Electronic device and its control method

Abstract

A robot vacuum cleaner is provided. The robot vacuum cleaner includes: a camera; a memory configured to store an artificial intelligence model trained to recognize an object from an input image and shape information corresponding to each of a plurality of objects; and a processor configured to control the robot vacuum cleaner by being connected to the camera and the memory, wherein the processor is configured to input an image obtained by the camera into the artificial intelligence model to recognize an object included in the image, obtain shape information corresponding to the recognized object among the plurality of shape information stored in the memory, and set a travel path of the robot vacuum cleaner based on the shape information and size information related to the object.

Description

Technical Field

[0001] The present disclosure relates to a robotic vacuum cleaner and a control method thereof. More specifically, the present disclosure relates to a robotic vacuum cleaner for setting a travel path of the robotic vacuum cleaner and a driving method thereof. Background Art

[0002] A robotic vacuum cleaner may be a device that automatically cleans a to-be-cleaned area by sucking in foreign matters while self-driving in the to-be-cleaned area without user operation.

[0003] The robotic vacuum cleaner is equipped with various sensors to accurately and effectively detect obstacles scattered in the driving direction. The sensors provided in the robotic vacuum cleaner detect the position and distance of the obstacles, and the robotic vacuum cleaner determines the moving direction using the sensed results.

[0004] Only the method of recognizing various types of obstacles in the home has been studied, and the study of a specific method of recognizing obstacles and using them to set the travel path of the robotic vacuum cleaner is insufficient.

[0005] In particular, it is necessary to recognize obstacles and consider the shape of the obstacles to set an optimized travel path of the robotic vacuum cleaner.

[0006] The above information is presented only as background information to help understand the present disclosure. No determination has been made, nor is any assertion made, as to whether any of the above constitutes prior art with respect to the present disclosure. Summary of the Invention

[0007] Technical Problem

[0008] Aspects of the present disclosure are directed to at least solving the above problems and / or disadvantages and at least providing the advantages described below. Accordingly, one aspect of the present disclosure is to provide a robotic vacuum cleaner for recognizing obstacles and setting a travel path of the robotic vacuum cleaner and a control method thereof.

[0009] Technical Solution

[0010] Additional aspects will be set forth in part in the description which follows and in part will be obvious from the description, or may be learned by practice of the presented embodiments.

[0011] According to one aspect of the present disclosure, a robotic vacuum cleaner is provided. The robotic vacuum cleaner includes: a camera; a memory configured to store an artificial intelligence model trained to recognize objects from an input image and shape information corresponding to each of a plurality of objects; and a processor configured to control the robotic vacuum cleaner by being connected to the camera and the memory, wherein the processor is configured to input an image obtained by the camera into the artificial intelligence model to recognize an object included in the image, obtain shape information corresponding to the recognized object from among the plurality of shape information stored in the memory, and set a travel path of the robotic vacuum cleaner based on the shape information and size information related to the object.

[0012] The memory may be configured to further store size information for each shape information, wherein the processor is configured to obtain size information corresponding to the shape information based on the image, or obtain size information corresponding to the shape information based on the size information stored in the memory.

[0013] The processor may be configured to identify a planar shape corresponding to the object based on the shape information of the object, and set a travel path for avoiding the object based on the planar shape of the object.

[0014] The robotic vacuum cleaner may further include an obstacle detection sensor, wherein the processor is configured to: set a travel path for avoiding the object based on the sensing data of the obstacle detection sensor based on failure to obtain a plan view corresponding to the object.

[0015] The memory may be configured to further store information on whether there is an object to be avoided for each of the plurality of objects, wherein the processor is configured to: set a travel path to climb the object based on identifying the object as an object not to be avoided based on the information on whether there is an object to be avoided.

[0016] The processor may be configured to stop the suction operation of the robotic vacuum cleaner when climbing the object.

[0017] The memory may be configured to further store first weight value information corresponding to each object and a first region and second weight value information corresponding to each object and a second region, wherein the processor is configured to: apply the first weight value information to each of the plurality of objects to obtain first region prediction information based on recognizing a plurality of objects from an image obtained by the camera, apply the second weight value information to each of the plurality of objects to obtain second region prediction information, and identify the region where the robotic vacuum cleaner is located as either the first region or the second region based on the first region prediction information and the second region prediction information.

[0018] The robot vacuum cleaner may further include a communication interface, wherein the processor is configured to: based on the area where the robot vacuum cleaner is located being identified as either a first area or a second area, control the communication interface to send identification information about the identified area, a floor plan of the identified area, and planar shapes corresponding to each object among a plurality of objects located in the identified area to an external server.

[0019] The processor may be configured to: based on a user command indicating that an object is received, identify, among the objects recognized from the image, an object corresponding to the user command, and drive the robot vacuum cleaner based on a floor plan of the area where the robot vacuum cleaner is located and a planar shape of at least one object located in the area, such that the vacuum cleaner moves to the position of the identified object.

[0020] The processor may be configured to: obtain shape information corresponding to the identified object from the shape information stored in the memory, and set a travel path for cleaning the surrounding environment of the object based on the shape information and size information related to the object.

[0021] According to another aspect of the present disclosure, a method of controlling a robot vacuum cleaner is provided. The robot vacuum cleaner includes an artificial intelligence model trained to recognize objects from an input image, and the method includes: inputting an image obtained by a camera into the artificial intelligence model to recognize an object included in the image, obtaining shape information corresponding to the recognized object from a plurality of shape information, and setting a travel path of the robot vacuum cleaner based on the shape information and size information related to the object.

[0022] The robot vacuum cleaner may be configured to further include size information for each shape information, and wherein the step of obtaining shape information includes obtaining size information corresponding to the shape information based on the image, or obtaining size information corresponding to the shape information based on size information stored in the memory.

[0023] The step of setting the travel path may include: recognizing a planar shape corresponding to the object based on the shape information of the object, and setting a travel path for avoiding the object based on the planar shape of the object.

[0024] The step of setting the travel path may include: based on failure to obtain a floor plan corresponding to the object, setting a travel path for avoiding the object based on sensing data of an obstacle detection sensor.

[0025] The robot vacuum cleaner may be configured to further include information regarding whether there is an object to be avoided for each of a plurality of objects, wherein the step of setting a travel path includes: setting the travel path to climb an object based on identifying that the object is not to be avoided according to the information regarding whether there is an object to be avoided.

[0026] The method may further include stopping the suction operation of the robot vacuum cleaner when climbing an object.

