uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (8 of 8) Show all publications
Gao, Y., Sibirtseva, E., Castellano, G. & Kragic, D. (2019). Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human–Robot Interaction. In: : . Paper presented at 2019 International Conference on Intelligent Robots and Systems, November 3 – 8, 2019, Macau.
Open this publication in new window or tab >>Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human–Robot Interaction
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and influenced the dynamics of gaining human's trust. Additionally, participants evaluated that the robot perceived them as more trustworthy during the interactions with the meta-learning based adaptation compared to the previously studied statistical adaptation model.

National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-398405 (URN)
Conference
2019 International Conference on Intelligent Robots and Systems, November 3 – 8, 2019, Macau
Note

Yuan Gao and Elena Sibirtseva contributed equally to this work.

Available from: 2019-12-05 Created: 2019-12-05 Last updated: 2019-12-09Bibliographically approved
Zhang, P., Gao, A. Y. & Theel, O. (2018). Bandit learning with concurrent transmissions for energy-efficient flooding in sensor networks. EAI Endorsed Transactions on Industrial Networks and Intelligent Systems, 4(13), Article ID e4.
Open this publication in new window or tab >>Bandit learning with concurrent transmissions for energy-efficient flooding in sensor networks
2018 (English)In: EAI Endorsed Transactions on Industrial Networks and Intelligent Systems, ISSN 2410-0218, Vol. 4, no 13, article id e4Article in journal (Refereed) Published
National Category
Communication Systems
Identifiers
urn:nbn:se:uu:diva-366206 (URN)10.4108/eai.20-3-2018.154369 (DOI)
Available from: 2018-03-20 Created: 2018-11-17 Last updated: 2019-04-06Bibliographically approved
Gao, Y., Wallkötter, S., Obaid, M. & Castellano, G. (2018). Investigating deep learning approaches for human-robot proxemics. In: Proc. 27th International Symposium on Robot and Human Interactive Communication: . Paper presented at RO-MAN 2018, August 27–31, Nanjing, China (pp. 1093-1098). IEEE
Open this publication in new window or tab >>Investigating deep learning approaches for human-robot proxemics
2018 (English)In: Proc. 27th International Symposium on Robot and Human Interactive Communication, IEEE, 2018, p. 1093-1098Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we investigate the applicability of deep learning methods to adapt and predict comfortable human-robot proxemics. Proposing a network architecture, we experiment with three different layer configurations, obtaining three different end-to-end trainable models. Using these, we compare their predictive performances on data obtained during a human-robot interaction study. We find that our long short-term memory based model outperforms a gated recurrent unit based model and a feed-forward model. Further, we demonstrate how the created model can be used to create customized comfort zones that can help create a personalized experience for individual users.

Place, publisher, year, edition, pages
IEEE, 2018
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-366204 (URN)10.1109/ROMAN.2018.8525731 (DOI)000494315600172 ()978-1-5386-7981-4 (ISBN)
Conference
RO-MAN 2018, August 27–31, Nanjing, China
Funder
Swedish Foundation for Strategic Research , RIT15-0133Swedish Research Council, 2015-04378
Available from: 2018-11-17 Created: 2018-11-17 Last updated: 2019-12-10Bibliographically approved
Gao, Y., Barendregt, W., Obaid, M. & Castellano, G. (2018). When robot personalisation does not help: Insights from a robot-supported learning study. In: Proc. 27th International Symposium on Robot and Human Interactive Communication: . Paper presented at RO-MAN 2018, August 27–31, Nanjing, China (pp. 705-712). IEEE
Open this publication in new window or tab >>When robot personalisation does not help: Insights from a robot-supported learning study
2018 (English)In: Proc. 27th International Symposium on Robot and Human Interactive Communication, IEEE, 2018, p. 705-712Conference paper, Published paper (Refereed)
Abstract [en]

In the domain of robotic tutors, personalised tutoring has started to receive scientists' attention, but is still relatively underexplored. Previous work using reinforcement learning (RL) has addressed personalised tutoring from the perspective of affective policy learning. However, little is known about the effects of robot behaviour personalisation on user's task performance. Moreover, it is also unclear if and when personalisation may be more beneficial than a robot that adapts to its users and the context of the interaction without personalising its behaviour. In this paper we build on previous work on affective policy learning that used RL to learn what robot's supportive behaviours are preferred by users in an educational scenario. We build a RL framework for personalisation that allows a robot to select verbal supportive behaviours to maximise the user's task progress and positive reactions in a learning scenario where a Pepper robot acts as a tutor and helps people to learn how to solve grid-based logic puzzles. A between-subjects design user study showed that participants were more efficient at solving logic puzzles and preferred a robot that exhibits more varied behaviours compared with a robot that personalises its behaviour by converging on a specific one over time. We discuss insights on negative effects of personalisation and report lessons learned together with design implications for personalised robots.

