Robot control method and device

Abstract

The embodiments of this specification provide a robot control method and device, wherein the robot control method includes controlling the robot to perform a cleaning task on a work area according to a pre-established partition map; when it is determined that the robot and a target object in the partition map meet a preset distance condition, controlling the robot to clean the work area according to the distance relationship between the robot and the target object; when controlling the robot to clean the work area based on a pre-established partition map in the work area, the robot control method can control the robot to selectively clean the target object based on the preset distance relationship between the robot and the target object, thereby realizing a more humane cleaning method, and through the robot's avoidance of the target object, collision protection of the target object is realized, thereby improving the user experience.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and more particularly to a robot control method. One or more embodiments of this specification also relate to a robot control device, a robot, and a computer-readable storage medium. Background Art

[0002] Existing robot vacuums have limited cleaning options. In automatic mode, they can only clean the entire work area (e.g., a room) or select specific areas within the work area. For example, even if someone is resting in a room and the door is closed, the robot vacuum will continue cleaning outside, potentially colliding with the door and disturbing the rest of the person, making it difficult to meet the personalized cleaning needs of a family. Furthermore, furniture such as sofas, beds, and wardrobes in a room are generally made of lacquered wood. If they are scratched and bumped by the robot vacuum for a long time, they will cause damage, resulting in a poor user experience.

[0003] Therefore, there is an urgent need to provide a robot control method that can meet the personalized cleaning needs of the family and improve the user experience. Summary of the Invention

[0004] In view of this, the present invention provides a robot control method. One or more embodiments of the present invention also relate to a robot control device, a robot, and a computer-readable storage medium to address technical deficiencies in the prior art.

[0005] According to a first aspect of an embodiment of this specification, there is provided a robot control method, comprising:

[0006] Controlling the robot to perform cleaning tasks on the work area according to a pre-established partition map;

[0007] When it is determined that the robot and the target object in the partition map meet a preset distance condition, controlling the robot to clean the working area using a first cleaning strategy;

[0008] The first cleaning strategy includes controlling the robot to perform a cleaning task on the working area according to a distance relationship between the robot and the target object.

[0009] Optionally, before controlling the robot to perform a cleaning task on the work area according to a pre-established partition map, the method further includes:

[0010] Upon receiving the initial start-up instruction, starting the robot and controlling the robot to clean the working area using a second cleaning strategy;

[0011] Collecting environmental information of the working area through the visual acquisition device of the robot;

[0012] Dividing the working area into regions based on environmental information of the working area to construct a partition map of the working area;

[0013] The second cleaning strategy includes controlling the robot to perform a cleaning task on the working area through a cleaning route preset in the robot.

[0014] Optionally, after constructing the partition map of the work area, the method further includes:

[0015] Identify the target object of each partition in the partition map and mark the target object.

[0016] Optionally, identifying the target object of each partition in the partition map includes:

[0017] Controlling the robot to collect images of objects in each partition according to the partition map;

[0018] determining an object label of the object based on the collected object image;

[0019] The object tag is matched with a preset object tag, and the object corresponding to the successfully matched object tag is determined as the target object.

[0020] Optionally, determining the object label of the object according to the collected object image includes:

[0021] Inputting the collected object image into an image recognition model, and the image recognition model outputting an object label corresponding to the object image; or

[0022] The collected object image is sent to a terminal that is in communication with the robot, and an object label set for the object by a user at the terminal according to the object image is received.

[0023] Optionally, matching the object tag with a preset object tag and determining the object corresponding to the successfully matched object tag as the target object includes:

[0024] Matching the object tag with a first preset object tag, and determining the object corresponding to the successfully matched object tag as the first target object; and

[0025] The object tag is matched with a second preset object tag, and an object corresponding to the successfully matched object tag is determined as a second target object.

[0026] Optionally, when it is determined that the robot and the target object in the partition map meet a preset distance condition, controlling the robot to clean the working area using a first cleaning strategy includes:

[0027] In a case where the first target object is captured by the visual acquisition device of the robot, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot;

[0028] When it is determined that the state of the first target object satisfies a preset cleaning condition, determining a first cleaning distance between the robot and the second target object by a distance sensor of the robot;

[0029] When the first cleaning distance satisfies a first preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the second target object.

[0030] Optionally, after determining the state of the first target object, the method further includes:

[0031] When it is determined that the state of the first target object does not meet the preset cleaning condition, determining a second cleaning distance between the robot and the first target object by a distance sensor of the robot;

[0032] When the second cleaning distance satisfies a second preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the first target object.

[0033] Optionally, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by a visual acquisition device of the robot includes:

[0034] Capturing a panoramic image of the partition where the first target object is located by a visual acquisition device of the robot, and extracting a top image of the current working area of ​​the partition where the first target object is located from the panoramic image;

[0035] Determine, based on the partition map, a top image of an initial working area of ​​the partition where the first target object is located;

[0036] The current working area top image is compared with the original working area top image to determine the state of the first target object.

[0037] Optionally, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by a visual acquisition device of the robot includes:

[0038] Capturing a panoramic image of the partition where the first target object is located by using a visual acquisition device of the robot;

[0039] Inputting the panoramic image into the image recognition model, and the image recognition model outputting an image label corresponding to the panoramic image;

[0040] In a case where the image tag matches the carrier object of the first target object, determining positions of the first target object and the carrier object in the panoramic image;

[0041] The state of the first target object is determined based on the positional relationship between the first target object and the bearing object in the panoramic image.

[0042] According to a second aspect of the embodiments of this specification, there is provided a robot control device, comprising:

[0043] a control module configured to control the robot to perform a cleaning task on a work area according to a pre-established partition map;

[0044] a cleaning module configured to control the robot to clean the working area using a first cleaning strategy when it is determined that the robot and the target object in the partition map meet a preset distance condition;

[0045] The first cleaning strategy includes controlling the robot to perform a cleaning task on the working area according to a distance relationship between the robot and the target object.

