Abstract: There are provided an autonomous vehicle, and an apparatus and method for estimating the motion of the autonomous vehicle and detecting three-dimensional (3D) information of an object appearing in front of the moving autonomous vehicle. The autonomous vehicle measures its orientation using an acceleration sensor and a magnetic flux sensor, and extracts epipolar geometry information using the measured orientation information. Since the corresponding points between images required for extracting the epipolar geometry information can be reduced to two, it is possible to more easily and correctly obtain motion information of the autonomous vehicle and 3D information of an object in front of the autonomous vehicle.

Abstract: A landmark used to effectively determine the location of an autonomous vehicle, and a self-localization apparatus and method using the landmark are provided. In the self-localization method, first, first and second outer line information and shape information are extracted from a landmark image received from a camera. Next, a projective invariant is calculated from the shape information and stored in a hash table. Thereafter, the calculated projective invariant is compared with reference projective invariants for a plurality of landmarks stored in a predetermined data storage area in the form of a hash table, thereby determining which landmark corresponds to the landmark image. Then, information on the distance and orientation of the determined landmark with respect to the autonomous vehicle is analyzed in response to the first and second outer line information.

Abstract: Provided is a hand/eye calibration method by using a projective invariant shape descriptor of a two-dimensional image. The method includes calculating a projective invariant shape descriptor of a two-dimensional image from at least two images obtained by a camera mounted on a robot hand, at a predetermined time interval, extracting corresponding points between the images by using the projective invariant shape descriptor, calculating a rotation matrix for the corresponding points from translation of the robot hand, calculating translation vector for the corresponding points from translation and rotation of the robot hand, and finding a relation between the robot hand and the camera based on the rotation matrix and the translation vector.

Abstract: A ground reaction force measuring module for a walking robot includes a housing installed at a predetermined portion of the walking robot facing the ground, a moving unit installed capable of moving with respect to the housing according to the presence of a pressing force to the ground transferred from the ground to the walking robot, and a compression sensor installed in the housing to measure a reaction force of the ground from the presence of the pressing force transferred through the moving unit. Thus, a change in the ground reaction force in a wide range can be stably coped with and the installation position of the robot foot can be easily changed.

Abstract: A method of controlling a biped walking robot to balance the robot based on a sensed ground reaction force. In the method, X and Y coordinates are assigned to positions of sensors attached to a sole of a leg of the robot and a corresponding Z coordinate is assigned for at least three of the sensors based on the sensed ground reaction force sensed by at the sensors, respectively. A ground reaction force plane is specified based on the sensed ground reaction force and a normal vector perpendicular to the ground reaction force plane is calculated. A roll angle about an X-axis and a pitch angle about a Y-axis are calculated and an actuator is driven in correspondence to the roll angle and the pitch angle to move a part of the robot to align the normal vector with a reference vector of the gravity direction.

Abstract: Provided is a hand/eye calibration method by using a projective invariant shape descriptor of a two-dimensional image. The method includes calculating a projective invariant shape descriptor of a two-dimensional image from at least two images obtained by a camera mounted on a robot hand, at a predetermined time interval, extracting corresponding points between the images by using the projective invariant shape descriptor, calculating a rotation matrix for the corresponding points from translation of the robot hand, calculating translation vector for the corresponding points from translation and rotation of the robot hand, and finding a relation between the robot hand and the camera based on the rotation matrix and the translation vector.

Abstract: Provided is a hand/eye calibration method by using a projective invariant shape descriptor of a two-dimensional image. The method includes calculating a projective invariant shape descriptor of a two-dimensional image from at least two images obtained by a camera mounted on a robot hand, at a predetermined time interval, extracting corresponding points between the images by using the projective invariant shape descriptor, calculating a rotation matrix for the corresponding points from translation of the robot hand, calculating translation vector for the corresponding points from translation and rotation of the robot hand, and finding a relation between the robot hand and the camera based on the rotation matrix and the translation vector.

Abstract: A electronic pen input device and a coordinate determining method are provided. The electronic pen input device includes an optical 3-dimensional detecting device for detecting orientation angles of a centerline of the pen relative to a ground and a height of the pen over a writing surface, a 3-axis accelerometer for detecting a movement of the pen, and a communication means for sending the detected information to a post processing device.

