the target structure type based on the type of target obstacle;

[0019] Based on the target structure type, determine the target area where the target obstacle contacts the ground in the original area;

[0020] The robot is controlled to clean the target area based on the target cleaning intensity.

[0021] Optionally, when the target structure type is a frame support type, determining the target area where the target obstacle contacts the ground on the original area based on the target structure type includes:

[0022] Based on the frame support type, the edge region is determined as the target region on the original region.

[0023] Optionally, controlling the robot to clean the target area based on the target cleaning intensity includes:

[0024] The starting position point is determined as the closest and most accessible point to the robot's current position within the target area.

[0025] The robot is controlled to clean along the target area starting from the starting position point, based on the target cleaning intensity.

[0026] Optionally, when the target structure type is a pivot support type, determining the target area where the target obstacle contacts the ground on the original area based on the target structure type includes:

[0027] Based on the fulcrum support type, a corner region is determined as the target region on the original region.

[0028] Optionally, controlling the robot to clean the target area based on the target cleaning intensity includes:

[0029] Determine the center point of the corner region and the radius of rotation around the center point;

[0030] Based on the target cleaning intensity, the robot is controlled to rotate and clean around the center point according to the rotation radius.

[0031] In a second aspect, embodiments of the present invention provide a non-volatile readable storage medium storing computer-executable instructions for causing a robot to perform any of the robot control methods described above.

[0032] In a third aspect, embodiments of the present invention provide a computer program product, the computer program product including a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions, which, when executed by a robot, cause the robot to perform the aforementioned robot control method.

[0033] In a fourth aspect, embodiments of the present invention provide a robot, comprising:

[0034] At least one processor; and,

[0035] A memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores instructions that can be executed by the at least one processor, which, when executed, enable the at least one processor to perform the robot control method.

[0037] In the robot control method provided in this embodiment of the invention, an environmental image is acquired when the robot performs a cleaning operation. The environmental image contains at least one obstacle region. Based on a preset visual semantic model, the target obstacle type of the obstacle region is determined. Based on the target obstacle type, the target movement type of the target obstacle corresponding to the obstacle region is determined. If the target movement type is a difficult-to-move type, the offset distance of the obstacle region relative to a preset original region is determined. The original region is the area where the target obstacle is initially placed. The robot's cleaning operation is controlled based on the offset distance. This embodiment can focus on whether the target obstacle of the difficult-to-move type has been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation based on the offset distance, thus adaptively selecting the appropriate cleaning operation and improving the cleaning effect. Attached Figure Description

[0038] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0039] Figure 1 A flowchart illustrating a robot control method provided in an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of the structure of a robot control device provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the circuit structure of a robot provided in an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0043] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0044] This invention provides a robot control method. Please refer to [link / reference]. Figure 1 The robot control method includes the following steps:

[0045] S11: Acquire environmental images collected by the robot during cleaning operations. The environmental images contain at least one obstacle area.

[0046] In this step, the robot includes a sweeping robot, a mopping robot, a combined sweeping and mopping robot, a vacuuming robot, or a floor-washing robot, etc. The cleaning operation refers to the robot controlling the cleaning components to clean the floor. The cleaning components can be determined based on the robot's cleaning functions, such as a roller brush, a mop, or a vacuuming component. The environmental image is an image of the environment captured by the camera controlled by the robot during the cleaning operation. The obstacle area is the region on the environmental image consisting of multiple pixels corresponding to obstacles.

[0047] S12: Determine the type of target obstacle in the obstacle area based on the preset visual semantic model.

[0048] In this step, the preset visual semantic model is pre-trained and generated by the designer. This preset visual semantic model can be an artificial intelligence model, which supports corresponding machine learning algorithms. In this embodiment, images of various indoor objects are collected as training images, and each image is labeled. The labeled images are then input into a neural network for training to generate the preset visual semantic model. The loss function of the neural network can be a BCE loss function, and the activation function can be a sigmoid function, etc.

