• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1999년도 춘계학술대회 논문집
• /
• pp.307-314
• /
• 1999

The potential use of ranging sensors for reducing the occurrence of accidents in real environment is explored by many companies and laboratories. Most of the sensors under investigation utilize the FMCW(Frequency Modulated Continuous Wave) waveforms. The automotive environment presents to the FMCW radar sensor a multitude of moving and fixed targets and the sensor must detect and track only the targets which may pose a threat of collision or passengers accident. The sensor must function accurately in the presence of background echoes generated by moving and fixed targets, ground reflections, atmospheric noises, including rains, fog, and, snow and noise generated within the receiver. False detection of the desired target in this environment may issue false alarms. That may be dangerous to the passenger and the vehicle. A high false alarm rate is totally unacceptable. The false alarm mechanism consists of noise peaks, crossing the threshold and the undesired response of the system to off lane targets which are not potentially hazardous to the radar equipped vehicle. This paper presents an improve technique safety performance for driver-less operation using FMCW radar sensors.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.1524-1530
• /
• 2008

Generally a road vehicle's wrong entry into level crossing gives rise to hazardous events, the eventual collision with a approaching train depends on the effective operation of safety barriers such a abnormal condition detecting or emergency braking. In this paper, the risk assessment models developed for the level-crossing accidents will be introduced. The definition of hazardous events and the related hazardous factors are identified by the review of the accident history and engineering interpretation of the accident behavior. A probability of the hazardous events will be evaluated by the FTA, which is based on the accident scenario. For the severity estimation, the critical factors which can effect on the consequence will be reviewed during the ETA. Finally, the number of casualty for the public(vehicle drivers) and the train passengers are converted into an equivalent fatality.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 B
• /
• pp.1368-1370
• /
• 2000

The automotive environment presents to the FMCW radar sensor a multitude of moving and fixed targets and the sensor must detect and track only the targets which may pose a threat of collision or passengers accident. The sensor must function accurately in the presence of background echoes generated by moving and fixed targets, ground reflections, atmospheric noises, including rains, fog, and, snow and noise generated within the receiver. False detection of the desired target in this environment may issue false alarms. That may be dangerous to the passenger and the vehicle. A high false alarm rate is totally unacceptable. The false alarm mechanism consists of noise peaks, crossing the threshold and the undesired response of the system to off lane targets which are not potentially hazardous to the radar equipped vehicle. This paper presents an improve technique safety performance for driver-less operation using FMCW radar sensors.

• 연구논문집
• /
• 통권24호
• /
• pp.97-106
• /
• 1994

Steering system is typically one of the vehicle parts that may injure an unrestrained driver in a frontal collision. Therefore, the engineers of vehicle safety parts researched the allowable injury criteria such as HIC(head injury criterion). chest acceleration and knee impact force. From their research, they recognized that development of energy absorbing steering system was necessary to protect the driver. Energy absorbing parts of steering system consist of shear capsule, ball sleeve and shaft assembly. We performed the modelling and dynamic analysis of the energy absorbing steering column with the unrestrained driver model. The conclusions of this study are as follows. 1) The variation of column angle has an important effects on the dynamic responses of steering system and driver behavior. 2) The energy absorbing steering system satisfies the safety criterion of FMVSS 203, 208, but not the safety criterion of FMVSS 204.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.486-487
• /
• 2012

본 논문에서는 차량 내에 설치된 카메라를 이용하여 전방차량을 인식하는 FCW(Forward Collision Warning)시스템에서 주행 중인 전방 차량을 추적하는 알고리즘을 제안한다. 전방 차량의 후보 영역을 검출하기 위해 Haar-Adaboost를 이용하였으며 검색된 차량 후보 영역 내의 에지 정보를 이용하여 차량 후보 영역을 필터링하였다. 필터링된 차량 영역은 영역기반과 Kalman 예측치를 이용하여 차량을 추적하는 방법으로 차량 검색기가 차량 영역을 검색하지 못하는 경우 Kalman 예측치를 통해 차량 후보 영역을 예측하고 예측된 차량 영역을 검증함으로써 효율적인 전방 차량 인식이 가능하였다. 본 제안 방법을 실험한 결과 이전 프레임에서 추적되던 차량 후보 영역이 현재 프레임에서 Haar-Adaboost가 차량 후보 영역을 검색하지 못하는 경우에 영역기반과 Kalman 예측치를 통하여 현재 프레임에서 전방차량을 연속적으로 추적하는 것을 확인하였다. 본 제안 방법은 영상을 이용한 FCW 시스템에 사용될 수 있을것으로 사료된다.

