Robot and control method therefor

Abstract

This drivable robot comprises: at least one sensor; a driving unit; at least one processor; and a memory for storing at least one instruction for, when executed by the at least one processor, identifying free space information of a free space in a revolving door and object information about an object that is scheduled to enter the revolving door on the basis of a captured image if the revolving door is identified in the captured image acquired by the at least one sensor, identifying a first time point at which the robot can enter the revolving door on the basis of the identified free space information and the object information, and controlling the driving unit so that the robot enters the revolving door at the first time point.

Description

Robot and method for controlling the same

[0001] The present disclosure relates to a robot and a control method thereof, and more particularly, to a robot that passes through a revolving door by considering information about the revolving door and information about an object obtained based on a captured image of a driving space, and a control method thereof.

[0002] Thanks to the advancement of electronic technology, various types of electronic devices are being developed and distributed, and recently, for example, technological development for robots that provide services to users is being promoted.

[0003] For robots navigating a specific space to provide services to users, they may encounter a revolving door along their route. To safely navigate a revolving door, the robot must consider its characteristics and operating conditions. Furthermore, the paths of people currently using or planning to use the revolving door must be taken into consideration when navigating through the revolving door.

[0004] According to one embodiment of the present disclosure, a mobile robot includes at least one sensor, a driving unit, at least one processor, and a memory that stores at least one command that, when executed by the at least one processor, identifies a revolving door in a captured image acquired by the at least one sensor, identifies free space information of a free space within the revolving door and object information about an object scheduled to enter the revolving door based on the captured image, identifies a first time point at which the robot can enter the revolving door based on the identified free space information and the object information, and controls the driving unit to allow the robot to enter the revolving door at the first time point.

[0005] The one or more processors may execute at least one command to control the driving unit so that the robot enters the revolving door when it is identified that the robot can enter the revolving door at the current time, and to control the driving unit so that the robot waits until a second time when the robot can enter the revolving door when it is identified that the robot cannot enter the revolving door at the current time, or to identify a driving path that avoids the revolving door.

[0006] The memory stores first space information corresponding to the robot, and the one or more processors can execute at least one command to identify whether a first shape of a space corresponding to the robot is included in a second shape of the free space based on the free space information and the first space information corresponding to the robot, and, if it is identified that the first shape is included in the second shape, to identify a third point in time at which the robot can enter the revolving door based on the first position of the free space.

[0007] The memory further includes second spatial information corresponding to the object, the object information further includes movement path information about a movement path of the object, and the one or more processors can execute at least one command to update the free space information based on the second spatial information when it is identified that the robot is about to enter the revolving door based on the movement path information, identify whether the first shape is included in the second shape based on the updated free space information and the first spatial information, and identify a fourth time point at which the robot can enter the revolving door based on a second position of the updated free space when it is identified that the first shape is included in a third shape of the updated free space of the updated free space information.

[0008] The one or more processors may execute at least one command to identify the number of the at least one second object and the entry position within the revolving door when at least one second object is identified as being scheduled to enter the revolving door based on the movement path information, and to identify a fifth entry point of the robot based on the number of the at least one second object and the entry position within the revolving door.

[0009] The free space information includes at least one of radius information, rotation axis information, and angle information corresponding to the free space, and the one or more processors can execute at least one command to identify position information for a third position of the free space within the revolving door and movement speed information of the free space based on the free space information, and to identify a sixth entry point of the robot based on the position information and the movement speed information.

[0010] The one or more processors may execute at least one command to control the driving unit so that the robot is positioned in the center region of an inscribed circle corresponding to the free space when the robot enters the revolving door.

[0011] The one or more processors may execute at least one command to control the driving unit to identify a preset reference point within the swing door corresponding to the free space when the robot enters the revolving door, and to move along the preset reference point.

[0012] The one or more processors may execute at least one command to identify first control information for positioning the robot in a central region of an inscribed circle corresponding to the free space, identify second control information for moving the robot by following the preset reference point, identify third control information for moving the robot within the revolving door by applying preset weights to each of the first control information and the second control information, and control the driving unit based on the third control information.

[0013] The one or more processors may execute at least one command to control the driving unit to exit the revolving door within a preset time from a seventh time point at which the robot is identified as being located within the preset distance when the robot enters the revolving door, and to identify whether the swing door corresponding to the free space is located within a preset distance from a target location outside the revolving door.

[0014] The one or more processors may be configured to identify whether at least one third object located within the revolving door has exited the revolving door, and, if the at least one third object is identified as having exited the revolving door, execute at least one command to control the driving unit to exit the revolving door within a preset time from the seventh time point identified as being located within the preset distance.

[0015] Meanwhile, a method for controlling a robot capable of driving according to an embodiment includes, when a revolving door is identified in a captured image acquired by at least one sensor, a step of identifying free space information about a free space within the revolving door and object information about an object scheduled to enter the revolving door based on the captured image, a step of identifying a first time point at which the robot can enter the revolving door based on the free space information and the object information, and a step of controlling a driving unit so that the robot enters the revolving door at the first time point.

[0016] The step of controlling the driving unit may further include, if it is determined that the robot can enter the revolving door at the current time, controlling the driving unit to allow the robot to enter the revolving door, and the control method may further include, if it is determined that the robot cannot enter the revolving door at the current time, controlling the driving unit to wait until a second time when the robot can enter the revolving door or identifying a driving path that avoids the revolving door.

[0017] The step of identifying the first point in time may include a step of identifying whether a first shape of a space corresponding to the robot is included in a second shape of the free space based on the free space information and the first space information corresponding to the robot, and a step of identifying a third point in time at which the robot can enter the revolving door based on the first position of the free space when the first shape is identified as being included in the second shape.

[0018] The object information further includes movement path information about the movement path of the object, and the step of identifying the first point of interest includes, when it is determined that the robot is about to enter the revolving door based on the movement path information, updating the free space information based on the second space information, identifying whether the first shape is included in the second shape based on the updated free space information and the first space information, and when it is determined that the first shape is included in a third shape of the updated free space of the updated free space information, identifying a fourth point of time at which the robot can enter the revolving door based on the second position of the updated free space.

[0019] The step of identifying the first point in time may include, when at least one second object is identified as being scheduled to enter the revolving door based on the movement path information, identifying the number of the at least one second object and the entry position within the revolving door, and identifying a fifth entry point in time for the robot based on the number of the at least one second object and the entry position within the revolving door.

[0020] The free space information includes at least one of radius information, rotation axis information, and angle information corresponding to the free space, and the step of identifying the first point in time may identify position information for a third position of the free space within the revolving door and movement speed information of the free space based on the free space information, and identify a sixth entry point of the robot based on the position information and the movement speed information.

[0021] The above control method may further include a step of controlling the driving unit so that the robot is positioned in the center area of ​​an inscribed circle corresponding to the free space when the robot enters the revolving door.

[0022] The above control method may further include a step of identifying a preset reference point within the swing door corresponding to the free space when the robot enters the revolving door, and controlling the driving unit to move by following the preset reference point.

[0023] A non-transitory computer-readable recording medium storing computer instructions that, when executed by at least one processor, cause a robot capable of driving to perform the following operations, the operations include: when a revolving door is identified in a photographed image acquired by at least one sensor, identifying free space information about a free space within the revolving door and object information about an object scheduled to enter the revolving door based on the photographed image; identifying a first time point at which the robot can enter the revolving door based on the free space information and the object information; and controlling a driving unit so that the robot enters the revolving door at the first time point.

[0024] The above-described and other features of one embodiment of the present disclosure and the advantages of specific embodiments are made clear by the following description taken in conjunction with the accompanying drawings.

[0025] FIG. 1 is a drawing schematically illustrating a method for controlling a robot according to one or more embodiments.

[0026] FIG. 2 is a block diagram showing the configuration of a robot according to one or more embodiments.

[0027] FIG. 3 is a flowchart for explaining a method for controlling a robot according to one or more embodiments.

[0028] FIG. 4 is a diagram for explaining edge information and free space information corresponding to a revolving door according to one or more embodiments.

[0029] FIG. 5 is a diagram illustrating a method for identifying an entry point according to one or more embodiments.

[0030] FIG. 6 is a drawing for explaining a method for identifying a point in time at which an object can enter a revolving door by considering one or more embodiments.

[0031] FIGS. 7A and 7B are drawings for explaining a method for identifying a possible entry point of a robot according to one or more embodiments.

[0032] FIG. 8A and FIG. 8B are drawings for explaining a method of driving a robot inside a revolving door according to one or more embodiments.

[0033] FIG. 9 is a drawing for explaining a method of moving a robot within a revolving door according to one or more embodiments.

[0034] FIG. 10 is a drawing for explaining a method for a robot to move to a target position according to one or more embodiments.

[0035] FIGS. 11A and 11B are drawings illustrating a method for a robot to exit a revolving door according to one or more embodiments.

[0036] FIG. 12 is a flowchart illustrating a method for identifying whether entry into a revolving door is possible according to one or more embodiments.

[0037] Fig. 13 is a block diagram showing the configuration of a robot according to one or more embodiments.

[0038] Fig. 14 is a block diagram for explaining a method of controlling a robot according to one or more embodiments.

[0039] Hereinafter, the present disclosure will be described in detail with reference to the attached drawings.

[0040] The terms used in this specification will be briefly explained, and the present disclosure will be described in detail.

[0041] The terms used in one or more embodiments of this disclosure are generally and widely used terms, as far as possible, considering the functions of this disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description of the relevant disclosure. Therefore, the terms used in this disclosure should not be defined simply as names of terms, but rather based on the meanings of the terms and the overall content of this disclosure.