[0027] The robot vacuum cleaner may be configured to further store first weight value information corresponding to each object and a first region and second weight value information corresponding to each object and a second region, wherein the robot vacuum cleaner further includes: identifying a plurality of objects from an image obtained by a camera, applying the first weight value information to each of the plurality of objects to obtain first region prediction information, applying the second weight value information to each of the plurality of objects to obtain second region prediction information, and identifying the region where the robot vacuum cleaner is located as either the first region or the second region based on the first region prediction information and the second region prediction information.

[0028] The method may further include: based on the region where the robot vacuum cleaner is located being identified as either the first region or the second region, sending identification information regarding the identified region, a floor plan of the identified region, and planar shapes corresponding to each of the objects located in the identified region among the plurality of objects to an external server.

[0029] The method may further include: based on a user command indicating that an object is received, identifying an object corresponding to the user command among the objects identified from the image, and driving the robot vacuum cleaner based on a floor plan of the region where the robot vacuum cleaner is located and a planar shape of at least one object located in the region such that the robot vacuum cleaner moves to the position of the identified object.

[0030] The method may further include: obtaining shape information corresponding to the identified object from the shape information stored in the memory, and setting a travel path for cleaning the surrounding environment of the object based on the shape information and size information related to the object.

[0031] According to the following detailed description of various embodiments of the present disclosure disclosed in conjunction with the accompanying drawings, other aspects, advantages, and significant features of the present disclosure will become apparent to those skilled in the art.

[0032] Advantageous Effects

[0033] One aspect of the present disclosure is to provide a robot vacuum cleaner and a control method thereof that identify obstacles and set a travel path of the robot vacuum cleaner. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In the following description with reference to the drawings, the above and other aspects, features, and advantages of certain embodiments of the present disclosure will become more apparent, where:

[0035] Figure 1 is a view showing a robotic vacuum cleaner according to an embodiment of the present disclosure;

[0036] Figure 2 is a block diagram showing the configuration of a robotic vacuum cleaner according to an embodiment of the present disclosure;

[0037] Figure 3 is a view showing the travel path of a robot according to an embodiment of the present disclosure;

[0038] Figure 4 is a view showing shape information corresponding to an object according to an embodiment of the present disclosure;

[0039] Figure 5 is a view showing shape information of each object and information on whether there is an object to be avoided according to an embodiment of the present disclosure;

[0040] Figure 6 is a view showing the travel path of a robotic vacuum cleaner according to another embodiment of the present disclosure;

[0041] Figure 7 is a view showing the travel path of a robotic vacuum cleaner according to another embodiment of the present disclosure;

[0042] Figure 8 is a view showing a method of obtaining a floor plan of the space where the robotic vacuum cleaner is located according to an embodiment of the present disclosure;

[0043] Figure 9 is a view showing a method of obtaining information on the space where the robotic vacuum cleaner is located according to an embodiment of the present disclosure;

[0044] Figure 10 is a view showing a robotic vacuum cleaner moving to the position of a specific object according to an embodiment of the present disclosure;

[0045] Figure 11 is a detailed block diagram of a robotic vacuum cleaner according to an embodiment of the present disclosure;

[0046] Figure 12 is a view showing a robotic vacuum cleaner communicating with an external server according to an embodiment of the present disclosure; and

[0047] Figure 13It is a flowchart showing a method for controlling a robotic vacuum cleaner according to an embodiment of the present disclosure.

[0048] Throughout the drawings, the same reference numerals will be understood to refer to the same components, elements, and structures. Detailed Description

[0049] The following description with reference to the drawings is provided to assist in a comprehensive understanding of the various embodiments of the present disclosure defined by the claims and their equivalents. It includes various specific details to aid understanding, but these details are only considered exemplary. Thus, those of ordinary skill in the art will recognize that various changes and modifications can be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and structures may be omitted for clarity and conciseness.

[0050] The terms and words used in the following description and claims are not limited to the written meanings, but are used by the inventors only to enable a clear and consistent understanding of the present disclosure. It will be apparent to those skilled in the art that the following description of the various embodiments of the present disclosure is provided for illustrative purposes only and not for the purpose of limiting the present disclosure defined by the appended claims and their equivalents.

[0051] It should be understood that, unless the context clearly dictates otherwise, the singular forms "a," "an," and "the" include plural referents. Thus, for example, a reference to "a component surface" includes a reference to one or more such surfaces.

[0052] The terms "have," "may have," "include," and "may include" used in the embodiments of the present disclosure indicate the existence of corresponding features (e.g., elements such as numerical values, functions, operations, or components), and do not preclude the existence of additional features.

[0053] In the specification, the term "at least one of A or / and B" should be understood to mean "A" or "B" or "A and B."

[0054] Expressions such as "1," "2," "first," or "second" used herein may modify various elements regardless of their order and / or importance, and are only used to distinguish one element from another. Thus, they do not limit the corresponding elements.

[0055] When an element (e.g., a first element) is "operatively or communicatively coupled to" / "operatively or communicatively coupled with" / "connected to" another element (e.g., a second element), the element may be directly coupled to the other element or may be coupled through another element (e.g., a third element).

[0056] Unless otherwise clearly specified in the context, the singular forms are intended to include the plural forms. Terms such as "comprising", "including", "configured to", etc. in this specification are used to indicate the presence of features, numbers, operations, elements, components, or combinations thereof, and they should not exclude the possibility of combining or adding one or more features, numbers, operations, elements, components, or combinations thereof.

[0057] In the present disclosure, a "module" or "unit" performs at least one function or operation and can be implemented by hardware or software or a combination of hardware and software. Additionally, multiple "modules" or multiple "units" can be integrated into at least one module, and can be at least one processor other than the "module" or "unit" that should be implemented in specific hardware.

[0058] Furthermore, the term "user" may refer to a person who uses an electronic device or a device that uses an electronic device (e.g., an artificial intelligence (AI) electronic device).

[0059] Hereinafter, embodiments will be described in more detail with reference to the accompanying drawings.

[0060] Figure 1 is a view showing a robotic vacuum cleaner according to an embodiment of the present disclosure.

[0061] Referring to Figure 1 , the robotic vacuum cleaner 100 refers to a device that is driven by electricity and automatically sucks foreign matters. In Figure 1 , it is assumed that the robotic vacuum cleaner 100 is implemented in a flat shape in close contact with the ground so as to suck foreign matters on the ground, but this is only an embodiment, and the robotic vacuum cleaner 100 can be implemented in various shapes and sizes.

[0062] Referring to Figure 1 , the robotic vacuum cleaner 100 according to an embodiment of the present disclosure may include a camera 110 to detect an object located near the robotic vacuum cleaner 100. For example, the robotic vacuum cleaner 100 may obtain a front image of the robotic vacuum cleaner 100 through the camera 110 and identify an object located in the driving direction of the robotic vacuum cleaner 100 based on the obtained image. The object may refer to various objects or situations that may interfere with the driving of the robotic vacuum cleaner 100 during driving or cause the stop, damage, or malfunction of the robotic vacuum cleaner 100. For example, when the robotic vacuum cleaner 100 is driven at home, the object can be various objects such as furniture, electrical appliances, carpets, clothes, walls, stairs, thresholds, etc.

