자율주행자동차의 추돌 회피를 위한 교통사고분석 및 기계 학습 기반 위험 시나리오 생성 연구

다국어 초록 (Multilingual Abstract)

In this paper, the critical scenario generation method for the scenario-based approach is proposed to validate collision avoidance systems on autonomous vehicles. Along with three abstraction levels of scenarios for the safety of the intended functionality(SOTIF), as proposed by a PEGASUS project in Germany, critical scenarios based on fatal traffic accidents in Korea were analyzed statistically. Then, the collision scenario model, including all critical scenarios, is proposed to generate logical scenarios systematically. Since the high dimension of parameters in a logical scenario results in a combinatorial explosion of concrete scenarios, it is quite necessary to search for appropriate scenarios. Therefore, many safe scenarios were omitted by applying for a series of conditions based on time-to-collision and support vector machines. Finally, It is shown how scenarios can be generated to validate an automatic emergency braking system, and the critical scenarios are searched out via the proposed generation procedure.

참고문헌 (Reference)

1 강지웅, "협력형 차량 안전 시스템의 잠재적 안전 효과 분석 연구" 한국ITS학회 17 (17): 128-141, 2018

2 "Traffic Accident Analysis System"

3 W. Wachenfeld, "The Worst-Time-To-Collision Metric for Situation Identification" 2016

4 W. Wachenfeld, "The Release of Autonomous Vehicles" Springer 425-449, 2016

5 General Motors, "Self-Driving Safety Report"

6 T. Menzel, "Scenarios for Development, Test and Validation of Automated Vehicle" 1821-1827, 2018

7 H. Winner, "Road Vehicle Automation 5" Springer 185-195, 2019

8 W. G. Najm, "Pre-crash Scenario Typology for Crash Avoidance Research" National Highway Traffic Safety Administration 2007

9 Waymo Safety Report, "On the Road to Fully Self-Driving"

10 J. Bakker, "IGLAD-International Harmonized In-depth Accident Data" (17-0248) : 2017

11 IGLAD, "IGLAD Codebook"

12 K. Lee, "Evaluation of Automotive Forward Collision Warning and Collision Avoidance Algorithms" 43 (43): 735-751, 2007

13 National Transportation Safety Board, "Collision Between Vehicle Controlled by Developmental Automated Driving System and Pedestrian" 2019

14 M. Tatar, "Chasing Critical Situations in Large Parameter Spaces" 2018

15 IPG Automotive, "CarMaker Reference Manual Version 7.0.2"

16 P. Rau, "Approach for Deriving Scenarios for Safety of the Intended Functionality" (19-0258) : 2019

17 D. Zhao, "Accelerated Evaluation of Automated Vehicles in Lane-Change Scenarios Based on Importance Sampling Techniques" 18 (18): 595-607, 2017

18 D. Zhao, "Accelerated Evaluation of Automated Vehicles in Car-Following Maneuvers" 19 (19): 733-744, 2018

19 G. Amid, "ASAM OpenSCENARIO: Version 2.0.0Concepts"

20 E. Thorn, "A Framework for Automated Driving System Testable Cases and Scenarios" NHTSA 2018