[0046] Optionally, the device further includes:

[0047] a start module configured to start the robot upon receiving an initial start instruction and control the robot to clean the working area using a second cleaning strategy;

[0048] an information collection module, configured to collect environmental information of the working area through a visual collection device of the robot;

[0049] a map construction module configured to divide the work area into regions based on environmental information of the work area to construct a partition map of the work area;

[0050] The second cleaning strategy includes controlling the robot to perform a cleaning task on the working area through a cleaning route preset in the robot.

[0051] Optionally, the device further includes:

[0052] The recognition module is configured to recognize the target object of each partition in the partition map and mark the target object.

[0053] Optionally, the identification module is further configured to:

[0054] Controlling the robot to collect images of objects in each partition according to the partition map;

[0055] determining an object label of the object based on the collected object image;

[0056] The object tag is matched with a preset object tag, and the object corresponding to the successfully matched object tag is determined as the target object.

[0057] Optionally, the identification module is further configured to:

[0058] Inputting the collected object image into an image recognition model, and the image recognition model outputting an object label corresponding to the object image; or

[0059] The collected object image is sent to a terminal that is in communication with the robot, and an object label set for the object by a user at the terminal according to the object image is received.

[0060] Optionally, the identification module is further configured to:

[0061] Matching the object tag with a first preset object tag, and determining the object corresponding to the successfully matched object tag as the first target object; and

[0062] The object tag is matched with a second preset object tag, and an object corresponding to the successfully matched object tag is determined as a second target object.

[0063] Optionally, the cleaning module is further configured to:

[0064] In a case where the first target object is captured by the visual acquisition device of the robot, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot;

[0065] When it is determined that the state of the first target object satisfies a preset cleaning condition, determining a first cleaning distance between the robot and the second target object by a distance sensor of the robot;

[0066] When the first cleaning distance satisfies a first preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the second target object.

[0067] Optionally, the device further includes:

[0068] a distance determination module configured to determine a second cleaning distance between the robot and the first target object by using a distance sensor of the robot when it is determined that the state of the first target object does not meet a preset cleaning condition;

[0069] The task execution module is configured to control the robot to perform a cleaning task on the working area according to the distance relationship between the robot and the first target object when the second cleaning distance meets a second preset distance condition.

[0070] Optionally, the cleaning module is further configured to:

[0071] Capturing a panoramic image of the partition where the first target object is located by a visual acquisition device of the robot, and extracting a top image of the current working area of ​​the partition where the first target object is located from the panoramic image;

[0072] Determine, based on the partition map, a top image of an initial working area of ​​the partition where the first target object is located;

[0073] The current working area top image is compared with the original working area top image to determine the state of the first target object.

[0074] Optionally, the cleaning module is further configured to:

[0075] Capturing a panoramic image of the partition where the first target object is located by using a visual acquisition device of the robot;

[0076] Inputting the panoramic image into the image recognition model, and the image recognition model outputting an image label corresponding to the panoramic image;

[0077] In a case where the image tag matches the carrier object of the first target object, determining positions of the first target object and the carrier object in the panoramic image;

[0078] The state of the first target object is determined based on the positional relationship between the first target object and the bearing object in the panoramic image.

[0079] According to a third aspect of the embodiments of this specification, a robot is provided, comprising:

[0080] A mechanical body, wherein the mechanical body is provided with a memory and a processor;

[0081] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the instructions are executed by the processor, the steps of the robot control method are implemented.

[0082] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer instructions, and when the instructions are executed by a processor, the steps of the robot control method are implemented.

[0083] One embodiment of the present specification implements a robot control method and device, wherein the robot control method includes controlling the robot to perform a cleaning task on a work area according to a pre-established partition map; when it is determined that the robot and a target object in the partition map meet a preset distance condition, controlling the robot to clean the work area according to the distance relationship between the robot and the target object; when the robot cleans the work area based on the pre-established partition map in the work area, the robot control method can control the robot to selectively clean the target object based on the preset distance relationship between the robot and the target object, thereby realizing a more humane cleaning method, and through the robot's avoidance of the target object, collision protection of the target object is realized, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 This is an example diagram of a specific application scenario of a robot control method provided by an embodiment of this specification;

[0085] Figure 2 is a flow chart of a robot control method provided by one embodiment of this specification;

[0086] Figure 3 This is a schematic diagram of a robot cleaning process with a door closed in a robot control method provided in one embodiment of this specification;

[0087] Figure 4 This is a schematic diagram of two cleaning modes of a robot with a door closed in a robot control method provided in one embodiment of this specification;

[0088] Figure 5 is a schematic diagram of a top image of a current working area of ​​a partition where a first target object is located in a robot control method provided by one embodiment of this specification;

[0089] Figure 6 is a schematic diagram of a top image of an initial working area of ​​a partition where a first target object is located in a robot control method provided in one embodiment of this specification;

[0090] Figure 7This is a process flow chart of a robot control method provided by one embodiment of this specification;

[0091] Figure 8 This is a schematic structural diagram of a robot control device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0092] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0093] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0094] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0095] First, the terms involved in one or more embodiments of this specification are explained.

[0096] Furniture: Household items including beds, cabinets, tables, chairs, coffee tables, etc.

[0097] Floor plan: A spatial layout diagram of a house, that is, a diagram that describes the use function, corresponding position, and size of each independent space. When used specifically, the floor plan.

[0098] This specification relates to a robot control method. One or more embodiments of this specification also relate to a robot control device, a robot, and a computer-readable storage medium, which are described in detail in the following embodiments.

[0099] See also Figure 1 , Figure 1 An example diagram showing a specific application scenario of a robot control method provided by an embodiment of this specification is shown.

