Lg Electronics Inc.

Sookhyun Yang

Minjung Kim

Jaeyoung Lee

JungSik Kim

Gyuho Eoh

Hyoungrock Kim

Donghak Lee

Joongtae Park

Dong Ki Noh

Jiyoung Huh

Moonsik Nam

Sang Ki Kim

Jinuh Joo

Donghi Sim

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.

Localization of robot

The present disclosure relates to a method for performing simultaneous localization and mapping (SLAM) with respect to a salient object in an image, a robot and a cloud server for implementing such method. According to an embodiment of the present disclosure, a robot includes a camera sensor configured to capture one or more images for the robot to perform the SLAM with respect to a salient object for estimating a location of the robot within the space, a map storage configured to store the information for the robot to perform the SLAM, and a controller that is configured to: detect an object from the captured image; select, as a specific salient object for identifying the space, the detected object verified as corresponding to the specific salient object; and store, in the map storage, the selected specific salient object and coordinate information related to the selected specific salient object.

Method of performing simultaneous localization and mapping with respect to a salient object in an image

Provided are a method for drawing a map of a specific area, a robot and an electronic device that implement such a method. According to the present disclosure, the method, the robot, and the electronic device improve quality of the drawn map by moving the robot so that loop closing is performed many times when the map is drawn. To this end, an accumulated moving distance from a first position and a second position of the robot moving in the specific area is measured, and when the loop closing is not performed at the second position, whether the loop closing is required at the second position is determined based on the measured accumulated moving distance and information on matching of feature points at the second position, and a movement of the robot is controlled based on a result of the determination.

Method for drawing map of specific area, robot and electronic device implementing thereof

Provided are a method of performing cloud simultaneous localization and mapping (SLAM), and a robot and a cloud server for performing the same, and a robot for performing cloud SLAM in real time includes a first sensor configured to acquire sensor data necessary to perform the SLAM, a map storage unit configured to store a map synchronized with a cloud server, a communication unit configured to transmit the sensor data, a feature, or a last frame to the cloud server and receive a local map patch or a global pose from the cloud server, and a control unit configured to generate the sensor data, the feature extracted from the sensor data, or the last frame and control movement of the robot using the local map patch or the global pose received from the cloud server.

Method of performing cloud slam in real time, and robot and cloud server for implementing the same

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.

Method of using a heterogeneous position information acquisition mechanism in an operating space and robot and cloud server implementing the same

Growing community of inventors

Seoul, South Korea

Sookhyun Yang