• International Journal of Automotive Technology
• /
• 제7권2호
• /
• pp.227-235
• /
• 2006

In this paper a robust image processing method with modified Otsu algorithm to recognize the road lane for a real-time controlled autonomous vehicle is presented. The main objective of a proposed method is to drive an autonomous vehicle safely irrespective of road image qualities. For the steering of real-time controlled autonomous vehicle, a detection area is predefined by lane segment, with previously obtained frame data, and the edges are detected on the basis of a lane width. For stable as well as psudo-robust autonomous driving with "good", "shady" or even "bad" road profiles, the variable threshold with modified Otsu algorithm in the image histogram, is utilized to obtain a binary image from each frame. Also Hough transform is utilized to extract the lane segment. Whether the image is "good", "shady" or "bad", always robust and reliable edges are obtained from the algorithms applied in this paper in a real-time basis. For verifying the adaptability of the proposed algorithm, a miniature vehicle with a camera is constructed and tested with various road conditions. Also, various highway road images are analyzed with proposed algorithm to prove its usefulness.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1109-1114
• /
• 2007

This paper presents the road simulator control technology for reproducing the road input signal to implement the real road data. The simulator consists of the hydraulic pump, servo valve, hydraulic actuator and its control equipment. The QFT is utilized to control the simulator effectively. The control system illustrates a tracking performance of the closed-loop controller with low order transfer function G(s) and pre-filter F(s) for a parametric uncertain model. A force controller is designed to communicate the control signal between simulator and digital controller. The efficacy of the QFT force controller is verified through the numerical simulation, in which combined dynamics and actuation of the hydraulic servo system are tested. The simulation results show that the proposed control technique works well under uncertain hydraulic plant system. The conventional software (Labview) is used to make up for the real controller in the real-time basis, and the experimental works show that the proposed algorithm works well for a single road simulator.

• 대한기계학회논문집A
• /
• 제31권11호
• /
• pp.1069-1076
• /
• 2007

This paper presents the road simulator control technology for reproducing the road input signal to implement the real road data. The simulator consists of the hydraulic pump, servo valve, hydraulic actuator and its control equipment. The QFT(Quantitative Feedback Theory) is utilized to control the simulator effectively. The control system illustrates a tracking performance of the closed-loop controller with low order transfer function G(s) and pre-filter F(s) for a parametric uncertain model. A force controller is designed to communicate the control signal between simulator and digital controller. Tracking specification is satisfied with upper and lower bound tolerances on the steep response of the system to the reference signal. The efficacy of the QFT force controller is verified through the numerical simulation, in which combined dynamics and actuation of the hydraulic servo system are tested. The simulation results show that the proposed control technique works well under uncertain hydraulic plant system. The conventional software (Labview) is used to make up for the real controller in the real-time basis, and the experimental works show that the proposed algorithm works well for a single road simulator.

• 한국인공지능학회지
• /
• 제11권4호
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• 한국소음진동공학회논문집
• /
• 제16권8호
• /
• pp.806-813
• /
• 2006

An important factor of vibration test using MAST(multi axial simulation table) system is the reliance of input excitation source. Generally the generation of input excitation source is obtained by the measured data on special road in proving ground. The measured data on special road have more exciting energy than the data of real fields, therefore the time and expense for test can be reduced. But the magnitude of input excitation source must be defined by comparison with the excited energy on real field. The object of this paper makes the data base of domestic roads for the definition of input excitation source which is obtained by the measured data on special road in proving ground. These real field data on domestic roads are analyzed by the power spectral density and interrelationship index.

• 대한토목학회논문집
• /
• 제32권4D호
• /
• pp.291-303
• /
• 2012

보다 안전한 운전을 유도하기 위해서는 불특정 운전자에게 획일적이고 정적인 감속정보를 제공하기보다는 개별차량 움직임을 고려하여 해당 도로를 이용하는 운전자가 어떻게 행동해야 하는지에 대해 개별 운전자 중심의 동적이고 구체적인 정보를 제공하여야 한다. 본 연구에서는 실시간으로 차량 및 도로교통상황에 대한 정보의 수집 및 전송이 가능한 스마트하이웨이의 도로 및 통신환경이 조성되었을 때를 가정하여, 노면상태 및 주행상태 등의 도로교통상황, 선 후행차량의 통행속도 및 차간거리를 고려하여 실시간으로 차량 안전거리 정보 제공을 목적으로 하였다. 노면상태에 따라 상태기준컬럼($C_{condition}$)의 값을 달리 정의하여 기본적인 위험상황정보를 제시하고자 하였으며, 이를 기준으로 표현컬럼($C_n$)의 범위에 선 후행차량의 통행속도, 차량간격, 종단경사, 노면상태 등을 종합적으로 반영하여 실시간 안전거리 지수(RSDI)를 산출하도록 하였다. 산출된 실시간 안전거리 지수(RSDI)를 운전자에게 제공함으로서, 운전자가 차량간 충돌(추돌) 가능 위험상황에 대해 직관적으로 인지하고 충분히 대응할 수 있도록 하여 안전을 도모하도록 하였다. 산출된 RSDI의 값은 30개의 단위컬럼으로 이루어지고, 사전에 정한 '경고', '위험, '보통'의 3단계 위험도 평가 등급으로 구분되어 운전자에게 제공되게 된다.