[0100] Take the robot as a sweeping robot and the working area as a room as an example. Figure 1 The application scenario includes a sweeping robot 102 and a room 104. Specifically, when the control end of the sweeping robot receives the initial start-up instruction, it starts the sweeping robot and controls the sweeping robot to walk along the wall of the room to clean the room for the first time. At the same time, the visual acquisition device of the sweeping robot obtains various environmental information of the room (such as the area of ​​the room, the furniture placed, the position of the furniture, and the position of the door of the room, etc.), and then uses the various environmental information of the room obtained to construct a map of the room, and constructs a partitioned floor plan based on the information of the door of each room; identifies and labels the target furniture in each partition according to the floor plan, such as the sofa in the living room, the dining table in the dining room, the wardrobe and the bed in the bedroom, etc.; and After the target furniture in the room is identified and marked, if the sweeping robot is controlled again to perform a global cleaning of the room based on the floor plan, when the sweeping robot reaches the vicinity of the marked target furniture, it will automatically avoid the preset distance and clean the marked target furniture, where the preset distance is 5 cm, 8 cm or 10 cm, etc., and when the sweeping robot reaches the door of each partition, it will first determine whether the door is open or closed based on the image information of the door collected by the visual acquisition device. If the door is open, the sweeping robot enters the corresponding room for cleaning. If the door is closed, the sweeping robot cleans the area greater than 10 cm or 20 cm from the door to avoid collision with the door.

[0101] The robot control method provided in the embodiments of this specification is applied to the scene of a sweeping robot cleaning a room. By controlling the sweeping robot to avoid the furniture in the room, the furniture is protected from collision. When the sweeping robot reaches the vicinity of the door of the room, it independently judges the switch status of the door and chooses to enter the room for cleaning or avoid cleaning. This further avoids the sweeping robot from colliding with the door when cleaning outside the door and generating noise, thereby achieving a more humane cleaning method.

[0102] See also Figure 2 , Figure 2 A flowchart of a robot control method provided according to an embodiment of the present specification is shown, which includes the following steps.

[0103] Step 202: Control the robot to perform a cleaning task on the work area according to a pre-established partition map.

[0104] In specific implementation, the robot control method provided in the embodiments of this specification can be applied to any scenario in which a robot cleans a work area, such as a scenario in which a robot sweeps the work area, a scenario in which a robot disinfects the work area, or a scenario in which a robot washes the floor of the work area, etc. This specification does not impose any restrictions on this; then based on different application scenarios, the type of robot is also different, for example, in a cleaning scenario, the robot can be a sweeping robot; in a disinfection scenario, the robot can be a disinfection robot; and in a floor washing scenario, the robot can be a floor washing robot.

[0105] The working area includes but is not limited to cleanable areas such as rooms, factories, schools or office buildings.

[0106] For ease of understanding, the following embodiments are described in detail using the robot control method in a scenario where the robot cleans the room. In this case, the robot can be understood as a sweeping robot, and the executor of the robot control method can be understood as the control component of the robot, such as the control motherboard.

[0107] Specifically, before controlling the robot to perform the cleaning task on the work area according to the pre-established partition map, the method further includes:

[0108] Upon receiving the initial start-up instruction, starting the robot and controlling the robot to clean the working area using a second cleaning strategy;

[0109] Collecting environmental information of the working area through the visual acquisition device of the robot;

[0110] Dividing the working area into regions based on environmental information of the working area to construct a partition map of the working area;

[0111] The second cleaning strategy includes controlling the robot to perform a cleaning task on the working area through a cleaning route preset in the robot.

[0112] Among them, the initial start-up instruction can be an initial start-up instruction implemented by touching the start button set on the robot, or an initial start-up instruction implemented by touching the start control set on the display panel of the robot, or an initial start-up instruction implemented by receiving a start-up voice recognizable by the robot, etc.; the preset cleaning route can be a cleaning route of any pre-set mode, such as a bow-shaped cleaning route or an S-shaped cleaning route, etc.

[0113] Specifically, when receiving the initial start-up instruction, the robot is started and the visual acquisition device of the robot is turned on, wherein the visual acquisition device includes but is not limited to a camera, a camera, etc.; after that, the robot is controlled to clean the working area for the first time through a cleaning route preset in the robot, and at the same time, the environmental information of the working area is collected through the visual acquisition device of the robot, wherein the environmental information of the working area includes but is not limited to information such as the area of ​​the working area, the objects placed, and the position of the objects. Taking the working area as a room as an example, the environmental information of the room may include the area of ​​each small room, the furniture placed in the room, the position of the furniture, and the position of the door of each small room, etc.

[0114] Specifically, after collecting the environmental information of the work area, the work area is divided into areas, that is, the work area is divided into multiple small work areas according to the collected environmental information of the work area; for example, the room is divided into a living room area, a dining room area, a bedroom area, a kitchen area, a bathroom area, and a balcony area, etc. according to the collected environmental information.

[0115] Then, a partition map of the work area is constructed based on the divided work area, that is, the work area is presented in the form of a partition map. In the case where the work area is a room, the partition map can be understood as a floor plan. Through the partition map, it can be determined which area is the living room of the room, which area is the dining room of the room, which area is the bedroom of the room, and so on.

[0116] Continuing with the above example, if the robot is controlled to walk along the wall of the room to be cleaned and encounters a door, the robot enters a room from the door. At this time, the robot walks along the wall of the room and cleans it in a circle. The robot uses the visual acquisition device to collect information about the area, furniture, etc. of the room, and then comes out of the door to continue walking along the wall to clean. When encountering another door, the robot enters the room corresponding to the door in the above manner, and uses the visual acquisition device of the robot to collect environmental information about the room corresponding to the door. This process is repeated until the robot is controlled to walk around the wall in the room to be cleaned and returns to the starting point. Finally, based on all the environmental information collected about the room to be cleaned, the room to be cleaned is divided into areas to construct a partition map of the room to be cleaned. Specifically, the area division of the room to be cleaned can be achieved through the door of each room to be cleaned, and each room with a door is regarded as an area of ​​the room to be cleaned to realize the construction of the partition map of the room to be cleaned.

[0117] In specific implementation, after constructing the partition map of the work area, the target objects in each partition of the partition map are identified and marked, so that when the robot is subsequently controlled to perform the next global cleaning of the work area, when the robot collects the marked target objects, the robot avoids the target objects based on the distance relationship between the robot and the target objects in each partition. The specific implementation method is as follows:

[0118] After constructing the partition map of the work area, the method further includes:

[0119] Identify the target object of each partition in the partition map and mark the target object.