[0049] The target obstacle type is the type of obstacle that corresponds to the obstacle area. The obstacle type is used to indicate the name of the obstacle. Obstacle types include furniture, fabric, wire, stepped base, body fat scale, pet feces, household waste, bed, sofa, large cabinet, bookcase, wardrobe, TV cabinet, table, coffee table, potted plant, chair, shoe, body fat scale, sofa chair, wooden stool, stroller, etc.

[0050] S13: Determine the target movement type of the target obstacle corresponding to the obstacle area based on the target obstacle type.

[0051] In this step, the target obstacle is the obstacle corresponding to the obstacle area.

[0052] The movement type indicates whether an obstacle can be easily moved. Movement types include "difficult to move" and "easy to move." "Difficult to move" indicates that the obstacle is not easily moved and is moved infrequently, while "easy to move" indicates that the obstacle is easily moved and is moved relatively infrequently. Typically, indoor obstacles include sofas, beds, large cabinets, bookshelves, wardrobes, TV cabinets, tables, and coffee tables. These obstacles are classified as "difficult to move," meaning they are not easily moved and are moved infrequently, such as once a year or once every six months. Obstacles on the other hand include sofas, chairs, wooden stools, flower pots, strollers, potted plants, chairs, shoes, etc. These obstacles are classified as "easy to move," meaning they require some effort to move and are moved infrequently, such as once a week, once a month, or twice a month.

[0053] This embodiment can identify various obstacles indoors in advance based on a preset visual semantic model, and construct a cleaning record table based on the identification results. The cleaning record table is shown in Table 1.

[0054] Table 1

[0055]

[0056] In Table 1, the weight range corresponding to the first weight level is larger than that corresponding to the second weight level, and the weight range corresponding to the second weight level is larger than that corresponding to the third weight level. The cleaning intensity of the first level is greater than that of the second level, which is greater than that of the third level, and the third level is greater than that of the fourth level. Therefore, the higher the weight level, the higher the cleaning intensity. The first weight level is the highest weight level, and the first cleaning intensity is the highest level. The fourth cleaning intensity is the cleaning intensity of the normal cleaning mode.

[0057] The weight class is determined based on the weight and weight range of the obstacle. For example, a sofa is very heavy, so in this embodiment, the sofa is matched with the first weight class. A table is relatively heavy, so in this embodiment, the bed is matched with the second weight class, and so on.

[0058] Cleaning intensity refers to the strength of the cleaning components controlled by the robot when performing cleaning operations. Cleaning intensity includes factors such as suction power and water output. Generally, a higher weight class corresponds to greater cleaning intensity, and a lower weight class corresponds to lower cleaning intensity.

[0059] The structure type refers to the type of structure in which the obstacle contacts the ground. Among them, the frame support type is the type in which the obstacle contacts the ground through a square frame, and the fulcrum support type is the type in which the obstacle contacts the ground through a pillar.

[0060] Understandably, users can modify and delete Table 1. The processed cleaning record table will be saved locally on the robot. For example, the structure type of obstacles can be customized by the user, matching the obstacle with a corresponding structure type. For instance, some beds contact the ground through a square frame, so the corresponding structure type for these beds is frame support, and users can add "frame support type" to these beds. Similarly, some beds contact the ground through supports, so the corresponding structure type for these beds is pivot support, and users can add "pivot support type" to these beds. Furthermore, users can match the corresponding cleaning intensity to the appropriate obstacle, such as matching the first cleaning intensity to the bed.

[0061] In some embodiments, the target movement type of the target obstacle corresponding to the obstacle area is determined based on the target obstacle type: the cleaning record table is traversed according to the target obstacle type to obtain the movement type corresponding to the target obstacle type, and the movement type corresponding to the target obstacle type is selected as the target movement type. For example, if the target obstacle type is a sofa, and the movement type corresponding to a sofa is the difficult movement type, then the target movement type is the difficult movement type.

[0062] S14: If the target movement type is difficult, determine the offset distance of the obstacle area relative to the preset original area, where the original area is the area where the target obstacle was initially placed.

