WO2024034855A1

WO2024034855A1 - Robot performing driving by using mask map and driving method thereof

Info

Publication number: WO2024034855A1
Application number: PCT/KR2023/009258
Authority: WO
Inventors: 고영일; 홍현기; 유인섭
Original assignee: 삼성전자주식회사
Priority date: 2022-08-09
Filing date: 2023-06-30
Publication date: 2024-02-15
Also published as: KR20240020880A

Abstract

A robot is disclosed. The robot according to the present disclosure comprises: a sensor; a memory in which a mask map is stored, the mask map being divided into a first region where the area around the robot can be sensed by the sensor and a second region where the area around the robot cannot be sensed by the sensor; and a processor which: identifies an object in the first region at a first time point through the sensor; identifies an object in the first region at a second time point through the sensor; on the basis of the location of the object identified at the first time point and movement of the robot at the second time point with respect to the first time point, identifies whether the object identified at the first time point is located in the second region at the second time point; if the object identified at the first time point is identified as being located in the second region at the second time point, stores, in the memory, location information of the object identified in the second region; and controls driving of the robot on the basis of the locations of the objects identified in the first and second regions at the second time point.

Description

A robot that performs driving using a mask map and its driving method

This disclosure relates to a robot that travels using a mask map and its driving method.

Robots are currently being used in many fields, and can be used not only in the aerospace field but also in industrial vehicles, autonomous driving of general vehicles, and robot vacuum cleaners in ordinary homes. In this case, the robot can sense the surrounding environment in real time using sensors, collect information, and drive autonomously.

A robot according to an embodiment of the present disclosure includes a sensor, a memory storing a mask map in which an area around the robot is divided into a first area detectable by the sensor and a second area not detected by the sensor, and a processor. do. The processor identifies an object in the first area through the sensor at a first time point, and identifies the object in the first area through the sensor at a second time point. The processor determines that the object identified at the first time point is based on the location of the object identified at the first time point and the movement of the robot at the second time point based on the first time point. Identify whether it is located in the second area. When the object identified at the first time point is identified as being located in the second area at the second time point, the processor stores the location information of the object identified in the second area in the memory, and stores the location information of the object identified in the second area in the memory at the second time point. The driving of the robot is controlled based on the positions of objects identified in the first and second areas.

A method of driving a robot including a sensor according to an embodiment of the present disclosure and a memory storing a mask map in which an area around the robot is divided into a first area detectable by the sensor and a second area not detected by the sensor. Identifying an object in the first area through the sensor at a first time point, identifying an object in the first area through the sensor at a second time point, the location of the object identified at the first time point, and Based on the movement of the robot at the second viewpoint relative to the first viewpoint, identifying whether the object identified at the first viewpoint is located in the second area at the second viewpoint, and the first If the object identified at the viewpoint is identified as being located in the second area at the second viewpoint, the location information of the object identified in the second area is stored in the memory, and the first and second objects are stored at the second viewpoint. A driving method comprising controlling the driving of the robot based on the position of an object identified in area 2.

A processor according to an embodiment of the present disclosure includes a memory storing a mask map in which the area around the sensor and the robot is divided into a first area that can be detected by the sensor and a second area that is not detected by the sensor. A non-transitory computer-readable medium storing computer instructions that cause the robot to perform an action when executed by the robot, wherein the action includes identifying an object in the first area through the sensor at a first time point, and a second time point. Identifying an object in the first area through the sensor, based on the location of the object identified at the first viewpoint and the movement of the robot at the second viewpoint with respect to the first viewpoint, identifying whether the object identified at a first time point is located in the second area at the second time point; and if the object identified at the first time point is identified as being located in the second area at the second time point, It includes storing location information of the object identified in the second area in the memory, and controlling the driving of the robot based on the location of the object identified in the first and second areas at the second time point.

1 is a diagram for explaining a robot according to an embodiment of the present disclosure;

2 is a block diagram for explaining the configuration of a robot according to an embodiment of the present disclosure;

3 is a diagram for explaining a mask map according to an embodiment of the present disclosure;

4 to 10 are diagrams for explaining a method of identifying an object located in an invisible area according to an embodiment of the present disclosure;

11 and 12 are diagrams for explaining a method of updating a mask map according to an embodiment of the present disclosure;

13 is a block diagram for explaining the detailed configuration of a robot according to an embodiment of the present disclosure, and

Figure 14 is a flowchart for explaining a robot driving method according to an embodiment of the present disclosure.

Since these embodiments can be modified in various ways and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope to specific embodiments, and should be understood to include various modifications, equivalents, and/or alternatives to the embodiments of the present disclosure. In connection with the description of the drawings, similar reference numbers may be used for similar components.

In describing the present disclosure, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present disclosure, the detailed description thereof will be omitted.

In addition, the following examples may be modified into various other forms, and the scope of the technical idea of the present disclosure is not limited to the following examples. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to completely convey the technical idea of the present disclosure to those skilled in the art.

The terms used in this disclosure are merely used to describe specific embodiments and are not intended to limit the scope of rights. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In the present disclosure, expressions such as “have,” “may have,” “includes,” or “may include” refer to the presence of the corresponding feature (e.g., component such as numerical value, function, operation, or part). , and does not rule out the existence of additional features.

In the present disclosure, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” includes (1) at least one A, (2) at least one B, or (3) it may refer to all cases including both at least one A and at least one B.

Expressions such as “first,” “second,” “first,” or “second,” used in the present disclosure can modify various components regardless of order and/or importance, and can refer to one component. It is only used to distinguish from other components and does not limit the components.

A component (e.g., a first component) is “(operatively or communicatively) coupled with/to” another component (e.g., a second component). When referred to as being “connected to,” it should be understood that any component may be directly connected to the other component or may be connected through another component (e.g., a third component).

On the other hand, when a component (e.g., a first component) is said to be “directly connected” or “directly connected” to another component (e.g., a second component), It may be understood that no other component (e.g., a third component) exists between other components.

The expression “configured to” used in the present disclosure may mean, for example, “suitable for,” “having the capacity to,” depending on the situation. ," can be used interchangeably with "designed to," "adapted to," "made to," or "capable of." The term “configured (or set to)” may not necessarily mean “specifically designed to” in hardware.

Instead, in some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "processor configured (or set) to perform A, B, and C" refers to a processor dedicated to performing the operations (e.g., an embedded processor), or by executing one or more software programs stored on a memory device. , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

In an embodiment, a 'module' or 'unit' performs at least one function or operation, and may be implemented as hardware or software, or as a combination of hardware and software. Additionally, a plurality of 'modules' or a plurality of 'units' may be integrated into at least one module and implemented with at least one processor, except for 'modules' or 'units' that need to be implemented with specific hardware.

Meanwhile, various elements and areas in the drawing are schematically drawn. Accordingly, the technical idea of the present invention is not limited by the relative sizes or spacing drawn in the attached drawings.

Hereinafter, with reference to the attached drawings, embodiments according to the present disclosure will be described in detail so that those skilled in the art can easily implement them.

1 is a diagram for explaining a robot according to an embodiment of the present disclosure.

Referring to FIG. 1, the robot 100 may be implemented as various types of robots. For example, the robot 100 may be implemented as a robot vacuum cleaner. That is, the robot 100 can move and suck foreign substances such as dirt and dust present on the floor. As another example, the robot 100 may be implemented as a retail robot or guide robot. That is, the robot 100 may perform functions such as guiding the user on a route within the store, explaining products within the store to the user, or carrying the user's items and moving along with the user within the store.

Meanwhile, the robot 100 can travel in the space where the robot 100 is located. In this case, the space may include a variety of spaces, including indoor spaces such as homes, offices, hotels, factories, stores, airports, etc., as well as outdoor spaces such as roads and construction sites.

Here, driving the robot may mean identifying the location of the robot on the map, establishing a travel plan, and moving the space where the robot is located.

