Learning Robot Objectives from Physical Human Interaction

Simple item page
dc.citation.firstpage217
dc.citation.journalTitleProceedings of Machine Learning Research
dc.citation.lastpage226
dc.citation.volumeNumber78
dc.contributor.authorBajcsy, Andrea
dc.contributor.authorLosey, Dylan P.
dc.contributor.authorO’Malley, Marcia K.
dc.contributor.authorDragan, Anca D.
dc.date.accessioned2018-07-03T16:08:36Z
dc.date.available2018-07-03T16:08:36Z
dc.date.issued2017
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.
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>.
dc.identifier.urihttps://hdl.handle.net/1911/102348
dc.language.isoeng
dc.publisherPMLR
dc.relation.urihttp://proceedings.mlr.press/v78/bajcsy17a.html
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.
dc.titleLearning Robot Objectives from Physical Human Interaction
dc.typeJournal article
dc.type.dcmiText
dc.type.publicationpublisher version
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