IMHuS: Intelligent Multi-Human Simulator - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

IMHuS: Intelligent Multi-Human Simulator

Camino Fernández
Phani-Teja Singamaneni
Anthony Favier
Vicente Matellán
Rachid Alami

Résumé

Social robotics research requires the replicability of the experiments used to validate new technical or scientific claims. However, humans behavior is difficult to replicate. We have designed and implemented a system to simulate interactive agents that can be perceived by a robot in a robotic simulator. These agents can exhibit social behaviour in human group movement, for example, by talking face-to-face. These humans are interactive with the robot and can be perceived so that the robot can react to their behavior. The humans can be choreographed to create high-level social behaviours such as waiting for an elevator, getting in and out of it, or standing in front of a store window and moving together to the next one. The tool would provide metrics to evaluate the robot's performance in defined social situations.
Fichier principal
Vignette du fichier
IROS_2022_Workshop_IMHuS.pdf (2.94 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03865622 , version 1 (22-11-2022)

Identifiants

  • HAL Id : hal-03865622 , version 1

Citer

Olivier Hauterville, Camino Fernández, Phani-Teja Singamaneni, Anthony Favier, Vicente Matellán, et al.. IMHuS: Intelligent Multi-Human Simulator. IROS2022 Workshop: Artificial Intelligence for Social Robots Interacting with Humans in the Real World, Oct 2022, Kyoto, Japan. ⟨hal-03865622⟩
66 Consultations
63 Téléchargements

Partager

Gmail Facebook X LinkedIn More