Towards Responsible AI: Advances in Safety, Fairness, and Accountability of Autonomous Systems

TL;DR

This paper presents new methods and frameworks to improve safety, fairness, transparency, and accountability in autonomous AI systems, with practical implementations and formal assessments to promote trustworthy AI deployment.

Contribution

It introduces resilient safety shields, a novel fairness enforcement approach, and a formal framework for assessing intentionality and responsibility in probabilistic autonomous agents.

Findings

Safety shields prevent collisions in autonomous driving simulations.

Fairness shields effectively enforce group fairness with minimal intervention.

Metrics for agency and intention enable retrospective responsibility analysis.

Abstract

Ensuring responsible use of artificial intelligence (AI) has become imperative as autonomous systems increasingly influence critical societal domains. However, the concept of trustworthy AI remains broad and multi-faceted. This thesis advances knowledge in the safety, fairness, transparency, and accountability of AI systems. In safety, we extend classical deterministic shielding techniques to become resilient against delayed observations, enabling practical deployment in real-world conditions. We also implement both deterministic and probabilistic safety shields into simulated autonomous vehicles to prevent collisions with road users, validating the use of these techniques in realistic driving simulators. We introduce fairness shields, a novel post-processing approach to enforce group fairness in sequential decision-making settings over finite and periodic time horizons. By optimizing intervention costs while strictly ensuring fairness constraints, this method efficiently balances fairness with minimal interference. For transparency and accountability, we propose a formal framework for assessing intentional behaviour in probabilistic decision-making agents, introducing quantitative metrics of agency and intention quotient. We use these metrics to propose a retrospective analysis of intention, useful for determining responsibility when autonomous systems cause unintended harm. Finally, we unify these contributions through the ``reactive decision-making'' framework, providing a general formalization that consolidates previous approaches. Collectively, the advancements presented contribute practically to the realization of safer, fairer, and more accountable AI systems, laying the foundations for future research in trustworthy AI.