• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.221-239
• /
• 2022

Various elements such as geometry, traffic safety facilities, congestion level, weather, etc., need to be appropriately reflected in the assessment scenario evaluating the driving safety of automated vehicles. Therefore, this study first established a scenario structure and defined the layer of elements, to derive the elements to be reflected in the automated driving safety evaluation. After that, all elemental candidates that can be reflected in each layer were derived by reviewing the relevant literature. Finally, as a result of an expert survey, 77 items were selected to be reflected in the automated driving safety evaluation. The selected elements are expected to be actively utilized in developing scenarios for the driving safety evaluation of automated vehicles in simulation, proving ground, and real road assessments.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.264-283
• /
• 2023

Unlike conventional vehicle traffic accidents, autonomous vehicles traffic accidents can be caused by various factors, including technical problems, the environment, and driver interaction. With the future advances in autonomous driving technology, new issues are expected to emerge in addition to the existing accident causes, and various scenario-based approaches are needed to respond to them. This study developed autonomous vehicle traffic accident scenarios by collecting autonomous driving accident reports, CA DMV collision reports, autonomous driving mode disengagement reports, and autonomous driving actual accident videos. The scenarios were derived based on the functional safety system failure modes of ISO 26262 and attempted to reflect the various issues of autonomous driving functions. The autonomous vehicle scenarios derived through this study are expected to play an essential role in preventing and preparing for various autonomous vehicle traffic accidents in the future and improving the safety of autonomous driving technology.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.230-245
• /
• 2023

The importance of evaluating the safety of Automated Vehicles (AV) is increasing with the advances in autonomous driving technology. Accordingly, an evaluation scenario that defines in advance the situations AV may face while driving is being used to conduct efficient stability evaluation. On the other hand, the single scenarios currently used in conventional evaluations address limited situations within short segments. As a result, there are limitations in evaluating continuous situations that occur on real roads. Therefore, this study developed a set of multiple scenarios that allow for continuous evaluation across entire sections of roads with diverse geometric structures to assess the safety of AV. In particular, the conditions for connecting individual scenarios were defined, and a methodology was proposed for developing concrete multiple scenarios based on the scenario evaluation procedure of the PEGASUS project. Furthermore, a simulation was performed to validate the practicality of these multiple scenarios.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.114-128
• /
• 2019

Recently, the interest in the safety of autonomous vehicles has globally been increasing. Also, there is controversy over the reliability and safety about autonomous vehicle. In Korea, the K-City which is a test-bed for testing autonomous vehicles has been constructing. There is a need for test scenarios for autonomous vehicle test in terms of safety. The purpose of this study is to develop the evaluation scenario for autonomous vehicle at community roads in K-City by using crash data collected by the Korea National Police Agency and a text-mining technique. As a result, 24 scenarios were developed in order to test autonomous vehicle in community roads. Finally, the logical and concrete scenario forms were derived based on the Pegasus 5-layer format.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.142-151
• /
• 2018

In the era of the 4th Industrial Revolution, research and development on autonomous vehicles have been actively conducted all over the world. Under these international trends, the Ministry of Land, Infrastructure and Transport is actively promoting the development of autonomous vehicles aiming at commercialization of autonomous vehicles at level 3 or higher by 2020. In the level 3 autonomous vehicle, it is essential to transfer control between the driver and the vehicle according to driving situations. Prior to the full-fledged autonomous vehicle age, this study developed a representative scenario for the safety evaluation on take-over on expressways. To accomplish this, we developed a highway driving scenario first, and then developed six control transition scenarios based on 2014 highway traffic accident data and take-over data. The variables to be considered in the developed scenarios are divided into drivers, vehicles, and environmental factors. A total of 36 variables are selected.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.250-265
• /
• 2022

Positive effects such as significantly reducing traffic accidents caused by human error can be expected by the introduction of Automated vehicles (AV). However, as new traffic safety issues are expected to occur in the future due to errors in H/W or S/W of autonomous vehicles and lack of its function, it is necessary to establish a scenario to evaluate the driving safety of AV. Therefore, in this study, functional scenario was developed to evaluate the driving safety of AV based on traffic accident data of the National Police Agency. Using the GIS program, QGIS, traffic accident data that occurred in the toll gate and ramp sections of expressway were extracted and accident summary items were checked to classify the types of accident. In addition, based on the results of accident type classification, functional scenario were developed that contains various dangerous situations in the tollgate and ramp sections.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1318-1321
• /
• 2022

본 논문에서는 단일 깊이 센서를 사용하는 자율주행 시나리오에서 거리 계산에 주로 이용되는 깊이 데이터만 이용하는 객체 감지 기술을 제안한다. 우선, 해당 시나리오에서 객체 감지 학습 데이터는 깊이 데이터가 사용되지만 상대적으로 객체 감지 성능을 비교하기 위해 동일한 시간의 색상, 깊이 데이터를 함께 획득하여 학습에 이용한다. 학습모델은 객체 감지 분야에서 최근 주목 받고 있는 YOLOv5로 선정하여 색상, 깊이 데이터의 객체 감지 학습의 결과를 각각 확인하였다. 결과적으로 색상과 깊이 데이터 사이에서 객체 감지 학습 결과의 차이를 확인하며 본 논문에서 제안하는 자율주행 시나리오에 깊이 영상만 이용하는 객체 감지 기술의 문제점과 향후 자율주행 기술 발전에 기여 가능성을 확인할 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.233-252
• /
• 2022

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.

• Convergence Security Journal
• /
• v.18 no.5_1
• /
• pp.105-112
• /
• 2018

Along with the recent technological development, autonomous vehicles are being commercialized. but The accident of autonomous driving car is becoming an issue, and safety problem of autonomous driving car is becoming a hot topic. Also There are currently no specific guidelines for clear laws and security ethics. These guidelines require a lot of information and experience. This study establishes basic guidelines based on cases of accidents from past to present. This study suggests security considerations through case study of security ethics in autonomous car accident.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.430-431
• /
• 2022

자율주행 차량의 성능을 검증하기 위해서는 다양한 검증용 시나리오가 필요하기 때문에 최근에는 검증용 시나리오를 자동으로 생성하기 위한 연구들이 수행되고 있다. 실세계에서 발생되는 다양한 현상을 반영한 시나리오를 생성하기 위해서는 자율주행 차량의 주변 상황에 대한 측정이 필요하지만, 공간적인 문제로 한계가 발생한다. 이와 같은 데이터 수집의 어려움을 자율주행 차량에 탑재된 블랙박스의 영상을 통해서 생성하는 것이 가능하다. 본 논문에서는 DRQN을 이용하여 자율주행 차량 사고영역을 자동으로 탐지하는 방법을 제안한다. 동영상에서 추출된 프레임을 분석해서 교통사고 원도우의 초기 위치를 설정한다. DRQN 학습 프레임워크로 차량의 특징을 도출한다. 마지막으로 특징을 기반으로 교통사고 원도우의 크기와 위치를 조정해서 교통사고 영역을 정확하게 찾는다.