• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2008년도 정기학술발표대회 논문집
• /
• pp.184-192
• /
• 2008

현재, 전 세계적으로 건설 산업의 문제점으로 인식되고 있는 낮은 생산성, 숙련공 부족, 인력의 부족, 높은 재해율 등을 해결하기 위한 방법으로 낙후된 건설 생산시스템의 첨단 기술화를 위한 건설 자동화연구가 활발히 진행되고 있다. 국내에서도 1980년대부터 건설자동화 연구가 진행되고 있으며 기계화 및 반자동화를 통한 생력화를 위한 연구가 주로 진행되었다. 그러나 최근 IT기술의 비약적 발전과 함께 건설 로봇의 개발에 대한 관심이 집중되고 있으며 2006년 말부터 국토해양부의 건설기술혁신사업의 일환으로 토공자동화를 위한 지능형 굴삭시스템이 개발되고 있다. 본 논문에서는 지능형 굴삭시스템의 최종 개발 목표와 2차 년도까지 진행된 연구내용에 대하여 소개하고자 한다.

• 농업과학연구
• /
• 제47권2호
• /
• pp.205-217
• /
• 2020

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs. The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9°. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

• 한국HCI학회논문지
• /
• 제10권2호
• /
• pp.45-55
• /
• 2015

최근 증강현실 분야에서 특징점 인식 및 추적 기술은 비마커 기반의 증강 현실 서비스 구현에 중요한 역할을 담당하고 있다. 특징점 인식 및 추적 기술은 오래 전부터 컴퓨터 비전 등 여러 분야의 많은 연구자들에 의해 심도 있게 연구되어 왔으며, 특히 최근 급성장하고 있는 모바일 관련 시스템에 적용하기 위해 모바일 임베디드 환경에 접목 가능한 특징점 기반의 다양한 인식 및 추적 기술들이 소개되고 있다. 따라서 본 논문에서는 널리 활용되고 있는 특징점 기반의 매칭 및 추적의 다양한 핵심 요소 기술 (특징점 추출, 특징점 기술, 특징점 매칭 및 추적)에 대한 최신 동향을 분석하고, 본 한국과학기술연구원 연구팀이 수행한 모바일 증강현실 서비스 관련 사례 연구인 관광 지도 인식 및 추적 연구를 소개하고자 한다.

• 한국산업융합학회 논문집
• /
• 제25권2_2호
• /
• pp.247-255
• /
• 2022

Robot Process Automation (RPA) is a computer technology called Robotic Process Automation, a form of business process automation based on the concept of software robots or artificial intelligence (AI) walkers. In general, in traditional workflow automation tools, software developers design software that creates a set of actions to automate tasks and interfaces for the back-end systems using internal APIs or dedicated script languages. However, in RPA software, automation can be implemented by configuring an operating processor as if the general user is directly performing the task of the application. In other words, it can be said that it is a suitable development method for automating simply repetitive tasks rather than developing specific programs in which all necessary functions are implemented, as in general software development. Thus, this is more appropriate for configuring and automating RPA software in traditional manufacturing companies that are not easy to develop and apply smart factories or high-end AI software. Therefore, this research aims to analyze the requirements required at the actual manufacturing companies, focusing on the manufacturer's case in Changwon, Gyeongsangnam-do, called SinceWin Co., Ltd., and to examine the possibility of RPA software in the manufacturing companies by implementing actual RPA software that supports office automation. Through the research, it was confirmed that the actually implemented RPA software met the requirements of the company and helped manufacturer practice significantly by automating the parts that were worked error-prone and manually periodically.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4084-4104
• /
• 2021

Visual place recognition (VPR) is a fundamental yet challenging task of mobile robot navigation and localization. The existing VPR methods are usually based on some pairwise similarity of image descriptors, so they are sensitive to visual appearance change and also computationally expensive. This paper proposes a simple yet effective four-step method that achieves adaptive convolutional neural network (CNN) landmark matching for VPR. First, based on the features extracted from existing CNN models, the regions with higher significance scores are selected as landmarks. Then, according to the coordinate positions of potential landmarks, landmark matching is improved by removing mismatched landmark pairs. Finally, considering the significance scores obtained in the first step, robust image retrieval is performed based on adaptive landmark matching, and it gives more weight to the landmark matching pairs with higher significance scores. To verify the efficiency and robustness of the proposed method, evaluations are conducted on standard benchmark datasets. The experimental results indicate that the proposed method reduces the feature representation space of place images by more than 75% with negligible loss in recognition precision. Also, it achieves a fast matching speed in similarity calculation, satisfying the real-time requirement.

