Дисертації з теми "Autonomous surface vehicle (ASV)"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-28 дисертацій для дослідження на тему "Autonomous surface vehicle (ASV)".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Özkahraman, Özer. "Multi-Agent Control of Autonomous Surface Vehicles for Shallow Water Exploration and Depth Mapping." Thesis, KTH, Robotik, perception och lärande, RPL, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-209948.
Повний текст джерелаAtt ha tillgång till en karta över ett område är en förutsättning för många olika aktiviteter, och därför har det skapats allt mer exakta kartor över de flesta landområden. För hav och sjöar har man skapat mer ungefärliga djupkartor för att undvika grundstötningar för sjöfart. Grundare områden har däremot ofta undvikits av stora djupmätningsfartyg, och är därför i hög grad okarterade.I denna rapport föreslås och analyseras en metod för att kartera djupet i grunda områden med hjälp av en grupp autonoma ytfarkoster. Givet en polygon inom vilken man vill ha botten karterad skall gruppen autonomt söka av området med få ytterligare antaganden. Gaussiska processer används för att styra farkosterna mot områden med stora mätosäkerheter, och algoritmen utvärderas i riktiga experiment.Resultaten jämförs med befintliga metoders prestanda, med avseende på kartkvalitet och tid för kartering. Resultaten visar att en av de föreslagna metoderna är snabb men mindre noggrann, medan den andra ger en bättre avvägning mellan kvalitet och uppdragstid.
Gong, Xiaojin. "Omnidirectional Vision for an Autonomous Surface Vehicle." Diss., Virginia Tech, 2008. http://hdl.handle.net/10919/30175.
Повний текст джерелаPh. D.
Stahl, Christopher Wayne. "Accumulated Surfaces & Least-Cost Paths: GIS Modeling for Autonomous Ground Vehicle (AGV) Navigation." Thesis, Virginia Tech, 2005. http://hdl.handle.net/10919/33266.
Повний текст джерелаMaster of Science
Svensson, Anton. "Composite Hydrofoil Manufacturing For An Autonomous Surface Vessel." Thesis, KTH, Marina system, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273220.
Повний текст джерелаRiggins, Jamie N. "Location Estimation of Obstacles for an Autonomous Surface Vehicle." Thesis, Virginia Tech, 2006. http://hdl.handle.net/10919/33227.
Повний текст джерелаMaster of Science
Watts-Willis, Tristan A. "Autonomous model selection for surface classification via unmanned aerial vehicle." Scholarly Commons, 2017. https://scholarlycommons.pacific.edu/uop_etds/224.
Повний текст джерелаPoudel, Om Prakash. "Identification of barriers and least cost paths for autonomous vehicle navigation using airborne LIDAR data." Thesis, Virginia Tech, 2007. http://hdl.handle.net/10919/43304.
Повний текст джерелаMaster of Science
Kragelund, Sean P. "Optimal sensor-based motion planning for autonomous vehicle teams." Thesis, Monterey, California: Naval Postgraduate School, 2017. http://hdl.handle.net/10945/53003.
Повний текст джерелаReissued 30 May 2017 with correction to student's affiliation on title page.
Autonomous vehicle teams have great potential in a wide range of maritime sensing applications, including mine countermeasures (MCM). A key enabler for successfully employing autonomous vehicles in MCM missions is motion planning, a collection of algo-rithms for designing trajectories that vehicles must follow. For maximum utility, these algorithms must consider the capabilities and limitations of each team member. At a minimum, they should incorporate dynamic and operational constraints to ensure trajectories are feasible. Another goal is maximizing sensor performance in the presence of uncertainty. Optimal control provides a useful frame-work for solving these types of motion planning problems with dynamic constraints and di_x000B_erent performance objectives, but they usually require numerical solutions. Recent advances in numerical methods have produced a general mathematical and computational framework for numerically solving optimal control problems with parameter uncertainty—generalized optimal control (GenOC)— thus making it possible to numerically solve optimal search problems with multiple searcher, sensor, and target models. In this dissertation, we use the GenOC framework to solve motion planning problems for di_x000B_erentMCMsearch missions conducted by autonomous surface and underwater vehicles. Physics-based sonar detection models are developed for operationally relevant MCM sensors, and the resulting optimal search trajectories improve mine detection performance over conventional lawnmower survey patterns—especially under time or resource constraints. Simulation results highlight the flexibility of this approach for optimal mo-tion planning and pre-mission analysis. Finally, a novel application of this framework is presented to address inverse problems relating search performance to sensor design, team composition, and mission planning for MCM CONOPS development.
