WO2024043575A1 - 신뢰도 값을 이용하여 이동 경로를 식별하는 로봇 장치 및 그 제어 방법 - Google Patents
신뢰도 값을 이용하여 이동 경로를 식별하는 로봇 장치 및 그 제어 방법 Download PDFInfo
- Publication number
- WO2024043575A1 WO2024043575A1 PCT/KR2023/011579 KR2023011579W WO2024043575A1 WO 2024043575 A1 WO2024043575 A1 WO 2024043575A1 KR 2023011579 W KR2023011579 W KR 2023011579W WO 2024043575 A1 WO2024043575 A1 WO 2024043575A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- robot device
- sensing data
- reliability value
- sensor
- robotic device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1628—Program controls characterised by the control loop
- B25J9/1653—Program controls characterised by the control loop parameters identification, estimation, stiffness, accuracy, error analysis
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/022—Optical sensing devices using lasers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/023—Optical sensing devices including video camera means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1656—Program controls characterised by programming, planning systems for manipulators
- B25J9/1664—Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1694—Program controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/20—Control system inputs
- G05D1/24—Arrangements for determining position or orientation
- G05D1/242—Means based on the reflection of waves generated by the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/20—Control system inputs
- G05D1/24—Arrangements for determining position or orientation
- G05D1/246—Arrangements for determining position or orientation using environment maps, e.g. simultaneous localisation and mapping [SLAM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2105/00—Specific applications of the controlled vehicles
- G05D2105/10—Specific applications of the controlled vehicles for cleaning, vacuuming or polishing
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2107/00—Specific environments of the controlled vehicles
- G05D2107/40—Indoor domestic environment
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2109/00—Types of controlled vehicles
- G05D2109/10—Land vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
- G05D2111/10—Optical signals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
- G05D2111/10—Optical signals
- G05D2111/17—Coherent light, e.g. laser signals
Definitions
- the present invention relates to a robotic device and a control method thereof, and more specifically, to a robotic device that identifies a movement path using a reliability value and a control method thereof.
- a robotic device acquired a map, estimated its position within the map, and moved along a movement path.
- the robot device moves, the error between the estimated position and the actual position accumulates, resulting in a significant deviation.
- the robot device itself is assumed to be located at the end point within the map, but there is a problem in that the actual location of the robot device is located in a completely different place rather than the end point of the movement path.
- the robot device includes at least one memory that stores at least one instruction, a sensor that senses the environment of the robot device and outputs sensing data, and executes the at least one instruction. Based on the sensing data received from the sensor, a map corresponding to the space where the robot device is located and a reliability value of each of a plurality of areas of the map are obtained, and a reliability value of the map and each of the plurality of areas is obtained. Stores in the at least one memory, identifies at least one area corresponding to a reliability value greater than a threshold based on a reliability value corresponding to each of the plurality of areas, and identifies the at least one area based on the identified at least one area. Identify the movement path of the robotic device in space.
- the one or more processors estimate one of the plurality of areas as the location of the robot device based on the sensing data, determine the probability that the estimated location matches the actual location of the robot device, and determine the probability that the estimated location matches the actual location of the robot device.
- An estimated reliability value corresponding to the estimated location of the device may be obtained.
- the one or more processors acquire movement information of the robot device based on first and second sensing data continuously received from the sensor, and obtain movement information corresponding to the second sensing data based on the movement information.
- the new location of the robotic device can be estimated.
- the sensor includes a LiDAR sensor, the first sensing data includes first point cloud data received from the LiDAR sensor, and the second sensing data is received from the LiDAR sensor. and second point cloud data, wherein the one or more processors perform an operation of combining a plurality of point clouds based on the first point cloud data and the second point cloud data, and the new point cloud of the robot device. An updated reliability value corresponding to the location is obtained, and the updated reliability value may be less than the threshold value.
- the sensor includes a camera, the first sensing data received from the camera includes first image data, the second sensing data received from the camera includes second image data, and the one or more
- the processor identifies a dynamic object based on the first image data and the second image data, and if the number of dynamic objects is more than a threshold number, obtains an updated reliability value corresponding to the new location of the robotic device. And the updated reliability value may be less than the threshold value.
- the sensor includes a camera, sensing data received from the camera includes image data, and the one or more processors identify a viewing angle of the camera based on the image data, and the viewing angle is less than a critical angle. If so, an updated reliability value corresponding to the new location of the robotic device is obtained, and the updated reliability value may be less than the threshold value.
- the movement information includes a movement direction of the robot device, a movement distance of the robot device, or a movement speed of the robot device, and the one or more processors include the movement direction of the robot device included in the movement information, If at least one of the movement distance and the movement speed is identified as being impossible to maintain, obtain an updated reliability value corresponding to the new position of the robotic device, and the updated reliability value may be less than the threshold value. .
- the one or more processors may update the reliability value corresponding to one area among the plurality of areas based on the obtained reliability value.
- the sensor includes a LiDAR sensor, and the one or more processors determine the orientation of the LiDAR sensor in one of the plurality of areas based on sensing data received from the LiDAR sensor.
- An error value according to the robot device may be identified, and the direction of the lidar sensor may be adjusted based on the error value while the robot device moves along the movement path within one of the plurality of areas.
- the one or more processors may modify the movement path to bypass the identified area.
- a control method of a robotic device includes obtaining a map of a space where the robotic device is located, including a plurality of regions, each of the plurality of regions including a corresponding reliability value, Identifying at least one area among the plurality of areas, which corresponds to a reliability value equal to or higher than a threshold based on a reliability value corresponding to each of the plurality of areas, and identifying the robot for the space based on the at least one area. It includes identifying the movement path of the device.
- the control method includes estimating one area among the plurality of areas as the location of the robot device based on sensing data from a sensor of the robot device, and determining a probability that the estimated location matches the actual location of the robot device. It may further include determining and obtaining an estimated reliability value corresponding to the estimated position of the robot device.
- the estimating step includes obtaining movement information of the robot device based on first and second sensing data continuously received from the sensor, and calculating movement information corresponding to the second sensing data based on the movement information. It may include estimating a new location of the robot device.
