Operationalising Ethical Rules in Autonomous Robotic Systems through Context-Oriented Programming

Roberto Casadei, Martina De Sanctis, Gianluca Filippone, Sara Pettinari, Gian Luca Scoccia, Nicolas Troquard

Keywords: ethical-aware systems, context-aware systems, SLEEC rules, multi-service robotics, context-oriented programming

TL;DR: The paper proposes CO-SLEEC, a framework that operationalizes SLEEC rules in autonomous systems by linking them to context-oriented programming, enabling ethical-aware behaviours of robots at runtime.

Abstract:

The increasing sensitivity to human aspects in autonomous systems engineering calls for principled approaches to embed ethical and
normative concerns into their behaviour. Indeed, recent research has focused on expressing and validating sets of social, legal, ethical,
empathetic, or cultural (SLEEC) concerns as rules, and on verifying that a system design adheres to them. However, to date, there is
limited work related to the actual implementation and actuation of SLEEC-aware behaviours. Yet, we believe that operationalising SLEEC rules can enable responsible behaviour of autonomous systems and advance research on the topic. For this purpose, we
provide an operational solution for ethical-aware autonomous systems, applied to the realm of multi-service robots. Specifically, we
devise a principled approach, which we call CO-SLEEC (Context-Oriented SLEEC), connecting the normative setting of SLEEC rules
to context-oriented programming (COP). CO-SLEEC enables runtime adaptation and exhibition of context-dependent ethical behaviour through a modular and transparent design. It features two reusable Python libraries for (i) parsing SLEEC rules into contextual
elements for operationalising them, and (ii) connecting the operational model to the Robot Operating System (ROS), respectively.
We evaluate our implementation for correctness, efficiency, and maintainability, over multi-service assistive robot scenarios.

Area: Engineering and Analysis of Multiagent Systems (EMAS)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 1210