• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권3호
• /
• pp.198-204
• /
• 2007

In mobile robotics, ultrasonic sensors became standard devices for collision avoiding. Moreover, their applicability for map building and navigation has exploited in recent years. In this paper, as the preliminary step for developing a multi-purpose autonomous carrier mobile robot to transport trolleys or heavy goods and serve as robotic nursing assistant in hospital wards. The aim of this paper is to present the use of multi-sensor data fusion such as ultrasonic sensor, IR sensor for mobile robot to navigate, and presents an experimental mobile robot designed to operate autonomously within both indoor and outdoor environments. The global map building based on multi-sensor data fusion is applied for recognition an obstacle free path from a starting position to a known goal region, and simultaneously build a map of straight line segment geometric primitives based on the application of the Hough transform from the actual and noisy sonar data. We will give an explanation for the robot system architecture designed and implemented in this study and a short review of existing techniques, Hough transform, since there exist several recent thorough books and review paper on this paper. Experimental results with a real Pioneer DX2 mobile robot will demonstrate the effectiveness of the discussed methods.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제6권4호
• /
• pp.341-349
• /
• 2016

글로벌 시대의 요구에 부응하기 위해 교육 분야에서도 글로벌 교육에 대한 필요성과 중요성이 급증하고 있다. 하지만 보는 관점에 따라 글로벌 교육의 정의와 모델에 대한 합의가 아직 명확하지 않고 글로벌 교육 과정에서의 고비용성, 저효과성, 지속성 결여 등으로 인해 실제 글로벌 교육의 성과는 예상보다 기대에 미치지 못하고 있다. 더구나 예비 교원의 글로벌 능력을 함양하기 위한 글로벌 교육에 관한 연구는 거의 이루지지지 않고 있다. 본 연구는 예비 교원의 글로벌 교육을 중심으로 IT 융합 접근 방법을 연구하였다. 본 연구에서는 우선 국내에서 시행되고 있는 글로벌 교원 양성을 위한 글로벌 교육 프로그램을 비교 분석하였다. 또한, 글로벌 교육에서의 제약 사항들을 해결할 수 있는 IT 융합 교육 시스템을 연구하여 구체적인 IT 융합 글로벌 교육 방법들을 알아보았다. 특히 빅데이터 분석 기술을 기반으로 복수학위나 교환학생 프로그램에 도움을 줄 수 있는 글로벌 교육과정 이수 추천 시스템을 제시하였다.

• Journal of Radiation Protection and Research
• /
• 제37권2호
• /
• pp.63-69
• /
• 2012

The second phase of the national program for fusion energy development in Korea starts from 2012 for design and construction of the fusion DEMO reactor. Radiological assessment for the fusion reactor is one of the key tasks to assure its licensability and the starting point of the assessment is determination of the source terms. As the first effort, the activities of the coolant due to activated corrosion product (ACP) were estimated. Data and experiences from fission reactors were used, in part, in the calculations of the ACP concentrations because of lack of operating experience for fusion reactors. The MCNPX code was used to determine neutron spectra and intensities at the coolant locations and the FISPACT code was used to estimate the ACP activities in the coolant of the fusion DEMO reactor. The calculated specific activities of the most nuclides in the fusion DEMO reactor coolant were 2-15 times lower than those in the PWR coolant, but the specific activities of $^{57}Co$ and $^{57}Ni$ were expected to be much higher than in the PWR coolant. The preliminary results of this study can be used to figure out the approximate radiological conditions and to establish a tentative set of radiological design criteria for the systems carrying coolant in the design phase of the fusion DEMO reactor.

• 대한교통학회지
• /
• 제19권6호
• /
• pp.171-182
• /
• 2001

본 연구는 지점검지체계와 구간검지체계와의 자료합성을 통하여 도심 간선도로 및 지방도로 구간별 효과척도를 산정할 뿐만 아니라 유고검지 및 통행패턴 예측, 네트워크 기종점에 대한 최적/최단 경로를 탐색하는데 기초가 되는 구간 통행시간 추정을 수행한다. 개개 수집원의 자료합성을 위해 퍼지이론과 인공신경 망의 합성모형인 FALEM(Fuzzy Adaptive Learning Estimator for travel time from Multi-information sources)을 개발, 개발된 모형 FALEM에 의해 개개구간의 통행시간을 산출하고 동일시간, 동일구간에서 조사된 실측데이터와의 오차율 비교를 통해 추정된 통행시간을 검증하였다. 테스트 환경은 개발모형에 의해 추정된 구간 통행시간의 적용성을 고려하여 실시간 운영하에서 수행되었다.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 Proceedings of the International Welding/Joining Conference-Korea
• /
• pp.418-424
• /
• 2002

Korean Fusion Reactor(KSTAR) system consists of a vacuum vessel, in-vessel components, cryostat, thermal shield, super-conducting magnets and magnet supporting structures. These systems are in the final stage of engineering design with the involvement of industrial manufacturers. The overall configuration and the detailed dimensions of the KSTAR structure have been determined and the first stage of manufacturing is progressing now. In this study, the fabrication and assembly sequence were evaluated in viewpoint of high strengthening joints and very high accuracy. Especially for this purpose, the special cleaning process and welding process were proposed for high strengthening austenitic stainless steel which shall be used at cryogenic temperature. The draft procedure qualification data for welding process are presented with precise welding data including special narrow groove design. For the cooling line attachment on the surface of inside wall of magnet structure case, Induction brazing technology is introduced with some special jigging system and some consumables.

