• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.263-272
• /
• 2021

At a time when securing driving safety is the most important in the development and commercialization of autonomous vehicles, AI and big data-based algorithms are being studied to enhance and optimize the recognition and detection performance of various static and dynamic vehicles. However, there are many research cases to recognize it as the same vehicle by utilizing the unique advantages of radar and cameras, but they do not use deep learning image processing technology or detect only short distances as the same target due to radar performance problems. Radars can recognize vehicles without errors in situations such as night and fog, but it is not accurate even if the type of object is determined through RCS values, so accurate classification of the object through images such as cameras is required. Therefore, we propose a fusion-based vehicle recognition method that configures data sets that can be collected by radar device and camera device, calculates errors in the data sets, and recognizes them as the same target.

• 한국ITS학회 논문지
• /
• 제20권6호
• /
• pp.299-312
• /
• 2021

V2X를 활용한 자율주행차량은 기존의 자율주행차량보다 더욱 많은 정보를 바탕으로 자율주행차량의 센서 커버리지 밖의 영역의 정보를 통하여 안전한 주행이 가능하다. V2X 기술이 자율주행차량의 핵심 구성 요소로 부각되면서 V2X 보안 문제에 대해 연구가 활발히 진행되고 있지만 자율주행차량이 V2X의 의존도가 높은 자율주행시스템에서 V2X 통신의 고장으로 인한 위험성에 대한 부분은 상대적으로 부각되고 있지 않으며 관련 연구도 미진한 편이다. 본 논문에서는 자율주행차량의 교차로 시나리오를 제시하여 V2X를 활용한 자율주행시스템의 서비스 시나리오를 정의 하였으며 이를 기반으로 기능을 도출하고 V2X의 위험 요인을 분석하여 오작동을 정의하였다. ISO26262 Part3 프로세스를 활용하여 HARA 및 고장 주입 시나리오의 시뮬레이션을 통해 V2X 모듈의 고장으로 인한 위험성과 이를 확인하는 검증 과정을 제시하였다.

• 자동차안전학회지
• /
• 제15권2호
• /
• 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
• /
• 제14권1호
• /
• 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.

• 대한임베디드공학회논문지
• /
• 제9권5호
• /
• 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
• /
• 제23권11호
• /
• 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.

• 자동차안전학회지
• /
• 제16권1호
• /
• pp.55-61
• /
• 2024

The advancement of autonomous driving technology is expected to transform cars beyond mere transportation into multifunctional spaces for relaxation and entertainment. As autonomous driving technology becomes more sophisticated, with no need for direct driver control, the interior space of vehicles is anticipated to be utilized for various purposes. Consequently, the importance of car seats, the component most frequently interacted with by passengers during travel, is expected to significantly rise. However, existing car seats are designed according to a seated posture, necessitating verification for passenger safety and seat structure considerations in the context of autonomous driving, where comfortable postures may differ. For these reasons, it is anticipated that the seats of future autonomous vehicles will evolve with the incorporation of additional safety and convenience features. In this study, a three-axis car simulator was employed to investigate seat angles for comfortable postures of passengers in autonomous driving scenarios. Representative postures were identified to enhance passenger convenience. Furthermore, functional design factors contributing to passenger comfort were applied to conduct seat design, seat structure, and collision analysis, with an analysis of the interrelationships among design factors.

• 한국ITS학회 논문지
• /
• 제17권6호
• /
• pp.84-95
• /
• 2018

자율주행 과실 여부 판단 위한 방법으로 수학적인 모형인 responsibility-sensitive safety(RSS)를 제시된 이후로 자율주행 관련 산업으로부터 많은 관심을 받고 있다. 하지만, 이러한 수학적 모형이 자율주행자동차가 관련된 교통사고 발생 시 책임소재를 명확히 하는 데 활용될 수 있는 지에 대한 종합적인 검토는 부족한 실정이다. 본 연구에서는 RSS 모형의 적용성과 활용을 위해서 추가적으로 해결되어야 할 사항에 대하여 분석하였다. 결론적으로 RSS 모형을 활용하기에는 모형식 자체 및 수용성 등에 한계가 있으며, RSS 모형을 실무적으로 사용하려고 한다면 자율주행자동차의 반응시간을 정의하고, 자율주행자동차별로 적절한 기술수준에 따라서 반응시간 값을 측정하고 관리할 필요가 있는 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• 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.

• 한국ITS학회 논문지
• /
• 제23권1호
• /
• pp.42-60
• /
• 2024

본 연구는 자율주행 차량이 혼재된 교통류의 안전성 평가에 적합한 안전성 지표를 선정하여 차량 추종 조합별 안전성을 분석하였다. 고속도로 엇갈림구간은 기본구간에 비해 차로 변경이 빈번하여 상충 빈도가 높은 구간으로, 일반 차량과 자율주행 차량의 주행행태 차이로 인한 위험이 증가할 것으로 예상하여 고속도로 엇갈림구간을 분석구간으로 설정하였다. 미시적 교통 시뮬레이션인 VISSIM을 활용하여 분석을 수행하였으며, 혼합 교통류의 환경은 본선-연결로 형태의 엇갈림구간을 300, 600m의 길이로 구분하고, IDM을 활용하여 자율주행 차량의 주행행태를 구현하였다. 혼합 교통류 평가에 적합한 안전성 지표는 운전자가 체감하는 위험도와 유사하게 위험 수준을 나타내는 것을 기준으로 4개의 지표를 선정하였다. 선정된 4개 지표의 위험 기준을 넘는 차량 추종 궤적을 대상으로 안전성을 분석한 결과, 자율주행 차량이 자율주행 차량을 추종하는 상황이 가장 안전한 추종 쌍이며, 인간 운전자 차량이 자율주행 차량을 추종할 경우가 가장 위험한 추종 쌍인 것으로 나타났다.