Robot vacuum cleaner and cleaning method thereof

Abstract

A robot vacuum cleaner is disclosed. Instructions stored in a memory of the robot vacuum cleaner, when executed individually or collectively by at least one processor of the robot vacuum cleaner, may cause the robot vacuum cleaner to: when an object is detected by a sensor while the robot vacuum cleaner is travelling in a space, acquire, using the sensor, first feature data about the characteristics of the object and second feature data about the environment in which the object is located; on the basis of the first and second feature data, acquire a score indicating whether the object is a movable object and the reliability of the score; identify whether the object is a movable object on the basis of the score and the reliability; and when the object is identified as a movable object, transmit, to an electronic device, a notification requesting movement of the object via a communication interface on the basis of a cleaning period for the area in which the object is located.

Description

Robot vacuum cleaner and its cleaning method

[0001] The present disclosure relates to a robot vacuum cleaner for cleaning a space and a cleaning method thereof.

[0002] In addition to simple repetitive functions, robots can detect their surroundings in real time based on sensors and cameras, collect information, and drive autonomously. Such robots are currently being used in many fields, and in the home, robotic vacuum cleaners are widely used. Robotic vacuum cleaners can navigate through spaces (e.g., indoor areas) and clean the space by sucking up debris.

[0003] A robot vacuum cleaner according to one embodiment may include at least one processor comprising a sensor, a communication interface, a memory for storing instructions, and a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may, when an object is detected by the sensor while traveling through a space, acquire first feature data regarding the characteristics of the object and second feature data regarding the environment in which the object is located using the sensor, acquire a score indicating whether the object is a movable object and a confidence level for the score based on the first and second feature data, identify whether the object is a movable object based on the score and the confidence level, and if the object is identified as a movable object, transmit a notification requesting the movement of the object through the communication interface based on the cleaning cycle for the area in which the object is located to an electronic device.

[0004] The memory may store data regarding a plurality of objects acquired using the sensor while the robot vacuum cleaner previously traveled through the space. The data regarding the plurality of objects may include feature data regarding the characteristics of the plurality of objects and feature data regarding the environment in which the plurality of objects are located.

[0005] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may identify the score based on the first score calculated based on the first feature data and the feature data stored in the memory and the second score calculated based on the second feature data and the feature data stored in the memory, and identify the reliability based on the first reliability calculated based on the first feature data and the feature data stored in the memory and the second reliability calculated based on the second feature data and the feature data stored in the memory.

[0006] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may calculate the first score based on the number of times it has traveled through the space, the number of times a first object similar to the object has been detected at a location different from where the object was detected, and the similarity between the object and the first object. The similarity between the object and the first object may be greater than or equal to a preset value.

[0007] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may acquire the first reliability based on the similarity between the object and the first object.

[0008] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may calculate the second score based on the occupancy rate of the location where the object is detected and the variability corresponding to the presence or absence of the object at the location where the object is detected.

[0009] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may acquire the second reliability based on the timeliness of the data used to calculate the occupancy rate and the sufficiency of the data used to calculate the occupancy rate and the variability.

[0010] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner identifies the object as a movable object if the reliability is greater than or equal to a preset value and the score is greater than or equal to a preset value, and if the reliability is less than the preset value, additionally acquires first feature data for the object using the sensor, acquires the score and the reliability based on the additionally acquired first feature data, and identifies whether the object is a movable object based on the score and the reliability.

[0011] When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner may identify a cleaning cycle for an area for the object, and when it is identified that the cleaning cycle has elapsed, transmit the notification to an electronic device.

[0012] A cleaning method of a robot vacuum cleaner including a sensor according to one embodiment may include, when an object is detected by the sensor while traveling through a space, acquiring first feature data regarding the characteristics of the object and second feature data regarding the environment in which the object is located using the sensor; acquiring a score indicating whether the object is a movable object and a reliability of the score based on the first and second feature data; identifying whether the object is a movable object based on the score and the reliability; and when the object is identified as a movable object, transmitting a notification requesting the movement of the object through the communication interface to an electronic device based on the cleaning cycle for the area in which the object is located.

[0013] In a non-transient computer-readable medium storing computer instructions that cause an electronic device to perform an operation when executed by at least one processor of a wearable device worn on a user's head according to one embodiment, the operation may include, when an object is detected by the sensor while moving through space, acquiring first feature data regarding the characteristics of the object and second feature data regarding the environment in which the object is located using the sensor; acquiring a score indicating whether the object is a movable object and a confidence level for the score based on the first and second feature data; identifying whether the object is a movable object based on the score and the confidence level; and when the object is identified as a movable object, transmitting a notification to the electronic device requesting the movement of the object through the communication interface based on a cleaning cycle for the area in which the object is located.

[0014] FIG. 1 is a diagram schematically illustrating a robot vacuum cleaner according to one embodiment.

[0015] FIG. 2 illustrates an example of a block diagram of a robot vacuum cleaner according to one embodiment.

[0016] FIG. 3 illustrates an example of a block diagram of a robot vacuum cleaner according to one embodiment.

[0017] FIG. 4 is a diagram illustrating the operations of a robot vacuum cleaner according to one embodiment.

[0018] FIG. 5 is a diagram illustrating an example of an operation in which a robot vacuum cleaner identifies whether an object is a movable object based on a score and reliability according to one embodiment.

[0019] FIGS. 6, FIGS. 7, and FIGS. 8 are drawings for illustrating an example of an operation in which a robot vacuum cleaner cleans an area where an object is located, according to one embodiment.

[0020] FIG. 9 is a diagram for explaining the operations of a robot vacuum cleaner according to one embodiment.

[0021] The present disclosure will be described in detail below with reference to the attached drawings.

[0022] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as "coupled" or "connected" to another (e.g., 2nd) component, with or without the terms "functionally" or "communicationly," it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0023] Throughout the specification, singular expressions include plural expressions unless the context clearly indicates otherwise. Wherever a part of the specification states that it "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0024] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0025] Meanwhile, the various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0026] The present disclosure will be described below with reference to the attached drawings.

[0027] FIG. 1 is a diagram schematically illustrating a robot vacuum cleaner according to one embodiment.

[0028] Referring to FIG. 1, the robot vacuum cleaner (100) can travel through a space. For example, the robot vacuum cleaner (100) can move through a space and perform cleaning operations.

[0029] The cleaning operation may include the robot vacuum cleaner (100) moving through the space, sucking up foreign substances such as dust on the floor, and wiping the floor using a wet mop.

[0030] The movement of the robot vacuum cleaner (100) may include the robot vacuum cleaner (100) exploring its surroundings to detect the location of the robot vacuum cleaner (100) and surrounding objects, and using the detected information to move autonomously within the space. Movement may be replaced with expressions such as driving, for example. The space may include various indoor spaces such as a house, office, hotel, factory, shop, mart, restaurant, etc. Objects may include various obstacles present in the indoor space where the robot vacuum cleaner (100) is located, such as walls, furniture, home appliances, chairs, movable drawers, movable trays, footrests, etc.

