정선암 이세민 정영훈 김승환 송봉섭 2024-03 1225-6382 https://aurora.ajou.ac.kr/handle/2018.oak/37908 https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003060015 The selection method of concrete scenarios based on scenario database and generative models is proposed in this paper. Two sampling methods are used in selecting appropriate parameters along a performance measure. First, the parameter space is extracted from scenario DB, and a set of parameters are selected via random sampling. Once the set of concrete scenarios are simulated, their distribution is analyzed with respect to a specific measure. The second method is based on parameter generative models. Simulated scenarios are used to train a surrogate model, which is a multi-layer perceptron model. Then, a generative model is designed to search for the desired parameter based on the surrogate model. Thus, the second one can be used to compensate for the imbalance in randomly sampled concrete scenarios. Finally, the proposed selection method is more efficient than random sampling from the viewpoint of the distribution of two different measures. Kor 한국자동차공학회 시나리오 데이터베이스와 생성형 모델을 이용한 상세 시나리오의 파라미터 선정과 선행차량 추종 및 끼어들기 시나리오 생성으로의 적용 Parameter Selection of Safety- Critical Scenari os Based on Scenario Database and Generative Models and Its Application to Generation of Car-Following and Cut- in Scenarios Article 318 3 309 한국자동차공학회 논문집 32 한국자동차공학회 논문집, Vol.32 No.3, pp.309-318 상세 시나리오 파라미터 공간 대리 모델 경사 하강법 생성형 모델 다층 퍼셉트론 자율주행 시나리오 Concrete scenario Parameter space Surrogate model Gradient descent Generative model Multi-layer perceptron Autonomous driving scenario Article