• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.5
• /
• pp.293-307
• /
• 2024

In mixed traffic conditions, the conservative driving behavior of autonomous vehicles (AV) would negatively affect overall traffic performance. In order to manage mobility and safety in mixed traffic conditions, it is essential to scientifically evaluate driving behavior using autonomous driving data collected from real-world. This study proposed a methodology to evaluate the driving behavior of autonomous vehicles (AV) and manual vehicles (MV) at different types of intersections using the Waymo Open Dataset. Urban street were identified through video data, and the autonomous driving conservativeness index (ADCI) was devised to compare the difference in time-to-collision (TTC) based conflict rates between AV and MV in car following situations. The results showed that unsignalized 4-way intersections had the highest ADCI value, indicating greater conservativeness in driving behavior. This indicates the necessity of analyzing the driving behavior of each road section and deriving support measures to prevent AV from negatively affecting the overall traffic performance in mixed traffic conditions. The methodology of this study is expected to serve as foundational for analyzing factors affecting AV using real-world datasets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.183-200
• /
• 2022

A variety of simulation approaches based on automated driving technologies have been proposed to develop traffic operations strategies to prevent traffic crashes and alleviate congestion. The maneuver of simulated autonomous vehicles (AVs) needs to be realistic and be effectively differentiated from the behavior of manually driven vehicles (MVs). However, the verification of simulated AV maneuvers is limited due to the difficulty in collecting actual AVs trajectory and interaction data with MVs. The purpose of this study is to develop a methodology to evaluate the suitability of AV maneuvers based on both driving and traffic simulation experiments. The proposed evaluation framework includes the requirements for the behavior of individual AVs and the traffic stream performance resulting from the interactions with surrounding vehicles. A driving simulation approach is adopted to evaluate the feasibility of maneuvering of individual AVs. Meanwhile, traffic simulations are used to evaluate whether the impact of AVs on the performance of traffic stream is reasonable. The outcome of this study is expected to be used as a fundamental for the design and evaluation of transportation systems using automated driving technologies.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.39-47
• /
• 2023

The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.13-27
• /
• 2021

In this study, the impact of traffic flow on the market penetration rate of autonomous vehicles(AV) was analyzed using the data for the year 2020 of the Yongin IC~Yangji IC section of Yeongdong Expressway. For this analysis, a microscopic traffic simulation model VISSIM was utilized. To construct the longitudinal control of the AV, the Intelligent Driver Model(IDM) was built and applied, and the driving behavior was verified by comparison with a normal vehicle. An examination of the study results of mobility and safety according to the market penetration rate of the AV, showed that the network's mobility improves as the market penetration rate increases. However, from the point of view of safety, the network becomes unstable when normal vehicles and AVs are mixed, so there should be a focus on traffic management for ensuring safety in mixed traffic situations.