Large scale environment partitioning in mobile robotics recognition tasks

Please use this identifier to cite or link to this item:
Información del item - Informació de l'item - Item information
Title: Large scale environment partitioning in mobile robotics recognition tasks
Authors: Bonev, Boyan | Cazorla, Miguel
Research Group/s: Robot Vision Group
Center, Department or Service: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: Visual localization | Entropy | Jensen-Rényi divergence | Classifier | Particle filter
Knowledge Area: Ciencia de la Computación e Inteligencia Artificial
Issue Date: May-2010
Publisher: Red de Agentes Físicos
Citation: BONEV, Boyan; CAZORLA QUEVEDO, Miguel Ángel. “Large scale environment partitioning in mobile robotics recognition tasks”. Journal of Physical Agents. Vol. 4, No. 2 (May 2010). ISSN 1888-0258, pp. 11-18
Abstract: In this paper we present a scalable machine learning approach to mobile robots visual localization. The applicability of machine learning approaches is constrained by the complexity and size of the problem’s domain. Thus, dividing the problem becomes necessary and two essential questions arise: which partition set is optimal for the problem and how to integrate the separate results into a single solution. The novelty of this work is the use of Information Theory for partitioning high-dimensional data. In the presented experiments the domain of the problem is a large sequence of omnidirectional images, each one of them providing a high number of features. A robot which follows the same trajectory has to answer which is the most similar image from the sequence. The sequence is divided so that each partition is suitable for building a simple classifier. The partitions are established on the basis of the information divergence peaks among the images. Measuring the divergence has usually been considered unfeasible in high-dimensional data spaces. We overcome this problem by estimating the Jensen-Rényi divergence with an entropy approximation based on entropic spanning graphs. Finally, the responses of the different classifiers provide a multimodal hypothesis for each incoming image. As the robot is moving, a particle filter is used for attaining the convergence to a unimodal hypothesis.
Sponsor: This research is funded by the project DPI2009-07144 from Ministerio de Ciencia e Innovación of the Spanish Government.
URI: |
ISSN: 1888-0258
DOI: 10.14198/JoPha.2010.4.2.02
Language: eng
Type: info:eu-repo/semantics/article
Peer Review: si
Appears in Collections:Journal of Physical Agents - 2010, Vol. 4, No. 2
INV - RVG - Artículos de Revistas
INV - RoViT - Artículos de Revistas
INV - MVRLab - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
ThumbnailJoPha_4_2_02.pdf1,49 MBAdobe PDFOpen Preview

This item is licensed under a Creative Commons License Creative Commons