Interactive learning of visual topological navigation

Abstract : We present a topological navigation system that is able to visually recognize the different rooms of an apartment and guide a robot between them. Specifically tailored for small entertainment robots, the system relies on vision only and learns its navigation capabilities incrementally by interacting with a user. This continuous learning strategy makes the system particularly adaptable to environmental lighting and structure modifications. From the computer vision point of view, the system uses a purely appearance-based image representation called bag of visual words, without any metric information. This representation was adapted to the incremental context of robotics and supplemented by active perception to enhance performances. Empirical validation on real robots and on the publicly available INDECS image database are presented.
Type de document :
Communication dans un congrès
International Conference on Intelligent Robots and Systems (IROS), 2008, France. pp.248 - 254, 2008, 〈10.1109/IROS.2008.4650681〉
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal-ensta.archives-ouvertes.fr/hal-00641356
Contributeur : David Filliat <>
Soumis le : mardi 15 novembre 2011 - 15:03:55
Dernière modification le : mercredi 29 novembre 2017 - 15:50:50
Document(s) archivé(s) le : vendredi 16 novembre 2012 - 10:56:43

Fichier

Filliat_IROS08.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

David Filliat. Interactive learning of visual topological navigation. International Conference on Intelligent Robots and Systems (IROS), 2008, France. pp.248 - 254, 2008, 〈10.1109/IROS.2008.4650681〉. 〈hal-00641356〉

Partager

Métriques

Consultations de la notice

229

Téléchargements de fichiers

375