[0063] In this step, the offset distance is the distance between the obstacle area and the original area. Typically, the robot records the original area of ​​each type of obstacle that is difficult to move.

[0064] In some embodiments, determining the offset distance of an obstacle area relative to a preset original area includes the following steps: determining the center position of the obstacle area and the center position of the original area, calculating the distance between the center position of the obstacle area and the center position of the original area, and obtaining the offset distance.

[0065] In some embodiments, determining the offset distance of an obstacle region relative to a preset original region includes the following steps: extracting the longest line segment from the obstacle region, determining a baseline segment from the original region, calculating the distance from the midpoint of the longest line segment to the midpoint of the baseline segment, and obtaining the offset distance. The baseline segment is the longest line segment in the baseline region.

[0066] In some embodiments, if the target movement type is easy to move, the robot is controlled to perform cleaning operations according to the regular cleaning mode.

[0067] S15: Control the robot's cleaning operation based on the offset distance.

[0068] This embodiment can monitor whether target obstacles of the type of difficulty in movement have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation according to the offset distance, so as to adaptively select the appropriate cleaning operation and thus improve the cleaning effect.

[0069] In some embodiments, controlling the robot's cleaning operation based on the offset distance includes the following steps: determining whether the offset distance is greater than a preset distance threshold; if it is greater, determining the target cleaning intensity based on the type of the target obstacle; and controlling the robot to clean the original area based on the target cleaning intensity, wherein the target cleaning intensity is greater than the cleaning intensity selected by the robot in the normal cleaning mode; if it is less than the target cleaning intensity, controlling the robot to clean the target obstacle along its edge. The preset distance threshold is customized by the designer based on engineering experience, such as 50cm, 1m, or 2m.

[0070] This embodiment can monitor whether a target obstacle that is difficult to move has been moved. When it is detected that a target obstacle that is difficult to move has been moved, it can apply a corresponding target cleaning intensity to clean the original area. This can effectively clean the traces left by the original area occupied by the target obstacle, thereby improving the cleaning effect.

[0071] In some embodiments, the weight class is positively correlated with the cleaning intensity. Determining the target cleaning intensity based on the type of target obstacle includes the following steps: determining the weight class corresponding to the target obstacle as the target weight class based on the type of target obstacle, and determining the cleaning intensity corresponding to the target weight class as the target cleaning intensity.

[0072] In some embodiments, determining the weight level corresponding to the target obstacle as the target weight level based on the target obstacle type includes: traversing a preset cleaning record table according to the target obstacle type to obtain the weight level corresponding to the target obstacle type, and using the weight level corresponding to the target obstacle type as the target weight level.

[0073] For example, when the target obstacle type is a "sofa," this embodiment, based on the cleaning record table for "sofa," obtains the weight level corresponding to "sofa" as the first weight level. Therefore, the target weight level is the first weight level, and the target cleaning intensity is the first level of cleaning intensity. When the target obstacle type is a "table," this embodiment, based on the cleaning record table for "table," obtains the weight level corresponding to "table" as the second weight level. Therefore, the target weight level is the second weight level, and the target cleaning intensity is the second level of cleaning intensity. When the target obstacle type is a "bed," this embodiment, based on the cleaning record table for "bed," obtains the weight level corresponding to "bed" as the first weight level. Therefore, the target weight level is the first weight level, and the target cleaning intensity is the first level of cleaning intensity.

[0074] In some embodiments, controlling the robot to clean the original area according to the target cleaning intensity includes: controlling the robot to perform a full-traverse cleaning operation on the original area according to the target cleaning intensity. In this embodiment, any cleaning path can be used to perform the full-traverse cleaning operation on the original area, including a bow-shaped path or a herringbone-shaped path.

[0075] In some embodiments, controlling a robot to clean an original area based on a target cleaning intensity includes: determining a target structure type based on the type of the target obstacle; determining a target area in the original area where the target obstacle contacts the ground based on the target structure type; and controlling the robot to clean the target area based on the target cleaning intensity. This embodiment selectively selects a corresponding local area as the target area in the original area based on the target structure type of the target obstacle, and then cleans the target area according to the target cleaning intensity, thus improving cleaning efficiency.

