• Journal of Astronomy and Space Sciences
• /
• v.35 no.4
• /
• pp.279-286
• /
• 2018

Radar sensors are used for space situational awareness (SSA) to determine collision risk and detect re-entry of space objects. The capability of SSA radar system includes radar sensitivity such as the detectable radar cross-section as a function of range and tracking capability to indicate tracking time and measurement errors. The time duration of the target staying in a range cell is short; therefore, the signal-to-noise ratio cannot be improved through the pulse integration method used in pulse-Doppler signal processing. In this study, a method of improving the signal-to-noise ratio during range migration is presented. The improved detection performance from signal processing gains realized in this study can be used as a basis for comprehensively designing an SSA radar system.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.601-611
• /
• 2007

Onboard ATC performs the train speed ristriction function by receiving the speed limit on sections of track from wayside ATC. Onboard ATC can protect passenger from collision and derailment, and so on. So, the high level of safety and reliability for Onboard ATC is required, and by this reason, it is also required to improve the safety of Onboard ATC by applying the result of safety analysis on the Onboard ATC into its design and developing from the concept definition to the detailed desing phase. The paper introduces, when developing Onboard ATC, the safety improvement of Onboard ATC can be accomplished by applying system requirements from Risk Analysis into software and hardware.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.2
• /
• pp.73-81
• /
• 2018

This paper describes a device platform which the blind can wear to keep path and to get surrounding information during their independent walking. Compared to the existing technologies, the proposed device could be used indoors and outdoors, and maps need not be provided in advance. It is composed of a glasses type device equipped with image sensors, and a portable device that analyzes sensor data for sighted guiding. RGB images and depth images are extracted to generate a walking map based on feature points. It also can cope with the risk of collision with bollard, color cone by applying vertical obstacle detection technology based on floor detection.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.2
• /
• pp.87-94
• /
• 2015

This paper proposes a situation awareness method based on data fusion and independent objects for autonomous driving in on-road environment. The proposed method, designed to achieve an accurate analysis of driving situations in on-road environment, executes preprocessing tasks that include coordinate transformations, data filtering, and data fusion and independent object based situation assessment to evaluate the collision risks of driving situations and calculate a desired velocity. The method was implemented in an open-source robot operating system called ROS and tested on a closed road with other vehicles. It performed successfully in several scenarios similar to a real road environment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.153-156
• /
• 2001

최근 들어 두드러지고 있는 승조원의 승선 기피현상에 따른 항해인력 부족현상을 근원적으로 해결하기 위하여 선박 항해 전반에 걸친 자동화 및 지능화에 대한 연구가 활발히 진행되고 있다. 특히 선박의 자동화된 항해를 위해서는 영역전문자 수준의 안전성과 정확성이 보장된 충돌회피 시스템이 요구된다. 충돌회피는 자선에서 이루어지는 해상 장애물들에 대한 피항 행위로 그 판단 기준은 각 장애물에 대한 충돌 위험도에 기반한다. 본 연구에서는 DCPA와 TCPA를 이용한 기존의 기법에 변침도(VDH: Variation Degree of Heading)의 개념을 추가하여 새로운 충돌 위험도 산출 기법을 제안한다. 입력변수가 되는 DCPA, TCPA, VDH의 퍼지 소속함수를 산출하고, 이를 기반으로 퍼지 규칙을 이용하여 세부적인 충돌 위험도를 산출한다. 본 연구에서 제안하는 기법은 충돌 위험도 산출시 장애물의 직선운항뿐만 아니라 곡선운항에 대한 경로예측이 가능하다는 장점을 지닌다. 과거의 변침도가 다음시점의 변침에 영향을 끼침으로써 장애물의 이동 경로에 대한 예측이 이루어지고, 이를 기반으로 보다 세분화된 충돌위험도 산출이 이루어진다. 제안된 기법은 DCPA와 TCPA만으로 충돌위험도를 산출해 낸 연구와 비교.평가하여 성능을 검증한다.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.92-97
• /
• 2024

This paper provides a study of distributional perspective on reinforcement learning for application in mobile robot navigation. Mapless navigation algorithms based on deep reinforcement learning are proven to promising performance and high applicability. The trial-and-error simulations in virtual environments are encouraged to implement autonomous navigation due to expensive real-life interactions. Nevertheless, applying the deep reinforcement learning model in real tasks is challenging due to dissimilar data collection between virtual simulation and the physical world, leading to high-risk manners and high collision rate. In this paper, we present distributional reinforcement learning architecture for mapless navigation of mobile robot that adapt the uncertainty of environmental change. The experimental results indicate the superior performance of distributional soft actor critic compared to conventional methods.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2014.10a
• /
• pp.185-186
• /
• 2014

