http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
신윤식,박요한,신재곤,정재일,Shin, Yunsik,Park, Yohan,Shin, Jae-Kon,Jeong, Jayil 한국자동차안전학회 2021 자동차안전학회지 Vol.13 No.4
In this study, The behavior of an autonomous vehicle in an intersection accident situation is predicted. Based on a representative intersection accident situation from actual intersection accident database, simulation was performed by applying the automatic emergency braking algorithm used in the autonomous driving system. Accident reconstruction was performed based on the accident report of the representative accident situation. After applying the autonomous driving system to the accident-related vehicle, the tendency of intersection accidents that may occur in autonomous vehicles was identified and analyzed.
차량 CAN 데이터를 이용한 딥러닝 기반 실시간 운전자 성향 분류 기법
신윤식(YunSik Shin),송희진(HeeJin Song),박재용(JaeYong Park),최준원(JunWon Choi) 한국자동차공학회 2020 한국자동차공학회 부문종합 학술대회 Vol.2020 No.7
In this paper, we propose a deep learning-based driver’s style classification method using the CAN data. We collected the 7 hours of CAN data for 100 drivers with different driving style in suburb area in Kwangju province. We categorized the driving style into “sport” versus “comfort” based on the surveys from both driver and passenger. We use the 1D Convolutional Neural Network(1D-CNN) model to extract the feature from 25.6 seconds of the CAN data and train the model to classify between the sport and comfort styles from the feature. Our evaluation shows that the proposed method achieves the accuracy of 80.94% for the test dataset and exhibits reasonable rea-time classification performance when deployed in a test vehicle.