Outlining the design space of eXplainable swarm (xSwarm): experts perspective

TL;DR

This paper explores the foundational aspects of explainability in swarm robotics, surveying experts to identify challenges and requirements for implementing effective explanations in human-swarm interactions.

Contribution

It introduces the concept of eXplainable Swarm (xSwarm), providing initial insights and defining research directions for explainability in swarm systems based on expert surveys.

Findings

Experts identified key challenges in generating explanations for swarms

The study highlights the need for tailored explainability methods in swarm robotics

Foundational questions about swarm explanations are still open

Abstract

In swarm robotics, agents interact through local roles to solve complex tasks beyond an individual's ability. Even though swarms are capable of carrying out some operations without the need for human intervention, many safety-critical applications still call for human operators to control and monitor the swarm. There are novel challenges to effective Human-Swarm Interaction (HSI) that are only beginning to be addressed. Explainability is one factor that can facilitate effective and trustworthy HSI and improve the overall performance of Human-Swarm team. Explainability was studied across various Human-AI domains, such as Human-Robot Interaction and Human-Centered ML. However, it is still ambiguous whether explanations studied in Human-AI literature would be beneficial in Human-Swarm research and development. Furthermore, the literature lacks foundational research on the prerequisites for explainability requirements in swarm robotics, i.e., what kind of questions an explainable swarm is expected to answer, and what types of explanations a swarm is expected to generate. By surveying 26 swarm experts, we seek to answer these questions and identify challenges experts faced to generate explanations in Human-Swarm environments. Our work contributes insights into defining a new area of research of eXplainable Swarm (xSwarm) which looks at how explainability can be implemented and developed in swarm systems. This paper opens the discussion on xSwarm and paves the way for more research in the field.