Online Explanation Generation for Human-Robot Teaming

Anonymous

Keywords: Human-Centered Robotics, Explainable AI, Cooperating Robots, Task Planning

TL;DR: We introduce online explanation to consider the cognitive requirement of the human for understanding the generated explanation by the agent.

Abstract:

As Artificial Intelligence (AI) becomes an integral part of our life, the development of explainable AI, embodied in the decision-making process of an AI or robotic agent, becomes imperative. For a robotic teammate, the ability to generate explanations to explain its behavior is one of the key requirements of an explainable agency. Prior work on explanation generation focuses on supporting the reasoning behind the robot's behavior. These approaches, however, fail to consider the mental workload needed to understand the received explanation. In other words, the human teammate is expected to understand any explanation provided, often before the task execution, no matter how much information is presented in the explanation.
In this work, we argue that an explanation, especially complex ones, should be made in an online fashion during the execution, which helps spread out the information to be explained and thus reducing the mental workload of humans. However, a challenge here is that the different parts of an explanation are dependent on each other, which must be taken into account when generating online explanations. To this end, a general formulation of online explanation generation is presented along with three different implementations satisfying different online properties. We base our explanation generation method on a model reconciliation setting introduced in our prior work. Our approaches are evaluated both with human subjects in a standard planning competition (IPC) domain, using NASA Task Load Index (TLX), as well as in simulation with ten different problems across two IPC domains.

Author Identity Visibility: Reveal author identities to reviewers