[0031] FIG. 2 illustrates an example of a block diagram of a robot vacuum cleaner according to one embodiment.

[0032] Referring to FIG. 2, a robot vacuum cleaner (100) according to one embodiment may include at least one sensor (110) (hereinafter referred to as sensor (110)), a communication interface (120), at least one memory (130) (hereinafter referred to as memory (130)), and at least one processor (140) (hereinafter referred to as processor (140)). The sensor (110), the communication interface (120), the memory (130), and / or the processor (140) may be electrically and / or operationally connected to each other by electronic components such as a communication bus. In the present disclosure, the operational connection of the electronic components may include a direct connection established between the electronic components and / or an indirect connection established between the electronic components such that a first electronic component among the electronic components is controlled by a second electronic component among the electronic components. The type and / or number of electronic components included in the robot vacuum cleaner (100) are not limited to those shown in FIG. 2. For example, the robot vacuum cleaner (100) may include at least some of the electronic components shown in FIG. 2.

[0033] The sensor (110) can generate electrical information that can be processed by the processor (140) and / or memory (130) from non-electronic information related to the robot vacuum cleaner (100). The sensor (110) can detect the operating state of the robot vacuum cleaner (100) or the external environmental state and generate electrical information corresponding to the detected state.

[0034] In one embodiment, the sensor (110) may include a camera and / or lidar sensor.

[0035] The camera can generate an image by capturing the surroundings of the robot vacuum cleaner (100) (e.g., the front of the robot vacuum cleaner (100)). The processor (140) can acquire the image using the camera. For example, the camera may include an RGB camera, a depth camera, etc. The depth camera may be implemented in a stereo format or a Time of Flight (TOF) format, etc.

[0036] A LiDAR sensor emits a laser in a 360-degree direction, and when a laser reflected from an object is received, it can obtain geometry information about the space by analyzing the time difference for the laser to be reflected back from the object and / or the signal strength of the received laser. The geometry information may include the location, distance, direction, etc. of objects around the robot vacuum cleaner (100). A processor (140) can obtain the above information using the LiDAR sensor.

[0037] However, the present disclosure is not limited thereto. For example, the sensor (110) may further include at least one of an obstacle detection sensor and / or a driving detection sensor.

[0038] An obstacle detection sensor can detect objects around the robot vacuum cleaner (100). For example, the obstacle detection sensor may include at least one of an ultrasonic sensor, an infrared sensor, an RF (radio frequency) sensor, a geomagnetic sensor, and a PSD (position sensitive device) sensor. The obstacle detection sensor can detect objects present in front, behind, to the side, or on the path of movement of the robot vacuum cleaner (100). The obstacle detection sensor can provide information about the detected objects to the processor (140).

[0039] A driving detection sensor can detect the driving of a robot vacuum cleaner (100). For example, the driving detection sensor may include at least one of a gyroscope sensor, a wheel encoder, and an accelerometer sensor. The gyroscope sensor can detect the rotation direction and rotation angle of the robot vacuum cleaner (100). The wheel encoder can detect the number of rotations of the wheels of the robot vacuum cleaner (100). The accelerometer sensor can detect changes in the speed of the robot vacuum cleaner (100). The driving detection sensor can provide the detected driving information to a processor (140).

[0040] The communication interface (120) may include hardware components to support the transmission and / or reception of electrical signals between the robot vacuum cleaner (100) and an electronic device. The electronic device may include a server, a home appliance, a mobile device (e.g., a smartphone, a tablet PC, a wearable device, etc.).

[0041] For example, the communication interface (120) may include a communication circuit capable of performing data communication between a robot vacuum cleaner (100) and an electronic device using at least one of a data communication method including wired LAN, wireless LAN, Wi-Fi, Wi-Fi Direct, Bluetooth, ZigBee, WFD (Wi-Fi Direct), infrared communication (IrDA, infrared Data Association), BLE (Bluetooth Low Energy), NFC (Near Field Communication), Wibro (Wireless Broadband Internet), WiMAX (World Interoperability for Microwave Access), SWAP (Shared Wireless Access Protocol), WiGig (Wireless Gigabit Alliances, WiGig) and RF communication.

[0042] According to various embodiments of the present disclosure, the memory (130) may store data necessary for the robot vacuum cleaner (100) to operate. Depending on the purpose of data storage, the memory (130) may be implemented as a memory embedded in the robot vacuum cleaner (100) (e.g., volatile memory (e.g., semi-permanent memory such as RAM (random access memory)), non-volatile memory (e.g., permanent memory such as ROM (read-only memory)), flash memory, hard drive or solid-state drive, etc.), or as a memory that can be attached to the robot vacuum cleaner (100) (e.g., memory card, external memory, etc.).

[0043] Instructions may be stored in the memory (130). The processor (140) may perform the operation of the robot vacuum cleaner (100) according to various embodiments of the present disclosure by executing the instructions stored in the memory (130) individually or collectively. Additionally, programs and data for operating the robot vacuum cleaner (100) may be stored in the memory (130). For example, the memory (130) may store one or more software applications, such as operating system (or system) software applications, firmware software applications, driver software applications, plugin (e.g., add-in, add-on, and / or applet) software applications, and / or any other suitable software applications.

[0044] The processor (140) can control the overall operations of the robot vacuum cleaner (100). For example, the processor (140) can cause other components of the robot vacuum cleaner (100) to perform various operations by executing instructions stored in memory (130). For example, the processor (140) can control the operation of the robot vacuum cleaner (100) by operatively connecting with the sensor (110), the communication interface (120), and memory (130). Additionally, the processor (140) can control the operation of the robot vacuum cleaner (100) according to the present disclosure by executing one or more instructions stored in memory (130). The processor (140) may be composed of one or more processors.

[0045] The processor (140) may be implemented as one or more integrated circuit (or circuitry) chips and may perform various data processing operations. The processor (140) may include at least one electrical circuit and may process instructions (or programs, data, etc.) stored in memory (130) individually or collectively. The processor (140) may include a processor assembly comprising one or more processing circuits. The processor (140) may include any processing circuit that is operative to control the performance and operations of one or more components of the robot vacuum cleaner (100) (e.g., sensor (110), communication interface (120), memory (130)). For example, the processor (140) (e.g., application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (140) may be implemented with a number of cores (or at least one core circuit), a number of chips, or a number of chipsets. For example, the processor (140) may include one or more processing circuits. For example, the processor (140) may include one or more processing circuits configured to perform the various functions of the present disclosure individually and / or collectively. As an example without limitation, at least a portion of the processor (140) may be included in a first chip of the robot vacuum cleaner (100), and at least another portion of the processor (140) may be included in a second chip of the robot vacuum cleaner (100) different from the first chip of the robot vacuum cleaner (100).

