• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.91-102
• /
• 2019

Autonomous vehicles can be exposed to severe danger when failure occurs in any of its components. For this reason many countries are making efforts on the legislative issue how to objectively evaluate failure safety of an autonomous vehicle when such a vehicle is commercially available to a customer in the near future. In level-3 automation, a driver must take over the control of his vehicle when failure occurs, and the driver's controllability must be secured for escape from the imminent danger. In this paper, quantitative methods have been developed for evaluating failure safety of the level-3 autonomous vehicle, and they were validated by simulation. And also, we confirmed that the proposed evaluation method can quantitatively evaluate the failure safety.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.198-208
• /
• 2022

In this paper, an autonomous driving system is implemented for the Segye AI Robot Race Competition that multiple vehicles drive simultaneously. By utilizing the ERP42-racing platform, RTK-GPS, and LiDAR sensors provided in the competition, we propose an autonomous driving system that can drive safely and quickly in a road environment with multiple vehicles. This system consists of a recognition, judgement, and control parts. In the recognition stage, vehicle localization and obstacle detection through waypoint-based LiDAR ROI were performed. In the judgement stage, target velocity setting and obstacle avoidance judgement are determined in consideration of the straight/curved section and the distance between the vehicle and the neighboring vehicle. In the control stage, adaptive cruise longitudinal velocity control based on safe distance and lateral velocity control based on pure-pursuit are performed. To overcome the limited experimental environment, simulation and partial actual experiments were conducted together to develop and verify the proposed algorithms. After that, we participated in the Segye AI Robot Race Competition and performed autonomous driving racing with verified algorithms.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.175-189
• /
• 2023

Fault detection and diagnosis (FDI) algorithms are actively being researched for ensuring the integrity and reliability of environment perception sensors in autonomous vehicles. In this paper, a fault detection algorithm based on a multi-sensor perception system composed of radar, camera, and lidar is proposed to guarantee the safety of an autonomous vehicle's perception system. The algorithm utilizes reference generation filters and residual generation filters based on finite impulse response (FIR) filter estimates. By analyzing the residuals generated from the filtered sensor observations and the estimated state errors of individual objects, the algorithm detects faults in the environment perception sensors. The proposed algorithm was evaluated by comparing its performance with a Kalman filter-based algorithm through numerical simulations in a virtual environment. This research could help to ensure the safety and reliability of autonomous vehicles and to enhance the integrity of their environment perception sensors.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.450-455
• /
• 2021

In this paper, we introduce the contents of research on the establishment of an evaluation environment for autonomous cooperative driving platform for commercial vehicles based on V2X communication. For the evaluation of the autonomous cooperative driving platform based on V2X communication, various standards, standards, and guidelines for test evaluation should be developed and provided to the test subject, along with the establishment of test beds such as roads and V2X infrastructure that can apply various driving scenarios. do. In addition, based on this, various reference equipment and test equipment for actual test and evaluation should be developed. In this paper, various technologies, standards, equipment, and construction infrastructure developed to construct the evaluation environment for autonomous cooperative driving platform for commercial vehicles based on V2X communication are introduced.

• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.303-312
• /
• 2000

In this paper, we describe an image processing algorithm which is able to recognize the road lane. This algorithm performs to recognize the interrelation between AGV and the other vehicle. We experimented on AGV driving test with color CCD camera which is setup on the top of vehicle and acquires the digital signal. This paper is composed of two parts. One is image preprocessing part to measure the condition of the condition of the lane and vehicle. This finds the information of lines using RGB ratio cutting algorithm, the edge detection and Hough transform. The other obtains the situation of other vehicles using the image processing and viewport. At first, 2 dimension image information derived from vision sensor is interpreted to the 3 dimension information by the angle and position of the CCD camera. Through these processes, if vehicle knows the driving conditions which are lane angle, distance error and real position of other vehicles, we should calculate the reference steering angle.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.4 no.6
• /
• pp.175-186
• /
• 1996

