AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms

TL;DR

This paper introduces AERoS, a process for assuring the safety of emergent behaviors in autonomous robotic swarms, addressing the challenge of verifying complex, self-organizing systems through a structured assurance methodology.

Contribution

It presents a novel safety assurance process for emergent behaviors in robotic swarms, adapting AMLAS guidance to this unique context.

Findings

Validated the AERoS process with a robot swarm case study

Demonstrated effective safety assurance for emergent swarm behaviors

Provided a framework for future safety verification of autonomous swarms

Abstract

The behaviours of a swarm are not explicitly engineered. Instead, they are an emergent consequence of the interactions of individual agents with each other and their environment. This emergent functionality poses a challenge to safety assurance. The main contribution of this paper is a process for the safety assurance of emergent behaviour in autonomous robotic swarms called AERoS, following the guidance on the Assurance of Machine Learning for use in Autonomous Systems (AMLAS). We explore our proposed process using a case study centred on a robot swarm operating a public cloakroom.