WO2023003158A1

WO2023003158A1 - Robot and control method thereof

Info

Publication number: WO2023003158A1
Application number: PCT/KR2022/007503
Authority: WO
Inventors: 권순범; 백아론; 김도훈; 김효묵; 홍현기
Original assignee: 삼성전자주식회사
Priority date: 2021-07-20
Filing date: 2022-05-26
Publication date: 2023-01-26

Abstract

A robot is disclosed. The robot comprises at least one sensor, a drive unit, and a processor, wherein the processor executes at least one instruction to: acquire characteristic information of an object on the basis of sensing data acquired by the at least one sensor during travel of the robot; acquire speed profile information according to distances to the object on the basis of the acquired characteristic information of the object; acquire a speed map including speed information for each area on the basis of the acquired speed profile information; and control the drive unit on the basis of a moving path identified on the basis of the acquired speed map.

Description

Robot and its control method

The present disclosure relates to a robot and a control method thereof, and more particularly to a robot and a control method thereof.

BACKGROUND OF THE INVENTION [0002] Recently, technology development for a robot that is placed in a specific space and provides services to users has been actively developed. In particular, a robot moving in a specific space must travel quickly while avoiding obstacles on a travel path in order to provide a prompt service to a user.

Accordingly, there is a need for a method of planning a path in which the robot can travel as quickly as possible in consideration of obstacles.

SUMMARY OF THE INVENTION The present disclosure is in accordance with the above-described needs, and is to provide a robot and a control method for planning a shortest time path in consideration of various types of obstacles identified while the robot is traveling.

A robot according to an embodiment of the present invention for achieving the above object is at least one sensor, a drive unit, a memory for storing at least one command, and connected to the at least one sensor, the drive unit, and the memory. and a processor controlling the electronic device, wherein the processor obtains characteristic information of an object based on sensing data acquired by the at least one sensor while the robot is driving by executing the at least one command. and obtaining velocity profile information according to a distance to the object based on the acquired object characteristic information, obtaining a velocity map including velocity information for each area based on the obtained velocity profile information, and obtaining the The driving unit may be controlled based on a movement path identified based on the determined speed map.

In addition, the processor obtains the velocity map based on first velocity profile information when the object is a static object, and obtains the velocity map based on second velocity profile information when the object is a dynamic object. The first velocity profile information is information in which the velocity decreases with a first gradient as it approaches the static object within a first threshold distance from the static object, and the second velocity profile information is information related to It may be information in which a speed decreases with a second slope smaller than the first slope as it approaches the dynamic object within a 2-threshold distance.

In addition, the processor obtains the velocity map based on the second velocity profile information when the object is a first-type dynamic object, and obtains a third velocity profile when the object is a second-type dynamic object. The speed map is obtained based on information, and the third speed profile information includes a second gradient smaller than the second gradient as it approaches the second type of dynamic object within a third threshold distance from the second type of dynamic object. 3 It may be information that the speed decreases with a slope.

In addition, when the object is a dynamic object, the processor may obtain the velocity map by obtaining velocity information of the dynamic object and applying different velocity profile information according to the velocity information of the dynamic object.

In addition, the processor obtains fourth velocity profile information corresponding to the predetermined space based on characteristic information of a first object located in the predetermined space, and based on characteristic information of a second object located in the predetermined space, Fifth velocity profile information corresponding to the predetermined space may be obtained, and velocity profile information corresponding to the predetermined space may be obtained based on the fourth velocity profile information and the fifth velocity profile information.

In addition, the processor obtains a first velocity value corresponding to each cell included in the constant space based on the fourth velocity profile information, and obtains a first velocity value corresponding to each cell included in the constant space based on the fifth velocity profile information. A second velocity value corresponding to each of the included cells is obtained, and the velocity corresponding to each cell is based on a smaller value of the first velocity value and the second velocity value corresponding to each cell included in the predetermined space. value, and a speed map corresponding to the predetermined space may be obtained based on the obtained speed value corresponding to each cell.

In addition, the memory further stores a distance map including distance information to an object, and the processor generates the stored distance map based on object information acquired by the at least one sensor while the robot is traveling. and a speed map including speed information for each area may be obtained based on the updated distance map and the obtained profile information.

In addition, the speed map includes speed values corresponding to each of a plurality of cells, and the processor obtains a required time between cells by dividing a distance between cells included in the speed map by a speed value corresponding to a cell, Based on the required time between cells, the shortest time path may be identified as the moving path of the robot.

In addition, the processor obtains distance information corresponding to each cell in a distance map including distance information to an object, and obtains velocity information corresponding to each cell based on the obtained distance information and the velocity profile information. and obtain the speed map including speed information corresponding to each cell.

Meanwhile, a method for controlling a robot according to an embodiment of the present disclosure includes obtaining property information of an object based on sensing data acquired by at least one sensor while the robot is traveling, and the acquired property information of the object. Obtaining speed profile information according to the distance to the object based on, obtaining a speed map including speed information for each area based on the obtained speed profile information, and identifying based on the obtained speed map It may include driving the robot based on the moved path.

