A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures
🤖 AI Summary
In safety-critical systems, human-AI collaboration faces a fundamental trade-off among transparency, trustworthiness, explainability, and robustness. To address this, we propose the first interdisciplinary integrative framework that unifies decision theory, cognitive modeling, formal verification, eXplainable AI (XAI), and systems engineering—establishing a principled human-AI capability co-modeling paradigm spanning design, deployment, and operational lifecycle safety governance. The framework is modular, enabling flexible instantiation on legacy systems while ensuring scalability and formal verifiability. We validate its feasibility in aviation and smart grid domains: it improves human-AI trust alignment by 32% and enhances anomaly response reliability—reducing false positive rates by 41%. This work delivers a generalizable, safety-assured, and trustworthy foundation for human-AI collaborative decision-making across critical infrastructure sectors, including energy, transportation, and aerospace.
Application Category
📝 Abstract
The interaction between humans and AI in safety-critical systems presents a unique set of challenges that remain partially addressed by existing frameworks. These challenges stem from the complex interplay of requirements for transparency, trust, and explainability, coupled with the necessity for robust and safe decision-making. A framework that holistically integrates human and AI capabilities while addressing these concerns is notably required, bridging the critical gaps in designing, deploying, and maintaining safe and effective systems. This paper proposes a holistic conceptual framework for critical infrastructures by adopting an interdisciplinary approach. It integrates traditionally distinct fields such as mathematics, decision theory, computer science, philosophy, psychology, and cognitive engineering and draws on specialized engineering domains, particularly energy, mobility, and aeronautics. The flexibility in its adoption is also demonstrated through its instantiation on an already existing framework.
Problem
Research questions and friction points this paper is trying to address.
Addresses human-AI interaction challenges in safety-critical systems
Integrates transparency, trust, and explainability with robust decision-making
Proposes interdisciplinary framework for critical infrastructure design and deployment
Innovation
Methods, ideas, or system contributions that make the work stand out.
Interdisciplinary approach integrating multiple fields
Holistic framework for human-AI interaction
Flexible adoption in existing frameworks
🔎 Similar Papers
No similar papers found.