[0063] The robot vacuum cleaner 100 according to an embodiment of the present disclosure may set a travel path or a movement path of the robot vacuum cleaner 100 based on information about an identified object. The information about the identified object may include shape (or form) information of the object and size information related to the object.

[0064] The robot vacuum cleaner 100 according to an embodiment may set a travel path for avoiding a corresponding object during driving of the robot vacuum cleaner 100, a travel path for climbing over a corresponding object (e.g., climbing over an object), etc. based on information about the identified object.

[0065] Hereinafter, various embodiments of the present disclosure in which the robot vacuum cleaner 100 sets a travel path will be described.

[0066] Figure 2 is a block diagram showing a configuration of a robot vacuum cleaner according to an embodiment of the present disclosure.

[0067] Referring to Figure 2 , the robot vacuum cleaner 100 according to an embodiment of the present disclosure includes a camera 110, a memory 120, and a processor 130.

[0068] The camera 110 is a component for acquiring one or more images of the surrounding environment of the robot vacuum cleaner 100. The camera 110 may be implemented as a red / green / blue (RGB) camera, a three-dimensional (3D) camera, etc.

[0069] In addition, in addition to the camera 110, the robot vacuum cleaner 100 according to an embodiment of the present disclosure may further include a detection sensor (not shown), and the robot vacuum cleaner 100 may identify an object based on sensing data of the detection sensor. For example, the detection sensor may be implemented as an ultrasonic sensor, an infrared sensor, etc. According to an embodiment, when the detection sensor is implemented as an ultrasonic sensor, the robot vacuum cleaner 100 may control the ultrasonic sensor to emit an ultrasonic pulse. Subsequently, when a reflected wave reflected from an object is sent to the ultrasonic pulse, the robot vacuum cleaner 100 may measure the distance between the object and the robot vacuum cleaner 100 by measuring the elapsed time between the object and the robot vacuum cleaner 100. In addition, the ultrasonic sensor may be implemented in various ways, including an ultrasonic proximity sensor. An infrared sensor is a device that detects infrared light information possessed by an object. The robot vacuum cleaner 100 may identify an object based on the infrared light information obtained through the infrared sensor.

[0070] In addition, the present disclosure is not limited thereto, and the detection sensor can be implemented using various types of sensors. The robotic vacuum cleaner 100 can analyze the presence or absence of an object, the position of the object, the distance to the object, etc. based on the sensing data of the detection sensor, and can set the travel path of the robotic vacuum cleaner 100 based on the analysis result. For example, when an object is recognized in front, the robotic vacuum cleaner 100 can rotate the robotic vacuum cleaner 100 itself to the right or left, or move backward.

[0071] The memory 120 can store various data, such as the O / S software module and applications for driving the robotic vacuum cleaner 100.

[0072] In particular, the artificial intelligence model can be stored in the memory 120. Specifically, the memory 120 according to an embodiment of the present disclosure can store an artificial intelligence model trained to recognize an object in an input image. The artificial intelligence model can be a model trained using a plurality of sample images including various objects. Recognizing an object can be understood as obtaining information about the object, such as the name and type of the object. In this case, the information about the object can be the information about the recognized object output by the artificial intelligence model that recognizes the corresponding object.

[0073] The artificial intelligence model according to an embodiment is a determination model trained based on an artificial intelligence algorithm based on a plurality of images, and can be a neural network-based model. The trained determination model can be designed to simulate the human brain structure on a computer, and can include a plurality of network nodes having weights of neurons simulating the human neural network. The plurality of network nodes can respectively form connection relationships to simulate the synaptic activities of neurons that send and receive signals through synapses. In addition, the trained judgment model can include, for example, a machine learning model, a neural network model, or a deep learning model developed from a neural network model. The plurality of network nodes in the deep learning model can exchange data according to a convolutional connection relationship when located at different depths (or layers).

[0074] As an example, the artificial intelligence model can be a convolutional neural network (CNN) model based on image learning. The CNN is a multi-layer neural network with a special connection structure designed for speech processing, image processing, etc. In addition, the artificial intelligence model is not limited to the CNN. For example, the artificial intelligence model can be implemented using at least one deep neural network (DNN) model among a recurrent neural network (RNN), a long short-term memory network (LSTM), a gated recurrent unit (GRU), or a generative adversarial network (GAN).

[0075] The artificial intelligence model stored in the memory 120 can be learned through various learning algorithms (such as the robotic vacuum cleaner 100 or a separate server / system). A learning algorithm is a method of training a predetermined target device (e.g., a robot) using multiple learning data so that the predetermined target device can make decisions or predictions on its own. Examples of learning algorithms are supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithms in the present disclosure are not limited thereto unless otherwise specified.

[0076] In addition, according to an embodiment of the present disclosure, shape information corresponding to each of the multiple objects can be stored in the memory 120.

[0077] The shape information may include a representative image of the corresponding object, information on whether the object corresponds to a typical object or an atypical object, and images viewed from multiple angles of the object.

[0078] The images viewed from multiple angles may include an image viewed from the front of the object (e.g., a front view), an image viewed from the side (e.g., a side view), an image viewed from above the object (e.g., a top view), etc. However, this is an embodiment and is not limited thereto. The representative image of the object may refer to any one of the multiple images viewed from multiple angles, and may refer to any one of the multiple images obtained by scraping images of the object through the network.

[0079] The information on whether the object corresponds to a typical object or an atypical object may indicate whether the object corresponds to an object having a typical shape or an object having a fixed shape (or a constant shape) with an unchanged shape of the object, or an object with an unfixed shape of the object. For example, a cup, a bowl, etc. may correspond to typical objects with fixed shapes, and liquids, cables, etc. may correspond to atypical objects without fixed shapes. A detailed description of the shape information corresponding to each of the multiple objects will be described additionally in Figure 5 In the following.

[0080] The processor 130 controls the overall operation of the robotic vacuum cleaner 100.

[0081] According to an embodiment, the processor 130 may be implemented as a digital signal processor (DSP) for processing digital image signals, a microprocessor, an artificial intelligence (AI) processor, or a timing controller (T-CON). However, it is not limited thereto, and the processor may include one or more of a central processing unit (CPU), a microcontroller unit (MCU), a microprocessing unit (MPU), a controller, and an application processor (AP), a communication processor (CP), or an ARM processor, or may be defined in corresponding terms. In addition, the processor 130 may be implemented in a system on chip (SoC) with built-in processing algorithms, a large scale integration (LSI), or a field programmable gate array (FPGA).

