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.

Abstract: Provided herein are a method of extracting a feature from an image using a laser pattern and an identification device and a robot including the same, and the identification device for extracting a feature from an image using a laser pattern, which includes a first camera coupled to a laser filter and configured to generate a first image including a pattern of a laser which is reflected from an object, a second camera configured to capture an area overlapping an area captured by the first camera to generate a second image, and a controller configured to generate a mask for distinguishing an effective area using the pattern included in the first image and extract a feature from the second image by applying the mask to the second image.

Abstract: Disclosed herein are a method of acquiring an image for recognizing a position and a robot implementing the same. In the method and robot, information value concerning movement of the robot is measured to efficiently acquire images including overlapped areas, and lenses of cameras on both sides of the robot are slided in a direction opposite to a direction of movement of the robot based on the measured information value concerning movement.

Abstract: 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.

Abstract: Provided herein are a method of extracting a feature from an image using a laser pattern and an identification device and a robot including the same, and the identification device for extracting a feature from an image using a laser pattern, which includes a first camera coupled to a laser filter and configured to generate a first image including a pattern of a laser which is reflected from an object, a second camera configured to capture an area overlapping an area captured by the first camera to generate a second image, and a controller configured to generate a mask for distinguishing an effective area using the pattern included in the first image and extract a feature from the second image by applying the mask to the second image.

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.

Abstract: 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.

Abstract: Disclosed herein are a method of acquiring an image for recognizing a position and a robot implementing the same. In the method and robot, information value concerning movement of the robot is measured to efficiently acquire images including overlapped areas, and lenses of cameras on both sides of the robot are slided in a direction opposite to a direction of movement of the robot based on the measured information value concerning movement.