Experiments on vision guided docking of an autonomous underwater vehicle using one camera

Park, Jin-Yeong; Jun, Bong-Huan; Lee, Pan-Mook; Oh, Jun-Ho

doi:10.1016/j.oceaneng.2008.10.001

Cited by 176 publications

(76 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Las cámaras de video más usadas son del tipo CCD (Charge Coupled Device) ya que son de mayor resolución y más sensibles a la luz [33], [34]. Se selecciona teniendo en cuenta criterios como: ubicación, tipo de transmisión del video, tamaño, resolución, tipo de lente, zoom, alimentación, protocolos ing.cienc., vol.…”

Section: Sistema De Visiónunclassified

Una arquitectura para el diseño conceptual de vehículos para exploración subacuática

et al. 2015

View full text Add to dashboard Cite

ResumenEste artículo presenta una arquitectura para el diseño conceptual de vehícu-los subacuáticos operados remotamente (ROV). La arquitectura propuesta está basada en una revisión extensa de literatura y la experiencia obtenida durante 20 años con el desarrollo de tres sistemas ROV diseñados para misiones de inspección subacuática. El ROV se divide en cinco subsistemas: vehículo, estación en superficie, interfaz superficie/vehículo, sistema de control y software. Para cada uno de estos subsistemas se definen funciones y tareas, se enuncian componentes, se establecen interrelaciones con otros subsistemas y se plantean alternativas comúnmente utilizadas. La delimitación de los subsistemas desde el diseño conceptual busca evitar problemas en las fases avanzadas del desarrollo del sistema robótico de exploración.Palabras clave: diseño de ROV; exploración subacuática; sistema robótico de exploración; vehículos submarinos autónomos

show abstract

Section: Sistema De Visiónunclassified

Una arquitectura para el diseño conceptual de vehículos para exploración subacuática

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Often underwater craft that explores the ocean floor, e.g., may only recharge their batteries and transmit data when docked-either to a seabed station or an ASV. Murarka et al [31] and Park et al [35] both use structured light for docking their autonomous underwater vehicle (AUV). The light serves as a reference signal which helps the robots approach the docking target.…”

Section: Related Workmentioning

confidence: 99%

Toward autonomous robotic containment booms: visual servoing for robust inter-vehicle docking of surface vehicles

Kim

Lee

Yang

et al. 2011

Intel Serv Robotics

View full text Add to dashboard Cite

Inter-vehicle docking is the problem of coordinating multiple robots to actively form and maintain physical contact. It is an important capability for autonomous surface vehicles (ASVs) and is an essential part of a wide class of missions. This article considers one such mission: the emergency response and environmental protection problem of containing a floating pollutant. We propose a solution in which multiple robots autonomously navigate so as to surround the surface matter. Before doing so, the robots dock with one another to secure specialized attachments designed to ensnare the contaminant. We describe the prototypical physical robot system developed to perform this task, and we detail the system architecture, sensing and computational hardware, control system, and visual processing pipeline. While employing multiple ASVs maximizes spatial reconfigurability, it depends on the inter-robot docking capabilities being particularly reliable. But achieving robust docking is Electronic supplementary material The online version of this article (a significant technical challenge because the water continually induces external disturbances on the control system. These disturbances are non-stationary and almost impossible to predict for unknown environments. Our system relies primarily on visual servoing within a control framework in which a variety of sensors are fused. Accurate disturbance measurements are obtained through traditional sensor modeling and filtering techniques. As the environment is a priori unknown, varies from trial to trial, and has proven difficult to model, we apply a model-free reinforcement learning algorithm, SARSA(λ), along with specialized initial conditions which ensure stable operation, and an exploration guidance approach that increases the speed of convergence. We adopt a two-loop control scheme for visual servoing to successfully make use of feature descriptors with various (and variable) computational times. We demonstrate this approach to the docking problem with autonomous ground vehicles and ASVs. The results from several situations are compared, showing that disturbance rejection coupled with SARSA(λ) is an effective approach.

show abstract

“…At present, aircraft types recognition methods include: image matching, neural network recognition [1], invariant moment (or boundary moment) [2][3], Fourier descriptor [4][5] or geometric in-variants [6] .…”

Section: Introductionmentioning

confidence: 99%

Adaptive Weighted Morphology Tree Classifier for Aircraft Type Recognition

Liu¹,

Guo²

2017

Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)

View full text Add to dashboard Cite

Aircraft type recognition is a problem and key factor of safe docking of aircraft in airport auto-docking guide system. Based on adaptive weighted morphology tree classifier algorithm, it is approved for aircraft type recognition to solve the key issues to docking guide, useing image analysis and recognition technology to complete the type discrimination, so as to overcome the shortcomings of the aircraft in the whole range of berth travel and improve the speed and reliability of the search. According to the feature of target size and feature change during the process of aircraft movement, the adaptive weight morphological algorithm extracts the invariant features, which can solve the problem of feature transform of aircraft type recognition. The experimental results indicate that the effectiveness of the current recognition system is given. The system provides a good performance in aircraft recognition and offers better robustness against noise and poor image quality, which can satisfy the auto-docking system requirements of high precision, rapid speed and stabilization.

show abstract

Experiments on vision guided docking of an autonomous underwater vehicle using one camera

Cited by 176 publications

References 8 publications

Una arquitectura para el diseño conceptual de vehículos para exploración subacuática

Una arquitectura para el diseño conceptual de vehículos para exploración subacuática

Toward autonomous robotic containment booms: visual servoing for robust inter-vehicle docking of surface vehicles

Adaptive Weighted Morphology Tree Classifier for Aircraft Type Recognition

Contact Info

Product

Resources

About