• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권2호
• /
• pp.45-56
• /
• 2021

군집주행은 여러 대의 자율 주행 차량이 통신을 사용하여 서로 정보를 교환하며 하나의 군집을 이루어 주행하는 것이다. 이러한 군집주행 기술은 더 좁은 차량 간 간격을 유지하며 주행함으로써 도로의 통행량 증대, 에너지 소비 및 오염물질 배출 감소 등의 다양한 장점을 가진다. 그러나 군집주행의 좁은 차량 간 간격은 긴급한 사고 발생 시 대처를 더 어렵게 만들며, 이에 따라 필수적으로 확보되어야 할 군집주행의 안전성을 보장하는데 어려움을 주고 있다. 특히 주행 중 나타날 수 있는 가변성은 군집주행의 안전에 악영향을 미칠 수 있다. 이러한 가변성은 발생 예측이 어렵고, 재현이 어려운 특성으로 인해 가변성으로부터 발생하는 위험 요소를 방지하는 안전대책 마련에 어려움이 있다. 본 논문에서는 군집주행 중에 생겨날 수 있는 가변성에 따른 위험을 회피하기 위한 시뮬레이션 방법을 연구하였다. 이를 위해 가변성을 고려하는 다양한 시나리오를 개발하고, 가변성을 핸들링할 수 있는 안전 대책을 고안, 적용하였으며, 또한 오픈소스 군집주행 시뮬레이터인 VENTOS를 확장하여 시나리오 시뮬레이션을 수행하였다. 그 결과 가변성으로 인한 군집주행의 위험성을 제거하여 안전한 군집주행이 가능함을 확인하였다. 제시하는 가변성 대응 시나리오 시뮬레이션은 군집주행에서의 안전성을 확보하기 위한 연구 개발에 기여할 것으로 판단한다.

• 한국도로학회논문집
• /
• 제18권5호
• /
• pp.63-73
• /
• 2016

PURPOSES : The objective of this study was to analyze variations in the vehicle driving behavior characteristics on signalized intersections according to the use of traffic enforcement camera (red light camera). METHODS : In order to analyze the driving behavior characteristics on signalized intersections when red light camera are installed, the target sites for investigation were selected depending on whether the red light camera is installed and accident rates increased after the installation. In particular, to analyze the characteristics of dilemma zones in signalized intersections, approach speed and deceleration speed of 3 type vehicles (passing vehicles during a yellow light, stopping at a yellow light, passing vehicles during a green light) were examined. Based on these data, the starting point, ending point, and distance of the dilemma zones were calculated. Also, the locations of increased traffic accidents and decreased accidents after the installation of the equipment were distinguished when analyzing the traffic accident characteristics. RESULTS : Analysis results revealed that there was a tendency for the dilemma zone distance to decrease after the installation of equipment(red light camera) in most sites. This tendency was found to be due to the decrease in the approaching speed of vehicles at intersections after the installation of equipment, resulting in the starting and ending points of dilemma zone to become closer to the stop line. Moreover, analysis showed that the number of traffic accidents decreased for most intersections after the installation of equipment and safety of the intersections increased somewhat. CONCLUSIONS : In general, installation of equipment(red light camera) caused the intersections approaching speed and dilemma zone distance to decrease. Decision-making is difficult for drivers in the dilemma zone, so the decrease in the dilemma zone distance implies an improvement in traffic safety. Furthermore, the number of accidents within intersections significantly decreased after the equipment was installed, leading to the conclusion that installation of the equipment affected the decrease in traffic accidents.

• 자동차안전학회지
• /
• 제14권2호
• /
• pp.57-69
• /
• 2022

Recently, as interest in self-driving cars has increased worldwide, research and development on the Advanced Driver Assist System is actively underway. Among them, the purpose of Adaptive Cruise Control (ACC) is to minimize the driver's driving fatigue through the control of the vehicle's longitudinal speed and relative distance. In this study, for the research of the ACC test in the real environment, the real-road test was conducted based on domestic-road test scenario proposed in preceding study, considering ISO 15622 test method. In this case, the distance measurement method using the dual camera was verified by comparing and analyzing the result of using the dual camera and the result of using the measurement equipment. As a result of the comparison, two results could be derived. First, the relative distance after stabilizing the ACC was compared. As a result of the comparison, it was found that the minimum error rate was 0.251% in the first test of scenario 8 and the maximum error rate was 4.202% in the third test of scenario 9. Second, the result of the same time was compared. As a result of the comparison, it was found that the minimum error rate was 0.000% in the second test of scenario 10 and the maximum error rate was 9.945% in the second test of scenario 1. However, the average error rate for all scenarios was within 3%. It was determined that the representative cause of the maximum error occurred in the dual camera installed in the test vehicle. There were problems such as shaking caused by road surface vibration and air resistance during driving, changes in ambient brightness, and the process of focusing the video. Accordingly, it was determined that the result of calculating the distance to the preceding vehicle in the image where the problem occurred was incorrect. In the development stage of ADAS such as ACC, it is judged that only dual cameras can reduce the cost burden according to the above derivation of test results.

