Towards Contrastive Explanations for Comparing the Ethics of Plans
This addresses the need for ethical decision-making in AI systems, particularly for users in robotics and AI domains, but it is incremental as it builds upon prior work.
The paper tackles the problem of enabling users to compare the ethical consequences of AI plans by using contrastive explanations, allowing users to make suggestions and receive explanations based on an existing ethical framework.
The development of robotics and AI agents has enabled their wider usage in human surroundings. AI agents are more trusted to make increasingly important decisions with potentially critical outcomes. It is essential to consider the ethical consequences of the decisions made by these systems. In this paper, we present how contrastive explanations can be used for comparing the ethics of plans. We build upon an existing ethical framework to allow users to make suggestions to plans and receive contrastive explanations.