To this end, the robot can detect objects 11 and 12 (e.g., obstacles such as walls, home appliances, furniture, people, cars, etc.) around the robot.

At this time, the robot can detect the object using a sensor. In this case, there may be areas around the robot that are not detected by the sensor depending on the characteristics of the sensor, attachment location, attachment environment, etc.

For example, in the case of a camera, there may be areas around the robot that cannot be detected by the camera because they are not captured due to the camera's viewing angle or the camera's fixed shooting direction. As another example, the LiDAR sensor may be attached to a specific space within the robot. At this time, there may be a pillar structure to form a space where the LiDAR sensor is attached. In this case, even if a 360° direction is detected through the LiDAR sensor, the visible range of the LiDAR sensor may be obscured by the pillar structure, which may result in an area that is not detected.

In this case, even though the obstacle has been observed more than once, if the obstacle is located in an area that is not detected by the sensor as the robot moves or rotates, the relative position information of the obstacle is missing, and the robot moves to the area. There is a possibility of collision with an object located in .

Accordingly, according to an embodiment of the present disclosure, the robot 100 uses the mask map 20 to identify whether an object is located in an area not detected by the sensor and performs driving using the identification result. You can.

Here, the mask map 20 may be a map that divides the area around the robot 100 into an area that can be detected by the sensor and an area that is not detected by the sensor. The mask map 10 may also be referred to as a nonvisibility mask map.

Specifically, the robot 100 can detect objects around the robot 100 using a sensor. And, when the robot 100 moves, the robot 100 determines whether an object previously detected by the sensor is located in an area not detected by the sensor on the mask map 20 according to the movement of the robot 100. can be identified.

As such, according to an embodiment of the present disclosure, the robot 100 uses previous detection results to identify whether an object is located in an area that is not currently detected by the sensor, and uses the most recent information among the collected obstacle location information. In that it is updated to reflect in the invisible area, more stable and reliable driving can be performed.

Figure 2 is a block diagram for explaining the configuration of a robot according to an embodiment of the present disclosure.

Referring to FIG. 2, the robot 100 includes a sensor 110, a memory 120, and a processor 130.

The sensor 110 can obtain various information related to the robot 100 and its surrounding environment.

For example, the sensor 110 may include a light detection and ranging (LiDAR) sensor or a laser distance sensor (LDS). The LiDAR sensor irradiates light, and when the irradiated light is reflected and received from an object around the robot 100, it can detect the distance to the object based on the time the light was received. In this case, the processor 120 can identify the distance to surrounding objects through the LiDAR sensor.

Additionally, the sensor 110 may include a camera. Cameras may include time of flight (TOF) cameras, stereo cameras, etc. The camera may acquire an image by photographing the surroundings of the robot 100. In this case, the processor 120 can recognize an object in an image acquired through a camera and obtain information about the location, type, shape, size, etc. of the object existing around the robot 100.

Additionally, the sensor 110 may include a gyro sensor. The gyro sensor can measure the rotational angular rate (roll-rate) about the x-axis, the rotational angular rate (pitch-rate) about the y-axis, and the rotational angular rate (yaw-rate) about the z-axis of the robot 100. In this case, the processor 120 may obtain information about the posture of the robot 100, such as the rotation angle and direction of the robot 100, through the gyro sensor.

Additionally, the sensor 110 may include an encoder. The encoder can measure the distance traveled by the robot 100 by detecting the number of rotations of the wheels installed on the robot 100. In this case, the processor 120 may obtain information about the moving distance of the robot 100 through the encoder.

The memory 120 may store at least one instruction regarding the robot 100. Additionally, an O/S (Operating System) for driving the robot 100 may be stored in the memory 120. Additionally, the memory 120 may store various software programs or applications for operating the robot 100 according to various embodiments of the present disclosure. Additionally, the memory 120 may include volatile memory such as a frame buffer, semiconductor memory such as flash memory, or magnetic storage media such as a hard disk.

Specifically, the memory 120 may store various software modules for operating the robot 100 according to various embodiments of the present disclosure, and the processor 130 may execute various software modules stored in the memory 120. The operation of the robot 100 can be controlled. That is, the memory 120 is accessed by the processor 130, and data read/write/modify/delete/update, etc. can be performed by the processor 140.

Meanwhile, in the present disclosure, the term memory 120 refers to memory 120, ROM (not shown), RAM (not shown) in the processor 130, or a memory card (not shown) mounted on the robot 100 (for example, For example, it can be used to mean including micro SD card, memory stick).

In particular, the memory 120 may store a mask map.

The mask map may be a map in which the area around the robot 100 is divided into a first area that can be detected by the sensor 110 and a second area that is not detected by the sensor 110. At this time, the first area may be referred to as a visible area, and the second area may be referred to as an invisible area. Here, the sensor 110 may include a camera and a LiDAR sensor.

For example, as shown in (1) of FIG. 3, the mask map 20 may include an area having the shape of a circle with the center of the robot 100 as the origin.

At this time, the radius of the circle may be set to a distance that can be detected by the sensor 110 from the robot 100 or less. Here, the distance that can be sensed by the sensor 110 may mean the distance from an image captured by a camera to an object that can be sensed and the distance to an object that can be sensed by a LiDAR sensor.

At this time, the mask map 20 may include a plurality of cells divided based on a polar coordinate system with the center of the robot 100 as the origin. At this time, the size of the cell can be determined based on the directed distance (radial, r) and the directed direction (azimuth, θ).

In this case, the first area 21 may include at least one cell in which an object located in the cell among the plurality of cells is detected by the sensor 110. That is, the first area 21 may include at least one cell in which the object can be detected by the sensor 110, if an object exists in the cell, based on the position of the robot 100. .

The second area 22 may include at least one cell among a plurality of cells in which an object located in the cell is not detected by the sensor 110 . That is, based on the position of the robot 100, the second area 22 may include at least one cell in which the object is not detected by the sensor 110, even if an object exists in the cell.

That is, depending on the characteristics of the camera, lidar sensor, etc., attachment location, attachment environment, etc., there may be an area around the robot 100 that cannot be detected by the sensor 110.

For example, depending on the camera's viewing angle or shooting direction, it may exist in an area around the robot 100 that cannot be detected by the camera. As another example, in the case of a LiDAR sensor, the light emitted from the LiDAR sensor may not be emitted to the outside of the robot 100 due to a pillar structure within the robot existing around the LiDAR sensor. In this case, the fan-shaped area may not be detected by the LiDAR sensor.

As another example, depending on the camera's viewing angle or shooting direction, it may exist in an area around the robot 100 that cannot be detected by the camera. Referring to (2) of FIG. 3, in the case of the mask map 23 generated by the camera, the front, which is the direction the camera is facing, is a visible area and can form the first area 24, and the first area 24 can be formed. The non-visible area may be determined as the second area 25.

Accordingly, in the present disclosure, the area detected by the sensor 110 and the area not detected around the robot 100 are confirmed in advance, a mask map 20 is generated based on this, and the generated mask map 20 is used. Can be stored in memory 120.

Hereinafter, a method for generating a mask map according to an embodiment of the present disclosure will be described.

Specifically, a plurality of cells based on polar coordinates can be created based on the directed distance and directed direction. At this time, the plurality of cells may form a circular area with the center of the robot 100 as the origin.

Also, the state of each of the plurality of cells can be initialized to nonvisible.

Thereafter, for each cell, after placing an object within the cell, it is possible to identify whether the corresponding object is detected by the sensor 110 of the robot 100.

At this time, in the case of a cell in which an object is detected, the state of the cell can be changed to visible, and in the case of a cell in which an object is not detected, the state of the cell can be maintained as invisible.

According to this method, a mask map 20 can be generated by dividing a plurality of cells into a visible area and an invisible area. At this time, a cell in a visible state may correspond to the first area 21 in the mask map 20, and a cell in an invisible state may correspond to the second area 22 in the mask map 20.