Hamren, Rasmus. "APPLYING UAVS TO SUPPORT THE SAFETY IN AUTONOMOUS OPERATED OPEN SURFACE MINES." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-53376.
Повний текст джерелаSelby, William Clayton. "Autonomous navigation and tracking of dynamic surface targets on-board a computationally impoverished aerial vehicle." Thesis, Massachusetts Institute of Technology, 2011. http://hdl.handle.net/1721.1/67801.
Повний текст джерелаCataloged from PDF version of thesis.
Includes bibliographical references (p. 113-120).
This thesis describes the development of an independent, on-board visual servoing system which allows a computationally impoverished aerial vehicle to autonomously identify and track a dynamic surface target. Image segmentation and target tracking algorithms are developed for the specific task of monitoring whales at sea. The computer vision algorithms' estimates prove to be accurate enough for quadrotor stabilization while being computationally fast enough to be processed on-board the platform. This differs from current techniques which require off-board processing of images for vehicle localization and control. The vision algorithm is evaluated on video footage to validate its performance and robustness. The quadrotor is then modeled to motivate and guide the development of Linear Quadratic Regulator (LQR) controllers for maneuvering the quadrotor. The controllers are tuned using a motion capture system which provides ground truth state measurements. The vision system is integrated into the control scheme to allow the quadrotor to track an iCreate. Additionally, an Extended Kalman Filter (EKF) fuses the vision system position estimates with attitude and acceleration measurements from an on-board Inertial Measurement Unit (IMU) to allow the quadrotor to track a moving target without external localization.
by William Clayton Selby.
S.M.
Zhang, Hongyi. "Road surface condition detection for autonomous vehicle by NIR LED system and machine learning approaches." Thesis, université Paris-Saclay, 2022. http://www.theses.fr/2022UPAST106.
Повний текст джерелаThe field of autonomous vehicles has aroused great interest in recent years. In order to ensure the passenger to get a safe and comfortable experience on autonomous vehicles, advanced obstacle systems have to be implemented. Although current solutions for detecting obstacles have shown quite good performances, they have to be improved for an increased safety of autonomous vehicles on road, both in day-time and night-time conditions. In particular, autonomous vehicles in real life may encounter ice, snow or water puddles, which may be the cause of severe crashes and traffic accidents. The detection systems must hence allow detecting changes in road conditions to anticipate the vehicle reaction and/or deactivate the automated functions. The aim of this thesis is to propose a system implemented on the autonomous vehicles in order to detect the road surface conditions induced by the weather. After deep investigation of the state of art, a near infrared (NIR) system based on LEDs and a machine learning system were proposed for daytime and night-time detection. The NIR systems with three LEDs were investigated with experimental validations. In addition, the specifications of the NIR systems are carefully discussed. Furthermore, the machine learning system is proposed as a supplementary system. The performance of different models is compared in terms of classification accuracy and model complexity. Finally, the results are discussed and a combination of the two systems is proposed
Galarza, Bogotá Cesar Mauricio. "Diseño del sistema de navegación en inmersión del vehículo Guanay II para aplicaciones de detección y seguimiento de vertidos de hidrocarburos en zonas costeras." Doctoral thesis, Universitat Politècnica de Catalunya, 2018. http://hdl.handle.net/10803/461415.
