Ankuj Arora - Action Model Learning for Socio-Communicative Human-Robot Interaction

08:00
Friday
8
Dec
2017
Organized by: 
Ankuj Arora
Speaker: 
Ankuj Arora
Teams: 

 

Jury :

  • M. Dominique Duhaut, professeur des Universités, Université Bretagne-Sud, examinateur
  • M. Cédric Buche, maître de conférences, HDR, ENIB Brest, rapporteur
  • M. Alexandre Pauchet, maître de conférences, HDR, Université de Normandie, rapporteur
  • M. Samir Aknine, professeur des universités, Université Claude Bernard Lyon 1, examinateur
  • Mme. Sophie Dupuy-Chessa, professeure des universités, Université Grenoble-Alpes, examinatrice
  • M. Damien Pellier, maître de conférences, Université Grenoble-Alpes, examinateur
  • M. Amit Pandey, Chief Scientist, Softbank Robotics, invité
  • M. Marc Métivier, maître de conférences, Université Paris-Descartes, invité
  • Mme. Sylvie Pesty, professeur des universités, Université Grenoble Alpes, directrice de thèse
  • M. Humbert Fiorino, maître de conférences, Université Grenoble Alpes, co-directeur de thèse

 

Driven with the objective of rendering robots as socio-communicative, there has been a heightened interest towards researching techniques to endow robots with social skills and “commonsense” in order to render them acceptable. This “commonsense” is, however, not so common, as even a standard dialogue exchanges integrates behavioral subtleties that are difficult to codify. In such a scenario, learning the behavioral model of the robot is a promising approach. This study tries to solve the problem of learning robot behavioral models in the Automated Planning and Scheduling (APS) paradigm of Artificial Intelligence. During the course of this study, we principally introduce two symbolic and deep learning systems, by the names SPMSAT and PDeepLearn respectively, which facilitate the learning of action models, and extend the scope of these new techniques to learn robot behavioral models in a Human-Robot Interaction (HRI) scenario. The long term objective is to empower robots to communicate autonomously with humans sans the need of “wizard” intervention.