WO2022154153A1

WO2022154153A1 - Robot and control method therefor

Info

Publication number: WO2022154153A1
Application number: PCT/KR2021/001045
Authority: WO
Inventors: 임지웅; 장경훈; 고종명; 김동우; 문경진; 박경세
Original assignee: 삼성전자주식회사
Priority date: 2021-01-13
Filing date: 2021-01-27
Publication date: 2022-07-21
Also published as: KR20220102343A

Abstract

A robot control method is disclosed. The control method may include the steps of: traveling to a first target position if information about the first target position, included in first map data corresponding to a first space included in a robot traveling space, is received from a server; transmitting, to the server, information indicating arrival at the first target position, if the arrival of the robot within a critical distance from the first target position is identified; and traveling to a second target position if second map data, which corresponds to a second space including the first target position, and information about the second target position, which is included in the second map data, are received from the server.

Description

Robot and its control method

The present invention relates to a robot that runs based on map data and a control method therefor.

Recently, technology development for robots that provide services to users, such as guide bots or retail bots, has been active. A robot equipped with a driving unit to provide a service may travel in a space based on map data for a predetermined space.

However, when the space in which the robot travels is wide, the size of the map data for the driving space also increases, and in this case, the robot cannot store the entire map data for the driving space. The conventional robot tried to overcome this problem by dividing the entire map data into a plurality of local map data and storing it, but there was an inconvenience of having to recognize the position of the robot whenever new local map data is applied in the driving process. Accordingly, there has been a continuous demand for a driving method that does not require an additional position recognition operation in the driving process of the robot and has a low load on the memory capacity and the amount of computation of the processor.

The present disclosure is in accordance with the above-mentioned necessity, and an object of the present invention is to provide a robot and a control method thereof that sequentially receive map data from a server based on at least one or more target positions identified on the traveling path of the robot and travel. have.

A robot according to an embodiment of the present invention for achieving the above object is a communication interface, a memory in which the first map data corresponding to the first space included in the driving space is stored, the driving unit and the server through the communication interface. When information on the first target position included in the first map data is received, the driving unit is controlled to travel to the first target position, and when it is identified that the robot has reached within a threshold distance from the first target position , transmits information indicating that the first target location has been reached to the server, and the second map data corresponding to the second space including the first target location from the server and the second map data included in the second map data When information on the second target location is received, the processor may include a processor controlling the driving unit to drive to the second target location.

Here, the second space overlaps the first space and a partial space, and the second map data includes map information on a partial space of the first space including the first target location, and the Map information for some of the first spaces that do not include the first target location may not be included.

Meanwhile, the processor may delete the first map data stored in the memory in at least one of a case in which the second map data is received from the server or a case in which the robot arrives at the second target location. .

In addition, further comprising a camera, wherein the processor, when it is identified that the robot has reached within a threshold distance from the first target position, acquires environmental information of the first target position based on the information obtained through the camera and, when it is identified that the driving environment is changed based on the obtained environment information, transmits the environment information of the first target location to the server, and an artificial intelligence model corresponding to the environment information of the first target location from the server may receive information about and store it in the memory.

In addition, further comprising a camera, wherein the processor, when it is identified that the robot has reached within a threshold distance from the first target position, acquires environmental information of the first target position based on the information obtained through the camera and control the driving unit to change the driving state of the robot based on the obtained environment information.

Meanwhile, the server according to an embodiment of the present invention includes a communication interface, first map data corresponding to a first space included in a traveling space of the robot, and a second space in which the first space and a partial space overlap. The first map data and information on the first target position on the first map data are transmitted to the robot through a memory in which second map data is stored and the communication interface, and the robot sends the first target position to the robot from the robot. and a processor for transmitting the second map data to the robot through the communication interface when information indicating that the . can

Here, the memory further stores third map data corresponding to a third space in which the first space and a partial space overlap, and the processor includes information indicating that the robot has reached the first target position. When received, the communication interface may be controlled to transmit map data including map information corresponding to a second target location after the first target location among the second map data and the third map data to the robot. .

Also, when the traveling path of the robot is identified, the processor may identify the first target position in a partial space where the first space and the second space overlap based on the traveling path of the robot.

In addition, when the traveling space of the robot includes a plurality of Z-axis spaces, the processor identifies each of the plurality of Z-axis spaces as the first space and the second space, and in the first space A partial space including a structure for moving to the second space may be identified as an overlapping space.

Here, the structure for moving from the first space to the second space may include at least one of an elevator, an escalator, and a staircase.

On the other hand, when the size of the first map data is equal to or greater than a threshold size, the processor is configured to identify the driving path among the first map data based on the driving path between the current position of the robot and the first target position. The communication interface may be controlled to transmit some map data corresponding to a partial space to the robot.

Meanwhile, in the control method according to an embodiment of the present invention, when information on a first target location included in first map data corresponding to a first space included in a traveling space of the robot is received from a server, the first target location is received. traveling to a first target position, if the robot is identified as reaching within a threshold distance from the first target position, transmitting information indicating that the first target position has been reached to the server and from the server to the first The method may include driving to the second target location when second map data corresponding to the second space including the target location and information on the second target location included in the second map data are received.

The method may further include deleting the stored first map data in at least one of a case in which the second map data is received from the server or a case in which the robot arrives at the second target location.

In addition, when it is identified that the robot has reached within a threshold distance from the first target location, obtaining environment information of the first target location based on information obtained through a camera, based on the obtained environment information When it is identified that the driving environment is changed, transmitting the environmental information of the first target location to the server, and receiving and storing information about the artificial intelligence model corresponding to the environmental information of the first target location from the server may further include.

