http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
강원율(Wonyul Kang) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.11
It takes many hours and restrictions once AD(Autonomous Driving) evaluation based on real vehicle tests. This paper presents a methodology for development of virtual driving environment that can replace the real vehicle test. When developing a virtual driving environment, it is important to develop the same virtual element model (Road, Vehicle model, etc.) as the real world. So the high-occupancy BRT (Bus Rapid Transit) bus route in Cheongna zone was modelled using the MMS(Mobile Mapping System) as the openDRIVE format which is the ASAM(Association for Standardization of Automation and Measuring Systems) road standard. In addition, we develop a vehicle model that simulates the dynamic performance of BRT based on Modelica language. Finally, we develop an interface module that integrates the virtual environment, the vehicle model, and the driver model. In conclusion, this paper present virtual test drive platform for AD Evaluation..
정비범(Beebum Jung),강원율(Wonyul Kang),이종현(Jonghyun Yi),허승진(Seung-Jin Heo) 한국자동차공학회 2013 한국자동차공학회 부문종합 학술대회 Vol.2013 No.5
Brake performance of the vehicle has a great influence on the driver safety and driving characteristics of the vehicle. This study proposes a method to analysis effect analysis of the brake design parameter through the simulation of multi-body dynamic vehicle model. Purpose of effect analysis is to analyze the relationship of brake design parameter and brake distance. The design variables are μ-peak, peak-slip ratio and μ-slide in longitudinal μ-slip curve. Before conducting an effect analysis, a vehicle model based on MBD(Multi-body dynamics) was made through reverse engineering, and it was verified by field test. As the design of experiment for effect analysis, a full factorial design method was used. As a result of conducting an effect analysis of the brake design parameter, it was identified that the μ -peak, peak-slip ratio and μ-slide in longitudinal μ-slip curve have an influence of 91%, 2%, 7% respectively in case of ABS(Anti lock brake system) on. In case of ABS off, it have an influence of 63%, 2% and 35% respectively.
딥러닝 기반 장애물 인식을 위한 가상환경 및 데이터베이스 구축
이재인(JaeIn Lee),곽기성(Gisung Gwak),김경수(KyongSu Kim),강원율(WonYul Kang),신대영(DaeYoung Shin),황성호(Sung-Ho Hwang) 유공압건설기계학회 2021 드라이브·컨트롤 Vol.18 No.4
This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user"s desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.