• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.3
• /
• pp.97-106
• /
• 2024

The Data Storage System for Automated Driving(DSSAD) is a system that records driving information of Lv.4 or higher autonomous vehicles and is different from EDR that records car information in emergency situations. The study of DSSAD recordings is important for responding to various events that may occur in the future commercialization of Lv.4 autonomous vehicles. Therefore, in this study, we conducted a expressway automated driving demonstration and analyzed the collected data to derive the recording elements of DSSAD. During our two-year demonstration of autonomous driving on expressways, we collected and analyzed instances of disengagement. Our findings indicate that 51.6% of disengagement on expressways occurred during lane changes. From the study, we have identified DSSAD record elements for analyzing disengagement situations. Furthermore, implications of future research direction of disengagement analysis were presented.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.3
• /
• pp.34-42
• /
• 2023

Simulation-based virtual testing is known to be a major requirement for verifying the safety of autonomous driving functions. However, in the simulation environment, there is a difficulty in that all driving environments related to the autonomous driving system must be realistically modeled. In particular, C-ITS (Cooperative-Intelligent Transport Systems) is essential for urban autonomous driving of Lv.4, but the approach to modeling for C-ITS service in the MILS (Model in the Loop Simulation) environment is not yet clear. Therefore, this paper aims to deal with V2X (Vehicle to Everything) modeling methods to effectively apply C-ITS-based autonomous cooperative driving services in the MILS environment. First, major C-ITS services and use cases for autonomous cooperative driving are analyzed, and a modeling method of V2X signals for C-ITS service simulation is proposed. Based on the modeled V2X messages, the validity of the proposed approach is reviewed through simulations on the C-ITS service use case.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.202-217
• /
• 2021

Following the fatal accident of pedestrians caused by Autonomous Vehicle by Uber, the world's largest ride-hailing company, two people were killed in a self-driving car accident by Tesla in April. There is a need to ensure the safety of road users. Accordingly, in order to secure the safety of Autonomous Vehicle driving, it is necessary to evaluate Autonomous Vehicle driving technologies in various situations based on the road and traffic environment in which the Autonomous vehicle will actually drive. Therefore, this study used UC-win/Road ver.14.0 based on general driver's license test questions to present a virtual reality-based Autonomous Vehicles driving ability evaluation tool among various driving ability test method. Based on this, it was intended to test driving ability for unexpected situations in complex and diverse driving environments, and to confirm its practical applicability as an optimal tool for Autonomous vehicle ability test and evaluation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.135-148
• /
• 2020

The ongoing development of autonomous driving-related technology may cause different kinds of accidents while testing new changes. As a result, more information on ODD suitable for the domestic road environment will be necessary to prevent safety accidents. Besides, implementation of the Autonomous Vehicle Act will increase autonomous driving demonstrations on roads currently in use. This study describes an ODD for demonstrating an autonomous driving shuttle in downtown areas. It addresses a possible scenario of autonomous driving around a downtown road in Anyang. Geometric, operational, and environmental factors are considered while maintaining a domestic road environment and safety. Autonomous driving shuttles are demonstrated in 30 nodes, each identified by node type and signal-communication. Link criteria are an autonomous driving restriction in 42 morning peak (8-9am) hours, 39 non-peak (12-13pm) hours, and 40 afternoon peak (18-19pm) hours. In the future, conclusions may be considered for preliminary safety assessments of roads where autonomous driving tests are performed.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.249-255
• /
• 2018

This paper presents a human-centered control algorithm for personalized autonomous driving based on the integration of inverse time-to-collision and time headway. In order to minimize the sense of difference between driver and autonomous driving, the human-centered control technology is required. Driving characteristics in case that vehicle drives with the preceding vehicle have been analyzed and reflected to the longitudinal control algorithm. The driving characteristics such as acceleration, inverse time-to-collision, time headway have been analyzed for longitudinal control. The control algorithm proposed in this study has been constructed on Matlab/Simulink environment and the performance evaluation has been conducted by using actual driving data.

• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.80-86
• /
• 2020

Autonomous driving is one of the most important new technologies of our time; it has benefits in terms of safety, the environment, and economic issues. Path following algorithms, such as automated lane keeping systems (ALKSs), are key level 3 or higher functions of autonomous driving. Pure-Pursuit and Stanley controllers are widely used because of their good path tracking performance and simplicity. However, with the Pure-Pursuit controller, corner cutting behavior occurs on curved roads, and the Stanley controller has a risk of divergence depending on the response of the steering system. In this study, we use the advantages of each controller to propose a hybrid control strategy that can be stably applied to complex driving environments. The weight of each controller is determined from the global and local curvature indexes calculated from HD map information and the current driving speed. Our experimental results demonstrate the ability of the hybrid controller, which had a cross-track error of under 0.1 m in a virtual environment that simulates K-City, with complex driving environments such as urban areas, community roads, and high-speed driving roads.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Design Convergence Study
• /
• v.17 no.4
• /
• pp.17-29
• /
• 2018

In the semi-autonomous vehicle, before reaching a fully autonomous driving stage, it is imperative for the system to issue a take-over request(TOR) that asks a driver to operate manually in a specific situation. The purpose of this study is to compare whether head-up display(HUD) is a better human-vehicle interaction than head-down display(HUD) in the event of TOR. Upon recognition of TOR in the experiment with a driving simulator, participants were prompted to switch over to manual driving after performing a secondart task, that is, playing a game, while in auto-driving mode. The results show that HUD is superior to HDD in 'ease of use' and 'satisfaction' although there is no significant difference in reaction time and subjective workload. Therefore, designing secondary tasks through HUD during autonomous driving situation improves the user experience of the TOR function. The implication of this study lies in the establishing an empirical case for setting up UX design guidelines for autonomous driving context.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.1
• /
• pp.15-25
• /
• 2020

This paper presents a longitudinal control algorithm for ensuring takeover time of autonomous vehicle using V2V communication. In the autonomous driving of more than level 3, autonomous systems should control the vehicles by itself partially. However if the driver's intervention is required for functional safety, the driver should take over the control reasonably. Autonomous driving system has to be designed so that drivers can take over the control from autonomous vehicle reasonably for driving safety. In this study, control algorithm considering takeover time has been developed based on computation method of takeover time. Takeover time is analysed by conditions of longitudinal velocity of preceding vehicle in time-velocity plane. In addition, desired clearance is derived based on takeover time. The performance evaluation of the proposed algorithm in this study was conducted using 3D vehicle model with actual driving data in Matlab/Simulink environment. The results of the performance evaluation show that the longitudinal control algorithm can control while securing takeover time reasonably.