Show simple item record

dc.contributor.authorMcQuillin, Emily
dc.contributor.authorChuramani, Nikhil
dc.contributor.authorGunes, Hatice
dc.date.accessioned2022-01-11T00:30:45Z
dc.date.available2022-01-11T00:30:45Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/332587
dc.description.abstractCurrent Humanoid Service Robot (HSR) behaviours mainly rely on static models that cannot adapt dynamically to meet individual customer attitudes and preferences. In this work, we focus on empowering HSRs with adaptive feedback mechanisms driven by either implicit reward, by estimating facial affect, or explicit reward, by incorporating verbal responses of the human ‘customer’. To achieve this, we first create a custom dataset, annotated using crowd-sourced labels, to learn appropriate approach (positioning and movement) behaviours for a Robo-waiter. This dataset is used to pre-train a Reinforcement Learning (RL) agent to learn behaviours deemed socially appropriate for the robo-waiter. This model is later extended to include separate implicit and explicit reward mechanisms to allow for interactive learning and adaptation from user social feedback. We present a within-subjects Human-Robot Interaction (HRI) study with 21 participants implementing interactions between the robo-waiter and human customers implementing the above-mentioned model variations. Our results show that both explicit and implicit adaptation mechanisms enabled the adaptive robo-waiter to be rated as more enjoyable and sociable, and its positioning relative to the participants as more appropriate compared to using the pre-trained model or a randomised control implementation.
dc.description.sponsorshipE. McQuillin was supported by the 2020/21 DeepMind Cambridge Scholarship. N. Churamani is funded by the EPSRC grant EP/R513180/1 (ref. 2107412). H. Gunes is supported by the EPSRC project ARoEQ under grant ref. EP/R030782/1.
dc.rightsAll Rights Reserved
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.subjectReinforcement Learning
dc.subjectHumanoid Robo-waiter
dc.subjectExplicit Feedback
dc.subjectImplicit Feedback
dc.subjectFacial Affect
dc.titleLearning Socially Appropriate Robo-waiter Behaviours through Real-time User Feedback
dc.typeConference Object
dc.publisher.departmentDepartment of Computer Science And Technology Student
dc.date.updated2022-01-07T14:36:36Z
dc.identifier.doi10.17863/CAM.80034
dcterms.dateAccepted2021-11-23
rioxxterms.versionofrecord10.17863/CAM.80034
rioxxterms.versionAM
dc.contributor.orcidChuramani, Nikhil [0000-0001-5926-0091]
dc.contributor.orcidGunes, Hatice [0000-0003-2407-3012]
pubs.funder-project-idEPSRC (2107412)
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/R030782/1)
pubs.conference-nameACM/IEEE International Conference on Human-Robot Interaction
pubs.conference-start-date2022-03-07
cam.orpheus.counter6*
cam.depositDate2022-01-07
pubs.conference-finish-date2022-03-10
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2023-01-10


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record