- the sensor includes a LiDAR sensor, the first sensing data includes first point cloud data received from the LiDAR sensor, and the second sensing data is received from the LiDAR sensor. comprising second point cloud data, wherein the step of obtaining the estimated reliability value includes performing an operation of combining a plurality of point clouds based on the first point cloud data and the second point cloud data, and and obtaining an updated reliability value corresponding to the new location of the robotic device, wherein the updated reliability value may be less than the threshold value.
- the sensor includes the camera, the first sensing data received from the camera includes first image data, and the second sensing data received from the camera includes second image data, Obtaining the estimated reliability value includes identifying a dynamic object based on the first image data and the second image data, and if the number of dynamic objects is greater than a threshold number, the new location of the robotic device and obtaining an updated reliability value corresponding to , wherein the updated reliability value may be less than the threshold value.
- a computer-readable recording medium including a program for executing a method for controlling a robotic device, wherein the method for controlling a robotic device includes a plurality of regions, each of the plurality of regions including a corresponding reliability value. Obtaining a map of the space where the robotic device is located, identifying at least one area among the plurality of areas corresponding to a reliability value greater than or equal to a threshold based on the reliability value corresponding to each of the plurality of areas, and and identifying a movement path of the robotic device with respect to the space based on at least one area.
- the control method includes estimating one area among the plurality of areas as the location of the robot device based on sensing data from a sensor of the robot device, and determining a probability that the estimated location matches the actual location of the robot device. It may further include determining and obtaining an estimated reliability value corresponding to the estimated position of the robot device.
- the estimating step includes obtaining movement information of the robot device based on first and second sensing data continuously received from the sensor, and calculating movement information corresponding to the second sensing data based on the movement information. It may include estimating a new location of the robot device.
- the sensor includes a LiDAR sensor, the first sensing data includes first point cloud data received from the LiDAR sensor, and the second sensing data is received from the LiDAR sensor. comprising second point cloud data, wherein the step of obtaining the estimated reliability value includes performing an operation of combining a plurality of point clouds based on the first point cloud data and the second point cloud data, and and obtaining an updated reliability value corresponding to the new location of the robotic device, wherein the updated reliability value may be less than the threshold value.
- the sensor includes the camera, the first sensing data received from the camera includes first image data, and the second sensing data received from the camera includes second image data, Obtaining the estimated reliability value includes identifying a dynamic object based on the first image data and the second image data, and if the number of dynamic objects is greater than a threshold number, the new location of the robotic device and obtaining an updated reliability value corresponding to , wherein the updated reliability value may be less than the threshold value.
- FIG. 1 is a diagram for explaining a robot device according to an embodiment of the present disclosure.
- Figure 2 is a block diagram showing the configuration of a robot device according to an embodiment of the present disclosure.
- FIG. 3 is a diagram for explaining a map corresponding to a space where a robot device is located according to an embodiment of the present disclosure.
- Figure 4 is a diagram for explaining movement information of a robot device according to an embodiment of the present disclosure.
- FIG. 5 is a diagram for explaining a plurality of areas included in a map according to an embodiment of the present disclosure.
- Figure 6 is a diagram for explaining a method of estimating the position of a robot device according to an embodiment of the present disclosure.
- Figure 7 is a diagram for explaining point cloud data according to an embodiment of the present disclosure.
- FIG. 8 is a diagram for explaining a dynamic object according to an embodiment of the present disclosure.
- FIG. 9 is a diagram for explaining a field of view according to an embodiment of the present disclosure.
- Figure 10 is a flowchart for explaining a control method of a robot device according to an embodiment of the present disclosure.
- expressions such as “have,” “may have,” “includes,” or “may include” refer to the presence of the corresponding feature (e.g., component such as numerical value, function, operation, or part). , and does not rule out the existence of additional features.
- a or/and B should be understood as referring to either “A” or “B” or “A and B”.
- expressions such as “first,” “second,” “first,” or “second,” can modify various components regardless of order and/or importance, and can refer to one component. It is only used to distinguish from other components and does not limit the components.
- a component e.g., a first component
- another component e.g., a second component
- connection to it should be understood that a certain component can be connected directly to another component or connected through another component (e.g., a third component).
- a “module” or “unit” performs at least one function or operation, and may be implemented as hardware or software, or as a combination of hardware and software. Additionally, a plurality of “modules” or a plurality of “units” 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.
- the term user may refer to a person using an electronic device or a device (eg, an artificial intelligence electronic device) using an electronic device.
- a device eg, an artificial intelligence electronic device
- FIG. 1 is a diagram for explaining a robot device according to an embodiment of the present disclosure.
- the robotic device 100 may refer to various types of devices that have the ability to perform functions on their own. For example, in addition to simple repetitive functions, the robotic device 100 detects the surrounding environment of the robotic device 100 in real time based on sensing data from sensors (e.g., LiDAR (Light Detection And Ranging) sensors, cameras, etc.) It may also mean a smart device that collects information and operates autonomously.
- sensors e.g., LiDAR (Light Detection And Ranging) sensors, cameras, etc.
- sensors e.g., LiDAR (Light Detection And Ranging) sensors, cameras, etc.
- the robot device 100 may be provided with a driving unit including an actuator or a motor.
- the driving unit may include a wheel, a brake, etc., and the robot device 100 can move within a specific space by itself using the wheel, a brake, etc. included in the driving unit.
- the robotic device 100 may control the movement of robot joints (articulated) using a driving unit.
- the robot joint may refer to a component of the robot device 100 to replace the function of a human arm or hand.
- the robot device 100 can sense the surrounding environment of the robot device 100 in real time based on sensing data from a sensor. Subsequently, the robot device 100 may control the driving unit based on the sensed surrounding environment. For example, the robot device 100 may identify the movement path of the robot device 100 based on sensing data from a sensor.
- the robotic device 100 may obtain a map corresponding to the space in which the robotic device 100 is located based on the sensing data and identify the location of the robotic device 100 within the map.
- the robotic device 100 can identify its location in real time and move within space according to a movement path. Therefore, in order for the robotic device 100 to move within space according to a movement path, it is necessary to accurately (or with high reliability) identify the location.
- the robotic device 100 identifies a location within the map, and identifies a movement path by considering whether the identified location matches the current location (or actual location) within the space of the robotic device 100.
