http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
DGPS를 이용한 주행차량의 정밀위치인식시스템에 관한 연구
엄재용(Jaeyong Um),이인식(Insik Lee) 한국자동차공학회 2004 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
As the first step to a DGPS-based autonomous driving system, the test ground was constructed and a DGPS RTK navigation system was developed fur the autonomous vehicle. Two sets of NovAtel DL-4 GPS receivers and Cisco-350 wireless LAN equipments were used for the DGPS test ground, and an accurate digital map for the test ground was made to provide the reference position of the vehicle. For the digital map, the test lane was measured five times using the DGPS RTK and the smooth lane data was obtained by the polynomial curve fitting.<br/> The positioning error of the traveling vehicle based on the digital map is composed of the map error and the navigation error of the vehicle.. The map error is composed of the DGPS rover setting error, measuring operation error and the inherent DGPS RTK measurement error with the curve fitting. The navigation error of the vehicle is composed of the DGPS RTK error and the GPS antenna installation error. Of course the positioning error due to latency should be examined and compensated in the autonomous system controller design later. The vehicle position was measured using the external equipments and compared with the estimated position to show the lateral positioning error of 3.2cm RMS.
레이더와 비전센서 융합을 통한 전방 차량 인식 알고리즘 개발
양승한(Seunghan Yang),송봉섭(Bongsob Song),엄재용(Jaeyong Um) 제어로봇시스템학회 2010 제어·로봇·시스템학회 논문지 Vol.16 No.7
This paper presents the sensor fusion algorithm that recognizes a primary vehicle by fusing radar and monocular vision data. In general, most of commercial radars may lose tracking of the primary vehicle, i.e., the closest preceding vehicle in the same lane, when it stops or goes with other preceding vehicles in the adjacent lane with similar velocity and range. In order to improve the performance degradation of radar, vehicle detection information from vision sensor and path prediction predicted by ego vehicle sensors will be combined for target classification. Then, the target classification will work with probabilistic association filters to track a primary vehicle. Finally the performance of the proposed sensor fusion algorithm is validated using field test data on highway.
양승한(Seunghan Yang),송봉섭(Bongsob Song),조석환(Sukhwan Cho),엄재용(Jaeyong Um) 한국자동차공학회 2009 한국자동차공학회 학술대회 및 전시회 Vol.2009 No.11
This paper presents the sensor fusion method that recognizes a relevant vehicle by combining data from radar and monocular vision. In general, most of radar may lose tracking of the relevant vehicle when it is stationary or goes with other preceding vehicles in the adjacent lane with similar velocity and rage. In order to improve these performance degradation of radar, vehicle detection information through vision sensor and path prediction estimated by ego vehicle sensors will be fused with radar information for sensor fusion. In addition, a Kalman filter is used for relevant vehicle tracking and the predicted state is also used to associate the relevant vehicle information. Finally the performance of the proposed sensor fusion algorithm is validated experimentally using field test data on highway.
애드혹을 이용한 자동차 네트워크에서 이동성에 따른 네트워크 성능 분석
김재현(Jaehyun Kim),최우혁(Woohyuk Choi),황윤일(Yunil Hwang),김태환(Taehwan Kim),한우진(Woojin Han),장주욱(Juwook Jang),엄재용(Jaeyong Um),임준채(JunChae Lim) 한국정보과학회 2005 한국정보과학회 학술발표논문집 Vol.32 No.1
본 논문은 애드혹을 이용한 자동차간 네트워크에서 도심 및 고속도로에서 소규모로 그룹을 지어 이동할 때의 네트워크 성능을 분석한다. 자동차를 위한 무선 네트워크를 구축하기 위하여 IEEE 802.11b를 이용한 애드혹 네트워크를 사용한다. 그리고 이러한 네트워크에서 다양한 이동성 환경에서 IEEE 802.11b를 이용한 네트워크의 성능을 분석한다. 이를 위하여 네트워크 시뮬레이터인 OPNET을 이용하여 실제 자동차가 이동하는 이동성 모델을 적용한 후 TCP와 UDP를 이용하여 대용량의 데이터를 전송할 때의 네트워크 성능을 측정한다. 또한 실제 자동차에 애드혹 네트워크를 구축하여 TCP와 UDP를 이용한 대용량의 자료를 주고받을 때의 네트워크 성능을 측정합니다.