• Journal of Positioning, Navigation, and Timing
• /
• 제10권4호
• /
• pp.235-242
• /
• 2021

Unmanned Aerial Vehicles (UAVs), which were used for military purposes, are gradually expanding their application fields under the influence of electrification and digitalization. Starting from the field of aerial imaging and Intelligence Surveillance and Reconnaissance (ISR) mission, nowadays the possibility of Urban Air Mobility (UAM), which transports passengers and cargo with drones, is widely under discussion. In order to occupy the rapidly growing global unmanned aerial vehicle market in advance, it is necessary to secure core technologies and develop key UAVs components based on the new technologies. In the navigation field, it is necessary to secure a precise position with guaranteed reliability and continuity, unrelated to the operating environments. The reliability and continuity should be secured in the algorithm level and in the H/W component levels also. In order to achieve this technical goal, the Ministry of Science and ICT has launched the 'Unmanned Vehicle Core Technology Research and Development Program' in 2019 to support the R&D on the unmanned vehicle technologies. In this paper, authors introduce the unmanned vehicle core technology research and development program to the related researchers. The authors summarize the backgrounds of the program and show the technological tasks and objectives on the sub-programs in the unmanned vehicle navigation program. We present the program schedules especially focused on the test and evaluation of the developed technologies and components.

• 한국군사과학기술학회지
• /
• 제25권5호
• /
• pp.476-486
• /
• 2022

Synthetic dynamic infrared image generation from the given virtual environment is being the primary goal to simulate the output of the infra-red(IR) camera installed on a vehicle to evaluate the control algorithm for various search & reconnaissance missions. Due to the difficulty to obtain actual IR data in complex environments, Artificial intelligence(AI) has been used recently in the field of image data generation. In this paper, CycleGAN technique is applied to obtain a more realistic synthetic IR image. We added the Structural Similarity Index Measure(SSIM) loss function to the L1 loss function to generate a more realistic synthetic IR image when the CycleGAN image is generated. From the simulation, it is applicable to the guided-missile flight simulation tests by using the synthetic infrared image generated by the proposed technique.

• 로봇학회논문지
• /
• 제18권3호
• /
• pp.299-307
• /
• 2023

In the midst of accelerating wars around the world, unmanned robot technology that can guarantee the safety of human life is emerging. ERP-42 is a modular platform that can be used according to the application. In the field of defense, it can be used for transporting supplies, reconnaissance and surveillance, and medical evacuation in conflict areas. Due to the nature of the military environment, atypical environments are predominant, and in such environments, the platform's path followability is an important part of mission performance. This paper focuses on reducing the minimum turning radius in terms of improving path followability. The minimum turning radius of the existing 2WS/2WD in-wheel platform was reduced by increasing the torque of the independent driving in-wheel motor on the rear wheel to generate oversteer. To determine the degree of oversteer, two GPS were attached to the center of the front and rear wheelbases and measured. A closed-loop speed control method was used to maintain a constant rotational speed of each wheel despite changes in load or torque.

• 대한임베디드공학회논문지
• /
• 제18권4호
• /
• pp.185-194
• /
• 2023

Currently, drones are used in various fields such as transportation, agriculture and military. Especially, drones for military use are developed and utilized in many ways such as reconnaissance and bombing to minimize one's own damages. Nevertheless, they are developed as new weapons of modern types, so it is difficult to use them together with existing weapons. In this study, a drone program for effective bombing of mortar, which is often used in modern warfare, is developed. In mortar, a forward soldier comprehends the location of enemy for its distance and altitude, input them in data computer of launching angle, and applies the result value to cannon to launch. However, the existing method has low accuracy of bombing because observing shall be done within 1km from the target, and measuring accurate direction and velocity of the wind is difficult. Whereas, in the program of this study, the location of target, GPS, direction and velocity of the wind, and altitude are measured through drone. Each digit is used to calculate bombing specification for optimal bombing through the calculating formula of launching angle. In addition, when specifications are input in the program, the calculation is done automatically, so that it can be used in various mortars and shells. With the use of the program in this study, the location of enemy can be comprehended, and bombing specifications can be calculated quickly. It also enables the intensity of the wind to be applied for accurate bombing.

