Modeling sensory-motor behaviors for social robots - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Modeling sensory-motor behaviors for social robots

Résumé

Modeling multimodal perception-action loops in face-to-face interactions is a crucial step in the process of building sensory-motor behaviors for social robots or users-aware Embodied Conversational Agents (ECA). In this paper, we compare trainable behavioral models based on sequential models (HMMs) and classifiers (SVMs and Decision Trees) inherently inappropriate to model sequential aspects. These models aim at giving pertinent perception/action skills for robots in order to generate optimal actions given the perceived actions of others and joint goals. We applied these models to parallel speech and gaze data collected from interacting dyads. The challenge was to predict the gaze of one subject given the gaze of the interlocutor and the voice activity of both. We show that Incremental Discrete HMM (IDHMM) generally outperforms classifiers and that injecting input context in the modeling process significantly improves the performances of all algorithms
Fichier non déposé

Dates et versions

hal-01527421 , version 1 (24-05-2017)

Identifiants

  • HAL Id : hal-01527421 , version 1

Citer

Alaeddine Mihoub, Gérard Bailly, Christian Wolf. Modeling sensory-motor behaviors for social robots. WACAI 2014 - Workshop Affect, Compagnon Artificiel, Interaction, Jun 2014, Rouen, France. ⟨hal-01527421⟩
191 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More