In addition, when it is identified that the robot has reached within a threshold distance from the first target location, obtaining environment information of the first target location based on information obtained through a camera and based on the obtained environment information The method may further include changing the driving state of the robot.

In addition, the server receives information indicating that the robot has reached the first target location, and includes map information on a third target location corresponding to a third space overlapping the first space and a part of the space Map data including map information corresponding to a second target location after the first target location among the third map data and the second map data may be transmitted to the robot.

In addition, the server may identify the traveling path of the robot, and based on the traveling path of the robot, identify the first target position in a partial space where the first space and the second space overlap.

Here, when the traveling space of the robot includes a plurality of Z-axis spaces, the server identifies each of the plurality of Z-axis spaces as the first space and the second space, and in the first space A partial region including a structure for moving to the second space may be identified as an overlapping region.

On the other hand, when the size of the first map data is equal to or greater than a threshold size, the server identifies the driving path among the first map data based on the driving path between the current position of the robot and the first target position. Some map data corresponding to some space may be transmitted to the robot.

According to various embodiments of the present disclosure, since the robot stores only local map data obtained by dividing the entire map data, efficient driving is possible even with a small memory capacity. In addition, since the robot does not need to perform a location recognition operation whenever new local map data is applied, it is possible to provide a faster service without burdening the processor.

1 is a view for explaining an operation in which a robot traveling in a predetermined space travels based on a plurality of local map data.

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

3 is a diagram for explaining the configuration of a server according to an embodiment of the present disclosure.

4A and 4B are diagrams for explaining an operation in which a robot travels based on a target position according to an embodiment of the present disclosure.

5 is a diagram for explaining an operation of downloading map data required for driving when the robot reaches a target position according to an embodiment of the present disclosure.

FIG. 6 is a diagram for explaining an operation in which a robot downloads an artificial intelligence model based on environmental information of a space according to an embodiment of the present disclosure.

7 is a view for explaining an operation of a robot changing a driving state based on environmental information of a space according to an embodiment of the present disclosure.

8 is a view for explaining an operation of providing a service while moving a robot according to an embodiment of the present disclosure while moving on several floors of a building.

9 is a diagram for explaining an operation in which a robot downloads some map data among local map data according to an embodiment of the present disclosure.

10 is a block diagram for specifically explaining a functional configuration of a robot according to an embodiment of the present disclosure.

11 is a flowchart illustrating a control method according to an embodiment of the present disclosure.

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

-

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

The terms used in the embodiments of the present disclosure are selected as currently widely used general terms as possible while considering the functions in the present disclosure, which may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, etc. . In addition, in specific cases, there are also terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding disclosure. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, rather than the simple name of the term.

In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of a corresponding characteristic (eg, a numerical value, function, operation, or component such as a part). and does not exclude the presence of additional features.

The expression “at least one of A and/or B” is to be understood as indicating either “A” or “B” or “A and B”.

As used in the present disclosure, expressions such as “first,” “second,” “first,” or “second,” may modify various elements, regardless of order and/or importance, and refer to one element. It is used only to distinguish it from other components, and does not limit the components.

A component (eg, a first component) is "coupled with/to (operatively or communicatively)" to another component (eg, a second component) When referring to "connected to", it should be understood that a component may be directly connected to another component or may be connected through another component (eg, a third component).

The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as "comprises" or "consisting of" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and are intended to indicate that one or more other It is to be understood that this does not preclude the possibility of addition or presence of features or numbers, steps, operations, components, parts, or combinations thereof.

In the present disclosure, a "module" or "unit" performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware and software. In addition, a plurality of “modules” or a plurality of “units” are integrated into at least one module and implemented with at least one processor (not shown) except for “modules” or “units” that need to be implemented with specific hardware. can be

In the present disclosure, the term user may refer to a person who uses the robot. Hereinafter, an embodiment of the present disclosure will be described in more detail with reference to the accompanying drawings.

Referring to FIG. 1 , the robot 100 may provide a service to a user while traveling in a predetermined space. The robot 100 may pre-store map data corresponding to a space for driving, but may also download map data from the server 200 if necessary.

Specifically, the robot 100 may electrically communicate with the server 200 , and the robot 100 may receive map data stored in the server 200 . In this specification, an operation in which the robot 100 receives specific data from the server 200 will be described using the term 'download'.

The entire map data corresponding to the space may be composed of a plurality of local map data obtained by dividing the entire map data. In this case, the robot 100 may download individual local map data from the server 200 and drive based on the downloaded local map data.

Specifically, the robot 100 includes local map data 310 including information on the current position of the robot 100 from the server 200 and another local map included in the travel path 300 of the robot 100 . The data 320 may be downloaded to drive through the space.

The map data, which is the basis for the driving of the robot 100 in the driving process, is from the local map data 310 including information on the initial position of the robot 100 to the local map data 320 including the driving path thereafter. When switched, the robot 100 needs to identify the position of the robot 100 in order to travel based on the new local map data 320 .

In this case, when the robot 100 performs a position recognition operation using a distance sensor such as a lidar to identify a position, there may be a problem in that continuous driving becomes difficult.

Accordingly, various embodiments in which the robot can identify the position of the robot without performing an additional position recognition operation during the driving process will be described in more detail below.

Referring to FIG. 2 , the robot 100 according to an embodiment of the present disclosure may include a communication interface 110 , a memory 120 , a driving unit 130 , and a processor 140 .

The communication interface 110 may input and output various types of data. For example, the communication interface 110 is AP-based Wi-Fi (Wi-Fi, Wireless LAN network), Bluetooth (Bluetooth), Zigbee (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., through communication methods such as external devices (eg, source devices), external storage media (eg, USB memory), external servers (eg, web hard drives) and various types of data can send and receive.