According to an embodiment of the present disclosure, the mask map 20 may be created based on the polar coordinate system. Here, the polar coordinate system has the characteristic that the closer it is to the origin, the smaller the cell size is, and the farther it is from the origin, the larger the cell size is. That is, if a polar coordinate system is used with the center of the robot 100 as the origin, the closer the cell is to the robot 100, the smaller the cell size is, and the farther away it is from the robot 100, the larger the cell size is. Therefore, if the mask map 20 is generated based on the polar coordinate system, the closer it is to the robot 100, the more precisely the invisible area where the sensor 110 cannot identify the object can be defined. However, this is only an example, and according to an embodiment of the present disclosure, the mask map 20 may be generated based on an orthogonal coordinate system.

Meanwhile, the processor 130 controls the overall operation of the robot 100. Specifically, the processor 130 is connected to the configuration of the robot 100 including the sensor 110 and the memory 120, and operates the robot 100 by executing at least one instruction stored in the memory 120. can be controlled overall. In this case, the processor 130 may not only be implemented as one processor, but may also be implemented as a plurality of processors. Meanwhile, in the present disclosure, the term processor 130 may be used to include a central processing unit (CPU), graphics-processing unit (GPU), etc.

Specifically, the processor 130 may identify an object in the first area 21 through the sensor 110 at a first time point. Additionally, the processor 130 may identify an object in the first area 21 through the sensor 110 at a second viewpoint.

As described above, the first area 21 corresponds to an area around the robot 100 that can be detected by the sensor 110. Accordingly, when an object exists around the robot 100, the processor 130 may detect the object in the first area 20 around the robot 100 using a camera, a lidar sensor, etc.

Additionally, the second time point may be a time point after the first time point. Specifically, the processor 130 can detect an object by scanning the area around the robot 100 at regular time intervals through the sensor 110. Here, scanning may include performing photography through a camera or irradiating light through a LiDAR sensor to detect an object. At this time, if the scan is performed at the first time point, the second time point may be a time point at which the scan is performed following the first time point. That is, in terms of the time point at which the scan is performed, the second time point may be a consecutive time point following the first time point. However, this is only an example, and the second viewpoint is not continuous with the first viewpoint, but may be a viewpoint after the first viewpoint. For example, the second viewpoint may be a certain point in time away from the first viewpoint.

The processor 130 may identify the location of the object identified at the first viewpoint and the location of the object identified at the second viewpoint.

Here, the location of the object identified at the first viewpoint and the location of the object identified at the second viewpoint may be expressed in polar coordinates. For example, the location of the object may be expressed as a directed distance (r) and a directed direction (θ) in the polar coordinate system of the robot 100 where the center of the robot 100 is located at the origin.

And, the processor 130 determines that the object identified at the first viewpoint is based on the position of the object identified at the first viewpoint and the movement of the robot 100 at the second viewpoint based on the first viewpoint. It is possible to identify whether it is located in the second area 22. As an example, the processor 130 may identify pose information at a first viewpoint and pose information at a second viewpoint, and identify the movement of the robot 100 based on the identified pose information.

Here, the movement of the robot 100 includes the distance the robot 100 moved based on the first viewpoint, the direction in which the robot 100 moved based on the first viewpoint, and the movement of the robot 100 based on the first viewpoint. It may include at least one of these rotation directions. That is, the movement of the robot 100 at the second viewpoint based on the first viewpoint takes into account the position and posture of the robot 100 at the first viewpoint, etc., so that the robot 100 at the second viewpoint is It may include how far the robot 100 is located in which direction from its position and how much it has rotated based on the posture of the robot 100 at the first viewpoint.

To this end, the processor 130 may identify the position of the robot 100 at the first viewpoint and the position of the robot 100 at the second viewpoint.

For example, the processor 130 uses data sensed through the sensor 110 and a simultaneous localization and mapping (SLAM) algorithm to identify the location of the robot 100 on a map of the space where the robot 100 is located. can do. Here, the position of the robot 100 can be expressed in polar coordinates. For example, the location of the robot 100 may be expressed in terms of directed distance and directed direction on the polar coordinate system of the map, where a specific point of the map is located at the origin. Although the polar coordinate system has been described as an example, it is not limited to this and, of course, other coordinate systems such as a Cartesian coordinate system can be used.

And, based on the identified location, the processor 130 may identify the movement of the robot 100 at the second viewpoint based on the first viewpoint.

For example, assume that the position of the robot 100 on the map at the first time point is (r _a , θ _a ), and that the position of the robot 100 on the map at the second time point is (r _b , θ _b ). do. In this case, the processor 130 calculates the difference between the identified directed distance and directed direction, that is, (Δr, Δθ)=(r _b -r _a , θ _b -θ _a ) at a second time point based on the first time point. It can be identified as the movement of the robot 100.

On the other hand, the processor 130 controls the movement of the robot 100 at the second viewpoint based on the first viewpoint based on the distance and direction in which the robot 100 moved from the first viewpoint to the second viewpoint. can also be identified. To this end, the processor 130 uses an encoder to identify the distance that the robot 100 has moved from the first point in time to the second point in time, and uses a gyro sensor to determine the distance that the robot 100 has moved from the first point in time to the second point in time. Direction can be identified.

For example, assume that the moving distance and moving direction of the robot 100 from the first time point to the second time point are (r _c , θ _c ). In this case, the processor 130 calculates the identified movement distance and movement direction, that is, (Δr, Δθ)=(r _c , θ _c ), as the movement of the robot 100 at the second viewpoint based on the first viewpoint. It can be identified as

And, the processor 130 determines that the object identified at the first viewpoint is based on the position of the object identified at the first viewpoint and the movement of the robot 100 at the second viewpoint based on the first viewpoint. It is possible to identify whether it is located in the second area 22.

To this end, the processor 130 identifies the coordinate value of an object located in the first area 21 at a first viewpoint, and converts the identified coordinate value based on the movement of the robot 100 to correspond to the second viewpoint. can do.

Here, converting the coordinate value to correspond to the second viewpoint means converting the coordinate value of the object identified in the first area 21 at the first viewpoint to the robot 100 on a coordinate system with the center of the robot 100 as the origin. This may mean conversion based on the distance and direction traveled from the first time point to the second time point. For example, the coordinate values of the object located in the first area 21 at the first viewpoint are (r _d , θ _d ), and the movement distance and direction of movement of the robot 100 from the first viewpoint to the second viewpoint are Assume the case is (r _e , θ _e ).

In this case, the processor 130 uses the coordinate values (r _d , θ _d ) of the object identified in the first area 21 at the first time point as (r _d ' , θ _d '). Specifically, the processor 130 determines that the location of the object identified at the first viewpoint in a coordinate system with the center of the robot 100 as the origin is (x, y)=(r _d cos(θ _d )-r _e cos(θ _e ), r _d sin(θ _d )-r _e sin(θ _e )), and this is calculated as (r _d ', θ _d ')=(

) can be expressed as

In this way, when converting the coordinate values (r _object , θ _object ) of an object using the movement (r _robot , θ _robot ) of the robot 100, the converted coordinate values (r _object ', θ _object ') are ( It can be expressed as r _object ', θ _object ')=f(r _object , θ _object , r _robot , θ _robot ).

For example, as shown in FIG. 4, the processor 130 may detect an object in the first area 21 around the robot 100 at t-1 seconds and identify the coordinate value of the detected object. At this time, the coordinate value of the object is the coordinate value in the polar coordinate system centered on the robot. And, as shown in FIG. 4, the processor 130 calculates the coordinate values of the object ((r ₁ , θ ₁ ) (411), (r ₂ , θ ₂ ) (412), (r ₃ , θ ₃ ) (413), (r ₄ , θ ₄ ) (414)) can be displayed on the mask map 20. Meanwhile, although it is shown that four points are detected in the embodiment, this is only an example for convenience of explanation, and of course, fewer or more points than four points may be detected.

Meanwhile, the robot 100 may move and be located in a different position from the first viewpoint at the second viewpoint.

