• 한국시뮬레이션학회논문지
• /
• 제31권2호
• /
• pp.21-32
• /
• 2022

해군은 대한민국의 해양안보를 책임지기 위해서 항공모함 확보를 추진하고 있다. 항모가 주어진 임무를 완수하기 위해서는 운용요원들이 항모를 완벽하게 운용할 수 있어야 하며, 이를 위한 항모 운용요원들의 완벽한 항모 운용술은 끊임없는 훈련에서 비롯된다. 이에 본고에서는 함정에서도 항상 최고의 훈련을 시행할 수 있도록 함정 탑재형 훈련체계(OBTS)를 제안한다. 항모를 위한 OBTS는 함정에 최적으로 적용되고 운용요원들에게 최고의 교육훈련 환경을 제공하는 것이 가능하도록 합성훈련환경(STE) 기반의 철저한 시뮬레이터 형태로 구축되어야 한다. 그리고 항모의 다양한 훈련소요와 시행 조건을 만족시킬 수 있도록, 내장 훈련체계(ETS), VR 훈련체계, AR 정비체계, MR 훈련체계, MR Metaverse 훈련체계, 실감 시뮬레이터(Realistic Simulator) 훈련체계로 구성하는 방안을 제안한다.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.

• Journal of Astronomy and Space Sciences
• /
• 제41권2호
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.

• 한국군사과학기술학회지
• /
• 제15권1호
• /
• pp.36-45
• /
• 2012

In this thesis, we propose an integrated simulation method of virtual tank simulators and an entity-based constructive simulation model for small unit tactical training. To do this, we first identify requirements for virtual-constructive integrated simulation in a synthetic environment. We then propose a virtual and constructive interoperation method where individual combat entities of virtual-constructive models are interacting with each others. We develop a method of aggregating individual combat entities into a larger combat unit and disaggregating an unit into entities from time to time. We also present a way of sharing synthetic environment information between the models. Finally, we suggest that for more effective interoperability, virtual and constructive models should be developed by using common combat object models. The proposed interoperation method can be extended to further live-virtual-constructive models.

• 한국시뮬레이션학회논문지
• /
• 제25권3호
• /
• pp.29-39
• /
• 2016

전투력 향상을 위해서는 전장환경에 부합하는 훈련체계의 구축 및 적응 노력이 무엇보다도 중요하다. 본 연구에서는 시뮬레이션 기반의 훈련 체계인 FST (Fleet Synthetic Training)에 대한 고찰 및 한국 해군 측면의 분석을 수행하고 정책적인 제안을 도출하였다. 먼저, FST의 개념 및 현재 우리 해군의 훈련체계에 대한 전반적인 실태를 고찰하였다. 객관적인 전략 및 제안의 도출을 위하여 우리 군의 내부 역량과 FST 측면의 환경에 대한 SWOT 분석을 수행하였다. 한국 해군이 나아갈 방안으로 현재 진행중인 함대들의 통합전술재박훈련 체계를 중심으로 단계적이고 점진적인 접근을 통한 FST의 체계 정착이 제시되었다.

• 한국시뮬레이션학회논문지
• /
• 제19권4호
• /
• pp.235-247
• /
• 2010

군사훈련을 지원하는 워게임 모델은 환경요소가 매우 중요하다. 한국군의 대부분 워게임 모델들은 동일한 기상을 모든 작전지역에 적용하고 있다. 이에 따라 충실도가 높은 모의결과를 도출하지 못하고 있다. 이러한 실정에 비추어 본 연구는 분포형 합성환경 모델링 자료를 군사시뮬레이션에 적용할 수 있는 충실도 높은 워게임을 위한 요소기술을 개발 하는 것이다. 그것은 본 연구를 위해 개발한 2D GIS기반의 "단순 탐지확률 모델"과 이 모델에 지역별로 상이한 분포형 강수량 자료의 적용 기술이다. 이로써 군사시뮬레이션 수행 시 모델 해상도(전구급~공학급), 용도(훈련용, 분석용), 묘사 수준(군단급~대대급)에 따라 다양하게 작전지역별 상이한 국지기상을 반영하는 분포형 합성환경의 제공과 사용이 가능해졌다.

• 한국IT서비스학회지
• /
• 제20권1호
• /
• pp.67-79
• /
• 2021

The advent of the 4th Industrial Revolution is also causing many changes in defense operations. Defense reform and the fourth industrial revolution promoted smart defense innovation, and attempts are being made to incorporate cutting-edge science and technology into various fields such as weapons systems and defense operations. Education and training is one of the areas in which information and intelligence are urgently needed in the spirit of defense operations. Due to the nature of defense education and training, which aims to fight against the enemy, there is no emphasis on psychological training in the field rather than informatization, but in developed countries with various experiences of modern warfare, investment and vitalization of education and training are vital. Through this, efforts are being made to foster soldiers with problem-solving skills in uncertain battlefields. The informatization and intelligence of defense education and training is no longer a matter that can be delayed, and the innovation of education and training using cutting-edge science and technology can be said to be an age-old task to improve the results of education and training in the fourth industrial revolution. The purpose of this is because the application of related technologies is not the goal itself as the 4th Industrial Revolution arrives, but it has been made possible through the rapid advancement of science and technology that has made it difficult to realize education and training, even though it has long been desired. Ultimately, education and training data will be integrated and artificial intelligence-based intelligent learning systems will maximize the performance of education and training, thereby improving the combat readiness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.421-441
• /
• 2021

Fruit detection in orchards is one of the most crucial tasks for designing the visual system of an automated harvesting robot. It is the first and foremost tool employed for tasks such as sorting, grading, harvesting, disease control, and yield estimation, etc. Efficient visual systems are crucial for designing an automated robot. However, conventional fruit detection methods always a trade-off with accuracy, real-time response, and extensibility. Therefore, an improved method is proposed based on coarse-to-fine multitask cascaded convolutional networks (MTCNN) with three aspects to enable the practical application. First, the architecture of Fruit-MTCNN was improved to increase its power to discriminate between objects and their backgrounds. Then, with a few manual labels and operations, synthetic images and labels were generated to increase the diversity and the number of image samples. Further, through the online hard example mining (OHEM) strategy during training, the detector retrained hard examples. Finally, the improved detector was tested for its performance that proved superior in predicted accuracy and retaining good performances on portability with the low time cost. Based on performance, it was concluded that the detector could be applied practically in the actual orchard environment.