TY - GEN
T1 - Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks
AU - Campbell, Joseph
AU - Stepputtis, Simon
AU - Amor, Heni Ben
N1 - Funding Information:
This work was supported by a grant from the Honda Research Institute and by the National Science Foundation under Grant No. (IIS-1749783).
Publisher Copyright:
© 2019, Robotics: Science and Systems. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Human-robot interaction benefits greatly from multimodal sensor inputs as they enable increased robustness and generalization accuracy. Despite this observation, few HRI methods are capable of efficiently performing inference for multimodal systems. In this work, we introduce a reformulation of Interaction Primitives which allows for learning from demonstration of interaction tasks, while also gracefully handling nonlinearities inherent to multimodal inference in such scenarios. We also empirically show that our method results in more accurate, more robust, and faster inference than standard Interaction Primitives and other common methods in challenging HRI scenarios.
AB - Human-robot interaction benefits greatly from multimodal sensor inputs as they enable increased robustness and generalization accuracy. Despite this observation, few HRI methods are capable of efficiently performing inference for multimodal systems. In this work, we introduce a reformulation of Interaction Primitives which allows for learning from demonstration of interaction tasks, while also gracefully handling nonlinearities inherent to multimodal inference in such scenarios. We also empirically show that our method results in more accurate, more robust, and faster inference than standard Interaction Primitives and other common methods in challenging HRI scenarios.
UR - http://www.scopus.com/inward/record.url?scp=85088509229&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85088509229&partnerID=8YFLogxK
U2 - 10.15607/RSS.2019.XV.047
DO - 10.15607/RSS.2019.XV.047
M3 - Conference contribution
AN - SCOPUS:85088509229
SN - 9780992374754
T3 - Robotics: Science and Systems
BT - Robotics
A2 - Bicchi, Antonio
A2 - Kress-Gazit, Hadas
A2 - Hutchinson, Seth
PB - MIT Press Journals
T2 - 15th Robotics: Science and Systems, RSS 2019
Y2 - 22 June 2019 through 26 June 2019
ER -