• Journal of Auto-vehicle Safety Association
• /
• v.15 no.2
• /
• pp.21-27
• /
• 2023

This paper presents a simulation tool for developing and evaluating automated driving systems' lane change algorithm in urban congested traffic. The behavior of surrounding vehicles was modeled based on driver driving data measured in urban congested traffic. Surrounding vehicles are divided into aggressive vehicles and non-aggressive vehicles. The degree of aggressiveness is determined according to the lateral position to initiate interaction with the vehicle in the next lane. In addition, the desired velocity and desired time gap of each vehicle are all randomly assigned. The simulation was conducted by reflecting the cognitive limitations and control performance of the autonomous vehicle. It was possible to confirm the change in the lane change performance according to the variation of the lane change decision algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.194-200
• /
• 2022

As of 2020, the cumulative number of electric vehicles worldwide increased 43% from 2019, exceeding 10 million. We surveyed and analyzed important factors when purchasing electric vehicles for consumers who own electric vehicles. Through this, we tried to find an effective way to supply electric vehicles in the future. The purpose of this study is to present customized marketing proposals for companies by empirically analyzing the factors affecting consumers' electric vehicle purchases and deriving market demands for electric vehicles. We identified the market status of electric vehicles through literature research and reviewed previous studies on the factors affecting the purchase intention of electric vehicles. Through empirical studies, differences in electric vehicle purchase factors according to gender, age, and the degree of importance of performance were analyzed. To this end, the SPSS statistics package was used. Factors influencing the purchase of electric vehicles were set to mileage, charging time, new technology, degree of driving autonomous development, design, price, infrastructure for charging, the phase of maintenance and repair, by the government and local governments. In addition, the most important factors were derived, and the average difference analysis was conducted according to gender, age, and performance importance.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.5
• /
• pp.269-276
• /
• 2014

In recent, autonomous navigation techniques to avoid obstacles have been studied by using unmanned aircraft vehicles(UAVs) since the increment of UAV's interest and utilization. Particularly, autonomous navigation based UAVs are utilized in several areas such as military, police, media, and so on. However, there are still some problems to avoid obstacle when UVAs perform autonomous navigation. For instance, the UAV can not forward in the corner of corridors even though it utilizes the improved vanish point algorithm that makes an autonomous navigation system. Therefore, in this paper, we propose an obstacle avoidance technique based on immune algorithm for autonomous navigation of Quadrotor. The proposed algorithm is consisted of two steps such as 1) single color discrimination and 2) multiple color discrimination. According to the result of experiments, we can solve the previous problem of the improved vanish point algorithm and improve the performance of autonomous navigation of Quadrotor.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.84-95
• /
• 2018

A mathematical model of responsibility-sensitive safety (RSS) has been proposed as a way to determine whether an autonomous driving accident has occurred. Autonomous vehicles related industry and academia have shown great interest in this model. However, this mathematical model lacks a comprehensive review on whether the model can be used to clarify responsibilities of autonomous vehicles in the event of a traffic accident. In this study, we analyzed the issues that need to be solved in order to apply the RSS model. In conclusion, there is a limit in the equation and the social acceptability of the RSS model. To use the RSS model practically, it is necessary to define the response time of the autonomous vehicle and to measure and control the reaction time value according to the appropriate technology level for each autonomous vehicle.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.5842-5861
• /
• 2019

