• 제어로봇시스템학회논문지
• /
• 제19권6호
• /
• pp.527-533
• /
• 2013

BCI (Brain-Computer Interface) is a system that transforms a subject's brain signal related to their intention into a control signal by classifying EEG (electroencephalograph) signals obtained during the imagination of movement of a subject's limbs. The BCI system allows us to control machines such as robot arms or wheelchairs only by imaging limbs. With the exact same experiment environment, activated brain regions of each subjects are totally different. In that case, a simple approach is to use as many channels as possible when measuring brain signals. However the problem is that using many channels also causes other problems. When applying a CSP (Common Spatial Pattern), which is an EEG extraction method, many channels cause an overfitting problem, and in addition there is difficulty using this technique for medical analysis. To overcome these problems, we suggest an optimal channel selection method using a BPSO (Binary Particle Swarm Optimization), BPSO with channel impact factor, and GA. This paper examined optimal selected channels among all channels using three optimization methods and compared the classification accuracy and the number of selected channels between BPSO, BPSO with channel impact factor, and GA by SVM (Support Vector Machine). The result showed that BPSO with channel impact factor selected 2 fewer channels and even improved accuracy by 10.17~11.34% compared with BPSO and GA.

• 대한전자공학회논문지SP
• /
• 제46권2호
• /
• pp.114-119
• /
• 2009

서비스 로봇에서 사용되는 음원인식 시스템은 사람이 로봇을 향해 말할 때 화자의 위치를 추정한다. 로봇용 음원인식 알고리즘들 중에서 복수개의 마이크로폰에 소리가 도착하는 시간지연 정보를 이용하여 음원을 추정하는 방법이 널리 이용된다. 마이크로폰에 도달하는 지연시간 정보를 구하기 위해서 상관관계 함수가 사용된다. 상관관계 함수에서 최대 값의 위치를 각도로 변환할 때 코사인 역함수가 사용되며 코사인 역함수의 비선형적인 특성 때문에 음원의 위치에 따라 마이크로폰 쌍에서 추정하는 각도의 정확성이 다르게 된다. 본 논문에서는 음원의 위치에 따라 각도를 가장 잘 추정할 수 있는 각도 영역을 구분하여 정확하게 음원의 위치를 인식하는 방법을 제안한다. 또한 제안한 방법을 이용하면 각 마이크 쌍에서 60도 범위에 대해서만 각도를 계산하므로 기존의 180도에 대한 방법에 비하여 연산이 1/2로 줄어든다. 테스트 환경을 구축하여 제안한 영역 분할 위치 추정 알고리즘과 기존 알고리즘의 성능을 비교한 결과 제안한 알고리즘의 기존 알고리즘에 의한 평균오차의 31%에 불과함을 보인다.

• 센서학회지
• /
• 제5권5호
• /
• pp.55-62
• /
• 1996

본 논문에서는 개발된 편광방식 스테레오 모니터링(KAERI-PSM) 시스템의 성능을 평가하기 위해 6 D.O.F의 퓨마 로보트를 이용한 원격조작 실험을 수행하였다. 카메라의 관측각도를 달리하는 3가지 원격조작실험은 6명의 실험자가 힘반향 조이스틱을 사용하여 로보트 암을 (1) 직접 (2) 일반 모니터 (3) 동기방식 스테레오 영상 모니터 및 (4) 개발된 편광방식 스테레오 영상 모니터를 통하여 보면서 6가지의 조합된 방법으로 총 36번 수행하여 걸린 평균 시간과 평균 에러 발생 수를 비교하는 것이다. 실험 결과 스테레오 영상 모니터를 사용한 원격작업은 일반 모니터를 이용했을 때 보다 훨씬 짧은 시간에 정확히 수행할 수 있었으며, 물체 이동에 대한 카메라의 각도가 실험의 주요한 변수가 됨을 알 수 있었다. 또한 동기방식과 편광방식의 비교에서 속도와 정확도 면에서는 두 방식이 비슷했으나 눈의 피로도로 인한 작업의 안정성 측면에서는 편광방식이 우수함을 알 수 있었다.

• Journal of Mechanical Science and Technology
• /
• 제20권4호
• /
• pp.437-446
• /
• 2006

Laser vision inspection systems are becoming popular for automated inspection of manufactured components. The performance of such systems can be enhanced by improving accuracy of the hardware and robustness of the software used in the system. This paper presents a new approach for enhancing the capability of a laser vision system by applying hardware compensation and using efficient analysis software. A 3D geometrical model is developed to study and compensate for possible distortions in installation of gantry robot on which the vision system is mounted. Appropriate compensation is applied to the inspection data obtained from the laser vision system based on the parameters in 3D model. The present laser vision system is used for dimensional inspection of car chassis sub frame and lower arm assembly module. An algorithm based on simplex search techniques is used for analyzing the compensated inspection data. The details of 3D model, parameters used for compensation and the measurement data obtained from the system are presented in this paper. The details of search algorithm used for analyzing the measurement data and the results obtained are also presented in the paper. It is observed from the results that, by applying compensation and using appropriate algorithms for analyzing, the error in evaluation of the inspection data can be significantly minimized, thus reducing the risk of rejecting good parts.

