Towards individualized affective human-machine interaction

Kazumi Kumagai, Daiwei Lin, Lingheng Meng, Alexandru Blidaru, Philip Beesley, Dana Kulić, Ikuo Mizuuchi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)


Robots and other autonomous systems interacting with humans should customize their behaviour to their human partner's preferences. We propose a method for learning and generating robot movement customized to individual preferences. Within a reinforcement learning framework, we generate rewards based on facial expressions observed during the robot's motion. Robot motions are parametrized; the rewards are used to modify these motion parameters using Q learning. The proposed approach is evaluated in a user study, using an interactive kinetic sculpture. The system interacts with participants and evolves its motion based on the rewards estimated from the participants' facial expressions. Our results show that, for a subset of participants, the system was able to successfully generate actions that resulted in higher than random rewards. The ability to successfully generate high-reward actions depends on: being able to recognize positive affect from the face, being able to generate actions that are pleasing to the participant, and being able to learn the mapping from rewards to actions.

Original languageEnglish
Title of host publication2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2018)
EditorsFulvio Mastrogiovanni, Amit Kumar Pandey, Haoping Wang, Tetsunari Inamura
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781538679807, 9781538679791
ISBN (Print)9781538679814
Publication statusPublished - 2018
Externally publishedYes
EventIEEE/RSJ International Symposium on Robot and Human Interactive Communication 2018 - Nanjing, China
Duration: 27 Aug 201831 Aug 2018
Conference number: 27th (Proceedings)


ConferenceIEEE/RSJ International Symposium on Robot and Human Interactive Communication 2018
Abbreviated titleRO-MAN 2018
Internet address

Cite this