2016 IEEE/OES Autonomous Underwater Vehicles (AUV)最新文献_第3页

Towards persistent cooperative marine robotics 走向持久合作的海洋机器人

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778706

B. Claus, J. Kinsey, Yogesh A. Girdhar

引用次数: 6

Development of a regional underwater positioning and communication system for control of multiple autonomous underwater vehicles 面向多自主水下航行器控制的区域水下定位与通信系统的研制

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778708

M. Sasano, Shogo Inaba, Akihiro Okamoto, T. Seta, K. Tamura, T. Ura, Shinichi Sawada, Taku Suto

引用次数: 8

Autonomous air & underwater vehicle 自主空气和水下航行器

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778723

T. Vikranth, Ch. Raghavendra, T. Surya Kumari

引用次数: 0

Multi-vehicle autonomous tracking and filming of white sharks Carcharodon carcharias 多车辆自动跟踪和拍摄白鲨Carcharodon carcharias

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778707

A. Kukulya, R. Stokey, Carl Fiester, Edgar Mauricio Hoyos Padilla, G. Skomal

引用次数: 14

UW MORSE: The underwater Modular Open Robot Simulation Engine UW MORSE:水下模块化开放式机器人模拟引擎

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778681

Eirik Hexeberg Henriksen, I. Schjølberg, Tor Berge Gjersvik

{"title":"UW MORSE: The underwater Modular Open Robot Simulation Engine","authors":"Eirik Hexeberg Henriksen, I. Schjølberg, Tor Berge Gjersvik","doi":"10.1109/AUV.2016.7778681","DOIUrl":"https://doi.org/10.1109/AUV.2016.7778681","url":null,"abstract":"This paper presents an open-source simulation environment for underwater vehicles and robots. The simulation environment allows the user to simulate underwater robotic vehicles with realistic dynamic behavior in a 3-dimensional virtual environment. The environment is highly configurable, and offers a set of modules for simulating different types of vehicles in a number of underwater scenarios. The simulator can be used for control system development, path planning, risk management and testing in a safe virtual environment. The possibility for virtual testing will lower the cost and reduce time of operations. The simulation environment is an expansion of MORSE - Modular Open Robots Simulation Engine. The modular nature of MORSE allows the user to easily configure the simulations, making new environments and robots, as well as adding sensor and control interfaces. This expansion includes modules for hydrodynamic simulation, thrusters and underwater sensors. These modules enables the user to make a virtual replica of a specific underwater robot system. Such replica may be used as a Software-in-the-loop system for testing and verification of control systems and algorithms. The simulation environment allows interaction with a large set of robotic middlewares.","PeriodicalId":416057,"journal":{"name":"2016 IEEE/OES Autonomous Underwater Vehicles (AUV)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127288511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 21

Towards autonomous underwater iceberg profiling using a mechanical scanning sonar on a underwater Slocum glider 在水下滑翔机上使用机械扫描声纳实现自主水下冰山分析

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778656

Mingxi Zhou, R. Bachmayer, B. deYoung

{"title":"Towards autonomous underwater iceberg profiling using a mechanical scanning sonar on a underwater Slocum glider","authors":"Mingxi Zhou, R. Bachmayer, B. deYoung","doi":"10.1109/AUV.2016.7778656","DOIUrl":"https://doi.org/10.1109/AUV.2016.7778656","url":null,"abstract":"A Slocum underwater glider is been modified to map the underside of icebergs for monitoring iceberg deterioration off the coast of Newfoundland, Canada. The vehicle is equipped with a mechanical scanning sonar to map the iceberg surface, and a thruster for level-flight at a higher surging speed. In this paper we are presenting a profile-following controller that uses the sonar ranges to compute desired headings guiding the Slocum glider traveling safely around icebergs. A vehicle-attached occupancy map (VOM) is updated using sonar measured ranges with a dynamic inverse-sonar model. A desired path is then generated from the VOM by applying polynomial regression on the occupied cells. The line-of-sight guidance law is implemented to compute the desired heading to follow the desired path. The algorithm is initially evaluated in a simulation environment. The vehicle operation is simulated on a real-time hardware simulator, while the sonar is modeled in ray-tracing method. The iceberg is derived from an iceberg database with additional translational and rotational motion emulating a floating iceberg. After that, the guidance system is applied on a set of field data collected in 2015. During the trial, the Slocum glider was deployed to profile an underwater ramp feature in Conception Bay, Newfoundland, Canada. The feasibility of the porposed controller is indicated by the outcomes from this paper.","PeriodicalId":416057,"journal":{"name":"2016 IEEE/OES Autonomous Underwater Vehicles (AUV)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129137994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A concept design of underwater docking robot and development of its fundamental technologies 水下对接机器人的概念设计及其基础技术的研究