• 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.

• 한국컴퓨터그래픽스학회논문지
• /
• 제23권5호
• /
• pp.57-66
• /
• 2017

본 연구는 물리 기반의 자동차 애니에이션 기술을 연구하였으며, 일반인도 손쉽게 차량 애니에이션을 제작할 수 있도록 직관적인 저작도구를 제안하였다. 사용자가 직접 차량의 이동 경로 및 속도를 지정하면, 이동 경로의 방향적 특성에 기반한 시뮬레이션 구간 분할과 피드백 기반 주행 경로 탐색 기법을 통해 기존 연구보다 빠르고 정확한 주행 시뮬레이션을 수행하도록 하였다. 결과적으로 차선 변경 및 추월을 포함한 단순 주행 애니메이션뿐만 아니라 기존 관련 연구에는 없었던 차량 충돌 애니메이션 또한 제작할 수 있다. 아울러 차체 모델을 실제 차량과 유사하게 설계하였기 때문에, 제동 시 차량이 미세하게 혼들리는 현상이나 추돌 시 차량이 찌그러지는 현상 등 실제에 가까운 차량의 웅직임을 묘사할 수 있다.

• 자동차안전학회지
• /
• 제11권4호
• /
• pp.6-15
• /
• 2019

Since introducing the offset frontal impact test in EuroNCAP in 1997, the vehicle has been constantly changing according to its usage and purpose. As of 2019, many vehicles have been released to the public, which has led to a large structural mass difference between small, medium and large vehicles. Also, the geometry of the front of the vehicle is completely different for each vehicle and tends not to be perfectly aligned at frontal collisions. The difference in mass of each of these vehicles and less performing structures for offset crashes have led to dramatically worse outcome in a car to car offset frontal impact tests. Even though a decade later passenger cars have become much safer due to consumer test programs and regulatory requirements, the aggressiveness and compatibility that can cause damage to the opponent car in the event of car to car collision is not considered in the above-mentioned section, and therefore much improvement is needed. After many years of study to solve this problem, EuroNCAP has developed a new mode MPDB offset front test that considers the aggressiveness and compatibility that can affect the opponent cars that have collided. This paper introduces the development process of aggressiveness and compatibility evaluation method of MPDB in EuroNCAP which will be implemented from 2020. Several impact tests have been conducted at different test conditions to rate the vehicle structure performance only focused on aggressiveness and compatibility of MPDB.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.139-147
• /
• 2007

In military transportation, the use of wide trailer for transporting the large and heavy weight equipments such as tank, armoured vehicle, and mobile gunnery is quite common. So, the vulnerability of causing traffic accidents for these wide military trailer to bump or collide with another car in adjacent lane is very high due to its broad width in excess of its own lane's width. Also, the possibility of these strayed accidents can be increased especially by the careless driver. In this paper, the recognition system of lane and vehicle headway direction is developed to detect the possible collision and warn the driver to prevent the fatal accident. In the system development, Kalman filtering is used first to extract the border of driving lane from the video images supplied by the CCD camera attached to the vehicle and the driving lane detection is completed with regression analysis. Next, the vehicle headway direction is recognized by using neural network scheme with the extracted parameters of the detected driving lane feature. The practical experiments for the developed system are also carried out in the real traffic road of Seoul city area and the results show us the more than 90% accuracy in recognizing the driving lane and vehicle headway direction.

• 한국자동차공학회논문집
• /
• 제12권2호
• /
• pp.205-214
• /
• 2004

This paper presents design concepts, specifications and performances of a newly developed Black Box, the reconstruction analysis tool with the records, and results of validation tests. The Black Box can detect crash accidents automatically, and record the vehicle's motion and driver's maneuvers during a pre-defined time period before and after the accident. The items of the Black Box included the acceleration, yaw-rate, vehicle speed, engine RPM, braking application, steering and several digital inputs for recording driver's maneuvers. To detect the accident-related-crash, it is important to understand characteristics of the crash signal, which are much different from those of normal driving. Therefore, analytical considerations should be taken in designing pre-filtering circuits and selecting appropriate parameters for identifying crash accidents. And, it is necessary to select proper combination of motion sensors and design proper pre-filtering circuits in order to describe the vehicle's motion. The analysis algorithms were developed and implemented which can perform accurate detection of crash accidents, simulating pre-crash trajectories, and calculating parameters for reconstruction analysis of crash accidents. The developed Black Box was installed on passenger cars and several types of validation tests were conducted. Through the tests, the accuracy of the recorded data and usefulness of the analysis tool for reconstruction have been validated.