An Abstract Architecture for Explainable Autonomy in Hazardous Environments

2026-06-05

AI Summary

This work addresses the challenge of insufficient trust in autonomous robots operating in hazardous environments, which often stems from a lack of explainability. The authors propose a modular, abstract architecture that integrates explainability as a core design principle—marking the first effort to embed such capability intrinsically within autonomous system design. This framework enables the system to proactively generate behavior explanations grounded in domain-specific knowledge. Offering a generalizable template adaptable across multiple application domains, the architecture was validated in a nuclear industry setting, where it successfully provided workers and regulators with transparent, credible justifications for robotic decisions, thereby significantly enhancing their understanding of and trust in the system’s behavior.

Abstract

Autonomous robotic systems are being proposed for use in hazardous environments, often to reduce the risks to human workers. In the immediate future, it is likely that human workers will continue to use and direct these autonomous robots, much like other computerised tools but with more sophisticated decision-making. Therefore, one important area on which to focus engineering effort is ensuring that these users trust the system. Recent literature suggests that explainability is closely related to how trustworthy a system is. Like safety and security properties, explainability should be designed into a system, instead of being added afterwards. This paper presents an abstract architecture that supports an autonomous system explaining its behaviour (explainable autonomy), providing a design template for implementing explainable autonomous systems. We present a worked example of how our architecture could be applied in the civil nuclear industry, where both workers and regulators need to trust the system's decision-making capabilities.

Problem

• explainable autonomy
• trust
• hazardous environments
• autonomous systems
• explainability

Innovation

• explainable autonomy
• abstract architecture
• trustworthy autonomous systems
• hazardous environments
• human-robot interaction