• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.47-54
• /
• 2022

For safe driving of autonomous vehicles, road damage detection is very important to lower the potential risk. In order to ensure safety while an autonomous vehicle is driving on the road, technology that can cope with various obstacles is required. Among them, technology that recognizes static obstacles such as poor road conditions as well as dynamic obstacles that may be encountered while driving, such as crosswalks, manholes, hollows, and speed bumps, is a priority. In this paper, we propose a method to extract similarity of images and find damaged road images using OpenCV image processing and CNN algorithm. To implement this, we trained a CNN model using 280 training datasheets and 70 test datasheets out of 350 image data. As a result of training, the object recognition processing speed and recognition speed of 100 images were tested, and the average processing speed was 45.9 ms, the average recognition speed was 66.78 ms, and the average object accuracy was 92%. In the future, it is expected that the driving safety of autonomous vehicles will be improved by using technology that detects road obstacles encountered while driving.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.3
• /
• pp.53-58
• /
• 2023

Defects in the vehicle itself were considered the biggest risk factor for traffic accidents as the electrical and electronic components of vehicles, which were not there before, increase. Therefore, the vehicles have been developed based on ISO 26262 (an international functional safety standard) which is focusing on functional defect safety evaluation of electrical and electronic component systems. However, in the future, as autonomous driving technology is applied, even vehicles without functional defects must be prepared for the dangerous traffic situation that may arise from exceptional or external factors. SOTIF (Safety Of The Intended Functionality) is a concept to prevent exceptional or external factors. The main objective of SOTIF is to decrease Unknown & Unsafe factors as much as possible by finding Known factors and Unsafe factors. In this study, Prescan provided SIEMENS, one of the autonomous driving simulators, is used to make scenarios of IGLAD traffic accident cases. From the simulation results, Unsafe & Safe cases were classified and analyzed to derive unsafe factors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.251-257
• /
• 2022

Self-driving vehicles are a type of smart vehicle with the help of ICT technology, which means a vehicle that operates without the intervention of a driver.Vehicles with vehicle safety communication technology (V2X) applied use information detected from various sensors or other vehicles/infrastructures to enable the smart vehicle to accurately and quickly predict the driver's potential danger situation, contributing to more stable autonomous driving. In this paper, among V2X communication technologies, a vehicle-to-vehicle communication (V2V) simulation communication technology is used to present a scenario for preventing collisions in autonomous vehicles. A vehicle collision prevention system based on V2V simulated communication was implemented and the suggested collision prevention application scenario was demonstrated. The suggested collision prevention utilization scenario can be considered as one application case of V2V communication technologies that are currently being developed/applied.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.5
• /
• pp.760-767
• /
• 2011

To strategically select the technology priority based on the understanding of technology development trends and prospects is very important. To provide such guidance for autonomous driving technology in unmanned ground combat vehicles, this report deals with followings; 1) The core technologies for autonomous driving are reviewed. 2) And domestic and foreign policies for relevant technology development are investigated. 3) Then, to estimate the technology development trend, the published patents and research papers are analyzed. 4) Based on those analyses, domestic technology level and development prospects are expected.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.230-232
• /
• 2019

There is an accelerating need for ocean sensing where autonomous vehicles can play a key role in assisting engineers, researcher and scientists with environmental monitoring and collecting oceanographic data. This paper is performed to develops an autonomous sailing drone to be used as a sensor carrying platform for autonomous data acquisition at Sea. From a sailing drone design viewpoint, it is important to establish reliable prediction methods for sailing drone's resistance. The required power for the propulsion unit depends on the ship resistance and speed. There are three solutions for the prediction of ship resistance as follow analytical methods, model tests in tanks and Computational Fluid Dynamics (CFD). The present paper aims at simulating sailing drone friction resistance using numerical method. The dynamic mesh motion is used to describe the sailing drone movement.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.63-71
• /
• 2024

Deep reinforcement learning (RL) significantly influences autonomous vehicle development by optimizing decision-making and adaptation to complex driving environments through simulation-based training. In deep RL, an activation function is used, and various activation functions have been proposed, but their performance varies greatly depending on the application environment. Therefore, finding the optimal activation function according to the environment is important for effective learning. In this paper, we analyzed nine commonly used activation functions for RL to compare and evaluate which activation function is most effective when using deep RL for autonomous vehicles to learn highway merging. To do this, we built a performance evaluation environment and compared the average reward of each activation function. The results showed that the highest reward was achieved using Mish, and the lowest using SELU. The difference in reward between the two activation functions was 10.3%.