• 방송공학회논문지
• /
• 제28권2호
• /
• pp.178-184
• /
• 2023

카메라로 촬영한 야외 일반 영상에서 텍스트 이미지를 찾아내고 그 내용을 인식하는 기술은 로봇 비전, 시각 보조 등의 기반으로 활용될 수 있는 매우 중요한 기술이다. 하지만 텍스트 이미지가 저해상도인 경우에는 텍스트 이미지에 포함된 노이즈나 블러 등의 열화가 더 두드러지기 때문에 텍스트 내용 인식 성능의 하락이 발생하게 된다. 본 논문에서는 일반 영상에서의 저해상도 한글 텍스트에 대한 이미지 초해상화를 통해서 텍스트 인식 정확도를 개선하였다. 트랜스포머에 기반한 모델로 한글 텍스트 이미지 초해상화를 수행 하였으며, 직접 구축한 고해상도-저해상도 한글 텍스트 이미지 데이터셋에 대하여 제안한 초해상화 방법을 적용했을 때 텍스트 인식 성능이 개선되는 것을 확인하였다.

• Journal of Astronomy and Space Sciences
• /
• 제29권4호
• /
• pp.381-387
• /
• 2012

The planetary exploration rover executes various missions after moving to the target point in an unknown environment in the shortest distance. Such missions include the researches for geological and climatic conditions as well as the existence of water or living creatures. If there is any obstacle on the way, it is detected by such sensors as ultrasonic sensor, infrared light sensor, stereo vision, and laser ranger finder. After the obtained data is transferred to the main controller of the rover, decisions can be made to either overcome or avoid the obstacle on the way based on the operating algorithm of the rover. All the planetary exploration rovers which have been developed until now receive the information of the height or width of the obstacle from such sensors before analyzing it in order to find out whether it is possible to overcome the obstacle or not. If it is decided to be better to overcome the obstacle in terms of the operating safety and the electric consumption of the rover, it is generally made to overcome it. Therefore, for the purpose of carrying out the planetary exploration task, it is necessary to design the proper suspension system of the rover which enables it to safely overcome any obstacle on the way on the surface in any unknown environment. This study focuses on the design of the new double 4-bar linkage type of suspension system applied to the Korea Aerospace Research Institute rover (a tentatively name) that is currently in the process of development by our institute in order to develop the planetary exploration rover which absolutely requires the capacity of overcoming any obstacle. Throughout this study, the negative moment which harms the capacity of the rover for overcoming an obstacle was induced through the dynamical modeling process for the rocker-bogie applied to the Mars exploration rover of the US and the improved version of rocker-bogie as well as the suggested double 4-bar linkage type of suspension system. Also, based on the height of the obstacle, a simulation was carried out for the negative moment of the suspension system before the excellence of the suspension system suggested through the comparison of responding characteristics was proved.