The obtaining of the speed map may include obtaining the speed map based on first velocity profile information when the object is a static object and based on second velocity profile information when the object is a dynamic object. and obtaining the speed map, wherein the first speed profile information is information in which a speed decreases with a first gradient as it approaches the static object within a first threshold distance from the static object, and the second The velocity profile information may be information indicating that the velocity decreases with a second slope smaller than the first slope as it approaches the dynamic object within a second threshold distance from the dynamic object.

The obtaining of the velocity map may include obtaining the velocity map based on the second velocity profile information when the object is a first-type dynamic object, and the object is a second-type dynamic object. , obtaining the speed map based on third velocity profile information, wherein the third velocity profile information is within a third threshold distance from the second type of dynamic object. It may be information in which the speed decreases with a third slope smaller than the second slope as it approaches the object.

In the obtaining of the speed map, if the object is a dynamic object, speed information of the dynamic object is obtained, and the speed map is obtained by applying different speed profile information according to the speed information of the dynamic object. can

The obtaining of the velocity profile information may include obtaining fourth velocity profile information corresponding to the specific space based on characteristic information of a first object located in the specific space, and obtaining the second velocity profile information corresponding to the specific space. Obtaining fifth velocity profile information corresponding to the predetermined space based on object characteristic information, and obtaining velocity profile information corresponding to the predetermined space based on the fourth velocity profile information and the fifth velocity profile information. Acquisition steps may be included.

The obtaining of the velocity map may include obtaining a first velocity value corresponding to each cell included in the predetermined space based on the fourth velocity profile information; obtaining a second velocity value corresponding to each cell included in the predetermined space based on a smaller value of the first velocity value and the second velocity value corresponding to each cell included in the predetermined space The method may include obtaining a velocity value corresponding to each cell, and acquiring a velocity map corresponding to the predetermined space based on the obtained velocity value corresponding to each cell.

In addition, the acquiring of the speed map may include updating a distance map including distance information to an object based on object information acquired by the at least one sensor while the robot is traveling, and updating the updated distance map. and acquiring a speed map including speed information for each region based on the distance map and the obtained profile information.

In addition, the speed map includes speed values corresponding to each of a plurality of cells, and the step of driving the robot comprises dividing the distance between cells included in the speed map by the speed value corresponding to the cell, and the required time between cells. and identifying a shortest time path as a moving path of the robot based on the required time between cells.

In addition, the obtaining of the speed map may include obtaining distance information corresponding to each cell from a distance map including distance information to an object, and determining each cell based on the obtained distance information and the velocity profile information. The method may include acquiring corresponding speed information and acquiring the speed map including speed information corresponding to each cell.

According to various embodiments described above, the shortest time path can be planned in consideration of various types of obstacles identified while the robot is driving.

1 is a diagram for explaining a path planning method of a robot for better understanding.

2 is a diagram for explaining the configuration of a robot according to an embodiment.

3 is a diagram for explaining a method for identifying a movement path of a robot according to an embodiment.

4A to 4C are diagrams for describing a velocity profile according to an object type according to an exemplary embodiment.

5A and 5B are diagrams for describing a velocity profile according to an object type according to an exemplary embodiment.

6A to 6C are diagrams for explaining a velocity profile according to the velocity of an object according to an exemplary embodiment.

7A to 7C are diagrams for describing velocity profiles according to a plurality of objects according to an exemplary embodiment.

8A to 8C are diagrams for explaining a speed map according to a plurality of objects according to an exemplary embodiment.

9 is a diagram for explaining a method for calculating a required time between cells according to an exemplary embodiment.

10A to 10C are diagrams for explaining a movement path identification method according to an embodiment.

11 is a block diagram showing a detailed configuration of a robot according to an embodiment.

12 is a flowchart illustrating a method of controlling a robot according to an exemplary embodiment.

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

Terms used in this specification will be briefly described, and the present disclosure will be described in detail.

The terms used in the embodiments of the present disclosure have been selected from general terms that are currently widely used as much as possible while considering the functions in the present disclosure, but they may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technologies, and the like. . In addition, in a specific case, there is also a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the disclosure. Therefore, terms used in the present disclosure should be defined based on the meaning of the term and the general content of the present disclosure, not simply the name of the term.

In this specification, expressions such as “has,” “can have,” “includes,” or “can include” indicate the existence of a corresponding feature (eg, numerical value, function, operation, or component such as a part). , which does not preclude the existence of additional features.

The expression at least one of A and/or B should be understood to denote either "A" or "B" or "A and B".

Expressions such as "first," "second," "first," or "second," as used herein, may modify various components regardless of order and/or importance, and may refer to one component It is used only to distinguish it from other components and does not limit the corresponding 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 "connected to", it should be understood that an element may be directly connected to another element, or may be connected through another element (eg, a third element).

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprise" or "consist of" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In the present disclosure, a “module” or “unit” performs at least one function or operation, and may be implemented in 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 by at least one processor (not shown), except for "modules" or "units" that need to be implemented with specific hardware. It can be.

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

In the present disclosure, 'user' may mean a person who is provided with a service by a robot, but is not limited thereto.

According to FIG. 1 , the robot 100 may provide services to users while traveling in a specific space. For example, the robot 100 may provide a service of cleaning a space, but is not limited thereto. The robot 100 may pre-store map data corresponding to the space in order to travel in the space, and may travel in the space by performing route planning based on this. According to an example, the map data may be various types of map data such as a traversability map and a distance map.

