Title :
Perceiving user´s intention-for-interaction: A probabilistic multimodal data fusion scheme
Author :
Mollaret, C. ; Mekonnen, A.A. ; Ferrane, I. ; Pinquier, J. ; Lerasle, F.
Author_Institution :
IRIT, Univ. de Toulouse, Narbonne, France
fDate :
June 29 2015-July 3 2015
Abstract :
Understanding people´s intention, be it action or thought, plays a fundamental role in establishing coherent communication amongst people, especially in non-proactive robotics, where the robot has to understand explicitly when to start an interaction in a natural way. In this work, a novel approach is presented to detect people´s intention-for-interaction. The proposed detector fuses multimodal cues, including estimated head pose, shoulder orientation and vocal activity detection, using a probabilistic discrete state Hidden Markov Model. The multimodal detector achieves up to 80% correct detection rates improving purely audio and RGB-D based variants.
Keywords :
hidden Markov models; human-robot interaction; pose estimation; probability; sensor fusion; user interfaces; estimated head pose; multimodal cues; nonproactive robotics; peoples intention; probabilistic discrete state hidden Markov model; probabilistic multimodal data fusion scheme; shoulder orientation; user intention-for-interaction; vocal activity detection; Estimation; Head; Hidden Markov models; Probabilistic logic; Robot sensing systems; Shoulder; Human-Robot Interaction; Intention Detection; Multimodal Data Fusion;
Conference_Titel :
Multimedia and Expo (ICME), 2015 IEEE International Conference on
Conference_Location :
Turin
DOI :
10.1109/ICME.2015.7177514