Abstract: A method of controlling a biped walking robot to balance the robot based on a sensed ground reaction force. In the method, X and Y coordinates are assigned to positions of sensors attached to a sole of a leg of the robot and a corresponding Z coordinate is assigned for at least three of the sensors based on the sensed ground reaction force sensed by at the sensors, respectively. A ground reaction force plane is specified based on the sensed ground reaction force and a normal vector perpendicular to the ground reaction force plane is calculated. A roll angle about an X-axis and a pitch angle about a Y-axis are calculated and an actuator is driven in correspondence to the roll angle and the pitch angle to move a part of the robot to align the normal vector with a reference vector of the gravity direction.

Abstract: A pen-shaped input system designed to recover handwriting trajectory in space by using a magnetic field sensor. The system detects a tilt angle relative to the geomagnetic field from a magnetic field detection unit and an acceleration detection unit, and respective three-dimensional axial direction accelerations based on movements of the pen, and calculates the absolute coordinates of the pen. Further, the system converts the acceleration measurement values of the pen into a pen tip acceleration value, and applies the acceleration value for recovering handwriting trajectory of the pen. Such a pen-shaped input system uses the magnetic sensor so that it can prevent accumulative errors occurring due to integrations of the detected information when using inertia sensors, and the system can improve a processing speed since its signal processing is simplified.

Abstract: A ground reaction force measuring module for a walking robot includes a housing installed at a predetermined portion of the walking robot facing the ground, a moving unit installed capable of moving with respect to the housing according to the presence of a pressing force to the ground transferred from the ground to the walking robot, and a compression sensor installed in the housing to measure a reaction force of the ground from the presence of the pressing force transferred through the moving unit. Thus, a change in the ground reaction force in a wide range can be stably coped with and the installation position of the robot foot can be easily changed.

Abstract: There are provided an autonomous vehicle, and an apparatus and method for estimating the motion of the autonomous vehicle and detecting three-dimensional (3D) information of an object appearing in front of the moving autonomous vehicle. The autonomous vehicle measures its orientation using an acceleration sensor and a magnetic flux sensor, and extracts epipolar geometry information using the measured orientation information. Since the corresponding points between images required for extracting the epipolar geometry information can be reduced to two, it is possible to more easily and correctly obtain motion information of the autonomous vehicle and 3D information of an object in front of the autonomous vehicle.

Abstract: Provided is a hand/eye calibration method by using a projective invariant shape descriptor of a two-dimensional image. The method includes calculating a projective invariant shape descriptor of a two-dimensional image from at least two images obtained by a camera mounted on a robot hand, at a predetermined time interval, extracting corresponding points between the images by using the projective invariant shape descriptor, calculating a rotation matrix for the corresponding points from translation of the robot hand, calculating translation vector for the corresponding points from translation and rotation of the robot hand, and finding a relation between the robot hand and the camera based on the rotation matrix and the translation vector.

Abstract: A landmark used to effectively determine the location of an autonomous vehicle, and a self-localization apparatus and method using the landmark are provided. In the self-localization method, first, first and second outer line information and shape information are extracted from a landmark image received from a camera. Next, a projective invariant is calculated from the shape information and stored in a hash table. Thereafter, the calculated projective invariant is compared with reference projective invariants for a plurality of landmarks stored in a predetermined data storage area in the form of a hash table, thereby determining which landmark corresponds to the landmark image. Then, information on the distance and orientation of the determined landmark with respect to the autonomous vehicle is analyzed in response to the first and second outer line information.

Abstract: A electronic pen input device and a coordinate determining method are provided. The electronic pen input device includes an optical 3-dimensional detecting device for detecting orientation angles of a centerline of the pen relative to a ground and a height of the pen over a writing surface, a 3-axis accelerometer for detecting a movement of the pen, and a communication means for sending the detected information to a post processing device.

Abstract: A method for modeling a roadway and a method for recognizing lane markers based on the modeling method. The method for recognizing lane markers of roadway for a vehicle by getting image information about the roadway and information about the speed and steering angle using a camera and a sensor attached to the vehicle, includes the steps of modeling the actual roadway on which the vehicle travels, as a structure having a plurality of rectangular plates linked to each other. The modeled plates are overlayed onto the image information about the actual roadway, photographed by the camera, pixels forming the lane markers are extracted, and linear lane marker information is then obtained from the pixels forming the land markers.