[0120] The identification of the target object in each partition can be achieved in the following ways:

[0121] The identifying the target object of each partition in the partition map includes:

[0122] Controlling the robot to collect images of objects in each partition according to the partition map;

[0123] determining an object label of the object based on the collected object image;

[0124] The object tag is matched with a preset object tag, and the object corresponding to the successfully matched object tag is determined as the target object.

[0125] Among them, the object can be understood as any object in each partition. For example, if the work area is a room, then the object can include doors and furniture in each partition, and the object tag of the object can be understood as the furniture tag of the door and furniture. Through the object tag, it can be clear whether the object is a door or furniture. If it is furniture, then what kind of furniture is it, such as a sofa, bed or wardrobe.

[0126] Specifically, the work area is divided into areas based on the environmental information of the work area to construct a partition map of the work area, and the robot is controlled to collect images of all objects in each partition according to the partition map, and then the object label of each object is determined according to the image of each object, and finally the object label is matched with the preset object label, and the object corresponding to the successfully matched object label is determined as the target object; for example, the robot is controlled to collect images of objects in a partition of the room, and the object labels of the objects are determined to be doors, beds, wardrobes, bedside tables, curtains, and chandeliers according to the images of the collected objects, and the preset object labels are doors, beds, wardrobes, and bedside tables, then the object labels are matched with the preset object labels, and the objects corresponding to the successfully matched object labels are doors, beds, wardrobes, and bedside tables, so the target objects are doors, beds, wardrobes, and bedside tables.

[0127] In the embodiment of the present specification, by capturing images of objects in each partition of the working area, the object label of the object is determined based on the image of each object, and then the object label is matched with the label of a preset object that cannot be colliding (i.e., the preset object label), and the object corresponding to the successfully matched object label is determined as the target object. Subsequently, when controlling the robot to clean the working area, the target object can be accurately avoided to avoid damage to the target object.

[0128] In specific implementation, when determining the object label of an object based on the collected image of the object, the object label of the object can be obtained quickly and accurately through a machine learning model, and the object label of the object can also be set by the user through user interaction, thereby improving the user's personalized experience. The specific implementation method is as follows:

[0129] The determining the object label of the object according to the collected object image includes:

[0130] Inputting the collected object image into an image recognition model, and the image recognition model outputting an object label corresponding to the object image; or

[0131] The collected object image is sent to a terminal that is in communication with the robot, and an object label set for the object by a user at the terminal according to the object image is received.

[0132] Among them, the image recognition model is a pre-trained image recognition model. During specific training, multiple existing images can be obtained as sample images, the real object name in each image can be used as the sample label, and then the sample image and the corresponding sample label are combined into a sample image pair. The image recognition model is obtained through training with the sample image pair.

[0133] After the image recognition model is trained and the collected image of the object is input into the image recognition model, the object label of the object corresponding to the image of the object can be obtained quickly and accurately.

[0134] In another case, in order to achieve user interaction and enhance the user's personalized experience, the collected image of the object can be sent to a terminal connected to the robot, such as a mobile phone, tablet computer, etc., and then the object label set by the user for the object based on the image of the object on the terminal is received, reflecting user interaction and enhancing the user's usage experience.

[0135] Furthermore, matching the object tag with a preset object tag and determining the object corresponding to the successfully matched object tag as the target object includes:

[0136] Matching the object tag with a first preset object tag, and determining the object corresponding to the successfully matched object tag as the first target object; and

[0137] The object tag is matched with a second preset object tag, and an object corresponding to the successfully matched object tag is determined as a second target object.

[0138] In actual use, the target object includes a first target object and a second target object. In a scenario where a robot cleans a room, the first target object may be the door of the room, and the second target object may be some furniture in the room.

[0139] Specifically, after obtaining the object tag of the object, the object tag is first matched with the first preset object tag, and the object corresponding to the successfully matched object tag is determined as the first target object. At the same time, the object tag is matched with the second preset object tag, and the object corresponding to the successfully matched object tag is determined as the second target object.

[0140] In the embodiments of this specification, the first target object and the second target object are obtained by matching the object tag with the preset object tag, so that when the robot is subsequently controlled to clean the work area, different strategies can be used to avoid obstacles for the first target object and the second target object based on the distance relationship between the robot and the first target object and the distance relationship between the robot and the second target object, thereby ensuring a personalized user experience.

[0141] Step 204: When it is determined that the robot and the target object in the partition map meet a preset distance condition, control the robot to clean the working area using a first cleaning strategy.

[0142] The first cleaning strategy includes controlling the robot to perform a cleaning task on the working area according to a distance relationship between the robot and the target object.

[0143] Specifically, after determining the first target object and the second target object, when controlling the robot to perform the cleaning task on the work area according to the partition map, the robot is controlled to clean the work area according to the distance relationship between the robot and the first target object and / or the second target object in each partition.

[0144] Specifically, when it is determined that the robot and the target object in the partition map meet a preset distance condition, controlling the robot to clean the working area using a first cleaning strategy includes:

[0145] In a case where the first target object is captured by the visual acquisition device of the robot, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot;

[0146] When it is determined that the state of the first target object satisfies a preset cleaning condition, determining a first cleaning distance between the robot and the second target object by a distance sensor of the robot;

[0147] When the first cleaning distance satisfies a first preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the second target object.

[0148] In actual applications, if the working area is a room and the first target object is a door, then the preset cleaning condition can be understood as the door being open; in addition, the first preset distance condition can be understood as the first cleaning distance being less than or equal to the first preset distance threshold, and the first preset distance threshold can be set according to actual applications. This application does not impose any restrictions on this. For example, the first preset distance threshold can be set to 5 cm, 8 cm, etc.

