• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.408-414
• /
• 2019

We developed a surveillance tool for collision avoidance of unmanned aerial vehicles (UAVs) in urban areas. In our tool, users can visualize the safety distance on the actual 3D map of urban area. The estimated positions of UAVs are assumed to be obtained based on the long-term evolution (LTE) signals. The safety distance is defined to include two or more signals with bias. The safety distance calculation method used in this paper enables simulation similar to the actual urban areas where signals are frequently biased due to multipath. In the simulation, the parameters were set based on the measured values, and the change of the safety distance according to the number of faulty signals was simulated. As a result, increasing the number of faulty signals led to a longer safety distance as expected.

• Journal of agriculture & life science
• /
• v.52 no.6
• /
• pp.111-125
• /
• 2018

In this study, we evaluated the uniformity of deposition rate and particle size distributions of the variable rate application technique using the unmanned rotorcraft by measuring the spray pattern according to path location in the range of spraying flight. The coefficient of variation (CV) of the lateral coverage rate for the overlapped distribution with the spray swath of 3.6 m in both guidance and auto-pilot flight modes maintaining constant flight speed was about 30% and the CV of the coverage rate by the flight path location was extremely small. Therefore, it was assessed that the variable rate application technology compensating for the variation of ground speed was superior in terms of spray uniformity. In addition, the droplet size distributions in both volume median diameter(VMD) and number median diameter(NMD) were adequate for aerial application and uniform in terms of lateral distribution. Thereafter, we intend to contribute to a precise application on small-scaled fields using the unmanned agricultural rotorcraft by the variable rate application.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.6
• /
• pp.505-513
• /
• 2021

We propose an autonomous mission management software design and verification technique for unmanned aerial vehicles to autonomously mitigate dynamic situation changes occurred in the inside and outside of an aircraft in compliance with the mitigation priority order. The proposed autonomous mission management software is designed in a modular architecture that consists of concurrently executing multiple threads. To verify it, we suggest three verification steps: 1) software integration by checking the expected request/response messages between the threads for all possible dynamic situation changes; 2) integration test to verify the software functionality; 3) performance test to verify the quantitative software performance. Especially, the software integration test environment is built and utilized to carry out the integration and performance tests.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.5
• /
• pp.425-435
• /
• 2021

It is imperative to examine the regulatory trends of leading overseas aviation authorities to accelerate the effort to integrate emerging new air vehicle concepts such as UAS and eVTOL into the existing national airspace system. Whilst EASA seems to react swiftly in relation to regulatory framework by proposing new sets of customised special conditions to cope with a growing demand to introduce new aircraft concepts, understanding of such movement lags behind mainly due to the complexity of EASA's regulation structure, not to mention EU's legal system. Witnessing this situation, this paper reviewed the legal system of the EU which forms the basis of EASA's regulation system together with its own recently published UAS regulations so as to contribute towards the improvement of the aviation regulatory framework.

• Journal of Aerospace System Engineering
• /
• v.16 no.3
• /
• pp.52-62
• /
• 2022

In the SORA methodology developed for the operational risk assessment of a specific category of operation of a UAS, the ground and the air risk levels are determined, and a SAIL indicating the level of assurance and integrity for the corresponding risk is assigned, and accordingly, the operational safety level for the proposed operation. Objectives should be demonstrated at an appropriate level of robustness. Because of the nature of the specific category of operation, people on the ground are the first risk subjects to be considered. The resulting ground risk class plays an important role in the allocation of SAIL. In this paper, the impact on SAIL and OSO according to the final risk level and the reduction of the level through the determination of the ground risk level and the application of mitigation measures among risk assessments for specific categories of UAV operation was investigated.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.295-299
• /
• 2023

In Korea, the birth rate is rapidly decreasing in the 21st century. Accordingly, if the current military service and personnel system are maintained, it will be difficult to maintain even the number of the Army reduced to 365,000. Nevertheless, the Army has a mission to protect the country from external aggression as the last bastion of national defense. To fulfill this mission, there are ways to improve the military service and personnel system, but there are ways to maximize individual combat power to create one warrior that is worth a hundred and overcome the insufficient number of troops through superior mobility to the enemy. This study studied how to solve the shortage of troops as well as strengthen combat power through a combined combat system that can maximize individual combat power and mobility by applying the latter concept, and further analyzed the future battle environment and suggested the developmental direction of the army's combined combat system.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.187-187
• /
• 2022

