• 한국산업융합학회 논문집
• /
• 제25권5호
• /
• pp.853-859
• /
• 2022

In this study, we analyzed the instantaneous trajectory generation capability and target arrival rate of a mobile robot by changing the parameter of the TEB (Timed Elastic Band) Local Planner among local planners that affect the instantaneous obstacle avoidance ability of the mobile robot using ROS (Robot Operating System) simulation and real experience. As a result, we can expect a decrease in the target arrival time of the mobile robot through a decrease in the parameter values of the TEB Local Planner's min_obstacle_dist, inflation_dist, and penalty_epsilon. However, if this parameter is reduced too much, the risk of obstacle collision of the moving robot is increases, so it is important to combine the appropriate values to construct the parameter.

• 수산해양교육연구
• /
• 제26권3호
• /
• pp.647-655
• /
• 2014

In this research, unlike other fishing, the diving apparatus fishery is that the diver is engaged in fishing for profits. Because it is unique fishery, conflicts can be occurred in members. So, the purpose of this research is to define the contractual relationship between the parties of the diving apparatus fishery. For example, the relationship between the owner and diver and the owner and fishing ship crew. In addition, civil liability of default on the obligation was reviewed. Also, because the trouble was occurred by illegal fishing, criminal liability of ship crash caused by illegal diving apparatus fishery was considered. As a result, It is important to notifying the necessity of some method for the status of diver and fishing ship crew in diving apparatus fishery. moreover, It is need to educate the risk of illegal fishery for the parties of diving apparatus fishery.

• Ocean Systems Engineering
• /
• 제10권4호
• /
• pp.415-434
• /
• 2020

Detecting objects is important for the safe operation of ships, and enables collision avoidance, risk detection, and autonomous sailing. This study proposes a ship detection method from images and videos taken at sea using one of the state-of-the-art deep neural network-based object detection algorithms. A deep learning model is trained using a public maritime dataset, and results show it can detect all types of floating objects and classify them into ten specific classes that include a ship, speedboat, and buoy. The proposed deep learning model is compared to a universal trained model that detects and classifies objects into general classes, such as a person, dog, car, and boat, and results show that the proposed model outperforms the other in the detection of maritime objects. Different deep neural network structures are then compared to obtain the best detection performance. The proposed model also shows a real-time detection speed of approximately 30 frames per second. Hence, it is expected that the proposed model can be used to detect maritime objects and reduce risks while at sea.

• 한국재난정보학회 논문집
• /
• 제19권2호
• /
• pp.421-431
• /
• 2023

연구목적: 건설기계의 안전사고를 예방하기 위해 사용하는 스마트 안전 시스템의 안전성과 재해 예방효과를 분석하여 그 안전성을 실증하고자 한다. 연구방법:건설기계 중 재해다발 및 위험성이 높은 굴삭기를 대상으로 스마트 안전 시스템의 유무에 따른 근로자의 행동 패턴을 분석하였다. 연구결과: 건설기계에 스마트 안전 시스템을 설치하였을 때 건설기계와 협착 및 충돌 등에 의한 재해로부터 근로자의 안전성이 확보되었다. 결론:건설기계에 설치된 스마트 안전 시스템은 건설기계 관련 재해 감소와 중대 재해예방에 실효성을 증대시킬 수 있을 것으로 판단된다.

• 한국항공우주학회지
• /
• 제34권5호
• /
• pp.56-64
• /
• 2006

정지궤도 위성의 상대위치보정은 제한된 위지보정 박스내에 다수의 위성을 운용함으로서 발생하는 위성간 충돌, 전파간섭, 가림현상 등을 해결하기 위해 반드시 필요한 기술이다. 본 논문에서는 정지궤도 위성의 상대 궤도 운동 분석과 최적화 기법에 근거한 문제의 정립으로 상대위치보정을 수행하였다. 이상적인 정지궤도에 대한 상대운동을 다수의 멱함수와 주기함수로 표현하고, 상대위치보정에 필요한 조건들을 이들 함수로 표현한다. 이러한 구속 조건식과 더불어 연료 최소화 같은 가격 함수를 최소화하는 과정에서 궤도 수정에 필요한 절차를 수립하게 된다. 비선형 시뮬레이션을 통하여 본 논문에서 제시하고 있는 절차의 타당성을 검증하였고 또한 기존의 고전적인 방법과 비교하였다.