According to an example, the robot 100 may download map data stored in the server 200 through the communication interface 110 .

The memory 120 may store data necessary for various embodiments of the present disclosure. The memory 120 may be implemented in the form of a memory embedded in the robot 100 or may be implemented in the form of a memory detachable to the robot 100 depending on the purpose of data storage. For example, data for driving the robot 100 is stored in a memory embedded in the robot 100 , and data for an extended function of the robot 100 is stored in a memory detachable from the robot 100 . can be On the other hand, in the case of the memory embedded in the robot 100, volatile memory (eg, dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM), etc.), non-volatile memory (eg, : OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory (such as NAND flash or NOR flash, etc.) , a hard drive, or a solid state drive (SSD) may be implemented as at least one of. In addition, in the case of a memory detachable to the robot 100, a memory card (eg, compact flash (CF); SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.), external memory that can be connected to the USB port (e.g. For example, it may be implemented in a form such as a USB memory).

According to an example, the memory 120 may store map data corresponding to the driving space of the robot 100 .

The driving unit 130 is a device capable of driving the robot 100 , and according to the control of the processor 140 , the driving unit 130 may adjust the traveling direction and the traveling speed. To this end, the driving unit 130 is a power generating device that generates power for the robot 100 to travel (eg, a gasoline engine, a diesel engine, or liquefied petroleum gas (LPG) depending on the fuel used (or energy source). engines, electric motors, etc.), steering devices to control the direction of travel (e.g., manual steering, hydraulics steering, electronic control power steering (EPS), etc.), robots (e.g., 100) may include a driving device (eg, wheels, propellers, etc.) for driving. Here, the driving unit 130 may be deformed according to a driving type (eg, a wheel type, a walking type, a flying type, etc.) of the robot 100 .

The processor 140 controls the overall operation of the robot 100 . Specifically, the processor 140 may be connected to each component of the robot 100 to control the overall operation of the robot 100 . For example, the processor 140 may be connected to the communication interface 110 , the memory 120 , and the driving unit 130 to control the operation of the robot 100 .

According to an embodiment, the processor 140 includes a digital signal processor (DSP), a microprocessor, a central processing unit (CPU), a micro controller unit (MCU), and a micro processing unit (MPU). unit), a Neural Processing Unit (NPU), a controller, an application processor (application processor (AP)), etc. may be named variously, but in the present specification, it will be referred to as the processor 140 .

The processor 140 may be implemented in a system on chip (SoC), large scale integration (LSI), or a field programmable gate array (FPGA) format. In addition, the processor 140 may include a volatile memory such as SRAM.

The processor 140 according to an embodiment of the present disclosure may receive information on the first target location included in the first map data from the server 200 through the communication interface 110 . Here, the first map data may be map data including information on an initial position of the robot 100 while driving. Also, the first target location may be a location adjacent to the target point of driving in the first space corresponding to the first map data.

According to an example, the processor 140 may control the driving unit 130 to drive the robot 100 to the first target location after receiving the first map data and information on the first target location.

Meanwhile, when the robot 100 is identified as reaching the threshold distance from the first target location, the processor 140 may transmit information indicating that the robot 100 has reached the first target location to the server 200 .

In addition, the processor 140 according to an example receives second map data corresponding to the second space including the first target location and information on the second target location included in the second map data from the server 200 . can do.

Here, the second space is a space that overlaps the first space and a part of the space and includes the first target location, and may be a space that includes a traveling path through which the robot 100 will travel in the future. Also, the second map data corresponding to the second space may include information on the second target location. Here, the second target location may be a location of a target point of driving in the second space.

Here, the processor 140 informs the server 200 that the robot 100 is close to the first target position in consideration of the speed of downloading data from the server through the communication interface 110, and sends map data to the server. You can request data transfer. For example, when the size of the second map data and the information on the second target location included in the second map data is 5 mb (mega byte) and the download speed is 1 mb/s, the processor 140 controls the first target location It is possible to request data transmission to the server 200 5 seconds before the scheduled arrival time.

The processor 140 according to an example may control the driving unit 130 to drive the robot 100 to the second target position when the second map data and information on the second target position included in the second map data are received. can

On the other hand, the second map data may include map information for some spaces in the first space including the first target location, and may not include map information for some spaces in the first space that do not include the first target location. can

Specifically, the second map data may include only map information included in the space overlapping the second space in the first space and at the same time including the first target location. Accordingly, since the processor 140 may download map data including only map information necessary for driving in the second space, an increase in traffic occurring in communication with the server 200 may be prevented.

Here, the processor 140 receives the first map data stored in the memory 120 in at least one of a case in which the second map data is received from the server 200 or a case in which the robot 100 arrives at the second target position. can be deleted.

Specifically, since the robot 100 traveling in the second space is driven based on the second map data corresponding to the second space, the capacity of the memory 120 is increased by deleting the first map data that is no longer necessary for driving. can be obtained

Meanwhile, the robot 100 may further include a camera. Here, when the robot 100 is identified as reaching within a threshold distance from the first target position, the processor 140 may acquire environmental information of the first target position based on information obtained through the camera. Here, the information obtained through the camera may include an image of a space adjacent to the first target location.

Specifically, the environment information may include information about obstacles located in the space, illuminance information of the space, or information about the floating population distributed in the space. When it is identified that the driving environment is changed based on the obtained environment information, the processor 140 may transmit the environment information of the first target location to the server 200 .

