Robot control method, device, robot and storage medium

Abstract

The embodiments of the present application disclose a robot control method, device, robot, and storage medium. The method includes obtaining obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of the obstacle's cross section; determining whether there is an obstacle that meets a preset first type based on the point cloud data of the obstacle's cross section; and when it is determined that there is an obstacle that meets the preset first type, obtaining a corresponding movement strategy and controlling the robot to perform cleaning work according to the movement strategy. The present application does not require too many sensors to work together. It only needs to use a certain type or a certain type of sensor that can achieve the same function to collect the cross-sectional data of the obstacle, determine the type of obstacle by analyzing the cross-sectional data, and especially accurately identify furniture objects, thereby quickly completing the cleaning work in the area where such obstacles are located.

Description

Technical Field

[0001] The present invention belongs to the field of robotics technology, and in particular relates to a robot control method, a robot control device, a robot and a storage medium. Background Art

[0002] In recent years, with the development of science and technology and the gradual improvement of people's living standards, service robots have begun to appear on the market, improving the convenience of people's lives. As a service robot, the sweeping robot can automatically clean the floor, freeing people's hands.

[0003] In a homework scenario, when identifying common objects like tables, chairs, sofas, and beds, existing robots use cameras to capture images of the objects, apply machine learning algorithms (such as pattern recognition) to analyze the images and determine the object type, and then calculate the object's position using ranging sensors or monocular estimation. This processing method requires the collaboration of multiple sensors, has complex algorithms, and is overly simplistic. Furthermore, calculating the object's position using ranging sensors or monocular estimation methods has drawbacks. For larger pieces of furniture, the angle and installation position of sensors such as cameras make it impossible to capture certain important features of the object, potentially leading to inaccurate object identification and position estimation. Summary of the Invention

[0004] To address the problems of the prior art, the present invention proposes a robot control method, device, robot, and storage medium. This method eliminates the need for multiple sensors to work together, instead using only one type of sensor, or a class of sensors that perform the same function, to collect cross-sectional data of obstacles. By analyzing this cross-sectional data, the type of obstacle is determined, particularly accurately identifying furniture, allowing for rapid cleaning of areas where such obstacles are located.

[0005] The specific technical solutions provided by the embodiments of the present invention are as follows:

[0006] In a first aspect, a robot control method is provided, the method comprising:

[0007] Obtaining obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of a cross section of the obstacle;

[0008] determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle;

[0009] When it is determined that there is an obstacle that meets the preset first type, a corresponding movement strategy is obtained and the robot is controlled to perform cleaning work according to the movement strategy.

[0010] In some embodiments, determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle specifically includes:

[0011] Extracting, based on the point cloud data of the cross section of the obstacle, all cross sections whose cross section widths satisfy a preset first threshold range;

[0012] Obtaining the distribution positions of all cross sections whose cross section widths satisfy a preset first threshold range and performing analysis and processing;

[0013] When it is determined that the distribution of the cross sections meets the preset distribution condition, it is determined that there is an obstacle that meets the preset first type.

[0014] In some embodiments, determining whether the distribution of the cross sections satisfies a preset distribution condition specifically includes:

[0015] Determining that the distribution of at least a portion of the cross section of the obstacle forms a rectangle or triangle of a predetermined size;

[0016] The determining that there is an obstacle that meets a preset first type includes:

[0017] The obstacles corresponding to the cross-sections of a rectangle or triangle of a preset size are determined as obstacles meeting the preset first type.

[0018] In some embodiments, the obstacle information further includes information on the height of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle determined based on the bottom surface point cloud data of the obstacle;

[0019] The method further comprises:

[0020] Determining whether there is an obstacle that meets a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle;

[0021] When it is determined that there is an obstacle that meets the preset second type, a corresponding cleaning mode is acquired and the robot is controlled to perform cleaning work according to the cleaning mode.

[0022] In some embodiments, determining whether there is an obstacle meeting a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle specifically includes:

[0023] Obtaining a comparison result of the height information of the bottom surface of the obstacle from the ground and a preset second threshold range;

[0024] When the height information of the bottom surface of the obstacle from the ground is within a preset second threshold range, determining whether the bottom surface area of ​​the obstacle is within a preset third threshold range;

[0025] When the bottom surface area of ​​the obstacle is within a preset third threshold range, it is determined that there is an obstacle that meets the preset second type.