- Various embodiments will be described.
- the robotic device 100 may be classified into industrial, medical, household, military, and exploration purposes depending on the field or function it can perform.
- industrial robot devices may be subdivided into robot devices used in the product manufacturing process in a factory, robot devices that respond to customers, take orders, and serve in stores or restaurants, etc.
- the robot device 100 is a serving robot device that can transport service items to a specific location desired by the user in various places such as restaurants, hotels, supermarkets, hospitals, and clothing stores. It can be implemented as:
- the robot device 100 can be classified in various ways depending on the application field, function, and purpose of use, and is of course not limited to the above-described example.
- the robot device 100 may be implemented as a robot cleaner located in a home.
- a robot vacuum cleaner refers to a device that is driven by electric power and automatically suctions foreign substances.
- the robot device 100 is assumed to be a robot vacuum cleaner, and the robot cleaner is shown assuming that the robot cleaner is implemented in a flat form that is in close contact with the floor to suck up floor debris.
- the robot device 100 can be implemented in various forms as described above.
- Figure 2 is a block diagram showing the configuration of a robot device according to an embodiment of the present disclosure.
- the robotic device 100 includes a memory 110, a sensor 120, and one or more processors 130 (hereinafter referred to as processors).
- the memory 110 may store data necessary for various embodiments of the present disclosure.
- the memory 110 may be implemented as a memory embedded in the robot device 100 or as a memory detachable from the robot device 100 depending on the data storage purpose. For example, in the case of data for driving the robot device 100, it is stored in the memory embedded in the robot device 100, and in the case of data for the expansion function of the robot device 100, it is detachable from the robot device 100. It can be stored in available memory.
- volatile memory e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM), etc.
- non-volatile memory e.g., 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.
- OTPROM one time programmable ROM
- PROM programmable ROM
- EPROM erasable and programmable ROM
- EEPROM electrically erasable and programmable ROM
- mask ROM e.g., flash ROM, flash memory (such as NAND flash or NOR flash, etc.)
- flash memory such as NAND flash or NOR flash, etc.
- SSD solid state drive
- a memory card e.g., 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 a USB port (e.g., it may be implemented in a form such as USB memory).
- the memory 110 may store at least one instruction or a computer program including instructions for controlling the robot device 100.
- various data may be stored in the external memory of the processor 130, and some of the data may be stored in the internal memory of the processor 130 and the rest may be stored in the external memory.
- the memory 110 may store a map corresponding to the space where the robot device 100 is located under the control of the processor 130.
- the processor 130 may obtain a map corresponding to the space where the robot device 100 is located based on the sensing data received from the sensor 120 and store the map in the memory 110.
- the senor 120 may include a Lidar sensor, a camera, etc.
- the processor 130 controls the LiDAR sensor to emit a laser beam to detect the surrounding environment of the robotic device 100, and the LiDAR sensor measures the distance to an object adjacent to the robotic device 100, the robot The direction in which the object is located relative to the device 100 and the characteristics of the object can be obtained as sensing data. Subsequently, the processor 130 may obtain 2D/3D image information (eg, a map) of the surrounding environment of the robot device 100 based on the sensing data.
- 2D/3D image information eg, a map
- the processor 130 may acquire image data by controlling a camera to detect the surrounding environment of the robot device 100.
- the camera may capture the surrounding environment of the robot device 100 under the control of the processor 130, acquire image data, and transmit it to the processor 130.
- the processor 130 analyzes the image data to obtain the distance to the object adjacent to the robot device 100, the direction in which the object is located relative to the robot device 100, and the characteristics of the object, and the robot device 100
- the surrounding environment of 100 can be obtained as 2D/3D image information (eg, map).
- the senor 120 may include various types of sensors that can sense the surrounding environment of the robot device 100 in addition to a LiDAR sensor and a camera.
- One or more processors 130 controls the overall operation of the robot device 100.
- the processor 130 may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON) that processes digital signals.
- DSP digital signal processor
- MCU micro controller unit
- MPU micro processing unit
- AP application processor
- communication processor It may include one or more of a communication processor (CP), an ARM processor, and an Artificial Intelligence (AI) processor, or may be defined by the corresponding term.
- the processor 130 is a System on Chip (SoC) with a built-in processing algorithm. ), may be implemented in the form of a large scale integration (LSI), or may be implemented in the form of a field programmable gate array (FPGA).
- SoC System on Chip
- the processor 130 performs various functions by executing computer executable instructions stored in memory. can be performed.
- FIG. 3 is a diagram for explaining a map corresponding to a space where a robot device is located according to an embodiment of the present disclosure.
- the processor 130 may perform a simultaneous localization and mapping (SLAM) operation to obtain a map corresponding to the space where the robot device 100 is located.
- SLAM simultaneous localization and mapping
- the SLAM operation is an operation of obtaining a map corresponding to the space where the robotic device 100 is located using sensing data received from the sensor 120 and identifying the location of the robotic device 100 within the map. It can mean.
- the processor 130 may estimate the location of the robotic device 100 within the map based on sensing data received from the sensor 120.
- the processor 130 when the first sensing data and the second sensing data are received sequentially (or continuously), the processor 130 generates movement information of the robot device 100 based on the first sensing data and the second sensing data. It can be obtained.
- the processor 130 may estimate the location of the robot device 100 within the map at the time the second sensing data is received based on the movement information.
- Figure 4 is a diagram for explaining movement information of a robot device according to an embodiment of the present disclosure.
- the sensor 120 provided in the robot device 100 may acquire first sensing data and transmit the first sensing data to the processor 130.
- the sensor 120 provided in the robot device 100' (the robot device 100' is the same as the robot device 100, but has moved forward in time) sends the second sensing data. and transmit the second sensing data to the processor 130.
- the processor 130 may obtain movement information of the robot device 100 from time t to time t+1 based on the first sensing data and the second sensing data.
- the processor 130 may estimate the location of the robot device 100' within the map at time t+1 based on movement information.
- the senor 120 may include a LiDAR sensor.
- the processor 130 combines the point cloud based on the first point cloud data included in the first sensing data and the second point cloud data included in the second sensing data (or , registration, alignment) can be performed.
