Probing the Inductive Biases of a Gaze Model for Multi-party Interaction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Probing the Inductive Biases of a Gaze Model for Multi-party Interaction

Résumé

The behavior management controls proposed for social robots are mostly designed for highly controlled scenarios. In the real world though, robots have to adapt to new situations, generalizing learned behaviors. To address this adaptation challenge, neural network models with embedding layers could be used. We present here an approach to better understand the inductive biases of our robotic gaze model. It was trained with multimodal features as inputs -- either endogenous or exogenous to the robot. Inductive biases were explored by observing feature representations in the embedding spaces. We found that the model was able to distinguish between the robot speech intentions that either request or provide information. Similarly, pairs of partners seem grouped according to their social behavior (speaking time, gaze). Finally, we checked that these groupings had a real impact on the model's performance. Driving these biases when facing new people should allow to generate adapted behavior.

Mots clés

Fichier principal
Vignette du fichier
Probing_the_Inductive_Biases_of_a_Gaze_Model_for_Multi_party_Interaction.pdf (845.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04510252 , version 1 (18-03-2024)

Identifiants

Citer

Léa Haefflinger, Frédéric Elisei, Brice Varini, Gérard Bailly. Probing the Inductive Biases of a Gaze Model for Multi-party Interaction. HRS 2024 - 2024 ACM/IEEE International Conference on Human-Robot Interaction (HRI '24), Mar 2024, Boulder, CO, United States. pp.507-511, ⟨10.1145/3610978.3640702⟩. ⟨hal-04510252⟩
0 Consultations
1 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More