• 대한임베디드공학회논문지
• /
• 제4권4호
• /
• pp.180-189
• /
• 2009

Currently, most automobile companies are interested in research on intelligent autonomous vehicle. They are mainly focused on driver's intelligent assistant and driver replacement. In order to develop an autonomous vehicle, lateral and longitudinal control is necessary. This paper presents a lateral and longitudinal control system for autonomous vehicle that has only mono-vision camera. For lane detection, we present a new lane detection algorithm using clothoid parabolic road model. The proposed algorithm in compared with three other methods such as virtual line method, gradient method and hough transform method, in terms of lane detection ratio. For adaptive control, we apply a vanishing point estimation to fuzzy control. In order to improve handling and stability of the vehicle, the modeling errors between steering angle and predicted vanishing point are controlled to be minimized. So, we established a fuzzy rule of membership functions of inputs (vanishing point and differential vanishing point) and output (steering angle). For simulation, we developed 1/8 size robot (equipped with mono-vision system) of the actual vehicle and tested it in the athletics track of 400 meter. Through the test, we prove that our proposed method outperforms 98 % in terms of detection rate in normal condition. Compared with virtual line method, gradient method and hough transform method, our method also has good performance in the case of clear, fog and rain weather.

• Journal of Advanced Research in Ocean Engineering
• /
• 제1권2호
• /
• pp.134-147
• /
• 2015

This study proposes a method to determine the effective angular velocity of each motor of a specific four-rows tracked vehicle (FRTV) in order to follow a given turning radius. The configuration of the four-rows tracked vehicle is introduced, and its dynamics analysis model is built using the DAFUL commercial software. The soil has been assumed to be hard ground, and the friction force between the ground and the tracked links is calculated using the Coulomb friction model. This paper uses a simulation to show that the error in the position increased with respect to the angle of the curvatures, so a method is proposed to compensate for the error in the motion of the motors. Various simulations are then carried out to verify the proposed formulation. The effects of the soil characteristics and the driving velocity will be further investigated in future studies.

• 자동차안전학회지
• /
• 제14권3호
• /
• pp.35-40
• /
• 2022

In this study, the driving performances of elderly who's age is over 65 were evaluated. The driving simulation was conducted using a compact driving simulation (CDS) and the simulation scenarios were developed from actual roads by replicating geometry of skewed intersection and traffic control devices located in Jungnang-gu, Seoul, Korea. 27 elderly drivers and 10 non-elderly drivers were recruited and participated on the virtual turning right and going straight driving experiment of CDS. Virtual driving data of driving time, speed, distance, acceleration and deceleration speeds, brake power, and steering wheel rotation angle were recorded and analyzed. Generally, elderly driver took more times to pass through the skewed intersection road and showed lower approaching speed as much as 40% and 25% in case of turning right and going straight scenarios respectively. The speed deviation at skewed intersection road between elderly and non-elderly driver is expected to cause frequent lane changes and overtaking.

• 한국컴퓨터그래픽스학회논문지
• /
• 제28권3호
• /
• pp.125-134
• /
• 2022

본 논문은 주로 사용되는 AR 콘텐츠의 증강 방법을 적용하기 어려운 차량 실내공간에서도 사용할 수 있는 차량용 AR매뉴얼을 구현하고, 실공간과 가상 객체의 증강 정합도 향상을 위해 딥러닝 모델을 적용하였다. 차량 핸들의 로고를 딥러닝 학습을 통해 위치와 각도, 기울기 등과 관계없이 인식하고, 이를 중심으로 3차원 실내 공간좌표를 생성하여 실제 차량 부품 위에 정확히 가상버튼을 증강한다. 여기에 동일 학습모델을 기반으로 차량의 주요 경고등 심볼을 인식할 수 있는 기능을 함께 구현하여 차량용 AR매뉴얼로서의 기능성과 활용성을 높인다.