• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.540-543
• /
• 1997

In this paper, a precise trajectory tracking method for mobile robot using a vision system is presented. In solving the problem of precise trajectory tracking, a hierarchical control structure is used which is composed of the path planer, vision system, and dynamic controller. When designing the dynamic controller, non-ideal conditions such as parameter variation, frictional force, and external disturbance are considered. The proposed controller can learn bounded control input for repetitive or periodic dynamics compensation which provides robust and adaptive learning capability. Moreover, the usage of vision system makes mobile robot compensate the cumulative location error which exists when relative sensor like encoder is used to locate the position of mobile robot. The effectiveness of the proposed control scheme is shown through computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2502-2507
• /
• 2003

In this paper, a crack sealing robot is developed. The crack sealing robot is built to detect, track, and seal the crack on the pavement. The sealing robot is required to brush all dirt in the crack out for preparing a better sealing job. Camera calibration has been done to get accurate crack position. In order to perform a cleaning job, the explicit force control method is used to regulate a specified desired force in order to maintain constant contact with the ground. Experimental studies of force tracking control are conducted under unknown environment stiffness and location. Crack tracking control is performed. Force tracking results are excellent and the robot finds and tracks the crack very well.

• 제어로봇시스템학회논문지
• /
• 제21권6호
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.

• 한국소음진동공학회논문집
• /
• 제14권9호
• /
• pp.819-826
• /
• 2004

A multi-step optimum strategy for the selection of the locations and directions of strain gauges is proposed in this paper to capture at best the modal response of blade in a series of modes on fan blades. It is consist of three steps including two pass reduction step, genetic algorithm and fine optimization to find the locations-directions of strain gauges. The optimization is based upon the maximum signal-to-noise ratio(SNR) of measured strain values with respect to the inherent system measurement noise, the mispositioning of the gauge in location and gauge failure. Optimal gauge positions for a fan blade is analyzed to prove the effectiveness of the multi-step optimum methodology and to investigate the effects of the considering parameters such as the mispositioning level, the probability of gauge failure, and the number of gauges on the optimal strain gauge position.

• 제어로봇시스템학회논문지
• /
• 제18권10호
• /
• pp.947-954
• /
• 2012

Sand scorpions are nocturnal animals to mostly use tactile senses to detect their prey. It has been reported that sand scorpions have high vibration sensitivity for their prey-localizing behavior. We tested vibration experiments in the sand with microphone sensors to model the sand scorpion's behavior and a time-difference model was applied to find the direction of a vibration source. Using the information of the arrival time of the vibration signal to reach each leg position, we can find the location of the vibration source.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.943-944
• /
• 2006

In this paper, we implemented the autonomous mobile robot which can recognize and avoid obstacles, then move to its destination using a camera and ultrasonic sensors. The mobile robot can avoid both stationary obstacles with a camera and moving obstacles with ultrasonic sensors. It can find the self-location with the map-based system, that is, it attempts to localize by collecting sensor data, then updating some belief about its position with respect to a map of the environment.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.14-21
• /
• 2019

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.65-67
• /
• 2021

본 논문에서는 발광 다이오드(LED)를 이용한 가시광통신(VLC)을 통해 삼각측량기법을 사용하여 위치 측정 시스템을 위한 새로운 알고리즘을 제안한다. 각각 LED로부터 센서까지의 길이를 도출하고, 도출된 길이를 바탕으로 삼각측량법을 이용해 위치 정보를 찾아낸다. 기존의 가시광통신을 이용한 측위 시스템과는 달리, 제안된 측위 시스템은 송신기와 수신기 사이의 동기화가 필요하지 않으므로 더욱 간단하고 비용 효과적이다.

• 한국방사선학회논문지
• /
• 제15권4호
• /
• pp.409-414
• /
• 2021

감마카메라에서 영상을 획득하기 위해서 직선성 보정을 시행해야 한다. 이를 위해서 섬광체와 감마선이 상호작용한 위치에 대한 정확한 위치 지정을 위해 직선성 맵을 활용하여 디지털 좌표를 획득한다. 본 연구에서는 직선성 맵을 사용하지 않고 순람표와 최대우도함수를 사용하여 왜곡되지 않은 영상을 획득함과 동시에 디지털 좌표를 획득하는 방법을 개발하였다. DETECT2000 시뮬레이션을 통해 소형의 감마카메라를 구성하여 제시된 방법에 대해 검증을 실시하였다. GAGG 섬광체와 SiPM 광센서를 사용하여 감마카메라를 구성하였고, 섬광체의 중심에서 감마선 반응을 일으켜 SiPM에서 획득한 신호의 비율을 사용하여 순람표를 작성하였다. 작성된 순람표와 최대우도함수를 통해 감마선 반응에 의해 획득한 신호의 위치를 디지털 좌표로 획득하여 영상을 구성하였다. 그 결과 일반적으로 획득되는 영상에 비해 직선성이 유지되었으며, 감마선 반응을 발생시킨 위치의 정확도가 우수하였으며, 위치 간 간격이 일정하게 나타났다. 시뮬레이션을 통해 획득한 순람표는 신호의 비율을 사용하여 작성되므로 이를 실험에 직접 활용할 수 있어, 직선성 맵을 작성하지 않고 편리하게 직선성이 보정된 디지털 좌표로 신호의 위치를 획득할 수 있다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.156-156
• /
• 2017

Most crop damages have been occurred by vermin(e.g., wild birds and herbivores) during the period between seeding and the cotyledon level. In this study, to minimize the damage by vermin and acquire the benefits such as protection against weeds and maintenance of water content in soil, immediately vinyl mulching after seeding was devised. Vinyl mulching has been generally covered with black color vinyl, that crop seeding locations cannot be detected by visible light range. Before punching vinyl, non-contact and non-destructive methods that can continuously determine the locations are necessary. In this study, a crop position detection method was studied that uses infrared thermal image sensor to determine the cotyledon position under vinyl mulch. The moving system for acquiring image arrays has been developed for continuously detecting crop locations under plastic mulching on the field. A sliding mechanical device was developed to move the sensor, which were arranged in the form of a linear array, perpendicular to the array using a micro-controller integrated with a stepping motor. The experiments were conducted while moving 4.00 cm/s speed of the IR sensor by the rotational speed of the stepping motor based on a digital pulse width modulation signal from the micro-controller. The acquired images were calibrated with the spatial image correlation. The collected data were processed using moving averaging on interpolation to determine the frame where the variance was the smallest in resolution units of 1.02 cm. For this study, the spline method was relatively faster than the other polynomial interpolation methods, because it has a lower maximum order of formulation when using a system such as the tridiagonal linear equation system which provided the capability of real-time processing. The temperature distribution corresponding to the distance between the crops was 10 cm, and the more clearly the leaf pattern of the crop was visually confirmed. The frequency difference was decreased, as the number of overlapped pixels was increased. Also the wave pattern of points where the crops were recognized were reduced.