Controlling the Autonomous Warrior

Abstract

The challenges posed by weapons with autonomous functions are not a tabula rasa. The capabilities of both State principals and military agents to control and channel violence for political purposes have improved across the centuries as technology has increased the range and lethality of weapons as well as the scope of warfare. The institutional relations between principals and agents have been adapted to account for, and take advantage of, these developments. Air forces encompass one realm where distance, speed, and lethality have been subjected to substantial and effective control. Air forces are also where systems with autonomous functionality will likely drive the most visible adaptation to command and control arrangements. This process will spread across other domains as States pursue institution-centric and agent-centric strategies to secure meaningful human control over artificial agents as they become increasingly capable of replacing human agents in military (and other) functions. Agent-centric approaches that consider emergent behaviour as akin to human judgment and institutional approaches that improve the ability to understand, interrogate, monitor, and audit the decisions and behaviour of artificial agents can together drive improvements in meaningful human control over warfare, just as previous adaptations have.