CaltechAUTHORS
  A Caltech Library Service

Dense Map Inference with User-Defined Priors: From Priorlets to Scan Eigenvariations

de la Puente, Paloma and Censi, Andrea (2012) Dense Map Inference with User-Defined Priors: From Priorlets to Scan Eigenvariations. In: Spatial Cognition VIII. Lecture Notes in Computer Science. No.7463. Springer , Berlin, pp. 94-113. ISBN 978-3-642-32731-5. https://resolver.caltech.edu/CaltechAUTHORS:20200520-111908977

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200520-111908977

Abstract

When mapping is formulated in a Bayesian framework, the need of specifying a prior for the environment arises naturally. However, so far, the use of a particular structure prior has been coupled to working with a particular representation. We describe a system that supports inference with multiple priors while keeping the same dense representation. The priors are rigorously described by the user in a domain-specific language. Even though we work very close to the measurement space, we are able to represent structure constraints with the same expressivity as methods based on geometric primitives. This approach allows the intrinsic degrees of freedom of the environment’s shape to be recovered. Experiments with simulated and real data sets will be presented.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/978-3-642-32732-2_6DOIArticle
https://rdcu.be/b4iHyPublisherFree ReadCube access
https://resolver.caltech.edu/CaltechCDSTR:2011.002Related ItemTechnical Report
ORCID:
AuthorORCID
Censi, Andrea0000-0001-5162-0398
Additional Information:© 2012 Springer-Verlag Berlin Heidelberg.
Subject Keywords:Penalty Function; Prior Constraint; Inference Engine; Unconstrained Optimization Problem; Consecutive Point
Series Name:Lecture Notes in Computer Science
Issue or Number:7463
Record Number:CaltechAUTHORS:20200520-111908977
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200520-111908977
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103355
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:20 May 2020 18:41
Last Modified:20 May 2020 18:41

Repository Staff Only: item control page