Modeling Trust in Human-Robot Interaction: A Survey

TL;DR

This survey reviews various models of trust in human-robot interaction, emphasizing the importance of calibrating trust appropriately for improved collaboration and outlining future research directions and challenges.

Contribution

It provides a comprehensive review of trust modeling techniques in HRI, highlighting gaps and proposing future research directions.

Findings

Various trust models exist for HRI.

Trust calibration is crucial for effective collaboration.

Future research needs to address existing challenges.

Abstract

As the autonomy and capabilities of robotic systems increase, they are expected to play the role of teammates rather than tools and interact with human collaborators in a more realistic manner, creating a more human-like relationship. Given the impact of trust observed in human-robot interaction (HRI), appropriate trust in robotic collaborators is one of the leading factors influencing the performance of human-robot interaction. Team performance can be diminished if people do not trust robots appropriately by disusing or misusing them based on limited experience. Therefore, trust in HRI needs to be calibrated properly, rather than maximized, to let the formation of an appropriate level of trust in human collaborators. For trust calibration in HRI, trust needs to be modeled first. There are many reviews on factors affecting trust in HRI, however, as there are no reviews concentrated on different trust models, in this paper, we review different techniques and methods for trust modeling in HRI. We also present a list of potential directions for further research and some challenges that need to be addressed in future work on human-robot trust modeling.