Towards a System Architecture for Recognizing Domestic Activity by Leveraging a Naturalistic Human Activity Model - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Towards a System Architecture for Recognizing Domestic Activity by Leveraging a Naturalistic Human Activity Model

Michele Dominici
  • Fonction : Auteur
  • PersonId : 904148
Myriam Fréjus
Julien Guibourdenche
  • Fonction : Auteur
Frédéric Weis
  • Fonction : Auteur
  • PersonId : 870764

Résumé

Existing activity recognition approaches in the smart home domain suffer from poor human activity models. Combining expertise from cognitive ergonomics and ubiquitous computing, we discuss the hard technical challenges to address when leveraging a realistic model of human activity. We present the architecture of a prototype smart home system that we are developing and show the gap that exists between our current capabilities in terms of contextual-knowledge extraction and the complexity of the targeted activity recognition. To fill this gap, we propose and discuss the integration of PHATT, an existing algorithm for plan recognition, into our system in order to mine additional information from the dynamics of context.

Domaines

Autre [cs.OH]
Fichier non déposé

Dates et versions

hal-00702164 , version 1 (29-05-2012)

Identifiants

  • HAL Id : hal-00702164 , version 1

Citer

Michele Dominici, Myriam Fréjus, Julien Guibourdenche, Bastien Pietropaoli, Frédéric Weis. Towards a System Architecture for Recognizing Domestic Activity by Leveraging a Naturalistic Human Activity Model. GAPREC 2011 : Workshop on Goal, Activity and Plan Recognition (Gaprec) at the International Conference on Automated Planning and Scheduling (ICAPS), Jun 2011, Freiburg, Germany. ⟨hal-00702164⟩
219 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More