In this case, as shown in FIG. 5, the processor 130 may detect an object in the first area 21 around the robot 100 at t seconds and identify the coordinate value of the detected object. At this time, the coordinate value of the object is the coordinate value in the polar coordinate system centered on the robot. And, as shown in FIG. 5, the processor 130 may display the coordinate values of the object ((r ₅ , θ ₅ ) 415, (r ₆ , θ ₆ ) 416) on the mask map 20. .

Referring to FIG. 5, an object that was detected at t-1 seconds may not be detected at t seconds. This is because, as the robot 100 moves, the object is located in the second area 22 where it is not detected by the sensor 110 at t seconds.

Meanwhile, the processor 130 may convert the coordinate value of the object identified at the first viewpoint based on the movement of the robot 100 at the second viewpoint based on the first viewpoint.

At this time, as described above, the movement of the robot 100 at the second viewpoint based on the first viewpoint may be expressed as a directed distance and directed direction in polar coordinates. Accordingly, the processor 130 can convert the coordinate value of the object identified at the first viewpoint by applying the directed distance and directed direction corresponding to the movement of the robot 100 to the coordinate value of the object identified at the first viewpoint. there is.

For example, assume that the movement of the robot 100 at the second viewpoint based on the first viewpoint is equal to (Δr ₁ , Δθ ₁ ). In this case, as shown in FIG. 6, the processor 130 converts (Δr ₁ , Δθ ₁ ) into the coordinate values ((r ₁ , θ ₁ ) of the object identified at t-1 seconds (411), (r ₂ , θ ₂ )(412), (r ₃ , θ ₃ )(413), (r ₄ , θ ₄ )(414)), the coordinate value of the object can be converted. Accordingly, the converted coordinate value is (r ₁ ', θ ₁ ')(=f(r ₁ , θ ₁ ,Δr ₁ , Δθ ₁ ))(421), (r ₂ ', θ ₂ ')(=f(r _2, θ ₂ ,Δr ₁ , Δθ ₁ ))(422), (r ₃ ', θ ₃ ')(=f(r ₃ , θ ₃ ,Δr ₁ , Δθ ₁ ))(423), (r ₄ ', θ ₄ ')(=f(r ₄ , θ ₄ ,It may be equal to Δr ₁ , Δθ ₁ ))(424).

Afterwards, the processor 130 may display the converted coordinate values on the mask map 20. Additionally, the processor 130 may identify whether a coordinate value located in the second area 22 of the mask map 20 exists among the converted coordinate values.

For example, as shown in FIG. 6, among the converted coordinate values, (r ₁ ', θ ₁ ') 421 and (r ₂ ', θ ₂ ') 422 are the first part of the mask map 20 at t seconds. It is located in area 2 (22). In this case, the processor 130 may identify (r ₁ ', θ ₁ ') and (r ₂ ', θ ₂ ') as being located in the second area 20 at t seconds.

In this way, when the converted coordinate value is located in the second area 22, the processor 130 may identify the object identified at the first viewpoint as being located in the second area 22 at the second viewpoint. .

That is, in that the position of the object identified at the first viewpoint is converted based on the movement of the robot 100 from the first viewpoint to the second viewpoint, the converted position corresponds to the position of the object at the second viewpoint. Accordingly, when the converted coordinate value is located in the second area 22, the processor 130 identifies the object identified at the first viewpoint as being located in the second area 22 at the second viewpoint.

In this way, if the object identified at the first time point is identified as being located in the second area at the second time point, the processor 130 may store the location information of the object identified in the second area in the memory 120.

Here, the location information of the object may mean information about the location of the object when the object identified at the first viewpoint is identified as being located in the second area at the second viewpoint. That is, the location information of the object may be a coordinate value converted from the coordinate value of the object identified at the first viewpoint based on the movement of the robot 100. In the above example, processor 130, in that (r ₁ ', θ ₁ ') 421 and (r ₂ ', θ ₂ ') 422 are located in the second region 22 at second t. (r ₁ ', θ ₁ ') 421 and (r ₂ ', θ ₂ ') 422 can be stored in the memory 120.

Additionally, the processor 130 may control the driving of the robot 100 based on the positions of objects identified in the first and

second areas

21 and 22 at the second viewpoint.

The second area is an area where no object is detected by the sensor 110, based on the current location of the robot 100. That is, even if the object exists in the second area, the object is not detected by the sensor 110. Accordingly, the processor 130 can identify whether the object is located in the second area at the second viewpoint based on the location of the object identified at the first viewpoint, and identify the location of the object in the second area at the second viewpoint. there is. Meanwhile, the first area is an area where objects around the robot 100 can be detected by the sensor 110, based on the current location of the robot 100. Accordingly, the processor 130 may identify the location of the object in the first area through the sensor 110 at the second viewpoint.

Additionally, the processor 130 may control the robot 100 to run while avoiding objects located in the first and second areas based on the positions of the objects identified in the first and second areas.

For example, referring to Figure 7, at second t, the coordinate values of the object identified in the second region are (r ₁ ', θ ₁ ') (421), (r ₂ ', θ ₂ ') (422) and the coordinate values of the object identified in the first area are (r ₅ , θ ₅ ) (415) and (r ₆ , θ ₆ ) (416). In this case, the processor 130 integrates these coordinate values, identifies the location of the object existing in the first and second areas around the robot 100, and uses the location of the identified object to avoid the object and drive. The robot 100 can be controlled to do so.

Meanwhile, if the processor 130 determines that the object identified at the first time point is not located in the second area at the second time point, the processor 130 moves the robot 100 based on the location of the object identified in the first area at the second time point. You can control the driving of .

That is, if the object identified at the first viewpoint is identified as not being located in the second area at the second viewpoint, the object can be viewed as existing only in the first area at the second viewpoint. In this case, the processor 130 identifies the location of the object in the first area through the sensor 110 at the second viewpoint, and controls the robot 100 to run while avoiding the object using the location of the identified object. You can.

Additionally, the processor 130 may identify an object in the first area through the sensor 110 at a third viewpoint.

The third point in time may be a point in time after the second point in time. Specifically, the processor 130 can detect an object by scanning the area around the robot 100 at regular time intervals through the sensor 110. Here, scanning may include performing photography through a camera or irradiating light through a LiDAR sensor to detect an object. At this time, if the scan is performed at the second time point, the third time point may be the time point at which the scan is performed following the second time point. That is, in terms of the time point at which the scan is performed, the third time point may be a consecutive time point following the second time point. However, this is only an example, and the third viewpoint is not continuous with the second viewpoint, but may be a viewpoint after the second viewpoint. For example, the third viewpoint may be a certain point in time away from the second viewpoint.

The processor 130 may identify the location of the object identified at the second viewpoint and the location of the object identified at the third viewpoint.

Here, the location of the object identified at the second viewpoint and the location of the object identified at the third viewpoint may be expressed in polar coordinates. For example, the location of the object may be expressed as a directed distance and a directed direction on the polar coordinate system of the robot 100 where the center of the robot 100 is located at the origin.

And, the processor 130 determines that the object identified at the second viewpoint is based on the position of the object identified at the second viewpoint and the movement of the robot 100 at the third viewpoint based on the second viewpoint. It is possible to identify whether it is located in the second area 22.

Here, the movement of the robot 100 includes the distance the robot 100 moved based on the second viewpoint, the direction in which the robot 100 moved based on the second viewpoint, and the movement of the robot 100 based on the second viewpoint. It may include at least one of these rotation directions.

That is, the movement of the robot 100 at the third viewpoint based on the second viewpoint takes into account the position and posture of the robot 100 at the second viewpoint, etc., so that the robot 100 at the third viewpoint is It may include how far the robot 100 is located in which direction from its position and how much it has rotated based on the posture of the robot 100 at the second viewpoint.

To this end, the processor 130 may identify the position of the robot 100 at the second viewpoint and the position of the robot 100 at the third viewpoint.