• 한국안전학회지
• /
• 제27권6호
• /
• pp.31-42
• /
• 2012

Urban transit vehicle that uses electrical energy, is faster, safer and energy-efficient public transit than other means. As a Research method, the Matlab/Simulink are used to modeling a regenerative brake-capable train, and actual parameters such as powering and braking characteristics, all kinds of resistance, passenger load, velocity, gradient, radius of curve etc and powering and breaking commands per time or distance are inputted to train's dynamic equation, then a simulation program is made and used to yield train driving pattern and driving time and the amount of driving energy used thereby at auto and manual operation and at all sector.

• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.728-734
• /
• 2021

최근 심층강화학습을 활용한 종단간 자율주행에 대한 관심이 크게 증가하고 있다. 본 논문에서는 차량의 종방향 주행 성능을 개선하는 잠재 SAC 기반 심층강화학습의 보상함수를 제시한다. 기존 강화학습 보상함수는 주행 안전성과 효율성이 크게 저하되는 반면 제시하는 보상함수는 전방 차량과의 충돌위험을 회피하면서 적절한 차간거리를 유지할 수 있음을 보인다.

• 산업경영시스템학회지
• /
• 제32권1호
• /
• pp.67-71
• /
• 2009

Using driving simulator, we analyzed the driving behavior of an older driver on intersection and measured the pychological load to HRV. As a results, older drivers started to enter the more complex intersection on a great distance and on low velocity for safety driving. On the other hand, the value of HRV would be lower on more complex intersections. It suggested that an older driver allowed for his own losses of physiological and cognitive function and recognized low level of driving confidence relatively.

• 한국도로학회논문집
• /
• 제20권1호
• /
• pp.137-146
• /
• 2018

PURPOSES : This study aims to analyze how the installation of advanced warning devices affects individual drivers' driving behaviors with operating record data collected from 100 vehicles. METHODS : With collected data, the changes in individual drivers' driving behaviors, such as Forward Collision Warning (FCW) and Lane Departure Warning (LDW), were investigated with respect to the cumulative distance traveled and driving time. For the analysis, operating record data collected from 100 vehicles for seven months were used. RESULTS : The results showed that individual drivers' driving behaviors could be categorized into six different types. In addition, most of the drivers showed unstable warning patterns in the initial stage after installation of an advanced warning device. Approximately 40% of vehicles equipped with advanced warning systems were found to have positive effects, indicating that the frequencies of both FCW and LDW had been continuously decreasing after installation of the system. CONCLUSIONS : The warning device might be helpful for making drivers' driving behaviors safer. Driving behaviors during the initial stage of the system installation, which might be regarded as an adaptation phase, were found to be very unstable compared with normal situations, indicating that adequate education and training should be provided to all the drivers to prevent operator disruption at the initial installation of the system.

• 한국자동차공학회논문집
• /
• 제20권4호
• /
• pp.60-67
• /
• 2012

Most of a driving cycle is used to measure fuel consumption (FC) and emissions for a specified vehicle. A driving cycle was reflected geography and traffic characteristics for each country, also, driving pattern is affected these parameters such as vehicle dynamics, FC and emissions. Therefore, this study is an attempt to develop a driving cycle for military operational area. The proposed methodology the driving cycle using micro-trips extracted from real-world data. The methodology is that the driving cycle is constructed considering important parameters to be affected FC. Therefore, this approach is expected to be a better representation of heterogeneous traffic behavior. The driving cycle for the military operational area is constructed using the proposed methodology and is compared with real-world driving data. The running time and total distance of the final cycle is 1461 s, 13.10 km. The average velocity is 32.25 km/h and average grade is 0.43%. The Fuel economy in the final cycle is 5.93 km/l, as opposed to 6.10 km/l for real-world driving. There were about 3% differences in driving pattern between the final driving cycle and real-world driving.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.233-238
• /
• 2004

In this study, speed survey has been conducted on Pusan Freeway to identify actual running speed. therefore, suggest that Highway Design Regulations and Highway Design Standard from Ministry of Construction and Transportation, which requires stopping sight distance for 20% less speed when rainy condition in accordance with Highway Safety Act, is not coincident with driver's characteristics. Consequently, it is prudent to compute stopping sight distance with 85th percentile running speed, considering driver's actual behavior and mountainous terrain.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.243-249
• /
• 2015

In direct vehicle teleoperation, a human operator drives a vehicle at a distance through a pair of master and slave device. However, if there is time delay, it is difficult to remotely drive the vehicle due to slow response. In order to address this problem, we introduced a novel methodology of shared vehicle teleoperation using a virtual driving interface. The methodology was developed with four components: 1) virtual driving environment, 2) interface for virtual driving environment, 3) path generator based on virtual driving trajectory, 4) path following controller. Experimental results showed the effectiveness of the proposed approach in simple and cluttered driving environment as well. In the experiments, we compared two sampling methods, fixed sampling time and user defined instant, and finally merged method showed best remote driving performance in term of completion time and number of collision.