According to an example, path planning based on a traversability map in which an obstacle is extended by a safe margin may create a safe path with a predetermined distance from a corner. However, if the safe margin is large, there is a problem that a path cannot be created in a narrow path (for example, path ①).

According to another example, distance map-based route planning, which includes distance information to the nearest obstacle for each cell (or grid) on the map, can create a safe route and a route that passes through a narrow passage. can create However, since passing through a wide passage (eg, route ③) is prioritized over a narrow passage (eg, routes ① and ②), an inefficient detour route may be created with a minimum time path passing through a narrow passage. there is a problem.

Accordingly, various embodiments of performing minimum-time path planning by reflecting real-time obstacle information will be described below.

According to FIG. 2 , the robot 100 may include at least one sensor 110, a memory 120, a driving unit 130, and a processor 140.

At least one sensor 110 may include a plurality of sensors of various types. The sensor 110 may measure a physical quantity or detect an operating state of the robot 100 and convert the measured or sensed information into an electrical signal. The sensor 110 may include a camera, and the camera may include a lens for focusing visible light and other optical signals received after being reflected by an object into an image sensor, and an image sensor capable of detecting visible light and other optical signals. Here, the image sensor may include a 2D pixel array divided into a plurality of pixels, and the camera according to an example may be implemented as a depth camera. In addition, the sensor 140 may include a distance sensor such as a light detection and ranging (LIDAR) sensor and a time of flight (TOF) sensor.

In addition, the sensor 110 may include a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor (eg, a red, green, blue (RGB) sensor), a bio sensor, It may include at least one of a temperature/humidity sensor, an illuminance sensor, or an ultra violet (UV) sensor.

The memory 120 may store data necessary for various embodiments. The memory 120 may be implemented in the form of a memory embedded in the robot 100 or in the form of a removable memory in the robot 100 depending on the data storage purpose. For example, data for driving the robot 100 is stored in a memory embedded in the robot 100, and data for extended functions of the robot 100 is stored in a memory attachable to and detachable from the robot 100. It can be. On the other hand, in the case of memory embedded in the robot 100, volatile memory (eg, DRAM (dynamic RAM), SRAM (static RAM), SDRAM (synchronous dynamic RAM), etc.), non-volatile memory (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 (e.g. NAND flash or NOR flash, etc.) , hard drive, or solid state drive (SSD). In addition, in the case of a memory attachable to and detachable from the robot 100, a memory card (eg, CF (compact flash), 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, a USB memory) may be implemented in the form of the like.

According to an example, the memory 120 may store a distance map including distance information to an object, velocity profile information according to characteristics of the object, and the like. However, the corresponding information may be received in real time from an external device. Here, the distance map may be in the form of storing a distance to an object, that is, an obstacle, and a probability value of the corresponding obstacle in each cell.

The driving unit 130 is a device capable of driving the robot 100. The driving unit 130 may adjust the traveling direction and driving speed under the control of the processor 140, and the driving unit 130 according to an example may be a power generating device that generates power for the robot 100 to travel (eg: Gasoline engine, diesel engine, LPG (liquefied gas petroleum) engine, electric motor, etc., depending on fuel (or energy source) used steering (hydraulics steering, electronic control power steering (EPS), etc.), driving devices (eg, wheels, propellers, etc.) for driving the robot 100 according to power may be included. Here, the drive unit 130 may be modified according to the driving type (eg, wheel type, walking type, flight type, etc.) of the robot 100 .

At least one 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 electrically connected to the memory 120 and the driving unit 130 to control the overall operation of the robot 100 . Processor 140 may be composed of one or a plurality of processors. For example, various functions (eg, map creation and route planning) described below may be performed by one processor, but different functions may be performed by a plurality of processors.

The processor 140 may perform the operation of the robot 100 according to various embodiments by executing at least one instruction stored in the memory 120 .

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), Neural Processing Unit (NPU), controller, application processor (AP), etc., but is described as processor 140 in this specification.

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

According to an embodiment, the processor 140 may obtain velocity profile information according to a distance to the object based on object characteristic information. Here, the object may be an obstacle obstructing the driving of the robot 100 . The object property information may include at least one of an object type, an object speed, and an object size. Here, the type of object may be divided into a static object without motion and a dynamic object with motion, but is not limited thereto. For example, dynamic objects may be classified into types such as people and animals, and static objects may be classified into types such as furniture and home appliances. Velocity profile information represents velocity information according to a distance from an obstacle, and may be different according to characteristics of the obstacle.

The processor 140 may obtain a speed map including speed information for each area based on the speed profile information obtained based on object property information. For example, the speed map may include speed information corresponding to each cell (or grid). In addition, the speed map may further store probability values of obstacles in each cell. Here, a cell (or grid) may be a minimum unit area included in the map. Also, the speed information may be an absolute value corresponding to the speed or a weighted value applied to a reference value. For example, the speed map may include speed values mapped to each of a plurality of cells.

According to an example, the processor 140 may obtain a speed map by replacing each distance information of a distance map including distance information to an obstacle corresponding to each cell with speed information.

