In recent years several architectures have been proposed to learn embodied agents complex self-awareness models. In this paper, dynamic incremental self-awareness (SA) models are proposed that allow experiences done by an agent to be modeled in a hierarchical fashion, starting from more simple situations to more structured ones. Each situation is learned from subsets of private agent perception data as a model capable to predict normal behaviors and detect abnormalities. Hierarchical SA models have been already proposed using low dimensional sensorial inputs. In this work, a hierarchical model is introduced by means of a cross-modal Generative Adversarial Networks (GANs) processing high dimensional visual data. Different levels of the GANs are detected in a self-supervised manner using GANs discriminators decision boundaries. Real experiments on semi-autonomous ground vehicles are presented.

HIERARCHY OF GANS FOR LEARNING EMBODIED SELF-AWARENESS MODEL

RAVANBAKHSH, SAYYED MAHDYAR;Baydoun, M;Campo, D;Marcenaro, L;Regazzoni, C. S.
2018-01-01

Abstract

In recent years several architectures have been proposed to learn embodied agents complex self-awareness models. In this paper, dynamic incremental self-awareness (SA) models are proposed that allow experiences done by an agent to be modeled in a hierarchical fashion, starting from more simple situations to more structured ones. Each situation is learned from subsets of private agent perception data as a model capable to predict normal behaviors and detect abnormalities. Hierarchical SA models have been already proposed using low dimensional sensorial inputs. In this work, a hierarchical model is introduced by means of a cross-modal Generative Adversarial Networks (GANs) processing high dimensional visual data. Different levels of the GANs are detected in a self-supervised manner using GANs discriminators decision boundaries. Real experiments on semi-autonomous ground vehicles are presented.
2018
978-147997061-2
File in questo prodotto:
File Dimensione Formato  
Hierarchy of Gans for Learning Embodied Self-Awareness Model ArXiv version.pdf

accesso chiuso

Descrizione: ArXiv version of main article
Tipologia: Documento in Pre-print
Dimensione 808.8 kB
Formato Adobe PDF
808.8 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/961212
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 6
social impact