[0076] In some embodiments, when the target structure type is a frame support type, determining the target area where the target obstacle contacts the ground on the original area according to the target structure type includes: determining the edge area as the target area on the original area according to the frame support type.

[0077] In some embodiments, controlling the robot to clean a target area according to the target cleaning intensity includes: determining a point on the target area that is closest to and accessible to the robot's current position as a starting point, and controlling the robot to clean along the target area from the starting point according to the target cleaning intensity.

[0078] In some embodiments, controlling the robot to clean along the target area from the starting position point according to the target cleaning intensity includes: determining the target cleaning direction according to the starting position point, and controlling the robot to clean along the target area according to the target cleaning direction and the target cleaning intensity.

[0079] For example, in this embodiment, the robot is controlled to select a clockwise direction as the target cleaning direction, and the robot is controlled to clean the target area in a clockwise direction according to the target cleaning intensity.

[0080] In some embodiments, when the target structure type is a pivot support type, determining the target area where the target obstacle contacts the ground on the original area according to the target structure type includes: determining the four corner areas as target areas on the original area according to the pivot support type.

[0081] In some embodiments, determining a corner region as a target region on the original region based on the fulcrum support type includes: determining each line segment of the original region, sorting each line segment according to its length, selecting the four longest line segments as target line segments, determining the intersection points formed by the intersections with the target line segments, and determining the corner region based on the intersection points and a preset distance.

[0082] In some embodiments, determining the corner region based on the intersection point and a preset distance includes: determining a region of a specified shape based on the intersection point and a preset distance to obtain the corner region.

[0083] In some embodiments, the shape is specified as a rectangle, square, or circle, etc.

[0084] In some embodiments, controlling the robot to clean the target area according to the target cleaning intensity includes: determining the center point of each corner area and the rotation radius around the center point, and controlling the robot to rotate and clean according to the rotation radius with the center point as the rotation center.

[0085] This embodiment can clean the edge area of ​​a frame-supported target obstacle or the corner area of ​​a fulcrum-supported target obstacle. Since the edge or corner area is the main stress area of ​​the target obstacle, small debris such as sand and dirt tend to remain in the edge or corner area, and the marks are also deeper. The robot is controlled to clean along the edge area from the starting position point according to the target cleaning intensity, or the robot is controlled to rotate and clean according to the rotation radius with the center point as the rotation center.

[0086] Since the heavier the target obstacle, the higher the target cleaning intensity level, the robot can adaptively select the appropriate cleaning intensity as the target cleaning intensity. Based on the target cleaning intensity, the robot can control the cleaning of edge or corner areas, and this cleaning method has a better cleaning effect.

[0087] In summary, this embodiment can focus on whether target obstacles that are difficult to move have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation based on the offset distance, thus adaptively selecting the appropriate cleaning operation and improving the cleaning effect. Furthermore, this embodiment can determine the target area based on the structural type of the target obstacle, avoiding the efficiency reduction caused by traversing the entire original area, and can clean the target area in a more targeted manner, which is beneficial for improving the cleaning effect.

[0088] It should be noted that in the above embodiments, there is no necessarily a certain order between the steps. Those skilled in the art can understand from the description of the embodiments of the present invention that the above steps may have different execution orders in different embodiments, that is, they may be executed in parallel or in turn, etc.

[0089] As another aspect of the present invention, an embodiment of the present invention provides a robot control device. The robot control device can be a software module, which includes several instructions stored in a memory. A processor can access the memory, invoke the instructions, and execute them to complete the robot control methods described in the various embodiments above.

[0090] In some embodiments, the robot's control device can also be constructed from hardware components. For example, the robot's control device can be constructed from one or more chips, which can work in coordination to complete the robot control methods described in the various embodiments above. As another example, the robot's control device can also be constructed from various logic devices, such as general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), microcontrollers, ARM (Acorn RISC Machine) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of these components.

