http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
차량 플랫폼에 최적화한 자차량 에고 모션 추정에 관한 연구
송문형,신동호,Song, Moon-Hyung,Shin, Dong-Ho 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.9
This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.
차량 플랫폼에 최적화한 자차량 에고 모션 추정에 관한 연구
송문형(Moon-Hyung Song),신동호(Dong-Ho Shin) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.4
This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.
시뮬레이션을 기반으로 한 초음파 사각지역 경보 시스템 개발
송문형(Moon-hyung Song),김창일(Chang-il Kim),이광수(Kwang-soo Lee),김문식(Mook-sik Kim) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.6
Recently, vehicle OEMs have begun to put considerable effort in developing ADAS to satisfy the customer’s new requirement. In striving to keep pace with the rapid changes in the market, this paper presents the development process for the multi-function ADAS module which integrates PAS and BSD using ultrasonic sensors. Development process is based on simulation in PreScan environment, and the proposed BSD algorithm is developed and evaluated in Matlab stateflow toolbox environment.
자율주행 자동차의 승차감 향상을 위한 차선 변경 경로 생성 기법 비교 연구
송문형(Moon-hyung Song),김창일(Chang-il Kim),이광수(Kwang-soo Lee),김문식(Mook-sik Kim) 대한전자공학회 2016 대한전자공학회 학술대회 Vol.2016 No.11
Most of OEM of vehicle has been developing autonomous system in which the vehicle does not require a driver’s control. By this consistent effort, we can expect that the customer will be able to experience the autonomous vehicle in daily life. However, the view of general public is still in doubt regarding on the safety of autonomous vehicle. To ensure its safety, therefore, the high level of driving comfort is crucial to satisfy the customer with its vehicle. This paper explains the similarity of a human driver to the autonomous vehicle system by applying certain human factor. Within its similarities, the various direction to create the safe driving path will be introduced. And from the simulation of its outcome, the relative comparison can be made on each method to see the advantage of the system.
Kalman Filter 기반 차선 추정 강화에 대한 연구
박상후(Sang-Hu Park),이희승(Hee ?Seung Lee),송문형(Moon-Hyung Song),김창일(Chang-Il Kim),이광수(Gwang-Soo Lee),김문식(Moon-Sik Kim) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.8
As more and more step into the age of the automated driving vehicle, the importance of lane detection technology is being magnified. Vision sensor-based lane detection technology has been strengthed. However, lane detection technology was used for vertical control system for forward target vehicle selection without being used alone for side risk assessment or lateral control alone. Ego lane detected by the vision sensor can assume as an ego vehicle’s driving path and be useful for front target vehicle decision. Therefore, the importance of curvature and curvature-rate which have been relatively devaluated then lateral offset and heading angle is getting higher. In this study, a new approach of lane estimator for accurate curvature information by Kalman filter is proposed. The lane estimator is designed with road model and an assumption based on lane width. Real-car tests are underway for verifying the performance of proposed lane estimator. The test result shows that accuracy of the proposed lane estimator even in failure situation of front camera. Furthermore, the result also showed usefulness of lane estimation based target selection. Through the test result analysis, filtered only two coefficients which related clothoid curvature parameters could make lane information more accurately.
어린이 승 · 하차 예방안전시스템의 경고 알고리즘 개발
이광수(Kwang-soo Lee),김창일(Chang-il Kim),송문형(Moon-hyung Song),김문식(Mook-sik Kim) 대한전자공학회 2015 대한전자공학회 학술대회 Vol.2015 No.6
This paper presents a warning algorithm for a school bus boarding safety assistance system which is developed to reduce the car accidents of school buses for children. In order to judge whether a certain surrounding condition is dangerous or not, and inform driver by reliable 3 step warning, the naval algorithm is proposed. For reliable warning algorithm, the different kinds of sensor data such as the school bus state (door close/open, gear position data and vehicle velocity), distance data from vehicle to children by ultrasonic sensor and children position data by Zigbee sensor are converged. The proposed warning algorithm is developed and evaluated in Matlab stateflow toolbox environment.