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

Notes:

Paper I wrote for my area examination. This is building off of work done by Austin Lillard, and Matt Aitken, as well as our advisors Nisar Ahmed, and Eric Frew. Thanks to Nisar Ahmed for extensive editing and review of this paper. This is only available as a pre-print right now. We plan to submit this work, in some polished form, to a journal in the near future.

Abstract: As technology becomes 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.

BibTeX:

@ARTICLE{Israelsen2017-db,
  title         = "``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",
  author        = "Israelsen, Brett W",
  abstract      = "As technology becomes 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.",
  month         =  "1~" # aug,
  year          =  2017,
  archivePrefix = "arXiv",
  primaryClass  = "cs.CY",
  eprint        = "1708.00495"
}