- the processor 130 may combine first point cloud data and second point cloud data using LiDAR Odometry (e.g., Iterative closest point (ICP) algorithm, Normal Distributions Transform (NDT), etc.) there is. Subsequently, the processor 130 may estimate the location (or movement trajectory) of the robot device 100' based on the result of combining the first point cloud data and the second point cloud data.
- LiDAR Odometry e.g., Iterative closest point (ICP) algorithm, Normal Distributions Transform (NDT), etc.
- the senor 120 may include a camera.
- the processor 130 processes the robot device 100 from time t to time t+1 based on the first image data included in the first sensing data and the second image data included in the second sensing data received from the camera. Movement information can be obtained.
- the processor 130 analyzes the first image data to identify features of at least one object included in the first image data (e.g., geometric features of the at least one object), By analyzing the second image data, characteristics of at least one object included in the second image data may be identified.
- the processor 130 compares the characteristics of at least one object included in the first image data with the characteristics of at least one object included in the second image data to determine the robot device 100 from time t to time t+1. ) movement information can be obtained.
- the processor 130 may estimate the location (or movement trajectory) of the robot device 100' based on the movement information.
- the senor 120 may include at least one of a LiDAR sensor or a camera.
- the processor 130 displays the robot device 100 in the map based on a plurality of sensing data received in real time or sequentially from the sensor 120 while the robot device 100 moves in space. Real-time location can be estimated.
- the processor 130 may identify the probability that the estimated location within the map matches the actual location of the robot device 100 within space.
- the processor 130 may identify whether the estimated location can be trusted as the actual location of the robotic device 100, that is, the probability that the estimated location matches the actual location (hereinafter referred to as a reliability value).
- the reliability value represents the reliability of the location estimated based on movement information, and may be inversely proportional to the localization failure value (LFV).
- LBV localization failure value
- the reliability value is high, there is a high probability that the location estimated based on the movement information matches the actual location of the robot device 100, and the location measurement failure value may be low. Conversely, if the reliability value is low, the probability that the location estimated based on the movement information matches the actual location of the robotic device 100 is low, and the location measurement failure value may be high.
- the processor 130 may divide the map into a plurality of areas and obtain and store a reliability value corresponding to each of the plurality of areas.
- FIG. 5 is a diagram for explaining a plurality of areas included in a map according to an embodiment of the present disclosure.
- the map may be divided into a plurality of areas.
- Each of the plurality of areas may be called a cell, but hereinafter, for convenience of explanation, they will be collectively referred to as areas. Meanwhile, of course, the sizes of the plurality of areas shown in FIG. 5 are examples and are not limited thereto.
- the processor 130 may estimate the real-time location of the robot device 100 based on a plurality of sensing data received in real time or sequentially from the sensor 120 while the robot device 100 is moving. there is.
- the processor 130 identifies the probability that the estimated location matches the actual location of the robotic device 100, that is, a reliability value, and maps the identified reliability value with an area corresponding to the estimated location among the plurality of areas. You can.
- the processor 130 identifies a reliability value corresponding to each of the plurality of areas, and creates a reliability value map (or, localization failure value (LFV) map (hereinafter, LFV Map)) corresponding to the map. It can be obtained.
- LFV Map localization failure value
- the processor 130 calculates the probability that the estimated position matches the actual position of the robotic device 100 using a confidence value map. It can be obtained from.
- the processor 130 identifies an appropriate movement path in space, and in order to accurately move the robotic device 100 according to the identified movement path, it is necessary to accurately (or with high reliability) estimate the position within the map. .
- the processor 130 may identify at least one area corresponding to a reliability value greater than or equal to a threshold value based on the reliability value corresponding to each of the plurality of areas included in the reliability value map. Subsequently, the processor 130 may identify the movement path of the robotic device 100 in space based on the at least one identified area.
- the processor 130 selects one of the plurality of movement paths with the same start point and end point based on the reliability value map, which preferentially moves to an area where the reliability value is greater than a threshold value. can be identified.
- the processor 130 selects one of the plurality of movement paths with the same start point and end point based on the reliability value map, bypassing an area where the reliability value is less than a threshold value. can be identified.
- the processor 130 may move the robotic device 100 based on the identified movement path.
- Figure 6 is a diagram for explaining a method of estimating the position of a robot device according to an embodiment of the present disclosure.
- the processor 130 based on first point cloud data included in the first sensing data received from the LiDAR sensor and second point cloud data included in the second sensing data. Point clouds can be combined (or registered, aligned).
- the processor 130 combines point clouds based on first point cloud data and second point cloud data corresponding to objects (e.g., sofas, etc.) adjacent to the robotic device 100. You can.
- the processor 130 may obtain movement information based on the combination result and estimate the location within the map of the robotic device 100 based on the obtained movement information.
- the processor 130 determines commonalities/similarities between the geometric features of the object obtained from each of the first image data included in the first sensing data received from the camera and the second image data included in the second sensing data. By identifying , movement information of the robot device 100 from time t to time t+1 can be obtained. Additionally, the processor 130 may estimate the location based on movement information.
- the processor 130 may identify a reliability value of an area corresponding to an estimated location among a plurality of areas as being equal to or greater than a threshold value.
- the processor 130 may obtain first point cloud data and second point cloud data. There is no, and point clouds may not be combined. In this case, the processor 130 may not obtain movement information based on the combination result and may fail to estimate the location within the map of the robot device 100. A detailed description of this will be made with reference to FIG. 7 .
- Figure 7 is a diagram for explaining point cloud data according to an embodiment of the present disclosure.
- the processor 130 may reduce the number of points included in the point cloud data. Accordingly, if the number of points included in the point cloud data is small, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the processor 130 acquires movement information by combining the point cloud of the first point cloud data and the second point cloud data, and estimates the location of the robot device 100 based on the obtained movement information. You can. If the number of points included in each of the first point cloud data and the second point cloud data is small, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the processor 130 may not obtain movement information and may fail to estimate the position within the map of the robotic device 100 if each of the first point cloud data and the second point cloud data does not include a point. Of course.
