http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Development of A Lane Departure Monitoring and Control System
Kunsoo Huh,Daegun Hong,Jeffrey L. Stein 대한기계학회 2005 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.19 No.11
The lane departure avoidance systems have been considered promising to assist human drivers in AVCS (Advanced Vehicle Control System). In this paper, a lane departure monitoring and control system is developed and evaluated in the hardware-in-the-loop simulations. This system consists of lane sensing, lane departure monitoring and active steering control subsystems. The road image is obtained based on a vision sensor and the lane parameters are estimated using image processing and Kalman Filter technique. The active steering controller for avoiding the lane departure is designed based on the lane departure metric. The proposed lane departure avoidance system is realized in a steering HILS (hardware-in-the-loop simulation) tool and its performance is evaluated with a driver in the loop.
허건수(Kunsoo Huh),서문석(Munsuk Suh),김재용(Jaeyong Kim),정순규(Soonkyu Jeong),정정주(Chungchoo Chung),김일민(Ilmin Kim) 대한기계학회 2003 대한기계학회 춘추학술대회 Vol.2003 No.4
Maintaining track tension in tracked vehicles minimizes the excessive load on the tracks and prevents the<br/> peal-off of tracks from the road-wheel, and adequately guarantees the stable and improved driving of the<br/> tracked vehicles. However, the track tension cannot be easily measured due to the limitation in the sensor<br/> technology, harsh environment, etc. In this study, the track tension is estimated in real-time from the<br/> measurable signals of tracked vehicles and controlled based on a fuzzy logic controller. The proposed control<br/> system is implemented on tracked vehicles and its performance is evaluated under various driving conditions.
허건수(Kunsoo Huh),박재학(Jaehak Park),홍대건(Daegun Hong),조동일(Dong-il Cho),박장현(Jahng-Hyon Park) 한국자동차공학회 2004 한국자동차공학회 춘 추계 학술대회 논문집 Vol.- No.-
Vision-based lane sensing systems require accurate and robust sensing performance in lane detection. Besides, there exists trade-off between the computational burden and processor cost, which should be considered for implementing the systems in passenger cars. In this paper, a stereo vision-based lane detection system is developed with considering sensor configuration aspects. An inverse perspective mapping method is formulated based on the relative correspondence between the left and right cameras so that the 3-dimensional road geometry can be reconstructed in a robust manner. A new monitoring model for estimating the road geometry parameters is constructed to reduce the number of the measured signals. The selection of the sensor configuration and specifications is investigated by utilizing the characteristics of standard highways. Based on the sensor configurations, it is shown that appropriate sensing region on the camera image coordinate can be determined. The proposed system is implemented on a passenger car and verified experimentally.