• Title/Summary/Keyword: UAS

Search Result 183, Processing Time 0.023 seconds

Analysis of Human Casualties on the Ground in Urban Area due to UAM Crash (UAM 추락 시 인구 밀접 지역 지상 인명피해 분석)

  • Kim, Youn-sil;Choi, In-ho
    • Journal of Advanced Navigation Technology
    • /
    • v.26 no.5
    • /
    • pp.281-288
    • /
    • 2022
  • This study quantitatively analyzed the human casualties that can occur when a multicopter-type Urban Air Mobility (UAM) with a weight of about 1 ton and a speed of about 100 km/h falls in an urban area. Based on the population density and building database in Seoul, the population exposed to collisions in the event of a UAM crash was derived. Through the ballistic descent model, the accident impact radius of the UAM fall was calculated. In addition, the change in human casualties on the ground was analyzed when the accident impact radius increased. Finally, the ground risk map was created for Seoul, and it was confirmed that about 1 to 10 people could be injured when a UAM crash.

The Development of Rule-based AI Engagement Model for Air-to-Air Combat Simulation (공대공 전투 모의를 위한 규칙기반 AI 교전 모델 개발)

  • Minseok, Lee;Jihyun, Oh;Cheonyoung, Kim;Jungho, Bae;Yongduk, Kim;Cheolkyu, Jee
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.25 no.6
    • /
    • pp.637-647
    • /
    • 2022
  • Since the concept of Manned-UnManned Teaming(MUM-T) and Unmanned Aircraft System(UAS) can efficiently respond to rapidly changing battle space, many studies are being conducted as key components of the mosaic warfare environment. In this paper, we propose a rule-based AI engagement model based on Basic Fighter Maneuver(BFM) capable of Within-Visual-Range(WVR) air-to-air combat and a simulation environment in which human pilots can participate. In order to develop a rule-based AI engagement model that can pilot a fighter with a 6-DOF dynamics model, tactical manuals and human pilot experience were configured as knowledge specifications and modeled as a behavior tree structure. Based on this, we improved the shortcomings of existing air combat models. The proposed model not only showed a 100 % winning rate in engagement with human pilots, but also visualized decision-making processes such as tactical situations and maneuvering behaviors in real time. We expect that the results of this research will serve as a basis for development of various AI-based engagement models and simulators for human pilot training and embedded software test platform for fighter.

Development and Validation of Dynamic Model for KC-100 UAS (KC-100 항공기 무인화를 위한 운동모델 구축 및 검증)

  • Seong Hyeon Kim;Ji Bon Kim;Jung Hoon Lee;Eung Tai Kim;Byoung Soo Kim
    • Journal of Aerospace System Engineering
    • /
    • v.17 no.1
    • /
    • pp.79-87
    • /
    • 2023
  • To design a control law of an aircraft, an accurate aircraft dynamic model is required. To obtain an aerodynamic database (DB) to build a dynamic model, a large number of wind tunnel tests are typically required. However, when flight test data of target aircraft exist such as in the process of unmanned conversion of a manned aircraft, an aircraft dynamic model can be obtained through a parameter estimation method and a DB tuning procedure. This paper describes a nonlinear model construction process and a verification method for KC-100 OPV aircraft. Flight data compatibility analysis was performed to determine suitability of the estimation method application. Linear model estimation was performed using the maximum likelihood estimation method. Results of aerodynamic DB tuning process and verification applying the FFS standard to the nonlinear model constructed are presented.

UAM Parallel Corridor Collision Risk Analysis based on Collision Risk Model (충돌 위험 모델을 활용한 UAM 평행 항로 충돌 위험 분석)

  • Youn-sil Kim;Joong-won Bae
    • Journal of Advanced Navigation Technology
    • /
    • v.27 no.5
    • /
    • pp.561-567
    • /
    • 2023
  • In this study, the collision risk of the UAM (Urban Air Mobility) corridor was analyzed using a collision risk model applied to the manned aircraft corridor. According to the K-UAM roadmap and operating concept, UAM is expected to fly on a designated route similar to existing manned aircraft operations and operate on two routes, traveling back and forth between the departure point and the destination point. Among domestic manned aircraft routes, the manned aircraft operation between Gimpo Airport and Jeju Airport is similar to this and takes the form of a parallel route with a lateral separation distance between the two routes. In this study, we analyzed the collision risk of the UAM corridor according to the lateral separation distance using a collision risk model used to analyze the collision risk of manned aircraft parallel routes for a similar type of UAM corridor. Based on this, we finally analyzed how many parallel routes could be installed within the width of the Han River, considering the K-UAM demonstration route.