[0026] In some embodiments, the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode;

[0027] The numerical value of the operating parameter of the enhanced cleaning mode is greater than the numerical value of the operating parameter of the normal cleaning mode; the operating parameter includes suction power;

[0028] The obtaining of the corresponding cleaning mode and controlling the robot to perform cleaning work according to the cleaning mode specifically includes:

[0029] An enhanced cleaning mode is acquired and the robot is controlled to perform cleaning work according to the enhanced cleaning mode.

[0030] In some embodiments, controlling the robot to perform cleaning work according to the movement strategy specifically includes:

[0031] determining an edge of the obstacle in contact with the ground based on point cloud data of a cross section of the obstacle, and controlling the robot to clean the edge of the obstacle;

[0032] A cleaning edge is determined based on the point cloud data of the cross section of the obstacle, and the robot is controlled to perform cleaning within the area determined by the cleaning edge.

[0033] In some embodiments, the method further comprises:

[0034] When the type of the obstacle is identified, the obstacle is marked in a preset map model based on the determined location information of the obstacle.

[0035] In a second aspect, a robot control device is provided, the device comprising:

[0036] An acquisition module, configured to acquire obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of a cross section of the obstacle;

[0037] a processing module, configured to determine whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle;

[0038] The control module is used to obtain a corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy when it is determined that there is an obstacle that meets the preset first type.

[0039] In a third aspect, a robot is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0040] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to the first aspect is implemented.

[0041] The embodiments of the present invention have the following beneficial effects:

[0042] 1. The present invention uses point cloud data of the obstacle's cross section to determine the type of obstacle currently encountered. Once the type is determined, the robot is controlled to move accordingly. Compared to existing technologies, this method does not require the coordinated operation of multiple sensors or complex recognition algorithms. Instead, it only requires a single sensor or a class of sensors that can perform the same function to collect the obstacle's cross-sectional data. By analyzing this cross-sectional data, furniture such as tables and chairs can be identified. The entire recognition process is efficient and rapid. Furthermore, the robot can be controlled to perform cleaning tasks based on a corresponding movement strategy according to the characteristics of the obstacle.

[0043] 2. This invention determines whether an obstacle is furniture such as tables and chairs by analyzing the width and distribution of the cross section. The algorithm is simple and can achieve accurate identification.

[0044] 3. The present invention can also determine the type of obstacle based on the height of the obstacle's bottom surface from the ground and the bottom area of ​​the obstacle, thereby effectively identifying furniture such as beds and sofas, and also quickly completing the cleaning work in the area where such obstacles are located;

[0045] 4. Since the bottom surfaces of furniture such as sofas and beds are usually close to the ground, the present invention first performs a preliminary judgment on the height of the obstacle's bottom surface from the ground. When the height meets the requirements, the obstacle's bottom surface area is further judged. Only when the bottom surface area meets the preset requirements is the current obstacle determined to be a bed or sofa. The entire judgment process ensures the accuracy of obstacle recognition;

[0046] 5. When the current obstacle is determined to be a sofa, bed, etc., considering that the bottom of such obstacles is an area that is usually difficult to reach, the cleaning mode is changed to the enhanced cleaning mode to control the robot to clean the area more cleanly;

[0047] 6. When it is determined that the current obstacle is a table or chair, the edges of the obstacle that are easily overlooked and prone to dirt accumulation (i.e., the edges where the legs of the table and chair touch the ground) are cleaned first, and then the entire ground area is cleaned to ensure the cleaning effect of the area;

[0048] 7. The present invention also realizes the marking of the location of obstacles, so that when the obstacle is encountered again in the future, the type can be quickly determined based on the pre-stored information to achieve cleaning work. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 is an exemplary flow chart of a robot control method according to an embodiment of the present disclosure;

[0051] Figure 2 is a schematic structural diagram of a robot control device according to an embodiment of the present disclosure;

[0052] Figure 3 Schematic diagram of the structure of a robot according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0054] As described in the background, when identifying common objects like tables, chairs, sofas, and beds, existing robots typically utilize two different sensors to separately acquire information such as object type and distance. Acquiring distance information typically involves using a range-finding sensor or monocular estimation to calculate the object's position, but this approach has certain drawbacks. For larger pieces of furniture, the angle and mounting position of sensors like cameras may prevent them from capturing certain key features of the object, resulting in inaccurate object identification and potentially inaccurate position estimation.