• Environmental Engineering Research
• /
• v.25 no.3
• /
• pp.366-373
• /
• 2020

The autonomous vehicles (AVs) could make a positive or negative impact on reducing mobile emissions. This study investigated the changes of mobile emissions that could be caused by large-scale adoption of AVs. The factors of road capacity increase and speed limit increase impacts were simulated using a conceptual modeling approach that combines a hypothetical speed-emission function and a traffic demand model using a virtual transportation network. The simulation results show that road capacity increase impact is significant in decreasing mobile emissions until the market share of AVs is less than 80%. If the road capacity increases by 100%, the mobile emissions will decrease by about 30%. On the other hand, driving speed limit increase impact is significant in increasing mobile emissions, and the environmentally desirable speed limit was found at around 95 km/h. If the speed limit increases to 140 km/h, the mobile emissions will increase by about 25%. This is because some vehicles begin to bypass the congested routes at high speeds as speed limit increases. Based on the simulation results, it is clear that the vehicle platooning technology implemented at reasonable speed limit is one of the AV technologies that are encouraging from the environmental point of view.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.251-261
• /
• 2019

The importance of autonomous driving systems that utilize V2X services such as V2V(Vehicle to Vehicle) and V2I(Vehicle to Infrastructure) for safer and more comfortable driving is increasing with the recent development of autonomous vehicles. Partly autonomous vehicles based on environmental sensors have limitations for predicting and determining areas beyond the recognition distance of the mounted sensors and in response to atypical objects that are difficult to detect. Therefore, it is important to utilize the V2X service to improve the limit of sensor detection performance and to make driving safer and more comfortable. However, there may be an accident risk of autonomous vehicles due to incorrect information provided by V2X. Thus, the application of technology to prevent this needs to be considered. In this pater, we used the ISO-26262 Part3 Process and performed HARA (Hazard Analysis and Risk Assessment) to derive the risk sources of autonomous vehicles due to V2I malfunctions by using the communication between vehicles and infrastructure among V2X. We also developed ASIL ratings based on the simulations and real vehicle tests of the malfunctions of major cases of usnig V2I.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.129-143
• /
• 2019

As the importance of autonomous vehicle safety is emphasized, the application of ISO-26262, a development verification guideline for improving safety and reliability, and the safety verification of autonomous vehicles are becoming increasingly important, in particular, SAE standard level 3 or higher level autonomous vehicles detect and decision the surrounding environment instead of the human driver. Therefore, if there is and failure or malfunction in the autonomous driving function, safety may be seriously affected. So autonomous vehicles, it is essential to apply and verity the safety concept against failure and malfunctions. In this study, we study the fault injection scenarios for safety evaluation and verification of autonomous vehicles using ISO-26262 part3 process and STPA were studied and safety measures for safety concept design were studied through simulation bases fault injection test.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.172-191
• /
• 2023

This study was undertaken to strategize the mixed traffic operation of autonomous vehicles in the pilot zone. This was achieved by analyzing the changes expected when autonomous vehicles are mixed in the autonomous vehicle pilot zone. Although finding a safe and efficient traffic operation strategy is required for the pilot zone to serve as a test bed for autonomous vehicles, there is no available operation strategy based on the mixture of autonomous vehicles. In order to presents a traffic operation strategies for each period of autonomous vehicle introduction, traffic efficiency and safety analysis was performed according to the autonomous vehicle market percentage rate. Based on the analysis results, the introduction stage was divided into introductory stage, transition period, and stable period based on the autonomous vehicle market share of 30% and 70%. This study presents the following traffic operation strategies. Considering the traffic flow operation strategy, we suggest the advancement of the existing road infrastructure at the introductory stage, and operating an autonomous driving lane and the mileage system during the transition period. We also propose expanding the operation of autonomous driving lanes and easing the speed limit during the stable period. In the traffic safety strategy, we present a manual and legal system for responding to autonomous vehicle accidents in the introductory stage, an analysis of the causes of autonomous vehicle accidents and the implementation of preventive policies in the transition period, and the advancement of the autonomous system and the reinforcement of the security system during the stable period. Through the traffic operation strategy presented in this study, we foresee the possibility of preemptively responding to the changes of traffic flow and traffic safety expected due to the mixture of autonomous vehicles in the autonomous vehicle pilot zone in the future.