Towards Providing Explanations for AI Planner Decisions

Borgo, Rita and Cashmore, Michael and Magazzeni, Daniele (2018) Towards Providing Explanations for AI Planner Decisions. In: IJCAI/ECAI 2018 Workshop on Explainable Artificial Intelligence (XAI), 2018-07-13 - 2018-07-13, Stockholmsmässan.

[img]
Preview
 Text (Borgo-etal-XAI-2018-Towards-providing-explanations-for-AI-planner-decisions)
Borgo_etal_XAI_2018_Towards_providing_explanations_for_AI_planner_decisions.pdf
Accepted Author Manuscript
Download (793kB)| Preview

    Abstract

    In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.

    Author(s):Borgo, Rita, Cashmore, Michael ORCID logoORCID: https://orcid.org/0000-0002-8334-4348 and Magazzeni, Daniele
    Item type:Conference or Workshop Item(Paper)
    ID code:69982
    Notes:Presented at the IJCAI/ECAI 2018 Workshop on Explainable Artificial Intelligence (XAI). Stockholm, July 2018
    Keywords:contingency planning, artifical intelligence, AI, explainable planning, Electronic computers. Computer science, Artificial Intelligence
    Subjects:Science > Mathematics > Electronic computers. Computer science
    Department:Faculty of Science > Computer and Information Sciences
    Depositing user: Pure Administrator
    Date deposited:27 Sep 2019 11:13
    Last modified:02 Oct 2019 02:39
    URI:https://strathprints.strath.ac.uk/id/eprint/69982
    Export data:
    CORE (COnnecting REpositories)