Advanced Search

Large-area visually augmented navigation for autonomous underwater vehicles

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Hanumant Singh and John J. Leonard. en_US Eustice, Ryan M en_US
dc.contributor.other Woods Hole Oceanographic Institution. en_US 2007-10-19T21:05:35Z 2007-10-19T21:05:35Z 2005 en_US 2005 en_US
dc.description Thesis (Ph. D.)--Joint Program in Applied Ocean Science and Engineering (Massachusetts Institute of Technology, Dept. of Ocean Engineering; and the Woods Hole Oceanographic Institution), 2005. en_US
dc.description This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. en_US
dc.description Includes bibliographical references (p. 173-187). en_US
dc.description.abstract This thesis describes a vision-based, large-area, simultaneous localization and mapping (SLAM) algorithm that respects the low-overlap imagery constraints typical of autonomous underwater vehicles (AUVs) while exploiting the inertial sensor information that is routinely available on such platforms. We adopt a systems-level approach exploiting the complementary aspects of inertial sensing and visual perception from a calibrated pose-instrumented platform. This systems-level strategy yields a robust solution to underwater imaging that overcomes many of the unique challenges of a marine environment (e.g., unstructured terrain, low-overlap imagery, moving light source). Our large-area SLAM algorithm recursively incorporates relative-pose constraints using a view-based representation that exploits exact sparsity in the Gaussian canonical form. This sparsity allows for efficient O(n) update complexity in the number of images composing the view-based map by utilizing recent multilevel relaxation techniques. We show that our algorithmic formulation is inherently sparse unlike other feature-based canonical SLAM algorithms, which impose sparseness via pruning approximations. In particular, we investigate the sparsication methodology employed by sparse extended information filters (SEIFs) and offer new insight as to why, and how, its approximation can lead to inconsistencies in the estimated state errors. Lastly, we present a novel algorithm for efficiently extracting consistent marginal covariances useful for data association from the information matrix. en_US
dc.description.abstract (cont.) In summary, this thesis advances the current state-of-the-art in underwater visual navigation by demonstrating end-to-end automatic processing of the largest visually navigated dataset to date using data collected from a survey of the RMS Titanic (path length over 3 km and 3100 m² of mapped area). This accomplishment embodies the summed contributions of this thesis to several current SLAM research issues including scalability, 6 degree of freedom motion, unstructured environments, and visual perception. en_US
dc.description.statementofresponsibility by Ryan M. Eustice. en_US
dc.format.extent 187 p. en_US
dc.language.iso eng en_US
dc.publisher Massachusetts Institute of Technology en_US
dc.rights M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. en_US
dc.subject /Woods Hole Oceanographic Institution. Joint Program in Applied Ocean Science and Engineering. en_US
dc.subject Ocean Engineering. en_US
dc.subject Woods Hole Oceanographic Institution. en_US
dc.subject.lcsh Underwater imaging systems en_US
dc.subject.lcsh Underwater navigation en_US
dc.subject.lcsh Submersibles en_US
dc.title Large-area visually augmented navigation for autonomous underwater vehicles en_US
dc.type Thesis en_US Ph.D. en_US
dc.contributor.department Joint Program in Applied Ocean Science and Engineering. en_US
dc.contributor.department Massachusetts Institute of Technology. Dept. of Ocean Engineering. en_US
dc.contributor.department Woods Hole Oceanographic Institution. en_US
dc.identifier.oclc 64030824 en_US

Files in this item

Name Size Format Description
64030824-MIT.pdf 23.02Mb PDF Full printable version

This item appears in the following Collection(s)

Show simple item record