An Architecture for a Military AI System with Ethical Rules

The current era of computer science has seen a significant increase in the application of machine learning (ML) and knowledge representation (KR). The problem with the current situation regarding ethics and AI is the weaknesses of ML and KR when used separately. ML will “learn” ethical behaviour as it is observed and may therefore disagree with human morals. On the other hand, KR is too rigid and can only process scenarios that have been predefined. This paper proposes a solution to the question posed by Rossi (2016) “How to combine bottom-up learning approaches with top-down rule-based approaches in defining ethical principles for AI systems?” This system focuses on potential unethical behaviors that are caused by human nature instead of ethical dilemmas caused by technology insufficiency in the wartime scenarios. Our solution is an architecture that combines a classifier to identify targets in wartime scenarios and a rules-based system in the form of ontologies to guide an AI agent’s behaviour in the given circumstance.