[0046] The processor (140) may include one or more of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), MIC (Many Integrated Core), DSP (Digital Signal Processor), NPU (Neural Processing Unit), hardware accelerator, or machine learning accelerator. The processor (140) may control one or any combination of other components of the robot vacuum cleaner (100) and may perform operations or data processing related to communication. The processor (140) may execute one or more programs or instructions stored in memory (130). For example, the processor (140) may perform a method according to one embodiment of the present disclosure by executing one or more instructions stored in memory.

[0047] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single processor or by a plurality of processors. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an artificial intelligence dedicated processor).

[0048] The processor (140) may be implemented as a single-core processor including one core, or as one or more multicore processors including multiple cores (e.g., homogeneous multicore or heterogeneous multicore). When the processor (140) is implemented as a multicore processor, each of the multiple cores included in the multicore processor may include internal processor memory such as cache memory or on-chip memory, and a common cache shared by the multiple cores may be included in the multicore processor. Additionally, each of the multiple cores included in the multicore processor (or some of the multiple cores) may independently read and execute program instructions for implementing a method according to one embodiment of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one embodiment of the present disclosure.

[0049] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor, or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor, or the first operation and the second operation may be performed by a first core included in a multi-core processor and the third operation may be performed by a second core included in a multi-core processor.

[0050] In the embodiments of the present disclosure, the processor may mean a system-on-chip (SoC) in which a processor and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, GPU, APU, MIC, DSP, NPU, hardware accelerator, or machine learning accelerator, but the embodiments of the present disclosure are not limited thereto.

[0051] FIG. 3 illustrates an example of a block diagram of a robot vacuum cleaner according to one embodiment.

[0052] Referring to FIG. 3, a robot vacuum cleaner (100) according to one embodiment may include a sensor (110), a communication interface (120), a memory (130), a processor (140), an input interface (150), a driving unit (160), an output interface (170), and a cleaning device (180). However, such configurations are exemplary, and it is understood that new configurations may be added or some configurations omitted in addition to such configurations when implementing the present disclosure. Meanwhile, detailed descriptions of configurations shown in FIG. 3 that overlap with configurations shown in FIG. 2 will be omitted.

[0053] The sensor (110) can detect the structure and / or objects of the space. Information obtained by the sensor (110) can be used to generate a map of the space. The sensor (110) may include at least one of a camera (111), a LiDAR sensor (112), an obstacle detection sensor (113), and a driving detection sensor (114).

[0054] The input interface (150) may include circuitry. The input interface (150) may receive user input and transmit the user input to the processor (140). For example, the input interface (150) may receive various user inputs for setting or selecting various functions supported by the robot vacuum cleaner (100).

[0055] The input interface (150) may include various types of input devices.

[0056] According to one example, the input interface (150) may include a physical button. The physical button may include a function key or a dial button. The physical button may be implemented as one or more keys.

[0057] According to one example, the input interface (150) can receive user input using a touch method. For example, the input interface (150) can be implemented as a touch screen capable of performing the function of a display (171).

[0058] According to one example, the input interface (150) can receive user voice using a microphone. The processor (140) can perform a function corresponding to the user voice using voice recognition. For example, the processor (140) can convert the user voice into text data using a Speech To Text (STT) function, obtain control command data based on the text data, and perform a function corresponding to the user voice based on the control command data. According to an embodiment, the STT function may be performed on an external server.

[0059] The drive unit (160) can control the movement of the robot vacuum cleaner (100) by the control of the processor (140). For example, the drive unit (160) can move the robot vacuum cleaner (100), stop the robot vacuum cleaner (100) while it is moving, and control the movement speed and / or direction of movement of the robot vacuum cleaner (100).

[0060] For example, the driving type of the robot vacuum cleaner (100) can be a wheel type or a walking type.

[0061] The wheel type refers to the method by which the robot vacuum cleaner (100) moves through the rotation of a wheel. If the robot vacuum cleaner (100) is a wheel-type robot, the robot vacuum cleaner (100) may include one or more wheels. The drive unit (160) may include a device that generates power to rotate the wheel. For example, the drive unit (160) may be implemented as a gasoline engine, a diesel engine, an LPG (liquefied petroleum gas) engine, or an electric motor, depending on the fuel (or energy source) used. For example, the drive unit (160) can control the direction of movement and the speed of movement of the robot vacuum cleaner (100) by controlling the rotational direction and rotational speed of one or more wheels.

[0062] The walking type refers to the method by which the robot vacuum cleaner (100) moves through the movement of its legs. If the robot vacuum cleaner (100) is of a walking type (e.g., a bipedal robot, a tripedal robot, a quadrupedal robot, etc.), the robot vacuum cleaner (100) may include two or more legs that support the robot vacuum cleaner (100). The legs may include a plurality of links and joints connected to the links. The driving unit (160) may include a device that generates power to lift or lower the legs by rotating the links around the joints. For example, the driving unit (160) may be implemented as a motor and / or actuator, etc.

[0063] The output interface (170) may include a display (171) and a speaker (172).

[0064] The display (171) can output visualized information to the user. For example, visual objects may include screens, images, icons, GUI, UI elements, etc. The processor (140) can display various notifications, messages, information, etc. related to the operation of the robot vacuum cleaner (100) on the display (171).

[0065] The display (171) may be implemented as a display including a self-emissive element or as a display including a non-emissive element and a backlight. For example, the display (171) may be implemented as various types of displays such as an LCD (Liquid Crystal Display), an OLED (Organic Light Emitting Diodes) display, an LED (Light Emitting Diodes) display, a micro LED display, a Mini LED display, a QLED (Quantum dot light-emitting diodes) display, etc.

[0066] The speaker (172) can output an audio signal. The processor (140) can output warning sounds, notification messages, response messages corresponding to user input, etc. related to the operation of the robot vacuum cleaner (100) through the speaker (172).

[0067] The cleaning device (180) may include a device for cleaning the floor. For example, the cleaning device (180) may include a cleaning module for sweeping and sucking up dust on the floor, a mop module for performing mop cleaning, etc. The processor (140) may control the cleaning device (180) to suck up foreign matter on the floor and perform mop cleaning while the robot vacuum cleaner (100) is stopped or while the robot vacuum cleaner (100) is moving.

[0068] FIG. 4 is a diagram illustrating the operations of a robot vacuum cleaner according to one embodiment. A processor (140) may perform at least one of the operations of FIG. 4. Instructions stored in memory (130) may cause the robot vacuum cleaner (100) to perform the operations of FIG. 4 when executed individually or collectively by the processor (140).

[0069] In operation 410, the robot vacuum cleaner (100) can travel through the space.

