• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.63-68
• /
• 2022

Autonomous driving technology has recently made great progress with the introduction of deep reinforcement learning. In order to effectively use deep reinforcement learning, it is important to select the appropriate activation function. In the meantime, many activation functions have been presented, but they show different performance depending on the environment to be applied. This paper compares and evaluates the performance of 12 activation functions to see which activation functions are effective when using reinforcement learning to learn autonomous driving on highways. To this end, a performance evaluation method was presented and the average reward value of each activation function was compared. As a result, when using GELU, the highest average reward could be obtained, and SiLU showed the lowest performance. The average reward difference between the two activation functions was 20%.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.4
• /
• pp.61-69
• /
• 2020

As a sales volume of autonomous vehicle continually grows up, regulations on this new technology are being introduced around the world. For example, safety standards for the Level 3 automated driving system was promulgated in December 2019 by the Ministry of Land, Infrastructure and Transport of Korean government. In order to promote the development of autonomous vehicle technology and ensure its safety simultaneously, the regulations on the automated driving systems should be phased in to keep pace with technology progress and market expansion. However, according to SAE J3016, which is well known to classify the level of the autonomous vehicle technologies, the description for classification is rather abstract. Therefore it is necessary to describe the automated driving system in more detail in terms of the 'Level.' In this study, the functions and characteristics of automated driving system are carefully classified at each level based on the commentary in the Informal Working Group (IWG) of the UN WP29. In particular, regarding the Level 4, technical issues are characterized with respect to vehicle tasks, driver tasks, system performance and regulations. The important features of the autonomous vehicles to meet Level 4 are explored on the viewpoints of driver replacement, emergency response and connected driving performance.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.162-170
• /
• 2022

Today, automobiles have become an indispensable element in people's lives, and the distribution of vehicles with various autonomous driving functions is expanding. Sensors such as cameras are used to recognize various situations on the road as an essential element for autonomous driving functions, but camera sensors have disadvantages that are vulnerable to bad weather. In this paper, we present a derivation process that defines external weather environment factors that negatively affect the performance of a camera for an autonomous vehicle. Through the proposed process, it is expected that it will contribute to securing the reliability of the camera and further improving the safety of autonomous vehicles.

• 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.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2200-2202
• /
• 1998

Autonomous mobile robot provide many functions such as sensing, processing, and driving. For more intelligent jobs, more intelligent functions are to be added and the existing functions may be updated. To execute a job autonomous mobile robot has a information of surrounding environment. So, robot uses sonar sensor, vision sensor and so on. Obtained sensor information is used map generation. This paper is focused on map generation using stereo vision system.

• 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.

• 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.22 no.5
• /
• pp.216-223
• /
• 2023

As the technology and level of autonomous vehicles advance and they drive in more diverse road environments, an intuitive and efficient interaction system is needed to resolve and respond to the situations the vehicle faces. The development of driving technology from the perspective of autonomous driving has the ultimate goal of responding to situations involving humans or more. In particular, in complex road environments where mutual concessions must be made, the role of a system that can respond flexibly through efficient communication methods to understand each other's situation between vehicles or between pedestrians and vehicles is important. In order to resolve the status of the vehicle or the situation being faced, the provision and method of information must be intuitive and the efficient operation of an autonomous vehicle through interaction with intention is required. In this paper, we explain the vehicle structure and functions that can display information about the situation in which the autonomous vehicle driving in a living lab can drive stably and efficiently in a diverse and complex environment.

• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.242-263
• /
• 2021

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.