[0149] Continuing with the above example, taking controlling the robot to clean a room with the first target object being a door as an example, specifically, when controlling the robot to perform the cleaning task on the room according to the partition map, when the robot's visual acquisition device captures the door, the state of the door (open or closed) is determined through the panoramic image of the partition where the door is located captured by the robot's visual acquisition device. When the state of the door meets the preset cleaning condition (i.e., the door is open), the robot's distance sensor (e.g., a lidar sensor) is used to obtain the first cleaning distance between the robot's current position and the second target object. When the first cleaning distance meets the first preset distance condition (i.e., the first cleaning distance is less than or equal to the first preset distance threshold), the robot is controlled to perform the cleaning task on the working area according to the distance relationship between the robot and the second target object. The distance relationship between the robot and the second target object can be understood as the relatively fixed distance between the robot and the second target object when performing the cleaning task on the working area. For example, the robot is controlled to perform the cleaning task in a working area 10 cm away from the second target object.

[0150] In the embodiments of this specification, when controlling the robot to clean the working area, it is necessary to first determine the state of the door. Only when the door is open can the robot enter the working area through the door to perform the cleaning task. When entering the working area to perform the cleaning task, it is also necessary to determine the cleaning distance between the current position of the robot and the identified second target object. When the cleaning distance is less than or equal to the first preset distance threshold, the robot is controlled to clean the partition of the working area according to the distance relationship between the robot and the second target object. In this way, when controlling the robot to clean the working area, by identifying the state of the door, the robot will enter the working area to clean only when the door is open, thereby avoiding collision with the door and disturbing the user's rest. By identifying the target furniture in the cleaning area, the cleaning task is performed in an area fixed distance away from the target furniture, thereby realizing collision protection for the target furniture and avoiding damage to the target furniture.

[0151] When the door is closed, in order to ensure that the robot's cleaning work is carried out normally and no cleaning area is missed, the robot will be controlled to clean an area at a certain distance from the door (the first target object), so as not to collide with the door and can clean the area outside the door. The specific implementation method is as follows:

[0152] After determining the state of the first target object, the method further includes:

[0153] When it is determined that the state of the first target object does not meet the preset cleaning condition, determining a second cleaning distance between the robot and the first target object by a distance sensor of the robot;

[0154] When the second cleaning distance satisfies a second preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the first target object.

[0155] In actual applications, if the working area is a room and the first target object is a door, then the preset cleaning condition can be understood as the door being open, and failure to meet the preset cleaning condition can be understood as the door being closed; in addition, the second preset distance condition can be understood as the second cleaning distance being less than or equal to the second preset distance threshold, and the second preset distance threshold can be set according to actual applications. This application does not impose any restrictions on this. For example, the second preset distance threshold can be set to 10 cm, 12 cm, etc., and the first preset distance threshold can be the same as or different from the second preset distance threshold.

[0156] Continuing with the above example, taking controlling the robot to clean a room with the second target object being a bed as an example, specifically, when controlling the robot to perform the cleaning task on the room according to the partition map, when the robot's visual acquisition device captures a door, the state of the door (open or closed) is determined through the panoramic image of the partition where the door is located captured by the robot's visual acquisition device. When the state of the door does not meet the preset cleaning condition (i.e., the door is closed), the second cleaning distance between the robot's current position and the first target object is obtained through the robot's distance sensor (e.g., a lidar sensor). When the second cleaning distance meets the second preset distance condition (i.e., the second cleaning distance is less than or equal to the second preset distance threshold), the robot is controlled to perform the cleaning task on the working area according to the distance relationship between the robot and the first target object. The distance relationship between the robot and the first target object can be understood as the relatively fixed distance between the robot and the first target object when performing the cleaning task on the working area. For example, the robot is controlled to perform the cleaning task in a working area 12 cm away from the first target object.

[0157] See also Figure 3 , Figure 3 A schematic diagram of a cleaning robot with a door closed in a robot control method provided by one embodiment of this specification is shown.

[0158] Figure 3 The first target object 302 is a door, and the door is in a closed state. At this time, if the robot 304 is controlled to perform a cleaning task on the working area, the robot 304 will only clean the working area 10 or 20 cm away from the door to avoid colliding with the door and generating noise.

[0159] At the same time, when controlling the robot to clean the working area 10 cm away from the door, the robot's distance sensor will still be used to determine the cleaning distance between the robot's current position and the second target object to avoid the robot colliding with the target furniture in the working area.

[0160] See also Figure 4 , Figure 4 A schematic diagram shows two cleaning modes of a robot when the door is closed in a robot control method provided by an embodiment of this specification.

[0161] If the cleaning route preset in the robot is Figure 4The bow-shaped cleaning route on the left controls the robot to perform cleaning tasks on the working area. If the door is determined to be closed through the visual acquisition device, the robot is controlled to perform cleaning tasks on the working area according to the distance relationship between the robot and the door. For example, the robot is controlled to perform cleaning tasks on the working area 10 cm away from the door. Every time the robot is 10 cm away from the door, it will return to the working area 10 cm away from the door for reverse cleaning, and then perform cleaning tasks in the direction of the door according to the bow-shaped route. When it is 10 cm away from the door again, it continues to clean in the reverse direction. The robot is controlled in this way to perform cyclic cleaning of the working area, so that the final cleaning route of the robot is in a horizontal bow shape with the door, so that the robot can perform cleaning tasks on the working area 10 cm away from the door.

[0162] In another case, when the robot is controlled to perform a cleaning task on the working area based on a bow-shaped cleaning route, if it is determined through a visual acquisition device that the door is closed and the distance between the robot and the door is less than a preset distance threshold, for example, less than 10 cm, the robot's cleaning route is changed, and a bow-shaped cleaning route horizontal to the door is adopted, and the robot is controlled to perform the cleaning task on the working area according to the distance relationship between the robot and the door; finally, the robot's bow-shaped cleaning route is horizontal to the door, and the cleaning task is performed on the working area 10 cm away from the door through this bow-shaped cleaning route; that is, the first case can be simply understood as a collision return, where the robot does not change its cleaning mode when encountering a door, returns to clean when encountering the door, cleans the area outside the door, and then cleans in the direction of the door again when encountering the door, and returns again when encountering the door, repeating this cycle; and the second case can be understood as changing the robot's cleaning mode when encountering a door, and performing a cleaning task in an area 10 cm away from the door along the horizontal direction of the door.

