Learning Personalized Human-Aware Robot Navigation Using Virtual Reality Demonstrations from a User Study




Authors:

J. de Heuvel, N. Corral, L. Bruckschen, M. Bennewitz

Type:

Conference Proceeding

Published in:

IEEE International on Human & Robot Interactive Communication (RO-MAN)

Year:

2022

Related Projects:

Anticipating Human Behavior

Links:

PreprintPublicationVideo

BibTex String

@article{deheuvel2022roman,
title={Learning Personalized Human-Aware Robot Navigation Using Virtual Reality Demonstrations from a User Study},
DOI={10.1109/ro-man53752.2022.9900554},
booktitle={Proc. of the IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},
author={de Heuvel, Jorge and Corral, Nathan and Bruckschen, Lilli and Bennewitz, Maren},
year={2022}
}

Topic

Abstract:

For the most comfortable, human-aware robot navigation, subjective user preferences need to be taken into account. This paper presents a novel reinforcement learning framework to train a personalized navigation controller along with an intuitive virtual reality demonstration interface. The conducted user study provides evidence that our personalized approach significantly outperforms classical approaches with more comfortable human-robot experiences. We achieve these results using only a few demonstration trajectories from non-expert users, who predominantly appreciate the intuitive demonstration setup. As we show in the experiments, the learned controller generalizes well to states not covered in the demonstration data, while still reflecting user preferences during navigation. Finally, we transfer the navigation controller without loss in performance to a real robot.