For example, the processor 130 uses information acquired through the sensor 110 and a simultaneous localization and mapping (SLAM) algorithm to identify the location of the robot 100 on a map of the space where the robot 100 is located. can do. Here, the position of the robot 100 can be expressed in polar coordinates. For example, the location of the robot 100 may be expressed in terms of directed distance and directed direction on the polar coordinate system of the map, where a specific point of the map is located at the origin.

And, based on the identified location, the processor 130 may identify the movement of the robot 100 at the third viewpoint based on the second viewpoint.

For example, assume that the position of the robot 100 on the map at the second viewpoint is (r _e , θ _e ), and that the position of the robot 100 on the map at the third viewpoint is (r _f , θ _f ). do. In this case, the processor 130 calculates the difference between the identified directed distance and directed direction, that is, (Δr, Δθ)=(r _f -r _e , θ _f -θ _e ) at a third time point based on the second time point. It can be identified as the movement of the robot 100.

On the other hand, the processor 130 controls the movement of the robot 100 at the third viewpoint based on the second viewpoint, based on the distance and direction in which the robot 100 moved from the second viewpoint to the third viewpoint. can also be identified. To this end, the processor 130 uses an encoder to identify the distance the robot 100 has moved from the second time point to the third time point, and uses the gyro sensor to determine the distance the robot 100 has moved from the second time point to the third time point. Direction can be identified.

For example, assume that the moving distance and moving direction of the robot 100 from the second to the third time point are (r _g , θ _g ). In this case, the processor 130 determines the identified movement distance and direction, that is, (Δr, Δθ)=(r _g , θ _g ), as the movement of the robot 100 at the third viewpoint based on the second viewpoint. can be identified.

To this end, the processor 130 identifies the coordinate value of an object located in the first area 21 at the second viewpoint, and converts the identified coordinate value based on the movement of the robot 100 to correspond to the third viewpoint. can do.

Here, converting the coordinate value to correspond to the third viewpoint means converting the coordinate value of the object identified in the first area 21 at the second viewpoint to the robot 100 on a coordinate system with the center of the robot 100 as the origin. This may mean moving based on the distance and direction moved from the second viewpoint to the third viewpoint. For example, the coordinate values of the object located in the first area 21 at the second viewpoint are (r _h , θ _h ), and the movement distance and direction of movement of the robot 100 from the second viewpoint to the third viewpoint are Assume the case is (r _i , θ _i ).

In this case, the processor 130 uses the coordinate values (r _d , θ _d ) of the object identified in the first area 21 at the second time point as (r _h ') using the movement distance and direction of movement of the robot 100. , θ _h '). As described above, the converted coordinate values (r _h ', θ _h ') can be expressed as (r _h ', θ _h ')=f(r _h , θ _h, r _i , θ _i ).

Meanwhile, the robot 100 may move and be located in a different position from the second viewpoint at the third viewpoint. In this case, as shown in FIG. 8, the processor 130 may detect an object in the first area 21 around the robot 100 at t+1 seconds and identify the coordinate value of the detected object. At this time, the coordinate value of the object is a coordinate value in the polar coordinate system. And, as shown in FIG. 8, the processor 130 can display the coordinate values of the object ((r ₇ , θ ₇ ) (511) and (r ₈ , θ ₈ ) (512)) on the mask map 20. . Meanwhile, in the embodiment, it is shown that two points are detected, but this is only an example for convenience of explanation, and of course, fewer or more points than two can be detected.

Referring to FIG. 8, an object that was not detected at t seconds may be detected at t+1 seconds. Additionally, an object that was detected at t seconds may not be detected at t+1 seconds. As the robot 100 moves, it is located in the first area 21 where the object is detected by the sensor 110 at t+1 seconds, and the second area 21 where the object is not detected by the sensor 110 ( This is because it was located at 22).

Meanwhile, the processor 130 may convert the coordinate value of the object identified at the second viewpoint based on the movement of the robot 100 at the third viewpoint based on the second viewpoint.

At this time, as described above, the movement of the robot 100 at the third viewpoint based on the second viewpoint may be expressed as a directed distance and directed direction in polar coordinates. Accordingly, the processor 130 can convert the coordinate value of the object identified at the second viewpoint by applying the directed distance and directed direction corresponding to the movement of the robot 100 to the coordinate value of the object identified at the second viewpoint. there is.

Here, the object identified at the second viewpoint may include the object identified in the first area through the sensor 110. Additionally, when an object identified in the second area exists, the object identified at the second time point may include the object identified in the second area.

For example, assume that the movement of the robot 100 at the third viewpoint based on the second viewpoint is equal to (Δr ₂ , Δθ ₂ ).

In this case, as shown in (1) and (2) of FIG. 9, the processor 130 calculates the coordinate values ((r ₅ , θ ₅ ) (415), (r ₆ , θ ₆ ) (416)) can be applied to (Δr ₂ , Δθ ₂ ) to transform the coordinate value of the object identified in the first area 21 at time t. In this case, the converted coordinate values are (r ₅ ', θ ₅ ')(=f(r ₅ , θ _5, Δr ₂ , Δθ ₂ ))(523), (r ₆ ', θ ₆ ')(=f It may be equal to (r _6, θ _6, Δr ₂ , Δθ ₂ )) (524).

In addition, as shown in (3) and (4) of FIG. 9, the processor 130 calculates the coordinate values ((r ₁ ', θ ₁ ') (421), (r ₂ ', θ ₂ ') (422)) by applying (Δr ₂ , Δθ ₂ ) to convert the coordinate value of the object identified in the second area 22 at time t. You can. In this case, the converted coordinate values are (r ₁ '', θ ₁ '')(=f(r ₁ ', θ ₁ ' _, Δr ₂ , Δθ ₂ ))(521), (r ₂ '', θ ₂ '')(=f(r ₂ ', θ ₂ ' _, Δr ₂ , Δθ ₂ )) (522).

For example, as shown in (1) and (2) of FIG. 9, (r ₆ ', θ ₆ ') 524 among the converted coordinate values is located in the second area 22 of the mask map 20. do. In addition, as shown in (3) and (4) of FIG. 9, (r ₁ '', θ ₁ '') 521 among the converted coordinate values is located in the second area 22 of the mask map 20. do. In this case, the processor 130 may identify (r ₆ ', θ ₆ ') 524 and (r ₁ '', θ ₁ '') 521 as being located in the second area 22. .

In this way, when the converted coordinate value is located in the second area 22, the processor 130 may identify the object identified at the second viewpoint as being located in the second area 22 at the third viewpoint. . That is, in that the position of the object identified at the second viewpoint was converted based on the movement of the robot 100 from the second viewpoint to the third viewpoint, the converted position corresponds to the position of the object at the third viewpoint. . Accordingly, when the converted coordinate value is located in the second area 22, the processor 130 identifies the object identified at the second viewpoint as being located in the second area 22 at the third viewpoint.

Additionally, if the object identified at the second time point is identified as being located in the second area at the third time point, the processor 130 may store location information of the object identified in the second area in the memory 120.

Here, the location information of the object may mean information about the location of the object when the object identified at the second viewpoint is identified as being located in the second area at the third viewpoint. That is, the location information of the object may be a coordinate value converted from the coordinate value of the object identified at the second viewpoint based on the movement of the robot 100. In the above-described example, given that (r ₆ ', θ ₆ ') 524 is located in the second region 22, processor 130 stores (r ₆ ', θ ₆ ') 524 as memory ( 120). Additionally, given that (r ₁ '', θ ₁ '') 521 is located in the second area 22, the processor 130 uses the existing coordinate value (r ₁ ', θ ₁ ') 421 can be updated to (r ₁ '', θ ₁ '') 521 , and (r ₁ '', θ ₁ '') 521 can be stored in the memory 120 .

second areas

21 and 22 at the third viewpoint.

