A Natural Feature Representation for Unstructured Environments

Fabio Tozeto Ramos, Kumar, Suresh, Upcroft, Ben and Durrant-Whyte, Hugh (2008) A Natural Feature Representation for Unstructured Environments. IEEE Transactions on Robotics, 24 6: 1329-1340.


Author Fabio Tozeto Ramos
Kumar, Suresh
Upcroft, Ben
Durrant-Whyte, Hugh
Title A Natural Feature Representation for Unstructured Environments
Journal name IEEE Transactions on Robotics   Check publisher's open access policy
ISSN 1552-3098
Publication date 2008
Year available 2008
Sub-type Article (original research)
DOI 10.1109/TRO.2008.2007933
Volume 24
Issue 6
Start page 1329
End page 1340
Total pages 12
Editor R. A. Volz
Place of publication United States
Publisher IEEE
Collection year 2009
Language eng
Subject C1
0913 Mechanical Engineering
9699 Other Environment
Abstract This paper addresses the long-standing problem of feature representation in the natural world for autonomous navigation systems. The proposed representation combines Isomap, which is a nonlinear manifold learning algorithm, with expectation maximization, which is a statistical learning scheme. The representation is computed off-line and results in a compact, nonlinear, non-Gaussian sensor likelihood model. This model can be easily integrated into estimation algorithms for navigation and tracking. The compactness of the model makes it especially attractive for deployment in decentralized sensor networks. Real sensory data from unstructured terrestrial and underwater environments are used to demonstrate the versatility of the computed likelihood model. The experimental results show that this approach can provide consistent models of natural environments to facilitate complex visual tracking and data-association problems.
Keyword Dimensionality reduction
feature extraction
field robotics
Isomap
probabilistic representation
Q-Index Code C1
Q-Index Status Confirmed Code

Document type: Journal Article
Sub-type: Article (original research)
Collections: 2009 Higher Education Research Data Collection
School of Mechanical & Mining Engineering Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 2 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Access Statistics: 47 Abstract Views  -  Detailed Statistics
Created: Thu, 09 Apr 2009, 11:56:07 EST by Gail Smith on behalf of School of Mechanical and Mining Engineering