Argument Schemes for Explainable Planning

TL;DR

This paper introduces argument schemes and critical questions to generate explanations for AI planning, enhancing transparency and user understanding of AI-generated plans.

Contribution

It develops a novel argumentation framework for explaining AI plans, including argument schemes and critical questions for interactive explanations.

Findings

Provides a set of argument schemes for plan explanation

Introduces critical questions for user interaction

Analyzes properties of plan arguments

Abstract

Artificial Intelligence (AI) is being increasingly used to develop systems that produce intelligent solutions. However, there is a major concern that whether the systems built will be trusted by humans. In order to establish trust in AI systems, there is a need for the user to understand the reasoning behind their solutions and therefore, the system should be able to explain and justify its output. In this paper, we use argumentation to provide explanations in the domain of AI planning. We present argument schemes to create arguments that explain a plan and its components; and a set of critical questions that allow interaction between the arguments and enable the user to obtain further information regarding the key elements of the plan. Finally, we present some properties of the plan arguments.