Bayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction

Joseph Campbell, Heni Ben Amor
Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:379-387, 2017.

Abstract

This paper introduces a fully Bayesian reformulation of Interaction Primitives for human-robot interaction and collaboration. A key insight is that a subset of human-robot interaction is conceptually related to simultaneous localization and mapping techniques. Leveraging this insight we can significantly increase the accuracy of temporal estimation and inferred trajectories while simultaneously reducing the associated computational complexity. We show that this enables more complex human-robot interaction scenarios involving more degrees of freedom.

Cite this Paper

BibTeX
@InProceedings{pmlr-v78-campbell17a, title = {Bayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction}, author = {Campbell, Joseph and Ben Amor, Heni}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {379--387}, year = {2017}, editor = {Levine, Sergey and Vanhoucke, Vincent and Goldberg, Ken}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/campbell17a/campbell17a.pdf}, url = {https://proceedings.mlr.press/v78/campbell17a.html}, abstract = {This paper introduces a fully Bayesian reformulation of Interaction Primitives for human-robot interaction and collaboration. A key insight is that a subset of human-robot interaction is conceptually related to simultaneous localization and mapping techniques. Leveraging this insight we can significantly increase the accuracy of temporal estimation and inferred trajectories while simultaneously reducing the associated computational complexity. We show that this enables more complex human-robot interaction scenarios involving more degrees of freedom.} }
Endnote
%0 Conference Paper %T Bayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction %A Joseph Campbell %A Heni Ben Amor %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-campbell17a %I PMLR %P 379--387 %U https://proceedings.mlr.press/v78/campbell17a.html %V 78 %X This paper introduces a fully Bayesian reformulation of Interaction Primitives for human-robot interaction and collaboration. A key insight is that a subset of human-robot interaction is conceptually related to simultaneous localization and mapping techniques. Leveraging this insight we can significantly increase the accuracy of temporal estimation and inferred trajectories while simultaneously reducing the associated computational complexity. We show that this enables more complex human-robot interaction scenarios involving more degrees of freedom.
APA
Campbell, J. & Ben Amor, H.. (2017). Bayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction. Proceedings of the 1st Annual Conference on Robot Learning, in Proceedings of Machine Learning Research 78:379-387 Available from https://proceedings.mlr.press/v78/campbell17a.html.

Related Material