• Title/Summary/Keyword: Underwater Robotics

Search Result 197, Processing Time 0.031 seconds

A study on visual tracking of the underwater mobile robot for nuclear reactor vessel inspection

  • Cho, Jai-Wan;Kim, Chang-Hoi;Choi, Young-Soo;Seo, Yong-Chil;Kim, Seung-Ho
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.1244-1248
    • /
    • 2003
  • This paper describes visual tracking procedure of the underwater mobile robot for nuclear reactor vessel inspection, which is required to find the foreign objects such as loose parts. The yellowish underwater robot body tends to present a big contrast to boron solute cold water of nuclear reactor vessel, tinged with indigo by Cerenkov effect. In this paper, we have found and tracked the positions of underwater mobile robot using the two color information, yellow and indigo. The center coordinates extraction procedures are as follows. The first step is to segment the underwater robot body to cold water with indigo background. From the RGB color components of the entire monitoring image taken with the color CCD camera, we have selected the red color component. In the selected red image, we extracted the positions of the underwater mobile robot using the following process sequences; binarization, labelling, and centroid extraction techniques. In the experiment carried out at the Youngkwang unit 5 nuclear reactor vessel, we have tracked the center positions of the underwater robot submerged near the cold leg and the hot leg way, which is fathomed to 10m deep in depth.

  • PDF

Localization of AUV Using Visual Shape Information of Underwater Structures (수중 구조물 형상의 영상 정보를 이용한 수중로봇 위치인식 기법)

  • Jung, Jongdae;Choi, Suyoung;Choi, Hyun-Taek;Myung, Hyun
    • Journal of Ocean Engineering and Technology
    • /
    • v.29 no.5
    • /
    • pp.392-397
    • /
    • 2015
  • An autonomous underwater vehicle (AUV) can perform flexible operations even in complex underwater environments because of its autonomy. Localization is one of the key components of this autonomous navigation. Because the inertial navigation system of an AUV suffers from drift, observing fixed objects in an inertial reference system can enhance the localization performance. In this paper, we propose a method of AUV localization using visual measurements of underwater structures. A camera measurement model that emulates the camera’s observations of underwater structures is designed in a particle filtering framework. Then, the particle weight is updated based on the extracted visual information of the underwater structures. The proposed method is validated based on the results of experiments performed in a structured basin environment.

Development of Underwater Cleaning Robot Control Algorithm for Cleanup Efforts in Industrial Area (산업현장 침전물 청소작업용 수중청소로봇 제어 알고리즘 기술 개발)

  • Lee, Jung-Woo;Lee, Jong-Deuk;Choi, Young-Ho;Han, Kyung-Lyong;Suh, Jin-Ho
    • Journal of Power System Engineering
    • /
    • v.21 no.4
    • /
    • pp.26-33
    • /
    • 2017
  • In this paper, we developed a control algorithm to maximize the cleaning performance and the cleaning efficiency of the underwater cleaning robot platform which has been developed for various cistern environment in the industrial field. Through these research and development, we have presented the operation and application of underwater cleaning robots that have been developed, and contributed to commercialization. Finally, this results were verified the effectiveness through actual field experiments.

Vision-based Localization for AUVs using Weighted Template Matching in a Structured Environment (구조화된 환경에서의 가중치 템플릿 매칭을 이용한 자율 수중 로봇의 비전 기반 위치 인식)

  • Kim, Donghoon;Lee, Donghwa;Myung, Hyun;Choi, Hyun-Taek
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.19 no.8
    • /
    • pp.667-675
    • /
    • 2013
  • This paper presents vision-based techniques for underwater landmark detection, map-based localization, and SLAM (Simultaneous Localization and Mapping) in structured underwater environments. A variety of underwater tasks require an underwater robot to be able to successfully perform autonomous navigation, but the available sensors for accurate localization are limited. A vision sensor among the available sensors is very useful for performing short range tasks, in spite of harsh underwater conditions including low visibility, noise, and large areas of featureless topography. To overcome these problems and to a utilize vision sensor for underwater localization, we propose a novel vision-based object detection technique to be applied to MCL (Monte Carlo Localization) and EKF (Extended Kalman Filter)-based SLAM algorithms. In the image processing step, a weighted correlation coefficient-based template matching and color-based image segmentation method are proposed to improve the conventional approach. In the localization step, in order to apply the landmark detection results to MCL and EKF-SLAM, dead-reckoning information and landmark detection results are used for prediction and update phases, respectively. The performance of the proposed technique is evaluated by experiments with an underwater robot platform in an indoor water tank and the results are discussed.

