Explainable Autonomous Robots: A Survey and Perspective

TL;DR

This survey reviews the current state of explainability in autonomous robots, discussing definitions, types, and future research directions to enhance human-robot coexistence.

Contribution

It provides a comprehensive overview of explainability in autonomous robots and proposes a clear definition and research agenda for future work.

Findings

Different types of explainability in machine learning are identified.

A definition of explainability specific to autonomous robots is proposed.

Future research topics for explainable autonomous robots are outlined.

Abstract

Advanced communication protocols are critical to enable the coexistence of autonomous robots with humans. Thus, the development of explanatory capabilities is an urgent first step toward autonomous robots. This survey provides an overview of the various types of "explainability" discussed in machine learning research. Then, we discuss the definition of "explainability" in the context of autonomous robots (i.e., explainable autonomous robots) by exploring the question "what is an explanation?" We further conduct a research survey based on this definition and present some relevant topics for future research.