• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.798-802
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper, the robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is to use different models (CAD model etc.) known a priori. Also fusion of multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Because voting is a very simple or no model is needed for fusion, voting-based fusion of cues is applied. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters, namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.3
• /
• pp.153-163
• /
• 2016

Local feature extraction methods for images and videos are widely applied in the fields of image understanding and computer vision. However, robust features are detected differently when using the latest feature detectors and descriptors because of diverse image environments. This paper analyzes various feature extraction methods by summarizing algorithms, specifying properties, and comparing performance. We analyze eight feature extraction methods. The performance of feature extraction in various image environments is compared and evaluated. As a result, the feature detectors and descriptors can be used adaptively for image sequences captured under various image environments. Also, the evaluation of feature detectors and descriptors can be applied to driving assistance systems, closed circuit televisions (CCTVs), robot vision, etc.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.2
• /
• pp.119-125
• /
• 2008

This paper presents the polygon-based Q-leaning and Cascade Support Vector Machine algorithm for object search with multiple robots. We organized an experimental environment with ten mobile robots, twenty five obstacles, and an object, and then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning and dodecagon-based Q-learning and Cascade SVM to enhance the fusion model with DBAM and ABAM process.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.5
• /
• pp.311-318
• /
• 2017

A reduced order observer is developed for depth control of a hybrid underwater glider which combines the good aspects of a conventional autonomous underwater vehicle and a underwater glider. State variables include the center of gravity of the robot and the weight of the buoyancy bag, which can not be directly measured. By using the mathematical model and available information such as directional velocities, accelerations, and attitudes, we developed a Luenberger's reduced order observer to estimate the center of gravity and the buoyancy weight. By simulations using Matlab/Simulink, the efficiency of the proposed observer is shown, where a LQR controller using full state variables is adopted as a depth controller.

• Electronics and Telecommunications Trends
• /
• v.29 no.3
• /
• pp.118-130
• /
• 2014

전문 서비스로봇인 국방 무인 로봇은 무기체계 개발 시, 소요군의 운용개념 미확정, 국내 로봇 기술수준(TRL) 및 기술성숙도 미흡 등으로 무인체계의 소요기획 및 전력화 소요 반영이 되지 않고 장기적인 획득 대안으로 생각하고 있으나, 미국의 미래 전투체계(Future Combat System)에서 보듯이 네트워크 중심전(NCW)으로의 전장 환경변화 등 무인전투체계의 통신 및 소프트웨어(복합체계 공통운용환경(SOSCOE: System of Systems Common Operating Environment))의 중요성은 더욱 커지고 있다. 국가적으로는 국방 무인 로봇을 시장확산분야로 인식하고 있으며, 그동안 해외 도입 위주의 국방 무인 로봇 시장에 대한 중요성이 부각되고 있어, 우리나라 창조경제 발전의 견인차 역할로 무인체계 시장의 선점 및 새로운 고용시장을 창출할 수 있는 기반으로 투자를 확대하고 있다. 따라서, 본 논고를 통하여 무인체계에 대한 체계개발 활성화 방안에 기여하기 위한 선제적인 방법으로 연구개발 방향을 설정하고, 기술개발 방향 및 획득 우선순위 등 개발전략을 수립하고 그 대안을 제시하고자 한다.

• Journal of the Optical Society of Korea
• /
• v.19 no.4
• /
• pp.421-426
• /
• 2015

This paper presents a hybrid single optical system for an LED surgical light that combines the advantages of both lens- and reflector-type single optical systems. The proposed hybrid single optical system includes a lens in the center and the LED light originating from the lens is redirected using a reflector to achieve a high beam spread. Iterative optical software simulations are used to provide data for the design of the lens and reflector for a single optical system, and for a complex optical system for the LED light assembly. The resulting data is also used to fabricate a prototype system. Experiments using the prototype of the hybrid single optical system and a mock-up LED surgical light confirm the system's shadow dilution performance and its applicability to surgical operations.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.9
• /
• pp.2191-2204
• /
• 1993

A sensor system has been developed to measure the posture(position and orientation) of mobile robots working in industrial environments. The proposed sensor system consists of a CCD camera, retro-reflective landmarks, a strobe unit and an image processing board. The proposed hardware system can be built in economic price compared to commercial vision systems. The system has the capability of measuring the posture of mobile robots within 60 msec when a 386 personal computer is used as the host computer. The experimental results demonstrated a remarkable performance of the proposed sensor system in the posture measurement of mobile robots - the average error in position is less than 3 mm and the average error in orientation is less than 1.5.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1817-1822
• /
• 1991

A method of reducing overhead caused by the processor synchronization process and common memory accesses in finely grained tasks is described. We propose a scheduler which considers the preparation time during searching to minimize the redundant accesses to shared memory. Since the suggested hardware (synchronizer) determines the access order of processors and bus arbitration simultaneously by including the synchronization process into the bus arbitration process, the synchronization time vanishes. Therefore this synchronizer has no overhead caused by the processor synchronization[l]. The proposed scheduler algorithm is processed in parallel. The processes share the upper bound derived by each searching and the lower bound function is built considering the preparation time in order to eliminate as many searches as possible. An application of the proposed method to a multi-DSP system to calculate inverse dynamics for robot arms, showed that the sampling time can be twice shorter than that of the conventional one.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1748-1751
• /
• 1991

Generally, we can't acquire clear boundary or area from an image having obscure boundary like allergy image by using Sobel or Lapalace operator. Also, when the image not uniform in some part of a image in brightness, there are difficulties to use the global operator such as histogram, for the contour line doesn't have the same grey level. In this paper, we will propose an algorithm to improve those difficulties. The main idea of the algorithm is that we divide the image into many rectangular parts like a chess board, calculate the average of each part, and decide the local threshold for each pixel on the calculated value. In experiment, we can get the contour and area by this algorithm which is much like to the contour and area measured by a doctor. Also, This algorithm has many advantages such as short processing time and little influences of noises and can be used in the robot vision, etc..

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.185-190
• /
• 1993

The POSTECH Hand adopting coupled tendon driven technique with planar two fingers is developed. The hand is designed to emulate principal motions of the human hand which has two and three joints respectively. Its kinematic parameters are determined through a parameter optimizing technique to aim at improving the isotropy of fingertip motions with new criterion functions of design. For the control of the hand, tension and torque control algorithms are developed. Based on the virtual stiffness concept, we develop the stiffness control method of a grasped object with redundant finger mechnism and investigate experimentally.