Effective Explanations for Belief-Desire-Intention Robots: When and What to Explain

TL;DR

This paper investigates when and what explanations BDI robots should provide during complex tasks, emphasizing user preferences for concise, context-aware explanations to improve human-robot understanding.

Contribution

It introduces algorithms to identify surprising actions and generate effective explanations tailored to user preferences in BDI robots.

Findings

Users prefer explanations in surprising situations

Concise explanations focusing on intentions and relevant context are favored

Algorithms successfully identify surprising actions and generate explanations

Abstract

When robots perform complex and context-dependent tasks in our daily lives, deviations from expectations can confuse users. Explanations of the robot's reasoning process can help users to understand the robot intentions. However, when to provide explanations and what they contain are important to avoid user annoyance. We have investigated user preferences for explanation demand and content for a robot that helps with daily cleaning tasks in a kitchen. Our results show that users want explanations in surprising situations and prefer concise explanations that clearly state the intention behind the confusing action and the contextual factors that were relevant to this decision. Based on these findings, we propose two algorithms to identify surprising actions and to construct effective explanations for Belief-Desire-Intention (BDI) robots. Our algorithms can be easily integrated in the BDI reasoning process and pave the way for better human-robot interaction with context- and user-specific explanations.