• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 추계학술대회
• /
• pp.961-964
• /
• 2016

본 논문은 쏘나 영상 촬영을 위한 무인자율항법(AUSV Autonomous Unmanned Surface Vehicle) 시스템 개발에 관한 연구이다. 자율항법 시스템은 선체에 모션센서, DGPS에 의한 현재 경위도 좌표와 목표지 경위도 좌표의 차를 가지고 선체의 추진체(Thrusters)를 FF-PID 알고리즘으로 제어한다. 실험결과, 목적지 좌표에 대한 제어좌표 오차는 전체 항법거리 1km 에서 6 meter 이하이며, 자율항법 모드에서의 Sonar Image 촬영 결과물은 유인선 촬영 결과물과의 차이는 12 pixel 이하로 전체 영상 차이는 거의 식별할 수 없이 동일하다. 개발된 시스템은 유인선으로 촬영 불가능한 해저 지형에 대한 Sonar Image 촬영을 위한 새로운 방법으로 활용 가능하다.

• 한국산업융합학회 논문집
• /
• 제23권6_2호
• /
• pp.979-987
• /
• 2020

This study used the Deep Learning models used in previous studies, we selected the basic model. The selected model was selected as ZFNet among ZFNet, Googlenet and ResNet, and the object was detected using a ZFNet based FRCNN. In order to reduce the detection error rate of FRCNN, location of four types of objects detected inside the image was designed by SVM classifier and location-based filtering was applied. As simulation results, it showed similar performance to the lane marking classification method with conventional 경계 detection, with an average accuracy of about 88.8%. In addition, studies using the Linear-parabolic Model showed a processing speed of 165.65ms with a minimum resolution of 600 × 800, but in this study, the resolution was treated at about 33ms with an input resolution image of 1280 × 960, so it was possible to classify lane marking at a faster rate than the previous study by CNN-based End to End method.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권4호
• /
• pp.243-251
• /
• 2021

Real-Time Kinematic (RTK) is a phase-based differential GNSS technique and uses additional observations from permanent reference stations to mitigate or eliminate effects like atmospheric delays or satellite clocks and orbit errors. In particular, as the position accuracy required in the fields of autonomous vehicles and drones is gradually increasing, the demand for RTK-based precise navigation that can provide cm-level position is increasing. Recently, with the rapid growth of the open-source software market, the use of open-source software for building navigation system of unmanned vehicles, which is difficult to mount an expensive GNSS receivers, is gradually increasing. RTKLIB is an open-source software package that can perform RTK positioning and is widely used for research and education purposes. However, since the performance and stability of RTK algorithm of RTKLIB is inevitably inferior to that of commercial GNSS receivers, users need to verify whether RTKLIB can satisfy the navigation performance requirements of unmanned vehicles. Therefore, in this paper, the performance evaluation of the RTK positioning algorithm of RTKLIB was performed using GNSS observation data acquired in a dynamic environment. Therefore, in this paper, the RTK positioning performance of RTKLIB was evaluated using GNSS observation data acquired in a dynamic environment. Our results show that the current RTK algorithm of RTKLIB is not suitable for precise navigation of unmanned vehicles.

• 드라이브 ㆍ 컨트롤
• /
• 제19권3호
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

• 대한조선학회논문집
• /
• 제59권4호
• /
• pp.225-234
• /
• 2022

The flow field measurement above whole area of the flight deck on 'Landing Platform Helicopter (LPH)' was performed by using PIV system in wind tunnel. In various heading angle conditions (0deg, -30deg, -45deg, -60deg, -75deg and ±90deg), the velocity fields such as U velocity & V velocity were measured at three different height above flight deck. Due to the geometrical characteristics of several bodies like deck, crane and super-structure, various vortex were generated. When the heading angle is 0deg, the deck edge vortex by flight deck and massive separation by super-structure were clearly observed by visualization with smoke and PIV, respectively. In other heading angles, the acceleration of flow in space between crane and super-structure were detected. And area with flow separation by super-structure is directly related to the heading angle of vessel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• 한국IT서비스학회지
• /
• 제22권2호
• /
• pp.57-70
• /
• 2023