[0070] In one embodiment, the robot vacuum cleaner (100) can move through a space and perform cleaning operations. For example, the robot vacuum cleaner (100) can plan a path using a map of the space and move along the path to perform cleaning. Various methods can be used for this path planning.

[0071] In one embodiment, the robot vacuum cleaner (100) can generate a map of the space. For example, the robot vacuum cleaner (100) can generate a map using SLAM (simultaneous localization and mapping). The robot vacuum cleaner (100) can acquire data about the surrounding environment by exploring the surrounding environment using a camera (111), a LiDAR sensor (112) and / or an ultrasonic sensor, etc., generate a map of the space based on the data, and identify the location of the robot vacuum cleaner (100) on the map.

[0072] In one embodiment, the map may contain information about the space. The memory (130) may store the map. The map may be used for the robot vacuum cleaner (100) to detect the surrounding environment, determine the location of the robot vacuum cleaner (100), and plan a path. For example, the map may include information about the location and size of obstacles (e.g., structures such as walls, pillars, etc.) and the area where the robot vacuum cleaner (100) can move on the map.

[0073] In operation 420, the robot vacuum cleaner (100) can detect objects while driving through the space.

[0074] In one embodiment, the robot vacuum cleaner (100) can detect an object using a sensor (110).

[0075] For example, a robot vacuum cleaner (100) can acquire an image using a camera (111) and recognize an object from the image. The robot vacuum cleaner (100) can recognize an object in the image by inputting the image into an artificial intelligence model stored in memory (130). The artificial intelligence model may include a neural network model trained to detect an object in the image and classify the detected object. However, the present disclosure is not limited thereto. For example, the robot vacuum cleaner (100) can detect an object using a LiDAR sensor (112) or an ultrasonic sensor, etc.

[0076] In operation 420-Y, 430, when an object is detected, the robot vacuum cleaner (100) can obtain feature data about the object using the sensor (110).

[0077] Feature data may include first feature data regarding the properties of an object and second feature data regarding the environment in which the object is located.

[0078] In one embodiment, the first feature data may include data representing the characteristics of an object. The characteristics may include at least one of shape, color, size, motion, sound, and temperature.

[0079] For example, the shape of an object may include the shape of the object. The robot vacuum cleaner (100) can identify the shape of the object by extracting an outline from an image obtained through a camera (111).

[0080] For example, the color of an object may include visual characteristics determined by the wavelength of light reflected by the object. The robot vacuum cleaner (100) can identify the color of an object using an image acquired through a camera (111).

[0081] For example, the size of an object may include at least one of the length, volume, and mass of the object. The robot vacuum cleaner (100) can identify the size of the object using an artificial intelligence model. The artificial intelligence model may include a neural network model trained to identify at least one of the length, volume, and mass of an object included in an image. The robot vacuum cleaner (100) can input an image acquired through a camera (111) into the artificial intelligence model to obtain information about the size of the object from the artificial intelligence model.

[0082] For example, the motion of an object may include a movement state of the object. The movement state may include at least one of a stop, a move, and a movement speed. A robot vacuum cleaner (100) can identify the motion of an object by tracking the object in an image.

[0083] For example, the sound of an object may include sound originating from the object. The robot vacuum cleaner (100) may include a microphone. The robot vacuum cleaner (100) may receive the sound of the object using the microphone. According to an embodiment, the robot vacuum cleaner (100) may receive sound originating from the direction in which the object is located through the microphone using beamforming.

[0084] For example, the sensor (110) may include a temperature sensor (e.g., an infrared temperature sensor). The robot vacuum cleaner (100) can identify the temperature of an object by using the temperature sensor to detect infrared radiation emitted from the object.

[0085] For example, a robot vacuum cleaner (100) can acquire characteristics of an object using an artificial intelligence model. The artificial intelligence model may include a neural network model trained to identify characteristics of an object contained in an image. The robot vacuum cleaner (100) can acquire feature data regarding the characteristics of an object from the artificial intelligence model by inputting an image acquired through a camera (111) into the artificial intelligence model.

[0086] For example, a robot vacuum cleaner (100) can acquire feature data regarding the characteristics of an object using a LiDAR sensor (112). For example, the robot vacuum cleaner (100) can acquire distance information between the robot vacuum cleaner (100) and an object using the LiDAR sensor (112) and generate a point cloud using the distance information. The robot vacuum cleaner (100) can acquire at least one of the shape, size, and motion of an object using the point cloud. However, the present disclosure is not limited thereto, and the robot vacuum cleaner (100) can acquire feature data regarding the characteristics of an object using an ultrasonic sensor or an infrared sensor, etc.

[0087] In one embodiment, the second feature data may include data regarding the features of the environment in which the object is located.

[0088] For example, the characteristics of the environment in which an object is located may include the location of the object.

[0089] For example, a robot vacuum cleaner (100) may acquire location information of an object using a camera (111) and / or a LiDAR sensor (112), and may identify the location of the object using the location of the robot vacuum cleaner (100) and the location information of the object. The location information of the object may include the direction (or direction angle) of the object, the distance between the robot vacuum cleaner (100) and the object, etc. For example, the robot vacuum cleaner (100) may acquire location information of the object from the artificial intelligence model by inputting an image acquired through the camera (111) into the artificial intelligence model. The artificial intelligence model may be a neural network model trained to estimate the location of the object from the image. Alternatively, the robot vacuum cleaner (100) may acquire location information of the object using a LiDAR sensor (112). However, the present disclosure is not limited thereto. The robot vacuum cleaner (100) may also acquire location information of the object using an ultrasonic sensor, an infrared sensor, etc.

[0090] Meanwhile, in the example described above, the characteristics of the environment in which an object is located were explained as including the location of the object, but the present disclosure is not limited thereto. For example, the characteristics of the environment in which an object is located may further include the amount or type of light received by the object, the degree of contamination of the object, the height or altitude of the area in which the object is located, etc. The robot vacuum cleaner (100) can acquire second feature data using an artificial intelligence model. The artificial intelligence model may include a neural network model trained to identify features of the environment in which an object is located that is included in an image. The robot vacuum cleaner (100) can acquire feature data of the environment in which an object is located from the artificial intelligence model by inputting an image acquired through a camera (111) into the artificial intelligence model.

[0091] In operation 440, the robot vacuum cleaner (100) can obtain a score and a confidence level for the score indicating whether the object is a movable object based on the first feature data and the second feature data.

[0092] The statement that an object is movable may mean that the object is not installed in a fixed position, but is an object whose position can be changed by the user.

[0093] In one embodiment, the memory (130) can store driving history data of the robot vacuum cleaner (100).

[0094] The driving history data may include information on the number of times (or the total number of times) the robot vacuum cleaner (100) has driven through the space in the past, and feature data on multiple objects acquired using a sensor (110) while the robot vacuum cleaner (100) has driven through the space in the past. The feature data on multiple objects may include feature data on the characteristics of multiple objects and feature data on the environment in which the multiple objects are located.