Повний текст джерелаEl estudio de los mares es un campo de la ciencia que se encuentra en constante desarrollo. A nivel tecnológico, en los últimos años, se han producido importantes avances en el diseño de plataformas y sistemas de medición de variables oceanográficas con importantes mejoras en su sensibilidad, así como en su capacidad de resolución espacial y temporal. Actualmente, debido a los altos costos de las técnicas tradicionales (barcos oceanográficos) se ha incrementado el uso de vehículos no tripulados como los ROV (Remotely Operated Vehicle), los ASV (Autonomous Surface Vehicle), los AUV (Autonomous Underwater Vehicle) y los AUV Glider. Desde el punto de vista de la realización de estudios oceanográficos, los AUV ofrecen mayores beneficios por su mayor maniobrabilidad y autonomía. Un ejemplo de este caso es el estudio del comportamiento de las especies marinas en función de variables ambientales. En estos estudios es indispensable la medida con buena resolución espacial de múltiples parámetros, como la salinidad, a diversas profundidades de una misma columna de agua. Para los sectores industriales y de conservación del medio ambiente no hay un uso específico de los AUV. Pueden ser utilizados en la obtención de mapas batimétricos y en la monitorización de las características físico-químicas especificas del agua del mar. La motivación de este trabajo se centra en la adaptación del vehículo Guanay II como plataforma de mediciones oceanográficas, con la capacidad de navegar en inmersión, así como la reducción de la posibilidad de colisión contra otros vehículos o estructuras marinas mediante el diseño e implantación de un sistema de detección y evasión de obstáculos. Esta adaptación permitiría en el futuro utilizar el vehículo Guanay para realizar la detección y seguimiento de vertidos contaminantes de hidrocarburos en el mar, así como la monitorización de datos oceanográficos para su utilización en modelos predictivos del desplazamiento del vertido. El Guanay II es un vehículo híbrido entre AUV y ASV, es decir, navega en superficie y realiza inmersiones verticales en puntos programados. Con base en la motivación descrita se han realizado modificaciones mecánicas y electrónicas en el vehículo, acompañadas de un proceso de estudio, análisis y de desarrollo matemático para obtener un modelado hidrodinámico desacoplado del vehículo sobre el plano vertical. Se ha diseñado e implementado un sistema de inmersión por propulsión vectorial utilizando los propulsores laterales para controlar la inclinación del vehículo durante la inmersión. Este sistema ha sido simulado en Matlab e implementado en el vehículo, lo que ha permitido probarlo en el canal olímpico de Castelldefels, Los resultados obtenidos en estas pruebas han sido satisfactorios, permitiendo que el vehículo entre en inmersión, se mantenga en inmersión durante el tiempo definido y posteriormente vuelva a superficie. Por otra parte, en paralelo al diseño e implementación de este sistema, se ha llevado a cabo el diseño e implementación de un sistema de detección y evasión de obstáculos de arquitectura reactiva implementado bajo un sistema fuzzy, basado en un sensor SONAR MK3. Este sistema ha sido simulado e implementado en la unidad de control del vehículo. Esta implementación ha permitido realizar múltiples pruebas de campo, las cuales se realizaron en el canal olímpico de Castelldefels. Los resultados obtenidos en estas pruebas han sido satisfactorios, logrando en todos casos la evasión de los obstáculos presentes en el entorno de navegación.
Masmitjà, i. Rusinyol Ivan. "Acoustic underwater target tracking methods using autonomous vehicles." Doctoral thesis, Universitat Politècnica de Catalunya, 2020. http://hdl.handle.net/10803/668828.
Повний текст джерелаLa biologia marina junt amb la importància que ha adquirit el sector pesquer, fa que es requereixin noves eines per a l’estudi dels nostres oceans. La capacitat de mesurar diferents poblacions i paràmetres ambientals d’espècies marines permet millorar el coneixement de l’impacte que l’ésser humà té sobre elles, millorant-ne els mètodes d’explotació. Per exemple, la capacitat de desplaçament i els patrons de moviment són crucials per obtenir el coneixement necessari per a una explotació sostenible de les pescaries involucrades. No obstant, la localització submarina és un dels principals problemes que s’ha de resoldre en l’explotació dels recursos submarins, on el sistema de posició global (GPS) no es pot utilitzar. A part dels mètodes tradicionals de posicionament submarí, com per exemple el Long Base-Line (LBL) o el Ultra-Short Base-Line (USBL), nous mètodes han estat desenvolupats per tal de millorar la navegació, la flexibilitat, i per reduir els costos de desplegament. Per exemple, el Range-Only and Single-Beacon (ROSB) utilitza un vehicle autònom per a localitzar i seguir diferents objectius submarins mitjançant mesures de rang realitzades a partir de mòdems acústics. En un escenari on l’objectiu a seguir és mòbil, el mètode ROSB de seguiment pot ser vist com a un problema de Hidden Markov Model (HMM). Aleshores, utilitzant la regla de Bayes, la funció de distribució de probabilitat dels estats del HMM pot ser solucionat utilitzant diferents mètodes de filtratge. Per tant, s’estudien diferents estratègies per millorar el sistema de localització i seguiment basat en ROSB, tant per objectius estàtics com mòbils. En aquesta tesis, presentem i comparem diferents mètodes utilitzant diferents escenaris, els quals s’han avaluat tant en simulacions com en proves de camp reals. A més, es presenten les principals notacions matemàtiques de cada algoritme i les millors pràctiques a utilitzar. Per tant, des d’un punt de vista metodològic, aquest treball fa un pas endavant en el coneixement de l’exactitud que es pot assolir utilitzant els mètodes de localització i seguiment d’espècies mitjançant algoritmes ROSB i vehicles autònoms. A més a més, mentre molts dels treballs realitzant durant els últims anys es centren en l’ús de mòdems acústics per al seguiment d’objectius submarins, en aquesta tesis es presenta un innovador mètode anomenat Area-Only Target Tracking (AOTT). Aquest sistema utilitza petites etiquetes acústiques comercials (tag), la qual cosa, redueix el cost i la complexitat en comparació amb els altres mètodes. Addicionalment, gràcies a l’ús d’aquests tags de dimensions reduïdes, aquest sistema permet seguir espècies marines com les meduses. La metodologia utilitzada per el mètode AOTT es mostra en aquesta tesis, on també es presenten els primers experiments realitzats a la badia de Monterey a Califòrnia.
