• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.18-29
• /
• 2022

Recently, cooperative intelligent transport systems (C-ITS) testbeds have been deployed in great numbers, and advanced autonomous driving research using V2X communication technology has been conducted actively worldwide. In particular, the broadcasting services in their beginning days, giving warning messages, basic safety messages, traffic information, etc., gradually developed into advanced network services, such as platooning, remote driving, and sensor sharing, that need to perform real-time. In addition, technologies improving these advanced network services' throughput and latency are being developed on many fronts to support these services. Notably, this research analyzed the network latency requirements of the advanced network services to develop a remote driving service for the droid type low-speed robot based on the 3GPP C-V2X communication technology. Subsequently, this remote driving service's performance was evaluated using system modeling (that included the operator behavior) and simulation. This evaluation showed that a respective core and access network latency of less than 30 ms was required to meet more than 90 % of the remote driving service's performance requirements under the given test conditions.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.81-90
• /
• 2016

As an autonomous driving vehicle (AV) need to cope with external road conditions by itself, its perception performance for road environment should be better than that of a human driver. A vision sensor, one of AV sensors, performs lane detection function to percept road environment for performing safe vehicle steering, which relates to define vehicle heading and lane departure prevention. Performance standards for a vision sensor in an ADAS(Advanced Driver Assistance System) focus on the function of 'driver assistance', not on the perception of 'independent situation'. So the performance requirements for a vision sensor in AV may different from those in an ADAS. In assuming that an AV keep previous steering due to lane detection failure, this study calculated lane departure distances between the AV location following curved road alignment and the other one driving to the straight in a curved section. We analysed lane departure distance and time with respect to the allowance of lane detection malfunction of an AV vision sensor. With the results, we found that an AV would encounter a critical lane departure situation if a vision sensor loses lane detection over 1 second. Therefore, it is concluded that the performance standards for an AV should contain more severe lane departure situations than those of an ADAS.

• Review of KIISC
• /
• v.19 no.4
• /
• pp.11-20
• /
• 2009

차량네트워크(VANET)는 이동형 에드 혹 네트워크의 가장 유망한 응용환경으로 인식되어 지고 있다. 특히, 차량간의 안전주행 통신인 V2V의 경우 운전자의 안전을 위한 통신기술로 주목받고 있다. 안전주행을 위해서 V2V에서 송수신되는 메시지는 다양한 네트워크 공격을 막기 위해서 반드시 인증이 되어야 하는 반면 운전자의 위치 프라이버시를 보호하기 위해서는 익명성이 보장되어야 한다. 이러한 보안 속성은 V2V 통신만의 고유한 성질로써, 현재 인증과 프라이버시를 동시에 보장하기 위한 인증기술에 대한 연구가 활발히 진행되고 있다. 본 고에서는 프라이버시를 보장하는 V2V 인증 프로트콜들을 분석하고 보안 및 효율성 관점에서 각 프로트콜을 비교분석한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.75-81
• /
• 2022

Autonomous vehicles, which can dramatically solve the lack of parking spaces, are making great progress through deep reinforcement learning. Activation functions are used for deep reinforcement learning, and various activation functions have been proposed, but their performance deviations were large depending on the application environment. Therefore, finding the optimal activation function depending on the environment is important for effective learning. This paper analyzes 12 functions mainly used in reinforcement learning to compare and evaluate which activation function is most effective when autonomous vehicles use deep reinforcement learning to learn parking. To this end, a performance evaluation environment was established, and the average reward of each activation function was compared with the success rate, episode length, and vehicle speed. As a result, the highest reward was the case of using GELU, and the ELU was the lowest. The reward difference between the two activation functions was 35.2%.

• Journal of the Korean Society for Railway
• /
• v.17 no.1
• /
• pp.19-27
• /
• 2014

Urban railway vehicles operate in downtown areas. Due to increases in the number of passengers and changes in the service plans, railway vehicles are expected to operate on sharp curved tracks. However, on these tracks, the running stability of the railway vehicles is significantly decreased and the creepage is increased. Creepage causes the wheel/rail to wear and vibration. Therefore, reducing the creepage helps ensure the running stability and can be beneficial for the environment and cost. In this paper, the longitudinal creepage is analyzed using a railway vehicle model on a sharp curved track. Furthermore, in order to minimize the problems when a railway vehicle runs on a sharp curved track, the characteristics of a bogie are optimized using response optimization.

• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.127-135
• /
• 2009

Most traffic information that drivers receive while driving are stored in their short-term memory and disappear within a few seconds. Contemporary modeling approaches using a dummy variable can't fully explain this phenomenon. As such, this study proposes to use utility functions of real-time in-vehicle traffic safety information (IVTSI), analyzing its safety impacts based on empirical data from an on-site driving experiment at signalized intersection approach with a limited visibility. For this, a driving stability evaluation model is developed based on driver's driving speed choice, applying an ordered probit model. To estimate the specified utility functions, the model simultaneously accounts for various factors, such as traffic operation, geometry, road environment, and driver's characteristics. The results show three significant facts. First, a normal density function (exponential function) is appropriate to explain the utility of IVTSI proposed under study over time. Second, the IVTSI remains in driver's short-term memory for up to nearly 22 second after provision, decreasing over time. Three, IVTSI provision appears more important than the geometry factor but less than the traffic operation factor.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.99-102
• /
• 2016

교통표지판 검출 및 인식은 차량의 자율주행 및 ADAS (Advanced Driver Assistance System)의 필수적인 요소이다. 교통표지판의 각종 표식을 인식하기 위해서는 먼저 교통표지판 영역을 검출해야 하며, 이 작업은 통상적으로 교통표지판에 포함된 빨간색을 추출하는 컬러 필터링을 통해 이루어진다. 하지만 차량 영상에 나타나는 색상 성분은 태양광의 방향이나 날씨 등에 상당한 영향을 받으며 이러한 조도 환경은 차량이 주행하게 되면 시간적으로도 수시로 변화한다. 더군다나 사용하는 카메라의 내부적인 특성에 따라서도 색상 성분의 분포가 달라지기 때문에 컬러 필터링을 위한 임계값은 고정값을 사용하기 보다는 적응적으로 변화시킬 필요가 있다. 본 논문에서는 다양한 조도 환경과 다양한 카메라 종류에 따라서 영상 내 교통표지판의 빨간색 성분의 분포를 분석하고 이를 바탕으로 임계값을 가변적으로 설정하는 방법을 제안한다. 그리고 모의실험을 통해 제안 방법을 적용하면 고정된 임계값을 사용한 방법보다 조도변화에 강인하게 교통표지판 영역을 검출할 수 있음을 확인하였다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.447-449
• /
• 2024

본 논문에서 다양한 환경적 요인에서 촬영한 이미지 데이터를 활용하여 신호등 위치의 정확한 탐지 및 신호등의 색상 인식을 통해 교통 신호를 판별하는데 사용되는 컴퓨터 비전 기반의 신호등 인식 시스템 알고리즘을 제안하였다. 이를 통해 기존에 신호를 인식하던 LiDAR 및 RADAR 센서를 대신해 카메라를 사용함으로써 자율주행 차의 제작비용 감소를 기대할 수 있다. 또한 다양한 환경의 이미지 데이터를 통해 실험을 진행하였고 이러한 실험결과를 분석하고 적용함으로써 악천후에서의 효과적인 신호등 인식 시스템을 구축하는데 기여하고자 한다.

• Electronics and Telecommunications Trends
• /
• v.30 no.5
• /
• pp.11-21
• /
• 2015

최근 IT기술과 산업 간 융합이 활발한 가운데 자동차에도 각종 첨단 IT기술이 접목되면서 운전자의 안전과 편의성이 향상된 스마트카(smart car)가 속속 개발되고 있다. 가까운 미래에 스마트카의 도움으로 운전자가 전방주시 의무에서 자유롭게 될 수 있게 되면, 운행 중에 언제 어디서나 모바일 인터넷을 통한 정보접근이 가능하도록 지원하는 컴퓨팅 환경인 자동차 사물인터넷(Internet of Vehicles, Automotive IoT)이 중요하게 대두될 것으로 전망된다. 자동차 사물인터넷의 개념이 아직은 명확히 잡혀있지 않지만, 대체로 모바일 연결성(mobile connectivity)을 중심으로, 교통안전 혼잡해소뿐만 아니라 다양한 사용자 맞춤형 서비스 산업을 창출할 수 있는 컴퓨팅 환경을 의미한다. 즉, 운전자와 자동차, 자동차와 주변환경 및 교통인프라, 그리고 일상생활의 모든 요소가 자동차를 매개로 해서 유기적으로 연결되는 컴퓨팅 환경을 의미하며, 가까운 미래에 이런 컴퓨팅 환경을 지원하는 자동차가 상용화될 것으로 전망된다. 본고에서는 이러한 전망을 반영하여 자동차 사물인터넷 환경의 스마트카에 적용될 주요 기술과 서비스를 분석하고, 스마트카와 자율주행의 핵심기술인 인포테인먼트 플랫폼의 주요 동항 및 이슈를 살펴보고자 한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.132-151
• /
• 2022

Vehicle localization is one of the core technologies for autonomous driving. Image-based localization provides location information efficiently, and various related studies have been conducted. However, the image-based localization methods using feature points or lane information has a limitation that positioning accuracy may be greatly affected by road and driving environments. In this study, we propose a line segment matching framework for accurate vehicle localization. The proposed framework consists of four steps: line segment extraction, merging, overlap area detection, and MSLD-based segment matching. The proposed framework stably performed line segment matching at a sufficient level for vehicle positioning regardless of vehicle speed, driving method, and surrounding environment.