http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박휘성(Hwi-sung Park),이희란(Hee-ran Lee),유명주(Myoung Ju Yu),전성혁(Seong Hyeok Jeon) 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
본 논문에서는 UAS (Unmanned Aerial Systwms) 에서 보조링크로 활용되는 C2 (Command and Control) 링크의 다중대역 동시수신구조의 성능분석 결과를 제시한다. 다중대역 동시수신구조에서는 ADC (Analog to Digital Converter) 양자화/포화 오류와 간섭신호로 인한 성능 열화가 존재한다. 무인기 C2링크 다중대역 동시수신기의 ADC 입력 레벨을 -15dBm으로 설정하였을 때 양자화/포화의 영향성이 없는 신호레벨 영역을 확인하였고, 인접대역으로 인한 성능 열화가 약 0.1dB 존재한다는 것을 확인하였다. 제안하는 다중대역 동시수신 구조는 거의 성능의 열화가 없고, 무인기 C2 링크의 운용환경에 적합한 것을 확인하였다.
통합 필터 변별도와 그래프 컬러링을 이용한 전술통신망 백본 무선 링크의 주파수 지정 방법
함재현,박휘성,이은형,최증원,Ham, Jae-Hyun,Park, Hwi-Sung,Lee, Eun-Hyoung,Choi, Jeung-Won 한국군사과학기술학회 2015 한국군사과학기술학회지 Vol.18 No.4
The tactical communications network has to be deployed rapidly at military operation area and support the communications between the military command systems and the weapon systems. For that, the frequency assignment is required for backbone wireless links of tactical communications network without frequency interferences. In this paper, we propose a frequency assignment method using net filter discrimination (NFD) and graph coloring to avoid frequency interferences. The proposed method presents frequency assignment problem of tactical communications network as vertex graph coloring problem of a weighted graph. And it makes frequency assignment sequences and assigns center frequencies to communication links according to the priority of communication links and graph coloring. The evaluation shows that this method can assign center frequencies to backbone communication links without frequency interferences. It also shows that the method can improve the frequency utilization in comparison with HTZ-warfare that is currently used by Korean Army.
커리큘럼 기반 심층 강화학습을 이용한 좁은 틈을 통과하는 무인기 군집 내비게이션
최명열,신우재,김민우,박휘성,유영빈,이민,오현동 한국로봇학회 2024 로봇학회 논문지 Vol.19 No.1
This paper introduces collective navigation through a narrow gap using a curriculum-based deep reinforcement learning algorithm for a swarm of unmanned aerial vehicles (UAVs). Collective navigation in complex environments is essential for various applications such as search and rescue, environment monitoring and military tasks operations. Conventional methods, which are easily interpretable from an engineering perspective, divide the navigation tasks into mapping, planning, and control; however, they struggle with increased latency and unmodeled environmental factors. Recently, learning-based methods have addressed these problems by employing the end-to-end framework with neural networks. Nonetheless, most existing learning-based approaches face challenges in complex scenarios particularly for navigating through a narrow gap or when a leader or informed UAV is unavailable. Our approach uses the information of a certain number of nearest neighboring UAVs and incorporates a task-specific curriculum to reduce learning time and train a robust model. The effectiveness of the proposed algorithm is verified through an ablation study and quantitative metrics. Simulation results demonstrate that our approach outperforms existing methods.