• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.368-376
• /
• 2021

With the recent development of deep learning technology, autonomous things technology is attracting attention, and DNNs are widely used in embedded systems such as drones and autonomous vehicles. Embedded systems that can perform large-scale operations and process multiple DNNs for high recognition accuracy without relying on the cloud are being released. DNNs with various levels of priority exist within these systems. DNNs related to the safety-critical applications of autonomous vehicles have the highest priority, and they must be handled first. In this paper, we propose a priority-based scheduling framework for DNNs when multiple DNNs are executed simultaneously. Even if a low-priority DNN is being executed first, a high-priority DNN can preempt it, guaranteeing the fast response characteristics of safety-critical applications of autonomous vehicles. As a result of checking through extensive experiments, the performance improved by up to 76.6% in the actual commercial board.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.6
• /
• pp.867-874
• /
• 2021

The IoT (Internet of Things) technology is rapidly becoming an important consideration in many engineering fields in the current 4th industrial era. In recent years, the concepts of digital shipbuilding and smart factories have been adopted as trends in shipyards. However, there is active interest in research on implementing autonomous driving in autonomous vehicles and airplanes, which is currently available in commercial form in a limited capacity. The present study is regarding the path-tracking performance of a boat to accomplish an autonomous driving mission using a flight controller (FC) and real-time kinematic (RTK) global positioning system (GPS) based on an open-source Ardupilot; an actual sea test is also performed using this system on a calm lake. The boat's mission is to evaluate the maneuverability of the self-driving process to a specific point and returning to the home position. For a given speed, the difference between the preset mission trajectory and actual operational trajectory was analyzed, and a series of studies were conducted on the applicability of the system to ships. In addition, the movements and maneuverability of the OmniX-type hull with four propellers were investigated, and the driving path-tracking performance was observed to increase by a maximum of 48%.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.183-187
• /
• 2020

The general Wi-Fi network connection structure is that a number of IoT (Internet of Things) sensor nodes are directly connected to one AP (Access Point) node. In this structure, the range of the network that can be established within the specified specifications such as the range of signal strength (RSSI) to which the AP node can connect and the maximum connection capacity is limited. To overcome these limitations, multiple middleware bridge technologies for dynamic scalability and load balancing were studied. However, these network expansion technologies have difficulties in terms of the rules and conditions of AP nodes installed during the initial network deployment phase In this paper, an intelligent edge computing IoT device is developed for constructing an intelligent autonomous cluster edge computing network and applying it to real-time road danger context aware and notification system through an intelligent risk situation recognition algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.430-431
• /
• 2022

자율주행 차량의 성능을 검증하기 위해서는 다양한 검증용 시나리오가 필요하기 때문에 최근에는 검증용 시나리오를 자동으로 생성하기 위한 연구들이 수행되고 있다. 실세계에서 발생되는 다양한 현상을 반영한 시나리오를 생성하기 위해서는 자율주행 차량의 주변 상황에 대한 측정이 필요하지만, 공간적인 문제로 한계가 발생한다. 이와 같은 데이터 수집의 어려움을 자율주행 차량에 탑재된 블랙박스의 영상을 통해서 생성하는 것이 가능하다. 본 논문에서는 DRQN을 이용하여 자율주행 차량 사고영역을 자동으로 탐지하는 방법을 제안한다. 동영상에서 추출된 프레임을 분석해서 교통사고 원도우의 초기 위치를 설정한다. DRQN 학습 프레임워크로 차량의 특징을 도출한다. 마지막으로 특징을 기반으로 교통사고 원도우의 크기와 위치를 조정해서 교통사고 영역을 정확하게 찾는다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.428-429
• /
• 2022