• 한국항만경제학회지
• /
• 제25권4호
• /
• pp.107-130
• /
• 2009

부산 신항은 현재 개발 중에 있어 항만배후단지의 효유적인 이용이 부산 신항의 미래를 결정짓는 중요한 과제이다. 따라서 본 논문은 부산 신항의 항만배후단지의 효율적인 이용을 위해 우리나라의 교역량의 상당부분을 차지하고 있는 중국 및 일본과의 국제분업구조와 부산항의 대 중국 및 일본과의 수출입구조를 RCA지수와 GL지수를 이용하여 분석하고, 또한 부산 발전 10대 전략산업 등을 근거로 하여 부산 신항의 항만배후 단지에 유치할 적절한 산업을 선정하려고 한다. 한 중 일 3국의 국제분업구조 분석과 부산항의 대 중국 및 일본의 수출입실적 분석, 그리고 한 중 일 3국의 RCA 및 GL분석의 결과에 의하면, 3국간의 교역에서 한국의 비교우위 품목은 섬유 의류, 귀금속, 펄프 인쇄물, 기계 전기제품 등이며, 한국의 대 중국 및 일본교역에서는 기계 전기제품과 1차금속 비금속제품 등에서 산업내 무역이 이루어지고 있다. 여기에 더하여 광학 정밀기구 의료 악기 등이 높은 수출실적을 나타내고 있다. 또한 부산의 10대 전략산업인 의료, 섬유 의류 및 기계는 이미 포함되어 있으므로 자동차, 조선, 우주항공, 지능형 로봇, 나노소재, 연료전지 및 수소에너지 등이 추가될 수 있다. 그 결과 부산 신항의 항만배후단지에 유치할 산업은 저위기술분야인 섬유 의류와 펄프 인쇄물, 중저위기술분야인 귀금속과 1차금속 비금속제품은 물론 중고위기술분야인 기계 전기제품, 자동차, 조선, 고위기술분야인 광학 정밀기구 의료 악기, 나노소재, 연료전기, 우주항공, 지능형 로봇 등을 위주로 하고 이와 연관된 산업도 유치하는 것이 합리적이라 할 수 있다.

• 지능정보연구
• /
• 제22권4호
• /
• pp.177-192
• /
• 2016

기계학습(Machine Learning)은 인공 지능의 한 분야로, 데이터를 이용하여 기계를 학습시켜 기계 스스로가 데이터 분석 및 예측을 하게 만드는 것과 관련한 컴퓨터 과학의 한 영역을 일컫는다. 그중에서 SVM(Support Vector Machines)은 주로 분류와 회귀 분석을 목적으로 사용되는 모델이다. 어느 두 집단에 속한 데이터들에 대한 정보를 얻었을 때, SVM 모델은 주어진 데이터 집합을 바탕으로 하여 새로운 데이터가 어느 집단에 속할지를 판단해준다. 최근 들어서 많은 금융전문가는 기계학습과 막대한 데이터가 존재하는 금융 분야와의 접목 가능성을 보며 기계학습에 집중하고 있다. 그러면서 각 금융사는 고도화된 알고리즘과 빅데이터를 통해 여러 금융업무 수행이 가능한 로봇(Robot)과 투자전문가(Advisor)의 합성어인 로보어드바이저(Robo-Advisor) 서비스를 발 빠르게 제공하기 시작했다. 따라서 현재의 금융 동향을 고려하여 본 연구에서는 기계학습 방법의 하나인 SVM을 활용하여 매매성과를 올리는 방법에 대해 제안하고자 한다. SVM을 통한 예측대상은 한국형 변동성지수인 VKOSPI이다. VKOSPI는 금융파생상품의 한 종류인 옵션의 가격에 영향을 미친다. VKOSPI는 흔히 말하는 변동성과 같고 VKOSPI 값은 옵션의 종류와 관계없이 옵션 가격과 정비례하는 특성이 있다. 그러므로 VKOSPI의 정확한 예측은 옵션 매매에서의 수익을 낼 수 있는 중요한 요소 중 하나이다. 지금까지 기계학습을 기반으로 한 VKOSPI의 예측을 다룬 연구는 없었다. 본 연구에서는 SVM을 통해 일 중의 VKOSPI를 예측하였고, 예측 내용을 바탕으로 옵션 매매에 대한 적용 가능 여부를 실험하였으며 실제로 향상된 매매 성과가 나타남을 증명하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.975-976
• /
• 1993

