Estimación de grupos conversacionales empleando cámaras 3D y aprendizaje automático para su aplicación a robótica social
- Delgado Chaves, Diego 1
- Praena Rodríguez, Jose Ángel 1
- Caballero, Fernando 2
- Gómez, Randy 3
- Merino, Luis 1
-
1
Universidad Pablo de Olavide
info
-
2
Universidad de Sevilla
info
-
3
Honda Research Institute Europe
info
Honda Research Institute Europe
Offenbach, Alemania
- Ramón Costa Castelló (coord.)
- Manuel Gil Ortega (coord.)
- Óscar Reinoso García (coord.)
- Luis Enrique Montano Gella (coord.)
- Carlos Vilas Fernández (coord.)
- Elisabet Estévez Estévez (coord.)
- Eduardo Rocón de Lima (coord.)
- David Muñoz de la Peña Sequedo (coord.)
- José Manuel Andújar Márquez (coord.)
- Luis Payá Castelló (coord.)
- Alejandro Mosteo Chagoyen (coord.)
- Raúl Marín Prades (coord.)
- Vanesa Loureiro-Vázquez (coord.)
- Pedro Jesús Cabrera Santana (coord.)
Éditorial: Servizo de Publicacións ; Universidade da Coruña
ISBN: 9788497498609
Année de publication: 2023
Pages: 575-580
Congreso: Jornadas de Automática (44. 2023. Zaragoza)
Type: Communication dans un congrès
Résumé
This study is situated within the domain of social robotics, specifically investigating the detection of F-Formations, spatial structures that emerge during human group interaction. The article presents perception system to detect conversational groups. The system can be used to improve the abilities of robots to interpret social contexts. The article presents a study of the capacity of various machine learning algorithms for the estimation of F-Formations from the 3D skeletons of the participants as obtained by a 3D Azure Kinect camera. As a result, a ROS module capable of recognizing groups of people has been developed.