[0091] Please see Figure 2 The robot's control device 200 includes an image acquisition module 21, a type determination module 22, a movement determination module 23, a distance calculation module 24, and a machine control module 25.

[0092] The image acquisition module 21 is used to acquire environmental images collected when the robot performs cleaning operations, and the environmental images include at least one obstacle area.

[0093] The type determination module 22 is used to determine the type of target obstacle in the obstacle area based on a preset visual semantic model.

[0094] The movement determination module 23 is used to determine the target movement type of the target obstacle corresponding to the obstacle area based on the target obstacle type;

[0095] The distance calculation module 24 is used to determine the offset distance of the obstacle area relative to the preset original area if the target movement type is a difficult movement type, wherein the original area is the area where the target obstacle is initially placed;

[0096] The machine control module 25 is used to control the cleaning operation of the robot according to the offset distance.

[0097] This embodiment can monitor whether target obstacles of the type of difficulty in movement have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation according to the offset distance, so as to adaptively select the appropriate cleaning operation and thus improve the cleaning effect.

[0098] In some embodiments, the machine control module 25 is specifically used to: determine whether the offset distance is greater than a preset distance threshold; if it is greater, determine the target cleaning intensity according to the type of the target obstacle; and control the robot to clean the original area according to the target cleaning intensity, wherein the target cleaning intensity is greater than the cleaning intensity selected by the robot in the normal cleaning mode; if it is less than the target cleaning intensity, control the robot to clean the target obstacle along the edge.

[0099] In some embodiments, the weight class is positively correlated with the cleaning intensity. The machine control module 25 is further specifically configured to: determine the weight class corresponding to the target obstacle as the target weight class based on the type of the target obstacle, and determine the cleaning intensity corresponding to the target weight class as the target cleaning intensity.

[0100] In some embodiments, the machine control module 25 is further configured to: determine the target structure type according to the target obstacle type, determine the target area where the target obstacle contacts the ground on the original area according to the target structure type, and control the robot to clean the target area according to the target cleaning intensity.

[0101] In some embodiments, when the target structure type is a frame support type, the machine control module 25 is further configured to: determine an edge region as a target region on the original region according to the frame support type.

[0102] In some embodiments, the machine control module 25 is further configured to: determine a starting position point on the target area that is closest to and accessible to the robot's current position, and control the robot to clean along the target area from the starting position point according to the target cleaning intensity.

[0103] In some embodiments, when the target structure type is a fulcrum support type, the machine control module 25 is further configured to: determine a corner region as the target region on the original region according to the fulcrum support type.

[0104] In some embodiments, the machine control module 25 is further configured to: determine the center point of the corner area and the rotation radius around the center point, and control the robot to perform rotation cleaning with the center point as the rotation center according to the target cleaning intensity.

[0105] It should be noted that the robot control device described above can execute the robot control method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in the robot control device embodiments can be found in the robot control method provided in the embodiments of the present invention.

[0106] Please see Figure 3 , Figure 3 This is a circuit structure diagram of a robot provided in an embodiment of the present invention, wherein the robot includes a sweeping robot, a mopping robot, a sweeping and mopping robot, a vacuuming robot, or a floor washing robot, etc. Figure 3 As shown, the robot 300 includes one or more processors 31 and a memory 32. Wherein, Figure 3 Take a processor 31 as an example.

[0107] Processor 31 and memory 32 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0108] The memory 32, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the robot control method in the embodiments of the present invention. The processor 31 executes various functional applications and data processing of the robot control device by running the non-volatile software programs, instructions, and modules stored in the memory 32, thereby realizing the robot control method provided in the above method embodiments and the functions of various modules or units in the above device embodiments.

[0109] Memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 32 may optionally include memory remotely located relative to processor 31, which can be connected to processor 31 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0110] The program instructions / modules are stored in the memory 32 and, when executed by one or more processors 31, execute the robot control method in any of the above method embodiments.

[0111] This embodiment can monitor whether target obstacles of the type of difficulty in movement have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation according to the offset distance, so as to adaptively select the appropriate cleaning operation and thus improve the cleaning effect.

