Electronics and Telecommunications Research Institute

Won Pil Yu

Kye Kyung Kim

Su Young Chi

Yun Koo Chung

Yu-Cheol Lee

Jae Yeong Lee

Heesung Chae

Hyoung Gu Lee

Soo Hyun Cho

Sung Lok Choi

Sang Ik Na

Jae Hyun Park

Jae Young Lee

Kwang Ryong Oh

Young Ick Cho

Sahnggi Park

Young Jo Cho

Kyu Seo Han

Jae-Yeong Lee

Young Sup Hwang

Hee Sung Chae

Hyo-Sung Ahn

Nakju Doh

Yu Cheol Lee

A mowing boundary area recognizing apparatus of a mowing robot includes a ground state measurer configured to acquire environment data of a ground based on a grass length on the ground, a determiner configured to determine the grass length on the ground on a basis of the ground environment data to recognize a mowing boundary area, and a controller configured to adjust running of the mowing robot to a mowing area for which mowing is needed.

Mowing robot with mowing boundary area and grass length recognizer

A method of creating an indoor environment map includes acquiring encoded position information by detecting revolutions of wheels when a mobile unit travels using encoders to predict a position of the mobile unit based on the encoded position information, acquiring a measured distance from the mobile unit to an object existing in a surrounding environment using the distance measuring sensor, predicting a position of the mobile unit to be moved, estimating a distance from the mobile unit to the object at the predicted position of the mobile unit, determining whether the estimated distance is matched with the measured distance, correcting the predicted position of the mobile unit to estimate a position of the mobile unit to be moved by the matching of the predicted position with the measured position, and creating the indoor environment map using the corrected position and the measured distance.

Method and system for creating indoor environment map

The method for building an outdoor map for a moving object according to an exemplary embodiment of the present invention includes: receiving a real satellite image for an outdoor space to which the moving object is to move; calculating pixel information including sizes of length and width pixels and a physical distance of one pixel in the real satellite image; measuring a reference position coordinate for a reference position selected from the real satellite image; and linking a pixel number corresponding to the reference position, the reference position coordinate, and the pixel information to the real satellite image in order to build the outdoor map for the moving object, and further includes creating information on a road network in which the moving object navigates based on the pixel number corresponding to the reference position, the reference position coordinate, and the pixel information.

Method for building outdoor map for moving object and apparatus thereof

Disclosed are an apparatus and a method for fast path search using learning of a heuristic function according to the present invention. An apparatus for fast path search according to the present invention includes: an input unit to receive destination information from a user, and to receive a search request for a path to the received destination information; a location recognizing unit to obtain current location information of the user when the search request for the path is received; and a control unit to search a map for a path from a start node corresponding to the current location information to a destination node corresponding to the destination information using a heuristic evaluation function.

Apparatus for fast path search by learning heuristic function and method thereof

A path search method of a mobile object in a grid map having a plurality of cells, each having an identical size, is provided. The path search method includes: generating a block map having a plurality of blocks by merging a specific number of cells in the grid map; obtaining a block path by finding a path from a starting position to a destination position in the block map; and obtaining a final path of the mobile object by performing a cell-based path search on cells in the blocks on the block path.

Path search method

Provided is a system and method for providing location information of robot in real time using an artificial mark. The system includes: an image processing module for obtaining an image signal by photographing artificial marks installed at a predetermined space with a space coordinate and detecting an image coordinate of artificial mark from the obtaining the image signal; a location calculating module for calculating a current location by comparing the image coordinate of detected artificial mark and a pre-stored space coordinate of artificial mark; and an artificial mark identifying module for updating current location information by selectively using one of an artificial mark tracing process and an image coordinate estimating process.

System and method for real-time calculating location

Provided are an optical vision chip (OVC) and an image recognition method using the OVC. The OVC includes: a first display displaying an object image; a second display displaying a standard model image; and an optical sensor optically or electrically coupling the object image and the standard model image respectively displayed on the first and second displays and outputting a difference between the object image and the standard model image as an electrical signal.