[0082] The processor 130 according to an embodiment of the present disclosure may input an image obtained by the camera 110 into an artificial intelligence model to identify an object included in the image. The processor 130 may obtain shape information corresponding to the identified object among the shape information corresponding to each of the plurality of objects stored in the memory 120. The processor 130 may set a travel path of the robotic vacuum cleaner 100 based on the obtained shape information and size information related to the object. A detailed description will be made with reference to Figure 3 this.

[0083] Figure 3 is a view showing a travel path of a robot according to an embodiment of the present disclosure.

[0084] Referring to Figure 3 , the robotic vacuum cleaner 100 according to an embodiment of the present disclosure may operate at home. The camera 110 provided in the robotic vacuum cleaner 100 may obtain an image by photographing the front (or a predetermined direction) while the robotic vacuum cleaner 100 travels. The processor 130 may input the obtained image into an artificial intelligence model to identify an object included in the image, for example, an object located in front of the robotic vacuum cleaner 100. As an example, the processor 130 may use the artificial intelligence model to identify a flower pot 10-1 included in the image. The processor 130 may obtain shape information corresponding to the flower pot 10-1 from the plurality of shape information.

[0085] The shape information corresponding to the object may include a representative image of the corresponding object, information on whether the object corresponds to a typical object or an atypical object. For example, the shape information corresponding to the flower pot 10-1 may include a representative image of the flower pot 10-1, and the flower pot 10-1 may include information corresponding to the shape of a typical object.

[0086] The processor 130 may identify the size information of the object based on the object image included in the image obtained by the camera 110. For example, the processor 130 may identify the width and height information of the object. Referring to Figure 3 , the processor 130 may identify the width and height information of the flower pot 10-1 based on the image of the flower pot 10-1 included in the image obtained by the camera 110.

[0087] The processor 130 may predict the actual shape of an object based on the shape information corresponding to the recognized object and the dimensional information related to the object. For example, if the recognized object is a shaped object, the processor 130 may recognize the planar shape corresponding to the object. The processor 130 may predict the actual shape and dimensions of the object based on the planar shape of the object and the dimensional information of the object, and may set the travel path of the robotic vacuum cleaner 100 based on the predicted shape and dimensions. The planar shape of the object may refer to the image observed from above among the multiple images observed from multiple angles of the object (e.g., top view). Details will be described with reference to Figure 4 this.

[0088] Figure 4 is a view showing the shape information corresponding to an object according to an embodiment of the present disclosure.

[0089] Referring to Figure 4 , the processor 130 may recognize an object based on the image obtained through the camera 110. For example, the processor 130 may recognize the bed 10-2 placed in the bedroom at home.

[0090] The processor 130 may obtain the shape information corresponding to the recognized object. Referring to Figure 4 , the processor 130 may obtain the shape information corresponding to the bed 10-2 from among the multiple shape information stored in the memory 120. Specifically, the processor 130 may recognize an object based on the shape information, e.g., the planar shape corresponding to the bed 10-2. The planar shape corresponding to the bed 10-2 may refer to the image observed from above the bed 10-2 among the multiple images observed from multiple angles (e.g., top view).

[0091] The processor 130 according to an embodiment may obtain the dimensional information corresponding to the object. For example, the processor 130 may obtain the dimensional information corresponding to the recognized object based on the dimensional information of each shape information stored in the memory 120. For example, the memory 120 may store multiple dimensional information of each shape information corresponding to the bed 10-2. The processor 130 may recognize at least one of the width, height, or length of the bed 10-2 based on the image obtained by the camera 110, and obtain the dimensional information of the bed 10-2 based on at least one of the recognized width, height, or length included in the multiple dimensional information of the shape information of the bed 10-2.

[0092] In addition, this is an embodiment, and the processor 130 may obtain the dimensional information of the bed 10-2, such as the width, height, and length of the bed 10-2, based on the image obtained by the camera 110.

[0093] The processor 130 may recognize the planar shape based on the shape information corresponding to the object, and predict the planar shape of the actual object based on the recognized planar shape and dimensional information of the object. Referring toFigure 4 The processor 130 may identify the planar shape (e.g., square) of the bed 10-2 based on the shape information corresponding to the bed 10-2, and predict (or obtain) the planar shape (or top view) of the bed 10-2 based on the identified planar shape and size information of the bed 10-2 so as to approximate the actual planar shape of the bed 10-2 (e.g., the width, height, and length of the actual bed 10-2).

[0094] The processor 130 may set a travel path for avoiding the corresponding object based on the planar shape of the object. For example, the processor 130 may set a travel path for cleaning and driving in the space by avoiding the bed 10-2 based on the predicted planar shape of the bed 10-2.

[0095] According to an embodiment, the robotic vacuum cleaner 100 may predict the planar shape of an object to approximate the actual planar shape based on an image obtained by the camera 110 without a separate sensor for detecting the object, and set an optimal travel path based on the predicted planar shape.

[0096] In addition, in addition to setting a travel path for avoiding the corresponding object based on the information about the identified object, the robotic vacuum cleaner 100 according to an embodiment of the present disclosure may also set a travel path for climbing over (e.g., climbing over) the corresponding object. This will be described in detail with reference to Figure 5 this.

[0097] Figure 5 is a view showing the shape information of each object and the information about whether there is an object to be avoided according to an embodiment of the present disclosure.

[0098] Referring to Figure 5 According to an embodiment of the present disclosure, the memory 120 may store the shape information of each object and the information about whether there is an object to be avoided.

[0099] For example, the memory 120 may store information about the type of the object 10, a representative image of each object 10, whether each object 10 causes contamination, and whether each object 10 can be climbed over. Figure 5 This is only an example of the shape information of the object, and the shape information of the object may be implemented in various forms. In addition, the shape information corresponding to each of the plurality of objects may be received from an external server and stored in the memory 120.

[0100] Referring to Figure 5, the processor 130 can identify the object 10 based on the image obtained by the camera 110 and obtain the shape information corresponding to the identified object 10. For example, if the identified object 10 is a carpet, the processor 130 can obtain the shape information corresponding to the carpet. The shape information corresponding to the carpet may include information about the representative image of the carpet, information about whether the carpet corresponds to a typical object or an atypical object, whether the carpet is likely to be contaminated, and information about whether the robot can climb the carpet.

[0101] The information about whether it can be climbed included in the shape information may include: when the robotic vacuum cleaner is moving, information about whether the corresponding object corresponds to an object to be avoided or whether the corresponding object corresponds to an object to be climbed (e.g., an object that can be climbed over).