- the processor 130 Based on the reliability value map, the processor 130 identifies which one of the plurality of movement paths with the same start point and end point preferentially moves to an area where the reliability value is greater than or equal to a threshold value. You can.
- the processor 130 moves the movement path indicated by a solid line in FIG. 6, that is, the reliability value is below the threshold.
- a movement path can be identified to include abnormal areas.
- FIG. 8 is a diagram for explaining a dynamic object according to an embodiment of the present disclosure.
- the processor 130 estimates the location based on point cloud data corresponding to the dynamic object, and the reliability value of the area corresponding to the estimated location. can be identified as being below the threshold.
- the processor 130 may obtain movement information by combining the point cloud of the first point cloud data and the second point cloud data, and estimate the location of the robotic device 100 based on the obtained movement information. there is. If each of the first point cloud data and the second point cloud data includes a point cloud corresponding to a dynamic object, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the movement information of the robotic device 100 from time t to time t+1 may include movement of the dynamic object in addition to the movement of the robotic device 100.
- the processor 130 estimates the position of the robotic device 100 based on movement information
- the position of the robotic device 100 is estimated by considering the movement of dynamic objects in addition to the movement of the robotic device 100, An error may occur between the estimated position and the actual position of the robot device 100. Therefore, if each of the first point cloud data and the second point cloud data includes a point cloud corresponding to a dynamic object, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value. .
- the sensor 120 includes a camera, and the processor 130 identifies a dynamic object based on first image data included in first sensing data and second image data included in second sensing data received from the camera. , if a dynamic object is identified (or if the number of identified dynamic objects is greater than or equal to a threshold), the reliability value of the area corresponding to the estimated location may be identified as less than the threshold value.
- FIG. 9 is a diagram for explaining a viewing angle according to an embodiment of the present disclosure.
- the processor 130 may identify the viewing angle based on sensing data received from the sensor.
- the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold.
- the processor 130 is located adjacent to the left direction and the right direction based on the moving direction (e.g., traveling direction) of the robot device 100 based on the image data received from the camera.
- An object eg, obstacle 10 can be identified.
- the processor 130 may identify the viewing angle of the robotic device 100 based on the identified object. If the identified viewing angle is less than the threshold angle, the processor 130 according to one embodiment may identify the reliability value of the area corresponding to the location estimated from the received image data as less than the threshold.
- the processor 130 receives information from the camera. It may be difficult to identify geometric characteristics of an object, photometric characteristics of an object, etc. from the image data.
- the processor 130 determines if the geometric characteristics of the object are not identified from each of the first image data included in the first sensing data and the second image data included in the second sensing data (or, identification (if it is difficult to do so), movement information of the robot device 100 from time t to time t+1 may not be obtained. Accordingly, the processor 130 may fail to estimate the location within the map of the robotic device 100.
- the processor 130 determines whether common points/similarities are identified between the geometric features of the object obtained from each of the first image data included in the first sensing data and the second image data included in the second sensing data. (or if it is difficult to identify), there is a low probability that the position estimated from the movement information of the robot device 100 from time t to time t+1 matches the actual position of the robot device 100. Accordingly, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the processor 130 acquires movement information based on the number of rotations of the wheel included in the driving unit, the rotation speed of the wheel, etc., in addition to the sensing data received from the sensor 120. Of course it is possible.
- the processor 130 acquires movement information of the robot device 100 from time t to time t+1, and includes the movement direction, movement distance, and movement of the robot device 100 included in the identified movement information. If at least one of the speeds is identified as being impossible to perform by the driving unit provided in the robot device 100, the reliability value of the area corresponding to the estimated position may be identified as less than the threshold value.
- the driving unit provided in the robot device 100 can only move forward or backward, and the robot device 100 moves left or right depending on the movement direction of the robot device 100 included in the identified movement information.
- the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the maximum speed of the driving unit provided in the robot device 100 is 5 m/s, and the robot device moves at 10 m/s according to the movement distance and movement speed of the robot device 100 included in the identified movement information. If identified, the processor 130 may identify the reliability value of the area corresponding to the estimated location as less than the threshold value.
- the processor 130 may identify the movement path based on the map and the reliability value map. Specifically, the processor 130 may identify the movement path to include at least one area corresponding to a reliability value greater than or equal to a threshold value based on the reliability value corresponding to each of the plurality of areas included in the map.
- the processor 130 may identify a movement path to bypass at least one area corresponding to a reliability value less than a threshold based on the reliability value corresponding to each of the plurality of areas included in the map.
- the processor 130 acquires a reliability value while the robot device 100 moves along a movement path, and of course, may update the reliability value map based on the obtained reliability value.
- the sensor 120 includes a LiDAR sensor, and the processor 130 determines the orientation of the LiDAR sensor in any one of a plurality of areas based on sensing data received from the LiDAR sensor. Error values can be identified.
- the processor 130 may adjust the direction of the LIDAR sensor based on the error value while the robot device 100 moves through one area along the movement path.
- the covariance and error values of the sensing data of the LiDAR sensor may be different depending on the direction in which the LiDAR sensor emits a laser beam at the same location.
- the processor 130 determines the orientation of the LiDAR sensor in which the Covariance value and Error value decrease when moving a specific area based on the sensing data received from the LiDAR sensor. can be identified.
- the processor 130 does not match the movement direction of the robot device 100 and the direction of the LiDAR sensor (i.e., the direction of emitting the laser beam), but rather uses the covariance (The direction of the LiDAR sensor can be adjusted to emit the laser beam in a direction that reduces covariance and error values.
- the direction in which the robot device 100 moves and the direction in which the LIDAR sensor emits the laser beam may be the same or different.
- the probability that the estimated location matches the actual location increases, and is included in the point cloud data. As the number of points increases, the probability that the estimated location matches the actual location increases. Additionally, as the object adjacent to the robot device 100 is a static object rather than a dynamic object, the probability that the estimated position matches the actual position increases.
- the probability that the estimated position matches the actual position increases, and the probability of the object included in the image data is increased.
- the probability that the estimated location matches the actual location increases.
- the probability that the estimated position matches the actual position increases.
- the robot device 100 moves adjacent to a static object (e.g., wall, furniture, home appliance, etc.) in space. You can do this, and you can move dynamic objects by bypassing them.
