Preferred Explanations: Theory and Generation via Planning

By Shirin Sohrabi, Jorge A. Baier, Sheila A. McIlraith. 2011

103 citations recorded by the source corpus.

In this paper we examine the general problem of generating preferred explanations for observed behavior with respect to a model of the behavior of a dynamical system. This problem arises in a diversity of applications including diagnosis of dynamical systems and activity recognition. We provide a logical characterization of the notion of an explanation. To generate explanations we identify and exploit a correspondence between explanation generation and planning. The determination of good explanations requires additional domain-specific knowledge which we represent as preferences over explanations. The nature of explanations requires us to formulate preferences in a somewhat retrodictive fashion by utilizing Past Linear Temporal Logic. We propose methods for exploiting these somewhat unique preferences effectively within state-of-the-art planners and illustrate the feasibility of generating (preferred) explanations via planning.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Explainable Planning (2017, background): “Plan Explanation is an area of Planning where the main goal is to help humans to understand the plans produced by the planners (e.g., [Sohrabi et al., 2011].”
Robot task planning and explanation in open and uncertain worlds (2015, background): “[47] tackled the problem of planning to provide explanations using an extension of linear temporal logic that has the ability to reference past events and action occurrences.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “A formal framework to generate preferred explanations of a plan was introduced in [129].”
Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations (2018, result): “…like [Seegebarth et al., 2012; Bercher et al., 2014; Kambhampati, 1990] looked at explanations as a way of describing the effects of plans, while works like [Sohrabi, Baier, and McIlraith, 2011; Meadows, Langley, and Emery, 2013] looked at plans itself as explanations for a set of observations.”
Robot task planning and explanation in open and uncertain worlds (2017, background): “[47] tackled the problem of planning to provide explanations using an extension of linear temporal logic that has the ability to reference past events and action occurrences.”