최근 선박의 자율운항기술이 활발하게 연구되어 오면서, 경로추종 제어 및 충돌회피 등의 자율운항 기술 연구가 많이 진행되고 있으며 그에 따른 시뮬레이션과 실해역 시험 등도 활발하게 수행되고 있다. 이러한 자율운항기술 중 본 연구에서는 AUV(Autonomous Underwater Vehicle) 진회수 시 모함에 활용되며 쌍동선형을 갖는 쌍동형 무인수상선을 대상으로 경로추종 제어에 대한 실해역 시험을 수행한 내용을 소개한다. 대상선인 쌍동형 무인수상선은 배수량이 약 10ton, 최대속도 10knots를 기준으로 설계된 선형이며 Sail drive 타입의 쌍축 추진기를 탑재하고 있으며 Fig. 1에 나타내었다. 실해역 시험은 경기도 화성시에 위치한 제부마리나 전면 해역에서 여러 속도에 대해 Fig. 2의 경로(빨간색)를 활용하여 수행되었다. 해당 경로는 변침각이 45도까지 이루어져 있다. 경로추종 제어 알고리즘은 목표경유점을 향하기 위해 선수각을 제어하는 부분과 목표속도로 추진하기 위해 속도를 제어하는 부분으로 나뉘어져 있다. 선수각 제어 시 경로와 무인선과의 위치 오차를 줄이는 방향으로 선수각이 향할 수 있도록 알고리즘이 설계되었다. 속도 제어의 경우 RPM 별로 실제 속도를 계측하여 데이터화 한 후, 실제 속도가 명령 속도와 다를 경우 RPM을 가감하여 명령 속도로 추진하기 위해 제어할 수 있도록 하였다. Fig. 2에서 파란색 선은 설계한 알고리즘을 활용하여 경로추종 제어를 한 결과의 궤적을 보여준다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.245-261
• /
• 2024

The COVID-19 pandemic has led to the widespread adoption of contactless transactions, resulting in a noticeable increase in the trend towards fully unmanned stores. In such stores, all operational processes are automated, primarily using artificial intelligence (AI) technology. However, this AI technology has several security vulnerabilities, which can be critical in the environment of fully unmanned stores. This paper analyzes the security vulnerabilities that AI-based fully unmanned stores may face, focusing particularly on the object detection model YOLO, demonstrating that Hiding Attacks and Altering Attacks using adversarial patches are possible. It is confirmed that objects with adversarial patches attached may not be recognized by the detection model or may be incorrectly recognized as other objects. Furthermore, the paper analyzes how Data Augmentation techniques can mitigate security threats by providing a defensive effect against adversarial patch attacks. Based on these results, we emphasize the need for proactive research into defensive measures to address the inherent security threats in AI technology used in fully unmanned stores.

• Journal of Aerospace System Engineering
• /
• v.18 no.3
• /
• pp.41-47
• /
• 2024

Recently, as the practical application and commercialization of unmanned aerial vehicles (UAVs) is pursued, interest in ensuring the safety of the UAV is increasing. Because UAV accidents can result in property damage and loss of life, it is important to develop technology to prevent accidents. For this reason, a technique to detect the abnormal flight state of UAVs has been developed based on the AutoEncoder model. However, the existing detection technique is limited in terms of performance and real-time processing. In this paper, we propose a U-Net based abnormal flight detection technique. In the proposed technique, abnormal flight is detected based on the increasing rate of Mahalanobis distance for the reconstruction error obtained from the U-Net model. Through simulation experiments, it can be shown that the proposed detection technique has superior detection performance compared to the existing detection technique, and can operate in real-time in an on-board environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.77-89
• /
• 2024

This paper presents an unmanned store management system that can provide inventory management and theft prevention for displayed products using a small camera that can monitor the shelves of sold products in small and medium-sized stores. This system is a service solution that integrates object recognition, real-time communication, security management, access management, and mobile authentication. The proposed system uses a custom YOLOv5-x model to recognize objects on the display, measure quantities in real time, and support real-time data communication with servers through Raspberry Pie. In addition, the number of objects in the database and the object recognition results are compared to detect suspected theft situations and provide burial images at the time of theft. The proposed unmanned store solution is expected to improve the efficiency of small and medium-sized unmanned store operations and contribute to responding to theft.