Multi-Task Trust Transfer for Human-Robot Interaction

TL;DR

This paper investigates how human trust in robots transfers across different tasks, proposing models that better predict trust evolution and transfer, thereby enhancing multi-task human-robot interaction.

Contribution

It introduces differentiable models of trust transfer across tasks, including rational, neural, and hybrid approaches, validated through human-subject experiments.

Findings

Models outperform existing ones in predicting trust over unseen tasks and users.

Task-dependent trust models are more accurate in capturing human trust.

Trust transfer can be inferred effectively across different tasks.

Abstract

Trust is essential in shaping human interactions with one another and with robots. This paper discusses how human trust in robot capabilities transfers across multiple tasks. We first present a human-subject study of two distinct task domains: a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers. The findings expand our understanding of trust and inspire new differentiable models of trust evolution and transfer via latent task representations: (i) a rational Bayes model, (ii) a data-driven neural network model, and (iii) a hybrid model that combines the two. Experiments show that the proposed models outperform prevailing models when predicting trust over unseen tasks and users. These results suggest that (i) task-dependent functional trust models capture human trust in robot capabilities more accurately, and (ii) trust transfer across tasks can be inferred to a good degree. The latter enables trust-mediated robot decision-making for fluent human-robot interaction in multi-task settings.