Subsequently, the processor 140 may identify a movement path of the robot 100 based on the obtained speed map, and control the driving unit 130 based on the identified movement path.

According to an example, the processor 140 obtains a velocity map based on first velocity profile information when the object is a static object, and obtains a velocity map based on second velocity profile information when the object is a dynamic object. can Here, the first velocity profile information may be information in which the velocity decreases with a first gradient as the object approaches the static object within a first threshold distance from the static object. Also, the second velocity profile information may be information in which the velocity decreases with a second gradient as the object approaches the dynamic object within a second threshold distance from the dynamic object. Here, the second threshold distance may be greater than the first threshold distance. Also, the second slope may be smaller than the first slope. That is, the velocity profile corresponding to the dynamic object may decrease with a relatively gentle slope from a relatively long distance compared to the velocity profile corresponding to the static object.

According to an example, the processor 140 obtains a velocity map based on second velocity profile information when the object is a first-type dynamic object, and third velocity profile information when the object is a second-type dynamic object. A speed map can be obtained based on Here, the third velocity profile information may be information in which the velocity decreases with a third gradient as the dynamic object of the second type approaches the dynamic object of the second type within a third threshold distance. Here, the third threshold distance may be greater than the second threshold distance. Also, the third slope may be smaller than the second slope. Here, the dynamic object of the second type may be a type that relatively requires attention to the driving of the robot 100 compared to the dynamic object of the first type. For example, the first type dynamic object may be an adult, and the second type dynamic object may be a child or pet, but is not limited thereto.

According to an example, if the object is a dynamic object, the processor 140 may acquire velocity information of the dynamic object and obtain a velocity map by applying different velocity profile information according to the velocity information of the dynamic object.

According to an example, if the object is a static object of the third type, the processor 140 obtains a velocity map based on the first velocity profile information, and if the object is a static object of the fourth type, the processor 140 obtains the fourth velocity profile information. A speed map can be obtained based on Here, the fourth velocity profile information may be information in which the velocity decreases with a fourth slope smaller than the first slope as the static object of the fourth type is approached within a fourth threshold distance from the static object of the fourth type. Here, the fourth threshold distance may be greater than the first threshold distance. Also, the fourth slope may be smaller than the first slope. That is, the velocity profile corresponding to the static object of the fourth type may have a shape in which the object decreases with a relatively gentle gradient from a relatively long distance compared to a velocity profile corresponding to the static object of the third type. Here, the static object of the third type may be an object that is not dangerous at all, such as a wall, and the static object of the fourth type may be an object that is relatively dangerous compared to a wall, such as a table on which a vase is placed, but is not limited thereto. not.

According to an example, the processor 140 acquires fourth velocity profile information corresponding to a certain space based on the property information of a first object located in a certain space, and based on the property information of a second object located in the corresponding space. Thus, fifth velocity profile information corresponding to the corresponding space can be obtained. Subsequently, the processor 140 may obtain velocity profile information corresponding to a certain space based on the fourth velocity profile information and the fifth velocity profile information.

In this case, the processor 140 obtains a first velocity value corresponding to each cell included in the corresponding space based on the fourth velocity profile information, and obtains a first velocity value corresponding to each cell included in the corresponding space based on the fifth velocity profile information. A second velocity value corresponding to each cell included in the corresponding space is acquired, and a velocity value corresponding to each cell based on a smaller value of the first velocity value and the second velocity value corresponding to each cell included in the corresponding space. can be obtained. Subsequently, the processor 140 may obtain a velocity map corresponding to a certain space based on the obtained velocity value corresponding to each cell.

According to an embodiment, the processor 140 may update the distance map stored in the memory 120 based on object information acquired by at least one sensor (not shown) while the robot is driving. Subsequently, the processor 140 may obtain a speed map based on profile information obtained based on the updated distance map and object characteristic information.

Subsequently, the processor 140 obtains the time required between cells by dividing the distance between cells included in the speed map by the speed value corresponding to the cell according to the preset event, and determines the shortest time path based on the time required between cells for the robot ( 100). Here, an event for the processor 140 to perform route planning (or re-planning) may be an event in which a speed map is updated. However, the event is not limited thereto and may be an event in which another map related to the speed map is updated. For example, it may be an event in which a free space map or/and a distance map described later is updated. According to an example, if the acquisition of the above-described various maps is performed by a different (or other module) than a processor that performs path planning, path planning may be performed when an event signal of the corresponding processor (or module) is received.

According to FIG. 3 , the processor 140 may obtain 320 a free space map based on Simulaneous Localization And Mapping (SLAM) 310 . Here, SLAM means generating a map and estimating the position of the robot 100 at the same time. For example, the processor 140 may obtain a free space map based on data obtained through at least one sensor (not shown). According to an example, the processor 140 determines the location of the robot 100 using GPS, and maps the free space using various sensors provided in the robot 100, such as a camera, lidar sensor, infrared sensor, and ultrasonic sensor. can be obtained. Here, the free space map may be in the form of dividing the space into at least one of an occupied space, a free space, and an unknown space.

