• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.72-79
• /
• 2020

To ensure the safety of Advanced Driver Assistance Systems (ADAS) or autonomous vehicles, it is important to recognize the vehicle position, and specifically, the increased accuracy of the lateral position of the vehicle is required. In recent years, the quality of GPS signals has improved a lot and the price has decreased significantly, but extreme urban environments such as tunnels still pose a critical challenge. In this study, we proposed stable and precise lane recognition and tracking methods to solve these two issues via fusion of AVM images and vehicle sensor data using an extended Kalman filter. In addition, the vehicle's lateral position recognition and the abnormal state of RTK GPS were determined using this approach. The proposed method was validated via actual vehicle experiments in urban areas reporting multipath and signal disconnections.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.4
• /
• pp.16-20
• /
• 2022

Accurate state estimation is important for autonomous driving. However, the estimation error increases in situations that a lot of longitudinal slip occurs. Therefore, this paper presents a vehicle state estimation method using an Extended Kalman Filter. The filter estimates the states of the host vehicle robust to wheel slip. It utilizes the measurements of the four-wheel rotational speeds, longitudinal acceleration, yaw-rate, and steering wheel angle. Nonlinear measurement model is represented by Ackermann Model. The main advantage of this approach is the accurate estimation of yaw rate due to the measurement of the steering wheel angle. The proposed algorithm is verified in scenarios of autonomous emergency braking (AEB), lane change (LC), lane keeping (LK) using an automated vehicle. The results show that the proposed algorithm guarantees accurate estimation in such scenarios.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.544-549
• /
• 2005

Web-based collaboration platforms present construction project teams with an opportunity to improve the efficiency of document exchange, better control project communications and enhance team collaboration. However, many construction professionals are still not convinced that these platforms, in their current form, are fit-for-purpose and yield sufficient efficiencies for the construction procurement process. In an attempt to improve the current ICT diffusion process, this paper evaluates the implementation of a web-based collaboration tool on the Lane Cove Tunnel (LCT) project in Sydney, Australia. Moreover, the paper provides strategies for achieving more effective implementation of web-based collaboration platforms in the construction sector.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.97-99
• /
• 2011

본 논문에서는 안전주행지원 솔루션인 스마트폰용 차선이탈경보 애플리케이션의 실행 속도 향상 방법을 연구하였다. 이전 연구에서 스마트폰(iPhone 3GS) 기반의 차선이탈경보 어플리케이션을 개발하였는데 입력 영상의 처리 속도가 1.52fps였다. 본 연구에서는 영상 처리 속도를 향상시키기 위한 최적화 작업을 진행하였으며 기존의 차선이탈경보 어플리케이션의 차선인식 속도보다 프레임당 평균 0.4초 정도 단축되어 약 4fps 속도로 성능을 보였다. 향후 추가 연구를 통해 처리 속도를 좀 더 향상시킬 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1151-1152
• /
• 2023

본 연구에서는 전동 차량의 자율주행 기능 구현을 위한 방법을 제시한다. 주요 구성 요소로는 카메라, PC, 아두이노, 모터드라이브, 가변저항 등이 사용되었다. 카메라를 통해 데이터를 수집한다. YOLOPv2 lane detection 딥러닝 모델을 사용하여 차선을 탐지하고, 후처리 과정을 통해 주행 경로를 정확히 인식한다. RANSAC 알고리즘을 활용하여 outlier 에 강건한 2 차 함수 회귀를 수행하고, 이를 바탕으로 주행 중 필요한 정보를 파악한다. 이러한 정보를 바탕으로 차량의 조향각을 조절하여 안전하고 효율적인 자율 주행을 구현하였다.

• 한국ITS학회:학술대회논문집
• /
• 2008.11a
• /
• pp.280-283
• /
• 2008

• 한국도로학회:학술대회논문집
• /
• 2002.10a
• /
• pp.237-244
• /
• 2002

• Proceedings of the KOR-KST Conference
• /
• 1999.10a
• /
• pp.211-216
• /
• 1999

• 한국도로학회:학술대회논문집
• /
• 2009.11a
• /
• pp.363-369
• /
• 2009

• 한국도로학회:학술대회논문집
• /
• 2006.03a
• /
• pp.133-136
• /
• 2006