[0102] Refer to Figure 5 , since the shape information corresponding to the carpet indicates that the carpet corresponds to an object that can be climbed, if the identified object is a carpet, the processor 130 can set a travel path to climb the carpet instead of avoiding it.

[0103] As another example, if the identified object is a cup, the shape information corresponding to the cup indicates that the cup does not correspond to an object to be climbed, so the processor 130 can set the travel path of the robotic vacuum cleaner 100 to avoid the cup.

[0104] In addition, if the identified object corresponds to an object that can be climbed by the object (or corresponds to an object that will not be avoided), the processor 130 according to an embodiment of the present disclosure can change the cleaning mode of the robotic vacuum cleaner 100 when climbing the corresponding object.

[0105] For example, the general cleaning mode of the robotic vacuum cleaner 100 can perform a suction operation to suck foreign matters and contaminants on the ground. If an object is sucked into the robotic vacuum cleaner 100 due to the suction operation when the robotic vacuum cleaner 100 climbs the identified object, it may cause the travel of the robotic vacuum cleaner 100 to stop, be damaged, or malfunction. Therefore, the processor 130 can change the cleaning mode of the robotic vacuum cleaner 100 based on the identified object when the robotic vacuum cleaner 100 climbs the object. For example, the processor 130 can stop the suction operation of the robotic vacuum cleaner 100 when climbing the identified object. As another example, the processor 130 can reduce the degree of the suction power of the robotic vacuum cleaner 100 when climbing the object.

[0106] Figure 6 is a view showing the travel path of a robotic vacuum cleaner according to another embodiment of the present disclosure.

[0107] Refer to Figure 6, the robotic vacuum cleaner 100 according to an embodiment of the present disclosure may further include an obstacle detection sensor. According to an embodiment, if a planar shape corresponding to an object cannot be obtained, the processor 130 may set a travel path for avoiding the object based on the sensing data of the obstacle detection sensor.

[0108] For example, the processor 130 may input the image obtained by the camera 110 into an artificial intelligence model to identify the objects included in the image. The processor 130 may obtain the shape information corresponding to the identified object among the multiple shape information of each object. The obtained shape information may include information on whether the identified object corresponds to a typical object or an atypical object.

[0109] According to an embodiment, if the identified object corresponds to an atypical object, the processor 130 may set a travel path for avoiding the object based on the sensing data of the obstacle detection sensor.

[0110] In other words, since an atypical object refers to an object with an unfixed shape, if the identified object is an atypical object, the processor 130 may not be able to obtain the planar shape (i.e., top view) of the identified object. In this case, the processor 130 may set a travel path for avoiding the identified object based on the sensing data of the obstacle detection sensor.

[0111] Refer to Figure 6 , the cable 10-3 is an example of an atypical object. When the cable 10-3 is identified, in addition to the image obtained by the camera 110, the processor 130 may also consider the sensing data obtained by the obstacle detection sensor to set a travel path for avoiding the cable 10-3. However, this is not limited thereto. For example, if the identified object is identified as corresponding to an atypical object, the processor 130 may obtain at least one of the width, height, or length of the corresponding object based on the image to predict the maximum size. The processor 130 may set a travel path based on the predicted size of the object.

[0112] Figure 7 is a view showing the travel path of a robotic vacuum cleaner according to another embodiment of the present disclosure.

[0113] Refer to Figure 7 , the processor 130 according to an embodiment of the present disclosure may identify whether the corresponding object corresponds to an object that may cause contamination based on the shape information corresponding to the identified object.

[0114] Return to refer to Figure 5 , the memory 120 may store information about the type of the object 10, the representative image of each object 10, whether each object 10 causes contamination, and whether each object 10 can be climbed.

[0115] Whether each object 10 causes pollution does not correspond to whether the corresponding object is a target to be avoided, but may refer to the possibility that a pollution area may extend when the robotic vacuum cleaner 100 climbs the corresponding object.

[0116] For example, referring to Figure 7 , since the spilled liquid 10-4 is not an object to be avoided, the processor 130 may control the robotic vacuum cleaner 100 to climb and travel on the spilled liquid 10-4. In this case, there is a problem that the range of pollution caused by the spilled liquid 10-4 may extend in space due to a driver (e.g., wheels, etc.) located at the bottom of the robotic vacuum cleaner 100, a suction unit, etc. As another example, the excrement of a pet is not an object to be avoided, but may be an object that causes concern about pollution.

[0117] When an object is recognized as an object causing pollution based on the shape information of the object, the processor 130 may set a travel path for avoiding the object.

[0118] Figure 8 is a view showing a method of obtaining a floor plan of the space where the robotic vacuum cleaner is located according to an embodiment of the present disclosure.

[0119] Referring to Figure 8 , the robotic vacuum cleaner 100 may capture various images when in an area on the travel map and input the captured images into multiple artificial intelligence models to identify the objects located in the area.

[0120] In addition, the robotic vacuum cleaner 100 may divide the space into multiple regions. For example, the robotic vacuum cleaner 100 may identify points on the ground where there are demarcation lines or thresholds, points where the movable width narrows, points where there are walls, starting points of walls, ending points of walls, points where there are doors, etc. based on the images obtained by the camera 110. The processor 130 may divide the space (e.g., a home) into multiple regions (e.g., a living room, a bedroom, a bathroom, a kitchen, etc.) by using the identified points as boundaries between the regions. Hereinafter, for ease of description, it is assumed that a region refers to a subordinate concept and a space refers to a superordinate concept, that is, a set of regions.

[0121] Furthermore, the processor 130 according to an embodiment of the present disclosure may use the information about the objects located in the regions in order to obtain region information corresponding to each of the multiple regions. The region information may refer to information for identifying each of the multiple regions. The region information may be composed of identification names, identification numbers, etc. indicating each of the multiple regions. In addition, the region information may include information about the use of each of the multiple regions. For example, the multiple regions may be defined as a living room, a bathroom, a bedroom, etc. through the region information. In addition, the information about the objects may include the names, types, etc. of the objects.

[0122] will be referred to Figure 9 for a detailed description.

[0123] Figure 9 is a view showing a method of obtaining information about a space where a robotic vacuum cleaner is located according to an embodiment of the present disclosure.

[0124] Referring to Figure 9 , a processor 130 according to an embodiment of the present disclosure may obtain area information corresponding to a corresponding area based on objects identified in the area. The area information may include information about the purpose of the area, the name of the area, and the like.

