Simulating Human-Robot Interactions for Dialogue Strategy Learning

Abstract : Many robotic projects use simulation as a faster and easier way to develop, evaluate and validate software components compared with on-board real world settings. In the human-robot interaction field, some recent works have attempted to integrate humans in the simulation loop. In this paper we investigate how such kind of robotic simulation software can be used to provide a dynamic and interactive environment to both collect a multimodal situated dialogue corpus and to perform an efficient reinforcement learning-based dialogue management optimisation procedure. Our proposition is illustrated by a preliminary experiment involving real users in a Pick-Place-Carry task for which encouraging results are obtained.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01071216
Contributor : Gregoire Milliez <>
Submitted on : Friday, October 3, 2014 - 1:56:40 PM
Last modification on : Friday, June 14, 2019 - 6:31:05 PM
Long-term archiving on : Sunday, January 4, 2015 - 10:46:36 AM

File

simulating-human-robot_3_.pdf
Files produced by the author(s)

Identifiers

Citation

Grégoire Milliez, Emmanuel Ferreira, Michelangelo Fiore, Rachid Alami, Fabrice Lefèvre. Simulating Human-Robot Interactions for Dialogue Strategy Learning. SIMPAR2014, Oct 2014, Bergamo, Italy. pp.62-73, ⟨10.1007/978-3-319-11900-7_6⟩. ⟨hal-01071216⟩

Share

Metrics

Record views

439

Files downloads

692