Practical Challenges in Explicit Ethical Machine Reasoning
This work addresses practical implementation problems for developers and researchers in AI ethics, but it is incremental as it builds on existing ideas without introducing a new paradigm.
The paper tackles the practical challenges of implementing ethical machine reasoning, proposing a general architecture with a declarative ethical arbiter and multiple evidential reasoners to address issues like multi-objective, proactive, and scrutable reasoning.
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.