• 한국게임학회 논문지
• /
• 제15권5호
• /
• pp.131-142
• /
• 2015

자율주행 자동차는 전통적인 차량의 주요 수송 기능을 수행 할 수 있는 자동 운전 차량 말하며, 그것은 주변 환경을 감지하고 인간의 어떠한 입력 없이 이동 가능하여야 한다. 본 논문에서는 이러한 자율주행 자동차를 시뮬레이션 할 수 있는 자율주행 자동차 에이전트를 설계하고 이에 대한 프로토타입을 개발하였다. 이를 위하여 자율주행 자동차에 대한 요구 사항을 분석하고, 전통적인 다중 에이전트 시스템에 적합하도록 에이전트를 설계하였다. 설계의 핵심 은 에이전트들은 오직 조종힘에 따라 이동하도록 하는 것이다. 설계된 에이전트의 프로토타입은 유니티3D를 이용하여 구현되었다. 프로토타입을 이용한 시뮬레이션 결과, 에이전트의 이동은 매우 자연스럽게 나타났다. 그러나 에이전트 수를 증가시키는 경우에 성능이 심각하게 저하되었고, 이에 대한 대안들을 제시하였다.

• 한국ITS학회 논문지
• /
• 제23권1호
• /
• pp.26-41
• /
• 2024

안전한 도로교통 환경 조성을 위하여 운전행동에 영향을 미치는 인적요인에 관한 연구가 필요하지만, 실제 주행행태에 영향을 미치는 개인별 인적요인 특성을 도출하기에는 많은 어려움이 있다. 이에, 개별 운전자의 자기 보고를 통하여 도출되는 위험운전성향을 분석하여 주행 행태 특성과 상관성이 있는지 확인하고, 교통상황에 따른 주행행태에 영향을 미치는 운전성향을 추정하는 방법을 제시하고자 하였다. 본 연구에서는 기존에 고안된 설문 기법을 활용하여 실험 참가자들의 위험운전성향을 여러 방법으로 도출하고, 가상환경 기반의 주행 시뮬레이터 실험을 통하여 도출된 주행행태 특성을 분석하여 위험운전성향과 주행행태 특성 간 유의미한 상관관계가 있는지 확인하였다. 실험 결과, 한국형 DBQ를 통하여 도출되는 난폭운전성향이 높은 사람들이 상대적으로 빠른 주행속도와 가속도 행태를 보이는 것을 확인할 수 있었다. 이를 통하여 상대적으로 위험운전행동을 보이는 운전자를 추정할 수 있는 평가 방법을 확인할 수 있었다.

• 한국자동차공학회논문집
• /
• 제22권6호
• /
• pp.75-82
• /
• 2014

The purpose of this study is to identify the effects of sensation seeking and driving confidence level on reckless driving behavior in motor sports club's members. Data was collected from 265participants of the Trackday, driving school. Subjects answered the questionnaire using convenient sampling method. Data which is obtained through self-administration was analyzed by using the frequency analysis and multiple regression. Results are as follows. First sensation seeking has influenced on reckless driving behavior such as, drunken driving and errors. Second, driving confidence level has influenced on reckless driving behavior such as, drunken driving, overspeed driving and errors.

• 대한임베디드공학회논문지
• /
• 제13권3호
• /
• pp.161-167
• /
• 2018

The improvement of the social environment and the rapid development of medicine are making possible the age of 100. So a great number of countries including Korea are rapidly becoming the aged society or the super aged society. The elderly are accompanied by discomfort and disability. A variety of systems are developed and distributed to overcome them. The electric wheelchair is an electric motorized system for people who can not manipulate a manual wheelchair. In this paper, we propose an autonomous driving platform for an electric wheelchair. Here we use QR (Quick Response) code for self-localization. We also present real test results of the proposed system.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권2호
• /
• pp.119-126
• /
• 2022

This paper presents a method to reduce the vibration-induced noise effect of an inertial measurement device mounted on a self-driving vehicle. The inertial sensor used in the GNSS/INS integrated navigation system of a self-driving vehicle is fixed directly on the chassis of vehicle body so that its navigation output is affected by the vibration of the vehicle's engine, resulting in the degradation of the navigational performance. Therefore, these effects must be considered when mounting the inertial sensor. In order to solve this problem, this paper proposes to use an in-house manufactured vibration suppression device and analyzes its impact on reducing the vibration effect. Experimental test results in a static scenario show that the vibration-induced noise effect is more clearly observed in the lateral direction of the vehicle, but can be effectively suppressed by using the proposed vibration suppression device compared to the case without it. In addition, the dynamic positioning test scenario shows the position, speed, and posture errors are reduced to 74%, 67%, and 14% levels, respectively.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.402-404
• /
• 2022

Recent research has shown that deep learning models are vulnerable to adversarial attacks not only in the digital but also in the physical domain. This becomes very critical for applications that have a very high safety concern, such as self-driving cars. In this study, we propose a physical adversarial attack technique for one of the common tasks in self-driving cars, namely segmentation of the urban scene. Our method can create a texture on a wall so that it can be misclassified as a road. The demonstration of the technique on a state-of-the-art cityscape pretrained model shows a fairly high success rate, which should raise awareness of more potential attacks in self-driving cars.

