Abstract: A method of initially estimating a front view portion of a photographed image and separating the photographed image into a front view and a background without user interaction and apparatus performing the method are provided. The method of separating a front view and a background of an image includes dividing one or more pixels included in a photographed image into pixel groups according to color similarity between the pixels, estimating the position of the front view in the image divided into the pixel groups, and separating the front view and the background based on the estimated position of the front view. The method automatically separates the front view and the background of the image without a user input.

Abstract: A method for estimating a connection order of modules in a robot including the modules each having a joint as a basic unit. Since a device and a program are connected by software and thus a joint and program are connected by software, it is possible for a user to control robot joints without being aware of the connection relationship between the devices and the joints in the modular robot in which the plurality of modules each including a movable joint as a basic unit is connected.

Abstract: A vital sign measurement robot which automatically measures vital signs, and a control method thereof. The vital sign measurement robot includes an input unit to receive vital sign measurement instructions, an image recognition unit to detect a distance between the robot and a person, vital signs of whom are to be measured, and a measurement portion of the body of the person, when the vital sign measurement instructions are received, a control unit to move electrodes provided on hands so as to locate the electrodes at the measurement portion of the body of the person, when the distance between the robot and the person and the measurement portion of the body of the person are detected, and a vital sign measurement unit to measure a vital sign, when the electrodes are located at the measurement portion of the body of the person.

Abstract: A system and method for extracting 3D coordinates, the method includes obtaining, by a stereoscopic image photographing unit, two images of a target object, and obtaining 3D coordinates of the object on the basis of coordinates of each pixel of the two images, measuring, by a Time of Flight (TOF) sensor unit, a value of a distance to the object, and obtaining 3D coordinates of the object on the basis of the measured distance value, mapping pixel coordinates of each image to the 3D coordinates obtained through the TOF sensor unit, and calibrating the mapped result, determining whether each set of pixel coordinates and the distance value to the object measured through the TOF sensor unit are present, calculating a disparity value on the basis of the distance value or the pixel coordinates, and calculating 3D coordinates of the object on the basis of the calculated disparity value.

Abstract: A method to control medical equipment that moves along at least one axis or performs joint movement is provided. While the medical equipment is passively moved as operated by the operator, the operation intention of the operator is determined using a force sensor, a torque sensor, or the like, and motor control is performed taking into consideration the determined operation intention to reduce load (or drive power) of the operator. To accomplish this, the method determines a direction and magnitude of force that an operator applies to the medical equipment to move the medical equipment and generates auxiliary force having a magnitude proportional to the force applied by the operator and having the same direction as the direction of the force applied by the operator such that the medical equipment is easily moved.

Abstract: A bumper structure of a cleaning robot which detects whether or not an obstacle contacts a bumper and a position of the obstacle, allows the bumper to be simply process and reduces the number of components of the cleaning robot to lower the production costs of the cleaning robot. The bumper structure includes a main body, a bumper installed on the front surface of the main body, a resistance film provided between the main body and the bumper and fixed to the main body, and a metal film provided between the main body and the bumper and fixed to the bumper such that the shape of the metal film is deformed together with the bumper and the metal film comes into contact with the resistance film when at least one obstacle contacts the bumper, so as to measure resistance values.

Abstract: A robot control method and apparatus estimates an error based on information of an object obtained using a motor drive current sensor, a force sensor or a tactile sensor mounted at a robot hand and information of the object obtained using an optical sensor and compensates for the error. The robot control method and apparatus includes measuring information of an object using an optical sensor or calculating information of the object input by a user, moving a robot hand to the object based on the information of the object, controlling the thumb and fingers of the robot hand to contact the object based on the information of the object, determining whether the thumb and fingers have contacted the object through a motor drive current sensor, a force sensor or a tactile sensor, and grasping the object depending upon whether the thumb and the fingers have contacted the object.

Abstract: An apparatus and method for estimating a three-dimensional face position. The method of estimating the three-dimensional face position includes acquiring two-dimensional image information from a single camera, detecting a face region of a user from the two-dimensional image information, calculating the size of the detected face region, estimating a distance between the single camera and the user's face using the calculated size of the face region, and obtaining positional information of the user's face in a three-dimensional coordinate system using the estimated distance between the single camera and the user's face. Accordingly, it is possible to estimate the distance between the user and the single camera using the size of the face region of the user in the image information acquired by the single camera so as to acquire the three-dimensional position coordinates of the user.

Abstract: A volume cell (VOXEL) map generation apparatus includes an inertia measurement unit to calculate inertia information by calculating inertia of a volume cell (VOXEL) map generator, a Time of Flight (TOF) camera to capture an image of an object, thereby generating a depth image of the object and a black-and-white image of the object, an estimation unit to calculate position and posture information of the VOXEL map generator by performing an Iterative Closest Point (ICP) algorithm on the basis of the depth image of the object, and to recursively estimate a position and posture of the VOXEL map generator on the basis of VOXEL map generator inertia information calculated by the inertia measurement unit and VOXEL map generator position and posture information calculated by the ICP algorithm, and a grid map construction unit to configure a grid map based on the recursively estimated VOXEL map generator position and posture.

Abstract: An object pose recognition apparatus and method. The object pose recognition method includes acquiring first image data of an object to be recognized and 3-dimensional (3D) point cloud data of the first image data, and storing the first image data and the 3D point cloud data in a database, receiving input image data of the object photographed by a camera, extracting feature points from the stored first image data and the input image data, matching the stored 3D point cloud data and the input image data based on the extracted feature points and calculating a pose of the photographed object, and shifting the 3D point cloud data based on the calculated pose of the object, restoring second image data based on the shifted 3D point cloud data, and re-calculating the pose of the object using the restored second image data and the input image data.

