• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.3
• /
• pp.85-93
• /
• 2016

According to Traffic Accident Statistics, the fatalities of accident while crossing is over represented. So, more active safety countermeasure should be considered to reduce the frequency and degree of severity of pedestrian-crossing involved accidents. The study analyses the safety effects of the Crossing Safety Assistant System which is composed of Led-embedded crosswalk lightings, text displayer and audio waning device for the safety consciousness both pedestrian and vehicles at crosswalk area. Operating speed of vehicles is reduced with statistical significance, and the level of vigilance expressed by pedestrian head movement to check out the vehicle existence is improved.

• Bulletin of the Korean Space Science Society
• /
• 2010.04a
• /
• pp.29.1-29.1
• /
• 2010

GPS(Global Positioning System)로 대표되는 위성항법시스템(GNSS: Global Navigation Satel lite System)은 우주공간의 위성을 이용하여 사용자에게 위치와 함께 시각 정보를 제공해 준다. 위성항법시스템은 항법 분야 뿐 아니라 측량, 측지를 비롯하여 정밀 시각동기 및 지각변동의 측정까지 다양한 분야에서 활용되고 있다. 항법분야에 있어서 위성항법시스템의 오차를 제거한 정밀한 위치 정보를 이용하여 이동체에 활용하는 연구가 활발히 진행되고 있다. 위성항법을 움직이는 이동체에 적용할 경우 주변 환경에 따라 위성항법 신호의 오차가 증가하여 급격한 위치 오차를 유발하므로 추가적인 센서 사용을 통하여 안전성을 향상시킬 필요가 있다. 이 논문에서는 위성항법 기반의 위치정보와 이동체에 부착되어 있는 센서 정보를 병렬적으로 사용하는 주행시스템을 구성하고 주행 시험을 수행하였다. 이동체에 부착되어 있는 센서 정보를 이용한 주행시스템의 경우 이동 거리를 측정할 수 있는 엔코더와 조향각을 측정할 수 있는 포텐셔미터 그리고 차량 모델을 이용하여 구성하였다. 시험 결과 위성항법기반의 위치 정보와 이동체의 센서 정보를 이용한 위치 오차의 차이는 0.4m 이내로 위성항법 신호에 급격한 오차가 들어오는 경우 이동체의 센서 정보를 이용하여 감지할 수 있음을 확인하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.2
• /
• pp.65-72
• /
• 2011

In this paper, a real-time monocular vision based navigation system is developed for the disabled people, where online background learning and vector field histogram are used for identifying obstacles and recognizing avoidable paths. The proposed system is performed by three steps: obstacle classification, occupancy grid map generation and VFH-based path recommendation. Firstly, the obstacles are discriminated from images by subtracting with background model which is learned in real time. Thereafter, based on the classification results, an occupancy map sized at $32{\times}24$ is produced, each cell of which represents its own risk by 10 gray levels. Finally, the polar histogram is drawn from the occupancy map, then the sectors corresponding to the valley are chosen as safe paths. To assess the effectiveness of the proposed system, it was tested with a variety of obstacles at indoors and outdoors, then it showed the a'ccuracy of 88%. Moreover, it showed the superior performance when comparing with sensor based navigation systems, which proved the feasibility of the proposed system in using assistive devices of disabled people.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.275-284
• /
• 2006

This paper deals with problems of safe and efficient navigation algorithm for autonomous mobile robots in unknown environments. Since the obstacle avoidance algorithms are very important in mobile robot navigation, two obstacle avoidance algorithms: VFH(vector field histogram) algorithm and a fuzzy algorithm are combined to have optimal performance in various environments. And a upper-level supervisor is to select the proper one from VFH algorithm and the fuzzy algorithm according to the situations the robot faces. Computer simulation results show the effectiveness of the proposed navigation algorithm for autonomous mobile robots.

• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.160-173
• /
• 2021

Recently, research on the development of autonomous vehicles has increased worldwide. Moreover, a means to identify and analyze the characteristics of traffic accidents of autonomous vehicles is needed. Accordingly, traffic accident data of autonomous vehicles are being collected in California, USA. This research examined the characteristics of traffic accidents of autonomous vehicles. Primarily, traffic accident data for autonomous vehicles were analyzed, and the text data used text-embedding techniques to derive major keywords and four topics. The methodology of this study is expected to be used in the analysis of traffic accidents in autonomous vehicles.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.368-376
• /
• 2021

With the recent development of deep learning technology, autonomous things technology is attracting attention, and DNNs are widely used in embedded systems such as drones and autonomous vehicles. Embedded systems that can perform large-scale operations and process multiple DNNs for high recognition accuracy without relying on the cloud are being released. DNNs with various levels of priority exist within these systems. DNNs related to the safety-critical applications of autonomous vehicles have the highest priority, and they must be handled first. In this paper, we propose a priority-based scheduling framework for DNNs when multiple DNNs are executed simultaneously. Even if a low-priority DNN is being executed first, a high-priority DNN can preempt it, guaranteeing the fast response characteristics of safety-critical applications of autonomous vehicles. As a result of checking through extensive experiments, the performance improved by up to 76.6% in the actual commercial board.

• Journal of Advanced Navigation Technology
• /
• v.14 no.5
• /
• pp.648-654
• /
• 2010

In this paper, a navigation system was designed, and performance tested in order to confirm the safety improvement of the GNSS(Global Navigation Satellite System)-based AGV(Autonomous Guided Vehicle) which used only position information on of GNSS. We developed DR(Dead Reckoning) navigation system that involve the use of GNSS abnormal positoning error detection and GNSS signal outage. The test results show that GNSS positioning error is detection can be archived with an error of more than 0.15m. In addition, the DR driving position error is 1.5m for an 8s GNSS positioning service outage.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.723-728
• /
• 2022

This study is a method for evaluating and quantifying driver's dangerous driving behavior. The quantification method calculates various driving information in real time after starting the vehicle operation such as the time that the vehicle has been continuously driven without a break, overspeed, rapid acceleration, and overspeed driving time. These quantified risk of driving behavior values can be individually provided as a safe driving index, or can be used to objectify the evaluation of a group of drivers on roads, or vehicle groups such as cargo/bus/passenger vehicles.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.51-63
• /
• 2022

Convoy driving is one of the technologies of multi-vehicle cooperation driving along with platoon driving. All over the world, research on vehicle control mechanisms to maintain vehicle formation during convoy driving convoy driving has been actively conducted and in Europe's Autonet 2030 project has developed and demonstrated convoy driving services for highways. But, even the concept of convoy driving is still insufficient in Korea. Therefore, in this study, the concept of convoy driving service was established and scenarios and communication messages for service application on urban roads were developed. And its effectiveness was verified through simulation analysis. As a result of comparing and analyzing individual vehicle cooperative driving and convoy driving for the blind spot support service and dilemma zone safety support service, which are representative V2I cooperative driving services on urban roads, the number of conflicts(indicator of traffic safety) and delays and stops(indicator of traffic efficiency) are significantly improved in convoy driving compared to individual vehicle cooperative driving.