• 전기학회논문지
• /
• 제64권10호
• /
• pp.1479-1485
• /
• 2015

Robot's technology was very simple and repetitive in the past. Nowadays, robots are required to perform intelligent operation. So, path planning has been studied extensively to create a path from start position to the goal position. In this paper, potential field algorithm was used for path planning in dynamic environments. It is used for a path plan of mobile robot because it is elegant mathematical analysis and simplicity. However, there are some problems. The problems are collision risk, avoidance path, time attrition. In order to resolve path problems, we amalgamated potential field algorithm with the artificial neural network system. The input of the neural network system is set using relative velocity and location between the robot and the obstacle. The output of the neural network system is used for the weighting factor of the repulsive potential function. The potential field algorithm problem of mobile robot's path planning can be improved by using artificial neural network system. The suggested algorithm was verified by simulations in various dynamic environments.

• Interaction and multiscale mechanics
• /
• 제5권1호
• /
• pp.75-90
• /
• 2012

This paper investigates the effects of sports ground materials on the transfer characteristics of the landing impact force using a coupled foot-shoe-ground interaction model. The impact force resulting from the collision between the sports shoe and the ground is partially dissipated, but the remaining portion transfers to the human body via the lower extremity. However, since the landing impact force is strongly influenced by the sports ground material we consider four different sports grounds, asphalt, urethane, clay and wood. We use a fully coupled 3-D foot-shoe-ground interaction model and we construct the multi-layered composite ground models. Through the numerical simulation, the landing impact characteristics such as the ground reaction force (GRF), the acceleration transfer and the frequency response characteristics are investigated for four different sports grounds. It was found that the risk of injury, associated with the landing impact, was reduced as the ground material changes from asphalt to wood, from the fact that both the peak vertical acceleration and the central frequency monotonically decrease from asphalt to wood. As well, it was found that most of the impact acceleration and frequency was dissipated at the heel, then not much changed from the ankle to the knee.

• 한국산업융합학회 논문집
• /
• 제24권5호
• /
• pp.547-553
• /
• 2021

Dynamic object recognition is an important task for autonomous vehicles. Since dynamic objects exhibit a higher collision risk than static objects, our own trajectories should be planned to match the future state of moving elements in the scene. Time information such as optical flow can be used to recognize movement. Existing optical flow calculations are based only on camera sensors and are prone to misunderstanding in low light conditions. In this regard, to improve recognition performance in low-light environments, we applied a normalization filter and a correction function for Gamma Value to the input images. The low light quality improvement algorithm can be applied to confirm the more accurate detection of Object's Bounding Box for the vehicle. It was confirmed that there is an important in object recognition through image prepocessing and deep learning using YOLO.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2019년도 추계학술대회
• /
• pp.266-266
• /
• 2019

해마다 증가하고 있는 해양사고는 기관고장, 충돌, 좌초, 화재 등 다양하게 발생하고 있다. 이러한 해양사고는 대형 인명사고의 위험이 있어 사전에 사고를 예방 하는 게 무엇보다 중요하다. 이를 위해서는 해양사고 발생을 사전에 예측하고 이에 대응할 수 있는 예측 체계가 요구된다. 본 연구에서는 과거에 발생한 데이터를 근거로 미래를 예측할 수 있는 마코프 체인 프로세스(Markov Chain Process)를 적용하여 해양사고 발생을 사전에 예측하기 위한 모델링을 제안한다. 제시된 모델링을 적용하여 미래 발생 가능한 해양사고 발생 확률을 산출하고 실제 발생한 빈도와 비교하였다. 또한 많이 사용되는 다른 예측 분석 방법과 비교하여 예측의 정확성을 측정하였다. 이를 통해 해양사고 발생에 관한 예측 체계를 마련하는데 하나의 확률 모형을 제안하였으며, 나아가 다양한 해양사고의 문제를 예측하는데 기여할 것으로 기대된다.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.329-334
• /
• 2011

본 논문은 실내형 이동로봇에 적용하기 위한 위치인식과 장애물 추적 방법을 제안한다. 제안된 방법을 구현하기 위해 레이저 스캐너가 사용되었으며 로봇이 운행되는 공간의 지도정보를 미리 알고 있다고 가정한다. 레이저 스캐너의 측정치를 지도정보와 매칭해가며 Sequential Monte Carlo (SMC)방법을 이용하여 로봇의 위치를 파악하고 파악된 위치에서 주변 장애물의 위치를 인식하고 다중 물체 추적 알고리즘을 이용함으로써 장애물과의 충돌 위험성 등을 미리 파악할 수 있다. 마지막으로, 본 논문에서 제안한 방법을 실험을 통해 검증한다.