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

Joseph Campbell; Heni Ben Amor

CoRL 20170 citations

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

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.

BibTeX

@inproceedings{corl2017_bayesianinteract,
  title = {Bayesian Interaction Primitives: A SLAM Approach to Human-Robot Interaction},
  author = {Joseph Campbell and Heni Ben Amor},
  booktitle = {CoRL 2017},
  year = {2017}
}