Explainable Goal Recognition: A Framework Based on Weight of Evidence

TL;DR

This paper presents an explainable goal recognition framework using the Weight of Evidence method, providing human-like explanations for goal recognition tasks and evaluating its effectiveness through computational and human studies.

Contribution

It introduces a novel XGR model based on WoE that generates human-centered explanations and demonstrates its effectiveness across multiple domains and user studies.

Findings

The XGR model produces explanations that align with human judgments.

Participants understood agent goals better with explanations.

The model increases trust and satisfaction in goal recognition outputs.

Abstract

We introduce and evaluate an eXplainable Goal Recognition (XGR) model that uses the Weight of Evidence (WoE) framework to explain goal recognition problems. Our model provides human-centered explanations that answer why? and why not? questions. We computationally evaluate the performance of our system over eight different domains. Using a human behavioral study to obtain the ground truth from human annotators, we further show that the XGR model can successfully generate human-like explanations. We then report on a study with 60 participants who observe agents playing Sokoban game and then receive explanations of the goal recognition output. We investigate participants' understanding obtained by explanations through task prediction, explanation satisfaction, and trust.