Optical vision chip (OVC) and image recognition method using the same

Provided is an apparatus for detecting the tension, moving direction, and length of a connector. The detecting apparatus includes a connector including one end connected inside the movement detecting apparatus and other end disposed at an outer side of the movement detecting apparatus, a tension detector measuring a tension force applied to the connector by detecting a minute change in a parameter of the tension detector when the other end of the connector is pulled away from the movement detecting apparatus, a direction detector measuring a movement of the connector in horizontal and vertical directions in a plane substantially perpendicular to the tension so as to detect a direction of the tension force applied to the connector, and a length detector detecting a length of the connector extended from the movement detecting apparatus by the tension force applied to the connector. When the connector such as a cable is pulled, the detecting apparatus detects information about the pulling conditions of the cable. Therefore, when a user walks with a dog robot by holding the cable of the detecting apparatus attached to the dog robot, the detecting apparatus provides information about the cable-holding conditions to inform the dog robot of user's intention, so that the dog robot can follow the user according to the user's intention. Thus, automatically-movable devices such as the dog robot can be conveniently used by employing the detecting apparatus since the detecting apparatus provides information about user's intention to the devices.

Apparatus for detecting the movement of its embedded attaching means

A localization system and method of a mobile robot using a camera and artificial landmarks in a home and a general office environment (or working zone) is provided. The localization system includes artificial landmarks having an LED flash function in an invisible wavelength band, a camera with a wide-angle lens, a module flashing landmarks attached at the ceiling and identifying positions and IDs of the landmarks from an image photographed by the camera having a filter, a module calculating position and orientation of the robot using two landmarks of the image in a stop state, a module, when a ceiling to which the landmarks are attached has different heights, a position of the robot, and a module, when a new landmark is attached in the working zone, calculating a position of the new landmark on an absolute coordinate.

Localization system and method of mobile robot based on camera and landmarks

Disclosed is a method of segmenting handwritten touching numeral strings having a non-vertical segmentation line. The method comprises the steps of: receiving an image of the handwritten touching numeral strings having the non-vertical segmentation line extracted from a specially patterned document; smoothing an uneven shape of the image of handwritten touching numeral strings; searching a contour line for the image of smoothed handwritten touching numeral strings; searching a candidate segmentation region, in which the touching numeral strings may exist, from the searched contour line; searching a candidate segmentation point within the candidate segmentation region; searching a vertical segmentation line for segmenting the handwritten touching numeral strings from the candidate segmentation point; searching the non-vertical segmentation line for segmenting the handwritten touching numeral strings having any inclination from the candidate segmentation lines; and segmenting the handwritten touching numeral strings by use of the vertical and non-vertical segmentation lines.

Method of segmenting handwritten touching numeral strings having non-vertical segmentation line

Disclosed is a method of segmenting touching numeral strings contained in handwritten touching numeral strings, and recognizing the numeral strings by use of feature information and recognized results provided by inherent structure of digits. The method comprises the steps of: receiving a handwritten numeral string extracted from a pattern document; smoothing a curved numeral image of the handwritten numeral string, and searching connecting components in the numeral image; determining whether or not the numeral string is a touching numeral string; if it is determined that the numeral string is the touching numeral string, searching a contour of the touching numeral string image; searching candidate segmentation points in the contour, and segmenting sub-images; computing a segmentation confidence value on each segmented sub-image by use of a segmentation error function to select the sub-image with the highest segmentation confidence value as a segmented numeral image in the touching numeral string image; if it is determined in the step c that the numeral string is not the touching numeral string, extracting a feature to recognize the segmented numeral image; segmenting the numeral image selected from the touching numeral string in the highest segmenting confidence value; and obtaining remaining numeral string image.

Growing community of inventors

Ulsan, South Korea

Won Pil Yu