Discovering and Manipulating Affordances

Abstract : Reasoning jointly on perception and action requires to interpret the scene in terms of the agent's own potential capabilities. We propose a Bayesian architecture for learning sensorimotor representations from the interaction between perception, action, and salient changes generated by robot actions. This connects these three elements in a common representation: affordances. In this paper, we are working towards a richer representation and formalization of affordances. Current experimental analysis shows the qualitative and quantitative aspects of affordances. In addition, our formalization motivates several experiments for exploring hypothetical operations between learned affordances. In particular, we infer affordances of composite objects, based on prior knowledge on the affordances of the elementary objects.
Type de document :
Communication dans un congrès
International Symposium on Experimental Robotics (ISER 2016), Oct 2016, Tokyo, Japan. 2016, 2016 International Symposium on Experimental Robotics. 〈http://www.iser2016.org/〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01391427
Contributeur : Mihai Andries <>
Soumis le : jeudi 3 novembre 2016 - 12:13:38
Dernière modification le : vendredi 31 août 2018 - 09:13:02
Document(s) archivé(s) le : samedi 4 février 2017 - 13:16:10

Fichier

finaliser2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01391427, version 1

Collections

Citation

Omar Chavez-Garcia, Mihai Andries, Pierre Luce-Vayrac, Raja Chatila. Discovering and Manipulating Affordances. International Symposium on Experimental Robotics (ISER 2016), Oct 2016, Tokyo, Japan. 2016, 2016 International Symposium on Experimental Robotics. 〈http://www.iser2016.org/〉. 〈hal-01391427〉

Partager

Métriques

Consultations de la notice

177

Téléchargements de fichiers

217