• 제어로봇시스템학회논문지
• /
• 제19권2호
• /
• pp.158-163
• /
• 2013

The fusion of the GPS (Global Positioning System) and DR (Dead Reckoning) is widely used for position and latitude estimation of vehicles such as a mobile robot, aerial vehicle and marine vehicle. Among the many types of aerial vehicles, grater focus is given on the quad-rotor and accuracy of the position information is becoming more important. In order to exactly estimate the position information, we propose the fusion method of GPS and Gyroscope sensor using the DEKF (Dual Extended Kalman Filter). The DEKF has an advantage of simultaneously estimating state value and a parameter of dynamical system. It can also be used even if state value is not available. In order to analyze the performance of DEKF, the computer simulation for estimating the position, the velocity and the angle in a circle trajectory of quad-rotor was done. As it can be seen from the simulation results using own proposed DEKF instead of EKF on own fusion method in the navigation of a quad-rotor gave better performance values.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1624-1627
• /
• 1997

The 6-DOF parallel manipulator is a closed-kindmatic chain robot manipulator that is capable of providing high structural rigidity and positional accuracy. Because of its advantage, the parallel manipulator have been widely used in many engineering applications such as vehicle/flight driving simulators, rogot maniplators, attachment tool of machining centers, etc. However, the kinematic analysis for the implementation of a real-time controller has some problem because of the lack of an efficient lagorithm for solving its highly nonliner forward kinematic equation, which provides the translational and orientational attitudes of the moveable upper platform from the lenght of manipulator linkages. Generally, Newton-Raphson method has been widely sued to solve the forward kinematic problem but the effectiveness of this methodology depend on how to set initial values. This paper proposes a hybrid method using genetic algorithm(GA) and Newton-Raphson method to solve forward kinematics. That is, the initial values of forward kinematics solution are determined by adopting genetic algorithm which can search grobally optimal solutions. Since determining this values, the determined values are used in Newton-Raphson method for real time calcuation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.846-851
• /
• 2004

In this paper, we propose a global ultrasonic system for the self-localization and autonomous navigation of indoor mobile robots. The ultrasonic sensor is regarded as the most cost-effective ranging system among the possible alternatives, and it is widely used for general purpose, since it requires simple electronic drivers and has relatively high accuracy. The global ultrasonic system presented in this paper consists of four or more ultrasonic generators fixed at reference positions in the global coordinates of an indoor environment and two receivers mounted on the mobile robots. By using the RF (Radio Frequency) modules added to the ultrasonic sensors, the robot is able to control the ultrasonic generation and to obtain the critical distances from the reference positions, which are required in order to localize is position in the global coordinates. A kalman filter algorithm designed for the self-localization using the global ultrasonic system and the experimental results of the autonomous navigation are presented in this paper.

• 제어로봇시스템학회논문지
• /
• 제14권10호
• /
• pp.1062-1072
• /
• 2008

When mobile robots perform the mission in the rough terrain, the traversability depended on the terrain characteristic is useful information. In the traversabilities, wheel-terrain maximum friction coefficient can indicate the index to control wheel-terrain traction force or whether mobile robots to go or not. This paper proposes estimating wheel-terrain maximum friction coefficient. The existing method to estimate the maximum friction coefficient is limited in flat terrain or relatively easy driving knowing wheel absolute velocity. But this algorithm is applicable in rough terrain where a lot of slip occurred not knowing wheel absolute velocity. This algorithm applies the tire-friction model to each wheel to express the behavior of wheel friction and classifies slip-friction characteristic into 3 major cases. In each case, the specific algorithm to estimate the maximum friction coefficient is applied. To test the proposed algorithm's feasibility, test bed(ROBHAZ-6WHEEL) simulations are performed. And then the experiment to estimate the maximum friction coefficient of the test bed is performed. To compare the estimated value with the real, we measure the real maximum friction coefficient. As a result of the experiment, the proposed algorithm has high accuracy in estimating the maximum friction coefficient.

• 로봇학회논문지
• /
• 제12권3호
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• 한국정밀공학회지
• /
• 제33권7호
• /
• pp.565-570
• /
• 2016

This paper presents the characteristics related to needle insertion of a robotic device for the automated biopsy procedure. The automated biopsy device, a main component of the robotic needle insertion type intervention system, allows performance of the full biopsy procedure, except for anesthesia, without direct handling of a radiologist or a tele-operated control. In this study, the needle length parameters corresponding to various insertion depths and precision for needle insertion of the automated biopsy device, are discussed. There were two combinations of needle length parameters for appropriate needle insertion and motion capture-based measurement was performed; 0.156 mm error for the 90 mm length commanded insertion displacement was measured. The pre-defined goal is a maximum 1 mm error and thus our measured error is within the acceptable range. In the repeatability check, it was also shown that the device can implement a highly accurate insertion.