Explainable Goal Recognition: A Framework Based on Weight of Evidence
This work addresses the need for interpretable AI in goal recognition, particularly for human users, though it is incremental as it applies an existing framework to a specific domain.
The authors tackled the problem of making goal recognition systems explainable by introducing an eXplainable Goal Recognition (XGR) model based on the Weight of Evidence framework, which provides human-centered explanations and was evaluated across eight domains, showing it can generate human-like explanations and improve participants' understanding in a study with 60 people.
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.