# Towards a Framework for Certification of Reliable Autonomous Systems

arXiv: https://arxiv.org/abs/2001.09124 · HTML: https://mlsanity.com/paper/2001.09124/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

## Built on by (most cited first, 12 of 12)

- [Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions](https://mlsanity.com/paper/2112.11561/) (2021)
- [On Specifying for Trustworthiness](https://mlsanity.com/paper/2206.11421/) (2022)
- [Safe Reach Set Computation via Neural Barrier Certificates](https://mlsanity.com/paper/2404.18813/) (2024)
- [SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer](https://mlsanity.com/paper/2409.11190/) (2024)
- [AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms](https://mlsanity.com/paper/2302.10292/) (2023)
- [Ensuring trustworthy and ethical behaviour in intelligent logical agents](https://mlsanity.com/paper/2402.07547/) (2024)
- [Ethical AI Governance: Methods for Evaluating Trustworthy AI](https://mlsanity.com/paper/2409.07473/) (2024)
- [ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents](https://mlsanity.com/paper/2604.13097/) (2026)
- [Consent as a Foundation for Responsible Autonomy](https://mlsanity.com/paper/2203.11420/) (2022)
- [Assessing Trustworthiness of Autonomous Systems](https://mlsanity.com/paper/2305.03411/) (2023)
- [SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving](https://mlsanity.com/paper/2510.24949/) (2025)
- [Community Norms in the Spotlight: Enabling Task-Agnostic Unsupervised Pre-Training to Benefit Online Social Media](https://mlsanity.com/paper/2602.02525/) (2026)

## Abstract (arXiv)

A computational system is called autonomous if it is able to make its own decisions, or take its own actions, without human supervision or control. The capability and spread of such systems have reached the point where they are beginning to touch much of everyday life. However, regulators grapple with how to deal with autonomous systems, for example how could we certify an Unmanned Aerial System for autonomous use in civilian airspace? We here analyse what is needed in order to provide verified reliable behaviour of an autonomous system, analyse what can be done as the state-of-the-art in automated verification, and propose a roadmap towards developing regulatory guidelines, including articulating challenges to researchers, to engineers, and to regulators. Case studies in seven distinct domains illustrate the article.