Governing lethal behavior

摘要

This paper provides the motivation and philosophy underlying the design of an ethical control and reasoning system potentially suitable for constraining lethal actions in an autonomous robotic system, so that its behavior will fall within the bounds prescribed by the Laws of War and Rules of Engagement. This research, funded by the U.S. Army Research Office, is intended to ensure that robots do not behave illegally or unethically in the battlefield. Reasons are provided for the necessity of developing such a system at this time, as well as arguments for and against its creation.