Haven, Scott. "Measuring surface ocean wave height and directional spectra using an Acoustic Doppler Current Profiler from an autonomous underwater vehicle." Thesis, Massachusetts Institute of Technology, 2012. http://hdl.handle.net/1721.1/78181.
Повний текст джерелаCataloged from PDF version of thesis.
Includes bibliographical references (p. 117-119).
The Acoustic Doppler Current Profiler (ADCP) is a proven technology which is capable of measuring surface wave height and directional information, however it is generally limited to rigid, bottom mounted applications which limit its capabilities for measuring deep water waves. By employing an upward looking ADCP on a moving platform, such as an autonomous underwater vehicle or submerged float, we show that it is possible to remove the wave induced motion of the platform and accurately measure surface ocean wave information. The platform selected for testing was a REMUS-100 vehicle equipped with an upward and downward looking ADCP and high accuracy Kearfott inertial navigation unit. Additionally, a Microstrain 3DM-GX3-25 Attitude Heading Reference System was tested as a low cost alternative to the Kearfott system. An experiment consisting of multiple REMUS deployments was conducted near the Martha's Vineyard Coastal Observatory (MVCO). The wave induced motion was measured by various inertial and acoustic sensors and removed from the ADCP data record. The surface wave height and mean directional estimates were compared against a Datawell MKIII directional Waverider buoy and bottom mounted 1200 kHz upward looking ADCP at the MVCO. Results demonstrate that the non-directional spectrum of wave height and the mean wave direction as a function of frequency can be accurately measured from an underway autonomous underwater vehicle in coastal depth waters using an ADCP.
by Scott Haven.
S.M.
Lundblad, Oscar. "The autonomous crewmate : A sociotechnical perspective to implementation of autonomous vehicles in sea rescue." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166452.
Повний текст джерелаWARA-PS
Hosseinyalamdary, Saivash Hosseinyalamdary. "Traffic Scene Perception using Multiple Sensors for Vehicular Safety Purposes." The Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1462803166.
Повний текст джерелаSantos, André Filipe Almeida. "Autonomy for Unmanned Surface Vehicle." Master's thesis, 2018. http://hdl.handle.net/10316/86059.
Повний текст джерелаAutonomous navigation has been successfully presented and developed both on ground and air. Though, autonomy on maritime surface vehicles has proven to be more challenging. In order to have an Autonomous Surface Vehicle (ASV), it ought to have a completely functional Guidance, Navigation and Control (GNC) system.This work presents part of the GNC system for the ASV giving special emphasis on collision avoidance and as the main focus the COLlision REGulationS (COLREGS) mode detection and it's application. For collision avoidance, two submodules were implemented, being the Dynamic Window Approach (DWA) for static obstacles, and a COLREGS compliant algorithm for multi-vehicle encounters, which are set with perimeters of safety.Slights modifications to the original DWA algorithm were introduced in order to better suit the conditions presented, such as the reset of the array of obstacles, when thus are outside of the inner perimeter, in order to reduce computational effort.The COLREGS algorithm implemented is able to detect the COLREGS rule to follow and to generate a new combination of heading and velocity to both, avoid collision and to correspond to the rules requirements.Sensors, such as an IMU and a GNSS system, were responsible to provide total knowledge of the vehicle's position and state, whereas a Lidar and an AIS system, were responsible for the representation of the obstacles and it's attributes. ROS has been employed as the middleware for the ASV, which avoids the need to develop your own code for many aspects of robot control.The computer simulations with Gazebo showed that the collision avoidance system could handle static and dynamic obstacles, with the condition that such dynamic obstacles were vessels with an AIS system integrated. It was demonstrated that the algorithm was capable of detecting the respective rule to follow and thus proceed with a new course which would lead to avoid collision.
Navegação autónoma tem sido desenvolvida e apresentada tanto para a terra como ar. No entanto, autonomia para veículos de superfície marítima tem provado algumas dificuldades. Para desenvolver um veículo autónomo de superfície aquático (ASV), é necessário um sistema de orientação, navegação e controlo (GNC) totalmente operacional. Esta tese apresenta uma parte deste sistema GNC para o ASV com um enfase em algoritmos para evitar colisão, com o maior foco na deteção das regras do mar a seguir, COLREGS, e da sua aplicação.Para os algoritmos para evitar colisão, dois sub-módulos foram implementados, sendo o Dynamic Window Approach (DWA) para obstáculos estáticos, e um algoritmo que segue as regras COLREGS para situações de cruzamento de veículos, sendo definidos com perímetros de segurança. Algumas modificações foram introduzidas relativamente ao algoritmo original de DWA, de modo a melhor responder às condições apresentadas, como um reset da variável de obstáculos, quando estes se encontram fora do perímetro interno, de modo a reduzir o esforço computacional requerido. O algoritmo que segue as regras COLREGS implementado, é capaz de detetar qual a regra a seguir e gera o novo conjunto de orientações e velocidades de modo a evitar colisão e cumprir as regras do mar. Sensores, como um IMU e um sistema GNSS, são responsáveis pela representação das posições e estados do veículo, em que por outro lado, o Lidar e um sistema AIS, são responsáveis pela representação dos obstáculos e seus atributos. ROS foi introduzido como o middleware para o ASV, o que evita a necessidade de desenvolver código para muitos aspetos do controlo do veículo. As simulações realizadas no Gazebo demonstraram que o sistema de evitar colisão consegue dar resposta a obstáculos estáticos e dinâmicos, na condição que os obstáculos dinâmicos sejam veículos com sistemas AIS integrados. Foi demonstrado que este algoritmo é capaz de detetar a respetiva regra a seguir e proceder com uma nova trajetória de modo a evitar colisão.
Rosa, Miguel da Fonseca. "Autonomous Surface Vehicle based docking for an Autonomous Underwater Vehicle." Master's thesis, 2017. https://repositorio-aberto.up.pt/handle/10216/106731.
Повний текст джерелаRosa, Miguel da Fonseca. "Autonomous Surface Vehicle based docking for an Autonomous Underwater Vehicle." Dissertação, 2017. https://repositorio-aberto.up.pt/handle/10216/106731.
Повний текст джерелаLin, Ni-Ching, and 林倪敬. "Autonomous Surface Vehicle for Maritime RobotX Challenge." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/df77ar.
Повний текст джерела國立交通大學
電控工程研究所
107
Robotic software and hardware systems of autonomous surface vehicles have been developed in transportation, military, and ocean researches for decades. Motivated from marine robot challenge call RobotX in Hawaii in December 2018, we proposed a surface vehicle with the designs of perception and propulsion systems for various tasks, such as obstacle avoidance, entrance, and exit gate. The MOOS-IvP and ROS are used to integrate hardware and software. This work aims to develop essential functionalities of autonomous navigation, from simulation (Gazebo) to real-world water/ocean environments. In Experiment 1 we evaluate how the vehicle executes 5 pre-defined desired trajectories in Gazebo with different noise settings. In real environment, we evaluate the basic capabilities about velocity and acceleration in Experiment 2. We compared two obstacle avoidance approaches in navigating from point A to B, and show the trade-off of safety (minimum distances from obstacles) and efficiency (the time from A to B). Some of the work will be used for the Team NCTU participations of the RobotX competition in Hawaii in 2018.
Hudson, Jonathan. "Adaptive Path Planning for an Autonomous Marine Vehicle Performing Cooperative Navigation for Autonomous Underwater Vehicle." 2012. http://hdl.handle.net/10222/14740.
Повний текст джерелаOliveira, Luís Alberto Silva. "Hydrodynamic Analysis and Optimization of an Autonomous Surface Vehicle." Master's thesis, 2018. http://hdl.handle.net/10400.6/8950.
Повний текст джерелаOs veículos marítimos não tripulados são ferramentas que têm sido desenvolvidas para explorar oceanos, rios, lagos e reservatórios. Estas ferramentas são essenciais para entender completamente o desconhecido mundo marítimo, uma vez que estas têm custos operacionais relativamente baixos e podem realizar variadíssimas investigações. As principais aplicações podem ser divididas em diferentes tipos de operações, como medições oceanográficas e de atmosfera. Uma dessas ferramentas é chamada de Veículo Autónomo de Superfície (ASV), que, como o nome indica, são embarcações autónomas que operam à superfície da água. Nesta dissertação, são estudadas diferentes tipos de geometrias para um ASV batimétrico da próxima geração. As duas primeiras são geometrias mais convencionais, um casco com um fundo plano e uma híbrida. A última, é um novo tipo que recentemente ganhou reconhecimento: uma geometria Small-Waterplane-Area Twin-Hull (SWATH). Esta, consiste num corpo axissimétrico, dois pequenos braços que separam o corpo da carga útil, um nariz elíptico e uma cauda cónica. Todas as geometrias foram projetadas tendo em conta as melhores gamas de relações empíricas/ analíticas, préviamente estudadas por outros autores. [...]
"Coordinated Navigation and Localization of an Autonomous Underwater Vehicle Using an Autonomous Surface Vehicle in the OpenUAV Simulation Framework." Master's thesis, 2020. http://hdl.handle.net/2286/R.I.62789.
Повний текст джерелаDissertation/Thesis
Masters Thesis Computer Science 2020
Sousa, José Pedro Martins Pires e. "Guidance of an Autonomous Surface Vehicle for Underwater Navigation Aid." Master's thesis, 2018. https://repositorio-aberto.up.pt/handle/10216/114120.
Повний текст джерелаSousa, José Pedro Martins Pires e. "Guidance of an Autonomous Surface Vehicle for Underwater Navigation Aid." Dissertação, 2018. https://repositorio-aberto.up.pt/handle/10216/114120.
Повний текст джерела"A Real-Time Vision System for a Semi-Autonomous Surface Vehicle." Master's thesis, 2014. http://hdl.handle.net/2286/R.I.25961.
Повний текст джерелаDissertation/Thesis
Masters Thesis Computer Science 2014
Huang, Yen-Hsiang, and 黃彥翔. "Study of The Passive Acoustic Monitoring System on Autonomous Surface Vehicle." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/5p2x22.
Повний текст джерела國立臺灣大學
工程科學及海洋工程學研究所
107
Due to the potential of the offshore wind energy in the Taiwan Strait, the development of the offshore wind farm is cost-effective. As the green energy concept growing, Taiwan are actively promoting the project “Thousand Wind Turbines” from 2012. Up to now, there are two mono-pile foundation wind turbines completed in 2016. The objective is to build up to 800 offshore wind turbines, and 450 onshore wind turbines before 2030. However, the expected develop area for potential offshore wind farms has overlapped with the habitat of the Sousa chinensis (also called Indo-Pacific Humpback Dolphin or Chinese White Dolphin). The impact noise from the pile driving process have shown to cause Temporary Threshold Shift (TTS) even Permanent Threshold Shift (PTS) to marine mammals at specific range from pile driving spot. Furthermore, out of the PTS and TTS range, noises from the construction are still high enough to disturb and even change the behavior of marine mammals. As a result, to know if there are dolphins in the construction area is the most important. This paper provides a process for checking if there are dolphin in the specific area and using unmanned surface vehicle to track the source and find the area they are. This process has 4 main parts, including real-time dolphin whistle detection, real-time shore side monitoring system, underwater acoustic source localization and source tracking behavior of the surface vehicle. This thesis will go into the details of those parts.
Rosendo, Michael Neto. "Enhancing the Tri-Dimensional Awareness of an Autonomous Surface Vehicle through Machine Learning Algorithms." Master's thesis, 2022. https://hdl.handle.net/10216/140752.
Повний текст джерела