• 한국산업안전학회:학술대회논문집
• /
• 한국안전학회 1998년도 춘계 학술논문발표회 논문집
• /
• pp.307-312
• /
• 1998

In forklift operations, awkward postures due to backward driving may put drivers to the risk of CTD or low back pain. In this research, 6 forklift drivers were surveyed with OWAS for objective posture evaluation and bodymaps for self-report evaluation. The backward driving happened more frequently than forward driving as expected, and, as work hours passed by, the drivers naturally tended to assume the easier work postures in inverse proportion to the frequency of the backward operations. According to the results of OWAS, 60 % of the work postures in the forklift operations belonged to the category II, III, and IV classified serious. Especially, in the backward driving, the postures with the neck twisted over $45^{\circ}$ occupied 82.4 %. In addition, discomfort on the neck, left shoulder, and low back was frequently reported in the self-reports.

• 대한안전경영과학회지
• /
• 제10권4호
• /
• pp.65-72
• /
• 2008

The Manchester Driver Behavior Questionnaire (DBQ) is the most commonly used frameworks for investigating the relationship between self-reported driving behavior and accident involvement. After Reason et al. introduced DBQ, there were many studies replicating the research of Reason et al. in many countries. There was, however, no study replication of the Reason's research in Korea. The aim of this study is to replicate the distinction among errors, lapses and violations, and to evaluate the relationship of these behaviors with road traffic accidents on Korean drivers. 223 Korean drivers completed the Korean version of original DBQ with questions regarding background information, such as age, gender, annual mileage and accident involvement. Participants answered self-assessment questions, also. Factor analysis revealed three factors like Reason et al. The three factors were dangerous errors, violations and relatively harmless errors.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.25-34
• /
• 2024

The paper investigates how the semiconductor and electric vehicle industries are addressing safety and security concerns in the era of autonomous driving, emphasizing the prioritization of safety over security for market competitiveness. Collaboration between these sectors is deemed essential for maintaining competitiveness and value. The research suggests solutions such as advanced autonomous driving technologies and enhanced battery safety measures, with the integration of AI chips playing a pivotal role. However, challenges persist, including the limitations of big data and potential errors in semiconductor-related issues. Legacy automotive manufacturers are transitioning towards software-driven cars, leveraging artificial intelligence to mitigate risks associated with safety and security. Conflicting safety expectations and security concerns can lead to accidents, underscoring the continuous need for safety improvements. We analyzed the expansion of electric vehicles as a means to enhance safety within a framework of converging security concerns, with AI chips being instrumental in this process. Ultimately, the paper advocates for informed safety and security decisions to drive technological advancements in electric vehicles, ensuring significant strides in safety innovation.

• 한국정보통신학회논문지
• /
• 제19권3호
• /
• pp.651-658
• /
• 2015

최근에 자율주행자동차에 대해 매우 활발한 연구와 개발이 진행되고 있다. 자율주행자동차를 구현하기 위해서는 매우 많은 기술들이 융복합적으로 해결되어야 한다. 이를 위해 차량에 장착된 블랙박스는 단순히 녹화기능 뿐만 아니라 신호등인식, 보행자검출, 정지선인식 등과 같이 자율주행차량을 구현하기 위한 핵심적인 기능을 제공할 수 있어 많은 연구 대상이 되고 있다. 따라서 자율주행차량을 구현하기 위한 한 가지 접근방법으로서 본 논문에서는 차량에 장착된 블랙박스 카메라를 이용하여 도로상에 위치한 거리를 효과적으로 예측할 수 있는 수식적인 모델을 제시한다. 제안한 모델은 도로의 기준선과 관찰선의 폭 또는 블랙박스 장착 높이 정보만을 이용함으로써 실제 도로상의 거리를 예측하는데 효과적으로 활용할 수 있음을 보인다. 다양한 실험을 통하여 본 논문에서 제안한 도로상의 거리 예측 모델이 타당함을 보인다.