http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
APF 기법을 이용한 자율주행차량의 운행 적합도 지표 개발
김좌헌(Joahun Kim),조건희(Kunhee Cho),이형철(Heongcheol Lee) 한국자동차공학회 2021 한국자동차공학회 부문종합 학술대회 Vol.2021 No.6
In this paper, we design a driving suitability Indicator based on situational measurement data around autonomous vehicles. Autonomous vehicle affect surrounding vehicles due to driving speed deceleration/acceleration and lane change in process of path tracking to the target position. In order to indicator the impact on surrounding vehicles, the Artificial Potential Field(APF) is constructed using longitudinal/lateral relative velocity and relative distance to the surrounding vehicles in traffic flow. This application quantifies the suitability of autonomous vehicles. The derived driving suitability index can be seen as an indicator of how conservative autonomous vehicles are driving toward surrounding vehicles in traffic flow or whether autonomous vehicles are driving properly. To validate the designed goodness-of-fit indicators, we construct longitudinal, lateral fusion scenarios based on traffic accident case data provided by the KoROAD and AEB tests provided by Euro NCAP. Based on the configured scenario, conservative/nonconservative driving data of many drivers were acquired and used for verification using dSPACE’s Automatic Simulation Model(ASM) Driving simulator. Scenario verification shows numerical suitability for all longitudinal and lateral situations based on the suitability indicators proposed in this paper. In conservative driving situations, it was found that the driving suitability of surrounding vehicles is high compared to non-conservative driving situation.
권대욱(Dae Wook Kwon),김좌헌(JoaHun Kim),조건희(Kun Hee Cho),이형철(Hyeongcheol Lee) 한국자동차공학회 2020 한국자동차공학회 학술대회 및 전시회 Vol.2020 No.11
In this paper, we classified and composed a set of driving scenarios based on the statistical results of the Traffic Accident Analysis System of the Road Traffic Authority. The driving environmental data and the relative distance between the vehicles were obtained using dSPACE’s ASM (Automotive Simulation Models) and Driving Simulator, respectively. At this time, the relative distance and relative speed were calculated using the position, speed, and acceleration of the autonomous vehicle and the of the surrounding vehicles. Since we need responses of driver or occupant to determine whether autonomous vehicle is appropriate or not, we created an input signal called ‘Trigger Signal’. The driver or occupant trigger it only for inappropriate driving situation of each scenarios. With this experimental data, we built MLP (Multilayer Perceptron) based on MATLAB and collected environmental/vehicle data and triggered signal were dealt with input/output for training MLP, respectively. Then the output of MLP is quantitatively considered as driving suitability index to visualize how driving situation is appropriate or not. With this designed index, it can be used for designing threshold of controllers in ADAS (Advanced Driver Assistance System)/AV (Automated Vehicle) systems to consider various drivers’ acceptances.