In Advanced Vehicle Control System(AVCS), Autonomous Intelligent Cruise Control(AICC) is generally understood to be a system that can be achieved in the near future without the demanding infrastructure components and technoloties. AICC is an automatic vehicle following system with no human engagement in the longitudinal vehicle direction. This paper presents a fuzzy control algorithm to develop the AICC system. The control performance was studied information of vehicles using computer simulations. The most improtant aspects of the work reported here are the adoption of the fuzzy adaptive control law, and the use of filtering concept to reduce the slinky effects that may appear in a formation of vehicles equipped with AICC systems. The simulation results demonstrate the effectiveness of the fuzzy adaptive AICC system and its beneficial effects on traffic flow.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1944-1945
• /
• 2011

본 논문은 심도각 범위를 고려한 무인 잠수정(autonomous underwater vehicles: AUVs)의 타카키-수게노 (Takagi-Sugeno: T-S) 퍼지 모델 기반 강인 심도 제어기의 설계 기법을 제안한다. 무인 잠수정의 비선형 시스템은 Sector nonlinearity 기법을 이용하여 T-S 퍼지 시스템으로 모델링된다. 리아푸노프(Lyapunov) 함수를 이용하여 무인 잠수정의 성능을 보장하는 선형 행렬 부등식(Linear matrix inequality: LMI) 형태의 강인 제어기 설계 조건은 유도된다. 또한 무인 잠수정의 심도각 범위를 고려하여 입력 및 출력에 제한 조건을 포함한다. 모의 실험을 통해 제안된 기법의 심도 제어 성능을 검증한다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1946-1947
• /
• 2011

본 논문은 파라미터의 불확실성을 포함한 비선형 무인 잠수정(autonomous underwater vehicles: AUVs)의 속도 제어를 위한 강인 퍼지 제어기를 제안한다. 효율적이고 안정적인 접근을 위해 불확실성을 포함한 비선형 무인 잠수정의 속도 시스템은 타카기-수게노(Takagi-Sugeno: T-S) 퍼지 모델로 표현된다. 리아푸노프(Lyapunov) 안정도 이론을 이용하여, 무인 잠수정의 제어 성능을 보장하는 선형 행렬 부등식(linear matrix inequality: LMI) 형태의 제어기 설계 조건을 유도한다. 제안된 강인 속도 제어기 성능의 유효성을 검증하기 위해 모의실험을 수행한다.

• Ocean Systems Engineering
• /
• v.1 no.4
• /
• pp.297-315
• /
• 2011

New applications of streamlined Autonomous Underwater Vehicles require an AUV capable of completing missions with both high-speed straight-line runs and slow maneuvers or station keeping tasks. At low, or zero, forward speeds, the AUV's control surfaces become ineffective. To improve an AUV's low speed maneuverability, while maintaining a low drag profile, through-body tunnel thrusters have become a popular addition to modern AUV systems. The effect of forward vehicle motion and sideslip on these types of thrusters is not well understood. In order to characterize these effects and to adapt existing tunnel thruster models to include them, an experimental system was constructed. This system includes a transverse tunnel thruster mounted in a streamlined AUV. A 6-axis load cell mounted internally was used to measure the thrust directly. The AUV was mounted in Memorial University of Newfoundland's tow tank, and several tests were run to characterize the effect of vehicle motion on the transient and steady state thruster performance. Finally, a thruster model was modified to include these effects.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.213-218
• /
• 2009

This paper describes a classical algorithm carrying out dynamic 3D obstacle recognition for autonomous underwater vehicles (AUVs), Support Vector Machines (SVMs). SVM is an efficient algorithm that was developed for recognizing 3D object in recent years. A recognition system is designed using Support Vector Machines for applying the capabilities on appearance-based 3D obstacle recognition. All of the test data are taken from OpenGL Simulation. The OpenGL which draws dynamic obstacles environment is used to carry out the experiment for the situation of three-dimension. In order to verify the performance of proposed SVMs, it compares with Back-Propagation algorithm through OpenGL simulation in view of the obstacle recognition accuracy and the time efficiency.