Trust Dynamics and Transfer Across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models
Abstract
This work contributes both experimental findings and novel computational human-robot trust models for multi-task settings. We describe Bayesian non-parametric and neural models, and compare their performance on data collected from real-world human-subjects study. Our study spans two distinct task domains: household tasks performed by a Fetch robot, and a virtual reality driving simulation of an autonomous vehicle performing a variety of maneuvers. We find that human trust changes and transfers across tasks in a structured manner based on perceived task characteristics. Our results suggest that task-dependent functional trust models capture human trust in robot capabilities more accurately, and trust transfer across tasks can be inferred to a good degree. We believe these models are key for enabling trust-based robot decision-making for natural human-robot interaction.
Cite
Text
Soh et al. "Trust Dynamics and Transfer Across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/868Markdown
[Soh et al. "Trust Dynamics and Transfer Across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/soh2019ijcai-trust/) doi:10.24963/IJCAI.2019/868BibTeX
@inproceedings{soh2019ijcai-trust,
title = {{Trust Dynamics and Transfer Across Human-Robot Interaction Tasks: Bayesian and Neural Computational Models}},
author = {Soh, Harold and Shu, Pan and Chen, Min and Hsu, David},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {6226-6230},
doi = {10.24963/IJCAI.2019/868},
url = {https://mlanthology.org/ijcai/2019/soh2019ijcai-trust/}
}