• 한국ITS학회 논문지
• /
• 제21권2호
• /
• pp.62-73
• /
• 2022

각국의 자율주행시스템 기술개발 경쟁이 심화함에 따라 정부도 자율주행시스템의 시장 진입을 전방위에서 지원하고 있다. SAE(Society of Automotive Engineers) 3단계 기술은 운전자가 위험 상황을 회피해야 하고, 4단계 기술은 자율주행시스템 스스로 위험 상황에 대응할 수 있어야 한다. 이에 따라, 공공부문은 도로 위험 상황을 모니터링하고, 도로 인프라 정보를 운전자와 자율주행시스템에 제공하여 대응할 수 있도록 지원할 필요가 있다. 본 연구는 도로 인프라 위험 요소를 자율주행시스템의 ODD(Operational Design Domain) 특성에 따라 모니터링 대상별 위험 요소를 세분화하고, 각 위험 요소가 차량에 미칠 영향에 따른 위험도 등급화 및 평가 방안을 제시하였다. 위험 상황 발생 시 자율주행차의 운행 특성을 시뮬레이션하고, 위험 요인 특성과 물리적인 차량 조건 사이의 영향 관계를 파악하여 등급화함으로써 위험도를 평가할 수 있다. 또한 수집된 모니터링 정보는 관리 센터와 공유하고, 요소별 특성에 따른 노드 혹은 링크 형태로 정밀지도에 표출하여 위치정보와 위험도 등급 등 종합적 관리가 가능한 모니터링 체계를 정립할 것을 제안하였다.

• Journal of Platform Technology
• /
• 제9권2호
• /
• pp.46-54
• /
• 2021

최근, 차량의 자율주행에 대한 기술이 개발되면서 안정성은 매우 흥미로운 요소로 관심이 증대되고 있다. 그리고 자율주행에 대하여 1980년대 중반부터 전세계의 많은 대학, 연구 센터, 자동차 회사, 그리고 다른 산업의 회사들에 의해 연구 및 개발되고 있다. 본 연구에서는 자율주행 차량의 안전성을 위한 도로의 위협적인 장애물을 자동 추출하는 방안에 대한 기초 연구를 제안한다. 자동차 도로 위에는 다양한 장애물들이 존재하지만, 본 연구에서는 위협적인 장애물은 도로의 중앙에 위치하며 비교적 큰 개체로 정의한다. 먼저, 입력 영상에 대하여 해상도를 달리하여 분할하고 분할된 영역들은 내부 영역과 외부 영역으로 분류한다. 외부 영역은 영상의 경계에 인접하고 내부 영역은 그렇지 않다. 또한, 저해상도 영상에 인접한 영역이 동일한 영역에 포함되면 각 영역은 인접 영역과 병합된다. 그리고 주요한 객체 영역과 주요한 배경 영역은 각각 내부 영역과 외부 영역에서 선택된다. 따라서, 주요한 객체 영역은 면적과 크기 정보를 활용하여 장애물을 대표하는 영역으로 추출된다. 실험을 통하여 제안된 방법이 자동차 자율주행 안전성을 높여 사고와 사상자를 줄일 수 있는 기초연구에 기여할 수 있을 것으로 기대한다.

• 한국도로학회논문집
• /
• 제19권5호
• /
• pp.163-171
• /
• 2017

PURPOSES : Traffic safety facilities are used to prevent traffic accidents before they occur by providing drivers with information on traffic situations and the geometric design of roads. However, some facilities not defined in guidelines do not meet installation criteria, yet are being installed and used in order to increase efficiency in traffic flow and prevent traffic accidents in a specific expressway zone. In this study, we have evaluated the effect of delineation system which are not defined in the guideline criteria. METHODS : Different virtual scenarios were created for roads using expressway median barrier chevron signs, with a driving simulator used to evaluate the installation and operational effect of such signs. Ten experiments were performed with left- and right-curved roads at curve radius intervals of 500 m, from 500 m to 2,500 m. RESULTS : For sections with a curve radius of more than 1,500 m, drivers had a clear tendency toward stable driving regardless of delineation system. When a chevron sign is installed on a protection fence in the road curving left, an expanded installation is recommended up to the section with a curve radius of 1,000 m. According to the analysis results for the RHB (Relative High Beta spectrum), driving concentration also improved up to a curve radius of 1,000 m. CONCLUSIONS :The experiment result indicates the extent of biasing within a lane and the manipulation amount of steering handle, were analyzed and found to be affected by curve radius and road alignment regardless of delineation system.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.57-61
• /
• 2011

The bimodal tram was designed to drive on the dedicated track as well as on the public road. The position and speed are automatically controlled on the dedicated track by the onboard computer, whereas they are manually controlled by driver like motor vehicles on the public road. The ride comfort the passengers feel and the effect of the vibration generated during driving on the passenger's health, comfortableness and motion sickness were evaluated with driving the bimodal tram prototype in automatic and manual mode, respectively. The test was done in automatic mode on the test track with various load conditions while it was done in manual mode on the public road with empty load.

