• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.9
• /
• pp.813-821
• /
• 2013

In this paper, we present the development of P-SURO II hybrid AUV (Autonomous Underwater Vehicle) which can be operated in both of AUV and ROV (Remotely Operated Vehicle) modes. In its AUV mode, the vehicle is supposed to carry out some of underwater missions which are difficult to be achieved in ROV mode due to the tether cable. To accomplish its missions such as inspection and maintenance of complex underwater structures in AUV mode, the vehicle is required to have high level of autonomy including environmental recognition, obstacle avoidance, autonomous navigation, and so on. In addition to its systematic development issues, some of algorithmic issues are also discussed in this paper. Various experimental studies are also presented to demonstrate these developed autonomy algorithms.

• Journal of Ocean Engineering and Technology
• /
• v.7 no.1
• /
• pp.62-72
• /
• 1993

This paper describes the results of 3 years project on the design and development of a 500 meter class ocean survery ROV model. The design concept and the design procedure are given for each component of the ROV model. The design concept and the design procedure are given for each component of the ROV. Special emphasis is laid on the development of the position control system together with the development of the performance evaluation technique.

• The Magazine of the IEIE
• /
• v.38 no.7
• /
• pp.20-29
• /
• 2011

무인잠수정(Unmanned Underwater Vehicle, UUV)은 하드웨어 구성과 관련하여 ROV (Remotely Operated Vehicle), SAUV (Semi-Autonomous Underwater Vehicle), AUV (Autonomous Underwater Vehicle) 등으로 구분할 수 있으며, 그 중에서 자율무인잠수정(AUV)은 주어진 임무의 난이도, 작업 환경의 정보, 그리고 운용자의 간섭 정도에 따라 다양한 수준으로 자율 정도를 분류한다. 무인잠수정은 미국을 중심으로 1952년부터 개발되기 시작하였으며 최초는 전적으로 운용자에 의해서 직접 운용되는 ROV가 주를 이루었다. 자율무인잠수정은 1980년대부터 다양한 수중관련 기술 및 컴퓨터 발전과, 민군의 사용분야가 증가되면서 급속한 발전을 이루어 왔으며 이에 따라 AUV 자율수준 정의와 기술개발도 급속한 진전이 이루어져 왔다. 본 기고에서는 무인잠수정의 개발현황, 자율개념 및 자율수준(Autonomy Levels for Underwater Vehicle, ALFUV)의 정의, 자율을 정립함에 필요한 방법 또는 기술 등을 알아보고 마지막으로 자율 알고리즘으로 개발된 구조의 표준화를 중심으로 현황을 파악하였으며 또한 미래의 자율수준 개발 동향을 살펴보았다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.808-814
• /
• 2010

In this paper we executed a SBL(Short Baseline) underwater acoustic positioning system that is a kind of underwater position estimation system to estimates the 3-dimensional position of ROV(Remotely Operated Vehicle) using hydrophones and DAQ(Data Acquisition) system in the basin which dimensions are $3{\times}3{\times}1.7(m)$. For this experiment, we let 4 hydrophones in different positions of the basin for receiver and 1 hydrophone is fixed on the underwater vehicle for transmitting sensor(pinger). These five hydrophones are communicated with each other to find the 3-D positions of the moving ROV in the basin. The measured signals are collected by DAQ system and the positions of the ROV are plotted by LabView program in real-time. To estimate the position of the ROV we used a trigonometric method. In X and Y plane the estimated data has a small errors but in Z plane the estimated data has large errors so we cannot use this data for position control. One solution of this problem is using depth sensor that implemented of the underwater vehicle. Hereafter, we will test in the ocean using designed SBL system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.15-16
• /
• 2012

본 논문에서는 우선순위 기반의 RTS/CTS 통신 기법을 적용하여 생체모방형 ROV 를 제어하기 위한 수중 MAC 프로토콜을 제안하였다. MANET 기반의 하천 수질 환경 감시 시스템이 효율적으로 운용되기 위한 수중 MAC 프로토콜이 지원됨으로써 이동성이 강조되는 생체모방형 ROV 제어를 위한 실시간성을 보장할 수 있다.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.172-177
• /
• 2004

This paper presents the results of the structural analysis and optimal design of frames of the UUV(Unmanned Underwater vehicle) to be operated at 6000m depth in the ocean. The structure of the UUV system can be classified into two structure, Launcher ana ROV. Frame of the launcher will be made by Galvanized Steel which has high strength and corrosion-resistant but this material has high specific gravity for tile object to be weight in the water Similarly, ROV will be made by AI6061-T6, and frame of the ROV will be fix many instruments and syntactic buoyancy materials. Before fabrication of tile frame, we performed sensitivity analysis - change in weight due to $\pm1\%$ change in design variables, for easy choice by change of dimension of the frame.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1250-1253
• /
• 2017

본 논문은 드론 산업이 발전함에 따라 하천, 호수, 바다 상공에서 활용하는 드론이 수중에 빠졌을 때, 물에 빠진 드론을 모선(Mothership)과 집게팔이 달린 ROV(Remotely Operated Vehicle)를 이용하여 인양하는 시스템을 제안한다. 제안한 시스템의 구성 요소는 세 가지로 첫 번째는 실시간으로 GCS(Ground Control Station)에 영상을 전송하며 ROV와 전력선 모뎀을 이용하여 통신을 하는 모선, 두 번째는 수중에 들어가 수중 카메라를 이용하여 육안으로 드론을 탐색하고 장착된 집게팔로 드론을 몸체에 고정시키는 ROV, 세 번째는 모선, ROV와 실시간으로 영상 데이터와 명령 신호를 주고 받는 GCS 이다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.8
• /
• pp.1107-1114
• /
• 2010

In this paper, a development of a new 5 d.o.f. underwater manipulator which is actuated by electric motors capable of carrying over 20kg payload and of various operation under the water has been studied. The manipulator for applying to midium-sized AUV or ROV has been designed small and light but to handle a heavy 25kg payload. The joint actuator for the manipulator is designed and builted as a new modular typed double oil jacket for waterproofness. Also, superior joint torque performance of the developed joint actuator has been varified through tests in the air. And, a 5 d.o.f. highly perfomable underwater manipulator has been builted applying the developed underwater joint actuators.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.291-292
• /
• 2011