"I can assure you [$\ldots$] that it's going to be all right" -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships

TL;DR

This paper surveys the concept of assurances in human-autonomy trust, defining their role in enabling users to understand and trust autonomous systems, and discusses future research directions.

Contribution

It provides a comprehensive survey of assurances in human-autonomy trust, refining their definition and highlighting key ideas and future research directions.

Findings

Assurances are crucial for building trust in autonomous systems.

The survey identifies key ideas and gaps in current assurance research.

Future research directions include developing standardized assurance frameworks.

Abstract

As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assurances that are the method by which users can understand how to trust this technology. Trust between humans and autonomy is reviewed, and the implications for the design of assurances are highlighted. A survey of research that has been performed with respect to assurances is presented, and several key ideas are extracted in order to refine the definition of assurances. Several directions for future research are identified and discussed.