[0125] For example, when only a bookshelf is identified in a first area, the processor 130 may identify the first area as a study. As another example, when a bed and a bookcase are identified in a second area, the processor 130 may identify the second area as a bedroom. However, these are only examples. In addition, according to another example, when only a television (TV) is identified in a third area, the third area may be a study or a living room, so obtaining area information using only a table as Figure 9 shown is somewhat unreliable or unclear to some extent.

[0126] Therefore, a processor 130 according to an embodiment of the present disclosure may obtain prediction information corresponding to a corresponding area by using weight information of each area.

[0127] A memory 120 according to an embodiment may store first weight information corresponding to a first area for each object and second weight information corresponding to a second area for each object. The weight information may be defined as Table 1 below.

[0128] Table 1

[0129]

[0130]

[0131] A processor 130 according to an embodiment of the present disclosure may obtain area prediction information for each area in a plurality of areas by using Table 1 and Equation 1 below for objects identified in the area.

[0132] Equation 1

[0133]

[0134] Find_Area(j) = MAX(Area(j)), 0 ≤ j < n

[0135] As an example, when multiple objects are recognized in an image obtained by a camera, that is, when multiple objects are recognized in a specific area, the processor 130 may apply first weight information to each of the multiple objects and obtain first spatial prediction information. The processor 130 may apply second weight information to each of the multiple objects and obtain second spatial prediction information.

[0136] For example, it may be assumed that a TV and a sofa are recognized in a specific area. In this case, the processor 130 may obtain area prediction information corresponding to each of a plurality of areas shown in Table 2 below based on Table 1 and Equation 1.

[0137] Table 2

[0138]

[0139] Since the TV and the sofa are generally located in the living room area relative to other areas, the first weight information corresponding to the living room may assign a high weight to the TV and the sofa and a small weight to the washing machine.

[0140] The processor 130 may identify the area where the robotic vacuum cleaner 100 is located as a first area or a second area based on the first area prediction information and the second area prediction information.

[0141] Referring to Table 2, when a TV and a sofa are recognized in a specific area, the processor 130 may obtain 2 as the area prediction information in the living room area and obtain 0.2 as the area prediction information in the bathroom area. The processor 130 may identify the specific area as the living room area.

[0142] Figure 10 is a view showing a robotic vacuum cleaner moving to the position of a specific object according to an embodiment of the present disclosure.

[0143] Referring to Figure 10 , the processor 130 according to an embodiment of the present disclosure may assign area information to each of a plurality of areas included in a space. For example, a first area in which a TV and a sofa are recognized may be recognized as a living room, and a second area in which a basin is recognized may be recognized as a bathroom. As another example, a third area in which a dressing table and a bed are recognized may be recognized as a bedroom.

[0144] Figure 10 The floor plan of the area shown and the floor plans of the multiple objects may be referred to as map information of the space. The robotic vacuum cleaner 100 according to an embodiment may send the map information of the space to a server or send it to an external device (e.g., a user terminal device) to provide the map information of the space to the user.

[0145] In addition, the robotic vacuum cleaner 100 according to an embodiment of the present disclosure can receive user commands. As an example, the user command can be a command indicating a specific object. The user command can be a voice command, a text command, or a control command received from a remote control device or an external device. As another example, the user terminal device can display map information of a space, and the robotic vacuum cleaner 100 can receive a user command indicating a specific object through the user terminal device.

[0146] For example, when receiving a user command indicating a specific object (e.g., "clean the surroundings of the TV"), the processor 130 can identify the position of the object corresponding to the user command based on the map information of the space. For example, the processor 130 can identify the TV 10-5 included in "clean the surroundings of the TV" by performing voice recognition on the user command. The processor 130 can obtain the position information of the TV 10-5 in the space based on the floor plan of the area and the planar shape of at least one object located in the area. The processor 130 can move the robotic vacuum cleaner 100 to the TV 10-5 based on the obtained position information of the TV 10-5.

[0147] Specifically, the processor 130 can control the robotic vacuum cleaner 100 to change the surroundings of the TV 10-5 according to the user command.

[0148] In addition, the processor 130 according to an embodiment of the present disclosure can move the robotic vacuum cleaner 100 to the position of the object corresponding to the user command and perform a cleaning operation based on the shape information of the object. For example, the processor 130 can set an optimal travel path for avoiding the corresponding object based on the shape information of the object corresponding to the user command, and move the robotic vacuum cleaner 100 based on the set travel path (i.e., by avoiding the object) to clean the surroundings of the corresponding object without colliding with the corresponding object.

[0149] For example, the processor 130 can obtain the shape information corresponding to the TV 10-5 from the shape information of each of the multiple objects according to the user command, and obtain a travel path for avoiding the TV 10-5 based on the shape information corresponding to the TV 10-5. The processor 130 can control the robotic vacuum cleaner 100 to avoid the TV 10-5 and effectively clean the surroundings of the TV 10-5.

[0150] Figure 11 is a detailed block diagram of a robotic vacuum cleaner according to an embodiment of the present disclosure.

[0151] Referring to Figure 11 , the robotic vacuum cleaner 100 according to an embodiment of the present disclosure can include a camera 110, a memory 120, a processor 130, a display 140, a communication interface 150, and a user interface 160.

[0152] The camera 110 can be implemented as an RGB camera, a 3D camera, etc. The 3D camera can be implemented as a time-of-flight (TOF) camera including a TOF sensor and infrared light. The 3D camera can include an infrared (IR) stereo sensor. The camera sensor can be a camera sensor using a charge-coupled device (CCD), complementary metal-oxide semiconductor (CMOS), etc., but is not limited thereto. When the camera 110 includes a CCD, the CCD can be implemented as a red / green / blue (RGB) CCD, an infrared (IR) CCD, etc.

[0153] The memory 120 can store an artificial intelligence model learned to recognize an object in an input image.

[0154] In addition, the memory 120 can include a ROM, a RAM (such as a dynamic RAM (DRAM), a synchronous DRAM (SDRAM), a double data rate SDRAM (DDR SDRAM)), etc., and can be implemented together with the processor 130.

[0155] The functions related to artificial intelligence according to the present disclosure are operated by the processor 130 and the memory 120. The processor 130 can be composed of one or more processors. In this case, the one or more processors can be a general-purpose processor (such as a CPU, an AP, a digital signal processor (DSP), etc.), or only a graphics processor (such as a GPU, a vision processing unit (VPU)), or only an artificial intelligence processor (such as an NPU). The one or more processors control to process input data according to a predefined operation rule or an artificial intelligence model stored in the memory 120. Optionally, when the one or more processors are only artificial intelligence processors, the only artificial intelligence processor can be designed with a hardware structure dedicated to processing a specific artificial intelligence model.

