Practical Challenges in Explicit Ethical Machine Reasoning

TL;DR

This paper explores practical challenges in implementing ethical reasoning in machines, emphasizing the need for complex, real-time, verifiable, and multi-objective systems that utilize heterogeneous evidential reasoning.

Contribution

It proposes a general architecture with a declarative ethical arbiter and multiple evidential reasoners to address practical challenges in ethical machine reasoning.

Findings

Identifies key practical challenges such as multi-objectivity and real-time operation.

Proposes a modular architecture to address these challenges.

Highlights the importance of verifiability and heterogeneity in evidential reasoning.

Abstract

We examine implemented systems for ethical machine reasoning with a view to identifying the practical challenges (as opposed to philosophical challenges) posed by the area. We identify a need for complex ethical machine reasoning not only to be multi-objective, proactive, and scrutable but that it must draw on heterogeneous evidential reasoning. We also argue that, in many cases, it needs to operate in real time and be verifiable. We propose a general architecture involving a declarative ethical arbiter which draws upon multiple evidential reasoners each responsible for a particular ethical feature of the system's environment. We claim that this architecture enables some separation of concerns among the practical challenges that ethical machine reasoning poses.