That is, the second area is an area in which objects around the robot 100 are not detected by the sensor 110, based on the current location of the robot 100. Even if it exists in the second area, the corresponding object is not detected by the sensor 110. Accordingly, the processor 130 identifies whether the object is located in the second area at the third viewpoint, based on the location of the object identified at the second viewpoint, and identifies the location of the object in the second area at the third viewpoint. You can. Meanwhile, the first area is an area where objects around the robot 100 can be detected by the sensor 110, based on the current location of the robot 100. Accordingly, the processor 130 may identify the location of the object in the first area through the sensor 110 from the third viewpoint.

For example, referring to FIG. 10, at t+1 second, the coordinate values of the object identified in the second area 22 are (r ₁ '', θ ₁ '') 521, (r ₆ ', θ ₆ ') (524), and the coordinate values of the object identified in the first area 21 are equal to (r ₇ , θ ₇ ) (511) and (r ₈ , θ ₈ ) (512). In this case, the processor 130 integrates these coordinate values, identifies the positions of objects existing in the first and second areas around the robot 100, and controls the robot 100 to run while avoiding the objects. can do.

Meanwhile, if the processor 130 identifies that an object located in the second area at a second time point is not located in the second area at a third time point, the processor 130 may delete the location information of the object stored in the memory 120. The purpose of updating at each time point is only to update the obstacle location information within the second area. Even without separately determining the creation and release of occupancy of a certain area by tracking a specific obstacle, the observation information in the first area utilizes the obstacle location information observed by the sensor at that point in time without modulation, so the past location information of the obstacle is not updated. The problem of afterimages detected by non-existent obstacles can be solved, and obstacle location information in a specific area can be updated with the latest observable information.

As described above, the processor 130 may store the coordinate value of the object identified in the second area at the second time point in the memory 120. Thereafter, the processor 130 may convert the coordinate values stored in the memory 120 based on the movement of the robot at the third viewpoint based on the second viewpoint. Additionally, if the converted coordinate value is not located in the second area 22, the processor 130 may delete the coordinate value stored in the memory 120 from the memory 120. This is because, when the converted coordinate value is located in the first area 21, the corresponding object can be detected through the sensor 110 from a third viewpoint. In this case, the processor 130 can manage the memory 120 by deleting coordinate values from the memory 120.

In the above example, referring to (3) and (4) of FIG. 9, (r ₂ '', θ ₂ '') 522 among the converted coordinate values is the first area 21 of the mask map 20. ) is located in. In this case, the processor 130 may delete (r ₂ ', θ ₂ ') 422 stored in the memory 120.

Meanwhile, if the processor 130 identifies that the object identified at the second time point is not located in the second area 22 at the third time point, the processor 130 sets the location of the object identified in the first area 21 at the third time point. Based on this, the driving of the robot 100 can be controlled.

That is, if the object identified at the second viewpoint is identified as not being located in the second area 22 at the third viewpoint, the object may be viewed as existing only in the first area at the third viewpoint. In this case, the processor 130 may identify the location of the object in the first area 21 through the sensor 110 at the third viewpoint and control the robot 100 to run while avoiding the object.

As such, according to an embodiment of the present disclosure, the robot 100 can identify whether an object exists for each unit cell of the mask map 20 of the sensor 110. At this time, the robot 100 not only uses the sensor 110 at the current viewpoint, but also considers the location of the object detected at the previous viewpoint to identify whether an object exists in an area that is not detected by the sensor 110 at the current viewpoint. can do. Additionally, when an object that was located in an invisible area becomes located in a visible area, the robot 100 may delete the location information of the object stored in the memory 120. That is, the robot 100 updates information about objects existing in the invisible area around the robot 100 based on the current time point. Accordingly, the location of the object detected according to the present disclosure can have high reliability. That is, when estimating the position of an object in an area not detected by the sensor 110 by considering the dynamic characteristics of the object (e.g., the object's movement speed, direction of movement, etc.), when unexpected movement of the object occurs , the estimated location becomes inaccurate. However, according to the present disclosure, based on the results already detected by the robot 100, it is possible to identify the object more accurately in that it identifies whether the object exists in an area that is not detected by the sensor 110, and thus Accordingly, it is possible to control the running of the robot 100 with high reliability.

Meanwhile, the mask map 20 may be created before the robot 100 actually drives and stored in the memory 120. In addition, according to an embodiment of the present disclosure, the mask map 20 may be updated while the robot 100 is traveling. That is, if a problem occurs in the identification range of the sensor 110 due to an external collision, contaminants, etc. while driving, or if a problem in the identification range of the sensor 110 is resolved, the processor 130 generates the mask map 20. The first area 21 and the second area 22 can be updated and stored in the memory 120.

Meanwhile, the processor 130 may update the mask map 20 by identifying that a change has occurred in an area that can be identified by the sensor 110.

In this case, the processor 130 may identify whether the identification range of the sensor 110 has changed based on whether the previously identified object corresponds to the currently identified object. Specifically, the processor 130 converts the position (e.g., coordinate value) of an object identified before the current point of view into a position at the current point of view based on the movement of the robot 100, and converts the coordinate values of the converted object into The mask map 20 may be updated by comparing the coordinate values of the object identified in the first or second area at the current time.

At this time, the processor 130 coordinates the coordinate value of the transformed object (for example, the coordinate value of a static object such as a wall on a map used as positioning reference information) and If the coordinate values of the currently identified object in the first area do not correspond, the area that can be identified by the sensor 110 may be identified as being reduced. Accordingly, the processor 130 may identify the cells of the first area 21 corresponding to the coordinate values of the coordinate-transformed object as being invisible and identify the corresponding area as the second area 22.

On the other hand, the processor 130 may identify that the area that can be identified by the sensor 110 has been expanded if the coordinate value of the converted object corresponds to the coordinate value of the object currently identified in the second area. Accordingly, the processor 130 may identify the cells of the second area 22 corresponding to the coordinate value of the coordinate-transformed object as being in a visible state and identify the corresponding area as the first area 22.

FIG. 11 is a diagram illustrating a method of updating a cell in a first area to a second area according to an embodiment of the present disclosure.

Referring to (1) of FIG. 11, it is a diagram showing an object identified at a previous viewpoint by the sensor 110. The processor 130 may identify

objects

1110, 1120, 1130, and 1140 in the first area 21 of the mask map 20 through the sensor 110.

Referring to (2) of FIG. 11, according to the movement of the robot 100, the relative positions of the

objects

1110, 1120, 1130, and 1140 change with respect to the robot 100, so that the objects 1110, Some (1110, 1120) of 1120, 1130, and 1140 may be located in the second area 22, and the remainder (1130, 1140) may be located in the first area 21.

At this time, it is assumed that no object is detected by the sensor 110 at the current time.

Referring to (3) of FIG. 11, the processor 130 converts the coordinate values of the

objects

1110, 1120, 1130, and 1140 identified at a previous time based on the movement of the robot 100, and converts the converted coordinate values You can obtain (1111, 1121, 1131, 1141).

And, the processor 130 determines that among the converted coordinate

values

1111, 1121, 1131, and 1141, the coordinate

values

1131 and 1141 of the object (e.g., static object) located in the first area 21 are at the current time. It can be identified whether it corresponds to the identified coordinate value.

Here, whether the coordinate value corresponds may be determined based on whether an object with a coordinate value that is the same as the converted coordinate value or approximates within a preset threshold range exists in the first area 21 at the current time.

At this time, if the processor 130 identifies that the object located at the coordinate value does not exist at the current time based on the converted coordinate

values

1131 and 1141 located in the first area 21, the converted coordinate value ( The cells of the mask map 20 where 1131 and 1141) are located can be identified as being in an invisible state. And, as shown in (4) of FIG. 11, the processor 130 updates the state of the cell identified as invisible to the invisible state, that is, the second area 22, and stores the updated mask map 20 in the memory. It can be saved at (120).