- a static object e.g., wall, furniture, home appliance, etc.
- the robot device 100 is moved in a space by bypassing a narrow passage (Path) or the sensor 120 is used when moving through a narrow passage.
- the detection direction eg, orientation of the lidar sensor
- the detection direction may not match the movement direction of the robot device 100.
- the robot device 100 includes a communication interface.
- the communication interface receives various data as input.
- communication interfaces include AP-based Wi-Fi (Wireless LAN network), Bluetooth, Zigbee, wired/wireless LAN (Local Area Network), WAN (Wide Area Network), and Ethernet ( 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, Input various data from at least one external device installed in the home, an external storage medium (e.g., USB memory), an external server (e.g., web hard drive, streaming server), etc. through a communication method such as Coaxial. You can receive it.
- an external storage medium e.g., USB memory
- an external server e.g., web hard drive, streaming server
- a communication method such as Coaxial. You can receive it.
- Figure 10 is a flowchart for explaining a control method of a robot device according to an embodiment of the present disclosure.
- a method for controlling a robot device including a map corresponding to the space where the robot device is located and a reliability value corresponding to each of a plurality of areas included in the map includes, first, a plurality of areas. Based on the reliability values corresponding to each, at least one area corresponding to a reliability value greater than or equal to a threshold value is identified (S1010).
- the movement path of the robot device in space is identified based on the at least one identified area (S1020).
- a control method includes estimating one of a plurality of areas as the location of the robot device based on sensing data from a sensor of the robot device, and determining the probability that the estimated location matches the actual location of the robot device.
- a step of obtaining a reliability value may be further included.
- the estimating step includes, when first sensing data and second sensing data are continuously received from the sensor, obtaining movement information of the robot device based on the first sensing data and second sensing data and based on the movement information. This may include estimating the location of the robot device corresponding to the second sensing data.
- the step of obtaining the probability includes combining the point cloud based on the first point cloud data included in the first sensing data received from the lidar sensor and the second point cloud data included in the second sensing data, and If the combination fails, it may include obtaining a reliability value less than a threshold value.
- Obtaining a probability includes identifying a dynamic object based on first image data included in first sensing data and second image data included in second sensing data received from a camera, and identifying the dynamic object. If the number of dynamic objects is greater than or equal to the threshold, the method may include obtaining a reliability value that is less than the threshold.
- Obtaining the probability includes identifying the viewing angle of the camera based on image data included in sensing data received from the camera, and if the identified viewing angle is less than the threshold angle, obtaining a reliability value less than the threshold value. It may include steps.
- Obtaining the probability includes obtaining a reliability value less than a threshold when at least one of the movement direction, movement distance, and movement speed of the robot device included in the movement information is identified as being impossible to perform in the robot device. may include.
- the control method according to an example may further include updating a reliability value corresponding to one of the plurality of areas based on the obtained reliability value.
- a control method includes identifying an error value according to the pose of a LiDAR sensor in one of a plurality of areas based on sensing data received from a LiDAR sensor and a movement path. Accordingly, the step of adjusting the posture of the lidar sensor based on the error value while the robot device moves in one area may be further included.
- Step S1020 of identifying a movement path includes, when an area corresponding to a reliability value less than a threshold value is identified based on the reliability value corresponding to each of the plurality of areas, identifying a movement route to bypass the identified area. May include steps.
- embodiments described above may be implemented in a recording medium that can be read by a computer or similar device using software, hardware, or a combination thereof.
- embodiments described herein may be implemented with a processor itself.
- embodiments such as 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.
- computer instructions for performing processing operations of the robot device according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium.
- the computer instructions stored in such a non-transitory computer-readable medium when executed by a processor of a specific device, cause the specific device to perform processing operations in the audio output device 100 according to the various embodiments described above.
- a non-transitory computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as registers, caches, and memories.
- Specific examples of non-transitory computer-readable media may include CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Human Computer Interaction (AREA)
- Optics & Photonics (AREA)
- Multimedia (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Electromagnetism (AREA)
Abstract
Description
Claims (15)
- 로봇 장치에 있어서,적어도 하나의 인스트럭션을 저장하는 적어도 하나의 메모리;상기 로봇 장치의 환경을 센싱하고, 센싱 데이터를 출력하는 센서; 및상기 적어도 하나의 인스트럭션을 실행함으로써,상기 센서로부터 수신된 상기 센싱 데이터에 기초하여 상기 로봇 장치가 위치하는 공간에 대응되는 맵(Map) 및 상기 맵의 복수의 영역 각각의 신뢰도 값을 획득하며,상기 맵 및 상기 복수의 영역 각각의 신뢰도 값을 상기 적어도 하나의 메모리에 저장하며,상기 복수의 영역 각각에 대응되는 신뢰도 값에 기초하여 임계 값 이상의 신뢰도 값에 대응되는 적어도 하나의 영역을 식별하며,상기 식별된 적어도 하나의 영역에 기초하여 상기 공간에 대한 상기 로봇 장치의 이동 경로를 식별하는, 로봇 장치.
- 제1항에 있어서,상기 하나 이상의 프로세서는,상기 센싱 데이터에 기초하여, 상기 복수의 영역 중 일 영역을 상기 로봇 장치의 위치로 추정하고,상기 추정된 위치와 상기 로봇 장치의 실제 위치가 일치할 확률을 판단하여 상기 로봇 장치의 상기 추정된 위치에 대응되는 추정된 신뢰도 값을 획득하는, 로봇 장치.
- 제2항에 있어서,상기 하나 이상의 프로세서는,상기 센서로부터 연속적으로 수신된 제1 센싱 데이터 및 제2 센싱 데이터에 기초하여 상기 로봇 장치의 이동 정보를 획득하며,상기 이동 정보에 기초하여 상기 제2 센싱 데이터에 대응되는 상기 로봇 장치의 새로운 위치를 추정하는, 로봇 장치.
