Vision Transformer를 활용한 비전 데이터 기반 자율주행자동차 사고 취약상황 예측 및 시나리오 도출
Predicting Accident Vulnerable Situation and Extracting Scenarios of Automated Vehicleusing Vision Transformer Method Based on Vision Data
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
자율주행자동차 상용화를 위해 자율주행자동차 안전성 제고를 위한 다양한 연구가 수행되고 있으며, 그 중 시나리오 연구가 안전성 평가에 직접적으로 연관되어 필수적으로 고려되고있다. 그러나 기존 시나리오 제시의 경우 데이터 부재 및 전문가 개입으로 인해 객관성 및 설명력이 보완될 필요가 있다는 의견이 제시되고 있다. 이에 본 연구에서는 실제 사고 데이터및 설명력 있는 인공지능 방법론인 ViT 모델을 활용하여 확장된 자율주행자동차 안전성 평가시나리오를 제시한다. 활용 데이터에 최적화시킨 ViT 모델 학습 결과, 94% 정확도가 확인되었으며 Attention Map을 추가적으로 활용하여 설명력 있는 시나리오를 제시하였다. 본 연구를 통해 기존 시나리오 접근법의 한계를 보완하고 인공지능을 활용하여 새로운 안전성 평가 시나리오 수립 프레임워크를 제시할 수 있을 것으로 기대된다.
Abstract
Recently, various studies have been conducted to improve automated vehicle (AV) safety for AVs commercialization. In particular, the scenario method is directly related to essential safety assessments. However, the existing scenario do not have objectivity and explanability due to lack of data and experts’ interventions. Therefore, this paper presents the AVs safety assessment extended scenario using real traffic accident data and vision transformer (ViT), which is explainable artificial intelligence (XAI). The optimal ViT showed 94% accuracy, and the scenario was presented with Attention Map. This work provides a new framework for an AVs safety assessment method to alleviate the lack of existing scenarios.
참고문헌 (45)
- Abbas, H., "Safe at any speed: A simulation-based test harness for autonomous vehicles", International Workshop on Design, Modeling, and Evaluation of Cyber Physical Systems, pp.94~106 (2017), Springer
- Alambeigi, H., "Crash themes in automated vehicles: A topic modeling analysis of the California Department of Motor Vehicles automated vehicle crash database", arXiv preprint arXiv:2001.11087, ~ (2020)
- Arvin, R., "Safety critical event prediction through unified analysis of driver and vehicle volatilities: Application of deep learning methods", Accident Analysis &Prevention, 151, pp.105949~ (2021)
- "Audi, A. G. and Volkswagen, A. G." (2022)[URL]
- Bartels, A., "D2.1. System Classification and Glossary", Adaptive Consortium, 63~ (2015)
- Chae, H., "Development and Implementation of Safety Evaluation Scenarios for Automated Driving Vehicles on Test Bed", 26th International Technical Conference on the Enhanced Safety of Vehicles (ESV): Technology: Enabling a Safer Tomorrow National Highway Traffic Safety Administration, pp.1~13 (2019)
- Das, A., "Opportunities and challenges in explainable artificial intelligence (xai): A survey", arXiv preprint arXiv:2006.11371, ~ (2020)
- "De Gelder, E., Den Camp, O. O. and De Boer, N" (2020)[URL]
- Demetriou, A., "Generation of driving scenario trajectories with generative adversarial networks", 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.1~6 (2020), IEEE
- Dosovitskiy, A., "An image is worth 16x16 words: Transformers for image recognition at scale", arXiv preprint arXiv:2010.11929, ~ (2020)
- "ENABLE-S3 Consortium" (2019)[URL]
- Erdogan, A., "Real-world maneuver extraction for autonomous vehicle validation: A comparative study", 2019 IEEE Intelligent Vehicles Symposium (IV), pp.267~272 (2019)
- Fremont, D. J., "Formal scenario-based testing of autonomous vehicles: From simulation to the real world", 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.1~8 (2020), IEEE
- Goodall, N. J., "Ethical decision making during automated vehicle crashes", Transportation Research Record, 2424(1), pp.58~65 (2014)
- Hiller, J., "The L3Pilot Common Data Format-Enabling efficient automated driving data analysis", Proceedings of the 26th International Technical Conference on the Enhanced Safety of Vehicles, pp.10~13 (2019)
- Jenkins, I. R., "Accident scenario generation with recurrent neural networks", 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp.3340~3345 (2018), IEEE
- Kang, M., "Is Only the Dedicated Lane for Automated Vehicles Essential in the Future? The Dedicated Lanes Optimal Operating System Evaluation", Sustainability, 14(18), pp.11490~ (2022)