[0163] In addition, the cleaning mode of the robot can also be set according to the area of ​​the working area. For example, when the area of ​​the working area is large, when the robot's visual acquisition device detects that there is a person in a certain partition, the robot can be controlled to perform cleaning tasks on the working area according to the first cleaning strategy of the above embodiment according to the distance relationship between the robot and the target object, thereby reducing the disturbance of noise to people. In other partitions farther away from the partition, the robot can be controlled to still perform cleaning tasks according to the second cleaning strategy, thereby achieving more comprehensive cleaning of the working area.

[0164] In another embodiment of the present specification, the determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by a visual acquisition device of the robot includes:

[0165] Capturing a panoramic image of the partition where the first target object is located by a visual acquisition device of the robot, and extracting a top image of the current working area of ​​the partition where the first target object is located from the panoramic image;

[0166] Determine, based on the partition map, a top image of an initial working area of ​​the partition where the first target object is located;

[0167] The current working area top image is compared with the original working area top image to determine the state of the first target object.

[0168] Take the first target object as an example to illustrate. Specifically, when acquiring the state of the door, the robot's visual acquisition device first collects a panoramic image of the partition where the door is located, and extracts the top image of the current working area of ​​the partition where the door is located from the panoramic image. For example, see Figure 5 , Figure 5 A schematic diagram of a top image of a current working area of ​​a partition where a first target object is located in a robot control method provided by one embodiment of the present specification is shown; and since the partition map is constructed based on the collected environmental information of the working area, the initial top image of the working area of ​​the partition where the first target object is located when the partition map is initially constructed can be determined through the partition map, for example, see Figure 6 , Figure 6 A schematic diagram of the top image of the initial working area of ​​the partition where the first target object is located in a robot control method provided in an embodiment of the present specification is shown, and then the top image of the current working area is compared with the top image of the initial working area to determine the state of the first target object.

[0169] pass Figure 6 It can be seen that the top image of the initial working area of ​​the partition where the door is located represents the state of the door being open. Figure 5 and Figure 6 By comparing the top image of the working area, it can be determined that Figure 5 The top image of the current work area in Figure 6 The initial work area top image in is different, so in Figure 6 The top image of the initial working area shows the door open. Figure 5 The top image of the current working area in the image indicates that the door is closed.

[0170] In an embodiment of the present specification, the top image of the current working area of ​​the partition where the first target object is located is compared with the top image of the initial working area of ​​the partition where the first target object is located, which is obtained when the robot first performs a cleaning task to construct a partition map. By comparing the images, it is possible to quickly determine whether the door is closed or open, thereby greatly improving the cleaning efficiency of the robot.

[0171] In addition, the state of the first target object can also be obtained by means of a machine learning model to more accurately determine the state of the first target object. The specific implementation method is as follows:

[0172] The determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot includes:

[0173] Capturing a panoramic image of the partition where the first target object is located by using a visual acquisition device of the robot;

[0174] Inputting the panoramic image into the image recognition model, and the image recognition model outputting an image label corresponding to the panoramic image;

[0175] In a case where the image tag matches the carrier object of the first target object, determining positions of the first target object and the carrier object in the panoramic image;

[0176] The state of the first target object is determined based on the positional relationship between the first target object and the bearing object in the panoramic image.

[0177] The detailed introduction of the image recognition model can be found in the above embodiments and will not be repeated here.

[0178] In actual applications, after the robot's visual acquisition device captures a panoramic image of the partition where the first target object is located, the panoramic image is input into the image recognition model to obtain image labels corresponding to all objects in the panoramic image, such as doors, door frames, etc., and then the image labels are matched with the carrier objects of the first target object, and the state of the first target object is determined based on the positional relationship between the first target object and the carrier object in the panoramic image.

[0179] In a specific implementation, when the first target object is a door, the carrier object of the first target object is a door frame; after the panoramic image is input into the image recognition model, the image labels of all objects in the panoramic image can be obtained. If the image label matches the carrier object of the first target object, it is determined that the carrier object of the first target object exists in the panoramic image. At this time, the positions of the door and the door frame are marked in the panoramic image, and then the angle between the door and the door frame is calculated. If the angle is less than or equal to a preset angle threshold, the door is determined to be in a closed state. If the angle is greater than the preset angle threshold, the door is determined to be in an open state; wherein the preset angle threshold can be set according to actual application, for example, set to 10 degrees, 20 degrees, etc.

[0180] Generally speaking, when the door is closed, the angle between the door and the door frame is small, and when the door is open, the angle between the door and the door frame is large. In the embodiment of this specification, the open and closed states of the door are determined by calculating the angle between the door and the door frame. In this way, the state of the first target object obtained can be made more accurate.

[0181] In the embodiments of the present specification, the robot control method constructs a partition map of the working area and marks the target objects in each partition based on the partition map. When the robot cleans the working area based on the partition map of the working area, the robot can selectively clean or avoid the target object based on the preset association relationship between the robot and the target object, thereby realizing a more humane cleaning method. In addition, through the robot's avoidance of the target object, collision protection of the target object is achieved, thereby improving the user experience.

[0182] The following combined Figure 7 , taking the application of the robot control method provided in this specification in cleaning a room by a robot as an example, the robot control method is further explained. Figure 7 A processing flow chart of a robot control method provided in one embodiment of this specification is shown, which specifically includes the following steps.

[0183] Step 702: When the sweeping robot performs the cleaning task for the first time, the sweeping robot is controlled to walk along the walls of the room to clean all the rooms, and the robot's visual acquisition device is used to collect environmental information of the room to build a partition map of the room.

[0184] Step 704: Mark the target objects in each partition according to the constructed partition map, where the target objects include a bed, a sofa, a wardrobe, and a door.

[0185] Step 706: When controlling the sweeping robot to perform subsequent cleaning tasks on the room according to the partition map, when controlling the sweeping robot to clean around the door, determine whether the door is closed. If so, execute step 708; if not, execute step 712.