Subsequently, when an artificial intelligence model most suitable to be utilized when driving in a corresponding space is received from the server 200 based on the environment information of the first target location, the processor 140 stores the received artificial intelligence model in the memory 120 . can

Meanwhile, the processor 140 may control the driving unit 130 to change the driving state of the robot 100 based on the obtained environment information.

Referring to FIG. 3 , the server 200 according to an embodiment of the present disclosure may include a communication interface 210 , a memory 220 , and a processor 230 .

The communication interface 210 may input and output various types of data. For example, the communication interface 210 is AP-based Wi-Fi (Wi-Fi, Wireless LAN network), Bluetooth (Bluetooth), Zigbee (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., through communication methods such as external devices (eg, source devices), external storage media (eg, USB memory), external servers (eg, web hard drives) and various types of data can send and receive.

According to an example, the server 200 may transmit map data to the robot 100 through the communication interface 210 .

The memory 220 may store data necessary for various embodiments of the present disclosure. The memory 220 may be implemented in the form of a memory embedded in the server 200 or may be implemented in the form of a memory that is detachable from the server 200 according to the purpose of data storage. For example, data for driving the server 200 is stored in a memory embedded in the server 200 , and data for an extension function of the server 200 is stored in a memory detachable from the server 200 . can be On the other hand, in the case of the memory embedded in the server 200 , a volatile memory (eg, dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM), etc.), non-volatile memory (eg, : OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory (such as NAND flash or NOR flash, etc.) , a hard drive, or a solid state drive (SSD) may be implemented as at least one of. In addition, in the case of a memory detachable to the server 200, a memory card (eg, a compact flash (CF); SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.), external memory that can be connected to the USB port (e.g. For example, it may be implemented in a form such as a USB memory).

According to an example, the memory 220 stores first map data corresponding to a first space included in the driving space of the robot 100 and map data corresponding to a second space in which the first space and a partial space overlap. can

The processor 230 controls the overall operation of the server 200 . Specifically, the processor 230 may be connected to each component of the server 200 to control the overall operation of the server 200 . For example, the processor 230 may be connected to the communication interface 210 and the memory 220 to control the operation of the server 200 .

According to an embodiment, the processor 230 includes a digital signal processor (DSP), a microprocessor, a central processing unit (CPU), a micro controller unit (MCU), and a micro processing unit (MPU). unit), a Neural Processing Unit (NPU), a controller, an application processor (application processor (AP)), etc. may be named variously, but in the present specification, it will be referred to as the processor 230 .

The processor 230 may be implemented as a system on chip (SoC), large scale integration (LSI), or a field programmable gate array (FPGA) type. In addition, the processor 230 may include a volatile memory such as SRAM.

The processor 230 according to an embodiment of the present disclosure may transmit the first map data and information on the first target location on the first map data to the robot 100 through the communication interface 210 .

In addition, when information indicating that the robot 100 has reached the first target position is received from the robot 100 , the processor 230 may transmit the second map data to the robot 100 through the communication interface 210 . . Here, the second map data may include map information on the first target location.

Here, the memory 220 may further store third map data corresponding to the third space in which the first space partially overlaps. According to an example, the third map data may be a space in which the first space and the second space partially overlap with the first space and a partial space overlap.

* When information indicating that the robot 100 has reached the first target position is received, the processor 230 according to an example corresponds to a second target position after the first target position among the second map data and the third map data. The communication interface 210 may be controlled to transmit map data including map information to the robot 100 .

Specifically, the second target position may be a position at which the robot 100 is expected to arrive after the first target position in the driving process, and the processor 230 provides map data corresponding to the space including the second target position. may be transmitted to the robot 100 . For example, when the second target location is included in the second space, the processor 230 transmits second map data corresponding to the second space to the robot 100, and the second target location is located in the third space. If included, the third map data corresponding to the third space may be transmitted to the robot 100 .

In addition, when the travel path of the robot 100 is identified, the processor 230 identifies the first target position in a partial space where the first space and the second space overlap based on the travel path of the robot 100, and the identified The communication interface 100 may be controlled to transmit information on the first target position to the robot 100 .

Specifically, the processor 230 may identify an arbitrary position on the travel path of the robot 100 included in a partial space where the first space and the second space overlap as the first target position. Here, the information on the identified first target location may include coordinates corresponding to the first target location on the second map data.

Also, when the traveling space of the robot 100 includes a plurality of Z-axis spaces, the processor 230 may identify each of the plurality of Z-axis spaces as a first space and a second space. Specifically, the driving space of the robot 100 may be an internal space of a building including a plurality of floors, and the processor 230 uses the floor including the current location of the robot 100 as the first space, and the robot 100 ) can be identified as the second space.

Subsequently, the processor 230 identifies a partial space including a structure for moving from the floor identified as the first space to the floor identified as the second space as the overlapping space, and assigns an arbitrary position of the overlapping space to the first space. It can be identified by the target location.

Here, the structure for moving from the first space to the second space may include at least one of an elevator, an escalator, or a staircase.

On the other hand, when the size of the first map data is equal to or greater than the threshold size, the processor 230 determines a partial space identified based on the driving path among the first map data based on the driving path between the current position of the robot 100 and the first target position. The communication interface 210 may be controlled to transmit some map data corresponding to the robot 100 to the robot 100 .

4A shows that the space 410 in which the robot 100 travels has a rectangular structure, and the map data corresponding to the space 410 has a square structure and eight map data 21-25, etc., corresponding to a space of the same size. ) is a diagram for explaining the running of the robot 100 when configured.

Here, the eight map data (21-25, etc.) are map data corresponding to a space divided so that some spaces overlap each other, and the robot 100 according to an embodiment of the present disclosure corresponds to the initial position (10). The resulting map data 21 may be downloaded from the server 200 and stored in the memory 120 .