[0055] Based on this, the applicant creatively came up with the idea of ​​using a depth camera to acquire point cloud data of obstacles for analysis and identification. Because different furniture features differ, for tables and chairs, point cloud data of their leg cross-sections is used for identification and judgment. For beds and sofas, point cloud data such as the height from the edge to the bottom and the bottom surface area are used for identification and judgment. This allows for cleaning of areas where different types of furniture are located.

[0056] Figure 1 An exemplary flow chart of a robot control method according to an embodiment of the present disclosure is shown. The robot control method is described in detail as follows:

[0057] Step 101: Obtain obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of the obstacle's cross section.

[0058] The obstacle information can be collected by a sensor element mounted on the robot body. In this embodiment, a depth camera is used as the sensor element, specifically including a structured light camera, a time-of-flight camera, etc. It should be understood that those skilled in the art can select a corresponding depth camera based on actual needs, and are not limited to structured light cameras and time-of-flight cameras. In this embodiment, the depth camera is mounted directly in front of the robot to obtain information about the area in front of the robot.

[0059] Furthermore, the cross-section described in this embodiment refers to a graphic representation of the outer surface of an obstacle captured within the sensor's reach. For example, if the obstacle is a tall column (e.g., 2 meters), the sensor cannot capture the entire column within its reach, only capturing information from a portion of it. Therefore, the captured cross-section of the portion of the column is rectangular. If the obstacle is a door, the cross-section captured within the sensor's reach is also rectangular, differing from the aforementioned column in that the two cross-sections differ in size.

[0060] The following uses a structured light camera as an example to illustrate the specific process of obtaining obstacle information:

[0061] When a structured light camera is installed directly in front of the robot, if there is a table as an obstacle in front of the robot, first, the projector of the structured light camera actively transmits structural information to the surface of the obstacle (the structural information can be laser stripes, Gray code, sinusoidal stripes, etc.). Since the legs of the table are usually long, the structured light camera cannot project onto the table surface and can only project onto the surface of the table legs; then, the surface of the table legs is photographed through its camera to obtain a structured light image of the table legs; finally, the obtained structured light image of the table legs is processed to obtain point cloud data of the cross section of the table legs.

[0062] When using a TOF camera, unlike structured light technology, TOF technology emits a continuous "area light source." Therefore, light will reflect off impenetrable objects. By recording the time it takes for the reflected light to reach the receiver, and given the speed and wavelength of light, the robot can quickly calculate the current distance from the table leg, creating a 3D image of the leg. This image is then converted into point cloud data representing the leg's cross-section.

[0063] It can be seen that whether using a structured light camera or a TOF camera, the depth image of the table leg can be acquired. After the coordinate change, the depth image can be converted into point cloud data of the cross section of the table leg, which is convenient for subsequent analysis and processing using the point cloud data of the cross section.

[0064] Step 102: Determine whether there is an obstacle that meets a preset first type based on the point cloud data of the cross section of the obstacle.

[0065] In some embodiments, determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle specifically includes:

[0066] Based on the point cloud data of the cross section of the obstacle, all cross sections whose cross section widths meet a preset first threshold range are extracted;

[0067] Obtaining the distribution positions of all cross sections whose cross section widths meet a preset first threshold range and performing analysis and processing;

[0068] When it is determined that the distribution of the cross sections meets the preset distribution condition, it is determined that there is an obstacle that meets the preset first type.

[0069] In this embodiment, the first type is furniture such as tables and chairs. Specifically, when the robot is cleaning, there may be multiple obstacles in front of it. To achieve accurate identification, when obtaining point cloud data of the cross sections of different obstacles, this data can be initially screened to extract all cross sections whose cross-sectional widths meet a preset first threshold range. For example, to identify furniture such as tables and chairs, the first threshold range can be set to 0-10 cm. When the width of the obstacle's cross section falls within this range, it can be preliminarily considered that the current obstacle belongs to the object to be identified.

