• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.90-101
• /
• 2000

In this paper, we propose a controller for differentially steered wheeled mobile robots. The controller uses input-output linearization algorithm and artificial neural network to stabilize the dynamic model and compensate uncertainties. The proposed neural network part has 6 inputs, 1 hidden layer, 2 torque outputs and features fast online learning and good performance on structure error learning basis. Simulation results show that the proposed controller perform precisely tracking of reference path and is robust to uncertainties.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.716-721
• /
• 1990

It is one of the essential task to determine the absolute location of mobile robot during its navigation. In this paper we propose an algorithm to calculate the distance and orientation of camera from landmark through the visual image of stripe typed landmark. Exact closed form solution of camera location is obtained with the correspondences from vertical line on mark plane to the intersection point of projected line with horizontal axis of image plane. It needs only one line image information, so that location determination can be processed in real time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.316-318
• /
• 2000

미래의 무선망에서는 자원의 한계를 극복하기 위해서 셀 크기가 작은 마이크로/피코 셀 구조를 갖을 것으로 기대된다. 하지만, 이런 구조는 핸드오프의 증가를 가져오기 때문에 시간과 위치에 따라 망의 상태는 급격히 변동하게 된다. 이러한 점은 QoS 보장이 어렵거나 저하시키는 원인이 된다. 따라서, 본 논문은 멀티미디어 서비스 분포를 제어함으로써 망의 변동폭을 완화시켜 이동 QoS를 개선시키는 호 수락 알고리즘(RCAC)을 제안하였다. 실험 결과, 제안된 방식이 QoS를 개선시킬 수 있음을 확인할 수 있다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1864-1865
• /
• 2006

무인지능형로봇 시스템에 있어서 자세의 정확도를 향상시키기 위한 많은 연구가 이루어져 왔다. 시스템의 자세 제어는 사용되는 모터의 위치 제어로 대응된다. 이와 같은 시스템은 운용 시에 충격 진동이 발생하게 된다. 이러한 충격 진동 외란을 잘 제거해야 요구되는 위치 정도로 제어를 수행할 수 있다. 로봇 제어 분야에서 불확실한 로봇에 대한 자세 제어 분야는 가장 기본적이면서 중요한 분야중의 하나이다. 이러한 문제를 다루기 위하여 계산 토크 방식에 기초한 선형 제어 기법이나 적응 제어 기법, 강인 제어 기법 등을 이용한 연구 결과들이 발표되고 있다. 그러나 그러한 기법은 일반적으로 로봇의 정확한 동력학식을 알아야 하며, 구현하기 복잡하다. 따라서 본 논문에서는 적응 규칙에 의하여 모델의 불확실성, 시스템의 변화, 외란으로 인해 발생하는 공칭 플랜트와의 오차를 보상하도록 제어 입력을 생성하는 내부 루프 부분과 공칭 플랜트 모델의 명령을 추종하도록 하는 제어 입력을 생성하는 외부 루프 부분으로 구성되는 방법인 외란관측기(Disturbance OBserver : DOB) 제어 알고리즘을 제안한다. 또한 프로세서의 신뢰성과 수치 연산 및 알고리즘의 빠른 처리를 위해 현재 사용 빈도가 높은 TI사의 DSP시리즈 중에서 부동 소수점 연산 기능을 가지면서 모터 제어에 적합한 TMS320C2000계열의 TMS320F2812을 사용하여, 운용 시 발생되는 진동 둥에 대한 외란 제거를 목적으로 한다. 본 논문은 규명된 시스템 모델식을 바탕으로 DOB 제어 시뮬레이션을 수행하고 PMSM 모터모델 시뮬링크 블록을 구성하여 검증된 외란 관측기 제어 알고리즘을 검증한다. 시뮬레이션으로 검증된 DOB 모터 자세 제어 알고리즘을 DSP에 적용하기 위해 코드변환하고 모터 실험 시스템에 실제 적용함으로써 타당성을 검증하여 상용 제어기로 실제 현장에 적용 가능함을 입증한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.135-140
• /
• 2004

In this paper, we study the posture control of an underwater vehicle with nonholonomic constraint. Generally, systems with nonholnomic constraints cannot be stabilized to an equilibrium points by smooth state feedback control. Therefore, we proposed a control strategy for posture control of the underwater vehicle using backstepping control. The proposed control scheme is applied to the posture control of an underwater vehicle and verified the effectiveness of control strategy by numerical simulation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.1
• /
• pp.123-128
• /
• 2017

This paper deals with performing missions through autonomous navigation using camera and other sensors. Extracting pose of the car is necessary to navigate safely within the given road. Homography is used to find it. Color image is converted into grey image and thresholding and edge is used to find control points. Two control ponits are converted into world coordinates using homography to find the angle and position of the car. Color is used to find traffic signal. It was confirmed that the given tasks performed well through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.906-912
• /
• 2014

The study of fish robot is a main subject that are related with the propulsive force comparison using a varying amplitude and frequency for body and tail motion trajectory, and the quick turn using a proper trajectory function. In this study, when a fish robot thrusts forward, feedback control is difficult to apply for a fish robot, because body and tail joints as a sine wave are rolled. Therefore, we detect the virtual position based on the path of the fish robot, define the angle errors using the detected position and the look-ahead point on the given path, and design a controller to track given path. We have found that the proposed method is useful through the computer simulations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.550-555
• /
• 2009

A violin plays an essential role among string instruments. It has an extremely strong expressive power that can be conveyed through beautiful timbre when played correctly. However, a beginner who attempts to play the violin will be most likely to face difficulties in placing his or her fingers on a specific point of the fingerboard or in bowing the violin on a specific string. In order to resolve this difficulty, the database of a professional violinist's bowing skills were inserted beforehand. By doing so, a beginner can emulate professional's violin by comparing his playing with the constructed database that is programmed in the computer. Accordingly, the results are displayed on the monitor after being evaluated by the performance evaluation function using a fuzzy logic.

• Journal of KSNVE
• /
• v.6 no.1
• /
• pp.35-44
• /
• 1996

This paper presents a new type of fuzzy-sliding mode controller for robust tip position control of a single-link flexible manipulator subjected to parameter variations. A sliding mode controller is formulated with an assumption that imposed parameter variations are bounded so that certain deterministic performance can be guaranted. In the design of the sliding mode controller, so called moving sliding surface is adopted to minimize the reaching phase and thus mitigate system sensitivity to the variations. The sliding mode controller is then incorporated with a fuzzy technique to reduce inherently ever-existing chattering which is impediment in position control of flexible manipulators. A set of fuzzy parameters and control rules are obtained from a relation between predetermined sliding surface and representative points in the state space. Computer simulations are undertaken in order to demonstrate superior control performance of the proposed methodology.