전자해도 및 레이더와 같은 첨단운항시스템이 도입되고 있으나, 선박간의 충돌사고는 줄어들고 있지 않고 있으며 전체 사고의 30%를 차지하는 선박충돌사고의 80% 이상이 운항자의 실수에 의해 발생되고 있어, 이를 방지할 수 있는 지능적인 운항지원 시스템이 필요하다. 이를 위하여, 본 연구에서는 선박 충돌위험도 식별 정보를 활용하여 운항자에게 안전운항정보를 지원할 수 있는 시스템을 개발하였다. 기존에 항해레이더에서는 운항자가 특정 선박을 지정하여야만 선박충돌여유거리 및 선박충돌여유시간 등의 충돌예방정보를 얻을 수 있으나, 신규로 개발된 시스템에서는 선박들 중에 충돌위험이 높은 선박들을 자동으로 식별하여 충돌예상선박들의 정보를 실시간으로 제공받을 수 있어, 충돌 전에 미리 사고를 예방하고 신속히 대처할 수 있다. 개발된 시스템은 선박에 탑재하여, 실해역 성능시험을 실시하였다. 본 논문에서는 선박 충돌 위험도 기반의 안전운항 지원 시스템의 특징과 실해역 시험결과에 대해 소개한다.

• Fisheries and Aquatic Sciences
• /
• v.27 no.1
• /
• pp.7-16
• /
• 2024

Fishing is considered one of the most dangerous industries alongside mining that needs further efforts to improve safety. In this study, we have investigated safety management of the gillnet fishing industry in South Korea through identifying safety level and classifying common accident types from the statements of accident com-pensation insurance payments for the last 5 years (2016-2020). There were in total 3,895 accidents and 159 fatalities with an average accident frequency of 5.34 × 10^-2 per year per fisher and an average fatality of 2.18 × 10^-3 fishers per year. We have also identified that 62.4% of the accidents occurred during Fishing (FS), and the most common and the most severe accident type is Slips and Trips (ST) and Other (OT) marine accidents such as collision and capsizing, respectively. The hand was most frequently injured. Finally, the risk assessment indicated that most of the accident types of gillnet fishing in South Korea have unacceptable levels of risks, and it is urgent to implement improved safety measures to reduce accidents during gillnet fishing operation. The findings of this study are expected to provide valuable data to create a safer working environment for fishers working on gillnet fishing vessels.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.67-68
• /
• 2016

해상교통환경평가는 선박 간 항행상황의 위험도를 정량화하여 나타냄으로써 선박의 안전운항을 효과적으로 지원하는 역할을 한다. 대표적인 해상교통환경평가모델로는 ES(Environmental Stress model)와 CR(Collision Risk)모델이 있다. 이러한 모델을 살펴보면, 각각의 평가지수를 이용하여 항행상황의 위험도를 정량화하며, 선박 간 조우관계를 기반으로 평가요소를 구성함을 알 수 있다. 이번 연구에서는 선박 간 조우관계를 포함한 항행상황의 위험도에 영향을 줄 것으로 기대되는 다양한 요소를 고려한 평가지수의 타당성을 살펴보고자 한다. 이를 위하여, AIS data를 이용하여 해상교통환경을 재현하고 분석하였으며, 동일한 항행상황을 ES, CR과 제안한 모델을 이용하여 위험도 평가를 실시하였다. 그 결과를 비교하여 제시함으로써 본 모델이 해상교통환경모델로서 항만 내 통항 안전성 평가에 적용 가능성을 평가하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6B
• /
• pp.859-866
• /
• 2010

Digital vessels can occur large a disaster at sea because vessels in fire and collision in case of certain unforeseen circumstances. In this paper, We propose digital vessel context monitoring system through risk analysis. We propose environment information analysis system using wireless sensor that have to acquire marine environment and context of marine digital vessel. For conducting simulation, we chose 300 data sets to train the neural network. As a result, we obtained about 96% accuracy for fire risk context and we obtained 88.7% accuracy for body of vessel risk context. To improve the accuracy of the system, we implement a FEC (Forward Error Correction) block. We implemented digital vessel context monitoring system that transmitted to diagnosis result in CDMA.