Analysis and Implication on the International Regulations related to Unmanned Aircraft -with emphasis on ICAO, U.S.A., Germany, Australia- (세계 무인항공기 운용 관련 규제 분석과 시사점 - ICAO, 미국, 독일, 호주를 중심으로 -)

  • Kim, Dong-Uk;Kim, Ji-Hoon;Kim, Sung-Mi;Kwon, Ky-Beom
    • The Korean Journal of Air & Space Law and Policy
    • /
    • v.32 no.1
    • /
    • pp.225-285
    • /
    • 2017
  • In regard to the regulations related to the RPA(Remotely Piloted Aircraft), which is sometimes called in other countries as UA(Unmanned Aircraft), ICAO stipulates the regulations in the 'RPAS manual (2015)' in detail based on the 'Chicago Convention' in 1944, and enacts provisions for the Rules of UAS or RPAS. Other contries stipulates them such as the Federal Airline Rules (14 CFR), Public Law (112-95) in the United States, the Air Transport Act, Air Transport Order, Air Transport Authorization Order (through revision in "Regulations to operating Rules on unmanned aerial System") based on EASA Regulation (EC) No.216/2008 in the case of unmanned aircaft under 150kg in Germany, and Civil Aviation Act (CAA 1998), Civil Aviation Act 101 (CASR Part 101) in Australia. Commonly, these laws exclude the model aircraft for leisure purpose and require pilots on the ground, not onboard aricraft, capable of controlling RPA. The laws also require that all managements necessary to operate RPA and pilots safely and efficiently under the structure of the unmanned aircraft system within the scope of the regulations. Each country classifies the RPA as an aircraft less than 25kg. Australia and Germany further break down the RPA at a lower weight. ICAO stipulates all general aviation operations, including commercial operation, in accordance with Annex 6 of the Chicago Convention, and it also applies to RPAs operations. However, passenger transportation using RPAs is excluded. If the operational scope of the RPAs includes the airspace of another country, the special permission of the relevant country shall be required 7 days before the flight date with detail flight plan submitted. In accordance with Federal Aviation Regulation 107 in the United States, a small non-leisure RPA may be operated within line-of-sight of a responsible navigator or observer during the day in the speed range up to 161 km/hr (87 knots) and to the height up to 122 m (400 ft) from surface or water. RPA must yield flight path to other aircraft, and is prohibited to load dangerous materials or to operate more than two RPAs at the same time. In Germany, the regulations on UAS except for leisure and sports provide duty to avoidance of airborne collisions and other provisions related to ground safety and individual privacy. Although commercial UAS of 5 kg or less can be freely operated without approval by relaxing the existing regulatory requirements, all the UAS regardless of the weight must be operated below an altitude of 100 meters with continuous monitoring and pilot control. Australia was the first country to regulate unmanned aircraft in 2001, and its regulations have impacts on the unmanned aircraft laws of ICAO, FAA, and EASA. In order to improve the utiliity of unmanned aircraft which is considered to be low risk, the regulation conditions were relaxed through the revision in 2016 by adding the concept "Excluded RPA". In the case of excluded RPA, it can be operated without special permission even for commercial purpose. Furthermore, disscussions on a new standard manual is being conducted for further flexibility of the current regulations.

  • PDF

Secure Framework for SIP-based VoIP Network (SIP 프로토콜을 기반으로한 VOIP 네트워크를 위한 Secure Framework)

  • Han, Kyong-Heon;Choi, Sung-Jong;Choi, Dong-You;Bae, Yong-Guen
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2008.05a
    • /
    • pp.295-297
    • /
    • 2008
  • Session Initiation Protocol (SIP) has become the call control protocol of choice for Voice over IP (VoIP) networks because of its open and extensible nature. However, the integrity of call signaling between sites is of utmost importance, and SIP is vulnerable to attackers when left unprotected. Currently a hop-by-hop security model is prevalent, wherein intermediaries forward a request towards the destination user agent server (UAS) without a user agent client (UAC) knowing whether or not the intermediary behaved in a trusted manner. This paper presents an integrated security model for SIP-based VoIP network by combining hop-by-hop security and end-to-end security.

  • PDF

A Transition based Joint Model for Korean POS Tagging & Dependency Parsing using Deep Learning (딥러닝을 이용한 전이 기반 한국어 품사 태깅 & 의존 파싱 통합 모델)