[0156] The predefined motion rule or artificial intelligence model is characterized by being generated through learning. Being generated through learning means learning a basic artificial intelligence model using a plurality of learning data through a learning algorithm so that a predefined motion rule or artificial intelligence model set to perform a desired characteristic (or purpose) is generated. Such learning can be performed in the device itself that executes the artificial intelligence according to the present disclosure, or can be performed through a separate server and / or system. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the above examples.

[0157] An artificial intelligence model may be composed of multiple neural network layers. Each neural network layer among the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weight values. The multiple weight values of the multiple neural network layers can be optimized through the learning results of the artificial intelligence model. For example, the multiple weight values can be updated to reduce or minimize the loss value or cost value obtained from the artificial intelligence model during the learning process. An artificial neural network may include a deep neural network (DNN), such as a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network, etc., but is not limited thereto.

[0158] The display 140 may be implemented as a display including self-luminous elements or a display including non-luminous elements and a backlight. For example, the display may be implemented as various types of displays, such as a liquid crystal display (LCD), an organic light-emitting diode (OLED) display, a light-emitting diode (LED), a micro-LED, a mini-LED, a plasma display panel (PDP), a quantum dot (QD) display, a quantum dot light-emitting diode (QLED), etc. The display 140 may include a driving circuit, a backlight unit, etc., which may be implemented in the form of, for example, an a-Si TFT, a low-temperature polycrystalline silicon (LTPS) TFT, an organic TFT (OTFT), etc. In addition, the display 140 may be implemented as a touch screen combined with a touch sensor, a flexible display, a scrollable display, a 3D display, a display in which multiple display modules are physically connected, etc. The processor 130 may control the display 140 to output the state information of the robotic vacuum cleaner 100 obtained according to the above various embodiments. The state information may include various information related to the driving of the robotic vacuum cleaner 100, such as the cleaning mode of the robotic vacuum cleaner 100, battery-related information, information on whether to return to the docking station 200, etc.

[0159] The communication interface 150 is a component for the robotic vacuum cleaner 100 to communicate with at least one external device to exchange signals / data. For this purpose, the communication interface 150 may include a circuit.

[0160] The communication interface 150 may include a wireless communication module, a wired communication module, etc.

[0161] The wireless communication module may include at least one of a Wi-Fi communication module, a Bluetooth module, an Infrared Data Association (IrDA) module, a third-generation (3G) mobile communication module, a fourth-generation (4G) mobile communication module, a 4G Long-Term Evolution (LTE) communication module.

[0162] The wired communication module may be implemented as a wired port, such as a Thunderbolt port, a USB port, etc.

[0163] The user interface 160 may include one or more buttons, a keyboard, a mouse, etc. Additionally, the user interface 160 may include a touch panel implemented together with a display (not shown) or a separate touchpad (not shown).

[0164] The user interface 160 may include a microphone to receive a user's command or information through voice, or may be implemented together with the camera 110 to recognize a user's command or information in the form of motion.

[0165] Figure 12 It is a view showing a robotic vacuum cleaner communicating with an external server according to an embodiment of the present disclosure.

[0166] Referring to Figure 12 , the robotic vacuum cleaner 100 may communicate with external devices 300-1 and 300-2, which may be smart phones, and a server device 500. In this case, the robotic vacuum cleaner 100 may communicate with the external devices 300-1, 300-2, and 500 through a relay device 400 configured with a router, etc.

[0167] For example, when the area where the robotic vacuum cleaner 100 is located is identified as the first area or the second area, the processor 130 may control the communication interface 150 to provide identification information (e.g., area information) about the identified area, a floor plan of the identified area, and planar shapes corresponding to each of the multiple objects located in the identified area to an external server or external devices 300-1 and 300-2.

[0168] Additionally, the robotic vacuum cleaner 100 may move to any one of multiple areas included in the space where the robotic vacuum cleaner 100 is located, or move to any one of the multiple objects in the space according to a control signal received from the external device 300-1 (the external device 300-1 may be a smart phone) or the external device 300-2.

[0169] Figure 13 It is a flowchart showing a method of controlling a robotic vacuum cleaner according to an embodiment of the present disclosure.

[0170] Referring to Figure 13 , in operation S1310, the method of controlling a robotic vacuum cleaner first inputs an image obtained by a camera into an artificial intelligence model and identifies objects included in the image, where the robotic vacuum cleaner includes an artificial intelligence model trained to identify objects in the input image and shape information corresponding to each of the multiple objects.

[0171] In operation S1320, shape information corresponding to the recognized object is obtained from the plurality of shape information.

[0172] In operation S1330, a travel path of the robotic vacuum cleaner is set based on the shape information and the size information related to the object.

[0173] The robotic vacuum cleaner may further include size information for each shape information. According to an embodiment, operation S1320 of obtaining the shape information may include obtaining size information corresponding to the shape information based on an image, or obtaining size information corresponding to the shape information based on size information stored in a memory.

[0174] Operation S1330 of setting the travel path includes recognizing a planar shape corresponding to the object based on the shape information of the object, and setting a travel path for avoiding the object based on the planar shape of the object.

[0175] In addition, operation S1330 of setting the travel path may include: if a planar shape corresponding to the object cannot be obtained, setting a travel path for avoiding the object based on sensing data of an obstacle detection sensor.

[0176] In addition, the robotic vacuum cleaner may further include information on whether there is an object to be avoided among the plurality of objects, and operation S1330 of setting the travel path according to an embodiment may include: if it is recognized based on the information on whether there is an object to be avoided that the object is not a target to be avoided, setting the travel path to climb over the object.

[0177] The control method according to an embodiment may further include stopping a suction operation of the robotic vacuum cleaner when climbing over the object.

[0178] In addition, the robotic vacuum cleaner may further store first weight information corresponding to each object and a first region and second weight information corresponding to each object and a second region, and the control method according to an embodiment may further include: obtaining first region prediction information by applying the first weight value information to each of the plurality of objects, obtaining second region prediction information by applying the second weight information to each of the plurality of objects, and identifying the region where the robotic vacuum cleaner is located as the first region or the second region based on the first region prediction information and the second region prediction information.

[0179] When the region where the robotic vacuum cleaner is located is identified as the first region or the second region, the control method according to an embodiment may include sending identification information on the identified region, a floor plan of the identified region, and planar shapes corresponding to each of the plurality of objects located in the identified region to an external server.

[0180] In addition, when a user command indicating an object is received, the control method according to an embodiment may include: identifying an object corresponding to the user command among the objects identified in the image, and driving the robotic vacuum cleaner based on a floor plan of the area where the robotic vacuum cleaner is located and the planar shape of at least one object, such that the robotic vacuum cleaner moves to the position of the identified object.

