Excuse My Explanations: Integrating Excuses and Model Reconciliation for Actionable Explanations

摘要

The ability to provide useful and intuitive explanations remains one of the major hurdles to creating robotic systems capable of working effectively with everyday users. In this paper, we consider a popular explanation generation framework for robot task plans, namely model reconciliation, and try to address one of its main drawbacks, namely its inability to generate actionable explanations. The current methods for generating model reconciliation focus on generating information that explains why the robot chose a certain behavior over one that was expected by the human. However, the user might also want to understand how they can influence the robot's behavior so it follows the one that was expected from it. Explanations that provide such information are called actionable, and we extend traditional model reconciliation explanations to be actionable by combining them with the existing notion of excuses. We will refer to the resulting explanations as Actionable Reconciliation Explanations (ARE), which explains the robot's decision-making process and suggests how its model might be modified for improved alignment with human expectations. However, as we will see, the generation of ARE requires methods that are distinct from existing model reconciliation and excuse generation methods, and ARE also exhibits properties that are distinct from these earlier methods. We assess our method through computational experiments and user studies and, in the process, also compare it against traditional forms of excuses and model reconciliation explanations.