• Wind and Structures
• /
• 제36권6호
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• Geomechanics and Engineering
• /
• 제34권1호
• /
• pp.87-102
• /
• 2023

The cover plate and the building loads often make the semi-covered deep excavations with existing buildings bearing asymmetric load, presenting different deformation characteristics with normal excavations, which is not absolutely clear in current studies. Based on a typical engineering, the building storeys, the basement storeys, the pile length, the existence of the cover plate (CP) and the depth of the diaphragm walls (DW) were selected as variables, and 44 groups of simulation were designed to study the influence of existing buildings and the semi-covered supporting system on the deformation of the excavations. The results showed that the maximum lateral displacement of DW, δ_hm, and the depth of δ_hm, H_m, are affected seriously by the building storeys and the basement storeys. Asymmetric structures and loading lead to certain lateral displacement of DW at the beginning of excavation, resulting in different relationships between δ_hm and excavation depth, H. The maximum surface settlement outside the pit, δ_vm, increases significantly and the location, d_m, moves away from the pit with the building storeys increases. δ_vm has a quadratic correlation with H due to the existing buildings. CP and building load will affect the style of the lateral displacement curve of DW seriously in different aspects.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.538-540
• /
• 2021

본 논문에서는 드론의 표적탐지 임무 수행 시 상대운동 정보 제공을 위하여 지정된 표적을 탐지하고 인식하는 스마트 표적탐지 시스템을 제안하였다. 제안된 시스템은 적절한 정확도(i.e. mAP, IoU) 및 높은 실시간성을 동시에 확보할 수 있는 알고리즘을 개발하는데 중점을 두었다. 제안된 시스템은 Google Inception V2 딥러닝 모델의 100k 학습 후 test 결과가 1.0에 가까운 정확성을 보였고 실시간성도 Nvidia GTX 2070 Max-Q를 기반으로 한 고성능 노트북 활용 시에 추론 속도가 약 60-80[Hz]를 기록하였다. 제안된 스마트 표적탐지 시스템은 드론과 같이 운용되어 컴퓨터 영상처리를 활용하여 표적을 자동으로 인식하고 표적을 따라가면서 감시정찰 임무를 성공적으로 수행하는데 도움이 될 것이다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제65차 동계학술대회논문집 30권1호
• /
• pp.325-326
• /
• 2022

최근 무인 항공 기술의 발전과 함께 드론의 상업적 활용이 가속화되고 있다. 산업계 및 학계에서는 인공지능, 사물인터넷 등 지능정보기술을 활용하여 드론 응용에 자율 비행을 적용하고자 노력하고 있지만 해결되지 못한 문제들이 산적해 있다. 그러므로 완전 자율 비행은 아니지만, 드론 조종에 경험이 없는 비전문가도 드론을 용이하게 조정할 수 있는 반자동 방식의 비행 제어를 채택한 드론 응용이 개발이 필요하다. 따라서 본 논문에서는 실내환경에서 정찰 임무 수행을 위한 반자동 비행 조종 시스템을 제안한다. 제안한 시스템은 교차로 지점마다 사용자에게 이동 방향을 선택할 기회를 제공하고 교차로 간 일정한 속도 및 벽면과의 일정한 간격으로 자율비행하도록 제어한다. 또한, 실내 측위 기술인 ORB-SLAM 알고리즘을 이용하여 드론이 실내 공간 및 자신의 위치를 파악하도록 한다.

• 항공우주시스템공학회지
• /
• 제17권5호
• /
• pp.28-33
• /
• 2023

본 연구에서는 기존 항공기 탑재 EO/IR 장비 내부 짐벌과 방진구를 스프링으로 대체하여, 외부 진동 감쇠 효과와 6자유도 구동이 가능한 내부 플랫폼 시스템을 분석하였다. 제안한 스프링 안정화 장치는 기계제작 스프링과 스프링 모듈, 스프링 모듈-내부 플랫폼 간 연결을 위한 지지 구조물로 구성된다. 본 연구에서는 모드 해석을 통해 스프링의 재질을 선정하였으며, 랜덤 진동 해석을 통해 스프링 안정화 장치의 구조 건전성을 분석하였다.

• Journal of Astronomy and Space Sciences
• /
• 제40권4호
• /
• pp.149-171
• /
• 2023

ShadowCam is a National Aeronautics and Space Administration Advanced Exploration Systems funded instrument hosted onboard the Korea Aerospace Research Institute (KARI) Korea Pathfinder Lunar Orbiter (KPLO) satellite. By collecting high-resolution images of permanently shadowed regions (PSRs), ShadowCam will provide critical information about the distribution and accessibility of water ice and other volatiles at spatial scales (1.7 m/pixel) required to mitigate risks and maximize the results of future exploration activities. The PSRs never see direct sunlight and are illuminated only by light reflected from nearby topographic highs. Since secondary illumination is very dim, ShadowCam was designed to be over 200 times more sensitive than previous imagers like the Lunar Reconnaissance Orbiter Camera Narrow Angle Camera (LROC NAC). ShadowCam images thus allow for unprecedented views into the shadows, but saturate while imaging sunlit terrain.