[0186] Step 708: Control the sweeping robot to clean only the area that is more than 10 centimeters away from the door.

[0187] Step 710: After cleaning the area at a distance greater than 10 centimeters, control the sweeping robot to leave the area around the door and control the sweeping robot to clean the room normally.

[0188] Step 712: Determine whether the sweeping robot has cleaned around the bed, sofa or wardrobe. If so, execute step 714; if not, execute step 718.

[0189] Step 714: Control the sweeping robot to clean only the area that is more than 5 cm away from the bed, sofa or wardrobe.

[0190] Step 716: After cleaning the area that is more than 5 centimeters away, control the sweeping robot to leave the area around the bed, sofa or wardrobe, and control the sweeping robot to clean the room normally.

[0191] Step 718: Control the sweeping robot to clean the entire room using the above method.

[0192] The robot control method provided in the embodiments of this specification is applied to the scenario of cleaning a room by a robot. When the sweeping robot is controlled to clean for the first time, the visual acquisition device of the sweeping robot is used to collect environmental information of the room while cleaning the room, and a floor plan of the partitioned room is constructed. Target objects such as sofas, wardrobes, and beds in the room are identified and marked according to the floor plan. When the sweeping robot is controlled to perform the next global cleaning of the room, when the sweeping robot is controlled near the door, it can automatically identify whether the door is closed or open. When the door is closed, the sweeping robot is controlled to automatically avoid it by 10 cm to avoid collision with the door and reduce noise. At the same time, when the room is cleaned globally, the furniture will be protected. When the sweeping robot is near the furniture, it can perform edge cleaning of the furniture and automatically avoid the furniture by 5 cm to avoid collision with the furniture and damage to the furniture, thereby meeting the user's personalized cleaning needs.

[0193] Corresponding to the above method embodiment, this specification also provides a robot control device embodiment, Figure 8 FIG1 shows a schematic diagram of the structure of a robot control device provided by an embodiment of this specification. Figure 8 As shown, the device includes:

[0194] The control module 802 is configured to control the robot to perform a cleaning task on the work area according to a pre-established partition map;

[0195] The cleaning module 804 is configured to control the robot to clean the working area using a first cleaning strategy when it is determined that the robot and the target object in the partition map meet a preset distance condition;

[0196] The first cleaning strategy includes controlling the robot to perform a cleaning task on the working area according to a distance relationship between the robot and the target object.

[0197] Optionally, the device further includes:

[0198] a start module configured to start the robot upon receiving an initial start instruction and control the robot to clean the working area using a second cleaning strategy;

[0199] an information collection module, configured to collect environmental information of the working area through a visual collection device of the robot;

[0200] a map construction module configured to divide the work area into regions based on environmental information of the work area to construct a partition map of the work area;

[0201] The second cleaning strategy includes controlling the robot to perform a cleaning task on the working area through a cleaning route preset in the robot.

[0202] Optionally, the device further includes:

[0203] The recognition module is configured to recognize the target object of each partition in the partition map and mark the target object.

[0204] Optionally, the identification module is further configured to:

[0205] Controlling the robot to collect images of objects in each partition according to the partition map;

[0206] determining an object label of the object based on the collected object image;

[0207] The object tag is matched with a preset object tag, and the object corresponding to the successfully matched object tag is determined as the target object.

[0208] Optionally, the identification module is further configured to:

[0209] Inputting the collected object image into an image recognition model, and the image recognition model outputting an object label corresponding to the object image; or

[0210] The collected object image is sent to a terminal that is in communication with the robot, and an object label set for the object by a user at the terminal according to the object image is received.

[0211] Optionally, the identification module is further configured to:

[0212] Matching the object tag with a first preset object tag, and determining the object corresponding to the successfully matched object tag as the first target object; and

[0213] The object tag is matched with a second preset object tag, and an object corresponding to the successfully matched object tag is determined as a second target object.

[0214] Optionally, the cleaning module 804 is further configured to:

[0215] In a case where the first target object is captured by the visual acquisition device of the robot, determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot;

[0216] When it is determined that the state of the first target object satisfies a preset cleaning condition, determining a first cleaning distance between the robot and the second target object by a distance sensor of the robot;

[0217] When the first cleaning distance satisfies a first preset distance condition, the robot is controlled to perform a cleaning task on the working area according to a distance relationship between the robot and the second target object.

[0218] Optionally, the device further includes:

[0219] a distance determination module configured to determine a second cleaning distance between the robot and the first target object by using a distance sensor of the robot when it is determined that the state of the first target object does not meet a preset cleaning condition;

[0220] The task execution module is configured to control the robot to perform a cleaning task on the working area according to the distance relationship between the robot and the first target object when the second cleaning distance meets a second preset distance condition.

[0221] Optionally, the cleaning module 804 is further configured to:

[0222] Capturing a panoramic image of the partition where the first target object is located by a visual acquisition device of the robot, and extracting a top image of the current working area of ​​the partition where the first target object is located from the panoramic image;

[0223] Determine, based on the partition map, a top image of an initial working area of ​​the partition where the first target object is located;

[0224] The current working area top image is compared with the original working area top image to determine the state of the first target object.

[0225] Optionally, the cleaning module 804 is further configured to:

[0226] Capturing a panoramic image of the partition where the first target object is located by using a visual acquisition device of the robot;

[0227] Inputting the panoramic image into the image recognition model, and the image recognition model outputting an image label corresponding to the panoramic image;

[0228] In a case where the image tag matches the carrier object of the first target object, determining positions of the first target object and the carrier object in the panoramic image;

[0229] The state of the first target object is determined based on the positional relationship between the first target object and the bearing object in the panoramic image.

[0230] In the embodiments of this specification, the robot control device can realize selective cleaning of the target object by the robot based on the preset distance relationship between the robot and the target object when controlling the robot to clean the work area based on the pre-established partition map in the work area, thereby realizing a more humane cleaning method, and through the robot's avoidance of the target object, collision protection of the target object is achieved, thereby improving the user experience.