- 제3항에 있어서,상기 센서는,라이다(LiDAR) 센서를 포함하며,상기 제1 센싱 데이터는, 상기 라이다 센서로부터 수신된 제1 포인트 클라우드 데이터를 포함하며,상기 제2 센싱 데이터는, 상기 라이다 센서로부터 수신된 제2 포인트 클라우드 데이터를 포함하며,상기 하나 이상의 프로세서는,상기 제1 포인트 클라우드 데이터와 상기 제2 포인트 클라우드 데이터에 기초하여 복수의 포인트 클라우드를 결합하는 동작을 수행하며,상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하고,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 로봇 장치.
- 제3항에 있어서,상기 센서는,카메라;를 포함하며,상기 카메라로부터 수신된 상기 제1 센싱 데이터는 제1 이미지 데이터를 포함하고,상기 카메라로부터 수신된 상기 제2 센싱 데이터는 제2 이미지 데이터를 포함하고,상기 하나 이상의 프로세서는,상기 제1 이미지 데이터 및 상기 제2 이미지 데이터에 기초하여 동적 오브젝트를 식별하고,상기 동적 오브젝트의 개수가 임계 개수 이상이면, 상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하고,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 로봇 장치.
- 제3항에 있어서,상기 센서는,카메라;를 포함하며,상기 카메라로부터 수신된 센싱 데이터는, 이미지 데이터를 포함하고,상기 하나 이상의 프로세서는,상기 이미지 데이터에 기초하여 상기 카메라의 시야각을 식별하고,상기 시야각이 임계 각 미만이면, 상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하고,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 로봇 장치.
- 제3항에 있어서,상기 이동 정보는,상기 로봇 장치의 이동 방향, 상기 로봇 장치의 이동 거리, 또는 상기 로봇 장치의 이동 속도를 포함하며,상기 하나 이상의 프로세서는,상기 이동 정보에 포함된 상기 로봇 장치의 상기 이동 방향, 상기 이동 거리, 및 상기 이동 속도 중 적어도 하나를 유지하기 불가능한 것으로 식별되면, 상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하고,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 로봇 장치.
- 제2항에 있어서,상기 하나 이상의 프로세서는,상기 획득된 신뢰도 값에 기초하여 상기 복수의 영역 중 일 영역에 대응되는 상기 신뢰도 값을 업데이트하는, 로봇 장치.
- 제2항에 있어서,상기 센서는,라이다(LiDAR) 센서를 포함하며,상기 하나 이상의 프로세서는,상기 라이다 센서로부터 수신된 센싱 데이터에 기초하여 상기 복수의 영역 중 일 영역에서 상기 라이다 센서의 방향(Orientation)에 따른 에러(Error) 값을 식별하고,상기 복수의 영역 중 상기 일 영역 내를 상기 이동 경로에 따라 상기 로봇 장치가 이동하는 동안에 상기 에러 값에 기초하여 상기 라이다 센서의 방향을 조정하는, 로봇 장치.
- 제1항에 있어서,상기 하나 이상의 프로세서는,상기 복수의 영역 중 일 영역이 상기 임계 값 미만의 신뢰도 값을 가지는 것으로 식별되면, 상기 식별된 영역을 우회하도록 상기 이동 경로를 수정(modify)하는, 로봇 장치.
- 로봇 장치의 제어 방법에 있어서,복수의 영역을 포함하며, 상기 복수의 영역 각각은 대응되는 신뢰도 값을 포함하는, 상기 로봇 장치가 위치한 공간의 맵을 획득하는 단계;상기 복수의 영역 각각에 대응되는 신뢰도 값에 기초하여 임계 값 이상의 신뢰도 값에 대응되는, 상기 복수의 영역 중 적어도 하나의 영역을 식별하는 단계; 및,상기 적어도 하나의 영역에 기초하여 상기 공간에 대한 상기 로봇 장치의 이동 경로를 식별하는 단계;를 포함하는, 제어 방법.
- 제11항에 있어서,상기 로봇 장치의 센서의 센싱 데이터에 기초하여 상기 복수의 영역 중 일 영역을 상기 로봇 장치의 위치로 추정하는 단계; 및상기 추정된 위치와 상기 로봇 장치의 실제 위치가 일치할 확률을 판단하여 상기 로봇 장치의 상기 추정된 위치에 대응되는 추정된 신뢰도 값을 획득하는 단계;를 더 포함하는, 제어 방법.
- 제12항에 있어서,상기 추정하는 단계는,상기 센서로부터 연속적으로 수신된 제1 센싱 데이터 및 제2 센싱 데이터에 기초하여 상기 로봇 장치의 이동 정보를 획득하는 단계; 및상기 이동 정보에 기초하여 상기 제2 센싱 데이터에 대응되는 상기 로봇 장치의 새로운 위치를 추정하는 단계;를 포함하는, 제어 방법.
- 제13항에 있어서,상기 센서는, 라이다(LiDAR) 센서를 포함하며,상기 제1 센싱 데이터는, 상기 라이다 센서로부터 수신된 제1 포인트 클라우드 데이터를 포함하며,상기 제2 센싱 데이터는, 상기 라이다 센서로부터 수신된 제2 포인트 클라우드 데이터를 포함하며,상기 추정된 신뢰도 값을 획득하는 단계는,상기 제1 포인트 클라우드 데이터와 상기 제2 포인트 클라우드 데이터에 기초하여 복수의 포인트 클라우드를 결합하는 동작을 수행하는 단계; 및상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하는 단계;를 포함하며,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 제어 방법.