Then, the processor 140 based on the information about the free space included in the free-space map and the information obtained through at least one sensor (not shown), for example, a lidar sensor while the robot 100 is driving A distance map may be obtained (330). Here, the Distance Map may be in the form of storing a distance to an obstacle and a probability value of the obstacle.

In addition, the processor 140 may acquire object information, particularly dynamic object information while driving (340), and identify the type, speed, and the like of the dynamic object.

Subsequently, the processor 140 may obtain a speed map based on distance information, object information, and speed profile information 360 included in the distance map (350).

Thereafter, the processor 140 may perform path planning 370 based on the speed information for each cell included in the speed map. For example, the processor 140 may identify a minimum time path from the current location of the robot 100 to a destination based on speed information for each cell included in the speed map.

Figure 4a is a velocity profile for a static object that provides space on only one side, such as a wall, Figure 4b is a velocity profile for a static object that provides space on at least both sides, such as furniture, Figure 4c is a relative approach risk Velocity profiles for highly static objects can be represented.

According to the velocity profile shown in FIG. 4A , the velocity may gradually decrease within a critical distance from the wall and decrease to zero when the velocity reaches a specific distance from the wall.

According to the velocity profile shown in FIG. 4B , the velocity may gradually decrease within a threshold distance from the furniture in a plurality of directions, and may decrease to zero when reaching a specific distance from the furniture.

According to the velocity profile shown in FIG. 4C, in the case of a furniture with a relatively high approach risk (eg, risk of a vase falling in case of collision) compared to the furniture shown in FIG. 4B, a threshold relatively farther than FIG. 4B. The speed decreases relatively gently based on the distance, and when a certain distance from the furniture is reached, the speed may decrease to zero.

Here, the specific distance may be determined as the same distance based on the size of the robot 100 . For example, a specific distance may be determined as n times the size of the robot 100 (n is an integer greater than or equal to 1) regardless of the characteristics of the object. However, it is not limited thereto and the specific distance may be different according to the characteristics of each object.

5A may show a velocity profile for a dynamic object with a low approach risk, such as an adult, and FIG. 5B may show a velocity profile for a dynamic object with a high approach risk, such as a child.

According to the velocity profile shown in FIG. 5A , the velocity may gradually decrease within a threshold distance in a plurality of directions from the adult, and may decrease to zero when the velocity reaches a specific distance from the adult.

According to the velocity profile shown in FIG. 5B , the velocity may gradually decrease within a threshold distance from the child in a plurality of directions, and may decrease to zero when the velocity reaches a specific distance from the furniture.

In this case, according to the velocity profile shown in FIG. 5B, the velocity decreases with a relatively gentle gradient at a critical distance greater than that of FIG. 5A, thereby reducing the risk of approaching a dynamic object with a high risk of approach. Here, the specific distance at which the speed converges to 0 may be determined as the same distance based on the size of the robot 100 . For example, a specific distance may be determined as n times the size of the robot 100 (n is an integer greater than or equal to 1) regardless of the characteristics of the object. However, it is not limited thereto and the specific distance may be different according to the characteristics of each object. For example, a relatively large specific distance can be set for a dynamic object with a high approach risk.

6A may show a velocity profile when a dynamic object, for example, a pet, such as a puppy, does not move, and FIGS. 6B and 6C may show velocity profiles when the pet does not move.

As shown in FIG. 6A, when the puppy is lying down, a speed profile different from that when the puppy is moving may be applied as shown in FIGS. 6B and 6C.

For example, according to FIG. 6B , the speed may decrease to 0 when the speed relatively gently decreases based on a critical distance relatively farther than that of FIG. 6A and reaches a specific distance from the furniture. In this case, the specific distance at which the speed converges to 0 may be the same as that of FIG. 6A.

As another example, according to FIG. 6C , the speed may decrease to zero at a relatively long distance while the speed relatively gently decreases based on a relatively far critical distance from FIG. 6A . That is, the specific distance at which the speed converges to 0 may be different from that of FIG. 6A.

Meanwhile, although not clearly shown in the drawings, it is needless to say that the slope of the velocity profile and the specific distance at which the velocity converges to 0 may be different according to the dog's velocity.

According to an embodiment, the processor 140, when a plurality of objects exist in a certain space, the velocity profile information obtained based on the characteristic information of the first object and the velocity profile information obtained based on the characteristic information of the second object Velocity profile information corresponding to the corresponding space can be obtained based on .

For example, the processor 140 may perform a velocity profile as shown in FIG. 7A obtained based on the characteristic information of the first object and a velocity profile as shown in FIG. 7B obtained based on the characteristic information of the second object. Based on, it is possible to obtain the final velocity profile as shown in FIG. 7c. That is, the processor 140 identifies the smaller value of the velocity value obtained in FIG. 7A and the velocity value obtained in FIG. 7B for the same cell belonging to the corresponding space, acquires it as the final velocity value for the corresponding cell, and applies it to all cells. A final velocity profile may be obtained by obtaining a final velocity value for .

8A shows an example of a speed map obtained based on velocity profile information corresponding to a static object (eg, a wall) located in a specific space, and FIG. 8B corresponds to a dynamic object (eg, an adult). An example of a speed map obtained based on the speed profile information to be obtained is shown. The speed map may include speed information corresponding to each cell. Also, the speed map may include object probability information corresponding to each cell. In this case, the object probability value may be mapped to each cell as it is, but the probability value may be mapped only to cells having an object probability value equal to or greater than this threshold value.