Development of the Underwater Cleaning Robot Platform for a Higher Efficiency (고효율 수중청소로봇 플랫폼 기술 개발)

  • Suh, Jin-Ho;Lee, Jung-Woo;Kim, Jong-Geol;Choi, Young-Ho;Choi, Il-Seop
    • Journal of Power System Engineering
    • /
    • v.21 no.3
    • /
    • pp.74-84
    • /
    • 2017
  • This paper presents the development of the underwater cleaning robot platform for a higher efficiency in manufacturing industry. Human operators directly go into the cistern and clean sludge after drainage of the water so far. It is sometimes dangerous because of the harmful chemical materials from the product making process. In addition, it takes long time for water drainage and supplying it back. However, the robot cleaning operation does not need to drain water so that it could be applied to the sludge cleaning work at any time without the plant pause. Moreover, it can prevent the safety accidents because human operators are not necessary to enter directly the sludge cisterns. This paper shows the performance of cleaning work that can be applied in the industrial field through the design and development of underwater cleaning robot platform. And these results demonstrate that the developed underwater cleaning robot has great possibilities to clean other industrial water cisterns.

Computational Flow Analysis and Drag Coefficient Research for Angle of Attack in Slocum Underwater Glider (Slocum 수중 글라이더의 유영 받음각에 대한 전산유동해석 및 항력계수 연구)

  • Park, Jeong-Woo;Lee, Jung-Woo;Choi, Young-Ho;Seo, Kap-Ho;Suh, Jin-Ho;Park, Jong-Jin
    • Journal of Ocean Engineering and Technology
    • /
    • v.30 no.5
    • /
    • pp.381-388
    • /
    • 2016
  • An underwater glider makes it easy to explore a wide area with low power. However, an underwater glider is difficult to use for rapid collection, because the surfacing location cannot be predicted after a dive. Thus, simulation research is needed to predict the swimming path. In this paper, based on research, a linearized equation is derived for the drag coefficient at each angle of attack by assuming the boundary conditions for the Slocum underwater glider and performing a computational flow analysis.

Extended Kalman Filter-based Localization with Kinematic Relationship of Underwater Structure Inspection Robots (수중 구조물 검사로봇의 기구학적 관계를 이용한 확장 칼만 필터 기반의 위치추정)

  • Heo, Young-Jin;Lee, Gi-Hyeon;Kim, Jinhyun
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.19 no.4
    • /
    • pp.372-378
    • /
    • 2013
  • In this paper, we research the localization problem of the crawler-type inspection robot for underwater structure which travels an outer wall of underwater structure. Since various factors of the underwater environment affect an encoder odometer, it is hard to localize robot itself using only on-board sensors. So in this research we used a depth sensor and an IMU to compensate odometer which has extreme error in the underwater environment through using Extended Kalman Filter(EKF) which is normally used in mobile robotics. To acquire valid measurements, we implemented precision sensor modeling after assuming specific situation that robot travels underwater structure. The depth sensor acquires a vertical position of robot and compensates one of the robot pose, and IMU is used to compensate a bearing. But horizontal position of robot can't be compensated by using only on-board sensors. So we proposed a localization algorithm which makes horizontal direction error bounded by using kinematics relationship. Also we implemented computer simulations and experiments in underwater environment to verify the algorithm performance.

Model-Based Pose Estimation for High-Precise Underwater Navigation Using Monocular Vision (단안 카메라를 이용한 수중 정밀 항법을 위한 모델 기반 포즈 추정)

  • Park, JiSung;Kim, JinWhan
    • The Journal of Korea Robotics Society
    • /
    • v.11 no.4
    • /
    • pp.226-234
    • /
    • 2016
  • In this study, a model-referenced underwater navigation algorithm is proposed for high-precise underwater navigation using monocular vision near underwater structures. The main idea of this navigation algorithm is that a 3D model-based pose estimation is combined with the inertial navigation using an extended Kalman filter (EKF). The spatial information obtained from the navigation algorithm is utilized for enabling the underwater robot to navigate near underwater structures whose geometric models are known a priori. For investigating the performance of the proposed approach the model-referenced navigation algorithm was applied to an underwater robot and a set of experiments was carried out in a water tank.

Swimming Plans for a Bio-inspired Articulated Underwater Robot (생체모방형 수중다관절 로봇의 유영계획)

  • Kim, Hee-Jong;Lee, Jihong
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.19 no.9
    • /
    • pp.782-790
    • /
    • 2013
  • In this paper, we propose a better solution for swimming plans of an articulated underwater robot, Crabster, with a view point of biomimetics. As a biomimetic model of underwater organisms, we chose diving beetles structurally similar to Crabster. Various swimming locomotion of the diving beetle has been observed and sorted by robotics technology through experiments with a high-speed camera and image processing software Image J. Subsequently, coordinated patterns of rhythmic movements of the diving beetle are reproduced by simple control parameters in a parameter space which make it easy to control trajectories and velocities of legs. Furthermore, a simulation was implemented with an approximated model to predict the motion of the robot under development based on the classified forward and turning locomotion. Consequently, we confirmed the applicability of parameterized leg locomotion to the articulated underwater robot through the simulated results by the approximated model.

Photorealistic Real-Time Dense 3D Mesh Mapping for AUV (자율 수중 로봇을 위한 사실적인 실시간 고밀도 3차원 Mesh 지도 작성)

  • Jungwoo Lee;Younggun Cho
    • The Journal of Korea Robotics Society
    • /
    • v.19 no.2
    • /
    • pp.188-195
    • /
    • 2024
  • This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.