Learning Robot Objectives from Physical Human Interaction

Simple item page
dc.citation.firstpage217en_US
dc.citation.journalTitleProceedings of Machine Learning Researchen_US
dc.citation.lastpage226en_US
dc.citation.volumeNumber78en_US
dc.contributor.authorBajcsy, Andreaen_US
dc.contributor.authorLosey, Dylan P.en_US
dc.contributor.authorO’Malley, Marcia K.en_US
dc.contributor.authorDragan, Anca D.en_US
dc.date.accessioned2018-07-03T16:08:36Zen_US
dc.date.available2018-07-03T16:08:36Zen_US
dc.date.issued2017en_US
dc.description.abstractWhen humans and robots work in close proximity, physical interaction is inevitable. Traditionally, robots treat physical interaction as a disturbance, and resume their original behavior after the interaction ends. In contrast, we argue that physical human interaction is informative: it is useful information about how the robot should be doing its task. We formalize learning from such interactions as a dynamical system in which the task objective has parameters that are part of the hidden state, and physical human interactions are observations about these parameters. We derive an online approximation of the robot’s optimal policy in this system, and test it in a user study. The results suggest that learning from physical interaction leads to better robot task performance with less human effort.en_US
dc.identifier.citationBajcsy, Andrea, Losey, Dylan P., O’Malley, Marcia K., et al.. "Learning Robot Objectives from Physical Human Interaction." <i>Proceedings of Machine Learning Research,</i> 78, (2017) PMLR: 217-226. <a href="https://hdl.handle.net/1911/102348">https://hdl.handle.net/1911/102348</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/102348en_US
dc.language.isoengen_US
dc.publisherPMLRen_US
dc.relation.urihttp://proceedings.mlr.press/v78/bajcsy17a.htmlen_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.titleLearning Robot Objectives from Physical Human Interactionen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bajcsy_CoRL_2017.pdf
Size:
2.28 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
Mechanical Engineering Publications