公开(公告)号：US11188753B2

公开(公告)日：2021-11-30

申请号：US15931724

申请日：2020-05-14

Applicant: LG ELECTRONICS INC.

Inventor： Sookhyun Yang ,  Jungsik Kim ,  Gyuho Eoh

IPC: G06K9/00 ,  G06T7/11 ,  G05D1/02 ,  G01S19/01 ,  G06T7/70

Abstract: A robot and/or a computer system may be used to generate position information of the robot operating in an operating space that is subdivided into a plurality of cells. The robot includes a sensor configured to acquire data related to the operating space. A memory of the robot and/or the computer server may store information regarding at least two of the cells and an indicator of a position information acquisition technique used to generate position information of the robot in a cell. The controller may be configured to acquire information related to a cell that the robot is positioned in and generate the position information of the robot based on the position information acquisition technique, the sensor data, and the cell information.

公开(公告)号：US20210229291A1

公开(公告)日：2021-07-29

申请号：US17098832

申请日：2020-11-16

Applicant: LG ELECTRONICS INC.

Inventor： Sookhyun YANG ,  Jungsik Kim ,  Jinuh Joo ,  Hyoungrock Kim ,  Sang Ki Kim ,  Minjung Kim ,  Moonsik Nam ,  Gyuho Eoh ,  Donghak Lee

IPC: B25J9/16

Abstract: A robot may include an input interface configured to obtain an image of a surrounding environment of the robot, and at least one processor configured to rotate the robot in place for localization, and estimate at least one of a position or a pose in a space, based on a plurality of sequential images obtained by the input interface during the rotation of the robot. The position or the pose of the robot may be estimated based on inputting the plurality of sequential images obtained during the rotation of the robot into a trained model based on an artificial neural network. In a 5G environment connected for the Internet of Things, embodiments of the present disclosure may execute an artificial intelligence algorithm and/or a machine learning algorithm.

公开(公告)号：US11858149B2

公开(公告)日：2024-01-02

申请号：US17098832

申请日：2020-11-16

Applicant: LG ELECTRONICS INC.

Inventor： Sookhyun Yang ,  Jungsik Kim ,  Jinuh Joo ,  Hyoungrock Kim ,  Sang Ki Kim ,  Minjung Kim ,  Moonsik Nam ,  Gyuho Eoh ,  Donghak Lee

IPC: B25J9/16

CPC classification number: B25J9/1697 ,  B25J9/1664

Abstract: A robot may include an input interface configured to obtain an image of a surrounding environment of the robot, and at least one processor configured to rotate the robot in place for localization, and estimate at least one of a position or a pose in a space, based on a plurality of sequential images obtained by the input interface during the rotation of the robot. The position or the pose of the robot may be estimated based on inputting the plurality of sequential images obtained during the rotation of the robot into a trained model based on an artificial neural network. In a 5G environment connected for the Internet of Things, embodiments of the present disclosure may execute an artificial intelligence algorithm and/or a machine learning algorithm.

公开(公告)号：US11709499B2

公开(公告)日：2023-07-25

申请号：US16660010

申请日：2019-10-22

Applicant: LG ELECTRONICS INC.

Inventor： Gyuho Eoh ,  Seungwook Lim ,  Dongki Noh

IPC: G05D1/02 ,  B25J9/00 ,  B25J9/16 ,  B25J13/08 ,  G06V10/764 ,  G06V10/44 ,  G06V20/10

CPC classification number: G05D1/0274 ,  B25J9/0003 ,  B25J9/163 ,  B25J9/1697 ,  B25J13/089 ,  G05D1/0246 ,  G06V10/44 ,  G06V10/454 ,  G06V10/764 ,  G06V20/10

Abstract: A controlling method for an artificial intelligence moving robot according to an aspect of the present disclosure includes: checking nodes within a predetermined reference distance from a node corresponding to a current position; determining whether there is a correlation between the nodes within the reference distance and the node corresponding to the current position; determining whether the nodes within the reference distance are nodes of a previously learned map when there is no correlation; and registering the node corresponding to the current position on the map when the nodes within the reference distance are determined as nodes of the previously learned map, thereby being able to generate a map in which the environment of a traveling section and environmental changes are appropriately reflected.

公开(公告)号：US11579626B2

公开(公告)日：2023-02-14

申请号：US16764377

申请日：2019-05-30

Applicant: LG ELECTRONICS INC.

Inventor： Gyuho Eoh ,  Jungsik Kim ,  Hyoungrock Kim ,  Dong Ki Noh ,  Joongtae Park

IPC: G05D1/02 ,  G06T7/579

Abstract: Disclosed herein are a method of localization by synchronizing multi sensors and a robot implementing the same. The robot according to an embodiment includes a controller that, when a first sensor acquires first type information, generates first type odometry information using the first type information, that, at a time point when the first type odometry information is generated, acquires second type information by controlling a second sensor and then generates second type odometry information using the second type information, and that the robot by combining the first type odometry information and the second type odometry information.

公开(公告)号：US11348276B2

公开(公告)日：2022-05-31

申请号：US16830964

申请日：2020-03-26

Applicant: LG ELECTRONICS INC.

Inventor： Dongki Noh ,  Jaekwang Lee ,  Seungwook Lim ,  Gyuho Eoh

IPC: G06T7/73 ,  G06T7/20

Abstract: A mobile robot and a method of controlling the mobile robot are disclosed. The method includes acquiring an image of an inside of a traveling zone. The method further includes performing a point-based feature point extraction by extracting a first feature point from the acquired image. The method also includes performing a block-based feature point extraction by dividing the acquired image into blocks having a predetermined size and extracting a second feature point from each of the divided block-unit images. The method also includes determining the current location by performing a point-based feature point matching using the first feature point and performing a block-based feature point using the second feature point. The method also includes storing the determined current location in association with the first feature point and the second feature point in a map.

公开(公告)号：US11119501B2

公开(公告)日：2021-09-14

申请号：US16225515

申请日：2018-12-19

Applicant: LG ELECTRONICS INC.

Inventor： Gyuho Eoh ,  Dongki Noh ,  Taekyeong Lee ,  Seungwook Lim

IPC: G05D1/00 ,  G05D1/02 ,  G06F16/29 ,  G01C21/32

Abstract: A method of controlling a moving-robot includes creating a plurality of maps having different generation-time information through a plurality of driving processes; choosing any one of the plurality of maps according to a certain map choosing algorithm based on current time information and the generation-time information, and attempting location recognition based on the chosen map.

公开(公告)号：US11010916B2

公开(公告)日：2021-05-18

申请号：US16550392

申请日：2019-08-26

Applicant: LG ELECTRONICS INC.

Inventor： Gyuho Eoh ,  Jungsik Kim

IPC: G06T7/00 ,  G06T7/70 ,  G06T7/80 ,  G05D1/00 ,  G05D1/02 ,  H04N5/225 ,  H04N5/232 ,  H04N5/247

Abstract: Disclosed herein are a method of configuring a camera position suitable for localization and a robot implementing the same, and the robot according to an embodiment, which configures a camera position suitable for localization, calculates a first SLAM index with respect to an image captured by a first camera sensor on a mounting unit, and calculates a second SLAM index by changing a position of the first camera sensor along the mounting unit, or selects any one of the first SLAM index and the second SLAM index by calculating the second SLAM index with respect to an image captured by a second camera sensor disposed in the mounting unit.