  • Min, Jin-Woo;Na, Seung-Hoon;Sin, Jong-Hoon
    • Annual Conference on Human and Language Technology
    • /
    • 2017.10a
    • /
    • pp.97-102
    • /
    • 2017
  • 형태소 분석과 의존 파싱은 자연어 처리 분야에서 핵심적인 역할을 수행하고 있다. 이러한 핵심적인 역할을 수행하는 형태소 분석과 의존 파싱에 대해 일괄적으로 학습하는 통합 모델에 대한 필요성이 대두 되었고 이에 대한 많은 연구들이 수행되었다. 기존의 형태소 분석 & 의존 파싱 통합 모델은 먼저 형태소 분석 및 품사 태깅에 대한 학습을 수행한 후 이어서 의존 파싱 모델을 학습하는 파이프라인 방식으로 진행되었다. 이러한 방식의 학습을 두 번 연이어 진행하기 때문에 시간이 오래 걸리고 또한 형태소 분석과 파싱이 서로 영향을 주지 못하는 단점이 존재하였다. 본 논문에서는 의존 파싱에서 형태소 분석에 대한 전이 액션을 포함하도록 전이 액션을 확장하여 한국어 형태소 분석 & 의존파싱에 대한 통합모델을 제안하였고 성능 측정 결과 세종 형태소 분석 데이터 셋에서 F1 97.63%, SPMRL '14 한국어 의존 파싱 데이터 셋에서 UAS 90.48%, LAS 88.87%의 성능을 보여주어 기존의 의존 파싱 성능을 더욱 향상시켰다.

  • PDF

Korean Dependency Parsing with Multi-layer Pointer Networks (멀티 레이어 포인터 네트워크를 이용한 한국어 의존 구문 분석)

  • Park, Cheoneum;Hwang, Hyunsun;Lee, Changki;Kim, Hyunki
    • Annual Conference on Human and Language Technology
    • /
    • 2017.10a
    • /
    • pp.92-96
    • /
    • 2017
  • 딥 러닝 모델은 여러 히든 레이어로 구성되며, 히든 레이어의 깊이가 깊어질수록 레이어의 벡터는 높은 수준으로 추상화된다. 본 논문에서는 Encoder RNN의 레이어를 여러 층 쌓은 멀티 레이어 포인터 네트워크를 제안하고, 멀티 태스크 학습 기반인 멀티 레이어 포인터 네트워크를 이용한 한국어 의존 구문 분석 모델을 제안한다. 멀티 태스크 학습 모델은 어절 간의 의존 관계와 의존 레이블 정보를 동시에 구하여 의존 구문 분석을 수행한다. 실험 결과, 본 논문에서 제안한 모델이 기존 한국어 의존 구문 분석 연구들 보다 좋은 UAS 92.16%, LAS 89.88%의 성능을 보였다.

  • PDF

Improving Stack LSTMs by Combining Syllables and Morphemes for Korean Dependency Parsing (Stack LSTM 기반 한국어 의존 파싱을 위한 음절과 형태소의 결합 단어 표상 방법)

  • Na, Seung-Hoon;Shin, Jong-Hoon;Kim, Kangil
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.9-13
    • /
    • 2016
  • Stack LSTM기반 의존 파싱은 전이 기반 파싱에서 스택과 버퍼의 내용을 Stack LSTM으로 인코딩하여 이들을 조합하여 파서 상태 벡터(parser state representation)를 유도해 낸후 다음 전이 액션을 결정하는 방식이다. Stack LSTM기반 의존 파싱에서는 버퍼 초기화를 위해 단어 표상 (word representation) 방식이 중요한데, 한국어와 같이 형태적으로 복잡한 언어 (morphologically rich language)의 경우에는 무수히 많은 단어가 파생될 수 있어 이들 언어에 대해 단어 임베딩 벡터를 직접적으로 얻는 방식에는 한계가 있다. 본 논문에서는 Stack LSTM 을 한국어 의존 파싱에 적용하기 위해 음절-태그과 형태소의 표상들을 결합 (hybrid)하여 단어 표상을 얻어내는 합성 방법을 제안한다. Sejong 테스트셋에서 실험 결과, 제안 단어표상 방법은 음절-태그 및 형태소를 이용한 방법을 더욱 개선시켜 UAS 93.65% (Rigid평가셋에서는 90.44%)의 우수한 성능을 보여주었다.

  • PDF

Korean Dependency Parsing with Multi-layer Pointer Networks (멀티 레이어 포인터 네트워크를 이용한 한국어 의존 구문 분석)

  • Park, Cheoneum;Hwang, Hyunsun;Lee, Changki;Kim, Hyunki
    • 한국어정보학회:학술대회논문집
    • /
    • 2017.10a
    • /
    • pp.92-96
    • /
    • 2017
  • 딥 러닝 모델은 여러 히든 레이어로 구성되며, 히든 레이어의 깊이가 깊어질수록 레이어의 벡터는 높은 수준으로 추상화된다. 본 논문에서는 Encoder RNN의 레이어를 여러 층 쌓은 멀티 레이어 포인터 네트워크를 제안하고, 멀티 태스크 학습 기반인 멀티 레이어 포인터 네트워크를 이용한 한국어 의존 구문 분석 모델을 제안한다. 멀티 태스크 학습 모델은 어절 간의 의존 관계와 의존 레이블 정보를 동시에 구하여 의존 구문 분석을 수행한다. 실험 결과, 본 논문에서 제안한 모델이 기존 한국어 의존 구문 분석 연구들 보다 좋은 UAS 92.16%, LAS 89.88%의 성능을 보였다.

  • PDF