Early-Stage Vision of Composite Scenes for Spatial Learning and Navigation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Early-Stage Vision of Composite Scenes for Spatial Learning and Navigation

Résumé

Developmental theories suggest that cognitive agents develop through an initial sensorimotor stage during which they learn sequential and spatial regularities. We implemented these views in a computer simulation. Following its intrinsic motivations, the agent autonomously learns sensorimotor contingencies and discovers permanent landmarks by which to navigate in the environment. Besides illustrating developmental theories, this model suggests new ways to implement vision and navigation in artificial systems. Specifically, we coupled a sequence learning mechanism with a visual system capable of interpreting composite visual scenes by inhibiting items that are irrelevant to the agent’s current motivational state.
Fichier principal
Vignette du fichier
Georgeon2011-ICDL.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01354453 , version 1 (20-10-2016)

Identifiants

Citer

Olivier L. Georgeon, James Marshall, Pierre-Yves Ronot. Early-Stage Vision of Composite Scenes for Spatial Learning and Navigation. First Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Aug 2011, Frankfurt am Main, Germany. pp.224-229, ⟨10.1109/DEVLRN.2011.6037348⟩. ⟨hal-01354453⟩
247 Consultations
84 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More