The server 200 according to an example identifies the driving path 31 of the robot 100 to the final destination 20 for which the service is requested, and corresponds to the identified path and a plurality of map data 21-25. A plurality of target locations 11 - 14 may be identified based on the space in which the plurality of spaces overlap.

First, the server 200 transmits information about the first map data 21 corresponding to the initial position 10 of the robot 100 and the first target position 11 included in the first map data 21 to the robot. (100) can be transmitted.

The robot 100 according to an example may drive to the first target location 11 when the first map data 21 and information on the first target location 11 included in the first map data 21 are received. can Here, the robot 100 may travel based on the driving path 31 identified by the server 200, but in order to cope with various situations occurring in the driving process, a driving different from the driving path 31 previously identified by itself. It can also drive based on a route.

Then, when the robot 100 is identified as reaching within the threshold distance from the first target position 11, the robot 100 transmits information indicating that it has reached the first target position 11 to the server 200 and At the same time, the second map data 22 corresponding to the second space including the subsequent driving route may be requested.

Accordingly, the server 200 may transmit the second map data 22 and information on the second target location 12 included in the second map data to the robot 100 . In this case, the second map data may not include map information for some spaces that do not include the first target location 11 among the spaces corresponding to the first map data 21 .

The robot 100 according to an example may delete the first map data 21 stored in the memory 120 when the second map data 22 is received from the server 200 . At the same time, the robot 100 may travel to the second target location 12 based on the downloaded second map data 22 . In this case, since the second map data 22 includes coordinates corresponding to the first target position 11 on the second map data 22 , the robot 100 moves the position of the robot 100 without an additional position recognition operation. can be identified.

Specifically, the robot 100 identifies the coordinates corresponding to the initial position 10 and the orientation direction of the robot through position recognition at the initial position 10, and then the first map data 21 and the driving unit 130. The robot 100 can drive to the first target position 11 based on the accumulated data of driving characteristics of It is possible to drive to the second target location 12 based on the information on the target location 12 .

In more detail, the coordinates corresponding to the first target position 11 on the first map data 21 are (70,35) and the coordinates corresponding to the first target position 11 on the second map data 22 are In the case of (10, 35), the robot 100 is identified as being close to the first target position 11 with the coordinates of (70, 35) on the first map data 21 by the robot 100, the server 200 The second map data 21 and information on the second target location 12 included in the second map data are downloaded from the (21) may be deleted, and driving may be performed based on the second map data (22).

In this case, since the position of the robot 100 on the second map data 22 is identified as the first target position 11 having the coordinates of (10, 35), the robot 100 can be quickly performed without additional position recognition operation. be able to drive

Similarly, when the robot 100 is close to the second target position 12, the map data 23 including the subsequent travel path and the information on the next target position 13 included in the map data 23 are sent to the server. 200 , and based on this, it can travel to the next target location 13 . The robot 100 may travel to the final destination 20 via the last target location 14 in the same manner.

4B shows that the space 420 in which the robot 100 travels has a complex polygonal structure, and the map data corresponding to the space 420 has a square structure and eight map data 26-29 corresponding to spaces of different sizes. etc.) is a diagram for explaining the driving of the robot 100 .

The robot 100 according to an embodiment of the present disclosure is the initial position

Here, the eight map data (26-29, etc.) are map data corresponding to a space divided so that some spaces overlap each other, and the robot 100 according to an embodiment of the present disclosure corresponds to the initial position (10). The map data 26 used may be downloaded from the server 200 and stored in the memory 120 .

The server 200 according to an example identifies the driving path 32 of the robot 100 to the final destination 20 for which the service is requested, and corresponds to the identified path and a plurality of map data (26-29, etc.) A plurality of target positions 15 - 17 may be identified based on the space in which the plurality of spaces overlap.

First, the server 200 transmits information about the first map data 26 corresponding to the initial position 10 of the robot 100 and the first target position 15 included in the first map data 26 to the robot. (100) can be transmitted.

The robot 100 according to an example may drive to the first target location 15 when the first map data 26 and information on the first target location 15 included in the first map data 26 are received. can Then, when the robot 100 is identified as reaching within the threshold distance from the first target position 15, the robot 100 transmits information indicating that it has reached the first target position 15 to the server 200 and At the same time, the second map data 27 corresponding to the second space including the subsequent driving route may be requested.

Accordingly, the server 200 may transmit the second map data 27 and information on the second target location 16 included in the second map data to the robot 100 . Meanwhile, the robot 100 may delete the first map data 26 stored in the memory 120 when the second map data 27 is received from the server 200 . Thereafter, the robot 100 may travel to the second target location 16 based on the information on the first target location 15 and the second target location 16 included in the second map data 27 . .

Similarly, when the robot 100 is close to the second target position 16, the map data 28 including the subsequent travel route and the information on the next target position 17 included in the map data 28 are sent to the server. It can download from 200 and drive to the next target location 17 based thereon. In the same manner, the robot 100 may travel to the final destination 20 .

The robot 100 according to an embodiment of the present disclosure travels to the target position 501 included in the map data 510 based on the map data 510 corresponding to the space including the current position of the robot 100 . can do.

Here, among the map data corresponding to the space including the target location 501 , the map data necessary for the future driving of the robot 100 is in the space including the travel route and information on the target location 502 thereafter. It may be the corresponding map data 520 .

Therefore, the robot 100 transmits the map data 520 including information about the target location 502 to the server 200 from among a plurality of

map data

520 and 530 including information on the target location 501 . may be requested, and the server 200 may transmit the map data 520 corresponding to the request of the robot 100 to the robot 100 .

