Computer Vision Applications in the Navigation of Unmanned Underwater Vehicles

Horgan, Jonathan; Toal, Daniel

doi:10.5772/6703

Cited by 12 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The third approach is a sensor based state estimator based only on onboard sensors, possibly aided by computer vision using visual beacons on the seafloor structure. Examples of state estimators for ROV are found in [6], [11] and [12], and vision based navigation systems in [13].…”

Section: B State Estimation Algorithmsmentioning

confidence: 99%

Positioning of subsea modules using an automated ROV

Henriksen

Gjersvik

Thorkildsen³

2015

OCEANS 2015 - Genova

View full text Add to dashboard Cite

When modules are installed on the seafloor they often need to interface with existing equipment. The modules will therefore need to be positioned and oriented precise. Today this is done by using guide-wires, or by using a manually controlled ROV. Both these methods are costly and time consuming. This paper propose a system for automating the ROV. We believe that such system will make installations of modules faster and easier. This will make installations less expensive as vessel time is a major factor of the installation cost.The paper describes a simulation model for a system consisting of a module hanging in a wire and an ROV. Further different control strategies, state estimators and applicable sensor technology are discussed.

show abstract

Section: B State Estimation Algorithmsmentioning

confidence: 99%

Positioning of subsea modules using an automated ROV

Henriksen

Gjersvik

Thorkildsen³

2015

OCEANS 2015 - Genova

View full text Add to dashboard Cite

show abstract

“…Particularly, sequential images captured by a monocular camera attached in the frontal part of a vehicle helps it to make decisions for autonomous navigation. This area has a wide significance for many problems in robotics such as SLAM (Simultaneous Localization and Mapping), target tracking, vision-based control, 3D-view mapping and place recognition (see general state-of-the-art references such as [1][2][3]). Even when the SLAM problem is stated in a complete and general form, particular problems in the exploration of unknown environments are not sufficiently dealt with, above all regarding the wide diversity of applications in subaquatic robotics and the tough accessibility to the oceanic world.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast in subaquatic applications, this issue will demand a huge care with respect to many aspects, among them security, robustness and long-term performance [3]. Clearly all these aspects point out the success of an autonomous vehicle to return by its own means to the source after a mission is concluded, among other things.…”

Section: Introductionmentioning

confidence: 99%

A Node-Based Method for SLAM Navigation in Self-Similar Underwater Environments: A Case Study

Trabes

Jordan

2017

Robotics

View full text Add to dashboard Cite

This work deals with the development of a node-based monocular visual methodology for autonomous vehicle navigation which has the goal of exploring unknown regions of the sea bottom with a posterior safe revisiting of them. The work accentuates characteristics of the seabed like self-similarity and backscattering. In a stepwise fashion, a visual guidance system constructs a shape similar to a narrow corridor by optimally creating a heading function on the basis of keypoints threads, which ensures future revisits. The corridor is composed of nodes and paths in between. Each path is composed of a visual-odometry-based trail which is generated in feature-poor environments, in combination with a feature-based trail which emerges in feature-rich regions. A probabilistic analysis of the uncertainties and their impact in the success rate on loop closings is carried out. We work out two case studies, the first employing an ad-hoc benchmark and the second a series of experiments in the real world. From here qualitative conclusions can be drawn out that enable us to anticipate potential applications of the approach in the field of autonomous navigation underwater.

show abstract

“…To increase accuracy of UV stabilization in desired space point additional automatic closed-loop systems for all linear and angular movement of this vehicle should be used. Said closedloop systems can use high-precision navigation systems [4,5] and also onboard gyroscopes.…”

Section: Introductionmentioning

confidence: 99%

System of automatic stabilization of underwater vehicle in hang mode with working multilink manipulator

Filaretov

Konoplin

2015

2015 International Conference on Computer, Control, Informatics and Its Applications (IC3INA)

View full text Add to dashboard Cite

In this work the synthesis method of combined closed-loop automatic system of underwater vehicle position and orientation stabilization in hang mode (station keeping regime) is described. Underwater vehicle invariance to external influences created by working underwater manipulator is provided by thrusts of vehicle screws. These thrusts are proportional to said external influences calculated in real time scale. For precise calculation of these influences the recursive algorithm for solving of inverse problem of underwater manipulator dynamic was developed. Presented algorithm allows to take into account all features of viscous environment influences on manipulator links committing random movements at high speed. To increase accuracy of underwater vehicle stabilization additional automatic closed-loop systems for all linear and angular movement of this vehicle was synthesized. Said systems can use data obtained from high-precision navigation onboard sensors and devices.

show abstract

Computer Vision Applications in the Navigation of Unmanned Underwater Vehicles

Cited by 12 publications

References 56 publications

Positioning of subsea modules using an automated ROV

Positioning of subsea modules using an automated ROV

A Node-Based Method for SLAM Navigation in Self-Similar Underwater Environments: A Case Study

System of automatic stabilization of underwater vehicle in hang mode with working multilink manipulator

Contact Info

Product

Resources

About