• 인터넷정보학회논문지
• /
• 제25권2호
• /
• pp.21-28
• /
• 2024

레이다는 자율주행 차에 있어 필수적인 센서 부품으로, 레이다가 활용되는 시장은 점차 커지고 있으며 제품 종류도 다양해지고 있다. 본 연구에서는 평가 공정에서부터 레이다의 불량 여부를 예측해 자율주행의 안정성과 효율성을 높일 수 있도록 성능 예측 모델을 구축하고 평가하였다. 레이더 공정 과정의 39607개 입력 데이터로 모델을 학습하였으며, 결과적으로 17개 모델을 스태킹 앙상블했을 때 Meta Ridge 모델이 가장 높은 학습률을 나타내는 것을 확인하였다. 이러한 연구 결과가 제품의 불량을 공정 단계에서 우선 예측해 수율을 극대화하고 불량으로 인한 제품 폐기 비용을 감축하는 데 도움이 될 것으로 기대 한다.

• 제어로봇시스템학회논문지
• /
• 제22권8호
• /
• pp.633-642
• /
• 2016

It is important for advanced active safety systems and autonomous driving cars to get the accurate estimates of the nearby vehicles in order to increase their safety and performance. This paper proposes a sensor fusion method for radar and vision sensors to accurately estimate the state of the preceding vehicles. In particular, we performed a study on compensating for the lateral state error on automotive radar sensors by using a vision sensor. The proposed method is based on the Interactive Multiple Model(IMM) algorithm, which stochastically integrates the multiple Kalman Filters with the multiple models depending on lateral-compensation mode and radar-single sensor mode. In addition, a Probabilistic Data Association Filter(PDAF) is utilized as a data association method to improve the reliability of the estimates under a cluttered radar environment. A two-step correction method is used in the Kalman filter, which efficiently associates both the radar and vision measurements into single state estimates. Finally, the proposed method is validated through off-line simulations using measurements obtained from a field test in an actual road environment.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1505-1515
• /
• 2016

The age of autonomous vehicles has come according to development of high performance sensing and artificial intelligence technologies. And importance of the vehicle's surrounding environment sensing and observation is increasing accordingly because of its stability and control efficiency. In this paper we propose an integrated platform for efficient networking, analysis and monitoring of multiple sensing data on the vehicle that are equiped with various automotive sensors such as GPS, weather radar, automotive radar, temperature and humidity sensors. From simulation results, we could see that the proposed platform could perform realtime analysis and monitoring of various sensing data that were observed from the vehicle sensors. And we expect that our system can support drivers or autonomous vehicles to recognize optimally various sudden or danger driving environments on the road.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1430-1437
• /
• 2019

In this paper, we proposed a methodology for estimating rainfall intensity using a W-band FMCW automotive radar signal which is the core technology of autonomous driving car. By comparing and analyzing the results of rainfall and non-rainfall observation, we found that the reflection intensity of the automotive radar is changed with rainfall intensity. We could confirm the possibility of deriving the quantitative precipitation estimation using the methodology derived from this result. In addition it can be possible to develop a new paradigm of precipitation observation technique by observing various events together with the weather radar and the ground rainfall observation equipment.

• International journal of advanced smart convergence
• /
• 제11권2호
• /
• pp.7-12
• /
• 2022

Safety and security are the topmost priority in every environment. With the aid of Artificial Intelligence (AI), many objects are becoming more intelligent, conscious, and curious of their surroundings. The recent scientific breakthroughs in autonomous vehicular designs and development; powered by AI, network of sensors and the rapid increase of Internet of Things (IoTs) could be utilized in maintaining safety and security in our environments. AI based on deep learning architectures and models, such as Deep Neural Networks (DNNs), is being applied worldwide in the automotive design fields like computer vision, natural language processing, sensor fusion, object recognition and autonomous driving projects. These features are well known for their identification, detective and tracking abilities. With the embedment of sensors, cameras, GPS, RADAR, LIDAR, and on-board computers in many of these autonomous vehicles being developed, these vehicles can properly map their positions and proximity to everything around them. In this paper, we explored in detail several ways in which these enormous features embedded in these autonomous vehicles, such as the network of sensors fusion, computer vision and natural image processing, natural language processing, and activity aware capabilities of these automobiles, could be tapped and utilized in safeguarding our lives and environment.