Accordingly, when the robot 100 reaches the target location, only map data necessary for subsequent driving can be downloaded from the server 200 , so that the capacity of the map data stored in the memory 120 can be minimized.

Referring to FIG. 6 , the server 200 may store a plurality of

artificial intelligence models

221 , 222 , etc. in the memory 220 . 6 shows that the two

artificial intelligence models

221 and 222 are stored in the server 200 for convenience, but in addition to the two

models

221 and 222, various artificial intelligence models may be stored in the server 200. have.

The robot 100 according to an example may utilize an artificial intelligence model in a driving process. Specifically, the robot 100 may further include a camera 150 , input an image obtained through the camera 150 into the artificial intelligence model, and may travel based on the output of the artificial intelligence model.

The robot 100 is an artificial intelligence that can provide a more accurate output based on the environmental information of the space in which the robot 100 travels among a plurality of artificial intelligence models (221, 222, etc.) stored in the server 200 for efficient driving. The intelligent model may be downloaded from the server 200 .

Functions related to artificial intelligence according to the present disclosure are operated through the processor 140 and the memory 120 of the robot 100 . The processor 140 may include one or a plurality of processors. In this case, one or more processors 140 may be general-purpose processors such as CPUs, APs, digital signal processors (DSPs), etc., graphics-only processors such as GPUs, VPUs (Vision Processing Units), or artificial intelligence-only processors such as NPUs. . One or a plurality of processors 140 control to process input data according to a predefined operation rule or artificial intelligence model stored in the memory 120 . Alternatively, when one or more processors 140 are AI-only processors, the AI-only processor 140 may be designed with a hardware structure specialized for processing a specific AI model.

The predefined action rule or artificial intelligence model is characterized in that it is created through learning. Here, being made through learning means that a basic artificial intelligence model is learned using a plurality of learning data by a learning algorithm, so that a predefined action rule or artificial intelligence model set to perform a desired characteristic (or purpose) is created means burden. Such learning may be performed in the device itself on which artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and/or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

The artificial intelligence model may be composed of a plurality of artificial intelligence layers. Each of the plurality of artificial intelligence layers has a plurality of weight values, and an artificial intelligence operation is performed through an operation between an operation result of a previous layer and the plurality of weights. The plurality of weights of the plurality of artificial intelligence layers may be optimized by the learning result of the artificial intelligence model. For example, a plurality of weights may be updated so that a loss value or a cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial intelligence may include Deep Neural Network (DNN), for example, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM). ), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), or deep Q-networks, etc., but is not limited to the above-described example.

According to an example, when the robot 100 is identified as reaching within a threshold distance from the target position 601 , the target position 601 and the future robot 100 will travel based on the image acquired through the camera 150 . Environment information of a space 620 including a driving path (hereinafter, a space to be driven in the future) may be acquired. Here, the environment information may include at least one of information about the

obstacles

621 and 622 distributed in the space 620 , information about the floating population 623 in the space 620 , or illuminance information of the space 620 . have.

Subsequently, the robot 100 may transmit the obtained environment information to the server 200 when it is identified that the environment of the space 620 to be driven in the future is different from the environment of the previous space 610 by more than a threshold degree based on the environment information. have.

Specifically, the space 620 to be driven in the future may be a space with lower illumination than the previous space 610 , and includes

many obstacles

621 and 622 and a floating population 623 compared to the previous space 610 . It could be space.

The server 200 may transmit an artificial intelligence model corresponding to the environment information received from the robot 100 to the robot 100 . According to an example, the artificial intelligence model corresponding to the environment information of the space 620 to be driven in the future may be the artificial intelligence model 221 capable of accurately identifying an object even in a low-illumination environment.

The robot 100 according to an example stores the artificial intelligence model 221 received from the server 200 in the memory 120, and runs based on this, so that it can efficiently travel in the space 620 to be driven in the future. do.

In FIG. 6 , an embodiment in which the robot 100 acquires environment information and the server 200 transmits an artificial intelligence model based on the environment information received from the robot 100 has been described, but according to another example, the server ( In addition to the map data of the space 620 in which the 200 is to be driven in the future, an artificial intelligence model corresponding to the environment information of the space 620 may be simultaneously transmitted to the robot 100 approaching the target location 601 .

Specifically, the server 200 according to another embodiment may store a plurality of map data, a plurality of environment information corresponding to each map data, and a plurality of artificial intelligence models corresponding to the environment information, and the robot 100 may When information indicating that the target location has been reached is received, the robot 100 may transmit map data corresponding to a space to be driven in the future and an artificial intelligence model corresponding thereto.

According to an example, when the robot 100 is identified as reaching within a threshold distance from the target position 701, the target position 701 and the space 720 to be driven in the future based on the image acquired through the camera 150 Environmental information can be obtained.

Then, the robot 100 determines that the environment of the space 720 to be driven in the future is different from the environment of the previous space 710 based on the environment information by more than a threshold degree, based on the obtained environment information. You can change driving conditions.

Specifically, the space 720 to be driven in the future may be a space with lower illuminance than the previous space 710 , and includes

many obstacles

721 and 722 and a floating population 723 compared to the previous space 710 . It could be space. The processor 140 of the robot 100 according to an example has the driving unit 130 to reduce the speed of the robot 100 in order to prevent collisions with

obstacles

721 and 722 and people in the space 720 to be driven in the future. ) can be controlled.

In FIG. 7 , only the operation of reducing the moving speed of the robot 100 has been described, but in addition to this, the robot 100 is a sensing period of the distance sensor provided in the robot 100 based on the environmental information of the space 720 to be driven in the future. Alternatively, an operation of shortening the photographing cycle of the camera may be performed.

