http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
무가선 트램의 주행안전성 향상을 위한 선로인식기반 충돌 판단 시스템
박승진(Seungjin Park),정상우(Sangwoo Jeong),이민철(Minchul Lee),선우명호(Myoungho Sunwoo) 한국철도학회 2016 한국철도학회 학술발표대회논문집 Vol.2016 No.10
트램은 일반철도와는 달리 선로상에 보행자와 같은 돌발 장애물이 나타날 수 있는 주행 환경을 가진다. 기존에 개발되고 있는 레이더 기반 충돌 판단 시스템의 경우 센서 특성상 사람을 인식하기 어렵고 횡 방향 운동 추정에 한계가 있다. 이러한 한계를 극복하기 위해 이 연구에서는 카메라와 레이저스캐너의 융합정보 기반 충돌 판단 시스템을 제안한다. 제안된 시스템은 단안 카메라 기반 선로 인식 부분 및 인식 정보와 레이저스캐너 기반 충돌가능물체 거동 예측 부분으로 구성된다. 해당 시스템은 실제 트램이 주행환경에서 취득한 데이터 기반으로 검증 되었다. 본 연구에서 제안한 선로 인식 부분은 선로에 인식에 적합한 필터를 설계해 보다 강건한 선로 인식을 할 수 있으며 충돌가능물체에 대한 예측을 통하여 효율적인 충돌 판단을 가능하게 하였다. Unlike general trains, a wireless tram’s driving environment carries the risk of people or vehicles suddenly entering into its rails. Previous systems for trams detected objects using radar. However, radar-based collision risk assessment systems were found to have several disadvantages. For instance, low-cost radar systems cannot detect people and have difficulty in estimating lateral motion. To overcome such issues, this paper will propose a camera and laser scanner convergence-based collision risk assessment system. The proposed system consists of a monocular camera-based rail detection module and a detected rail and object-based behavior recognition module. The applicability of this system was evaluated based on logged sensor data-based simulations. The proposed system in this paper effectively detects rails by removing lanes from its detection range and assesses the collision risk efficiently through the prediction of collisional objects.
종횡방향 충돌 통합 안전제어용 주행상황 판단 척도 알고리즘 개발
김수철(Sucheol Kim),현진우(Jinwoo Hyun),김일환(Ilhwan Kim),강대오(Daeoh Kang),허승진(Seung-Jin Heo) 한국자동차공학회 2010 한국자동차공학회 부문종합 학술대회 Vol.2010 No.5
Driver errors are the main cause of most car accidents. To decrease the accident rate, driver assistance system is necessary to minimize the risk and occurrence of accidents. In this paper, the criterional algorithm for estimating driving state for advanced driver assistance system was employed to avoid the rear end collision. And TTE(Time to enter), TTD(Time to disappear), TTC(Time to collision), TTB(Time to break) and TTT(Time to touch) were calculated by using the criterional algorithm for estimating driving state for ADAS. The effect of applying the criterional algorithm for estimating driving state for ADAS in shown from TTE, TTD, TTC, TTB and TTT to assist actuating timing on the simulation results.
이동휘(Donghwi Lee),한광진(Kwangjin Han),조상민(Sangmin Cho),김용선(Yongsun Kim),허건수(Kunsoo Huh) 한국자동차공학회 2012 한국 자동차공학회논문집 Vol.20 No.3
Collision detection plays a key role in collision mitigation system. The malfunction of the collision mitigation system can result in another dangerous situation or unexpected feeling to driver and passenger. To prevent this situation, the collision time, offset, and collision decision should be determined from the appropriate collision detection algorithm. This study focuses on a method to determine the time to collision (TTC) and frontal offset (FO) between the ego vehicle and the target object. The path prediction method using the ego vehicle information is proposed to improve the accuracy of TTC and FO. The path prediction method utilizes the ego vehicle motion data for better prediction performance. The proposed algorithm is developed based on laser scanner. The performance of the proposed detection algorithm is validated in simulations and experiments.
후보 궤적을 이용한 비구조화된 환경에서의 교차로 인식 및 주행
김민수(Minsoo Kim),안준우(Joonwoo Ahn),김민성(Minsung Kim),박재흥(Jaeheung Park) 한국자동차공학회 2020 한국자동차공학회 학술대회 및 전시회 Vol.2020 No.11
In this paper, we present intersection detection and navigation method in the unstructured environment. The presented method uses only a camera image. It generates candidate trajectories in the segmented camera image and decides whether the vehicle enters an intersection using a histogram of the candidate trajectories. In addition, the vehicle selects the target trajectory and tracks it with considering the vehicle velocity, static obstacles, and navigation information. The proposed method was tested and evaluated in a simulation.