• 한국ITS학회 논문지
• /
• 제17권2호
• /
• pp.142-151
• /
• 2018

제4차 산업혁명 시대가 도래하면서 전 세계적으로 자율주행자동차에 대한 연구개발이 활발히 진행되고 있다. 이러한 국제적인 기조 속에서 국토교통부는 2020년 SAE 기준 레벨 3이상의 자율주행자동차 상용화를 목표로 자율주행자동차 관련 연구개발을 적극적으로 추진하고 있다. 레벨 3 수준의 자율주행자동차에서는 운전자와 자동차 상호 간의 운행주체를 주고받는 제어권 전환이 필수적으로 발생하게 된다. 본격적인 자율주행자동차 시대에 앞서 본 연구에서는 우선적으로 고속도로를 대상으로 가상현실을 이용한 제어권 전환 안전성 평가를 위하여 대표 시나리오를 개발하였다. 이를 위해 자율주행자동차의 고속도로 주행 시나리오를 만들었고, 2014년 발생한 고속도로 교통사고 경위자료와 제어권 전환 특성을 고려하여 6개의 제어권 전환 시나리오를 개발하였다. 개발된 시나리오에서 고려된 변수는 운전자, 차량, 그리고 환경요인으로 크게 나눌 수 있으며, 총 36개의 변수가 포함되었다.

• 한국정밀공학회지
• /
• 제30권2호
• /
• pp.164-170
• /
• 2013

The latest vehicle yields a superior safety and reduction of driving burden by monitoring the driving state of vehicle and its environment with various sensors. To detect other vehicles and objects of the rear left and right-side blind spot area of driver, provide the information about a existence of objects inside the blind spot, and give a signal to avoid collision, this study proposes the intelligent outside rear-view mirror system. This study proposes SILS system with PreScan and Matlab/Simulink to verify practical applicability of developed BSDS. PreScan yields realistic driving environments and road conditions and vehicle model dynamics and collision warning is controlled by Matlab/Simulink.

• 한국ITS학회 논문지
• /
• 제17권2호
• /
• pp.98-112
• /
• 2018

공격운전은 상대방 운전자에 대한 공격 의지를 가지고 위협을 가하는 매우 위험한 운전행태이다. 기존 연구의 경우 공격운전자에 대한 주행특성 및 유발요인 등 공격운전자를 초점으로 한 연구가 대부분인 것으로 나타났다. 그러나 공격운전을 안전성 관점에서 분석하기 위해서는 공격운전 가해자와 피해자간의 상호작용에 대한 분석이 필요하다. 따라서 본 연구에서는 Multi-Agent 주행시뮬레이션 환경을 구축하여 공격운전 가해자와 공격운전 피해자간의 차량간격 및 상대속도를 통해 상호작용을 분석하였다. 공격운전 가해자와 피해자의 가감속 패턴을 파악하고 차간거리를 통해 TTC(Time-to-Coillison)를 도출하였다. 또한 도출된 TTC를 EDF(Exponential Decay Function)를 통해 사고발생가능성으로 전환하여 일반운전과 공격운전의 사고발생가능성을 분석하였다. 분석결과, 공격운전 시 일반운전에 비해 사고발생가능성이 높은 것으로 나타났다. 본 연구결과를 통해 공격운전의 위험성을 경고하며, 공격운전 관리방안 수립을 위한 기초연구로 활용될 수 있을 것으로 기대된다.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.217-223
• /
• 2015

Autonomous driving is no longer atechnology of the future since the development of autonomous vehicles has now been realized, and many technologies have already been developed for the convenience of drivers. For example, autonomous vehicles are one of the most important drive assistant systems. Among these many drive assistant systems, Cruise Control Systems are now a typical technology. This system constantly maintains a vehicle's speed and distance from a vehicle in front by using Radar or LiDAR sensors in real time. Cruise Control Systems do not only serve their original role, but also fulfill another role as a 'Driving Safety' measure as they can detect a situation that a driver did not predict and can intervene by assuming a vehicle's longitude control. However, these systems have the limitation of only focusing on driver safety. Therefore, in this paper, an Intelligent Cruise Control System that utilizes the path planning method and GIS is proposed to overcome some existing limitations.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.31-37
• /
• 2018

Recently, the safety in vehicle also has become a hot topic as self-driving car is developed. In passive safety systems such as airbags and seat belts, the system is being changed into an active system that actively grasps the status and behavior of the passengers including the driver to mitigate the risk. Furthermore, it is expected that it will be possible to provide customized services such as seat deformation, air conditioning operation and D.W.D (Distraction While Driving) warning suitable for the passenger by using occupant information. In this paper, we propose robust vehicle occupant detection algorithm based on RGB-Depth-Thermal camera for obtaining the passengers information. The RGB-Depth-Thermal camera sensor system was configured to be robust against various environment. Also, one of the deep learning algorithms, OpenPose, was used for occupant detection. This algorithm is advantageous not only for RGB image but also for thermal image even using existing learned model. The algorithm will be supplemented to acquire high level information such as passenger attitude detection and face recognition mentioned in the introduction and provide customized active convenience service.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.915-919
• /
• 2005