This talk presents the overview of the author's research and development activities on fuzzy inference hardware. We involved it with two distinct approaches. The first approach is to use application specific integrated circuits (ASIC) technology. The fuzzy inference method is directly implemented in silicon. The second approach, which is in its preliminary stage, is to use more conventional microprocessor architecture. Here, we use a quantitative technique used by designer of reduced instruction set computer (RISC) to modify an architecture of a microprocessor. In the ASIC approach, we implemented the most widely used fuzzy inference mechanism directly on silicon. The mechanism is beaded on a max-min compositional rule of inference, and Mandami's method of fuzzy implication. The two VLSI fuzzy inference chips are designed, fabricated, and fully tested. Both used a full-custom CMOS technology. The second and more claborate chip was designed at the University of North Carolina(U C) in cooperation with MCNC. Both VLSI chips had muliple datapaths for rule digital fuzzy inference chips had multiple datapaths for rule evaluation, and they executed multiple fuzzy if-then rules in parallel. The AT & T chip is the first digital fuzzy inference chip in the world. It ran with a 20 MHz clock cycle and achieved an approximately 80.000 Fuzzy Logical inferences Per Second (FLIPS). It stored and executed 16 fuzzy if-then rules. Since it was designed as a proof of concept prototype chip, it had minimal amount of peripheral logic for system integration. UNC/MCNC chip consists of 688,131 transistors of which 476,160 are used for RAM memory. It ran with a 10 MHz clock cycle. The chip has a 3-staged pipeline and initiates a computation of new inference every 64 cycle. This chip achieved an approximately 160,000 FLIPS. The new architecture have the following important improvements from the AT & T chip: Programmable rule set memory (RAM). On-chip fuzzification operation by a table lookup method. On-chip defuzzification operation by a centroid method. Reconfigurable architecture for processing two rule formats. RAM/datapath redundancy for higher yield It can store and execute 51 if-then rule of the following format: IF A and B and C and D Then Do E, and Then Do F. With this format, the chip takes four inputs and produces two outputs. By software reconfiguration, it can store and execute 102 if-then rules of the following simpler format using the same datapath: IF A and B Then Do E. With this format the chip takes two inputs and produces one outputs. We have built two VME-bus board systems based on this chip for Oak Ridge National Laboratory (ORNL). The board is now installed in a robot at ORNL. Researchers uses this board for experiment in autonomous robot navigation. The Fuzzy Logic system board places the Fuzzy chip into a VMEbus environment. High level C language functions hide the operational details of the board from the applications programme . The programmer treats rule memories and fuzzification function memories as local structures passed as parameters to the C functions. ASIC fuzzy inference hardware is extremely fast, but they are limited in generality. Many aspects of the design are limited or fixed. We have proposed to designing a are limited or fixed. We have proposed to designing a fuzzy information processor as an application specific processor using a quantitative approach. The quantitative approach was developed by RISC designers. In effect, we are interested in evaluating the effectiveness of a specialized RISC processor for fuzzy information processing. As the first step, we measured the possible speed-up of a fuzzy inference program based on if-then rules by an introduction of specialized instructions, i.e., min and max instructions. The minimum and maximum operations are heavily used in fuzzy logic applications as fuzzy intersection and union. We performed measurements using a MIPS R3000 as a base micropro essor. The initial result is encouraging. We can achieve as high as a 2.5 increase in inference speed if the R3000 had min and max instructions. Also, they are useful for speeding up other fuzzy operations such as bounded product and bounded sum. The embedded processor's main task is to control some device or process. It usually runs a single or a embedded processer to create an embedded processor for fuzzy control is very effective. Table I shows the measured speed of the inference by a MIPS R3000 microprocessor, a fictitious MIPS R3000 microprocessor with min and max instructions, and a UNC/MCNC ASIC fuzzy inference chip. The software that used on microprocessors is a simulator of the ASIC chip. The first row is the computation time in seconds of 6000 inferences using 51 rules where each fuzzy set is represented by an array of 64 elements. The second row is the time required to perform a single inference. The last row is the fuzzy logical inferences per second (FLIPS) measured for ach device. There is a large gap in run time between the ASIC and software approaches even if we resort to a specialized fuzzy microprocessor. As for design time and cost, these two approaches represent two extremes. An ASIC approach is extremely expensive. It is, therefore, an important research topic to design a specialized computing architecture for fuzzy applications that falls between these two extremes both in run time and design time/cost. TABLEI INFERENCE TIME BY 51 RULES {{{{Time }}{{MIPS R3000 }}{{ASIC }}{{Regular }}{{With min/mix }}{{6000 inference 1 inference FLIPS }}{{125s 20.8ms 48 }}{{49s 8.2ms 122 }}{{0.0038s 6.4㎲ 156,250 }} }}