Geometric reasoning under uncertainty for map-basedlocalization

Authors:
William B. Thompson;Carolyn M. Valiquette;Bonnie H. Bennett;Karen T. Sutherland
Affiliations:
Department of Computer Science, University of Utah, U.S.A.;Department of Computer Science, University of Utah, U.S.A.;Graduate Programs in Software, University of St. Thomas, St. Paul, MN, U.S.A.;Department of Computer Science, Augsburg College, Minneapolis, MN, U.S.A.
Venue:
Spatial Cognition and Computation
Year:
1999

Citing 6
Cited 1

Navigation and mapping in large-scale space

AI Magazine
Sensor fusion in certainty grids for mobile robots

AI Magazine
Qualitative navigation for mobile robots

Artificial Intelligence
Object recognition by computer: the role of geometric constraints

Object recognition by computer: the role of geometric constraints
Problem-solving approach to the localization problem

Problem-solving approach to the localization problem
Algorithms for Hierarchical Spatial Reasoning

Geoinformatica

Place learning in humans: The role of distance and direction information

Spatial Cognition and Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Map-based navigation in outdoor terrain lacking man-made structuresorother highly distinctive landmarks can produce severe localizationproblems. This paper presents an approach to navigation whichimplements high level geometric reasoning and matching strategiesbasedon those used by skilled human navigators. This approach, which isdemonstrated on a real example involving imagery of mountainousterrain obtained with a video camera and USGS map data, is designed toavoidmany of the pitfalls occurring when an attempt is made to navigatebymodeling the environment mathematically. It exploits featureattributeswhich cannot be easily expressed quantitatively but are central tothesuccessful human navigation process.