[0070] After initially screening out obstacles, the distribution of their cross-sections is analyzed for accurate identification. For example, if an obstacle has only a single cross-section, it clearly does not belong to the furniture category of tables and chairs, and is therefore excluded. Only when the cross-section distribution satisfies a predefined distribution can it be determined that an obstacle of the first type exists, i.e., that the obstacle is considered a furniture category of tables and chairs.

[0071] The above-mentioned determination that the distribution of the cross section meets the preset distribution situation specifically includes:

[0072] Determining that the distribution of at least a portion of the cross section of the obstacle forms a rectangle or triangle of a predetermined size;

[0073] The above determination of the presence of an obstacle meeting the preset first type includes:

[0074] The obstacles corresponding to the cross-sections of a rectangle or triangle of a preset size are determined as obstacles meeting the preset first type.

[0075] In a home setting, tables and chairs are typically constructed with four or three legs, so their corresponding cross-sections must also form a rectangle or triangle. Furthermore, the size of the rectangle or triangle must meet certain requirements, such as the side length (the straight-line distance between cross-sections) being between 40 and 80 cm. When at least part of the cross-section of an obstacle forms a rectangle or triangle of a preset size, the obstacle corresponding to the cross-section of the preset rectangle or triangle can be determined to meet the preset first type of obstacle, i.e., a table or chair.

[0076] It should be noted that after initially screening out obstacles, the obstacles can also be classified based on cross-sectional width. When different types of obstacles are determined to exist, it is determined whether the distribution of the cross sections of the different types of obstacles meets the preset distribution conditions.

[0077] For example, when an obstacle in front of the robot meets the first threshold range but has a different cross-sectional width, it can be further classified based on the cross-sectional width, and the distribution of each obstacle can be determined after classification. This has the effect of speeding up the processing process compared to analyzing the distribution of all data at once. In addition, it can further distinguish obstacles. For some furniture with easily changing positions (such as chairs), it may not be necessary to mark their current position to avoid affecting subsequent judgments.

[0078] The present invention determines whether an obstacle is furniture such as a table or chair by analyzing the width and distribution of the cross section. The algorithm is simple and can achieve accurate identification.

[0079] Step 103: When it is determined that there is an obstacle that meets the preset first type, a corresponding movement strategy is obtained and the robot is controlled to perform cleaning work according to the movement strategy.

[0080] In some embodiments, controlling the robot to perform cleaning work according to the movement strategy specifically includes:

[0081] The edge of the obstacle in contact with the ground is determined based on the point cloud data of the obstacle's cross section, and the robot is controlled to clean the edge of the obstacle;

[0082] The cleaning edge is determined based on the point cloud data of the cross section of the obstacle, and the robot is controlled to clean within the area determined by the cleaning edge.

[0083] For example, if the obstacle is a table, the robot will first clean the edge where the table legs touch the ground when cleaning. Preferably, the robot can be controlled to clean the above-mentioned area in a rotation manner, and then determine the cleaning edge formed by the table legs, and control the robot to clean within the area determined by the cleaning edge.

[0084] When it is determined that the current obstacle is furniture such as tables and chairs, the edges of the obstacles that are not noticed and easily accumulate dirt (i.e., the edges where the legs of the tables and chairs contact the ground) are cleaned first, and then the entire ground area is cleaned to ensure the cleaning effect of the area.

[0085] In some embodiments, the obstacle information further includes information on the height of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle determined based on the bottom surface point cloud data of the obstacle;

[0086] The robot control method of the embodiment of the present disclosure further includes:

[0087] Determining whether there is an obstacle that meets a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle;

[0088] When it is determined that there is an obstacle that meets the preset second type, a corresponding cleaning mode is obtained and the robot is controlled to perform cleaning work according to the cleaning mode.

[0089] In this embodiment, the second type is furniture such as beds and sofas. Similarly, the above obstacle information can be collected by a depth camera installed on the robot body. Specifically, it can be any one of a laser radar, a structured light camera, a time-of-flight camera, etc.

[0090] It should be noted that, considering that some large non-enclosed furniture, such as beds and sofas, are shorter and larger in area than tables and chairs, when the robot is at the bottom of the bed or sofa, it can more easily obtain the height of the edge of the bed or sofa from the ground and the bottom area of ​​the furniture. Therefore, this feature is used to design a recognition algorithm that is completely different from that of tables and chairs, so as to complete the recognition of different objects and improve the recognition effect.