Abstract: A simultaneous localization and map building method of a mobile robot including an omni-directional camera. The method includes acquiring an omni-directional image from the omni-directional camera, dividing the obtained omni-directional image into upper and lower images according to a preset reference to generate a first image, which is the lower image, and a second image, which is the upper image, extracting feature points from the first image and calculating visual odometry information calculating visual odometry information to track locations of the extracted feature points based on a location of the omni-directional camera, and performing localization and map building of the mobile robot using the calculated visual odometry information and the second image as an input of an extended Kalman filter.

Abstract: A crosswalk walking assistance system to assist a pedestrian by moving a movable robot along with the pedestrian along a boundary of a crosswalk when the pedestrian crosses at the crosswalk, and a method of controlling the same. The crosswalk walking assistance system includes guide rails formed along boundary lines of a crosswalk, robots moving along the guide rails, and a controller connected to the guide rails.

Abstract: A moving robot and a method to build a map for the same, wherein a 3D map for an ambient environment of the moving robot may be built using a Time of Flight (TOF) camera that may acquire 3D distance information in real time. The method acquires 3D distance information of an object present in a path along which the moving robot moves, accumulates the acquired 3D distance information to construct a map of a specific level and stores the map in a database, and then hierarchically matches maps stored in the database to build a 3D map for a set space. This method may quickly and accurately build a 3D map for an ambient environment of the moving robot.

Abstract: An X-ray apparatus includes guide rails arranged along different axes, an X-ray tube movably mounted on at least one of the guide rails and adapted to be moved upon user force, motors provided at the guide rails to move the X-ray tube, a force detection unit to detect the user force, and a control unit to determine a direction of force and drive the motor provided at the guide rail on an axis corresponding to the determined direction. The X-ray apparatus may be easily moved based on force detection and velocity control of the motor, thereby achieving more precise and safe movement in a desired direction. Accordingly, the X-ray apparatus may provide rapid and efficient medical examination and treatment in hospitals.

Abstract: A walking robot and a control method in which conversion between walking servo control methods is stably carried out. The walking robot includes a sensor unit to measure angles and torques of joints, and a control unit to calculate voltages applied in a Finite State Machine (FSM) control mode and a Zero Moment Point (ZMP) control mode according to the angles and torques of the joints to drive respective joint motors, to store last target joint angles in the FSM control mode during conversion from the FSM control mode to the ZMP control mode, and to perform a motion based on the FSM control mode by substituting the last target joint angles in the FSM control mode for target joint angles in the FSM control mode during conversion from the ZMP control mode to the FSM control mode, thereby performing stable conversion between walking servo control modes without joint sagging.

Abstract: A 3D object tracking method and apparatus in which a model of an object to be tracked is divided into a plurality of polygonal planes and the object is tracked using texture data of the respective planes and geometric data between the respective planes to enable more precise tracking. The 3D object tracking method includes modeling the object to be tracked to generate a plurality of planes, and tracking the plurality of planes, respectively. The modeling of the object includes selecting points from among the plurality of planes, respectively, and calculating projective invariants using the selected points.

Abstract: A robot and a control method thereof. The robot has plural robot arms, each having at least one joint unit and a hand, and the control method includes dividing an object into target and feasible grasp regions and storing grasp policies respectively corresponding to the grasp regions, sensing respective orientations of the object, the at least one joint unit, and an obstacle, judging whether or not grasping of the target grasp region is feasible after sensing the orientations, generating a grasp route using the grasp policy for the target grasp region, upon judging that grasping of the target grasp region is feasible, and generating a grasp route using the grasp policy for one of the feasible grasp regions, upon judging that grasping of the target grasp region is not feasible, and controlling the at least one joint unit and the hand to trace the generated grasp route.

Abstract: A robot and a control method thereof. The robot has plural robot arms, each having at least one joint unit and a hand, and the control method includes calculating in advance and storing a plurality of grasp poses to generate grasp routes, sensing respective orientations of an object, the robot arms, and an obstacle, selecting one grasp pose from among the plurality of grasp poses by judging a movable angle range of the at least one joint unit, whether or not the object collides with the obstacle, and self-collision between the robot hands based on the sensed respective orientations, and generating grasp routes using the selected grasp pose. In the control method, the plurality of feasible grasp poses is calculated in advance and then stored, thereby rapidly and stably performing grasping of the object.

Abstract: A robot, which performs natural walking similar to a human with high energy efficiency through optimization of actuated dynamic walking, and a control method thereof. The robot includes an input unit to which a walking command of the robot is input, and a control unit to control walking of the robot by calculating torque input values through control variables, obtaining a resultant motion of the robot through calculation of forward dynamics using the torque input values, and minimizing a value of an objective function set to consist of the sum total of a plurality of performance indices through adjustment of the control variables.

Abstract: A method and apparatus to generate an object descriptor using extended curvature gabor filters. The method and apparatus may increase a recognition rate of even a relatively small image with use of an extended number of curvature gabor filters having controllable curvatures and may reduce the amount of calculation required for face recognition by performing the face recognition using only some of the extended curvature gabor filters which have a great effect on the recognition rate. The object descriptor generating method includes extracting gabor features from an input object image by applying a plurality of curvature gabor filters, generated via combination of a plurality of curvatures and a plurality of Gaussian magnitudes, to the object image, and generating an object descriptor for object recognition by projecting the extracted features onto a predetermined base vector.