[0042] The expressions "has," "may have," "includes," or "may include" indicate the presence of a feature (e.g., a number, function, operation, or component such as a part) and do not exclude the presence of additional features.

[0043] The expression "at least one of A and / or B" should be understood to mean either "A" or "B" or "A and B".

[0044] Expressions such as "first," "second," "first," or "second," can describe various components, regardless of order and / or importance, and are used only to distinguish one component from another, but do not limit the components in question.

[0045] When it is said that a component (e.g., a first component) is “(operatively or communicatively) coupled with / to” or “connected to” another component (e.g., a second component), it should be understood that the component may be directly coupled to the other component, or may be coupled via another component (e.g., a third component).

[0046] Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "comprise" or "consist of" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof, but should be understood not to preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0047] In the present disclosure, a "module" or "part" performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Furthermore, multiple "modules" or multiple "parts" may be integrated into at least one module and implemented as at least one processor, excluding any "modules" or "parts" that need to be implemented in hardware.

[0048] FIG. 1 is a drawing schematically illustrating a method for controlling a robot according to one or more embodiments.

[0049] According to FIG. 1, according to one or more embodiments, a robot (10) can travel within a driving space to reach a destination. The robot (10) may be a robot that moves to a specific location and provides services to a user. According to one or more embodiments, the robot may be a different type of driving robot, including, but not limited to, a drone or a wheeled robot.

[0050] According to one embodiment, the robot (10) may pass through a revolving door (1) to reach a destination. Here, the revolving door (1) may be a cylindrical object including a plurality of rotatable doors (or swing doors). According to one or more embodiments, the robot (10) may acquire a photographed image of a driving space. The robot (10) may identify a revolving door (1) within a driving path based on the acquired photographed image of the driving space. According to one or more embodiments, the revolving door (1) may rotate at a preset speed, and the speed may vary depending on the presence or absence of an object, but is not limited thereto. It is to be understood that the revolving door may rotate at a preset speed regardless of the presence or absence of an object. Here, the object may be a person according to one or more embodiments, but is not limited thereto, and may of course be a robot or an animal entering or exiting the revolving door. According to one embodiment, when the revolving door (1) is identified, the robot (10) may identify a time point at which the revolving door (1) can be entered. The robot (10) can identify a time point at which it can enter the revolving door (1) by using information about the space in which the robot (10) can move within the revolving door (1) and information about an object that has entered or is scheduled to enter the revolving door (1).

[0051] The robot (10) can enter the revolving door (1) based on the identified entry point of the revolving door (1). When the robot (10) enters the revolving door (1), the robot (10) can move within the revolving door (1) based on the movement speed of the revolving door (1). In this case, the robot (10) can also move to a state located in a preset area within the revolving door (1) by taking into account objects within the revolving door (1).

[0052] Below, various embodiments are described for determining when it is possible to enter a revolving door, entering the revolving door at an appropriate time, driving within the revolving door while considering information about free space and objects within the revolving door, and safely exiting the revolving door while considering information about the edge of the revolving door and objects.

[0053] FIG. 2 is a block diagram showing the configuration of a robot according to one or more embodiments.

[0054] According to FIG. 2, the robot (100) may include at least one sensor (110), a driving unit (120), and one or more processors (130).

[0055] At least one sensor (110, hereinafter referred to as a sensor) may include a plurality of sensors of various types. The sensor (110) may measure a physical quantity or detect an operating status of the robot (100) and convert the measured or detected information into an electrical signal. The sensor (110) may include a camera, and the camera may include a lens that focuses visible light or other optical signals reflected by an object and received onto an image sensor, and an image sensor that may detect visible light or other optical signals. Here, the image sensor may include a 2D pixel array divided into a plurality of pixels. According to one or more embodiments, the robot (100) may obtain a photographic image of a driving space through at least one sensor (110).

[0056] The camera according to one or more embodiments may be implemented as a depth camera. Furthermore, according to one or more embodiments, the sensor (110) may include a thermal imaging sensor for shape reading, as well as a distance sensor such as a LIDAR (Light Detection And Ranging) sensor and a TOF (Time of Flight) sensor.

[0057] The driving unit (120) is a device that can drive the robot (100). The driving unit (120) can adjust the driving direction and driving speed according to the control of one or more processors (130), and the driving unit (120) according to one or more embodiments may include a power generation device that generates power for driving the robot (100) (for example, a gasoline engine, a diesel engine, an LPG (liquefied petroleum gas) engine, an electric motor, etc. depending on the fuel (or energy source) used), a steering device for controlling the driving direction (for example, manual steering, hydraulics steering, electronic control power steering (EPS), etc.), a driving device that drives the robot (100) according to the power (for example, wheels, propellers, etc.). Here, the driving unit (120) may be modified and implemented according to the driving type of the robot (100) (for example, wheel type, walking type, flight type, etc.).

[0058] One or more processors (130) (hereinafter, “processors”) are electrically connected to at least one sensor (110) and a driving unit (120) to control the overall operation of the robot (100). The processor (130) may be composed of one or more processors. Specifically, the processor (130) may perform operations of the robot (100) according to various embodiments of the present disclosure by executing at least one instruction stored in a memory.

[0059] According to one embodiment, the processor (130) may be implemented as a digital signal processor (DSP), a microprocessor, a graphics processing unit (GPU), an artificial intelligence (AI) processor, a neural processing unit (NPU), or a time controller (TCON) for processing a digital image signal. However, the present invention is not limited thereto, and may include one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, or may be defined by the relevant terminology. In addition, the processor (130) may be implemented as a system on chip (SoC) or large scale integration (LSI) having a built-in processing algorithm, or may be implemented in the form of an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

[0060] According to one embodiment, the processor (130) may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON). However, the present invention is not limited thereto, and may include one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, or may be defined by the corresponding terminology. In addition, the processor (130) may be implemented as a system on chip (SoC) having a built-in processing algorithm, a large scale integration (LSI), or may be implemented in the form of a field programmable gate array (FPGA).

[0061] According to one embodiment, the processor (130) may identify a revolving door within a driving space based on a captured image acquired through the sensor (110). According to one or more embodiments, the revolving door may include at least one swing door as illustrated in FIG. 1 and may include a plurality of passenger spaces. The swing door is a rotatable door that divides the space within the revolving door into a plurality of sub-spaces. According to one or more embodiments, the revolving door may include a plurality of swing doors. According to one or more embodiments, the processor (130) may acquire a captured image corresponding to the driving space through the sensor (110), and may identify a revolving door present in the acquired captured image using a learned neural network model. According to one or more embodiments, the learned neural network model may be pre-stored in a memory, and the learned neural network model may be a neural network model trained to receive a captured image of the driving space and output information on whether a revolving door exists in the captured image.

[0062] However, the present invention is not limited thereto, and according to one or more embodiments, the memory may store map information about the driving space, and the map information about the driving space may include information about the location and size of a revolving door existing within the driving space. The processor (130) may identify a revolving door within the driving space using the map information stored in the memory or a learned neural network model. According to one or more embodiments, the processor (130) may identify whether a revolving door exists on the driving path of the robot (100).

[0063] According to one embodiment, the processor (130) may identify information about a free space within a revolving door and information about an object corresponding to the revolving door. A movement space and a free space exist within the revolving door. The movement space refers to a floor area corresponding to a space within the revolving door in which a robot (100) or an object can move, and the free space refers to a floor area corresponding to a space excluding a space in which an object exists among the movement spaces within the revolving door. For example, the free space refers to a floor area corresponding to a space within the revolving door in which a robot (100) can freely move. According to one or more embodiments, the processor (130) may identify edge information corresponding to the revolving door based on a captured image, and identify movement space information and free space information within the revolving door based on the identified edge information. The edge information corresponding to the revolving door is information about an outline (or, outer line) of the revolving door existing within the captured image. However, the present invention is not limited thereto, and the edge information may also be information about a line calculated based on pixel values ​​within the captured image. The edge information may include a straight line or curve corresponding to the point where the revolving door meets the floor within the driving space, or may include a straight line perpendicular to the floor among the outlines corresponding to the revolving door.

[0064] For example, if edge information corresponding to a revolving door is identified based on a captured image, the processor (130) may identify an area for an object to board within the revolving door based on the identified edge information, and identify this as movement space information. In this case, the movement space information may be information on an area excluding an area corresponding to a swing door among the floor area of ​​the revolving door (an area where the revolving door and the floor within the driving space meet). According to one or more embodiments, the processor (130) may identify an area excluding an area occupied by an object within the movement space as a free space. In this case, an area excluding an area including a preset margin area within the area occupied by the object may be identified as a free space. The preset margin area may be an area adjacent to the floor area of ​​the object according to one or more embodiments, and may be an area located within a preset distance from the floor area. According to one or more embodiments, the movement space information may include position information and movement speed information corresponding to the movement space within the revolving door, and the free space information may include position information and movement speed information corresponding to the free space within the revolving door.

[0065] According to one or more embodiments, the processor (130) may identify information about an object corresponding to a revolving door based on a captured image. The object may be, for example, a person, but is not limited thereto. According to one or more embodiments, the object corresponding to the revolving door may include an object that has entered the revolving door or an object that is scheduled to enter the revolving door. The information about the object may include information about a movement path of the object, according to one or more embodiments. The processor (130) may identify or predict the movement path of the object using a captured image acquired in real time.