[0112] This invention also provides a non-volatile computer storage medium storing computer-executable instructions that are executed by one or more processors, for example... Figure 3 One of the processors 31 can enable the one or more processors to execute the robot control method in any of the above method embodiments.

[0113] This embodiment can monitor whether target obstacles of the type of difficulty in movement have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation according to the offset distance, so as to adaptively select the appropriate cleaning operation and thus improve the cleaning effect.

[0114] This invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions, which, when executed by a robot, cause the robot to perform any of the robot control methods described above.

[0115] This embodiment can monitor whether target obstacles of the type of difficulty in movement have been moved. The offset distance is used to characterize whether the target obstacle has been moved. This embodiment can control the robot's cleaning operation according to the offset distance, so as to adaptively select the appropriate cleaning operation and thus improve the cleaning effect.

[0116] The device or equipment embodiments described above are merely illustrative. The unit modules described as separate components may or may not be physically separate. The components shown as module units may or may not be physical units; that is, they may be located in one place or distributed across multiple network module units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling a robot, characterized in that, include: Acquire environmental images captured by the robot during cleaning operations, wherein the environmental images contain at least one obstacle area; Based on a preset visual semantic model, the target obstacle type of the obstacle region is determined, wherein the target obstacle type is the obstacle type corresponding to the obstacle region, and the obstacle type is used to represent the name of the obstacle; Determine the target movement type of the target obstacle corresponding to the obstacle region based on the target obstacle type; If the target movement type is a difficult movement type, then the offset distance of the obstacle area relative to the preset original area is determined, where the original area is the area where the target obstacle was initially placed. The difficult movement type indicates that the obstacle is not easy to move and the frequency of being moved is very small. Controlling the robot's cleaning operation based on the offset distance includes: determining whether the offset distance is greater than a preset distance threshold; if it is greater, determining the target cleaning intensity based on the type of the target obstacle, and controlling the robot to clean the original area based on the target cleaning intensity, wherein the target cleaning intensity is greater than the cleaning intensity selected by the robot in the normal cleaning mode; if it is less than the target obstacle, controlling the robot to clean the target obstacle along its edge. The weight class is positively correlated with the cleaning intensity. The step of determining the target cleaning intensity based on the target obstacle type includes: determining the weight class corresponding to the target obstacle as the target weight class based on the target obstacle type; and determining the cleaning intensity corresponding to the target weight class as the target cleaning intensity.

2. The control method according to claim 1, characterized in that, The step of controlling the robot to clean the original area according to the target cleaning intensity includes: Determine the target structure type based on the type of target obstacle; Based on the target structure type, determine the target area where the target obstacle contacts the ground in the original area; The robot is controlled to clean the target area based on the target cleaning intensity.

3. The control method according to claim 2, characterized in that, When the target structure type is a frame support type, determining the target area where the target obstacle contacts the ground on the original area based on the target structure type includes: Based on the frame support type, the edge region is determined as the target region on the original region.

4. The control method according to claim 3, characterized in that, The step of controlling the robot to clean the target area based on the target cleaning intensity includes: The starting position point is determined as the closest and most accessible point to the robot's current position within the target area. The robot is controlled to clean along the target area starting from the starting position point, based on the target cleaning intensity.

5. The control method according to claim 2, characterized in that, When the target structure type is a pivot support type, determining the target area where the target obstacle contacts the ground on the original area based on the target structure type includes: Based on the fulcrum support type, a corner region is determined as the target region on the original region.

6. The control method according to claim 5, characterized in that, The step of controlling the robot to clean the target area based on the target cleaning intensity includes: Determine the center point of the corner region and the radius of rotation around the center point; Based on the target cleaning intensity, the robot is controlled to rotate and clean around the center point according to the rotation radius.

7. A non-volatile readable storage medium, characterized in that, The robot is equipped with computer-executable instructions for causing the robot to perform the robot control method as described in any one of claims 1 to 6.

8. A robot, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the robot control method as described in any one of claims 1 to 6.

Images