Plan Explanations as Model Reconciliation

Tathagata Chakraborti, Sarath Sreedharan, Sachin Grover, Subbarao Kambhampati

Research output: Chapter in Book/Report/Conference proceedingConference contribution

45 Scopus citations

Abstract

Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same, and how the explanation process as a result of this mismatch can be then seen as a process of reconciliation of these models. Existing algorithms in such settings, while having been built on contrastive, selective and social properties of explanations as studied extensively in the psychology literature, have not, to the best of our knowledge, been evaluated in settings with actual humans in the loop. As such, the applicability of such explanations to human-AI and human-robot interactions remains suspect. In this paper, we set out to evaluate these explanation generation algorithms in a series of studies in a mock search and rescue scenario with an internal semi-autonomous robot and an external human commander. During that process, we hope to demonstrate to what extent the properties of these algorithms hold as they are evaluated by humans.

Original languageEnglish (US)
Title of host publicationHRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction
PublisherIEEE Computer Society
Pages258-266
Number of pages9
ISBN (Electronic)9781538685556
DOIs
StatePublished - Mar 22 2019
Event14th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2019 - Daegu, Korea, Republic of
Duration: Mar 11 2019Mar 14 2019

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
Volume2019-March
ISSN (Electronic)2167-2148

Conference

Conference14th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2019
Country/TerritoryKorea, Republic of
CityDaegu
Period3/11/193/14/19

Keywords

  • Explainable AI
  • explanations as model reconciliation
  • human-robot interaction
  • planning and decision-making

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Plan Explanations as Model Reconciliation'. Together they form a unique fingerprint.

Cite this