Is It My Looks? Or Something I Said? The Impact of Explanations, Embodiment, and Expectations on Trust and Performance in Human-Robot Teams

摘要

Trust is critical to the success of human-robot interaction. Research has shown that people will more accurately trust a robot if they have an accurate understanding of its decision-making process. The Partially Observable Markov Decision Process (POMDP) is one such decision-making process, but its quantitative reasoning is typically opaque to people. This lack of transparency is exacerbated when a robot can learn, making its decision making better, but also less predictable. Recent research has shown promise in calibrating human-robot trust by automatically generating explanations of POMDP-based decisions. In this work, we explore factors that can potentially interact with such explanations in influencing human decision-making in human-robot teams. We focus on explanations with quantitative expressions of uncertainty and experiment with common design factors of a robot: its embodiment and its communication strategy in case of an error. Results help us identify valuable properties and dynamics of the human-robot trust relationship.