• 한국대기환경학회지
• /
• 제31권6호
• /
• pp.562-572
• /
• 2015

$NO_x$ emissions from diesel vehicles have been regarded as a main cause of high $NO_2$ concentration in metropolitan area. Recent studies have shown that the on-road $NO_x$ emissions of diesel vehicles are quite higher than the emission limits specified with the pre-defined test method for emission certification. To reduce air pollutants effectively, the discrepancy of emissions in certification and real-driving conditions should be tackled. In this study, the real-driving emissions have been estimated with portable emission measurement system (PEMS). The results of this study have shown that the on-road $NO_x$ emissions from diesel vehicles have been decreased as the introduction of stricter emission regulation, EURO-6, but additional reduction should be still required and robust technologies should be applied to control $NO_x$ in real-driving conditions. RDE-LDV (Real Driving Emission - Light Duty Vehicles) test method being developed in the European Union can represent excessive on-road $NO_x$ emissions of diesel vehicles as applied emission technologies and can be a solution to remove discrepant $NO_x$ emissions between certification and Korean real-driving conditions. Among the $NO_x$ reduction technologies for EURO-6 diesel vehicles, selective catalytic reduction (SCR) system has shown the better performance than lean $NO_x$ trap (LNT) system to control on-road $NO_x$ emissions. Implementing RDE-LDV will require vehicle manufacturers to adopt the more effective $NO_x$ reduction technology in real driving conditions.

• 한국대기환경학회지
• /
• 제28권1호
• /
• pp.94-104
• /
• 2012

The purpose of this research is to quantify the compliance of on-road emission from a light duty diesel vehicle, based on a comparison to emission regulation standard. $NO_x$, CO and THC emissions were measured using a portable device on a selected real-world driving route with a length of approximately 22 km. On-road measurements were repeated by 10 times on a same route to reflect variability in traffic conditions. A test route was divided into 22 road links with length of 1 km to analyze emission results with higher spatial resolution. The average emissions of $NO_x$, CO and THC over total travel distance, which is approximately 220 km, were quantified to be in compliance with emission regulation standards. Under higher spatial resolution, $NO_x$ concentration exceeded a standard in 92 links out of 220 links. The extended time in stop period and the stop-and-go driving cycle were identified as two important reasons for increased $NO_x$ emissions in observed cases. Heavy traffics showed higher $NO_x$ emissions than free flow. These results indicate that the real-world vehicle emissions might exceed the compliance level associate with traffic conditions. Another interesting observation of this research is that the on-road emission characteristics can be independent to the average speed of road links with higher spatial resolution. Variability in on-road emission might not be fully described by solely relying on an average speed, because variability in traffic conditions and road conditions can influence on real-world vehicle emissions.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 춘계학술대회논문집
• /
• pp.326-331
• /
• 2006

The durability of recent motors is longer than the past one because there are the rapid technique development of the automobile industry and the vehicle maintenance of users. And then the importance of the durability test due to vibration is increased from day to day. So full vehicle and parts companies accomplish the durability test using various methods. The most public test method among them is the reliable field test but it bring on higher cost and period of the development process. The durability test using MAST(multi axis simulation table) is a solution in order to improve the development process of automobiles. Generally its excitation source uses the optimized road profiles that are obtained by the road test of belgian road, country road, cobbleston road and so on instead of a real field but the interrelations and influences accordingly vehicle damage are considered by a field test between specific roads and real fields in the first place. Therefore this study, in order to accomplish a basic research for the durability test using the MAST, performed on the real field driving test at various domestic roads and the results which are analyzed by PSD(power spectrum density) are compared with relative sensitivity among the roads. Consequently they can present a basic material for generation of road profiles which is applied to the durability test using MAST.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.773-778
• /
• 1991

In this paper we describe a road following method for an autonomous vehicle. From a road image in gray level, a road boundary is detected using a gradient operator, and then the road boundary is converted to orthogonal view of the road showing the vehicle position and heading direction. In this research an efficient road boundary search technique is developed to support real time vehicle control. Also, an obstacle detection method, using images taken from two different positions, has been developed.