http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
문병일(Byeongil Mun),김윤정(Yunjeong Kim),손행선(Haengseon Son),이선영(Seonyoung Lee),민경원(Kyungwon Min) 대한전자공학회 2019 대한전자공학회 학술대회 Vol.2019 No.6
In this paper, a novel and simplified method to create a vector map using satellite map is presented. By replacing a point cloud map which is used in the conventional vector map making with a satellite map, the proposed vector map making method can save time, resolve space constraints, and make it easier to create vector maps in real-world as well as virtual environments. Furthermore, the global path planning is performed based on the vector map, and it is verified by simulation results.
문병일(Byeongil Mun),김윤정(Yunjeong Kim),손행선(Haengseon Son),이선영(Seonyoung Lee),민경원(Kyungwon Min) 대한전자공학회 2019 대한전자공학회 학술대회 Vol.2019 No.11
In this paper, a sensor fusion and tracking method using multi camera and LiDAR is proposed. The relation between a camera and LiDAR is obtained using an existing LiDAR and camera calibration method in ROS package. In order to detect objects using LiDAR and camera, we use lidar-eucliean-cluster-detect package in Autoware and YoloV3, respectively. We propose a simple fusion method between detection data from multi-camera and clustering data from LiDAR. An experiment is conducted to verify the proposed algorithm.
김윤정(Yunjeong Kim),문병일(Byeongil Mun),하상욱(Sangwook Ha),민경원(Kyungwon Min),이선영(Seongyoung Lee),손행선(Haengseong Son) 한국자동차공학회 2019 한국자동차공학회 학술대회 및 전시회 Vol.2019 No.11
Self-driving vehicles are a maturing technology with the potential to reshape mobility. The main technologies consisting of self-driving vehicles includes detection objects around the vehicle, decision-making procedure, and control. In this paper, route planning and local planning algorithms in part of decision-making procedure regards to the urban setting using vector map are suggested. Road networks are converted to the specific form which can be treated easily in route and local motion planning, and route and local planning containing lane changing are conducted. Simulations are conducted in CarLA simulator and shows the validation of the planning algorithm.