Toward lifelong visual localization and mapping
Citable URI
https://hdl.handle.net/1912/5980DOI
10.1575/1912/5980Keyword
Robotics; Underwater navigationAbstract
Mobile robotic systems operating over long durations require algorithms that are
robust and scale efficiently over time as sensor information is continually collected.
For mobile robots one of the fundamental problems is navigation; which requires the
robot to have a map of its environment, so it can plan its path and execute it. Having
the robot use its perception sensors to do simultaneous localization and mapping
(SLAM) is beneficial for a fully autonomous system. Extending the time horizon of
operations poses problems to current SLAM algorithms, both in terms of robustness
and temporal scalability. To address this problem we propose a reduced pose graph
model that significantly reduces the complexity of the full pose graph model. Additionally
we develop a SLAM system using two different sensor modalities: imaging
sonars for underwater navigation and vision based SLAM for terrestrial applications.
Underwater navigation is one application domain that benefits from SLAM, where
access to a global positioning system (GPS) is not possible. In this thesis we present
SLAM systems for two underwater applications. First, we describe our implementation
of real-time imaging-sonar aided navigation applied to in-situ autonomous ship
hull inspection using the hovering autonomous underwater vehicle (HAUV). In addition
we present an architecture that enables the fusion of information from both
a sonar and a camera system. The system is evaluated using data collected during
experiments on SS Curtiss and USCGC Seneca. Second, we develop a feature-based
navigation system supporting multi-session mapping, and provide an algorithm for
re-localizing the vehicle between missions. In addition we present a method for managing
the complexity of the estimation problem as new information is received. The
system is demonstrated using data collected with a REMUS vehicle equipped with a BlueView forward-looking sonar.
The model we use for mapping builds on the pose graph representation which has
been shown to be an efficient and accurate approach to SLAM. One of the problems
with the pose graph formulation is that the state space continuously grows as more
information is acquired. To address this problem we propose the reduced pose graph
(RPG) model which partitions the space to be mapped and uses the partitions to reduce
the number of poses used for estimation. To evaluate our approach, we present
results using an online binocular and RGB-Depth visual SLAM system that uses
place recognition both for robustness and multi-session operation. Additionally, to
enable large-scale indoor mapping, our system automatically detects elevator rides
based on accelerometer data. We demonstrate long-term mapping using approximately
nine hours of data collected in the MIT Stata Center over the course of six
months. Ground truth, derived by aligning laser scans to existing
floor plans, is used
to evaluate the global accuracy of the system. Our results illustrate the capability of
our visual SLAM system to map a large scale environment over an extended period
of time.
Description
Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution June 2013
Suggested Citation
Thesis: Johannsson, Hordur, "Toward lifelong visual localization and mapping", 2013-06, DOI:10.1575/1912/5980, https://hdl.handle.net/1912/5980Related items
Showing items related by title, author, creator and subject.
-
Seismic constraints on shallow crustal processes at the East Pacific Rise
Christeson, Gail L. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1994-02)This thesis is concerned with understanding how oceanic crust is emplaced at mid-ocean ridges. The emphasis is upon fast-spreading ridges, and the use of seismic techniques to image the uppermost several hundred meters ... -
When an eddy encounters shelf-slope topography
Cherian, Deepak A. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2016-09)Eddies in the ocean move westwards. Those shed by western boundary currents must then interact with continental shelf-slope topography at the western boundary. The presence of other eddies and mean lows complicates this ... -
Biological-physical interactions on Georges Bank : plankton transport and population dynamics of the ocean quahog, Arctica islandica
Lewis, Craig V. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1997-06)Advective losses of bank water during winter because of strong wind forcing were hypothesized to be a significant factor limiting recruitment of Georges Bank cormnunities. This hypothesis was examined using biological-physical ...