In this way, if a problem occurs in the identification range of the sensor 110 due to external collisions, contaminants, etc. while driving, the robot 100 changes the first area 21 of the mask map 20 to the second area 22 accordingly. ) can be updated. The method of updating the first area 21 of the mask map 20 to the second area 22 is not limited to the above example.

FIG. 12 is a diagram illustrating a method of updating a cell in a second area to a first area according to an embodiment of the present disclosure.

As an example, referring to (1) of FIG. 12, it is a diagram showing an object identified by the sensor 110 at a previous viewpoint. The processor 130 may identify the

objects

1210, 1220, 1230, and 1240 in the first area 21 of the mask map 20 through the sensor 110.

Referring to (2) of FIG. 12, according to the movement of the robot 100, the relative positions of the

objects

1210, 1220, 1230, and 1240 change with respect to the robot 100, so that the objects 1210, Some (1210, 1220) of 1220, 1230, and 1240 may be located in the second area 22, and the remainder (1230, 1240) may be located in the first area 21.

At this time, it is assumed that the

objects

1230 and 1240 are detected in the first area 21 by the sensor 110 and the

objects

1210 and 1220 are detected in the second area 22 at the current time.

As shown in (4) of FIG. 12, the processor 130 identifies cells corresponding to the

objects

1210 and 1220 in the second area 22 as visible, and then changes the state of the cells identified as visible to the visible state. That is, the first area 21 can be updated, and the updated mask map 20 can be stored in the memory 120 .

As another example, referring to (1) of FIG. 12, it is a diagram showing an object identified by the sensor 110 at a previous viewpoint. The processor 130 may identify

objects

At this time, it is assumed that the

objects

1230 and 1240 are detected in the first area 21 by the sensor 110 and the

objects

1210 and 1220 are detected in the second area 22 at the current time.

Referring to (3) of FIG. 12, the processor 130 converts the coordinate values of the

objects

1210, 1220, 1230, and 1240 identified at a previous time based on the movement of the robot 100, and converts the coordinate values to You can obtain (1211, 1221, 1231, 1241).

And, the processor 130 determines whether the coordinate values 1211 and 1221 of the object located in the second area 22 among the converted coordinate

values

1211, 1221, 1231, and 1241 correspond to the coordinate values identified at the current time. can be identified.

Here, whether the coordinate value corresponds may be determined based on whether an object with a coordinate value that is the same as the converted coordinate value or approximates within a preset threshold range exists in the second area 22 at the current time.

At this time, if the processor 130 identifies that an object located at the corresponding coordinate value is detected at the current viewpoint based on the converted coordinate values 1211 and 1221 located in the second area 22, the converted coordinate value 1211 The cell of the mask map 20 where , 1221) is located can be identified as being in a visible state. And, as shown in (4) of FIG. 12, the processor 130 updates the state of the cell identified as visible to the visible state, that is, the first area 21, and stores the updated mask map 20 in the memory 120. ) can be saved in .

In this way, when the problem that occurred in the identification range of the sensor 110 is resolved due to contaminants being removed during driving, the robot 100 changes the second area 22 of the mask map 20 to the first area ( 21) can be updated. The method of updating the second area 22 of the mask map 20 to the first area 21 is not limited to the above example.

Figure 13 is a block diagram for explaining the detailed configuration of a robot according to an embodiment of the present disclosure.

Referring to FIG. 13, the robot 100 includes a sensor 110, a memory 120, a processor 130, a driver 140, an input interface 150, a communication interface 160, an output interface 170, and a battery. It may include (180). However, this configuration is an example, and of course, in carrying out the present disclosure, new configurations may be added or some configurations may be omitted in addition to these configurations. Meanwhile, when describing FIG. 13, descriptions overlapping with FIGS. 1 to 12 will be omitted.

The sensor 110 may include a lidar sensor 111, a camera 112, a gyro sensor 113, and an encoder 114. However, this is only an example, and the sensor 110 may include only some of these, or may further include other types of sensors in addition to these sensors.

The driving unit 140 is configured to move the robot 100. For example, the driving unit 140 may include wheels installed on the left and right sides of the main body of the robot 100, respectively, and a motor for driving the wheels. Accordingly, the driving unit 140 can perform various driving operations of the robot 100, such as moving, stopping, controlling speed, changing direction, and changing angular speed. The processor 130 may drive the driving unit 140 to move the robot 100. Accordingly, the robot 100 can move, stop, and rotate. For example, the processor 130 determines the movement direction and movement speed so that the robot 100 moves without colliding with the object based on the position of the object, and the robot 100 moves according to the determined movement direction and speed. The driving unit 140 can be controlled to move. However, this is only an example, and the driving unit 140 may be implemented in various ways depending on the driving type of the robot 100.

The input interface 150 includes a circuit and can receive user commands for setting or selecting various functions supported by the robot 100. To this end, the input interface 150 may include a plurality of buttons and may be implemented as a touch screen that can simultaneously perform the display function.

In this case, the processor 130 may control the operation of the robot 100 based on a user command input through the input interface 150. For example, the processor 143 controls the robot 100 based on an on/off command for the robot 100 input through the input interface 150, an on/off command for the function of the robot 100, etc. You can.

The communication interface 160 includes a circuit and can perform communication with an external device. The processor 130 may receive various data or information from an external device connected through the communication interface 160, and may also transmit various data or information to the external device.

The output interface 170 may include a display 171 and a speaker 172.

The display 171 can display various information. To this end, the display 171 may be implemented as a liquid crystal display (LCD), etc., and may also be implemented as a touch screen that can simultaneously perform the function of the input interface 151. Specifically, the processor 130 may display various information related to the operation of the robot 100 on the display 171.

Speaker 172 can output audio. Specifically, the processor 130 may output various notification sounds or voice guidance messages related to the operation of the robot 100 through the speaker 172.

Battery 180 may supply power to at least one component of robot 100. In this case, the battery 180 may include a secondary battery.

A robot according to an embodiment of the present disclosure may include a sensor and a memory storing a mask map in which an area around the robot is divided into a first area that can be detected by the sensor and a second area that is not detected by the sensor.

First, an object is identified in the first area through a sensor at a first viewpoint (S1410).

Afterwards, an object is identified in the first area through a sensor at a second viewpoint (S1420).

And, based on the position of the object identified at the first viewpoint and the movement of the robot at the second viewpoint based on the first viewpoint, identify whether the object identified at the first viewpoint is located in the second area at the second viewpoint. Do it (S1430).

And, if the object identified at the first time point is identified as being located in the second area at the second time point, the location information of the object identified in the second area is stored in the memory, and the first and second areas at the second time point are stored in the memory. The driving of the robot is controlled based on the location of the object identified in (S1440). The above-described operations may be performed repeatedly as the robot moves and its position changes.

Here, the area around the robot is divided into a plurality of cells based on a polar coordinate system with the center of the robot as the origin. The first area includes at least one cell among a plurality of cells in which an object located in the cell is detected by a sensor. The second area includes at least one cell among the plurality of cells in which an object located in the cell is not detected by the sensor.

Additionally, the movement of the robot may include at least one of the distance the robot moves relative to the first viewpoint, the direction in which the robot moves relative to the first viewpoint, and the direction in which the robot rotates relative to the first viewpoint.

Meanwhile, step S1430 identifies the coordinate value of an object located in the first area at the first viewpoint, converts the identified coordinate value based on the movement of the robot to correspond to the second viewpoint, and converts the converted coordinate value to the second viewpoint. When located in an area, the object identified at the first viewpoint may be identified as being located in the second area at the second viewpoint.

Additionally, if the object identified at the first time point is identified as not being located in the second area at the second time point, the movement of the robot may be controlled based on the location of the object identified in the first area at the second time point.

