Many systems proposed for the implementation of ethical reasoning involve an encoding of user values as a set of rules or a model. We consider the question of how changes of context affect these encodings. We propose the use of a reasoning cycle, in which information about the ethical reasoner's context is imported in a logical form, and we propose that context-specific aspects of an ethical encoding be prefaced by a guard formula. This guard formula should evaluate to true when the reasoner is in the appropriate context and the relevant parts of the reasoner's rule set or model should be updated accordingly. This architecture allows techniques for the model-checking of agent-based autonomous systems to be used to verify that all contexts respect key stakeholder values. We implement this framework using the hybrid ethical reasoning agents system (HERA) and the model-checking agent programming languages (MCAPL) framework.

To address the requirement for autonomous moral decision making, we introduce a software library for modeling hybrid ethical reasoning agents (short: HERA). The goal of the HERA project is to provide theoretically well-founded and practically usable logic-based machine ethics tools for implementation in robots. The novelty is that HERA implements multiple ethical principles like utilitarianism, the principle of double effect, and a Pareto-inspired principle. These principles can be used to automatically assess moral situations represented in a format we call causal agency models. We discuss how to model moral situations using our approach, and how it can cope with uncertainty about moral values. Finally, we briefly outline the architecture of our robot IMMANUEL, which implements HERA and is able to explain ethical decisions to humans.

The conversational ethical reasoning robot Immanuel is presented. Immanuel can reason about moral dilemmas from multiple ethical views. The reported study evaluates the perceived morality of the robot. The participants had a conversation with the robot on whether lying is permissibile in a given situation. Immanuel first signaled uncertainty about whether lying is right or wrong in the situation, then disagreed with the participant's view, and finally asked for justification. The results indicate that participants with a higher tendency to utilitarian judgments are initially more certain about their view as compared to participants with a higher tendency to deontological judgments. These differences vanish towards the end of the dialogue. Lying is defended and argued against by both utilitarian and deontologically oriented participants. The diversity of the reported arguments points to the variety of human moral judgment and calls for more fine-grained representations of moral reasons for social robots.