• 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.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• 한국초전도ㆍ저온공학회논문지
• /
• 제23권4호
• /
• pp.56-60
• /
• 2021

The microwave Radar used for special purposes in the past is being applied in various areas due to the technological advancement and cost reduction, and is particularly applied to autonomous driving in the automobile field. The FMCW (Frequency Modulated Continuous Wave) Radar can acquire level information of liquid in vessel based on the beat frequency obtained by continuously transmitting and receiving signals by modulating the frequency over time. However, for cryogenic fluids with small impedance differences between liquid medium and gas medium, such as liquid nitrogen and liquid hydrogen, it is difficult to apply a typical Radar-based level meter. In this study, we develop an 80 GHz FMCW Radar for level measurement of cryogenic fluids with small impedance differences between media and analyze its characteristics. Here, because of the low intrinsic impedance difference, most of the transmitted signal passes through the liquid nitrogen interface and is reflected at the bottom of the vessel. To solve this problem, a radar measurement algorithm was designed to detect multiple targets and separate the distance signal to the bottom of the vessel in order to estimate the precise position on the liquid nitrogen interface. Thereafter, performance verification experiments were performed according to the liquid nitrogen level using the developed radar level meter.

• 한국지리정보학회지
• /
• 제23권3호
• /
• pp.132-145
• /
• 2020

4차 산업혁명의 도래로 정밀도로지도는 미래형자동차, 물류, 로봇 등의 분야에서 자율주행의 위치결정을 위한 핵심 인프라로 자리잡고 있다. 특히, 자율주행자동차는 자기위치 결정뿐만 아니라 LiDAR, GNSS, Radar, 스테레오카메라 등 다양한 센서에서 감지하는 대상체의 정확한 위치결정을 위하여 정밀도로지도의 의존도가 더욱 증대되고 있는 실정이다. 현재 자율주행 및 C-ITS 기술이 현실화됨에 따라 정밀도로지도의 정밀한 위치정보에 대한 요구가 증가하고 있으며, 각종 변화정보의 감지 및 실시간 정보 융합에 따른 새로운 정밀지도 생성 기술 요구도 함께 증가하고 있다. 따라서 본 연구에서는 정밀도로지도와 관련된 국내·외 표준 및 관련된 제반 환경의 동향을 분석하고, 이를 기반으로 현재 정밀도로지도를 구축하는 기관별로 표준 정밀도로지도와 비교하여 활용성을 연구하였다. 또한 추가적으로 표준 정밀도로지도에 대하여 실제 자율주행자동차에 적용하기 위한 정밀도로지도를 재가공하여 활용성을 연구하였다. 연구 결과 표준 정밀도로지도는 항법레이어 구축과 교통안전시설의 재가공이 필요하나 다양한 기관이 유용하게 활용할 수 있도록 구축되어 있음을 확인하였다. 향후 본 연구에서 제시한 결과를 기반으로 자율주행 협력모델에서 기관별 레이어 분류와 정의 등에 대하여 추가적인 연구가 진행된다면 보다 효율적인 정밀도로지도 및 도로 주변 공간정보가 구축 및 갱신이 이루어질 것으로 기대된다.

• 전기전자학회논문지
• /
• 제24권1호
• /
• pp.232-237
• /
• 2020

본 논문에서는 자율주행 자동차에 물체를 인식하고 거리를 측정하는데 효율적인 센서 융합을 제안한다. 자율주행 자동차에 사용되는 대표적인 센서는 레이더, 라이다, 카메라이다. 이 중 라이다 센서는 차량 주변의 맵을 만드는 역할을 한다. 하지만 날씨 조건에 성능이 하락하고 센서의 가격이 매우 비싸다는 단점 있다. 본 논문에서는 이러한 단점을 보완하고자 비교적 저렴하고 눈, 비, 안개에 지장 없는 레이더 센서로 거리를 측정하며 차량 주변을 관찰한다. 물체 인식률이 뛰어난 카메라 센서를 융합하여 물체 인식 및 거리를 측정한다. 융합된 영상은 IP서버를 통해 실시간으로 스마트폰에 전송되어 현재 차량의 상황을 내부, 외부에서 판단하는 자율주행 보조 시스템에 사용될 수 있다.