In this case, when a dynamic object appears in a specific space, a velocity map as shown in FIG. 8C may be obtained based on the velocity profile according to FIG. 8A and the velocity profile according to FIG. 8B. That is, the processor 140 identifies the smaller value of the velocity value obtained in FIG. 8A and the velocity value obtained in FIG. 8B for the same cell belonging to the corresponding space, acquires it as the final velocity value for the corresponding cell, and applies it to all cells. A final velocity profile may be obtained by obtaining a final velocity value for , and a velocity map may be obtained based on the final velocity profile.

According to an embodiment, the processor 140 may obtain a required time between cells based on the speed map, and may identify the moving path of the robot 100 based on the obtained required time between cells.

According to an example, as shown in FIG. 9 , a required time between cells may be obtained based on a speed mapped to each cell and a distance between centers of each cell in a speed map to which a speed corresponding to each cell is mapped. For example, the velocity mapped to the first cell 911 is v11 (eg, a velocity unit such as mm/s or cm/s), the velocity mapped to the second cell 912 is v21, If the distance between 1

cell

911 and 2 cell 912 is xmm (or a distance unit such as cm, etc.) (actual distance), x/v11 is defined as It can be calculated from the time required. However, it is also possible to calculate the required time between the first cell 911 and the second cell 912 based on the average value of v11 and v21, v21, and the like, rather than the speed v11 mapped to the first cell 911.

Subsequently, the processor 140 may identify the shortest time path as the moving path of the robot 100 based on the required time between each cell. According to an example, the processor 140 may identify a path having the smallest cumulative cost by using the time required between cells as a cost, for example, an edge cost.

According to FIG. 10A , when a static obstacle and a dynamic obstacle appear on an already identified movement path ① and the movement path is maintained, the movement path ① may be updated in the form of ②. In this case, the moving path ② may not be the minimum path. Accordingly, the processor 140 may identify the shortest time path ③ based on the speed map according to various embodiments described above, and may drive the robot based on the moving path ③.

According to FIG. 10B, when an obstacle existing on a path other than the previously identified movement path ①, for example, a static obstacle disappears and a dynamic obstacle appears on the movement path ①, the movement path ① will be updated in the form of ②. can The movement path ② may not be the minimum path. Accordingly, the processor 140 may identify the shortest time path ③ based on the speed map according to various embodiments described above, and may drive the robot based on the moving path ③.

According to FIG. 10C, when an obstacle existing on a path other than the previously identified movement path ①, for example, a static obstacle disappears and a dynamic obstacle appears on the movement path ①, the movement path ① is updated in the form of ②. can The moving path ② may not be the minimum path. Accordingly, the processor 140 may identify the shortest time path ③ based on the speed map according to various embodiments described above, and may drive the robot based on the moving path ③.

According to FIG. 11, a robot 100' includes at least one sensor 110, a memory 120, a driving unit 130, a processor 140, a communication interface 150, a user interface 160, and a display 170. can include Among the components shown in FIG. 11 , detailed descriptions of components overlapping with those shown in FIG. 2 will be omitted.

The communication interface 150 may input and output various types of data. For example, the communication interface 150 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 External device (eg, source device), external storage medium (eg, USB memory), external server (eg, web hard) and various types of data through communication methods such as , Coaxial, etc. can transmit and receive.

According to an example, when map information is received from an external device (or external server), map information may be received through the communication interface 150 .

The user interface 160 is a component for the robot 100' to perform an interaction with a user. For example, the user interface 160 may include at least one of a touch sensor, a motion sensor, a button, a jog dial, a switch, a microphone, or a speaker, but is not limited thereto.

The display 170 may be implemented as a display including a self-light emitting element or a display including a non-light emitting element and a backlight. For example, LCD (Liquid Crystal Display), OLED (Organic Light Emitting Diodes) display, LED (Light Emitting Diodes), micro LED (micro LED), Mini LED, PDP (Plasma Display Panel), QD (Quantum dot) display , QLED (Quantum dot light-emitting diodes), etc. can be implemented in various types of displays. The display 110 may also include a driving circuit, a backlight unit, and the like that may be implemented in the form of an a-si TFT, a low temperature poly silicon (LTPS) TFT, or an organic TFT (OTFT). Meanwhile, the display 170 is implemented as a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display, a display in which a plurality of display modules are physically connected, and the like. It can be. Also, since the display 170 has a built-in touch screen, a program may be executed using a finger or a pen (eg, a stylus pen).

According to the method for controlling a robot shown in FIG. 12 , property information of an object is acquired based on sensing data obtained by at least one sensor while the robot is traveling, and based on the obtained property information of the object, the robot is traveling to the object. Velocity profile information according to distance is acquired (S1210).

Subsequently, a speed map including speed information for each area is obtained based on the obtained speed profile information (S1220).

Subsequently, a movement path is identified based on the obtained speed map (S1230).

Then, the robot is driven based on the identified movement path (S1240).