[0091] In some embodiments, the determining whether there is an obstacle meeting the preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle specifically includes:

[0092] Obtaining a comparison result of the height information of the bottom surface of the obstacle from the ground and a preset second threshold range;

[0093] When the height information of the bottom surface of the obstacle from the ground is within the preset second threshold range, determining whether the bottom surface area of ​​the obstacle is within the preset third threshold range;

[0094] When the bottom surface area of ​​the obstacle is within a preset third threshold range, it is determined that there is an obstacle that meets the preset second type.

[0095] In the above embodiment, a preliminary determination is first made of the height of the obstacle's bottom surface from the ground, completing the initial screening of obstacles. For example, if the second threshold range is 15 to 30 cm, then when the obtained height of the obstacle's bottom surface from the ground is 25 cm, it can be determined that the current obstacle preliminarily meets the preset conditions. Further analysis is then performed to determine its bottom surface area. For example, if the third threshold range is 1 to 2 square meters, when the obtained bottom surface area of ​​the obstacle is 1 square meter, the specific type of the current obstacle can be determined to be furniture such as a bed or sofa. The entire processing process ensures the accuracy of obstacle judgment.

[0096] In some embodiments, the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode;

[0097] The values ​​of the operating parameters of the enhanced cleaning mode are greater than the values ​​of the operating parameters of the normal cleaning mode; the operating parameters include suction power;

[0098] Obtaining the corresponding cleaning mode and controlling the robot to perform cleaning work according to the cleaning mode specifically includes:

[0099] Get the enhanced cleaning mode and control the robot to perform cleaning work according to the enhanced cleaning mode.

[0100] Suction power is a crucial operating parameter for most cleaning robots. A high suction power yields the best results. When the obstacle is identified as a sofa or bed, the robot switches to Enhanced Cleaning mode, which deep cleans the area beneath it, taking into account the inaccessible areas.

[0101] In some embodiments, the robot control method of the embodiment of the present disclosure further includes:

[0102] When the type of the obstacle is identified, the obstacle is marked in the preset map model based on the determined location information of the obstacle.

[0103] The present invention also realizes the marking of obstacles, so that when the obstacle is encountered again in the future, the type can be quickly determined according to the pre-stored information to realize the cleaning work.

[0104] The present invention uses point cloud data of the obstacle's cross section to determine the type of obstacle currently encountered, and controls the robot to achieve corresponding movement after determining the type. Compared with the existing technology, there is no need for too many sensors to work together, nor is there a need to use complex recognition algorithms. It is only necessary to use a certain type or a certain type of sensor that can achieve the same function to collect the cross-sectional data of the above-mentioned obstacles. By analyzing the cross-sectional data, the identification of furniture such as tables and chairs can be achieved. The entire recognition process is efficient and fast. At the same time, the robot can be controlled to perform cleaning work based on the corresponding movement strategy according to the characteristics of this type of obstacle; the present invention can also determine the type of obstacle based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle, thereby achieving effective recognition of furniture such as beds and sofas, and at the same time, it can also quickly achieve cleaning work in the area where such obstacles are located.

[0105] See also Figure 2 , as a response to the above Figure 1 The implementation of the method shown provides an embodiment of a robot control device, which is similar to Figure 1 The method embodiment shown corresponds to Figure 2 As shown, the robot control device of this embodiment includes:

[0106] An acquisition module 201 is configured to acquire obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of a cross section of the obstacle;

[0107] A processing module 202 is configured to determine whether there is an obstacle meeting a preset first type based on point cloud data of a cross section of the obstacle;

[0108] The control module 203 is configured to obtain a corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy when it is determined that there is an obstacle that meets the preset first type.

[0109] In some embodiments, the processing module 202 is specifically configured to:

[0110] Based on the point cloud data of the cross section of the obstacle, all cross sections whose cross section widths meet a preset first threshold range are extracted;

[0111] Obtaining the distribution positions of all cross sections whose cross section widths meet a preset first threshold range and performing analysis and processing;

[0112] When it is determined that the distribution of the cross sections meets the preset distribution condition, it is determined that there is an obstacle that meets the preset first type.

