Towards a Theory of Longitudinal Trust Calibration in Human–Robot Teams

Abstract

The introduction of artificial teammates in the form of autonomous social robots, with fewer social abilities compared to humans, presents new challenges for human–robot team dynamics. A key characteristic of high performing human-only teams is their ability to establish, develop, and calibrate trust over long periods of time, making the establishment of longitudinal human–robot team trust calibration a crucial part of these challenges. This paper presents a novel integrative model that takes a longitudinal perspective on trust development and calibration in human–robot teams. A key new proposed factor in this model is the introduction of the concept relationship equity. Relationship equity is an emotional resource that predicts the degree of goodwill between two actors. Relationship equity can help predict the future health of a long-term relationship. Our model is descriptive of current trust dynamics, predictive of the impact on trust of interactions within a human–robot team, and prescriptive with respect to the types of interventions and transparency methods promoting trust calibration. We describe the interplay between team trust dynamics and the establishment of work agreements that guide and improve human–robot collaboration. Furthermore, we introduce methods for dampening (reducing overtrust) and repairing (reducing undertrust) mis-calibrated trust between team members as well as methods for transparency and explanation. We conclude with a description of the implications of our model and a research agenda to jump-start a new comprehensive research program in this area.