*Also, an object can be identified in the first area through a sensor at a third viewpoint. And, based on the position of the object identified in the second area at the second time point and the movement of the robot at the third view point based on the second time point, the object identified in the second area at the second time point is moved to the third view point. It is possible to identify whether it is located in the second area at the viewpoint. And, if the object located in the second area at the second viewpoint is identified as being located in the second area at the third viewpoint, the location information of the object identified in the second area is stored in the memory, and the object located in the second area at the third viewpoint is stored in the memory. And the driving of the robot can be controlled based on the object identified in the second area.

Additionally, if the object located in the second area at the second time point is identified as not being located in the second area at the third time point, the location information of the object stored in the memory is deleted, and the object identified in the first area at the third time point is deleted. The robot's movement can be controlled based on the object.

Meanwhile, in step S1440, the robot can be controlled to run while avoiding objects located in the first and second areas based on the stored location information.

Meanwhile, a specific method for identifying an object located in the second area has been described above.

According to one embodiment, methods according to various embodiments disclosed in this document may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. 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 through an application store (e.g. Play StoreTM) or on two user devices (e.g. It can be distributed (e.g. downloaded or uploaded) directly between smartphones) or online. In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) is stored on a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server. It can be temporarily stored or created temporarily.

Each component (e.g., module or program) according to various embodiments of the present disclosure as described above may be composed of a single or multiple entities, and some of the sub-components described above may be omitted. Alternatively, other sub-components may be further included in various embodiments. Alternatively or additionally, some components (e.g., modules or programs) may be integrated into a single entity and perform the same or similar functions performed by each corresponding component prior to integration.

According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added. You can.

Meanwhile, the term "unit" or "module" used in the present disclosure includes a unit comprised of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. You can. A “part” or “module” may be an integrated part, a minimum unit that performs one or more functions, or a part thereof. For example, a module may be comprised of an application-specific integrated circuit (ASIC).

Meanwhile, a non-transitory computer readable medium storing a program that sequentially performs the control method according to the present disclosure may be provided. A non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as registers, caches, and memories. Specifically, the various applications or programs described above may be stored and provided on non-transitory readable media such as CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, etc.

Additionally, embodiments of the present disclosure may be implemented as software including instructions stored in a machine-readable storage media (e.g., a computer). The device is a device capable of calling instructions stored in a storage medium and operating according to the called instructions, and may include an electronic device (eg, robot 100) according to the disclosed embodiments.

When the instruction is executed by a processor, the processor may perform the function corresponding to the instruction directly or using other components under the control of the processor. Instructions may contain code generated or executed by a compiler or interpreter.

In the above, preferred embodiments of the present disclosure have been shown and described, but the present disclosure is not limited to the specific embodiments described above, and may be used in the technical field to which the disclosure pertains without departing from the gist of the disclosure as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical ideas or perspectives of the present disclosure.

Claims

In robots,

sensor;

a memory storing a mask map in which an area around the robot is divided into a first area detectable by the sensor and a second area not detected by the sensor; and

Identifying an object in the first area through the sensor at a first time point,

Identifying an object in the first area through the sensor at a second time point,

Based on the location of the object identified at the first time point and the movement of the robot at the second time point with respect to the first time point, the object identified at the first time point is moved to the second time point at the second time point. Identify whether it is located in an area,

If the object identified at the first time point is identified as being located in the second area at the second time point, the location information of the object identified in the second area is stored in the memory, and the first time point is stored at the second time point. A robot comprising a processor that controls the movement of the robot based on the positions of objects identified in the first and second areas.
According to paragraph 1,

The area around the robot is divided into a plurality of cells based on either a rectangular coordinate system or a polar coordinate system with the center of the robot as the origin,

The first area includes at least one cell in which an object located in a cell among the plurality of cells is detected by the sensor,

The second area includes at least one cell in which an object located in a cell among the plurality of cells is not detected by the sensor.
According to paragraph 1,

The movement of the robot is,

A robot including at least one of the distance the robot moved relative to the first viewpoint, the direction in which the robot moved relative to the first viewpoint, and the direction in which the robot rotated relative to the first viewpoint.
According to paragraph 1,

The processor,

Identify the coordinate value of the object located in the first area at the first viewpoint, convert the identified coordinate value to correspond to the second viewpoint based on the movement of the robot, and the converted coordinate value A robot that, when located in the second area, identifies an object identified at the first viewpoint as being located in the second area at the second viewpoint.
According to paragraph 1,

The processor,

If the object identified at the first time point is identified as not being located in the second area at the second time point, control the running of the robot based on the location of the object identified in the first area at the second time point. A robot that does.
According to paragraph 1,

The processor,

Identifying an object in the first area through the sensor at a third viewpoint,

Based on the location of the object identified in the second area at the second viewpoint and the movement of the robot at the third viewpoint with respect to the second viewpoint, the object identified in the second area at the second viewpoint Identify whether is located in the second area at the third time point,

If an object located in the second area at the second time point is identified as being located in the second area at the third time point, location information of the object identified in the second area is stored in the memory, and the first A robot that controls the movement of the robot based on objects identified in the first and second areas at three viewpoints.
According to clause 6,

The processor,

If the object located in the second area at the second time point is identified as not being located in the second area at the third time point, the location information of the object stored in the memory is deleted, and the object is located at the third time point. A robot that controls its movement based on objects identified in area 1.
According to paragraph 1,

The processor,

Based on the location of the object identified at the first viewpoint and the movement of the robot at the second viewpoint relative to the first viewpoint, the object identified at the first viewpoint is moved to the first viewpoint at the second viewpoint. Identify whether it is located in an area,

If the object identified at the first time point is identified as being located in the first area at the second time point, the location of the object identified in the first area and the location of the object identified at the second time point correspond to Identify whether or not

If it is identified that the location of the object identified in the first area and the location of the object identified at the second viewpoint do not correspond, the first area corresponding to the location of the object in the mask map is selected as the second area. A robot that changes into.
According to paragraph 1,

The processor,

Based on the location of the object identified at the first time point and the movement of the robot at the second time point with respect to the first time point, the object identified at the first time point is moved to the second time point at the second time point. Identify whether it is located in an area,

When the object identified at the first viewpoint is identified as being located in the second area at the second viewpoint, the robot changes the second area corresponding to the location of the object in the mask map to the first area.
According to paragraph 1,

The processor,

A robot that controls the robot to run while avoiding objects located in the first and second areas based on the stored location information.
A method of driving a robot comprising a sensor and a memory storing a mask map in which the area around the robot is divided into a first area that can be detected by the sensor and a second area that is not detected by the sensor,

Identifying an object in the first area through the sensor at a first viewpoint;

identifying an object in the first area through the sensor at a second viewpoint;

Based on the location of the object identified at the first time point and the movement of the robot at the second time point with respect to the first time point, the object identified at the first time point is moved to the second time point at the second time point. identifying whether it is located in an area; and

If the object identified at the first time point is identified as being located in the second area at the second time point, the location information of the object identified in the second area is stored in the memory, and the first time point is stored at the second time point. A driving method comprising: controlling the driving of the robot based on the positions of objects identified in the first and second areas.
According to clause 11,

The area around the robot is divided into a plurality of cells based on a polar coordinate system with the center of the robot as the origin,

The first area includes at least one cell in which an object located in a cell among the plurality of cells is detected by the sensor,

The second area includes at least one cell in which an object located in a cell among the plurality of cells is not detected by the sensor.
According to clause 11,

The movement of the robot is,

A driving method including at least one of the distance the robot moved relative to the first viewpoint, the direction in which the robot moved relative to the first viewpoint, and the direction in which the robot rotated relative to the first viewpoint.
According to clause 11,

The step of identifying whether it is located in the second area is,

Identify the coordinate value of the object located in the first area at the first viewpoint, convert the identified coordinate value to correspond to the second viewpoint based on the movement of the robot, and the converted coordinate value A driving method in which, when located in the second area, an object identified at the first viewpoint is identified as being located in the second area at the second viewpoint.
According to clause 11,

If the object identified at the first time point is identified as not being located in the second area at the second time point, control the running of the robot based on the location of the object identified in the first area at the second time point. A driving method further comprising: