Зміст
Добірка наукової літератури з теми "Robots sous-marins – Navigation"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Robots sous-marins – Navigation".
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.
Дисертації з теми "Robots sous-marins – Navigation"
Sistiaga, Marc. "Navigation référencée images de terrain pour engins sous-marins." Montpellier 2, 2000. http://www.theses.fr/2000MON20103.
Повний текст джерелаBaccou, Philippe. "Navigation et positionnement sur une balise d'engins sous-marins autonomes." Montpellier 2, 2001. http://www.theses.fr/2001MON20172.
Повний текст джерелаDe, Césare Cédric. "Acquisition de mosaïques d'images complètes à l'aide d'un engin sous-marin autonome." Nice, 2009. http://www.theses.fr/2009NICE4055.
Повний текст джерелаDuring the last years, visual imagery has been more and more used in the underwater environment, as well as an help for navigation than as a tool for cartography allowing the study and survey of seafloors. These operations of survey consist principally in the establishment of maps of the seafloor on large zones (several km2). The constraints of the environment (depth, low absorption of light, etc…) impose as systematic the use of autonomous underwater vehicles (AUV), and this at an altitude close to the ground. The map (image mosaic) is then obtained by matching and fusing the recorded images. The current construction methods of large mosaics do not guarantee the overlap of these ones, leading to the possible existence of holes in the mosaics. However, this stake is high in order to allow the complete observation of the mission zone. It is in this context that we have developed our subject of research : “Acquisition of complete image mosaics with an autonomous underwater vehicle”. We develop an adaptive strategy that ensures the mosaic overlapping. We base our study on lawnmower trajectories and determine, at the end of each observed segment, the distance with the next segment. This distance depends on the robot relative positioning incertitude. This incertitude increasing with the time, the vehicle must recalculate its position frequently in order to not lose itself. The relief characteristics of the observed zone will define possible registration events, for which the vehicle will reset his positioning error. The more the textured region is, the higher the number of events is, and thus the vehicle can better position itself. The inter-track distance is then high. On the contrary, the less the region is informative, the lower the distance is. In our aim of inter-track distance optimisation, we risk to be confronted to low overlap image matching situations. The classical methods fail in such situations because they force the association between image localities (templates). We have established a method, based on Information Theory, that palliates this problem and take into account these ambiguities
Khadhraoui, Adel. "Modélisation et simulation interactive pour la navigation d'un robot sous-marin de type ROV Observer." Thesis, Université Paris-Saclay (ComUE), 2015. http://www.theses.fr/2015SACLE014/document.
Повний текст джерелаToday cross oceans can be done easily. However, it is not the same case for the seabed exploration. As this hostile and dangerous environment can be biologically rich and has exploitable resources, the man needs help in his discovery of the depths. Therefore, the intervention of underwater robots was a solution. In this context, the present manuscript deals with modeling and control of a ROV (Remotely Operated Vehicle). After identifying the different variables characterizing the fixed geometry, we study, at first, kinematics and dynamic modeling of the ROV. It is important to note that sets of inertia parameters of added mass and streaks coefficients is identified by means of the geometrical characteristics of the robot. A full nonlinear dynamic model of the submarine has been established. The second part of the thesis deals with the stabilization problem of the ROV’s model. We offer an explicit unsteady dependent control of both the state and time. A robust study of the control relative to external interference checking certain degree of homogeneity has been established. The autonomy of Rov also requires control movement along a reference path. We treated in the third part the Rov’s stability problem to ensure the tracking of a reference trajectory. These results are operated on a virtual platform, and implemented on the dedicated Virtools software for this application. To lighten the structure in terms of sensors and because of the high prices of various sensors, it is necessary to design a system called auxiliary observer who charge rebuild unmeasurable states using available information. A nonlinear observer has been proposed to the estimation of linear and non-measurable angular velocity, which will be considered as virtual sensors. These sensors will be implemented on the platform that will be used to animate the ROV in its virtual world
Sola, Yoann. "Contributions to the development of deep reinforcement learning-based controllers for AUV." Thesis, Brest, École nationale supérieure de techniques avancées Bretagne, 2021. http://www.theses.fr/2021ENTA0015.
Повний текст джерелаThe marine environment is a very hostile setting for robotics. It is strongly unstructured, very uncertain and includes a lot of external disturbances which cannot be easily predicted or modelled. In this work, we will try to control an autonomous underwater vehicle (AUV) in order to perform a waypoint tracking task, using a machine learning-based controller. Machine learning allowed to make impressive progress in a lot of different domain in the recent years, and the subfield of deep reinforcement learning managed to design several algorithms very suitable for the continuous control of dynamical systems. We chose to implement the Soft Actor-Critic (SAC) algorithm, an entropy-regularized deep reinforcement learning algorithm allowing to fulfill a learning task and to encourage the exploration of the environment simultaneously. We compared a SAC-based controller with a Proportional-Integral-Derivative (PID) controller on a waypoint tracking task and using specific performance metrics. All the tests were performed in simulation thanks to the use of the UUV Simulator. We decided to apply these two controllers to the RexROV 2, a six degrees of freedom cube-shaped remotely operated underwater vehicle (ROV) converted in an AUV. Thanks to these tests, we managed to propose several interesting contributions such as making the SAC achieve an end-to-end control of the AUV, outperforming the PID controller in terms of energy saving, and reducing the amount of information needed by the SAC algorithm. Moreover we propose a methodology for the training of deep reinforcement learning algorithms on control tasks, as well as a discussion about the absence of guidance algorithms for our end-to-end AUV controller