• 한국건설관리학회논문집
• /
• 제5권4호
• /
• pp.139-146
• /
• 2004

Resent removal work for road signs has been labor intensive and required times since it has been done manually using shaving type equipment. While traditional process is conducting, there are traffic jams caused by the passing control, and happened unexpected accidents to workers working at dangerous road circumstance. Besides, in current shaving method, there are high potentialities on the air pollution as well as the explosive accident occurred by using a propane gas. So, as an alternative, we have studied to develop the automatic erasing equipment made up with a high pressure water-jet system and automatic control system, mobile system; Wate-rjet system consists of an intensifier and nozzles to give a high pressure and spray on the sign, and automatic control system is composed of one axis robot using a hydraulic servo actuator controlled by a lever, And as a mobile system, a truck plays an important role for the transport of equipment and the forward movement in a removal process. In this paper, we have analyzed the characteristics of road signs and have investigated current erasing methods in the field. And we have organized and designed automatic erasing equipment, and we have made a basic experiment to find out the optimal spray condition as like the spray distance, spray angle and injection pressure.

• 드라이브 ㆍ 컨트롤
• /
• 제19권4호
• /
• pp.97-103
• /
• 2022

Low fertility rates and increased life expectancy further exacerbate the process of an aging society. This is also reflected in the gradual increase in the proportion of vulnerable groups in the social population. The demand for improved mobility among vulnerable groups such as the elderly or the disabled has greatly driven the growth of the electric-assisted mobility device market. However, such mobile devices generally require a certain operating capability, which limits the range of vulnerable groups who can use the device and increases the cost of learning. Therefore, autonomous driving technology needs to be introduced to make mobility easier for a wider range of vulnerable groups to meet their needs of work and leisure in different environments. This study uses mini PC Odyssey, Velodyne Lidar VLP-16, electronic device and Linux-based ROS program to realize the functions of working environment recognition, simultaneous localization, map generation and navigation of electric powered mobile devices for vulnerable groups. This autonomous driving mobility device is expected to be of great help to the vulnerable who lack the immediate response in dangerous situations.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2007년도 정기학술발표대회 논문집
• /
• pp.197-204
• /
• 2007

현재 건설산업 현장에서 나타나는 숙련공 부족 현상, 고령화 문제, 안전상의 문제로 인한 노무 생산성 저하, 임금 상승으로 인한 채산성 악화, 품직 확보의 어려움 및 시공기술 경쟁력의 약화는 국내 건설산업이 해결해야 할 필수적인 당면과제이다. 한편 위험${\cdot}$유해한 작업환경에서 운용되는 토공장비나 매립지에서의 다짐 및 복토공사, 지뢰 및 폭탄 등에 의한 폭발의 위험이 있는 장소에서의 토공작업, 극한지 공사와 같은 환경에서의 공사수요도 점차 늘어가고 있다. 이와 같은 상황에서 토공의 생산성, 품질 및 안전도를 확보하기 위해서는 지능화된 자동화 장비를 이용하여 효율적으로 작업을 수행할 수 있도록 해야 할 필요가 있다. 따라서 본 연구에서는 지능형 굴삭시스템의 개발을 통하여 작업현장의 안전성을 제고하고 품질, 생산성 및 채산성을 향상시키고 선진외국에 비해 보다 진보되고도 경제성 확보가 가능한 건설 자동화 기술의 구현과 기술개발을 통해 국내 건설산업에 있어 새로운 Market Sector의 창출하고자 한다.

• 한국건축시공학회지
• /
• 제21권5호
• /
• pp.387-396
• /
• 2021

건축공사에서 먹매김 공정은 건물의 구성요소를 계획된 위치에 정확히 형성하기 위한 기준이 되므로 높은 정밀도가 요구된다. 최근의 건축물 규모 증가 및 숙련공 부족 추세에서 먹매김 공사는 로봇 기반의 자동화 기술 도입을 통한 생산성 및 품질 향상 요구가 크게 나타나고 있으며, 특히 가장 선행되는 골조공사 먹매김 작업의 중요도 및 자동화 필요성은 더욱 크다고 할 수 있다. 이러한 배경에서 본 연구는 건축물 골조공사용 먹매김에 적합한 시공 자동화 시스템 개발 방향을 제시하고자 한다. 기존 유사 기술 고찰을 토대로 하여 5가지 구성기술과 17개의 세부 기술요소를 도출하였으며, 전문가 설문을 통한 중요도 평가를 수행하였다. 설문 결과, 열악한 주행 및 작업 환경에 대응하기 위한 주행부 및 마킹부 기술이 가장 중요한 구성기술로 파악되었으며, 이러한 환경에서 정밀도를 확보하기 위한 제어기술과 전반적인 프로세스의 자동화기술의 중요성이 높게 나타났다. 본 연구 결과는 향후 보다 실용적이고 효율적인 자동화 시스템 개발에 기여할 것이다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.567-572
• /
• 2002

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS ). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 추계학술대회(한국공작기계학회)
• /
• pp.140-145
• /
• 2001

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 한국산업융합학회 논문집
• /
• 제17권2호
• /
• pp.54-60
• /
• 2014

The equipment of SCARA robot in processing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS). We can save much efforts and time in adjusting robots to newly defined workcells by using OLPS. A proposed visual calibration scheme is based on position-based visual feedback. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not requirethe precise calculation of tree-dimensional object data and image Jacobian.

• 한국측량학회지
• /
• 제32권3호
• /
• pp.253-259
• /
• 2014

There has been a need for replacing human labors with a robot in such dangerous and hard jobs of various construction sites. For that reason, many researches have been made about the high quality robot, which performs its duty instead of human labors. This study is about auto surveying system development based on VRS-GPS which enables autodriving in dangerous areas where it's difficult for humans to measure directly. This study is about the auto-surveying system development, based on VRS-GPS, which enables auto-drive in dangerous areas, whereas difficult for humans to measure directly. The GPS is made with GRXI and SHC250 controllers of the SOKKIA company. The auto surveying system is composed of DPS module, geomagnetism sensor, bluetooth, gimbals, IMU, etc to automatic drive via enter into a route of position. The developed auto surveying system has installed the carmeras for front and vertical axis as well as systems to grasp situation of surveying with smartphone in real time. The result from analysed RMSE of auto surveying system and VRS-GPS surveying is 0.0169m of X-axis and 0.0246m of Y-axis.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권11호
• /
• pp.449-456
• /
• 2019

본 논문은 진공을 이용한 흡착방식과 바퀴형 이동방식을 사용하는 벽면 이동로봇의 구성과 이러한 임베디드 환경에 적합하고 기계학습에 기반한 벽면 균열 자동 검출 알고리즘의 성능 비교에 관한 연구이다. 임베디드 시스템 환경에서 객체 학습을 위해 YOLO 등 최근에 시도된 학습 방법들을 적용하여 성능을 비교, 검토하였으며 기존의 에지 검출 알고리즘들과도 성능을 비교하였다. 결국, 본 연구에서는 균열검출을 잘하며 임베디드 환경에도 적합한 최적의 기계학습방법을 선택하고 기존 방법과 성능을 비교하여 우수성을 제시하였다. 또한, 검출된 균열의 영상을 저장하고 위치 정보를 추정하여 균열에 대한 정보를 관리자 기기로 전송하는 지능적인 문제해결 기능을 구축하였다.

• 드라이브 ㆍ 컨트롤
• /
• 제20권2호
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.