Martina De Sanctis

Martina De Sanctis, Gianluca Filippone, Paola Inverardi et al.

This paper addresses the challenge of operationalizing ethics in autonomous systems through runtime enforcement. It first conceptualizes the system's ethical space and outlines a structured ethics assurance process. Building on this foundation, it introduces an enforcement subsystem that operationalizes ethical rules, specifically social, legal, ethical, empathetic, and cultural (SLEEC) requirements, through the Abstract State Machine (ASM) formalism. The enforcement subsystem is built on the MAPE-K control-loop architecture for monitoring and controlling the system's ethical behavior, and it relies on an ASM-based runtime model of the ethical rules to enforce. This enables the dynamic evaluation, adaptation, and enforcement of ethical behavior within a runtime formal model. The overall approach, named SLEEC@run.time, is demonstrated on an assistive robot scenario, showcasing how both the robot's behavior and the governing ethical rules can dynamically adapt to contextual changes. By leveraging a flexible runtime model, SLEEC@run.time accommodates changes such as the addition or removal of SLEEC rules, ensuring a robust and evolvable approach to ethical assurance in autonomous systems. The evaluation of SLEEC@run.time shows that it effectively ensures the system's adherence to ethical principles with negligible execution time overhead.

Nicolas Troquard, Martina De Sanctis, Paola Inverardi et al.

The rise of AI-based and autonomous systems is raising concerns and apprehension due to potential negative repercussions stemming from their behavior or decisions. These systems must be designed to comply with the human contexts in which they will operate. To this extent, Townsend et al. (2022) introduce the concept of SLEEC (social, legal, ethical, empathetic, or cultural) rules that aim to facilitate the formulation, verification, and enforcement of the rules AI-based and autonomous systems should obey. They lay out a methodology to elicit them and to let philosophers, lawyers, domain experts, and others to formulate them in natural language. To enable their effective use in AI systems, it is necessary to translate these rules systematically into a formal language that supports automated reasoning. In this study, we first conduct a linguistic analysis of the SLEEC rules pattern, which justifies the translation of SLEEC rules into classical logic. Then we investigate the computational complexity of reasoning about SLEEC rules and show how logical programming frameworks can be employed to implement SLEEC rules in practical scenarios. The result is a readily applicable strategy for implementing AI systems that conform to norms expressed as SLEEC rules.