# AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms

arXiv: https://arxiv.org/abs/2302.10292 · HTML: https://mlsanity.com/paper/2302.10292/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 6 of 6)

- [Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)](https://mlsanity.com/paper/2102.01564/) (2021)
- [The Role of Explainability in Assuring Safety of Machine Learning in Healthcare](https://mlsanity.com/paper/2109.00520/) (2021)
- [Towards a Framework for Certification of Reliable Autonomous Systems](https://mlsanity.com/paper/2001.09124/) (2020)
- [On Specifying for Trustworthiness](https://mlsanity.com/paper/2206.11421/) (2022)
- [DOTS: An Open Testbed for Industrial Swarm Robotic Solutions](https://mlsanity.com/paper/2203.13809/) (2022)
- [Using Models at Runtime to Address Assurance for Self-Adaptive Systems](https://mlsanity.com/paper/1505.00903/) (2015)

## Built on by (most cited first, 2 of 2)

- [Runway Sign Classifier: A DAL C Certifiable Machine Learning System](https://mlsanity.com/paper/2310.06506/) (2023)
- [Autonomous Robotic Swarms: A Corroborative Approach for Verification and Validation](https://mlsanity.com/paper/2407.15475/) (2024)

## Abstract (arXiv)

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.