• 산업경영시스템학회지
• /
• 제34권4호
• /
• pp.35-41
• /
• 2011

The purpose of this study was to examine drivers' driving behaviors and eye-movements according to driving speed and navigation- position while operation of the navigation in driving. For this purpose, two driving conditions (low-speed and high-speed) and two navigation-positions (top and bottom location of the center console) were set. Drivers' driving behaviors (speed, speed variation, coefficient of variation, and the number of collisions) and eye-movements (overall eye pattern, the average scanning time of navigation, and the number of gaze-out on the road for more 2 seconds) were measured. As a result, when the navigation was located at the bottom of the console, difficulties of lateral control was appeared in low-speed driving condition, and the that of longitudinal control was appeared in high-speed driving condition. In addition, above situation made the drivers' scanning times of navigation long, increased the number of gaze-out on the road for more 2 seconds, and made overall eye pattern monotonous. These results could be interpreted that the manipulation of the navigation at the bottom of console cause reduced attention capacity due to the cognitive load.

• Safety and Health at Work
• /
• 제13권2호
• /
• pp.187-191
• /
• 2022

Background: Traffic injuries have become a significant public health problem in low- and middle-income countries. Several studies have examined the role of personality and attitude toward traffic safety in predicting driving behaviors in diverse types of drivers. Few studies have investigated risky behavior among public passenger van drivers. This study aims to identify the predictors of self-reported risky driving behavior among public van drivers. Method: A total of 410 public van drivers were interviewed at terminal stations in Bangkok. Hierarchical regression models were applied to determine the effects of demographics, personality traits, and attitude on self-reported risky driving behaviors. Results: The results indicated that drivers with a high education level, more working days, and high scores for normlessness and anger were more likely to report risky driving behaviors (p < 0.05). Conclusion: The personality traits and attitude toward speeding account for aberrant self-reported risky driving behavior in passenger van drivers. This could be another empirical basis for evidence-based road safety interventions in the context of public transport.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.210-216
• /
• 2015

This paper proposes a method to determine vehicle driving state using the driving characteristics index. This index is a quantitative value to classify the driving state of a vehicle with its velocity and heading angle in that instant. It can classify driving state into straight driving, lane changing driving and curve driving in real time. In addition, the number of positional information is movably set up by designed region of interest. The proposed index is expressed on the stable driving states. Each driving state has characteristic tendency, and is compared with index distributional areas. The proposed method is verified by the actual driving experiment on the KATECH proving ground.

• 자동차안전학회지
• /
• 제12권1호
• /
• pp.33-38
• /
• 2020

Since a diesel vehicle scandal related to the 'A' automobile company was issued in the United States in 2015, many countries have been interested in emission defeat devices. Being embedded in some diesel passenger cars sold in Korea, a defeat device for exhaust gas may have influence on both fuel economy and NOx emissions. In order to examine such effects, we carried out laboratory indoor tests as well as real road driving tests using four models of 'A' automobile company which may employ defeat devices. Those tests were performed observing the test modes of FTP-75, HWFET, and NEDC. Although fuel economy and NOx emissions according to indoor tests comply with the suggested tolerance, the findings in the real road driving tests do not satisfy the tolerance. Along with the results provided in this study, further evaluation may be necessary to investigate the noticeable difference between the indoor and real road tests.

• 대한교통학회지
• /
• 제23권7호
• /
• pp.137-148
• /
• 2005

일정구간의 도로를 주행하는 차량에 대한 단위시간대별 위치정보를 취득하게 되면, 도로의 교통상황에 대한 정보와 개별차량의 미시적인 주행행태를 파악할 수 있게 된다. 기존 사용되는 영상기술은 짧은 지점에 대한 교통량, 속도 등의 제한적인 자료만의 취득이 가능하여 도로구간의 교통상황을 대표하는데 한계가 있다. 또한 기존 영상기술은 주행차량의 미시적행태분석을 위해서 비디오로 촬영된 영상을 한 프레임씩 수동으로 작동하여 데이터를 수집함으로써 많은 인력과 시간이 소요되었다. 본 연구에서는 차량의 단위시간대별 위치자료를 자동으로 얻어낼 수 있는 규칙기반 차량추적기술을 개발하였다. 또한 기술의 검증을 위해 130m의 도로구간에서 차량의 주행위치를 0.05초 단위로 추적한 기초 자료를 추출하였으며, 이 데이터의 가공을 통해 산출된 속도와 실측된 속도와의 비교를 통해 차량추적의 정확도를 검증하였다. 향후 이러한 차량추적기술은 도로의 교통상황에 대한 주요 정보의 제공 등의 실용적 측면과 차량의 주행행태 분석 등의 학문적 분야에 널리 활용될 수 있을 것이다.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• pp.273-280
• /
• 2022

Along with the advancement of deep learning technology, securing high-quality dataset for verification of developed technology is emerging as an important issue, and developing robust deep learning models to the domestic road environment is focused by many research groups. Especially, unlike expressways and automobile-only roads, in the complex city driving environment, various dynamic objects such as motorbikes, electric kickboards, large buses/truck, freight cars, pedestrians, and traffic lights are mixed in city road. In this paper, we built our dataset through multi camera-based processing (collection, refinement, and annotation) including the various objects in the city road and estimated quality and validity of our dataset by using YOLO-based model in object detection. Then, quantitative evaluation of our dataset is performed by comparing with the public dataset and qualitative evaluation of it is performed by comparing with experiment results using open platform. We generated our 2D dataset based on annotation rules of KITTI/COCO dataset, and compared the performance with the public dataset using the evaluation rules of KITTI/COCO dataset. As a result of comparison with public dataset, our dataset shows about 3 to 53% higher performance and thus the effectiveness of our dataset was validated.