[0095] For example, when the robot vacuum cleaner (100) travels through a space, it can detect an object using a sensor (110), acquire feature data regarding the characteristics of the object and the environment in which the object is located, and store the acquired feature data in memory (130). The robot vacuum cleaner (100) can acquire feature data and store it in memory (130) each time it travels through a space. For example, if the robot vacuum cleaner (100) travels through a space n times (e.g., n is a natural number), the travel history data may include the number of times the robot vacuum cleaner (100) traveled through the space (e.g., n times) and the feature data acquired during the n times the robot vacuum cleaner (100) traveled.

[0096] In one embodiment, the score may be a score used to determine whether the object is a movable object. The robot vacuum cleaner (100) may identify whether the object is a movable object based on the score for the object. For example, the score may be a value between 0 and 1. The higher the score, the higher the likelihood that the object corresponds to a movable object. The higher the score, the more easily the object can move.

[0097] In one embodiment, the robot vacuum cleaner (100) can identify a score based on a first score calculated based on first feature data and feature data stored in memory (130), and a second score calculated based on second feature data and feature data stored in memory (130).

[0098] In one embodiment, the robot vacuum cleaner (100) can identify a first score based on first feature data and feature data stored in memory (130).

[0099] For example, a robot vacuum cleaner (100) can calculate a first score based on the number of times it has traveled through the space, the number of times a first object similar to the object has been detected at a location different from where the object was detected, and the similarity between the object and the first object. The similarity between the object and the first object may be greater than or equal to a preset first value.

[0100] For example, when an object is detected, the robot vacuum cleaner (100) can acquire feature data for the object using a sensor (110). The robot vacuum cleaner (100) can identify the number of times a first object similar to the object has been detected in the past at a location different from the location where the object was detected, by using the feature data for the object and the feature data for each of the plurality of objects stored in memory (130). For example, the robot vacuum cleaner (100) can identify at least one object among the plurality of objects that was previously detected at a location different from the object based on the location of the object and the location of each of the plurality of objects. The robot vacuum cleaner (100) can identify the first object among the at least one object. For example, the robot vacuum cleaner (100) can convert the feature data for the characteristics of the object into a first vector and convert the feature data for the characteristics of the at least one object into at least one second vector. The robot vacuum cleaner (100) can calculate the similarity between the first vector and the at least one second vector and identify the first object among the at least one object based on the similarity. For example, the robot vacuum cleaner (100) can identify a first object among the at least one object whose similarity to the object is greater than or equal to a preset first value. The similarity between vectors can be calculated by a method such as cosine similarity. The robot vacuum cleaner (100) can identify the number of times the first object was detected when it traveled through the space in the past, and identify the number of times a first object similar to the object was detected at a location different from the location where the object was detected.

[0101] For example, the robot vacuum cleaner (100) can calculate a first score based on the following mathematical formula 1.

[0102]

[0103] Here, s1 is the first score, discoveredanywhere is the number of times the robot vacuum cleaner (100) has traveled through the space, discoveredelsewhere is the number of times the robot vacuum cleaner (100) has detected the first object, and similarity may be the similarity between the object and the first object.

[0104] In one embodiment, the robot vacuum cleaner (100) can identify a second score based on the second feature data and the feature data stored in the memory (130).

[0105] For example, a robot vacuum cleaner (100) can identify a second score based on the occupancy rate of the location where an object is detected and the variability corresponding to the presence or absence of an object at the location.

[0106] Occupancy rate can refer to the extent to which a location where an object is detected was previously occupied by an object. Occupancy rate can be calculated based on the number of times an object was previously detected at the location where the object is detected.

[0107] For example, when an object is detected, the robot vacuum cleaner (100) can acquire feature data for the object using a sensor (110). The robot vacuum cleaner (100) can identify the number of times an object was detected in the past at the location where the object was detected by using the feature data for the object and the feature data for each of the plurality of objects stored in memory (130). For example, the robot vacuum cleaner (100) can identify the number of times a second object was detected in the past at the location where the object was detected based on the location of the object and the location of each of the plurality of objects. The second object may be an object that is substantially the same as the object. Being identical to the object means that the similarity between the object and the second object, calculated based on the feature data for the characteristics of the second object and the feature data for the characteristics of the object, is greater than a preset second value. The preset second value may be a value greater than a preset first value for identifying an object similar to the object (e.g., a first object). However, the present disclosure is not limited thereto. For example, the second object may be an object that is not identical to the object.

[0108] The robot vacuum cleaner (100) can identify the occupancy rate of the location where an object is detected. For example, the occupancy rate may be the value of a second number of times relative to a first number of times. The first number is the number of times the robot vacuum cleaner (100) has traveled through the space in the past, and the second number is the number of times a second object was detected in the past at the location where the object is detected.

[0109] Variability may refer to the variability regarding the presence or absence of an object at a location where the object is detected. For example, even if the number of times an object was detected in the past at a location where the object is detected is the same, the variability corresponding to a case where the time the object was continuously located at the said location is long may be set to a smaller value than the variability corresponding to a case where the time the object was continuously located at the said location is short. The memory (130) may store information (e.g., a numerical value representing variability) corresponding to the variability corresponding to the time the object was continuously located at the said location for each number of times the object was detected. The robot vacuum cleaner (100) may identify the number of times a second object was continuously detected in the past at a location where the object was detected based on feature data for a plurality of objects stored in the memory (130), and obtain the variability corresponding to the identified number of times using the information stored in the memory (130). The second object may be the same object as the object, or may be an object that is not the same as the object.

[0110] For example, the robot vacuum cleaner (100) can calculate a second score based on the following mathematical formula 2.

[0111]

[0112] Here, s2 can be the second score, occupancyrate can be the share, and variability can be the variability.

[0113] In one embodiment, the robot vacuum cleaner (100) can obtain a score based on a first score and a second score. For example, the robot vacuum cleaner (100) can calculate a score based on the following mathematical formula 3.

[0114]

[0115] Here, s is the score, s1 is the first score, s2 is the second score, and α1, β1 may be the weights.

[0116] In one embodiment, confidence may be a score used to determine the confidence of the score. The robot vacuum cleaner (100) can identify whether the score for an object is a reliable score based on the confidence. For example, the confidence may be a value between 0 and 1. The higher the confidence, the more reliable the score for the object may be.

[0117] In one embodiment, the robot vacuum cleaner (100) can identify reliability based on a first reliability calculated based on first feature data and feature data stored in memory (130) and a second reliability calculated based on second feature data and feature data stored in memory (130).

[0118] In one embodiment, the robot vacuum cleaner (100) can identify a first reliability based on the first feature data and the feature data stored in the memory (130).

[0119] The robot vacuum cleaner (100) can calculate a first reliability based on the similarity between an object and a first object. As described above, the first object is similar to the object and may be an object that was previously detected at a location different from the location where the object was detected.