[0231] The above is a schematic diagram of a robot control device according to this embodiment. It should be noted that the technical solution of the robot control device and the technical solution of the robot control method described above are based on the same concept. For details not described in detail in the technical solution of the robot control device, please refer to the description of the technical solution of the robot control method described above.

[0232] An embodiment of this specification further provides a robot, comprising:

[0233] A mechanical body, wherein the mechanical body is provided with a memory and a processor;

[0234] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the instructions are executed by the processor, the steps of the robot control method are implemented.

[0235] The above is a schematic scheme of a robot of this embodiment. It should be noted that the technical scheme of this robot and the technical scheme of the above-mentioned robot control method are of the same concept. For details not described in detail in the technical scheme of the robot, please refer to the description of the technical scheme of the above-mentioned robot control method.

[0236] An embodiment of the present specification further provides a computer-readable storage medium storing computer instructions, which implement the steps of the robot control method when executed by a processor.

[0237] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the robot control method described above are based on the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the robot control method described above.

[0238] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0239] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0240] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0241] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0242] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A robot control method, characterized in that: include: Controlling the robot to perform cleaning tasks on the work area according to a pre-established partition map; In a case where a first target object is captured by a visual acquisition device of the robot, determining a state of the first target object based on a panoramic image of a subarea where the first target object is located captured by the visual acquisition device of the robot, wherein the first target object is a door, and the state of the first target object is determined based on a top image of a current working area and a top image of an initial working area of ​​the subarea where the first target object is located in the panoramic image; When it is determined that the state of the first target object is the open state, determining a first cleaning distance between the robot and a second target object by a distance sensor of the robot, and when the first cleaning distance meets a first preset distance condition, controlling the robot to perform a cleaning task on the working area according to the distance relationship between the robot and the second target object, so as to avoid the robot colliding with the second target object; When it is determined that the state of the first target object is closed, the second cleaning distance between the robot and the first target object is determined by the distance sensor of the robot. When the second cleaning distance meets the second preset distance condition, the robot is controlled to perform the cleaning task on the working area according to the distance relationship between the robot and the first target object to avoid the robot colliding with the first target object.

2. The robot control method according to claim 1, characterized in that: Before controlling the robot to perform a cleaning task on the work area according to the pre-established partition map, the method further includes: Upon receiving the initial start-up instruction, starting the robot and controlling the robot to clean the working area using a second cleaning strategy; Collecting environmental information of the working area through the visual acquisition device of the robot; Dividing the working area into regions based on environmental information of the working area to construct a partition map of the working area; The second cleaning strategy includes controlling the robot to perform a cleaning task on the working area through a cleaning route preset in the robot.

3. The robot control method according to claim 2, characterized in that: After constructing the partition map of the work area, the method further includes: Identify the target object of each partition in the partition map and mark the target object.

4. The robot control method according to claim 3, characterized in that: The identifying the target object of each partition in the partition map includes: Controlling the robot to collect images of objects in each partition according to the partition map; determining an object label of the object based on the collected object image; The object tag is matched with a preset object tag, and the object corresponding to the successfully matched object tag is determined as the target object.

5. The robot control method according to claim 4, characterized in that: The determining the object label of the object according to the collected object image includes: Inputting the collected object image into an image recognition model, and the image recognition model outputting an object label corresponding to the object image; or The collected object image is sent to a terminal that is in communication with the robot, and an object label set for the object by a user at the terminal according to the object image is received.

6. The robot control method according to claim 4 or 5, characterized in that: The matching of the object tag with a preset object tag and determining an object corresponding to the successfully matched object tag as a target object includes: Matching the object tag with a first preset object tag, and determining the object corresponding to the successfully matched object tag as the first target object; and The object tag is matched with a second preset object tag, and an object corresponding to the successfully matched object tag is determined as a second target object.

7. The robot control method according to claim 1, characterized in that: The determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot includes: Capturing a panoramic image of the partition where the first target object is located by a visual acquisition device of the robot, and extracting a top image of the current working area of ​​the partition where the first target object is located from the panoramic image; Determine, based on the partition map, a top image of an initial working area of ​​the partition where the first target object is located; The current working area top image is compared with the original working area top image to determine the state of the first target object.

8. The robot control method according to claim 1, wherein: The determining the state of the first target object by using a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot includes: Capturing a panoramic image of the partition where the first target object is located by using a visual acquisition device of the robot; Inputting the panoramic image into an image recognition model, wherein the image recognition model outputs an image label corresponding to the panoramic image; In a case where the image tag matches the carrier object of the first target object, determining positions of the first target object and the carrier object in the panoramic image; The state of the first target object is determined based on the positional relationship between the first target object and the bearing object in the panoramic image.

9. A robot control device, characterized in that: include: a control module configured to control the robot to perform a cleaning task on a work area according to a pre-established partition map; The cleaning module is configured to, when a first target object is captured by a visual acquisition device of the robot, determine a state of the first target object through a panoramic image of the partition where the first target object is located captured by the visual acquisition device of the robot, wherein the first target object is a door, and the state of the first target object is determined based on a top image of a current working area and a top image of an initial working area of ​​the partition where the first target object is located in the panoramic image; when it is determined that the state of the first target object is an open state, determine a first cleaning distance between the robot and a second target object through a distance sensor of the robot, and when the first cleaning distance meets a first preset distance condition, control the robot to perform a cleaning task on the working area based on the distance relationship between the robot and the second target object, so as to avoid the robot colliding with the second target object, wherein the second target object is furniture in the working area where the robot is working through the first target object; when it is determined that the state of the first target object is a closed state, determine a second cleaning distance between the robot and the first target object through the distance sensor of the robot, and when the second cleaning distance meets a second preset distance condition, control the robot to perform a cleaning task on the working area based on the distance relationship between the robot and the first target object, so as to avoid the robot colliding with the first target object.

10. A robot, characterized in that: include: A mechanical body, wherein the mechanical body is provided with a memory and a processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the instructions are executed by the processor, the steps of the robot control method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that It stores computer instructions, which, when executed by a processor, implement the steps of the robot control method according to any one of claims 1 to 8.

Images