In addition, in step S1220 of obtaining a speed map, if the object is a static object, a speed map is obtained based on the first speed profile information, and if the object is a dynamic object, a speed map is obtained based on the second speed profile information. can be obtained In this case, the first velocity profile information is information in which the velocity decreases with a first gradient as it approaches the static object within a first threshold distance from the static object, and the second velocity profile information is information within a second threshold distance from the dynamic object. It may be information that the speed decreases with a second slope smaller than the first slope as it approaches the dynamic object.

In addition, in step S1220 of obtaining a speed map, if the object is a dynamic object of the first type, a speed map is obtained based on the second speed profile information, and if the object is a dynamic object of the second type, a third speed is obtained. The speed map is obtained based on the profile information. In this case, the third velocity profile information may be information in which the velocity decreases with a third slope smaller than the second slope as it approaches the second type dynamic object within a third threshold distance from the second type dynamic object.

Further, in step S1220 of acquiring the speed map, if the object is a dynamic object, the speed map may be obtained by obtaining speed information of the dynamic object and applying different speed profile information according to the speed information of the dynamic object.

In addition, in step S1220 of obtaining a speed map, fourth velocity profile information corresponding to a certain space is obtained based on the property information of a first object located in a certain space, and the property information of a second object located in the certain space is obtained. Based on this, fifth velocity profile information corresponding to a certain space may be obtained, and velocity profile information corresponding to a certain space may be obtained based on the fourth and fifth velocity profile information.

In this case, in step S1220 of obtaining a velocity map, a first velocity value corresponding to each cell included in a certain space is obtained based on the fourth velocity profile information, and the first velocity value is obtained based on the fifth velocity profile information. A second velocity value corresponding to each cell included in the certain space is obtained, and the velocity corresponding to each cell is based on a smaller value of the first velocity value and the second velocity value corresponding to each cell included in the certain space. value, and a speed map corresponding to a certain space may be obtained based on the speed value corresponding to each cell.

In addition, in step S1220 of acquiring the speed map, the distance map including distance information to the object is updated based on the object information obtained by the sensor while the robot is traveling, and the updated distance map and the obtained profile information are updated. Based on this, it is possible to obtain a speed map including speed information for each area.

The speed map may include speed values corresponding to each of a plurality of cells. In this case, in step S1240 of driving the robot, the distance between cells included in the speed map is divided by the speed value corresponding to the cell to obtain the required time between cells, and based on the required time between cells, the shortest time path is the moving path of the robot. can be identified by

In addition, in step S1220 of obtaining a speed map, distance information corresponding to each cell is obtained from the distance map including distance information to the object, and the speed corresponding to each cell is based on the obtained distance information and speed profile information. information can be obtained.

Meanwhile, the methods according to various embodiments described above may be implemented in the form of an application that can be installed in an existing electronic device. Alternatively, the above-described methods according to various embodiments of the present disclosure may be performed using a deep learning-based artificial neural network (or deep artificial neural network), that is, a learning network model.

In addition, the methods according to various embodiments described above may be implemented only by upgrading software or hardware of an existing electronic device.

In addition, various embodiments described above may be performed through an embedded server included in the electronic device or an external server of the electronic device.

Meanwhile, according to an exemplary embodiment, various embodiments described above may be implemented as software including instructions stored in a machine-readable storage medium (eg, a computer). A device is a device capable of calling a stored command from a storage medium and operating according to the called command, and may include an electronic device (eg, the electronic device A) according to the disclosed embodiments. When a command is executed by a processor, the processor may perform a function corresponding to the command directly or by using other components under the control of the processor. An instruction may include code generated or executed by a compiler or interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' only means that the storage medium does not contain a signal and is tangible, but does not distinguish whether data is stored semi-permanently or temporarily in the storage medium.

Also, according to one embodiment, the method according to various embodiments described above may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product may be distributed in the form of a device-readable storage medium (eg compact disc read only memory (CD-ROM)) or online through an application store (eg Play Store™). In the case of online distribution, at least part of the computer program product may be temporarily stored or temporarily created in a storage medium such as a manufacturer's server, an application store server, or a relay server's memory.

In addition, each of the components (eg, modules or programs) according to various embodiments described above may be composed of a single object or a plurality of entities, and some sub-components among the aforementioned sub-components may be omitted, or other sub-components may be used. Components may be further included in various embodiments. Alternatively or additionally, some components (eg, modules or programs) may be integrated into one entity and perform the same or similar functions performed by each corresponding component prior to integration. According to various embodiments, operations performed by modules, programs, or other components may be executed sequentially, in parallel, repetitively, or heuristically, or at least some operations may be executed in a different order, may be omitted, or other operations may be added. can

Although preferred embodiments have been shown and described above, the present disclosure is not limited to the specific embodiments described above, and is available to those skilled in the art without departing from the subject matter claimed in the claims. Of course, various modifications are possible, and these modifications should not be individually understood from the technical spirit or perspective of the present disclosure.