[0181] The control method according to an embodiment may further include: obtaining shape information corresponding to the identified object among a plurality of shape information, and setting a travel path for cleaning the surrounding environment of the object based on the shape information and size information related to the object.

[0182] However, various embodiments of the present disclosure may be applied not only to robotic vacuum cleaners but also to all movable electronic devices.

[0183] The above-described various embodiments may be implemented in a recording medium readable by a computer or a computer-like device by using software, hardware, or a combination thereof. In some cases, the embodiments described herein may be implemented by the processor itself. In a software configuration, various embodiments described in the specification (such as processes and functions) may be implemented as separate software modules. The software modules may perform one or more functions and operations described in the specification, respectively.

[0184] In addition, computer instructions for performing the processing operations of the robotic vacuum cleaner according to the various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When the computer instructions stored in the non-transitory computer-readable medium are executed by a processor of a specific device, the specific device is allowed to perform the processing operations in the robotic vacuum cleaner 100 according to the various embodiments described above.

[0185] A non-transitory computer-readable recording medium refers to a medium that stores data and can be read by a device. For example, the non-transitory computer-readable medium may be a CD, DVD, hard disk, Blu-ray disc, USB, memory card, ROM, etc.

[0186] Although the present disclosure has been described with reference to various embodiments of the present disclosure, those skilled in the art will understand that various changes in form and detail may be made therein without departing from the spirit and scope of the present disclosure defined by the appended claims and their equivalents.

Claims

1. A robotic vacuum cleaner, comprising: A camera; A memory configured to store an artificial intelligence model trained to recognize objects from input images, shape information corresponding to each of a plurality of objects, information about objects to be avoided, first weight value information corresponding to each object and a first region, and second weight value information corresponding to each object and a second region; And A processor configured to control the robotic vacuum cleaner by being connected to the camera and the memory, wherein the processor is further configured to: Input an image obtained by the camera into the artificial intelligence model to recognize objects included in the image, Obtain shape information corresponding to the recognized object from the shape information stored in the memory, Based on the information about objects to be avoided, identify whether the recognized object corresponds to an object to be avoided, Based on the recognized object corresponding to the object to be avoided, based on the shape information, identify whether the recognized object is a contaminating object, Based on the recognized object corresponding to the object to be avoided or the recognized object corresponding to the contaminating object, set a travel path of the robotic vacuum cleaner based on the shape information and size information related to the recognized object, and Based on the recognized object not corresponding to the object to be avoided or the recognized object not corresponding to the contaminating object, set the travel path to climb over the recognized object, and Wherein the processor is further configured to: Based on recognizing a plurality of objects from the image obtained by the camera, apply first weight value information to each of the plurality of objects to obtain first region prediction information, Apply second weight value information to each of the plurality of objects to obtain second region prediction information, and Based on the first region prediction information and the second region prediction information, identify the region where the robotic vacuum cleaner is located as either a first region or a second region.

2. The robotic vacuum cleaner according to claim 1, Among them, The memory is further configured to store size information of each of the shape information, and Wherein the processor is further configured to obtain size information corresponding to the shape information based on the image, or obtain size information corresponding to the shape information based on the size information stored in the memory.

3. The robotic vacuum cleaner according to claim 1, wherein, The processor is further configured to: Based on the shape information of the recognized object, identify a planar shape corresponding to the recognized object, and Based on the planar shape of the recognized object, set a travel path for avoiding the recognized object.

4. The robotic vacuum cleaner according to claim 1, further comprising: An obstacle detection sensor, wherein the processor is further configured to: based on failure to obtain a planar view corresponding to the recognized object, set a travel path for avoiding the recognized object based on the sensing data of the obstacle detection sensor.

5. The robotic vacuum cleaner according to claim 1, wherein, The processor is further configured to stop the suction operation of the robotic vacuum cleaner when climbing over the object.

6. The robot vacuum cleaner according to claim 1 further comprises: A communication circuit, wherein the processor is further configured to: based on the area where the robot vacuum cleaner is located being identified as either a first area or a second area, control the communication circuit to send identification information about the identified area, a floor plan of the identified area, and planar shapes corresponding to each object among the plurality of objects located in the identified area to an external server.

7. The robotic vacuum cleaner according to claim 1, wherein, The processor is further configured to: Based on receiving a user command indicating an object, identify an object corresponding to the user command among the objects recognized from the image, and Based on the floor plan of the area where the robot vacuum cleaner is located and the planar shapes of at least one object located in the area, drive the robot vacuum cleaner so that the robot vacuum cleaner moves to the position of the identified object.

8. The robotic vacuum cleaner according to claim 7, wherein, The processor is further configured to: Obtain shape information stored in the memory corresponding to the identified object, and Based on the shape information and size information related to the identified object, set a travel path for cleaning the surrounding environment of the identified object.

9. A method for controlling a robot vacuum cleaner, the robot vacuum cleaner including an artificial intelligence model trained to recognize objects from an input image, the method comprising: Inputting an image obtained by a camera into the artificial intelligence model to recognize objects included in the image; Obtaining shape information corresponding to the recognized objects from among a plurality of shape information; Based on information about an object to be avoided, identifying whether the recognized object corresponds to the object to be avoided; Based on the recognized object corresponding to the object to be avoided, identifying whether the recognized object is an object causing contamination based on the shape information; Based on the recognized object corresponding to the object to be avoided or the recognized object corresponding to the object causing contamination, setting a travel path of the robot vacuum cleaner based on the shape information and size information related to the recognized object; And Based on the recognized object not corresponding to the object to be avoided or the recognized object not corresponding to the object causing contamination, setting the travel path to climb over the recognized object, wherein the method further comprises: Based on recognizing a plurality of objects from the image obtained by the camera, applying first weight value information corresponding to a first area to each of the plurality of objects to obtain first area prediction information, Applying second weight value information corresponding to a second area to each of the plurality of objects to obtain second area prediction information, and Based on the first area prediction information and the second area prediction information, identifying the area where the robot vacuum cleaner is located as either a first area or a second area.

10. The method according to claim 9, Among them, The method further comprises storing size information of each shape among the plurality of shape information, and Among them, the step of obtaining shape information includes: obtaining dimension information corresponding to the shape information based on the image, or obtaining dimension information corresponding to the shape information based on the dimension information stored in the memory.

11. The method according to claim 9, wherein, The step of setting a travel path includes: identifying a planar shape corresponding to the identified object based on the obtained shape information of the identified object, and setting a travel path for avoiding the identified object based on the planar shape of the identified object.

12. The method according to claim 9, wherein, The step of setting a travel path includes: based on the failure to obtain a planar map corresponding to the identified object, setting a travel path for avoiding the identified object based on the sensing data of the obstacle detection sensor.

Images