In order to establish an autonomous driving environment, it is necessary to study traffic safety and demand prediction by analyzing information generated from the transportation infrastructure beyond relying on sensors by the vehicle itself. In this paper, we propose a real-time traffic information generation method using sensor convergence technology of transportation infrastructure. The proposed method uses sensors such as cameras and radars installed in the transportation infrastructure to generate information such as crosswalk pedestrian presence or absence, crosswalk pause judgment, distance to stop line, queue, head distance, and car distance according to each characteristic. create information An experiment was conducted by comparing the proposed method with the drone measurement result by establishing a demonstration environment. As a result of the experiment, it was confirmed that it was possible to recognize pedestrians at crosswalks and the judgment of a pause in front of a crosswalk, and most data such as distance to the stop line and queues showed more than 95% accuracy, so it was judged to be usable.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2022년도 추계학술대회
• /
• pp.188-188
• /
• 2022

선박의 운용 효율을 높일 수 있는 방법인 무인 운용체계는 근래에 많은 관심을 받고 연구되어 왔다. 특히 무인수상선과 무인수중체의(USV-AUV)의 복합 운용 분야는 그 동안 어려움이 있었던 심해저 탐사 및 특수 임무 활용에 용이하여 많은 연구가 수행되고 있다. 본 연구에서는 쌍동선 형태인 무인수상선이 모선이 되고 무인수중체가 결합하여 충전하고 다시 진수하여 원거리 및 심해저 조건에서 무인수중체가 운용 가능하도록 하는 시스템의 일부인 USV-AUV의 docking을 위한 DP 시스템을 개발하고 선박해양플랜트연구소 해양공학수조에서 모형시험을 통해 이를 검증하였다. 또한, 실제 제작된 무인쌍동선과 추진 시스템을 활용하여 모형시험을 통해 검증한 DP 알고리즘을 적용하여 화성 제부도 앞바다에서 실선 DP 테스트를 수행하였다. 실 해역에서의 DP 시스템 테스트는 정확한 환경 조건의 계측 및 구현이 어려워 모형시험과 같은 정량적인 평가는 어렵지만, 정성적으로 DP 시스템이 작동하는 것을 확인할 수 있었다.

• 로봇학회논문지
• /
• 제18권4호
• /
• pp.472-480
• /
• 2023

This paper describes the development of a test-equipment for the pre-verification of navigation performance in cluster-based AUVs (Autonomous Underwater Vehicle). In the development of an AUV, conducting hardware and software development sequentially is not efficient due to the limited research and development period. Therefore, in order to reduce the overall development time and achieve successful development results, it is essential to pre-validate the navigation system and navigation algorithms. Accordingly, this paper explains the test-equipment for pre-verification of navigation performance, and ultimately confirms the stability of the navigation system and the performance of the navigation algorithms through the analysis of five types of navigation sensor data stored during real-sea experiments. The results demonstrate that through the development and verification of the test-equipment, it is possible to shorten the overall development period and improvement of product quality in the process of developing multiple AUVs.

• 한국항행학회논문지
• /
• 제27권6호
• /
• pp.861-864
• /
• 2023

Recently, V2X (vehicle-to-everyting) communication has established itself as an essential technology for cooperative autonomous driving. V2X communication currently includes DSRC (dedicated short range communication) communication technology, which is a WLAN (wireless local area network) based communication technology, and C-V2X (cellular-V2X) communication technology, which is a Cellular-based communication technology. Since these two communication methods are not compatible with each other, various studies and experiments are being conducted to select one of the two communication methods. In the case of C-V2X communication, there are LTE-V2X (long term evolutionV2X) communication technology, which is an initial version, and 5G-V2X communication technology, which is a next-generation version. 5G-V2X communication technology has been completed only until standardization, so LTE-V2X communication technology is mainly used. In this paper, we introduce trends related to various issues in V2X communication, including communication method decisions.