It is materialized an unmanned vehicle system as a part of Intelligent Transportation System (ITS) which is a fundamental constituent for unmanned vehicle. Remote control system, monitoring system and remote operating system which are consisted of unmanned vehicle system. Network program by TCP/IP socket, and real-time control & operating controlled by servo-motors from a remote place, those are used to verify safety and stability of the unmanned vehicle system in this research. This unmanned vehicle is divided into two major sections which are an unmanned vehicle part and control station part. The server PC is installed on the unmanned vehicle and a client PC is installed at a remote place, which can control the u manned vehicle. In this research work, main theme is that we experimented and tested to check the speed and utilization of the wireless LAN communication.

• 한국자동차공학회논문집
• /
• 제17권2호
• /
• pp.34-41
• /
• 2009

The latest vehicle yields a superior safety and reduction of driving burden by monitoring the driving state of vehicle and its environment with various sensors. To detect other vehicles and objects of the rear left and right-side blind spot area of driver, provide the information about a existence of objects inside the blind spot, and give a signal to avoid collision, this study proposes the intelligent outside rear-view mirror system. This task has substantially complicated several factors. For example, the size, geometry and features of the various vehicles which might enter the monitored zone is varied widely and therefore present various reflective characteristics. This study proposes the optimal specification and configuration of optical system and IR array sensor of blind spot detection system, and shows the results of the performance evaluation of developed system.

• Journal of Mechanical Science and Technology
• /
• 제20권1호
• /
• pp.29-41
• /
• 2006

Nowadays, with the advancement of computers, computer simulation linked with VR (Virtual Reality) technology has become a useful method for designing the automotive driving system. In this paper, the VR simulation system was developed to investigate the driving performances of the ASV (Advanced Safety Vehicle) equipped with an ACC (Adaptive Cruise Control) system. For this purpose, VR environment which generates visual and sound information of the vehicle, road, facilities, and terrain was organized for the realistic driving situation. Mathematical models of vehicle dynamic analysis, which includes the ACC algorithm, have been constructed for computer simulation. The ACC algorithm modulates the throttle and the brake functions of vehicles to regulate their speeds so that the vehicles can keep proper spacing. Also, the real-time simulation algorithm synchronizes vehicle dynamics simulation with VR rendering. With the developed VR simulation system, several scenarios are applied to evaluate the adaptive cruise controlled vehicle for various driving situations.

• 한국자동차공학회논문집
• /
• 제12권4호
• /
• pp.163-172
• /
• 2004

Nowadays, to analyze the dynamic characteristics of the automotive driving system, the computer simulation linked up with VR(Virtual Reality) technology is treated as the useful method with the improvement of computing ability. In this paper, the VR simulation system has been developed to investigate the driving characteristics of the ASV(Advanced Safety Vehicle) equipped with an ACC(Adaptive Cruise Control) system. For the purpose, VR environment which generates 3D graphic and sound information of the vehicle, the road, the facilities, and the terrain has been organized for the driving reality. Mathematical models of vehicle dynamic analysis including the ACC model have been constructed for computer simulation. The ACC modulates the throttle and brake functions to regulate the vehicle speed so that vehicles could keep proper spacing. Also, the real-time simulation algorithm synchronizes vehicle dynamic simulation with the graphic rendering. With the developed VR simulation system, simple scenarios are applied to analyze the dynamic characteristics. It is shown that the VR simulation system could be useful to evaluate the adaptive cruise controlled vehicle on various driving conditions.

• 자동차안전학회지
• /
• 제10권4호
• /
• pp.33-39
• /
• 2018

Recently, the automobile industry has developed ADAS (Advanced Driver Assistance System) to prevent traffic accidents and reduce driver's driving burden. Among the ADAS, the LKAS (Lane Keeping Assistance System) is a support system for the convenience and safety of the driver, and the main function is to maintain the driving lane of the vehicle. LKAS is a system that uses radar sensor and camera sensor to collect information about the position of the vehicle in the lane and to support keeping the lane through control if necessary. In many countries, LKAS has already been commercialized and the convenience and safety of drivers have been improved. The international LKAS evaluation test procedure is being developed and discussed by standardization committees such as the ISO (International Organization for Standardization) and the Euro NCAP (New Car Assessment Program). In Korean, the LKAS test method is specified in the KNCAP (Korean New Car Assessment Program), but the evaluation method is not defined. Therefore, the LKAS test procedure that meets international standards and is suitable for domestic road environment is necessary. In this paper, development of LKAS test evaluation scenarios that meets international standards and considering domestic road environment, and the formula that can evaluate the result value after control as the relative distance of lane and the front wheel are suggested. And a comparative analysis was conducted to verify the validity of the suggested scenario and formula. The test evaluation was conducted using the vehicle equipped with the LKAS.