- Kang, M., "For Preventative Automated Driving System (PADS):Traffic Accident Context Analysis Based on Deep Neural Networks", Electronics, 9(11), pp.1829~ (2020)
- Kang, M., "Congress on Intelligent Systems", pp.1~15 (2022), Springer
- Karim, M. M., "A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention", arXiv preprint arXiv:2106.10319, ~ (2021)
- 김두용, "SAE Level 3 자율주행자동차의 고장 안전성 정량적 평가 방법 개발에 관한 연구", 한국ITS학회 논문지, 18(1), pp.91~102 (2019), 한국ITS학회[DOI]
- Kim, K., "Design of integrated risk management-based dynamic driving control of automated vehicles", IEEE Intelligent Transportation Systems Magazine, 9(1), pp.57~73 (2017)
- Ko, W., "Development of a framework for generating driving safety assessment scenarios for automated vehicles", Sensors, 22(16), pp.6031~ (2022)
- 고우리, "자율주행차 평가 시나리오 구성요소 도출: 고속도로 본선구간을 중심으로", 한국ITS학회 논문지, 21(1), pp.221~239 (2022), 한국ITS학회[DOI]
- Koopman, P., "A safety standard approach for fully autonomous vehicles", International Conference on Computer Safety, Reliability, and Security, pp.326~332 (2019), Springer
- 이지민, "자율주행자동차의 추돌 회피를 위한 교통사고분석 및 기계 학습 기반 위험 시나리오 생성 연구", 한국자동차공학회 논문집, 28(11), pp.817~826 (2020), 한국자동차공학회
- Lee, W., "The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network", Electronics, 10(14), pp.1737~ (2021)
- 임형호, "주행데이터 기반 자율주행 안전성 평가 시나리오 개발 및 검증", 자동차안전학회지, 9(4), pp.7~13 (2017), 사단법인 한국자동차안전학회
- Liu, L., "On the variance of the adaptive learning rate and beyond", arXiv preprint arXiv:1908.03265, ~ (2019)
- Luettel, T., "Autonomous ground vehicles-Concepts and a path to the future", Proceedings of the IEEE, pp.1831~1839 (2012)
- Masmoudi, M., "Object detection learning techniques for autonomous vehicle applications", 2019 IEEE International Conference on Vehicular Electronics and Safety (ICVES), pp.1~5 (2019), IEEE
- Norden, J., "Efficient black-box assessment of autonomous vehicle safety", arXiv preprint arXiv:1912.03618, ~ (2019)
- Osman, O. A., "Prediction of near-crashes from observed vehicle kinematics using machine learning", Transportation Research Record, 2673(12), pp.463~473 (2019)
- 박상민, "5-레이어 포맷을 이용한 자율주행자동차 실험 시나리오 개발(커뮤니티부 도로를 중심으로)", 한국ITS학회 논문지, 18(2), pp.114~128 (2019), 한국ITS학회[DOI]
- 박성호, "드라이빙 시뮬레이터를 이용한 자율주행자동차 제어권 전환 소요시간 및 안정화 특성 분석", 한국ITS학회 논문지, 18(4), pp.31~43 (2019), 한국ITS학회[DOI]
- Remmen, F., "Cut-in scenario prediction for automated vehicles", 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES), pp.1~7 (2018), IEEE
- Riedmaier, S., "Survey on scenario-based safety assessment of automated vehicles", IEEE Access, 8, pp.87456~87477 (2020)
- Strickland, M., "Deep predictive models for collision risk assessment in autonomous driving", 2018 IEEE International Conference on Robotics and Automation (ICRA), pp.4685~4692 (2018), IEEE
- Sui, B., "A clustering approach to developing car-to-two-wheeler test scenarios for the assessment of Automated Emergency Braking in China using in-depth Chinese crash data", Accident Analysis & Prevention, 132, pp.105242~ (2019)
- Szegedy, C., "Rethinking the inception architecture for computer vision", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2818~2826 (2016), IEEE
- Ulbrich, S., "Defining and substantiating the terms scene, situation, and scenario for automated driving", 2015 IEEE 18th International Conference on Intelligent Transportation Systems, pp.982~988 (2015), IEEE
- Vaswani, A., "Attention is all you need", Advances in Neural Information Processing Systems, 30 (2017)
- Virdi, J., "Using deep learning to predict obstacle trajectories for collision avoidance in autonomous vehicles", pp.2018
- Yu, R., "Identifying High Risk Driving Scenarios Utilizing a CNN-LSTM Analysis Approach", 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.1~6 (2020), IEEE
- Zhao, X., "Assessing the safety and reliability of autonomous vehicles from road testing", 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE), pp.13~23 (2019), IEEE