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778704

H. Yoshida, S. Ishibashi, Ohta Yutaka, M. Sugesawa, Kiyotaka Tanaka

引用次数: 7

The design and 200 day per year operation of the Autonomous Underwater Vehicle Sentry 自主水下航行器哨兵的设计和每年200天的运行

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778680

C. Kaiser, D. Yoerger, J. Kinsey, Sean Kelley, A. Billings, Justin Fujii, S. Suman, M. Jakuba, Z. Berkowitz, C. German, A. Bowen

引用次数: 19

End-to-end object detection and recognition in forward-looking sonar images with convolutional neural networks 基于卷积神经网络的前视声纳图像端到端目标检测与识别

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778662

Matias Valdenegro-Toro

{"title":"End-to-end object detection and recognition in forward-looking sonar images with convolutional neural networks","authors":"Matias Valdenegro-Toro","doi":"10.1109/AUV.2016.7778662","DOIUrl":"https://doi.org/10.1109/AUV.2016.7778662","url":null,"abstract":"Object detection and recognition are typically stages that form part of the perception module of Autonomous Underwater Vehicles, used with different sensors such as Sonar and Optical imaging, but their design is usually separate and they are only combined at test time. In this work we present a convolutional neural network that does both object detection (through detection proposals) and recognition in Forward-Looking Sonar images and is trained with bounding boxes and class labels only. Convolutional layers are shared and a 128-element feature vector is shared between both tasks. After training we obtain 93% correct detections and 75% accuracy, but accuracy can be improved by fine-tuning the classifier sub-network with the generated detection proposals. We evaluated fine-tuning with a SVM classifier trained on the shared feature vector, increasing accuracy to 85%. Our detection proposal method can also detect unlabeled and untrained objects, and has good generalization performance. Our unified method can be used in any kind of sonar image, does not make assumptions about an object's shadow, and learns features directly from data.","PeriodicalId":416057,"journal":{"name":"2016 IEEE/OES Autonomous Underwater Vehicles (AUV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128629560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 35

Technologies for under-ice AUV navigation 冰下AUV导航技术

2016 IEEE/OES Autonomous Underwater Vehicles (AUV) Pub Date : 2016-11-01 DOI: 10.1109/AUV.2016.7778657

D. Bandara, Z. Leong, H. Nguyen, S. Jayasinghe, A. Forrest

{"title":"Technologies for under-ice AUV navigation","authors":"D. Bandara, Z. Leong, H. Nguyen, S. Jayasinghe, A. Forrest","doi":"10.1109/AUV.2016.7778657","DOIUrl":"https://doi.org/10.1109/AUV.2016.7778657","url":null,"abstract":"Approximately 12% of the world's oceans are covered by ice. Understanding the physical processes, ecosystem structure, mixing dynamics and the role of these inaccessible environments in the context of global climate change is extremely important. Autonomous Underwater Vehicles (AUVs) play a major role in the potential exploration of these water systems due to the challenges of human access and relatively high associated risk. That said, AUV navigation and localization is challenging in these environments due to the unavoidable growth of navigational drift associated with inertial navigation systems, especially in long range missions under ice where surfacing in open water is not possible. While acoustic transponders have been used, they are time consuming and difficult to deploy. Terrain Relative Navigation (TRN) and Simultaneous Localization and Mapping (SLAM) based technologies are emerging in recent years as promising navigation solutions as they neither require deploying navigational aids or calculating the distance travelled from a reference point to determine location. One of the key challenges of underwater or under-ice image based localization results from the unstructured nature and lack of significant features in underwater environments. This issue has motivated the review presented in this paper, which outlines a potential area of under-ice AUV navigation and localization by combining TRN and SLAM with image matching methods for navigation in featureless environments.","PeriodicalId":416057,"journal":{"name":"2016 IEEE/OES Autonomous Underwater Vehicles (AUV)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122348207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7