[0120] For example, the robot vacuum cleaner (100) can calculate a first reliability based on the following mathematical formula 4.

[0121]

[0122] Here, c1 may be the first confidence level, and similarity may be the similarity between the object and the first object.

[0123] In one embodiment, the robot vacuum cleaner (100) can identify a second reliability based on the second feature data and the feature data stored in the memory (130).

[0124] For example, a robot vacuum cleaner (100) can identify a second reliability based on the data recency used to calculate the share and the data sufficiency used to calculate the share and variability.

[0125] Recentness may indicate whether the data used to calculate the occupancy rate was recently collected and stored in memory (130). For example, the higher the recentness of the data used to calculate the occupancy rate, the more likely it is that the second object was at the location where the object was detected relatively recently. Additionally, the lower the recentness of the data used to calculate the occupancy rate, the more likely it is that the second object was at the location where the object was detected a long time ago. Memory (130) may store information corresponding to the recentness corresponding to the time of data collection (e.g., a numerical value indicating recentness). The robot vacuum cleaner (100) can obtain the recentness corresponding to the time of data collection used to calculate the occupancy rate by using the information stored in memory (130).

[0126] Sufficiency can indicate whether the amount of data used to calculate the occupancy rate and variability is sufficient. For example, the more times the robot vacuum cleaner (100) travels through the space and the greater the amount of data obtained, the more sufficient the data used to calculate the occupancy rate and variability can be considered. In addition, the less times the robot vacuum cleaner (100) travels through the space and the less the amount of data obtained, the less sufficient the data used to calculate the occupancy rate and variability can be considered. For example, the occupancy rate and variability may be set to a higher value of sufficiency when calculated based on feature data obtained while the robot vacuum cleaner (100) travels through the space n1 times (n1 > n2) than when calculated based on feature data obtained while the robot vacuum cleaner (100) travels through the space n2 times (n1 > n2). The memory (130) can store information regarding sufficiency (e.g., a numerical value indicating sufficiency) corresponding to the amount of data (or the number of times the robot vacuum cleaner (100) travels through the space). The robot vacuum cleaner (100) can obtain sufficiency corresponding to the amount of data by using information stored in the memory (130).

[0127] For example, the robot vacuum cleaner (100) can calculate a second reliability based on the following mathematical formula 5.

[0128]

[0129] Here, c2 may be the second reliability, data recency may be recency, and data sufficiency may be sufficiency.

[0130] In one embodiment, the robot vacuum cleaner (100) can identify reliability based on a first reliability and a second reliability. For example, the robot vacuum cleaner (100) can calculate reliability based on the following mathematical formula 6.

[0131]

[0132] Here, c may be the confidence level, c1 the first confidence level, c2 the second confidence level, and α2 and β2 may be weights. Since the first confidence level, based on feature data regarding the characteristics of an object, is a more important factor than the second confidence level, α2 >> β2 may be true.

[0133] In operation 450, the robot vacuum cleaner (100) can identify whether an object is a movable object based on a score and reliability.

[0134] FIG. 5 is a diagram illustrating an example of an operation in which a robot vacuum cleaner identifies whether an object is a movable object based on a score and reliability according to one embodiment. A processor (140) may perform at least one of the operations of FIG. 5. Instructions stored in memory (130) may cause the robot vacuum cleaner (100) to perform the operations of FIG. 5 when executed individually or collectively by the processor (140).

[0135] In operation 510, the robot vacuum cleaner (100) can compare the reliability of the score with a reference value.

[0136] In operation 510-N, if the reliability of the robot vacuum cleaner (100) is less than a reference value, operations 430 and 440 may be performed again. For example, the reference value may be set at the time of manufacturing or initial use of the robot vacuum cleaner (100), or may be set and changed by user input. For example, the reference value may be 0.8.

[0137] In one embodiment, the robot vacuum cleaner (100) may move to a different location and then use the sensor (110) to acquire feature data about an object. The other location may be the surroundings of the object. For example, the robot vacuum cleaner (100) may additionally collect first feature data about an object and perform operations 430 and 440 based on the additionally acquired first feature data to obtain a score and reliability.

[0138] In operation 510-Y, 520, the robot vacuum cleaner (100) can compare the score for an object with the reference value if the reliability is greater than or equal to the reference value. For example, the reference value may be set at the time of manufacturing or initial use of the robot vacuum cleaner (100), or may be set and changed by user input. For example, the reference value may be 0.8.

[0139] In operation 520-Y, 530, the robot vacuum cleaner (100) can identify the object as a movable object if the score is identified as being greater than or equal to a reference value.

[0140] In operation 520-N, 540, the robot vacuum cleaner (100) can identify an object as an immovable object if the score is identified as being smaller than a reference value.

[0141] Returning to Fig. 4, in operation 460-N, 470, the robot vacuum cleaner (100) can move to another area if it identifies the object as being immovable.

[0142] In one embodiment, if the robot vacuum cleaner (100) identifies that an object is an immovable object, it may not clean the area where the object is located and may move to another area to perform a cleaning operation.

[0143] In operation 460-Y, 480, if the robot vacuum cleaner (100) identifies that the object is a movable object, it can provide a notification to the user to request the movement of the object.

[0144] In one embodiment, when the robot vacuum cleaner (100) identifies that an object is a movable object, it can send a notification to an electronic device requesting the movement of the object through a communication interface (120) based on a cleaning cycle for the area where the object is located.

[0145] The robot vacuum cleaner (100) can identify a cleaning cycle for an area where an object is located. The cleaning cycle may be a time interval during which the robot vacuum cleaner (100) cleans the area where an object is located.

[0146] For example, the cleaning cycle may be set at the time of manufacturing or initial use of the robot vacuum cleaner (100), or may be set and changed by user input. The memory (130) may store information regarding the cleaning cycle. The robot vacuum cleaner (100) may identify the cleaning cycle for the area where an object is located using the information stored in the memory (130).

[0147] For example, the cleaning cycle can be determined based on cleaning history data.

[0148] For example, cleaning history data may include information about the time at which the robot vacuum cleaner (100) cleaned each of a plurality of locations. For example, regarding the area where an object is currently located, the robot vacuum cleaner (100) may perform a cleaning operation at a past time when the object was not located and store information about the time at which the cleaning was performed in memory (130). The robot vacuum cleaner (100) can identify the cleaning cycle for the area where the object is located by using the information stored in memory (130) to identify the time interval at which cleaning was performed for the area where the object is located. For example, if cleaning for the area where the object is located is performed at 3-day intervals, the robot vacuum cleaner (100) can identify the cleaning cycle for the area where the object is located as 3 days.

[0149] For example, cleaning history data may include information regarding the amount of dust obtained when the robot vacuum cleaner (100) cleans each of a plurality of locations. The sensor (110) may further include a dust detection sensor for detecting the amount of dust. The robot vacuum cleaner (100) may detect the amount of dust sucked in while performing cleaning using the dust detection sensor and store information regarding the amount of dust in the memory (130). The robot vacuum cleaner (100) may identify the cleaning cycle for the area where an object is located based on the amount of dust. For example, the memory (130) may store information regarding the cleaning cycle corresponding to the amount of dust. The cleaning cycle may be set to become shorter as the amount of dust increases, and longer as the amount of dust decreases. The robot vacuum cleaner (100) may identify the cleaning cycle for the area where an object is located corresponding to the amount of dust using the information stored in the memory (130).

[0150] In one embodiment, the robot vacuum cleaner (100) can identify whether a cleaning cycle has elapsed for the area where an object is located.

[0151] For example, the robot vacuum cleaner (100) can identify that the cleaning cycle has elapsed if it identifies that the time interval between the current time and the time when the last cleaning was performed on the area where the object is located is greater than or equal to the cleaning cycle. The robot vacuum cleaner (100) can identify that the cleaning cycle has not elapsed if it identifies that the time interval between the current time and the time when the last cleaning was performed on the area where the object is located is less than the cleaning cycle.

[0152] In one embodiment, if the robot vacuum cleaner (100) identifies that the cleaning cycle has not elapsed, it may not clean the area where the object is located, but instead move to another area and perform a cleaning operation.

[0153] In one embodiment, when the robot vacuum cleaner (100) identifies that the cleaning cycle has elapsed, it provides a notification to the user requesting the movement of an object, and can move to another area to perform a cleaning operation without cleaning the area where the object is located. For example, the robot vacuum cleaner (100) can transmit a control command for displaying the notification to a server via a communication interface (120), so that the server displays the notification on an electronic device.

[0154] For example, the server can perform functions such as managing user accounts, registering devices (e.g., robot vacuum cleaner (100)) associated with user accounts, and managing or controlling the registered devices. For example, a user can create a user account by accessing the server through an electronic device. The electronic device may be a user device. For example, a user device may include, but is not limited to, a personal computer, a terminal, a portable telephone, a smartphone, a handheld device, or a wearable device (e.g., a smart watch, a smart ring). A user account may be identified by an ID and password set by the user. The server may register devices to the user account according to a set procedure. For example, the server may register, manage, and control devices by linking the registration information of the devices to the user account.

[0155] In one embodiment, an application may be stored in the memory of an electronic device. The application may be installed on the electronic device at the time of manufacturing or downloaded and installed from an external server. For example, by running an application installed on the electronic device, a user can access a server to create a user account and communicate with the server based on the logged-in user account to register, manage, and control devices.

[0156] In one embodiment, the server may transmit a control command to at least one of the devices. A device that receives the control command and performs an action corresponding to the control command may be referred to as the target device. The control command may refer to data that causes a controllable device to perform a specific action. The specific action is an action performed by the device and may include, but is not limited to, the output of information, detection (or sensing) of information, and management of information (e.g., deletion or creation). A user may control the target device among the devices using an application installed on an electronic device. For example, when a user logs into a user account using an application installed on an electronic device, the devices registered to the user account may be displayed on the display of the electronic device. The user may input user input into the application to control the target device among the devices. The server may obtain information (or a request) for generating a control command from the electronic device, generate a control command based on the received request, and transmit the generated control command to the target device.

[0157] In one embodiment, when the robot vacuum cleaner (100) identifies that an object is a movable object, it can plan a path to clean the area where the object is located. For example, when the robot vacuum cleaner (100) performs the next cleaning operation after the current cleaning operation is completed, it can plan a path to clean an area that was not previously cleaned (e.g., an area where the object was located) and perform the cleaning operation by moving along the path.

[0158] FIGS. 6, FIGS. 7, and FIGS. 8 are drawings for illustrating an example of an operation in which a robot vacuum cleaner cleans an area where an object is located, according to one embodiment.

[0159] Referring to 601 in FIG. 6, the robot vacuum cleaner (100) can detect a chair (610) in the living room and acquire feature data for the chair (610) to identify whether the chair (610) is a movable object. If the robot vacuum cleaner (100) identifies that the chair (610) is a movable object, it can send a notification to the user's electronic device via a server to request the movement of the chair (610). Referring to 602 in FIG. 6, the robot vacuum cleaner (100) can move around the chair (610) and perform a cleaning operation on another area.

[0160] Referring to FIG. 7, the electronic device (700) can display a notification (710) received from a server. The notification (710) may include text such as "Please remove objects in the living room for cleaning the living room."

[0161] For example, when the electronic device (700) receives user input rejecting a request to move an object (e.g., touch input to a "No" button), it can transmit the user input to a server. When the robot vacuum cleaner (100) receives user input from the server, it may identify the chair (e.g., 610 in FIG. 6) as an immovable object and not perform a cleaning action on the area where the chair (610) is located.

[0162] For example, when the electronic device (700) receives user input accepting a request to move an object (e.g., touch input to a "Yes" button), it can transmit the user input to a server. When the robot vacuum cleaner (100) receives user input from the server, it can plan a path to clean the area where the chair (e.g., 610 in FIG. 6) is located. For example, the user can move the chair (610) in the living room to another location. Referring to 801 and 802 in FIG. 8, the robot vacuum cleaner (100) can clean the area where the chair is located in the living room the next time it cleans the living room.

[0163] According to various embodiments of the present disclosure as described above, the robot vacuum cleaner (100) can determine whether an object is a movable object or an immovable object and provide a notification to the user according to the cleaning cycle. Accordingly, when the object is moved by the user, the robot vacuum cleaner can clean the area where the object was located, and the inconvenience of the user having to manually search for obstacles every time before cleaning by the robot vacuum cleaner is minimized.

[0164] FIG. 9 is a diagram illustrating the operations of a robot vacuum cleaner according to one embodiment. A processor (140) may perform at least one of the operations of FIG. 9. Instructions stored in memory (130) may cause the robot vacuum cleaner (100) to perform the operations of FIG. 9 when executed individually or collectively by the processor (140).

[0165] In operations 910 and 920, the robot vacuum cleaner (100) can drive through the space and detect objects. Since the description of operations 410 and 420 can be applied to operations 910 and 920 respectively, a repeated description is omitted.

[0166] In operation 930, the robot vacuum cleaner (100) can identify whether there is labeling for the object.

[0167] In one embodiment, the robot vacuum cleaner (100) can identify whether labeling information for a detected object is stored in memory (130). Memory (130) can store labeling information corresponding to the type of the object. The robot vacuum cleaner (100) can identify whether there is a label for the object by identifying whether labeling information corresponding to the type of the detected object is stored in memory (130).

[0168] In one embodiment, the labeling information may include information indicating whether the object is a movable object or a non-movable object. Alternatively, the labeling information may include feature data regarding the characteristics of the object. The labeling information may be input by a user. For example, an interface screen for inputting the labeling may be provided through an application installed on an electronic device. The electronic device may transmit the labeling information input through the interface screen to the robot vacuum cleaner (100) via a server.

[0169] In operations 930-N and 940, if the robot vacuum cleaner (100) identifies that there is no labeling for the object, it can obtain first feature data regarding the characteristics of the object and second feature data regarding the environment located on the object. Since the description of operation 430 can be applied to operation 940, a repeated description is omitted.

[0170] In operations 950 and 960, the robot vacuum cleaner (100) obtains a score and a confidence level for the score indicating whether the object is a movable object based on the first feature data and the second feature data, and can identify whether the object is a movable object based on the score and confidence level for the object. Since the description of operations 440 and 450 can be applied to operations 950 and 960 respectively, a repeated description is omitted.

[0171] In operation 930-Y, when the robot vacuum cleaner (100) identifies that there is a label for an object, it can identify whether the object is a movable object or a non-movable object based on the label information.

[0172] In operations 970-N, 980, the robot vacuum cleaner (100) can move to another area if it identifies the object as an immovable object. Since the description of operations 460-N, 470 can be applied to operations 970-N, 980, a repeated description is omitted.

[0173] In operation 970-Y, 990, if the robot vacuum cleaner (100) identifies that the object is a movable object, it may provide a notification to the user to request the movement of the object. Since the description of operation 460-Y, 480 can be applied to operation 970-Y, 990, a repetitive description is omitted.

[0174] In the present disclosure, the artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the robot vacuum cleaner (100) itself where the artificial intelligence model is executed, or through a separate server. The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers. The artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may additionally or substantially include a software structure.

[0175] Various embodiments of the present document may be implemented as software comprising one or more instructions stored in a storage medium (e.g., memory (130)) readable by a machine (e.g., robot vacuum cleaner (100)). For example, a processor (e.g., processor (140)) of the machine (e.g., robot vacuum cleaner (100)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0176] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or an application store (e.g., Play Store). ™It can be distributed online (e.g., downloaded or uploaded) through ) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0177] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0178] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

Claims

1. Regarding robot vacuum cleaners, Sensor; Communication interface; Memory for storing instructions; and at least one processor including processing circuitry; and When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, When an object is detected by the sensor while driving in space, the sensor is used to obtain first feature data regarding the characteristics of the object and second feature data regarding the environment in which the object is located. Based on the first and second feature data above, a score indicating whether the object is a movable object and a confidence level for the score are obtained, and Based on the above score and the above reliability, identify whether the object is a movable object, and A robot vacuum cleaner that, when the object is identified as a movable object, transmits a notification to an electronic device requesting the movement of the object through the communication interface based on the cleaning cycle for the area where the object is located.

2. In Paragraph 1, The above memory stores data regarding a plurality of objects acquired using the sensor while the robot vacuum cleaner previously traveled through the space, and The data for the above plurality of objects is, A robot vacuum cleaner comprising feature data regarding the characteristics of the plurality of objects and feature data regarding the environment in which the plurality of objects are located.

3. In Paragraph 2, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, Identifying the score based on the first score calculated based on the first feature data and the feature data stored in the memory, and the second score calculated based on the second feature data and the feature data stored in the memory. A robot vacuum cleaner that identifies the reliability based on a first reliability calculated based on the first feature data and the feature data stored in the memory, and a second reliability calculated based on the second feature data and the feature data stored in the memory.

4. In Paragraph 3, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, The first score is calculated based on the number of times the space is traveled, the number of times a first object similar to the object is detected at a location different from the location where the object is detected, and the similarity between the object and the first object. A robot vacuum cleaner in which the similarity between the above object and the above first object is greater than or equal to a preset value.

5. In Paragraph 4, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, A robot vacuum cleaner that obtains the first reliability based on the similarity between the object and the first object.

6. In Paragraph 3, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, A robot vacuum cleaner that calculates the second score based on the occupancy rate of the location where the object is detected and the variability corresponding to the presence or absence of the object at the location where the object is detected.

7. In Paragraph 6, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, A robot vacuum cleaner that obtains the second reliability based on the timeliness of the data used to calculate the above share and the sufficiency of the data used to calculate the above share and the above variability.

8. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, If the above reliability is greater than or equal to a preset value and the above score is greater than or equal to a preset value, the object is identified as a movable object, and If the above reliability is smaller than a preset value, the first feature data for the object is additionally acquired using the sensor, and Based on the additionally acquired first feature data above, the score and the reliability are obtained, and A robot vacuum cleaner that identifies whether the object is a movable object based on the above score and the above reliability.

9. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the robot vacuum cleaner, Identify the cleaning cycle for the area for the above object, and A robot vacuum cleaner that transmits the notification to an electronic device when it is identified that the above cleaning cycle has elapsed.

10. A cleaning method of a robot vacuum cleaner including a sensor, When an object is detected by the sensor while traveling through space, the operation of obtaining first feature data regarding the characteristics of the object and second feature data regarding the environment in which the object is located using the sensor; An operation to obtain a score indicating whether the object is a movable object and a reliability of the score based on the first and second feature data; An action of identifying whether the object is a movable object based on the above score and the above reliability; and A cleaning method comprising: an action of transmitting a notification to an electronic device requesting the movement of the object through the communication interface based on a cleaning cycle for the area where the object is located, when the object is identified as a movable object.

11. In Paragraph 10, The robot vacuum cleaner stores data regarding a plurality of objects acquired using the sensor while the robot vacuum cleaner previously drove through the space, and The data for the above plurality of objects is, A cleaning method comprising feature data regarding the characteristics of the plurality of objects and feature data regarding the environment in which the plurality of objects are located.

12. In Paragraph 11, The operation of obtaining the above score and reliability is, An operation of identifying the score based on the first score calculated based on the first feature data and the feature data stored in the memory, and the second score calculated based on the second feature data and the feature data stored in the memory; and A cleaning method comprising: an operation of identifying the reliability based on the first reliability calculated based on the first feature data and the feature data stored in the memory, and the second reliability calculated based on the second feature data and the feature data stored in the memory.

13. In Paragraph 12, The operation of identifying the above score is, The operation of calculating the first score based on the number of times the space was traveled, the number of times a first object similar to the object was detected at a location different from the location where the object was detected, and the similarity between the object and the first object; A cleaning method in which the similarity between the above object and the above first object is greater than or equal to a preset value.

14. In Paragraph 13, The operation of identifying the above reliability is, A cleaning method comprising: an operation to obtain the first reliability based on the similarity between the object and the first object.

15. In Paragraph 12, The operation of identifying the above score is, A cleaning method comprising: an operation to calculate the second score based on the occupancy rate of the location where the object is detected and the variability corresponding to the presence or absence of the object at the location where the object is detected.

Images