A current autonomous vehicle determines its driving strategy by considering only external factors (Pedestrians, road conditions, etc.) without considering the interior condition of the vehicle. To solve the problem, this paper proposes "An Optimal Driving Support Strategy(ODSS) based on an Genetic Algorithm for Autonomous Vehicles" which determines the optimal strategy of an autonomous vehicle by analyzing not only the external factors, but also the internal factors of the vehicle(consumable conditions, RPM levels etc.). The proposed ODSS consists of 4 modules. The first module is a Data Communication Module (DCM) which converts CAN, FlexRay, and HSCAN messages of vehicles into WAVE messages and sends the converted messages to the Cloud and receives the analyzed result from the Cloud using V2X. The second module is a Data Management Module (DMM) that classifies the converted WAVE messages and stores the classified messages in a road state table, a sensor message table, and a vehicle state table. The third module is a Data Analysis Module (DAM) which learns a genetic algorithm using sensor data from vehicles stored in the cloud and determines the optimal driving strategy of an autonomous vehicle. The fourth module is a Data Visualization Module (DVM) which displays the optimal driving strategy and the current driving conditions on a vehicle monitor. This paper compared the DCM with existing vehicle gateways and the DAM with the MLP and RF neural network models to validate the ODSS. In the experiment, the DCM improved a loss rate approximately by 5%, compared with existing vehicle gateways. In addition, because the DAM improved computation time by 40% and 20% separately, compared with the MLP and RF, it determined RPM, speed, steering angle and lane changes faster than them.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.42-60
• /
• 2024

This study analyzed the characteristics of mixed traffic flows with autonomous vehicles on highway weaving sections and assessed the safety of vehicle-following pairs based on surrogate safety indicators. The intelligent driver model (IDM) was utilized to emulate the driving behavior of autonomous vehicles, and the weaving sections were divided into lengths of 300 and 600 meters for analysis within a micro-traffic simulation (VISSIM). Although significant differences were found in the average speed, density, and headway between the two sections through t-test results, no significant differences were observed when comparing the number of conflicts per indicator and the vehicle-following pair. Four safety indicators were selected for the mixed traffic evaluation based on their ability to represent risk levels similar to those perceived by drivers. The safety analysis, based on the selected four indicators, determined that autonomous vehicles following other autonomous vehicles were the safest pairing. Future research should focus on integrating these indicators into a single comprehensive index for analysis.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.123-133
• /
• 2024

Existing autonomous driving technology has been developed based on sensors attached to the vehicles to detect the environment and formulate driving plans. On the other hand, it has limitations, such as performance degradation in specific situations like adverse weather conditions, backlighting, and obstruction-induced occlusion. To address these issues, cooperative autonomous driving technology, which extends the perception range of autonomous vehicles through the support of road infrastructure, has attracted attention. Nevertheless, the real-time analysis of the 3D centroids of objects, as required by international standards, is challenging using single-lens cameras. This paper proposes an approach to detect objects and estimate the centroid of vehicles using the fixed field of view of road infrastructure and pre-measured geometric information in real-time. The proposed method has been confirmed to effectively estimate the center point of objects using GPS positioning equipment, and it is expected to contribute to the proliferation and adoption of cooperative autonomous driving infrastructure technology, applicable to both vehicles and road infrastructure.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.2
• /
• pp.110-116
• /
• 2016

Autonomous vehicles must obey the traffic laws in order to drive actual roads. Traffic signs erected at the side of roads explain the road traffic information or regulations. Therefore, traffic sign recognition is necessary for the autonomous vehicles. In this paper, color characteristics are first considered to detect traffic sign candidates. Subsequently, we establish HOG (Histogram of Oriented Gradients) features from the detected candidate and recognize the traffic sign through a SVM (Support Vector Machine). However, owing to various circumstances, such as changes in weather and lighting, it is difficult to recognize the traffic signs robustly using only SVM. In order to solve this problem, we propose a tracking algorithm with RANSAC-based motion estimation. Using two-point motion estimation, inlier feature points within the traffic sign are selected and then the optimal motion is calculated with the inliers through a bundle adjustment. This approach greatly enhances the traffic sign recognition performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.154-160
• /
• 2012

Recently, development of technologies for autonomous vehicles has been actively carried out. This paper proposes a computer vision system to recognize lanes, crosswalks, and stop lines for autonomous vehicles. This vision system first recognizes lanes required for autonomous driving using the RANSAC algorithm and the Kalman filter, and changes the viewpoint from the perspective-angle view of the street to the top-view using the fact that the lanes are parallel. Then in the reconstructed top-view image this system recognizes a crosswalk based on its geometrical characteristics and searches for a stop line within a region of interest in front of the recognized crosswalk. Experimental results show excellent performance of the proposed vision system in recognizing lanes, crosswalks, and stop lines.