[0113] In some embodiments, the processing module 202 is further configured to:

[0114] Determining that the distribution of at least a portion of the cross section of the obstacle forms a rectangle or triangle of a predetermined size;

[0115] The obstacles corresponding to the cross-sections of a rectangle or triangle of a preset size are determined as obstacles meeting the preset first type.

[0116] In some embodiments, the obstacle information further includes information on the height of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle determined based on the bottom surface point cloud data of the obstacle;

[0117] The processing module 202 is further configured to:

[0118] Determining whether there is an obstacle that meets a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle;

[0119] The control module 203 is further configured to:

[0120] When it is determined that there is an obstacle that meets the preset second type, a corresponding cleaning mode is obtained and the robot is controlled to perform cleaning work according to the cleaning mode.

[0121] In some embodiments, the processing module 202 is further configured to:

[0122] Obtaining a comparison result of the height information of the bottom surface of the obstacle from the ground and a preset second threshold range;

[0123] When the height information of the bottom surface of the obstacle from the ground is within the preset second threshold range, determining whether the bottom surface area of ​​the obstacle is within the preset third threshold range;

[0124] When the bottom surface area of ​​the obstacle is within a preset third threshold range, it is determined that there is an obstacle that meets the preset second type.

[0125] In some embodiments, the cleaning mode includes a normal cleaning mode and an enhanced cleaning mode;

[0126] The values ​​of the operating parameters of the enhanced cleaning mode are greater than the values ​​of the operating parameters of the normal cleaning mode; the operating parameters include suction power;

[0127] The control module 203 is further configured to obtain an enhanced cleaning mode and control the robot to perform cleaning work according to the enhanced cleaning mode.

[0128] In some embodiments, the control module 203 is further configured to:

[0129] The edge of the obstacle in contact with the ground is determined based on the point cloud data of the obstacle's cross section, and the robot is controlled to clean the edge of the obstacle;

[0130] The cleaning edge is determined based on the point cloud data of the cross section of the obstacle, and the robot is controlled to clean within the area determined by the cleaning edge.

[0131] In some embodiments, the apparatus further includes a marking module 204 configured to:

[0132] When the type of the obstacle is identified, the obstacle is marked in the preset map model based on the determined location information of the obstacle.

[0133] Figure 3 A schematic diagram of a robot provided by one embodiment of the present invention is disclosed. Figure 3 As shown, the robot includes: a memory 31, a processor 32, and a computer program 33 stored in the memory 31 and executable on the processor 32, such as a program for a robot control method. When the processor 32 executes the computer program 33, the steps in the above-mentioned embodiment of the robot control method are implemented, such as Figure 1 Alternatively, when the processor 32 executes the computer program 33, the functions of each module in the above-mentioned embodiment of the robot control device are realized, for example Figure 2 The functions of the modules 201 to 204 are shown. In addition, the robot further comprises a measuring element 34 and a motion unit 35 .

[0134] The measuring element 34 may be a radar, a sensor, etc., wherein the radar may be a laser radar or an infrared radar, and the laser radar may be a single-line radar or a multi-line radar.

[0135] The motion unit 35 is used to control the motion of the robot.

[0136] The processor 32 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0137] The memory 31 may be an internal storage unit of the robot, such as a hard drive or memory of the robot. The memory 31 may also be an external storage device of the robot, such as a plug-in hard drive equipped on the robot, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 31 may include both an internal storage unit of the robot and an external storage device. The memory 31 is used to store the computer program and other programs and data required by the robot. The memory 31 may also be used to temporarily store data that has been output or is about to be output.

[0138] Those skilled in the art will understand that Figure 3 It is only an example of a robot and does not constitute a limitation of a robot. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the robot may also include input and output devices, network access devices, buses, etc.

[0139] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0141] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0142] The program portion of the technology can be considered a "product" or "article of manufacture" in the form of executable code and / or related data, implemented or implemented through computer-readable media. Tangible, permanent storage media can include any memory or storage used by a computer, processor, or similar device or related module. For example, various semiconductor memories, tape drives, disk drives, or any similar device that can provide storage for software.

[0143] All or part of the software may sometimes be communicated over a network, such as the Internet or other communications network. Such communications can load the software from one computer device or processor to another. Therefore, another medium capable of transmitting software elements may also be used as a physical connection between local devices, such as light waves, radio waves, electromagnetic waves, etc., which are transmitted through cables, optical cables or air. Physical media used to carry data, such as cables, wireless connections or optical cables and the like, can also be considered as the medium that carries the software. As used herein, unless limited to tangible "storage" media, other terms referring to computer or machine "readable media" refer to media that participate in the process of executing any instructions by the processor.