Claims

in robots,

at least one sensor;

driving unit;

a memory storing at least one instruction; and

A processor connected to the at least one sensor, the driving unit, and the memory to control the electronic device;

the processor,

By executing the at least one command,

Obtaining property information of an object based on sensing data acquired by the at least one sensor while the robot is traveling;

Obtaining velocity profile information according to a distance to the object based on the acquired characteristic information of the object;

Obtaining a speed map including speed information for each area based on the obtained speed profile information;

Controlling the driving unit based on the movement path identified based on the obtained speed map, the robot.
According to claim 1,

the processor,

If the object is a static object, obtaining the velocity map based on first velocity profile information;

When the object is a dynamic object, obtaining the velocity map based on second velocity profile information;

The first velocity profile information is information in which the velocity decreases with a first gradient as it approaches the static object within a first threshold distance from the static object;

The second velocity profile information is information in which a velocity decreases with a second slope smaller than the first slope as it approaches the dynamic object within a second threshold distance from the dynamic object.
According to claim 2,

the processor,

If the object is a dynamic object of a first type, obtain the velocity map based on the second velocity profile information;

When the object is a dynamic object of a second type, obtaining the velocity map based on third velocity profile information;

The third velocity profile information is information in which the speed decreases with a third slope smaller than the second slope as the robot approaches the second type of dynamic object within a third threshold distance from the second type of dynamic object. .
According to claim 2,

the processor,

If the object is a dynamic object, obtaining speed information of the dynamic object;

Acquiring the speed map by applying different speed profile information according to the speed information of the dynamic object.
According to claim 1,

the processor,

Obtaining fourth velocity profile information corresponding to the predetermined space based on characteristic information of a first object located in the predetermined space;

Obtaining fifth velocity profile information corresponding to the predetermined space based on property information of a second object located within the predetermined space;

The robot, which obtains velocity profile information corresponding to the predetermined space based on the fourth velocity profile information and the fifth velocity profile information.
According to claim 5,

the processor,

Obtaining a first velocity value corresponding to each cell included in the predetermined space based on the fourth velocity profile information;

Obtaining a second velocity value corresponding to each cell included in the predetermined space based on the fifth velocity profile information;

Obtaining a velocity value corresponding to each cell based on a smaller value of a first velocity value and a second velocity value corresponding to each cell included in the predetermined space;

Acquiring a speed map corresponding to the predetermined space based on the obtained speed value corresponding to each cell.
According to claim 1,

the memory,

Further stores a distance map containing distance information to the object,

the processor,

Updating the stored Distance Map based on object information obtained by the at least one sensor while the robot is traveling;

A robot that obtains a speed map including speed information for each area based on the updated Distance Map and the obtained profile information.
According to claim 1,

The speed map includes speed values corresponding to each of a plurality of cells,

the processor,

Divide the distance between cells included in the speed map by a speed value corresponding to the cell to obtain a required time between cells;

Based on the time required between the cells, the robot identifies the shortest time path as the moving path of the robot.
According to claim 1,

the processor,

Acquiring distance information corresponding to each cell from a distance map including distance information to an object,

obtaining speed information corresponding to each cell based on the obtained distance information and the speed profile information;

A robot that obtains the speed map including speed information corresponding to each cell.
In the robot control method,

obtaining characteristic information of an object based on sensing data obtained by at least one sensor while the robot is driving;

obtaining velocity profile information according to a distance to the object based on the acquired characteristic information of the object;

obtaining a speed map including speed information for each area based on the obtained speed profile information; and

and driving the robot based on a movement path identified based on the obtained speed map.
According to claim 10,

Obtaining the speed map,

obtaining the velocity map based on first velocity profile information when the object is a static object; and

When the object is a dynamic object, obtaining the velocity map based on second velocity profile information;

The first velocity profile information is information in which the velocity decreases with a first gradient as it approaches the static object within a first threshold distance from the static object;

The second velocity profile information is information in which a velocity decreases with a second slope smaller than the first slope as it approaches the dynamic object within a second threshold distance from the dynamic object.
According to claim 11,

Obtaining the speed map,

obtaining the velocity map based on the second velocity profile information when the object is a dynamic object of a first type; and

When the object is a dynamic object of a second type, obtaining the velocity map based on third velocity profile information;

The third velocity profile information is information indicating that the velocity decreases with a third slope smaller than the second slope as it approaches the second type dynamic object within a third threshold distance from the second type dynamic object. Way.
According to claim 11,

Obtaining the speed map,

If the object is a dynamic object, obtaining speed information of the dynamic object;

The control method of obtaining the speed map by applying different speed profile information according to the speed information of the dynamic object.
According to claim 10,

Obtaining the speed profile information,

obtaining fourth velocity profile information corresponding to a predetermined space based on characteristic information of a first object located in the predetermined space;

obtaining fifth velocity profile information corresponding to the predetermined space based on characteristic information of a second object located within the predetermined space; and

and obtaining velocity profile information corresponding to the predetermined space based on the fourth velocity profile information and the fifth velocity profile information.
According to claim 14,

Obtaining the speed map,

obtaining a first velocity value corresponding to each cell included in the predetermined space based on the fourth velocity profile information;

obtaining a second velocity value corresponding to each cell included in the predetermined space based on the fifth velocity profile information;

obtaining a velocity value corresponding to each cell based on a smaller value of a first velocity value and a second velocity value corresponding to each cell included in the predetermined space; and

and obtaining a speed map corresponding to the predetermined space based on the obtained speed value corresponding to each cell.