Place, publisher, year, edition, pages
IEEE, 2018
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-366205 (URN)10.1109/ROMAN.2018.8525832 (DOI)000494315600112 ()978-1-5386-7981-4 (ISBN)
Conference
RO-MAN 2018, August 27–31, Nanjing, China
Funder
Swedish Research Council, 2015-04378Swedish Foundation for Strategic Research , RIT15-0133
Available from: 2018-11-17 Created: 2018-11-17 Last updated: 2019-12-10Bibliographically approved
Obaid, M., Gao, A. Y., Barendregt, W. & Castellano, G. (2017). Exploring users' reactions towards tangible implicit probes for measuring human-robot engagement. In: Social Robotics: . Paper presented at 9th International Conference on Social Robotics (ICSR), November 22–24, 2017, Tsukuba, Japan (pp. 402-412). Springer
Open this publication in new window or tab >>Exploring users' reactions towards tangible implicit probes for measuring human-robot engagement
2017 (English)In: Social Robotics, Springer, 2017, p. 402-412Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we present an exploratory study of the use of tangible implicit probes to gauge the user's social engagement with a robot. Our results show that users' paying attention to the robot's implicit probes is related to higher social engagement, but also that introducing implicit probes can lead to a more positive interaction with a robot. As we observed that users in our study started paying more attention to the implicit probes after they had encountered them, the need for careful design to capture changes in social engagement over time is justified here. Finally, we discuss some of the user recommendations to design better implicit probes.

Place, publisher, year, edition, pages
Springer, 2017
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 10652
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-335325 (URN)10.1007/978-3-319-70022-9_40 (DOI)000449941100040 ()978-3-319-70021-2 (ISBN)
Conference
9th International Conference on Social Robotics (ICSR), November 22–24, 2017, Tsukuba, Japan
Funder
Swedish Research Council, 2015-04378Swedish Foundation for Strategic Research , RIT15-0133
Available from: 2017-10-24 Created: 2017-12-04 Last updated: 2019-02-28Bibliographically approved
Zhang, P., Gao, A. Y. & Theel, O. (2017). Less is More: Learning more with concurrent transmissions for energy-efficient flooding. In: Proc. 14th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. Paper presented at MobiQuitous 2017, November 7–10, Melbourne, Australia. New York: ACM Press
Open this publication in new window or tab >>Less is More: Learning more with concurrent transmissions for energy-efficient flooding
2017 (English)In: Proc. 14th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, New York: ACM Press, 2017Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
New York: ACM Press, 2017
National Category
Communication Systems
Identifiers
urn:nbn:se:uu:diva-335332 (URN)
Conference
MobiQuitous 2017, November 7–10, Melbourne, Australia
Available from: 2017-12-04 Created: 2017-12-04 Last updated: 2018-08-13Bibliographically approved
Gao, A. Y., Barendregt, W. & Castellano, G. (2017). Personalised human-robot co-adaptation in instructional settings using reinforcement learning. In: : . Paper presented at IVA Workshop on Persuasive Embodied Agents for Behavior Change: PEACH 2017, August 27, Stockholm, Sweden.
Open this publication in new window or tab >>Personalised human-robot co-adaptation in instructional settings using reinforcement learning
2017 (English)Conference paper, Published paper (Other academic)
National Category
Human Computer Interaction
Identifiers
urn:nbn:se:uu:diva-335324 (URN)
Conference
IVA Workshop on Persuasive Embodied Agents for Behavior Change: PEACH 2017, August 27, Stockholm, Sweden
Available from: 2017-12-04 Created: 2017-12-04 Last updated: 2018-01-13Bibliographically approved
Gao, A. Y. & Glowacka, D. (2016). Deep gate recurrent neural network. In: Proc. 8th Asian Conference on Machine Learning: . Paper presented at ACML 2016, November 16–18, Hamilton, New Zealand (pp. 350-365).
Open this publication in new window or tab >>Deep gate recurrent neural network
2016 (English)In: Proc. 8th Asian Conference on Machine Learning, 2016, p. 350-365Conference paper, Published paper (Refereed)
Series
Proceedings of Machine Learning Research, ISSN 1938-7228 ; 63
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:uu:diva-335328 (URN)
Conference
ACML 2016, November 16–18, Hamilton, New Zealand
Available from: 2017-05-29 Created: 2017-12-04 Last updated: 2018-01-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3324-4418

Search in DiVA

Show all publications