[0144] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above embodiments merely illustrate several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A robot control method, characterized in that: The method comprises: Obtaining obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of a cross section of the obstacle; determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle; When it is determined that there is an obstacle that meets the preset first type, a corresponding movement strategy is obtained and the robot is controlled to perform cleaning work according to the movement strategy. The determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle specifically includes: Extracting, based on the point cloud data of the cross section of the obstacle, all cross sections whose cross section widths satisfy a preset first threshold range; Obtaining the distribution positions of all cross sections whose cross section widths satisfy a preset first threshold range and performing analysis and processing; When it is determined that the distribution of the cross sections meets the preset distribution condition, it is determined that there is an obstacle that meets the preset first type.

2. The method according to claim 1, characterized in that The determining whether the distribution of the cross section meets the preset distribution condition specifically includes: Determining that the distribution of at least a portion of the cross section of the obstacle forms a rectangle or triangle of a predetermined size; The determining that there is an obstacle that meets a preset first type includes: The obstacles corresponding to the cross-sections of a rectangle or triangle of a preset size are determined as obstacles meeting the preset first type.

3. The method according to claim 1, wherein the obstacle information further includes information on the height of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle determined based on the bottom surface point cloud data of the obstacle; The method further comprises: Determining whether there is an obstacle that meets a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle; When it is determined that there is an obstacle that meets the preset second type, a corresponding cleaning mode is acquired and the robot is controlled to perform cleaning work according to the cleaning mode.

4. The method according to claim 3, wherein determining whether there is an obstacle meeting a preset second type based on the height information of the bottom surface of the obstacle from the ground and the bottom surface area of ​​the obstacle specifically comprises: Obtaining a comparison result of the height information of the bottom surface of the obstacle from the ground and a preset second threshold range; When the height information of the bottom surface of the obstacle from the ground is within a preset second threshold range, determining whether the bottom surface area of ​​the obstacle is within a preset third threshold range; When the bottom surface area of ​​the obstacle is within a preset third threshold range, it is determined that there is an obstacle that meets the preset second type.

5. The method according to claim 3 or 4, characterized in that The cleaning mode includes a normal cleaning mode and an enhanced cleaning mode; The numerical value of the operating parameter of the enhanced cleaning mode is greater than the numerical value of the operating parameter of the normal cleaning mode; The operating parameters include suction power; The obtaining of the corresponding cleaning mode and controlling the robot to perform cleaning work according to the cleaning mode specifically includes: An enhanced cleaning mode is acquired and the robot is controlled to perform cleaning work according to the enhanced cleaning mode.

6. The method according to any one of claims 1 to 4, characterized in that Controlling the robot to perform cleaning work according to the movement strategy specifically includes: determining an edge of the obstacle in contact with the ground based on point cloud data of a cross section of the obstacle, and controlling the robot to clean the edge of the obstacle; A cleaning edge is determined based on the point cloud data of the cross section of the obstacle, and the robot is controlled to perform cleaning within the area determined by the cleaning edge.

7. The method according to any one of claims 1 to 4, characterized in that The method further comprises: When the type of the obstacle is identified, the obstacle is marked in a preset map model based on the determined location information of the obstacle.

8. A robot control device, characterized in that: The device comprises: An acquisition module, configured to acquire obstacle information during the robot's movement; wherein the obstacle information includes point cloud data of a cross section of the obstacle; a processing module, configured to determine whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle; A control module is used to obtain a corresponding movement strategy and control the robot to perform cleaning work according to the movement strategy when it is determined that there is an obstacle that meets the preset first type. The determining whether there is an obstacle meeting a preset first type based on the point cloud data of the cross section of the obstacle specifically includes: Extracting, based on the point cloud data of the cross section of the obstacle, all cross sections whose cross section widths satisfy a preset first threshold range; Obtaining the distribution positions of all cross sections whose cross section widths satisfy a preset first threshold range and performing analysis and processing; When it is determined that the distribution of the cross sections meets the preset distribution condition, it is determined that there is an obstacle that meets the preset first type.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images