• 한국정보통신학회논문지
• /
• 제10권11호
• /
• pp.1973-1977
• /
• 2006

본 논문에서는 IMU(Inertial Motion Unit), DVL(Doppler Velocity Log), USBL(Ultra Short Base Line) DGPS(Differential Global Positioning System) 등의 센서로부터 취득된 데이터를'융합하여 ROV(Remotely Operated Vehicle)와 AUV(Autonomous Underwater Vehicle)와 같은 수중체의 위치를 지구 전체영역에서 추정하기 위한 기본적인 알고리즘을 다루고 있다. 본 논문에 소개된 알고리즘은 6,000m급 과학 조사용 심해무인잠수정인 해미래[1]의 수중 위치추적에 사용될 예정이다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.325-328
• /
• 2019

자율주행 자동차는 운전자가 개입하지 않고 차량에 부착된 다양한 센서를 통해 얻은 데이터를 기반으로 차량을 스스로 제어하며 설정한 목적지까지 주행한다. 본 논문에서는 단일 카메라와 영상을 사용한 차선 검출하고 추적하는 방법을 제안한다. 영상의 하단 부분만 분리하여 차선을 검출하기 위하여 외곽선 검출 과정을 거친 후 허프 변환을 통해 양 차선의 중심을 구한다. 이 값을 바탕으로 PID 제어로 차량의 차선을 유지한다. 모형 차량과 모형 트랙에서 차선 인식 후 차선을 추적하여 주행하는 동작을 시험하였다. PID 제어를 위헌 적정 각 항의 값을 구하였다. 시험 결과 차선 검출 알고리즘은 성공적으로 동작함을 확인할 수 있었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1411-1412
• /
• 2015

Detection of road lanes is an important technology, which is being used in autonomous vehicles from last few years. This method is very helpful and supportive for the drivers to provide them safety and to avoid road accidents. Alot of methods are being used to detect road lane markings. We can categorize them into three major categories: sensor-based, feature-based, and model-based methods. And in this study we give the comprehensive survey on lane marking techniques.

• 대한임베디드공학회논문지
• /
• 제6권3호
• /
• pp.124-131
• /
• 2011

There are many researches in unmanned vehicles such as UGV(Unmanned Ground Vehicle), AUV(Autonomous Underwater Vehicle). In these researches, differential wheeled mobile robots are mainly used to develop the experimental stage algorithm because of the simplicity of modeling and control. Usually a commercial product used in the study, but in order to operate a commercial product to the restrictions because there would need to use a fixed protocol. Using the microprocessor makes the internal sensors(encoder and INS) and external sensors(ultrasonic sensors, infrared sensors) operate and to determine commands for robot operation. This paper propose a mobile robot design for suitable purpose.

• 전자통신동향분석
• /
• 제34권2호
• /
• pp.51-59
• /
• 2019

Edge computing, which is computing on the edge of the network, is becoming a market value as a means of overcoming the fear of communication disconnection and delay reduction, which are the technical weaknesses of cloud computing. Edge computing is continuously expanding applications in various applications such as safety industry, smart factories, autonomous vehicles, mobile communications, and AR/VR. Looking at edge computing trends from Microsoft, IBM, HPE, and Dell EMC, current edge computing must be understood as an integral binding technology and not as a simple complement to the cloud. This paper examines market trends in edge computing and analyzes the impact of edge computing on major related industries.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• 전자통신동향분석
• /
• 제34권1호
• /
• pp.23-35
• /
• 2019

In the upcoming post-app era, real-time, intelligent and immersive services such as autonomous vehicles, virtual secretaries, virtual reality, and augmented reality are expected to dominate. However, there is a growing demand for new networking and computing infrastructure capabilities because existing physical connection-oriented networks and centralized cloud-based service environments have inherent limitations to effectively accommodate these services. To this end, research on intelligent edge network computing technology is underway to analyze the contextual situation of human and things and to configure the service environment on the network edge so that the application services can be performed optimally. In this article, we describe the technology issues for edge network intelligence and introduce related research trends.

• 자동차안전학회지
• /
• 제11권3호
• /
• pp.13-18
• /
• 2019

According to the development of autonomous vehicles worldwide, the driver's posture may not be a normal posture but the various seating positions. Recently, a numbers of research activities has been focused to protect of driver and passengers in various seating positions as well as seating postures. In this paper, the occupant injury severity was evaluated with different seat positions, seatback angles and TTF times.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5669-5684
• /
• 2018

The new mobile edge network architecture has been required for an increasing amount of traffic, quality requirements, advanced driver assistance system for autonomous driving and new cloud computing demands on highway. This article proposes a hierarchical cloud computing architecture to enhance performance by using adaptive data load distribution for buses that play the role of edge computing server. A vehicular dynamic cloud is based on wireless architecture including Wireless Local Area Network and Long Term Evolution Advanced communication is used for data transmission between moving buses and cars. The main advantages of the proposed architecture include both a reduction of data loading for top layer cloud server and effective data distribution on traffic jam highway where moving vehicles require video on demand (VOD) services from server. Through the description of real environment based on NS-2 network simulation, we conducted experiments to validate the proposed new architecture. Moreover, we show the feasibility and effectiveness for the connected car media service on highway.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.