최근에 자율 주행 자동차에 관련한 관심이 증가하면서 다양한 연구들이 도출되고 있다. 특히, 자율 주행 자동차를 시뮬레이터에서 검증하는 방법은 실 환경과 비교할 때 상대적으로 안전한 성능 검증 방법으로 많이 활용되고 있다. 시뮬레이터의 핵심 기술은 실 환경과 가상 시뮬레이션 환경의 차이를 줄이는 데 있다. 본 논문에서는 Generative Adversarial Imitation Learning(GAIL)[1] 기반으로 자율 주행 자동차 시뮬레이터 내에서 다수의 가상 동적 객체들의 움직임을 제어하는 방법을 제안한다. GAIL은 생성기와 판별기로 구성된다. 생성기는 강화학습 정책 생성기와 전문가 정책 생성기를 포함한다. 판별기는 보상 학습기를 포함한다. GAIL 기반으로 가상 자동차 및 가상 보행자를 제어함으로써 동영상에서의 이동경로를 학습해서 표현할 수 있다.

• Electronics and Telecommunications Trends
• /
• v.38 no.4
• /
• pp.70-80
• /
• 2023

In recent years, our society has shifted from an information society to an intelligent information society, in which computing has become a key factor in shaping and driving social development. In this new era of digital civilization powered by the Internet of Things, traditional data-based computing is no longer sufficient to meet the growing demand for higher levels of intelligence. Therefore, intelligent computing has emerged, reshaping traditional computing and forming new computing paradigms to promote the digital revolution in the era of the Internet of Things, big data, and artificial intelligence. Intelligent computing has greatly expanded the scope of computing through new computing theories, architectures, methodologies, systems, and applications, and it is expanding into diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. This paper introduces the concept and main features of intelligent computing and describes trends in standardization for intelligent computing within the ISO/IEC JTC 1, focusing on the technical trend report on intelligent computing that is currently under development within ISO/ IEC JTC 1/AG 2.

• Journal of Advanced Navigation Technology
• /
• v.22 no.6
• /
• pp.507-513
• /
• 2018

The maritime autonomous surface ship is automatically collects and manages various information necessary for the operation to minimize human intervention and safely perform the mission assigned to the ship. And the ship may autonomously operate the partial or entire route to the destination determined by the ship himself. This ship navigation technology allows partially remote control the ship to be operated if necessary. The maritime autonomous surface ship (MASS) should collect and manage signals of various navigation communication equipments and engines mounted on the ship for safe operation. This requires a common platform technology. In this paper, we propose a common platform that is the core of smart ship implementation. Territorial authorities and ships are connected by satellite or terrestrial communication. In such a communication environment, information is exchanged smoothly in real time. This allows the onshore authorities to monitor ships and provide remote control to enable safe vessel navigation at sea.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1597-1600
• /
• 1997

Most autonomous mobile robots view things only in front of them. As a result they may collide against objects moving from the side or behind. To overcome the problem we have built an Active Omni-directional Range Sensor that can obtain omni-directional depth data by a laser conic plane and a conic mirror. Also we proposed a self-localization algorithm of mobile robot in unknown environment by fusion of Odometer and Active Omn-directional Range Sensor.

• Lingua Humanitatis
• /
• v.1 no.1
• /
• pp.3-11
• /
• 2001

This article maintains that language not only connects the domains of objectivity and subjectivity but simultaneously occupies its own autonomous realm and creates the two domains as well. This means that the role of language in recognizing things in the universe is more important than we usually think, and that the system of language exists independently of the human thinking and objective reality. In this respect, study of language stands as a core subject in humanities, making itself a common denominator for full understanding of philosophy, theology, history, psychology, and arts.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.170-172
• /
• 2021

최근 메타버스, 디지털트윈 등 산업계의 요구가 높아지고, 아울러 스마트홈, 스마트시티, 스마트팩토리와 같은 사물인터넷을 근간으로 하는 상용화 기술의 발전이 가속화되고 있다. 현실 세계의 센서와 구동기의 연결을 통해 사물들을 통한 현실세계 인식 및 제어에 초점을 맞추어 왔던 기존 사물인터넷 기술에서 이제는 사물 간 자율협업을 통한 문제 해결에 대한 요구가 커지고 있다. 본 논문은 미디어사물인터넷 국제표준인 MPEG-IoMT의 아키텍처 및 유스케이스를 통해 미디어사물의 자율협업에 대한 기본적인 개념을 전달하려 한다.