Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations

TL;DR

This paper introduces a hierarchical modeling approach to generate tailored explanations of robot plans for users with different expertise levels, using abstraction of the domain model and efficient algorithms.

Contribution

It presents a novel method for explaining robot plans to users with varying expertise by modeling user understanding as domain abstractions and developing algorithms for minimal explanations.

Findings

Efficient algorithms for generating explanations based on user model abstractions.

Empirical validation across diverse problem scenarios.

Reduction of explanation generation to a search over abstract models.

Abstract

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users. One aspect of the explanation generation problem that has yet to receive much attention is the task of explaining plans to users whose level of expertise differ from that of the explainer. We propose an approach for addressing this problem by representing the user's model as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating explanation to a search over the space of abstract models and investigate possible greedy approximations for minimal explanations. We also empirically show that our approach can efficiently compute explanations for a variety of problems.