- 제13항에 있어서,상기 센서는, 상기 카메라를 포함하며,상기 카메라로부터 수신된 상기 제1 센싱 데이터는, 제1 이미지 데이터를 포함하고,상기 카메라로부터 수신된 상기 제2 센싱 데이터는, 제2 이미지 데이터를 포함하고,상기 추정된 신뢰도 값을 획득하는 단계는,상기 제1 이미지 데이터 및 상기 제2 이미지 데이터에 기초하여 동적 오브젝트를 식별하는 단계; 및상기 동적 오브젝트의 개수가 임계 개수 이상이면, 상기 로봇 장치의 상기 새로운 위치에 대응되는 업데이트된 신뢰도 값을 획득하는 단계;를 포함하고,상기 업데이트된 신뢰도 값은, 상기 임계 값 미만인, 제어 방법.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP23857609.4A EP4512580B1 (en) | 2022-08-23 | 2023-08-07 | Robotic device for identifying movement path using reliability values, and method for controlling same |
| CN202380053799.8A CN119562883A (zh) | 2022-08-23 | 2023-08-07 | 使用可靠性值识别移动路径的机器人装置及其控制方法 |
| US18/238,902 US20240069563A1 (en) | 2022-08-23 | 2023-08-28 | Robot device for identifying movement path using reliability value and control method thereof |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2022-0105742 | 2022-08-23 | ||
| KR1020220105742A KR20240027473A (ko) | 2022-08-23 | 2022-08-23 | 신뢰도 값을 이용하여 이동 경로를 식별하는 로봇 장치 및 그 제어 방법 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US18/238,902 Continuation US20240069563A1 (en) | 2022-08-23 | 2023-08-28 | Robot device for identifying movement path using reliability value and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024043575A1 true WO2024043575A1 (ko) | 2024-02-29 |
Family
ID=90013516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2023/011579 Ceased WO2024043575A1 (ko) | 2022-08-23 | 2023-08-07 | 신뢰도 값을 이용하여 이동 경로를 식별하는 로봇 장치 및 그 제어 방법 |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR20240027473A (ko) |
| WO (1) | WO2024043575A1 (ko) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110038962A (ko) * | 2009-10-09 | 2011-04-15 | 한양대학교 산학협력단 | 물체의 공간적 의미정보를 이용한 로봇의 능동적 자기위치 추정 방법 |
| JP2014203144A (ja) * | 2013-04-02 | 2014-10-27 | パナソニック株式会社 | 自律移動装置 |
| JPWO2013002067A1 (ja) * | 2011-06-29 | 2015-02-23 | 株式会社日立産機システム | 移動ロボット、及び移動体に搭載される自己位置姿勢推定システム |
| JP2017188066A (ja) * | 2016-04-01 | 2017-10-12 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 自律移動体システム |
| JP2020166702A (ja) * | 2019-03-29 | 2020-10-08 | 日本電産シンポ株式会社 | 移動体システム、地図作成システム、経路作成プログラムおよび地図作成プログラム |
-
2022
- 2022-08-23 KR KR1020220105742A patent/KR20240027473A/ko active Pending
-
2023
- 2023-08-07 WO PCT/KR2023/011579 patent/WO2024043575A1/ko not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110038962A (ko) * | 2009-10-09 | 2011-04-15 | 한양대학교 산학협력단 | 물체의 공간적 의미정보를 이용한 로봇의 능동적 자기위치 추정 방법 |
| JPWO2013002067A1 (ja) * | 2011-06-29 | 2015-02-23 | 株式会社日立産機システム | 移動ロボット、及び移動体に搭載される自己位置姿勢推定システム |
| JP2014203144A (ja) * | 2013-04-02 | 2014-10-27 | パナソニック株式会社 | 自律移動装置 |
| JP2017188066A (ja) * | 2016-04-01 | 2017-10-12 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 自律移動体システム |
| JP2020166702A (ja) * | 2019-03-29 | 2020-10-08 | 日本電産シンポ株式会社 | 移動体システム、地図作成システム、経路作成プログラムおよび地図作成プログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20240027473A (ko) | 2024-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2014297039B2 (en) | Auto-cleaning system, cleaning robot and method of controlling the cleaning robot | |
| WO2018135870A1 (en) | Mobile robot system and control method thereof | |
| WO2018043957A1 (en) | Robot cleaner | |
| WO2018128353A1 (en) | Robot cleaner and method for controlling thereof | |
| WO2017091008A1 (ko) | 이동 로봇 및 그 제어 방법 | |
| WO2011013862A1 (ko) | 이동 로봇의 위치 인식 및 주행 제어 방법과 이를 이용한 이동 로봇 | |
| WO2017008224A1 (zh) | 一种移动物体的距离检测方法、装置及飞行器 | |
| WO2020046038A1 (ko) | 로봇 및 그의 제어 방법 | |
| WO2019098631A1 (en) | Moving apparatus for cleaning and control method thereof | |
| WO2016200098A1 (ko) | 이동 로봇 및 그 제어방법 | |
| WO2022186598A1 (ko) | 로봇 청소기 및 이의 제어 방법 | |
| WO2020141900A1 (ko) | 이동 로봇 및 그 구동 방법 | |
| WO2022154242A1 (ko) | 로봇 및 그 제어 방법 | |
| WO2020196948A1 (ko) | 인공 지능 청소기 및 그의 동작 방법 | |
| WO2024090942A1 (ko) | 다수의 카메라들에 의해 촬영된 객체를 나타내는 영상을 증강하여 신경망 모델을 학습시키는 방법 및 전자 장치 | |
| WO2024043575A1 (ko) | 신뢰도 값을 이용하여 이동 경로를 식별하는 로봇 장치 및 그 제어 방법 | |
| EP3562369A2 (en) | Robot cleaner and method of controlling the same | |
| WO2020138954A1 (ko) | 이동 로봇 및 이동 로봇의 제어방법 | |
| WO2021215668A1 (ko) | 로봇 장치 및 그 제어 방법 | |
| WO2025029111A1 (ko) | 발광부를 포함하는 로봇 청소기 및 그 제어 방법 | |
| WO2021149874A1 (en) | Robot cleaner and method for controlling the same | |
| WO2025089842A1 (ko) | 대상 영역에 대한 촬영 이미지를 이용하여 공간 맵을 생성하는 방법 및 이를 수행하기 위한 전자 장치 | |
| WO2024034855A1 (ko) | 마스크 맵을 이용하여 주행을 수행하는 로봇 및 그의 주행 방법 | |
| WO2023027341A1 (ko) | 로봇 및 로봇의 제어 방법 | |
| WO2023219253A1 (ko) | 로봇 및 그 제어 방법 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23857609 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2023857609 Country of ref document: EP Ref document number: 23 857 609.4 Country of ref document: EP |
|
| ENP | Entry into the national phase |
Ref document number: 2023857609 Country of ref document: EP Effective date: 20241120 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202380053799.8 Country of ref document: CN |
|
| WWP | Wipo information: published in national office |
Ref document number: 202380053799.8 Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2023857609 Country of ref document: EP |