Leveraging Context-Oriented Programming to Implement Normative Rules in Autonomous Systems

Theincreasingsensitivitytohumanaspectsinautonomoussystems engineering calls for principled approaches to embed normative concerns into their behaviour. Recent research has focused on expressing and validating sets of social, legal, ethical, empathetic, and 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 SLEECaware 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 propose an operational solution for ethical-aware autonomous systems. 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 promotes runtime adaptation and exhibition of context-dependent ethical behaviour through a modular and transparent design.

Authors

• Roberto Casadei Alma Mater Studiorum—Università di Bologna
• Martina De Sanctis Gran Sasso Science Institute
• Gianluca Filippone Gran Sasso Science Institute
• Sara Pettinari Gran Sasso Science Institute
• Gian Luca Scoccia Gran Sasso Science Institute
• Nicolas Troquard Gran Sasso Science Institute

Keywords

• Ethical-aware systems
• normative multi-agent systems
• contextaware systems
• SLEEC rules
• context-oriented programming