An Architecture For Goal-Driven Explanation

In complex and changing environments explanation must be a a dynamic and goal-driven process. This paper discusses an evolving system implementing a novel model of explanation generation --- Goal-Driven Interactive Explanation --- that models explanation as a goal-driven, multi-strategy, situated process inter-weaving reasoning with action. We describe a preliminary implementation of this model in gobie, a system that generates explanations for its internal use to support plan generation and execution. 1 INTRODUCTION In standard AI models of explanation, explanation is purely a reasoning process done in isolation from the situation being explained. Likewise in models of explanation that consider explanation goals, goals exert a fixed topdown influence. Our model, termed goal-driven interactive explanation (GDIE) [Leake, 1994] allows incremental information obtained by interaction with the environment to influence the explainer's goals and dynamically re-focus the explanation process...