Analysing Explanation-Related Interactions in Collaborative Perception-Cognition-Communication-Action

TL;DR

This paper analyzes communication patterns in collaborative emergency response tasks to identify explanation types humans expect from AI teammates, highlighting clarification messages' role in task performance.

Contribution

It classifies explanation-related interactions in human collaboration, informing AI explanation capabilities for improved teamwork and trust.

Findings

Most messages seek clarification of decisions or actions

Explanation messages influence task performance

Humans expect specific explanation types from AI teammates

Abstract

Effective communication is essential in collaborative tasks, so AI-equipped robots working alongside humans need to be able to explain their behaviour in order to cooperate effectively and earn trust. We analyse and classify communications among human participants collaborating to complete a simulated emergency response task. The analysis identifies messages that relate to various kinds of interactive explanations identified in the explainable AI literature. This allows us to understand what type of explanations humans expect from their teammates in such settings, and thus where AI-equipped robots most need explanation capabilities. We find that most explanation-related messages seek clarification in the decisions or actions taken. We also confirm that messages have an impact on the performance of our simulated task.