Referring to FIG. 8 , the robot 100 located on the first floor 810 may travel to the fifth floor 820 of the same building to provide services. The server 200 according to an example identifies the first floor 810 as the first space and the fifth floor 820 as the second space, and an elevator for moving from the first floor 810 to the fifth floor 820 ( 801) and a partial space including the stairs 802 may be identified as a space where the first space and the second space overlap.

Subsequently, the server 200 may transmit the map data corresponding to the first floor 810 and information on the location 811 adjacent to the elevator 801 located on the first floor 810 to the robot 100 . The robot 100 according to an example may travel to a location 811 adjacent to the elevator 801 based on the received map data corresponding to the first floor 810 .

In addition, when the server 200 is identified that the robot 100 has reached the position 811 adjacent to the elevator 801 located on the first floor 810, the robot 100 corresponds to the fifth floor 820 to be driven in the future. It is possible to transmit the map data and information on the location 821 adjacent to the elevator 801 located on the fifth floor 820 to the robot 100 . According to an example, the robot 100 may download map data from the server 200 while the elevator 801 is moving.

Subsequently, the robot 100 arriving at the fifth floor 820 travels to a position 821 adjacent to the elevator 801 based on the map data corresponding to the fifth floor 820 , and the robot 100 moves to the corresponding position 821 . ), the map data corresponding to the first floor 810 may be deleted and the vehicle may drive to the destination.

* According to an example, since the map data may include data related to measurement of a plurality of sensors that may be provided in the robot 100 and data related to environment information of the space 910 , the space in which the robot 100 is located There may be a case in which the data capacity of the map data 910 corresponding to , is larger than that of map data corresponding to other spaces.

In this case, the server 200 transmits some map data corresponding to the partial space of the space 910 to the robot 100 based on the travel path between the current position of the robot 100 and the target position in the space 910 . can Specifically, the server 200 may transmit map data corresponding to the space 911 within a threshold distance from the travel path of the robot 100 to the target location 901 to the robot 100 .

Accordingly, traffic generated due to communication between the robot 100 and the server 200 is minimized, and the problem of insufficient storage capacity of the memory 120 of the robot 100 can be prevented.

According to FIG. 10 , the robot 100 includes a communication interface 110 , a memory 120 , a driving unit 130 , a processor 140 , a camera 150 , a distance sensor 160 , and a service providing unit 170 . do. A detailed description of the configuration shown in FIG. 10 overlapping the configuration shown in FIG. 2 will be omitted.

The camera 150 may acquire an image by capturing an area within a field of view (FoV) of the camera.

The camera 150 may include a lens for focusing the visible light or other optical signal received by being reflected by the object to the image sensor, and an image sensor capable of detecting the visible light and other optical signals. Here, the image sensor may include a 2D pixel array divided into a plurality of pixels.

The distance sensor 160 may obtain distance information. Specifically, the distance sensor 160 may measure a distance between the position of the robot 100 and the position of the object. The distance sensor 160 according to an example may be implemented as a LIDAR (Light Detection And Ranging) or a Time of Flight (TOF) sensor.

The service providing unit 170 is configured to receive a user's command or to output a UI necessary for providing a service corresponding to the user's command. Specifically, the service providing unit 170 may include at least one of a display including a touch screen, a speaker, and a microphone. The robot 100 according to an example may change the UI output through the service providing unit 170 based on the type of service to be provided and the step of providing the service.

* In the control method of the robot according to an embodiment of the present disclosure, when information on the first target position included in the first map data corresponding to the first space included in the driving space of the robot is received from the server, the first target position Step (S1110) of traveling to (S1110), when the robot is identified as reaching within a threshold distance from the first target location, transmitting information indicating that it has reached the first target location to the server (S1120) and the first target location from the server When the second map data corresponding to the included second space and information on the second target location included in the second map data are received, the method may include driving to the second target location ( S1130 ).

Here, the second space partially overlaps the first space, and the second map data includes map information for a partial space including the first target position in the first space, and the first target position in the first space Map information for some spaces that do not include may not be included.

The method may further include deleting the stored first map data in at least one of a case in which the second map data is received from the server or a case in which the robot arrives at the second target position.

In addition, when it is identified that the robot has reached within a threshold distance from the first target position, obtaining environmental information of the first target position based on information obtained through the camera; When identified, the method may further include transmitting the environmental information of the first target location to the server, and receiving and storing information on the artificial intelligence model corresponding to the environmental information of the first target location from the server.

In addition, when it is identified that the robot has reached within a threshold distance from the first target position, obtaining environmental information of the first target position based on information obtained through the camera and determining the driving state of the robot based on the obtained environment information It may further include the step of changing.

On the other hand, the server receives information indicating that the robot has reached the first target position, and third map data including map information for the third target position corresponding to the third space overlapping the first space and a part of the space, and Map data including map information corresponding to the second target location after the first target location among the second map data may be transmitted to the robot.

In addition, the server may identify the traveling path of the robot and identify the first target position in a partial space where the first space and the second space overlap based on the traveling path of the robot.

Here, when the traveling space of the robot includes a plurality of Z-axis spaces, each of the plurality of Z-axis spaces is identified as a first space and a second space, and a structure for moving from the first space to the second space is provided. A partial region including the region may be identified as an overlapping region.

On the other hand, when the size of the first map data is equal to or greater than the threshold size, based on the driving path between the current position of the robot and the first target position, the server provides some map data corresponding to some spaces identified based on the driving path among the first map data. can be transmitted to the robot.