[0066] According to one embodiment, the processor (130) may identify a point in time when the robot (100) can enter the revolving door. According to one or more embodiments, the processor (130) may identify a point in time when the robot (100) can enter the revolving door based on the identified free space information and information about the identified object. For example, if the processor (130) identifies that the size of the robot (100) can be included in the free space within the revolving door, the robot (100) may enter the free space within the revolving door. In this case, the processor (130) may identify information about the rotation speed of the revolving door and the location of the revolving door entrance based on edge information of the revolving door, and may identify a point in time when the robot (100) can enter the revolving door based on the identified information.

[0067] According to one or more embodiments, the processor (130) may identify whether the robot (100) is capable of entering the revolving door. For example, if the size of the robot (100) cannot be contained within the movement space of the revolving door, the processor (130) may identify that the robot (100) is unable to enter the revolving door. Alternatively, if the size of the robot (100) is contained within the movement space of the revolving door, the processor (130) may identify that the robot (100) is capable of entering the revolving door. If the robot (100) is identified as capable of entering the revolving door, the processor (130) may identify a point in time when the robot (100) is capable of entering.

[0068] For example, the processor (130) may identify whether the robot (100) can enter the revolving door at the current time based on information about an object corresponding to the revolving door and information about free space, and if it is identified that the robot (100) can enter the revolving door at the current time, the processor (130) may control the driving unit (120) to allow the robot (100) to enter the revolving door. Alternatively, for example, the processor (130) may enter the revolving door when the movement of an object scheduled to exit the revolving door or an object scheduled to enter the revolving door has finished. In this case, the processor (130) may control the driving unit (120) to allow the robot (100) to enter the revolving door within a time period during which the entrance to the revolving door is open based on the free space information. The time period during which the entrance to the revolving door is open means a time period during which the robot can enter the revolving door because an obstacle (or a screen) that prevents the object from entering the revolving door is removed. A specific method for identifying the point in time when the robot (100) can enter the revolving door will be described in detail with reference to FIGS. 5 to 7b.

[0069] According to one embodiment, the processor (130) may control the driving unit (120) to allow the robot (100) to enter the revolving door at a time when the robot can enter the revolving door. According to one or more embodiments, the processor (130) may control the driving unit (120) to allow the robot to enter the revolving door within a time period during which the revolving door is open. In this case, if an object within the revolving door exits the revolving door or an object that is scheduled to enter the revolving door exists, the processor (130) may control the driving unit (120) to allow the robot to enter the revolving door after the object's movement has ended.

[0070] According to one embodiment, the memory may store a learned neural network model. According to one or more embodiments, the learned neural network model may be a neural network model trained to receive a captured image and output driving information for the robot (100) to pass through the revolving door (for example, at least one of entry point information for entering the revolving door, control information for controlling the driving unit (120) to enter the revolving door, control information for driving within the revolving door, exit point information for exiting the revolving door, and control information for controlling the driving unit (120) to exit the revolving door). The processor (130) may input a captured image of a driving space into the trained neural network model to obtain driving information for the robot (100) to pass through the revolving door.

[0071] FIG. 3 is a flowchart and drawing for explaining a control method of a robot (100) according to one or more embodiments.

[0072] According to FIG. 3, first, according to one embodiment, the control method can determine whether a revolving door is identified in a captured image acquired by at least one sensor (110) (S310). According to one or more embodiments, when a captured image of a driving space is acquired through the sensor (110), the processor (130) can identify whether a revolving door is included in the acquired image. For example, the processor (130) can input the captured image into a learned neural network model stored in a memory to identify whether a revolving door is included in the captured image.

[0073] Next, according to one embodiment, when a revolving door is identified in the captured image (S310: Y), the control method can identify information on a free space within the revolving door and information on an object scheduled to enter the revolving door based on the acquired captured image (S320). According to one or more embodiments, when the revolving door is identified in the captured image, the processor (130) can identify edge information corresponding to the revolving door based on the identification. The processor (130) can identify movement space information and free space information within the revolving door based on the identified edge information. In addition, the processor (130) can identify an object (e.g., a person) existing in the driving space based on the captured image. For example, the processor (130) can identify an object existing in the revolving door or an object scheduled to enter the revolving door. The processor (130) can also identify information on a movement path of an object existing in the revolving door or an object scheduled to enter the revolving door based on the captured image.

[0074] Next, according to one embodiment, the control method may identify a point in time when the robot (100) can enter the revolving door based on the identified free space information and the information about the identified object (S330). According to one or more embodiments, if the processor (130) determines that the identified free space information and the size of the robot (100) can be included in the free space within the revolving door, the robot (100) may enter the free space within the revolving door. The processor (130) may obtain information about a time interval during which the revolving door opens based on the identified free space information, and may identify a point in time when the robot (100) can enter the revolving door based on the obtained time interval information. In this case, the processor (130) may change a point in time when the robot (100) can enter the revolving door based on the information about the identified object. For example, if an object that has exited or is scheduled to exit the revolving door is identified, the processor (130) may identify a point in time when the robot (100) can enter the revolving door as a point in time after the object's exit has ended. Alternatively, if an object scheduled to enter the revolving door is identified, the processor (130) may identify the point in time at which the object can enter the revolving door as the point in time after the object's entry is completed.

[0075] Next, according to one embodiment, the control method can control the driving unit (120) to allow the robot (100) to enter the revolving door at a time when the robot can enter the revolving door (S340).

[0076] According to the above-described example, the robot (100) can obtain information about the revolving door through the captured video and use this to determine when it is possible to enter the revolving door. Once the robot (100) determines when it is possible to enter the revolving door, it can enter and move through the revolving door and reach a target location. In this case, the robot (100) can drive while taking into account objects that are passing through or are scheduled to pass through the revolving door. Accordingly, the robot (100) can safely pass through the revolving door while taking into account people around the revolving door and reach the target location without having to bypass the revolving door.

[0077] FIG. 4 is a drawing for explaining edge information and free space information corresponding to a revolving door according to one or more embodiments.

[0078] According to FIG. 4, according to one embodiment, the processor (130) can identify a revolving door (40) included in a captured image. According to one or more embodiments, the processor (130) can identify a revolving door (40) included in the captured image using a learned neural network model stored in a memory. However, the present invention is not limited thereto, and according to one or more embodiments, the processor (130) can also identify a revolving door using location information of the robot and map information stored in the memory.

[0079] According to one embodiment, when a revolving door is identified in the captured image, the processor (130) may identify edge information (400) corresponding to the identified revolving door. According to one or more embodiments, the edge information corresponding to the revolving door may include an outline of the revolving door existing in the captured image. In this case, edge information (401) for a swing door included in the revolving door may also be included. According to one or more embodiments, the edge information may include a straight line or a curved line corresponding to a point where the revolving door (40) meets the floor within the driving space, or may include a straight line perpendicular to the floor among the outlines corresponding to the revolving door.

[0080] According to one embodiment, the processor (130) may identify movement space information and free space information corresponding to the revolving door based on the identified edge information (400). According to one or more embodiments, the movement space (402) may be a space in which a dynamic object, including a robot within the revolving door, moves to pass through the revolving door. The processor (130) may identify movement space information based on the identified edge information (400). According to one or more embodiments, the processor (130) may identify an area of ​​the movement space (402) excluding an area occupied by an object as a free space, and the processor (130) may identify free space information based on the movement space information and information about the object. As illustrated in FIG. 4, when there is no object within the revolving door, the movement space (402) may be identical to the free space. The processor (130) may identify information about the movement space (402) (or movement space information) as free space information.

[0081] FIG. 5 is a diagram illustrating a method for identifying an entry point according to one or more embodiments.

[0082] According to FIG. 5, according to one embodiment, the processor (130) may identify a point in time when the robot (50) can enter the revolving door based on free space information and space information corresponding to the robot (50). Here, the space information corresponding to the robot (50) may include information on an occupied space (51) of the robot (50). According to one or more embodiments, the occupied space (51) of the robot (50) may be an area including a footprint area and a margin area of ​​the robot (50). According to one or more embodiments, the information on the occupied space (51) of the robot (50) may include information on a shape and a size of the occupied space (51). According to one or more embodiments, the space information corresponding to the robot (50) including information on the occupied space (51) of the robot (50) may be stored in a memory.

[0083] According to one or more embodiments, if the processor (130) identifies that the shape of the space corresponding to the robot (50) is included within the shape of the free space based on the free space information and the space information corresponding to the robot (50), the processor (130) may identify a point in time at which the robot (50) can enter the revolving door based on the location of the free space within the revolving door. For example, the processor (130) may first compare the shape of the free space (501) included in the identified free space information with the shape of the occupied space (51) of the robot (50) included in the space information corresponding to the robot (50), to identify whether the shape of the space corresponding to the robot (50) (or the occupied space (51) of the robot (50)) is included within the shape (501) of the free space. According to one or more embodiments, if the processor (130) identifies that the shape of the space (51) corresponding to the robot (50) is included within the shape of the free space (501), the processor (130) may identify a time point at which the robot (50) can enter the revolving door based on the position of the free space (501) within the revolving door. For example, the processor (130) may identify a time period during which the revolving door opens based on the position of the free space (501) within the revolving door, and the processor (130) may identify a time point at which the robot (50) can enter the revolving door within the time period during which the revolving door opens. Hereinafter, a method for identifying a time point at which the robot (50) can enter the revolving door within the time period during which the revolving door opens will be described.

[0084] According to one embodiment, the processor (130) may identify a time period in which a revolving door is opened based on position information of the free space (501) and movement speed information of the free space (501). According to one or more embodiments, the free space information may include at least one of radius information, rotation axis information, and angle information corresponding to the free space (501). For example, when the free space (501) has a fan shape, the processor (130) may obtain radius information and angle information corresponding to the free space (501) based on edge information (500) corresponding to the identified revolving door. The processor (130) may also obtain real-time position change information of the free space (501) based on the edge information (500), and the processor (130) may obtain rotation axis information corresponding to the free space (501) and movement speed information of the free space (501) based thereon. In this case, the movement speed information of the free space (501) may include at least one of linear speed information and angular speed information of the free space (501). According to one or more embodiments, when the processor (130) identifies the position information of the free space (501) within the revolving door and the movement speed information of the free space (501) based on the free space information, the processor (130) may identify the time interval during which the revolving door is opened based on the same. When the time interval during which the revolving door is opened is identified, the processor (130) may identify the entry point of the robot (50) based on the same.

[0085] According to the above-described example, the robot (50) can determine whether the occupied space (51) can be included in the free space (501), and if it is determined that the occupied space (51) can be included in the free space (501), it can determine the entry point into the revolving door.

[0086] FIG. 6 is a drawing for explaining a method for identifying a point in time at which an object can enter a revolving door by considering one or more embodiments.

[0087] According to FIG. 6, according to one embodiment, the processor (130) can update information of the free space (601) (the darkly hatched area in the image) based on information about the object (6).

[0088] According to one or more embodiments, the processor (130) may identify whether the object (6) is about to enter the revolving door based on information about the object (6). According to one or more embodiments, the information about the object (6) may further include information about a movement path of the object (6). According to one or more embodiments, the information about the movement path of the object (6) may be information about a predicted movement path of the object (6) identified based on a captured image. The processor (130) may identify whether at least one object (6) is about to enter the revolving door based on the information about the movement path of the object (6). When the processor (130) identifies that at least one object (6) is about to enter the revolving door, the processor (130) may update free space (601) information based on spatial information corresponding to the object (6). The spatial information corresponding to the object (6) means information about a space occupied by the object (6), and according to one or more embodiments, the spatial information corresponding to the object (6) may be stored in a memory. The processor (130) can update free space (601) information based on spatial information corresponding to the object (6) stored in the memory. For example, the processor (130) can identify an area corresponding to a movement space, from which the occupied space of the object (6) is excluded, as free space (601).

[0089] According to one embodiment, the processor (130) may identify whether the shape of the space corresponding to the robot (60) is included within the shape of the free space (601) based on the updated free space (601) information and the space information corresponding to the robot (60). According to one or more embodiments, the processor (130) may compare the shape of the updated free space (601) with the shape of the occupied space (61) corresponding to the robot (60) to identify whether the shape of the space corresponding to the robot (60) is included within the shape of the updated free space (601).

[0090] According to one embodiment, if the processor (130) identifies that the shape of the space corresponding to the robot (60) is included in the shape of the updated free space (601), the processor (130) may identify a time point at which the robot (60) can enter the revolving door based on the location of the updated free space (601) within the revolving door. According to one or more embodiments, the processor (130) may identify a time interval during which the revolving door opens (or a time interval during which the robot (60) can enter) based on information about the location of the updated free space (601). For example, the processor (130) may identify a movement speed of the free space (601) based on a change in position over time of the updated free space (601), and may identify whether the revolving door is open based on edge information (600). The processor (130) may identify a time interval during which the revolving door is open based on information about the movement speed of the free space (601) and whether the revolving door is open. The processor (130) can enter the revolving door within the time period in which it is opened.

[0091] According to one embodiment, the processor (130) can identify an entry point for the robot (60) based on the number of at least one object (6) to be entered and the entry position of at least one object (6) within the revolving door.

[0092] According to one or more embodiments, the processor (130) may identify at least one object (6) that is scheduled to enter the revolving door based on the captured image. When the at least one object (6) scheduled to enter the revolving door enters the revolving door, the processor (130) may identify the entry location of the at least one object (6) within the revolving door. For example, assume a case where a person is scheduled to enter the revolving door. The processor (130) may identify at least one object (6) that is scheduled to enter the revolving door based on the captured image. When the at least one object (6) enters the revolving door, the processor (130) may identify the location information of the at least one object (6) within the revolving door, and update the free space (601) information based on the location information. The processor (130) can compare the shape of the updated free space (601) with the shape of the occupied space (61) corresponding to the robot (60) to identify whether the shape of the space corresponding to the robot (60) is included in the shape of the updated free space (601). If the shape of the space corresponding to the robot (60) is included in the shape of the updated free space (601), the processor (130) can identify the time period during which the revolving door is opened and, based on this, identify the time period during which the robot (60) can enter. In this case, the processor (130) can identify the time period during which the robot (60) can enter as a time period after the time period during which the object (6) is identified as having entered the revolving door.

[0093] According to one embodiment, the processor (130) can identify a possible entry point of the robot (60) based on the number of at least one object (6) that is scheduled to exit the revolving door and movement path information of the at least one object (6). According to one or more embodiments, it is assumed that there are two objects (6) inside the revolving door. If the processor (130) identifies that there are two objects (6) inside the revolving door based on the captured image, the processor (130) can identify movement path information of the objects (6) inside the revolving door. If the processor (130) identifies that two objects (6) are scheduled to exit the revolving door based on the movement path information of the objects (6), the processor (130) can update free space (601) information based thereon. For example, the processor (130) can identify a movement space that includes an occupied space (61) corresponding to an object (6) that is scheduled to exit the revolving door as a free space (601). The processor (130) can identify whether the shape of the occupied space (61) of the robot (60) is included in the shape of the updated free space (601) based on the updated free space (601) information. If the shape of the occupied space (61) of the robot (60) is included in the shape of the updated free space (601), the processor (130) can identify the time point at which the robot (60) can enter. The processor (130) can identify the time period during which the revolving door is opened and, based on this, can identify the time point at which the robot (60) can enter. In this case, the processor (130) can identify the time point at which the robot (60) can enter as a time point after the time point at which each of the two objects (6) is identified as having exited the revolving door within the time period during which the revolving door is opened.

[0094] FIGS. 7A and 7B are drawings for explaining a method for identifying an entry point of a robot according to one or more embodiments.

[0095] According to FIG. 7A, according to one embodiment, the processor (130) can identify an entry point based on information about an object. According to one or more embodiments, as shown in the upper drawing of FIG. 7A, assume a case where multiple objects (711 and 712) are included within a revolving door (701). The processor (130) can identify movement path information of the multiple objects based on the captured image.

[0096] According to one embodiment, if it is identified that a plurality of objects (711 and 712) are scheduled to exit the revolving door (701) based on movement path information of the plurality of objects (711 and 712), as shown in the lower left drawing of FIG. 7A, the processor (130) may update a space including the occupied spaces of the plurality of objects (711 and 712) to a free space. The processor (130) may identify whether the shape of the space corresponding to the robot is included in the shape corresponding to the updated free space based on the updated free space information. If the shape of the space corresponding to the robot is included in the shape corresponding to the updated free space, the processor (130) may identify a time period when the robot can enter based on the updated free space information. For example, the processor (130) may identify a time period in which the revolving door (701) opens based on movement speed information and edge information of the free space. The processor (130) can identify the point in time when the robot (70) can enter after the point in time when each of the two objects (711 and 712) is identified as having exited the revolving door (701) within the time period when the revolving door (701) is opened. In this case, the processor (130) can identify the point in time when the two objects (711 and 712) have completed exiting the revolving door (701) based on movement path information corresponding to each of the two objects (711 and 712), and can identify the point in time when the robot (70) can enter based on this. The point in time when the object has completed exiting the revolving door (701) means the point in time corresponding to a state in which the robot can enter the revolving door (701) without the influence of the object after the object has exited the revolving door (701).

[0097] According to one embodiment, as shown in the lower right drawing of FIG. 7A, if one of the plurality of objects (711 and 712) is identified as being about to exit the revolving door (701) based on the movement path information of the plurality of objects (711 and 712), the processor (130) may update the space including the occupied space of one of the objects (712) to a free space. The processor (130) may identify whether the shape of the space corresponding to the robot (70) is included in the shape corresponding to the updated free space based on the updated free space information. If the shape of the space corresponding to the robot (70) is included in the shape corresponding to the updated free space, the processor (130) may identify a possible entry point of the robot (70) based on the updated free space information. For example, the processor (130) may identify a time period in which the revolving door (701) opens based on movement speed information and edge information of the free space. The processor (130) can identify a point in time when the robot (70) can enter after a point in time when one (712) is identified as having exited the revolving door (701) within the time period when the revolving door (701) is opened. In this case, the processor (130) can identify a point in time when one (712) completes exiting the revolving door (701) based on movement path information corresponding to one (712), and can identify a point in time when the robot (70) can enter based on this.

[0098] According to the above-described example, the robot (70) can identify a time point at which entry is possible by considering an object within the revolving door. That is, the robot considers the movement path information of the object within the revolving door and, if the object is scheduled to exit the revolving door, enters the revolving door at a time point after the object exits the revolving door, thereby improving usability. However, the present invention is not limited thereto, and according to one embodiment, if the processor (130) identifies that the object cannot enter the revolving door after the time point at which the object is identified as exiting the revolving door within a first time interval during which the revolving door is opened, the processor (130) can identify a time point at which entry into the revolving door is possible within a second time interval after the first time interval. According to one or more embodiments, it is assumed that, after the object's exit is completed within the first time interval during which the revolving door is opened, the robot identifies that the time required for entry is not secured. If the processor (130) determines that the time required for the robot to enter the revolving door is not secured, the processor can identify a time point at which the robot can enter the revolving door within a second time interval during which the revolving door opens after the first time interval.

[0099] According to FIG. 7B, according to an embodiment, the processor (130) may identify an entry point based on information about an object (713) that is scheduled to enter the revolving door (701). According to one or more embodiments, it is assumed that there is an object (713) that is scheduled to enter the revolving door (701) as in the upper drawing of FIG. 7B. The processor (130) may identify movement path information of a plurality of objects (713) based on a captured image. If the processor (130) determines that the object (713) is scheduled to enter the revolving door (701) based on the identified movement path information, the processor (130) may update an area in the movement space within the revolving door (701) excluding the occupied space (or occupied area) of the object (713) as a free space. The processor (130) may identify whether the shape of the space corresponding to the robot (70) is included in the shape corresponding to the updated free space based on the updated free space information. If the shape of the space corresponding to the robot (70) is included in the shape corresponding to the updated free space, the processor (130) can identify the entry point of the robot (70) based on the updated free space information. According to one or more embodiments, as shown in the lower drawing of FIG. 7B, the processor (130) can identify the entry point for the robot (70) to enter the revolving door (701) after the entry of the object (713) scheduled to enter has been completed. For example, the processor (130) can identify the entry point of the robot (70) as a point in time after the point in time at which the object (713) is identified as having completed entry within the time period during which the revolving door (701) is opened.

[0100] However, it is not limited thereto, and the processor (130) may identify the entry point of the robot (70) as a point in time after the point in time at which the object (713) is identified as having completed entry, not only when the object (713) is located at the rear of the robot (70) as in the upper drawing of FIG. 7b, but also when the object (713) is located at the front of the robot (70), according to one or more embodiments.

[0101] According to one embodiment, the processor (130) can control the drive unit (120) to cause the robot (70) to enter the revolving door (701) at an identified entry point.

[0102] FIG. 8A and FIG. 8B are drawings for explaining a method of driving a robot inside a revolving door according to one or more embodiments.

[0103] According to FIG. 8A, according to one embodiment, when the robot (80) enters the revolving door, the processor (130) may control the driving unit (120) to position the robot (80) in the center region of the inscribed circle (810) corresponding to the free space (801). The inscribed circle (810) corresponding to the free space (801) refers to a circle inscribed within the shape (e.g., a fan) of the free space (801). Here, the center region refers to a region located within a preset distance from the center of the inscribed circle (810). According to one or more embodiments, when the robot (80) enters the revolving door within the time when the robot (80) can enter, the processor (130) may control the driving unit (120) to position the robot (80) in the center region of the inscribed circle (810) based on information about the free space (801). According to one or more embodiments, the free space (801) information may include at least one of radius information, rotation axis information, and angle information corresponding to the free space (801), and the processor (130) may identify at least one of the radius information, rotation axis information, and angle information corresponding to the free space (801) based on the edge information (800). The processor (130) may identify a center area of ​​an inscribed circle (810) based on at least one of the radius information, rotation axis information, and angle information corresponding to the free space (801), and control the driving unit (120) so that the robot (80) is positioned in the center area of ​​the identified inscribed circle (810). According to one or more embodiments, the processor (130) may identify real-time position information of the free space (801) based on edge information (800) acquired from a real-time captured image, and the processor (130) may update the center area of ​​the inscribed circle (810) in real time based on the real-time position information. The processor (130) can control the driving unit (120) so that the robot (80) is positioned in the center area of ​​the updated inscribed circle (810).

[0104] According to FIG. 8B, according to one embodiment, the processor (130) can identify the center area of ​​the inscribed circle (820) corresponding to the updated free space (802) when the free space (802) (the darkly hatched area in the illustration) is updated by considering information about the object (8). According to one or more embodiments, the processor (130) can obtain the updated free space (802) when the object (8) exists in the revolving door. The processor (130) can identify the center area of ​​the inscribed circle (820) corresponding to the free space (802) by using at least one of the radius information, the rotation axis information, and the angle information corresponding to the updated free space (802). The processor (130) can control the driving unit (120) so that the robot (80) is positioned in the center area of ​​the inscribed circle (820) corresponding to the updated free space (802).

[0105] FIG. 9 is a drawing for explaining a method of moving a robot within a revolving door according to one or more embodiments.

[0106] According to FIG. 9, according to one embodiment, the processor (130) may control the driving unit (120) to move the robot (90) by following a reference point (903, Reference Point) corresponding to a swing door (902) included in a revolving door. Here, the swing door (902) included in the revolving door refers to a static object (9) for dividing a plurality of movement spaces within the revolving door. The reference point (903) refers to a point corresponding to a preset position within the swing door (902) among edge information (900) corresponding to the swing door (902). For example, the reference point (903) may be a point located at a preset distance from the rotation axis among a straight line adjacent to the floor within the edge information corresponding to the swing door (902), but is not limited thereto.

[0107] According to one or more embodiments, the processor (130) may identify a preset reference point (903) within a swing door (902) corresponding to a free space (901) when the robot (90) enters the revolving door. According to one or more embodiments, the processor (130) may identify a swing door (902) included within the revolving door based on edge information (900) acquired based on a captured image. According to one or more embodiments, the swing door (902) corresponding to the free space (901) means a swing door (902) that is ahead of the robot (900) based on the rotation direction of the revolving door among a plurality of swing doors (902) adjacent to the free space (901). For example, if a revolving door rotates relatively from left to right based on FIG. 9, the swing door (902) corresponding to the free space (901) may be a swing door (902) located on the right side of the robot (90) based on FIG. 9, which is relatively ahead of the robot (90). When the swing door (902) corresponding to the free space (901) is identified, the processor (130) may identify a preset reference point (903) within the identified swing door (902).

[0108] According to one or more embodiments, when a reference point (903) is identified, the processor (130) may control the driving unit (120) to move in accordance with the identified reference point (903). For example, the processor (130) may identify at least one of position change information and movement speed information of the reference point (903) based on the captured image. The movement speed information of the reference point (903) may include at least one of linear speed and angular speed information of the reference point (903). The processor (130) may move using the movement speed information of the reference point (903). For example, the processor (130) may control the driving unit (120) to move in the same speed and direction as the movement of the identified reference point (903). However, it is not limited thereto, and according to one or more embodiments, the processor (130) may control the driving unit (120) to move while considering the center area of ​​the reference point (903) and the inscribed circle (910), respectively.

[0109] According to one embodiment, the processor (130) may identify third control information by applying preset weights to each of first control information for positioning the robot (90) at the center of an inscribed circle (910) corresponding to a free space (901) and second control information for moving the robot (90) by following an identified reference point (903), and control the driving unit (120) based on the identified third control information.

[0110] According to one or more embodiments, the processor (130) may identify first control information for positioning the robot (90) at the center of an inscribed circle (910) corresponding to a free space (901), and may identify second control information for positioning the robot (90) to follow and move to the identified reference point (903). For example, the processor (130) may identify first control information for positioning within a preset distance from the center area of ​​the identified inscribed circle (910). In addition, the processor (130) may identify second control information for moving to follow and move to the identified reference point (903) based on edge information (900).

[0111] According to one or more embodiments, the processor (130) may identify third control information for moving the robot (90) within the revolving door by applying preset weights to each of the identified first control information and second control information, and control the driving unit (120) based on the identified third control information. For example, the processor (130) may identify the third control information using the following mathematical expression 1.

[0112]

[0113] According to mathematical expression 1, v denotes the linear velocity of the robot (90), and w denotes the angular velocity of the robot (90). a denotes a weight corresponding to the first control information, and b denotes a weight corresponding to the second control information. The sum of a and b is 1. cost (A) denotes a distance value between the center of the inscribed circle (910) and the position of the robot (90) (i.e., a distance error value from the center of the inscribed circle (910). cost (B) denotes a distance value (or a distance error value) between the expected position of the robot (90) in the free space (901) and the current position of the robot (90) when the robot (90) follows the reference point (903). The processor (130) can identify the linear velocity and angular velocity of the robot (90) using mathematical expression 1, and identify third control information for moving the robot (90) based on the identified linear velocity and angular velocity. The processor (130) can control the driving unit (120) using the third control information.

[0114] FIG. 10 is a drawing for explaining a method for a robot to move to a target position according to one or more embodiments.

[0115] According to FIG. 10, according to one embodiment, if the processor (130) identifies that the robot (1000) is located within a preset distance from the revolving door, the processor (130) may control the driving unit (120) to allow the robot (1000) to enter the revolving door at a time when the robot (1000) can enter the revolving door. According to one or more embodiments, the memory may store map information corresponding to the driving space. According to one or more embodiments, the map information corresponding to the driving space may include map information (1010) corresponding to the revolving door. The processor (130) may identify the location information (1001) of the robot (1000) through a sensor, and may identify whether the robot (1000) is located within a preset distance from the revolving door based on the identified location information (1001) and map information. When the processor (130) identifies that the robot (1000) is located within a preset distance from the revolving door, the processor (130) can identify a time point at which the robot (1000) can enter the revolving door, and control the driving unit (120) so that the robot (1000) can enter the revolving door at the identified time point at which the robot (1000) can enter. After entering the revolving door, the processor (130) can control the driving unit (120) so that the robot (1000) can exit the revolving door, and the robot (1000) can reach a target location (1002). Here, the target location (1002) may be any one of a plurality of intermediate target points included in the driving path, and according to one or more embodiments, the target location (1002) may be an intermediate target point adjacent to the revolving door among the plurality of intermediate target points included in the driving path.

[0116] FIG. 11A and FIG. 11B are drawings for explaining how a robot according to one or more embodiments exits a revolving door.

[0117] According to FIG. 11A, according to one embodiment, the processor (130) may control the driving unit (120) to exit the revolving door (1110). According to one or more embodiments, when the robot (1100) enters the revolving door (1110), the processor (130) may identify whether the swing door (1111, Door) corresponding to the free space (1112) is located within a preset distance from the target location (1113) outside the revolving door (1110). The processor (130) may identify the location information of the swing door (1111) corresponding to the free space (1112) based on the captured image, and may obtain distance information between the swing door (1111) and the target location (1113) outside the revolving door (1110) based on the location information of the identified swing door (1111). For example, when a swing door (1111) and a target location (1113) are identified in the identified captured image, the processor (130) can identify the distance between the identified swing door (1111) and the target location (1113).

[0118] Alternatively, for example, the processor (130) may identify the position of the swing door (1111) based on the movement speed information of the free space (1112). That is, since the movement speed of the swing door (1111) and the movement speed of the free space (1112) are the same, the processor (130) may predict the position of the swing door (1111) using the movement speed of the free space (1112). The processor (130) may compare the predicted position with the target position (1113) to identify the distance between the swing door (1111) and the target position (1113). The processor (130) may identify the distance between the swing door (1111) and the target position (1113) using map information corresponding to the driving space stored in the memory.

[0119] According to one or more embodiments, the processor (130) may control the driving unit (120) to exit the revolving door (1110) within a preset time period from the time point at which the swing door (1111) corresponding to the free space (1112) is identified as being located within a preset distance from a target location (1113) outside the revolving door (1110). According to one or more embodiments, the preset time period may be a time period required for the robot to safely exit the revolving door. The preset time period may be less than the time period during which the entrance of the revolving door is open.

[0120] According to FIG. 11B, according to one embodiment, the processor (130) may control the driving unit (120) to cause the robot (1100) to exit the revolving door (1110) based on information about the object (1101). According to one or more embodiments, the processor (130) may identify whether at least one object (1101) located within the revolving door (1110) exits the revolving door (1110). For example, the processor (130) may identify whether at least one object (1101) located within the revolving door (1110) exits the revolving door (1110) by using information about a movement path of the object (1101) included in the information about the object (1101).

[0121] According to one or more embodiments, when the processor (130) identifies that at least one object (1101) has exited the revolving door (1110), the processor (130) may control the driving unit (120) to exit the revolving door (1110) within a preset time from the time point at which the swing door is identified as being located within a preset distance from the target location (1113). For example, when the processor (130) identifies that an object (1101) within the revolving door (1110) has exited the revolving door (1110) based on the acquired captured image or the movement path information of the object (1101), the processor (130) may control the driving unit (120) to exit the revolving door (1110) within a preset time from the time point at which the swing door is identified as being located within a preset distance from the target location (1113).

[0122] In this case, the time point at which the robot (1100) exits the revolving door (1110) may be a time point after the time point at which the object (1101) is identified as having exited the revolving door (1110). For example, if the processor (130) identifies that the object (1101) inside the revolving door (1110) has exited the revolving door (1110), the processor (130) may control the driving unit (120) to exit the revolving door (1110) within a preset time from a relatively later time point among the first time point at which the object (1101) has completed exiting the revolving door (1110) or the second time point at which the swing door is identified as being located within a preset distance from the target position (1113).

[0123] According to one or more embodiments, if the entrance of the revolving door (1110) is identified as closing before a preset time elapses from a first time point or a second time point at which the swing door is identified as being located within a preset distance from the target location (1113), whichever is later, (or, if the robot (1100) is identified as not being able to exit the revolving door (1110),) the processor (130) may control the driving unit (120) to exit the revolving door (1110) within a preset time from a third time point at which the swing door is identified as being located within a preset distance from the target location (1113) after the time point at which the entrance of the revolving door (1110) is closed. In other words, if the processor (130) determines that it is difficult to exit the revolving door (1110) before the revolving door (1110) closes after the object (1101) has exited, the processor (130) can exit the revolving door (1110) after the revolving door (1110) is closed and the swing door is again identified as being located within a preset distance from the target location (1113).

[0124] FIG. 12 is a flowchart illustrating a method for identifying whether entry into a revolving door is possible according to one or more embodiments.

[0125] According to FIG. 12, the control method can first determine whether entry into the revolving door is possible at the current time (S1210). According to one or more embodiments, the processor (130) can determine whether entry into the revolving door is possible at the current time based on the acquired captured image. For example, the processor (130) can compare the shape of the free space included in the free space information with the shape of the space occupied by the robot (100), and if it is determined that the shape of the space occupied by the robot (100) is included in the shape of the free space, it can determine that entry into the revolving door is possible at the current time.

[0126] Alternatively, for example, the processor (130) may determine that it is impossible to enter the revolving door at the current time if it is determined that the shape of the free space included in the free space information and the shape of the occupied space of the robot (100) are not included in the shape of the free space. However, this is not limited to this, and for example, the processor (130) may determine that it is impossible to enter the revolving door at the current time if a preset number of objects are included in the revolving door (i.e., if a preset number of people are on the revolving door).

[0127] Next, according to one embodiment, if it is determined that the revolving door can be entered at the current point in time (S1210: Y), the control method can control the driving unit (120) to allow the robot (100) to enter the revolving door (S1220).

[0128] According to one embodiment, if it is determined that the revolving door is not accessible at the current time (S1210: N), the control method may control the driving unit (120) to wait until the revolving door is accessible or identify a driving path that avoids the revolving door (S1230). According to one or more embodiments, if the processor (130) identifies that the revolving door contains a preset number or more objects, it may determine that the revolving door is not accessible at the current time and control the driving unit (120) to wait until the revolving door is accessible. After a preset time has elapsed from the current time, the processor (130) may compare the shape of the free space included in the free space information with the shape of the space occupied by the robot (100) to re-identify whether the shape of the free space includes the shape of the space occupied by the robot (100). Alternatively, if it is determined that the driving time is shortened when avoiding the revolving door, the processor (130) may identify a driving path that avoids the revolving door and control the driving unit (120) to avoid the revolving door.

[0129] Fig. 13 is a block diagram showing a detailed configuration of a robot according to one or more embodiments.

[0130] According to FIG. 13, the robot (100') may include at least one sensor (110), a driving unit (120), one or more processors (130), a memory (140), a microphone (150), a speaker (160), a communication interface (170), a user interface (180), and a display (190). Among the configurations illustrated in FIG. 13, configurations that overlap with the configuration illustrated in FIG. 2 may be applied as described above in FIG. 2.

[0131] The memory (140) can store data required for various embodiments. The memory (140) may be implemented in the form of a memory (140) embedded in the robot (100') or may be implemented in the form of a memory (140) that can be attached or detached to the robot (100') depending on the purpose of data storage. For example, data for driving the robot (100') may be stored in the memory (140) embedded in the robot (100'), and data for the expansion function of the robot (100') may be stored in the memory (140) that can be attached or detached to the robot (100').

[0132] In the case of the memory (140) embedded in the robot (100'), it may be implemented as at least one of volatile memory (140) (e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (140) (non-volatile memory) (e.g., one time programmable ROM (OTPROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (140) (e.g., NAND flash or NOR flash), hard drive, or solid state drive (SSD)). In addition, in the case of the memory (140) that can be attached or detached to the robot (100'), it may be implemented as at least one of a memory (140) card (e.g., compact flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (Mini-SD), xD (extreme digital), MMC (multi-media card), etc.), external memory (140) connectable to a USB port (for example, it can be implemented in the form of a USB memory, etc.).

[0133] According to one embodiment, the memory (140) may store a learned neural network model and control information corresponding to each of a plurality of gait steps.

[0134] A robot (100') according to an embodiment of the present disclosure may include a plurality of artificial intelligence models (or artificial neural network models or learning network models) each consisting of at least one neural network layer. The artificial neural network may include a deep neural network (DNN), for example, 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), or deep Q-networks, but is not limited to the examples described above.

[0135] A microphone (150) may refer to a module that acquires sound and converts it into an electrical signal, and may be a condenser microphone, a ribbon microphone, a moving coil microphone, a piezoelectric element microphone, a carbon microphone, or a MEMS (Micro Electro Mechanical System) microphone. In addition, it may be implemented in an omnidirectional, bidirectional, unidirectional, subcardioid, supercardioid, or hypercardioid manner.

[0136] The speaker (160) may be composed of a tweeter for reproducing high-frequency sounds, a midrange for reproducing mid-frequency sounds, a woofer for reproducing low-frequency sounds, a subwoofer for reproducing ultra-low-frequency sounds, an enclosure for controlling resonance, and a crossover network for dividing the frequency of an electric signal input to the speaker into bands.

[0137] The speaker (160) can output an audio signal to the outside of the robot (100'). The speaker (160) can output multimedia playback, recording playback, various notification sounds, voice messages, etc. The robot (100') may include an audio output device such as the speaker (160), but may also include an output device such as an audio output terminal. In particular, the speaker (160) can provide acquired information, information processed and produced based on acquired information, response results to user voice, operation results, etc. in voice form.

