Merging probabilistic models of navigation: the Bayesian Map and the Superposition operator

Julien Diard 1 Pierre Bessiere 1 Emmanuel Mazer 1
1 E-MOTION - Geometry and Probability for Motion and Action
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
Abstract : This paper deals with the probabilistic modeling of space, in the context of mobile robot navigation. We define a formalism called the Bayesian Map, which allows incremental building of models, thanks to the Superposition operator, which is a formally well-defined operator. Firstly, we present a syntactic version of this operator, and secondly, a version where the previously obtained model is enriched by experimental learning. In the resulting map, locations are the conjunction of underlying possible locations, which allows for more precise localization and more complex tasks. A theoretical example validates the concept, and hints at its usefulness for realistic robotic scenarios.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00182041
Contributor : Christian Laugier <>
Submitted on : Wednesday, October 24, 2007 - 6:34:20 PM
Last modification on : Thursday, February 7, 2019 - 4:31:11 PM
Long-term archiving on : Monday, April 12, 2010 - 12:32:13 AM

File

diard05.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00182041, version 1

Collections

INRIA | UGA | IMAG

Citation

Julien Diard, Pierre Bessiere, Emmanuel Mazer. Merging probabilistic models of navigation: the Bayesian Map and the Superposition operator. Proc. of the IEEE-RSJ Int. Conf. on Intelligent Robots and Systems, 2005, Edmonton, Canada. pp.668--673. ⟨inria-00182041⟩

Share

Metrics

Record views

359

Files downloads

368