• International Journal of Ocean System Engineering
• /
• 제1권2호
• /
• pp.102-109
• /
• 2011

This paper describes the implementation of a precise underwater navigation solution using a multiple sensor fusion technique based on USBL, GPS, DVL and AHRS measurements for the operation of a remotely operated mine disposal vehicle (MDV). The estimation of accurate 6DOF positions and attitudes is the key factor in executing dangerous and complicated missions. To implement the precise underwater navigation, two strategies are chosen in this paper. Firstly, the sensor frame alignment to the body frame is conducted to enhance the performance of a standalone dead-reckoning algorithm. Secondly, absolute position data measured by USBL is fused to prevent cumulative integration error. The heading alignment error is identified by comparing the measured absolute positions with the DR algorithm results. The performance of the developed approach is evaluated with the experimental data acquired by MDV in the South-sea trial.

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.390-395
• /
• 2009

In this paper, we design an on-road vehicle detection system based on the combination of a camera and a LIDAR system. In the proposed system, the candidate area is selected from the LIDAR data using a grouping algorithm. Then, the selected candidate area is scanned by an SVM to find an actual vehicle. The morphological edged images are used as features in a camera. The principal components of the edged images called eigencar are employed to train the SVM. We conducted experiments to show that the on-road vehicle detection system developed in this paper demonstrates about 80% accuracy and runs with 20 scans per second on LIDAR and 10 frames per second on camera.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.158-164
• /
• 1999

This paper investigated and evaluated the NASA's Shuttle Imaging Radar-C (SIR-C) multiple frequency SAR data for differential backscattering effects of microwave from the surface geological materials overlying the skarn type mineralization. Although an integrated approach in mineral exploration is more cost effective and is well in use, there are still many technical and scientific issues to be further investigated and researched. In this study we have reprocessed several sets of previously surveyed exploration data and experimented with fuzzy logic digital fusion of the preprocessed data with respect to chosen exploration targets. Among the numerous fuzzy logic operators, which are currently available for a data driven integrated exploration strategy, we used varying combinations of fuzzy MIN, fuzzy MAX, and fuzzy SUM operators along with Gamma operator for fusion of exploration data, including the contact metamorphic zone information. The final exploration target tested was a skarn type W-Mo-F mineralization in the study area. The fuzzy logic derived mineral potential anomaly almost exactly matched the differential backscattering anomalies on the C-band and L-band SIR_C data when overlaid on each other. Although this high degree of correlation between these two data sets is remarkable, the differential backscattering anomaly over the skarn type W-Mo-F mineralization in the study area requires further investigation.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.1099-1110
• /
• 2023

자율주행 및 robot navigation의 인식 시스템은 성능 향상을 위해 다중 센서를 융합(Multi-Sensor Fusion)을 한 후, 객체 인식 및 추적, 차선 감지 등의 비전 작업을 한다. 현재 카메라와 라이다 센서의 융합을 기반으로 한 딥러닝 모델에 대한 연구가 활발히 이루어지고 있다. 그러나 딥러닝 모델은 입력 데이터의 변조를 통한 적대적 공격에 취약하다. 기존의 다중 센서 기반 자율주행 인식 시스템에 대한 공격은 객체 인식 모델의 신뢰 점수를 낮춰 장애물 오검출을 유도하는 데에 초점이 맞춰져 있다. 그러나 타겟 모델에만 공격이 가능하다는 한계가 있다. 센서 융합단계에 대한 공격의 경우 융합 이후의 비전 작업에 대한 오류를 연쇄적으로 유발할 수 있으며, 이러한 위험성에 대한 고려가 필요하다. 또한 시각적으로 판단하기 어려운 라이다의 포인트 클라우드 데이터에 대한 공격을 진행하여 공격 여부를 판단하기 어렵도록 한다. 본 연구에서는 이미지 스케일링 기반 카메라-라이다 융합 모델(camera-LiDAR calibration model)인 LCCNet 의 정확도를 저하시키는 공격 방법을 제안한다. 제안 방법은 입력 라이다의 포인트에 스케일링 공격을 하고자 한다. 스케일링 알고리즘과 크기별 공격 성능 실험을 진행한 결과 평균 77% 이상의 융합 오류를 유발하였다.

• 한국ITS학회:학술대회논문집
• /
• 한국ITS학회 2010년도 춘계학술대회
• /
• pp.148-150
• /
• 2010