[0138] The communication interface (170) can input and output various types of data. For example, the communication interface (170) can transmit and receive various types of data to and from an external device (e.g., a source device), an external storage medium (e.g., a USB memory), an external server (e.g., a web hard drive) through a communication method such as AP-based Wi-Fi (Wireless LAN network), Bluetooth, Zigbee, wired / wireless LAN (Local Area Network), WAN (Wide Area Network), Ethernet, IEEE 1394, HDMI (High-Definition Multimedia Interface), USB (Universal Serial Bus), MHL (Mobile High-Definition Link), AES / EBU (Audio Engineering Society / European Broadcasting Union), optical, coaxial, etc.

[0139] According to one or more embodiments, the communication interface (170) may include a BLE (Bluetooth Low Energy) module. BLE refers to Bluetooth technology that enables transmission and reception of low-power, low-capacity data in the 2.4 GHz frequency band with a range of about 10 m.

[0140] However, the present invention is not limited thereto, and the communication interface (170) may also include a Wi-Fi communication module. That is, the communication interface (170) may include at least one of a BLE (Bluetooth Low Energy) module or a Wi-Fi communication module.

[0141] The user interface (180) is a configuration for the robot (100') to interact with a user. For example, the user interface (180) may include, but is not limited to, at least one of a touch sensor, a motion sensor, a button, a jog dial, a switch, a microphone, or a speaker.

[0142] The display (190) may be implemented as a display including a self-luminous element or a display including a non-luminous element and a backlight. For example, it 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), a micro LED, a Mini LED, a PDP (Plasma Display Panel), a QD (Quantum dot) display, a QLED (Quantum dot light-emitting diodes), etc. The display (190) may also include a driving circuit, a backlight unit, etc., which may be implemented in a form such as an a-si TFT, an LTPS (low temperature poly silicon) TFT, an OTFT (organic TFT), etc. The display (190) may be implemented as a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display, a display in which a plurality of display modules are physically connected, etc. The processor (130) can control the display (190) to output an output image obtained according to the various embodiments described above. Here, the output image can be a high-resolution image of 4K or 8K or higher.

[0143] According to one embodiment, the display (190) may be implemented as a display capable of adjusting the angle. According to one or more embodiments, a driving unit (120) for adjusting the angle of the display (190) may be provided on one side of the display (190), and the processor (130) may adjust the display angle of the display (190) through the driving unit (120).

[0144] According to the above-described example, the robot (100') can obtain information about the revolving door through the captured video and use this to determine a time point at which the robot can enter the revolving door. Once the time point at which the robot (100') can enter the revolving door is identified, the robot (100') can enter the revolving door, move, and reach a target point. In this case, the robot (100') can drive while considering an object that has passed or is scheduled to pass through the revolving door. Accordingly, the robot (100') can safely pass through the revolving door while considering people around the revolving door, and can reach the target point without having to detour the revolving door, thereby enabling efficient driving.

[0145] Fig. 14 is a block diagram for explaining a method of controlling a robot according to one or more embodiments.

[0146] According to FIG. 14, according to one embodiment, the robot (100) may include a revolving door identification module (1405), an edge information identification module (1410), an object information identification module (1415), a free space information identification module (1420), a revolving door entry point identification module (1425), a revolving door movement path identification module (1430), a first control information identification module (1435), a second control information identification module (1440), a revolving door exit point identification module (1445), and a target position driving module (1450).

[0147] According to one embodiment, the revolving door identification module (1405) can identify a revolving door within a driving space based on a captured image acquired through a sensor (110). According to one or more embodiments, the revolving door can include at least one swing door and can include a plurality of boarding spaces. According to one or more embodiments, the robot (100) can acquire a captured image corresponding to the driving space through the sensor (110), and the revolving door identification module (1405) can identify a revolving door present in the acquired captured image using a learned neural network model. According to one or more embodiments, the learned neural network model can be a neural network model trained to receive a captured image of the driving space as input and output information on whether a revolving door exists in the captured image.

[0148] According to one embodiment, the edge information identification module (1410) may identify edge information corresponding to a revolving door based on a captured image acquired through the sensor (110). The edge information corresponding to the revolving door is information about an outline (or, outer line) of the revolving door existing in the captured image. However, the present invention is not limited thereto, and the edge information may also be information about a line calculated based on a pixel value in the captured image. According to one or more embodiments, the edge information may include a straight line or a curve corresponding to a point where the revolving door meets the floor in the driving space, or may include a straight line perpendicular to the floor among the outlines corresponding to the revolving door. According to one or more embodiments, when a revolving door in the driving space is identified, the edge information identification module (1410) may identify edge information corresponding to the revolving door based on the acquired captured image.

[0149] According to one embodiment, the object information identification module (1415) can identify information about an object corresponding to a revolving door based on the acquired captured image. According to one or more embodiments, the object corresponding to the revolving door may include an object that has entered the revolving door or an object that is scheduled to enter the revolving door. The information about the object may include information about the movement path of the object. The object information identification module (1415) can identify or predict the movement path of the object using the captured image acquired in real time.

[0150] According to one embodiment, the free space information identification module (1420) can identify free space information within a revolving door based on edge information and object information corresponding to the revolving door.

[0151] According to one or more embodiments, the free space information identification module (1420) may identify an area for an object to board within the revolving door based on edge information identified based on a captured image, and identify this area as a movement space based on the identified edge information. The movement space may be an area excluding an area corresponding to a swing door among the floor area of ​​the revolving door (an area where the revolving door and the floor within the travel space meet), and according to one or more embodiments, the free space information identification module (1420) may identify an area excluding an area occupied by an object among the identified movement spaces as a free space based on object information. Alternatively, an area excluding an area including a preset margin area in the area occupied by the object from the movement space may be identified as a free space.

[0152] According to one or more embodiments, the free space information may include position information and movement speed information corresponding to the free space within the revolving door. The free space information identification module (1420) may identify free space information including position information and movement speed information corresponding to the free space based on the acquired captured image. For example, if the free space is a fan-shaped space, the free space information identification module (1420) may identify at least one of radius information, rotation axis information, and angle information corresponding to the free space based on the acquired captured image, and may identify free space information including position information and movement speed information corresponding to the free space based on the identified information. The position information corresponding to the free space may be information on the relative position of the free space within the driving space, and the movement speed information may be information on the movement speed of the free space over time (for example, at least one of linear velocity information and angular velocity information of the free space).

[0153] According to one embodiment, the module for identifying when a robot can enter a revolving door (1425) can identify when a robot can enter a revolving door based on information about free space and information about an object. For example, if the module for identifying when a robot can enter a revolving door identifies the location information of a free space within a revolving door and the movement speed information of the free space, the module for identifying when a robot can enter a revolving door can identify the location information of the free space, the movement speed information of the free space, and the information about the identified object.

[0154] According to one or more embodiments, the revolving door entry possible time identification module (1425) can identify a time interval during which the revolving door opens based on the position information of the identified free space and the movement speed information of the free space. For example, if the free space is fan-shaped, the revolving door entry possible time identification module (1425) can identify a time interval during which the revolving door opens based on the position information within the travel space of the free space and the angular velocity information of the free space, and can identify a time interval during which the robot (100) can enter the revolving door based on the information about the acquired time interval.

[0155] According to one or more embodiments, the revolving door entry-possible time identification module (1425) may update the time at which the robot (100) can enter the revolving door based on information about an object corresponding to the revolving door. For example, if an object that is or is scheduled to enter the revolving door is identified, the revolving door entry-possible time identification module (1425) may update the time at which the robot (100) can enter the revolving door to a time after the object that is or is scheduled to enter the revolving door has completed its entry. Alternatively, if an object that is or is scheduled to enter the revolving door is identified, the revolving door entry-possible time identification module (1425) may identify the time at which the robot (100) can enter the revolving door to a time after the object that is or is scheduled to enter the revolving door has completed its entry. According to one or more embodiments, the revolving door entry-possible time identification module (1425) may control the driving unit (120) to allow the robot (100) to enter the revolving door at the time at which the robot (100) can enter the revolving door.

[0156] According to one embodiment, the revolving door movement path identification module (1430) may identify the movement path of the robot (100) based on the movement path and movement speed of the swing door within the revolving door when the robot (100) enters the revolving door, and control the driving unit (120) to move the robot (100) based on the identified movement path. According to one or more embodiments, the revolving door movement path identification module (1430) may identify the movement path of the robot (100) within the revolving door based on first control information received from the first control information identification module (1435) and second control information received from the second control information identification module (1440).

[0157] According to one embodiment, the first control information identification module (1435) may identify first control information for positioning the robot (100) in the center region of an inscribed circle corresponding to a free space when the robot enters a revolving door. The inscribed circle corresponding to the free space refers to a circle inscribed within a shape (e.g., a fan) of the free space, and the center region refers to a region located within a preset distance from the center of the inscribed circle. The first control information identification module (1435) may identify the center region of the inscribed circle based on at least one of radius information, rotation axis information, and angle information corresponding to the free space, and may identify first control information for positioning the robot in the center region of the identified inscribed circle. According to one or more embodiments, the first control information identification module (1435) may update the center region of the inscribed circle of the free space in real time based on edge information acquired from a captured image acquired in real time.

[0158] According to one embodiment, the second control information module (1440) can identify a movement path and a movement speed of a swing door within a revolving door, and identify second control information for moving the robot (100) based on the identified movement path and movement speed of the swing door.