According to the driving method of the robot according to an embodiment of the present disclosure, the robot may start driving based on the current map data after receiving information on the target location from the server (S1210).

Subsequently, when the robot is identified as reaching within the threshold distance from the target location, the next map data may be downloaded from the server (S1220). Here, the next map data may be map data corresponding to a space in which the robot will drive in the future.

Subsequently, when the robot reaches the target position (S1230), the robot may identify whether the reached target position is the final destination (S1240). If the currently reached target position is the final destination (S1240: Y), the robot may end driving and provide a service to the user.

Conversely, if the currently reached target location is not the final destination (S1250: N), the robot may drive to the next target location based on the downloaded next map data (S1250). If the robot has reached within a threshold distance from the next target location, the robot can then download the map data.

Meanwhile, the above-described methods according to various embodiments of the present disclosure may be implemented in the form of an application that can be installed in an existing robot.

In addition, the above-described methods according to various embodiments of the present disclosure may be implemented only by software upgrade or hardware upgrade for an existing robot.

In addition, various embodiments of the present disclosure described above may be performed through an embedded server provided in the robot or at least one external server.

Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof. In some cases, the embodiments described herein may be implemented by the processor 140 itself. According to the software implementation, embodiments such as the procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

In the above, preferred embodiments of the present disclosure have been illustrated and described, but the present disclosure is not limited to the specific embodiments described above, and is commonly used in the technical field pertaining to the present disclosure without departing from the gist of the present disclosure as claimed in the claims. Various modifications may be made by those having the knowledge of

Claims

In the robot,

communication interface;

a memory in which first map data corresponding to a first space included in the driving space is stored;

drive unit; and

When information on the first target location included in the first map data is received from the server through the communication interface, the driving unit is controlled to drive to the first target location,

When it is identified that the robot has reached within a threshold distance from the first target location, information indicating that the first target location has been reached is transmitted to the server,

When second map data corresponding to the second space including the first target location and information on the second target location included in the second map data are received from the server, the vehicle drives to the second target location. A processor that controls the driving unit; including, a robot.
According to claim 1,

The second space, the first space and a partial space overlap,

The second map data is

and map information for a partial space including the first target location among the first space,

The robot, which does not include map information for a part of the first space that does not include the first target location.
According to claim 1,

The processor is

To delete the first map data stored in the memory in at least one of when the second map data is received from the server or when the robot reaches the second target position.
According to claim 1,

It further includes a camera;

The processor is

When it is identified that the robot has reached within a threshold distance from the first target location, obtaining environmental information of the first target location based on the information obtained through the camera,

When it is identified that the driving environment is changed based on the obtained environment information, the environment information of the first target location is transmitted to the server,

Receives information on the artificial intelligence model corresponding to the environment information of the first target location from the server and stores the information in the memory.
According to claim 1,

It further includes a camera;

The processor is

When it is identified that the robot has reached within a threshold distance from the first target location, obtaining environmental information of the first target location based on the information obtained through the camera,

A robot that controls the driving unit to change the driving state of the robot based on the obtained environment information.
in the server,

communication interface;

a memory in which first map data corresponding to a first space included in the traveling space of the robot and second map data corresponding to a second space overlapping the first space and a part of the space are stored; and

Transmitting the first map data and information on the first target location on the first map data to the robot through the communication interface,

a processor for transmitting the second map data to the robot through the communication interface when information indicating that the robot has reached the first target position is received from the robot;

The second map data, the server including map information for the first target location.
7. The method of claim 6,

The memory further stores third map data corresponding to a third space in which the first space and a partial space overlap,

The processor is

When information indicating that the robot has reached the first target location is received, a map including map information corresponding to a second target location after the first target location among the second map data and the third map data A server controlling the communication interface to transmit data to the robot.
7. The method of claim 6,

The processor is

When the traveling path of the robot is identified, the server identifies the first target position in a partial space where the first space and the second space overlap based on the traveling path of the robot.
7. The method of claim 6,

The processor is

When the traveling space of the robot includes a plurality of Z-axis spaces, each of the plurality of Z-axis spaces is identified as the first space and the second space, and moving from the first space to the second space A server that identifies some spaces containing structures for the overlapping spaces.
10. The method of claim 9,

The structure for moving from the first space to the second space is

A server comprising at least one of an elevator, an escalator or a stair.
7. The method of claim 6,

The processor is

When the size of the first map data is equal to or greater than a threshold size, a portion corresponding to a partial space identified based on the driving path among the first map data based on a driving path between the current position of the robot and the first target position A server that controls the communication interface to transmit map data to the robot.
A method for controlling a robot, comprising:

when information on a first target location included in first map data corresponding to a first space included in the traveling space of the robot is received from the server, driving to the first target location;

transmitting information indicating that the robot has reached the first target position to the server when it is identified that the robot has reached the first target position within a threshold distance; and

Driving to the second target location when second map data corresponding to the second space including the first target location and information on the second target location included in the second map data are received from the server Control method including ;.
13. The method of claim 12,

The second space, the first space and a partial space overlap,

The second map data is

and map information for a partial space including the first target location among the first space,

The control method of claim 1 , which does not include map information for some spaces that do not include the first target location among the first spaces.
13. The method of claim 12,

Deleting the stored first map data in at least one of when the second map data is received from the server or when the robot arrives at the second target location.
13. The method of claim 12,

if the robot is identified as reaching within a threshold distance from the first target location, obtaining environmental information of the first target location based on information obtained through a camera;

transmitting the environment information of the first target location to the server when it is identified that the driving environment is changed based on the obtained environment information; and

and receiving and storing information on an artificial intelligence model corresponding to the environment information of the first target location from the server.