Multi-Task Trust Transfer for Human-Robot Interaction
This work addresses the problem of modeling trust transfer for more fluent human-robot interaction in multi-task settings, representing an incremental advance with new models.
This paper investigates how human trust in robots transfers across multiple tasks, using studies with a Fetch robot and a virtual reality autonomous vehicle simulation. It proposes three models (Bayes, neural network, and hybrid) that outperform existing models in predicting trust for unseen tasks and users, with results showing improved accuracy in capturing task-dependent trust and enabling trust-mediated robot decision-making.
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.