[0159] According to one or more embodiments, the second control information module (1440) can identify second control information for the robot to move by following a reference point corresponding to a swing door included in a revolving door. The reference point means a point corresponding to a preset position within the swing door among edge information corresponding to the swing door. For example, the reference point may be, but is not limited to, a point located at a preset distance from the rotation axis among a straight line adjacent to the floor within the swing door. According to one or more embodiments, the second control information module (1440) can identify second control information for the robot (100) to move according to the movement path and movement speed of the identified reference point.

[0160] According to one or more embodiments, the revolving door movement path identification module (1430) may identify third control information for the robot (100) to move within the revolving door by applying preset weights to each of the received first control information and second control information. The revolving door movement path identification module (1430) may control the driving unit (120) to move the robot (100) based on the identified third control information.

[0161] According to one embodiment, the revolving door entry point identification module (1445) can identify whether a swing door corresponding to a free space is located within a preset distance from a target location outside the revolving door. If the swing door is located within the preset distance from the target location outside the revolving door, the revolving door entry point identification module (1445) can control the driving unit (120) to exit the revolving door within a preset time from the time at which the swing door is identified as being located within the preset distance. The target location here may be any one of a plurality of intermediate target points included in the driving path.

[0162] According to one or more embodiments, the revolving door entry point identification module (1445) can identify the distance between the swing door and the target location based on the acquired captured image and map information corresponding to the driving space stored in the memory. The revolving door entry point identification module (1445) can control the driving unit (120) to exit the revolving door within a preset time from a time point identified as being within a preset distance. The preset time may be the time required for the robot to safely exit the revolving door. The preset time may be less than the time period during which the entrance of the revolving door is open.

[0163] According to one embodiment, the target position driving module (1450) can control the driving unit (120) to move the robot (100) to the target position when the robot (100) exits the revolving door.

[0164] According to the above-described example, the robot (100) can obtain information about the revolving door through the captured video and use this to determine a time point at which the robot can enter the revolving door. Once the time point at which the robot can enter the revolving door is identified, the robot (100) can enter the revolving door, move, and reach a target location. In this case, the robot (100) can drive while considering objects passing through or scheduled to pass through the revolving door. Accordingly, the robot (100) can safely pass through the revolving door while considering people around the revolving door, and can reach the target location without having to detour through the revolving door, thereby enabling efficient driving.

[0165] The methods according to the various embodiments of the present disclosure described above can be implemented in the form of applications that can be installed on existing robots. Alternatively, the methods according to the various embodiments of the present disclosure described above can be performed using a deep learning-based trained neural network (or a deep learning neural network), i.e., a learning network model. Furthermore, the methods according to the various embodiments of the present disclosure described above can be implemented with only a software upgrade or hardware upgrade for an existing robot. Furthermore, the various embodiments of the present disclosure described above can also be performed through an embedded server provided in the robot or an external server of the robot.

[0166] According to an example embodiment of the present disclosure, the various embodiments described above may be implemented as software including instructions stored in a machine-readable storage medium that can be read by a machine (e.g., a computer). The machine is a device that can call instructions stored in the storage medium and operate according to the called instructions, and may include a display device (e.g., display device (A)) according to the disclosed embodiments. When an instruction is executed by a processor, the processor can perform a function corresponding to the instruction directly or under the control of the processor by using other components. The instruction may include code generated or executed by a compiler or interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' means that the storage medium does not contain a signal and is tangible, but does not distinguish between data being stored semi-permanently or temporarily in the storage medium.

[0167] Furthermore, according to one embodiment, the method according to the various embodiments described above may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0168] In addition, each of the components (e.g., modules or programs) according to the various embodiments described above may be composed of a single or multiple entities, and some of the sub-components described above may further include other sub-components belonging to the various embodiments. Alternatively or additionally, some components (e.g., modules or programs) may be integrated into a single entity, which may perform the same or similar functions performed by each of the respective components prior to integration. Operations performed by modules, programs or other components according to the various embodiments may be executed sequentially, in parallel, iteratively or heuristically, or at least some operations may be executed in a different order, or other operations may be added.

[0169] Although examples have been illustrated and described above, the present disclosure is not limited thereto, and those skilled in the art to which the present disclosure pertains may make various modifications without departing from the scope of the present disclosure.

Claims

1. For robots that can drive, At least one sensor; drive unit; at least one processor; and When executed on at least one processor, When a revolving door is identified in the captured image acquired by at least one sensor, free space information of a free space within the revolving door and object information about an object scheduled to enter the revolving door are identified based on the captured image, Based on the identified free space information and the object information, the robot identifies a first point in time at which it can enter the revolving door, A robot comprising a memory storing at least one command for controlling the driving unit to allow the robot to enter the revolving door at the first point in time.

2. In paragraph 1, One or more of the above processors, If it is identified that the robot can enter the revolving door at the present time, the driving unit is controlled so that the robot enters the revolving door. A robot that executes at least one command to control the driving unit to wait until a second time point at which the revolving door can be entered, or to identify a driving path that avoids the revolving door, if it is identified that the revolving door cannot be entered at the current time point.

3. In paragraph 1, The above memory is, Store the first spatial information corresponding to the above robot, One or more of the above processors, Based on the free space information and the first space information corresponding to the robot, identify whether the first shape of the space corresponding to the robot is included within the second shape of the free space, A robot executing at least one command that identifies a third point in time at which the robot can enter the revolving door based on the first position of the free space, when the first shape is identified as being included within the second shape.

4. In paragraph 3, The above memory is, Further including second spatial information corresponding to the above object, The above object information is, It further includes movement path information about the movement path of the above object, One or more of the above processors, If it is identified that an entry into the revolving door is expected based on the above movement path information, the free space information is updated based on the second space information, Identifying whether the first shape is included in the second shape based on the updated free space information and the first space information, A robot executing at least one command that identifies a fourth point in time at which the robot can enter the revolving door based on a second position of the updated free space, when the third shape of the updated free space of the updated free space information is identified as including the first shape.

5. In paragraph 4, One or more of the above processors, If at least one second object is identified as expected to enter the revolving door based on the above movement path information, the number of the at least one second object and the entry location within the revolving door are identified, A robot executing at least one command that identifies a fifth entry point of the robot based on the number of at least one second object and the entry position within the revolving door.

6. In paragraph 1, The above free space information is, Contains at least one of radius information, rotation axis information, and angle information corresponding to the above free space, One or more of the above processors, Based on the above free space information, identify the location information for the third location of the free space within the revolving door and the movement speed information of the free space, A robot executing at least one command that identifies a sixth entry point of the robot based on the position information and the movement speed information.

7. In paragraph 6, One or more of the above processors, A robot that executes at least one command to control the driving unit so that the robot is positioned in the center area of ​​an inscribed circle corresponding to the free space when the robot enters the revolving door.

8. In paragraph 6, One or more of the above processors, When the robot enters the revolving door, it identifies a preset reference point within the swing door corresponding to the free space, A robot that executes at least one command to control the driving unit to move by following the above-described preset reference point.

9. In paragraph 8, One or more of the above processors, Identifying first control information for positioning the robot in the center area of ​​the inscribed circle corresponding to the free space, Identifying second control information for the robot to move by following the preset reference point, By applying preset weights to each of the first control information and the second control information, the robot identifies third control information for moving within the revolving door, A robot that executes at least one command that controls the driving unit based on the third control information.

10. In paragraph 1, One or more of the above processors, When the robot enters the revolving door, it identifies whether the swing door corresponding to the free space is located within a preset distance from the target location outside the revolving door, A robot that executes at least one command to control the driving unit to exit the revolving door within a preset time from a seventh time point identified as being located within the preset distance.

11. In paragraph 10, One or more of the above processors, Identifying whether at least one third object located within said revolving door exits said revolving door, A robot that executes at least one command to control the driving unit to exit the revolving door within a preset time from the seventh time point identified as being located within the preset distance, when at least one third object is identified as having exited the revolving door.

12. In a method for controlling a robot capable of driving, A step of identifying free space information about a free space within the revolving door and object information about an object scheduled to enter the revolving door based on the captured image when a revolving door is identified in a captured image acquired by at least one sensor; A step of identifying a first point in time at which the robot can enter the revolving door based on the free space information and the object information; and A control method, comprising: a step of controlling a driving unit so that the robot enters the revolving door at the first point in time; 13. In paragraph 12, The step of controlling the above driving unit is: If it is identified that the robot can enter the revolving door at the present time, the driving unit is controlled so that the robot enters the revolving door. The above control method is, A control method further comprising: a step of controlling the driving unit to wait until a second time point at which the revolving door can be entered, or identifying a driving path that avoids the revolving door, if it is identified that the revolving door cannot be entered at the current time point.

14. In paragraph 12, The step of identifying the first point in time is: A step of identifying whether a first shape of a space corresponding to the robot is included in a second shape of the free space based on the free space information and the first space information corresponding to the robot; and A control method comprising: a step of identifying a third point in time at which the robot can enter the revolving door based on the first position of the free space, when the first shape is identified as being included in the second shape.

15. A non-transitory computer-readable recording medium storing computer instructions that, when executed by at least one processor, cause a robot capable of operating to perform the following actions, wherein the actions are: A step of identifying free space information about a free space within the revolving door and object information about an object scheduled to enter the revolving door based on the captured image when a revolving door is identified in a captured image acquired by at least one sensor; A step of identifying a first point in time at which the robot can enter the revolving door based on the free space information and the object information; and A computer-readable recording medium, comprising: a step of controlling a driving unit so that the robot enters the revolving door at the first point in time;

Images