Abstract

As arti® cial intelligence moves ever closer to the goal of producing fully autonomous agents, the question of how to design and implement an arti® cial moral agent (AMA) becomes increasingly pressing. Robots possessing autonomous capacities to do things that are useful to humans will also have the capacity to do things that are harmful to humans and other sentient beings. Theoretical challenges to developing arti® cial moral agents result both from controversies among ethicists about moral theory itself, and from computational limits to the implementation of such theories. In this paper the ethical disputes are surveyed, the possibility of a `moral Turing Test ’ is considered and the computational di culties accompanying the diŒerent types of approach are assessed. Human-like performance, which is prone to include immoral actions, may not be acceptable in machines, but moral perfection may be computationally unattainable. The risks posed by autonomous machines ignorantly or deliberately harming people and other sentient beings are great. The development of machines with enough intelligence to assess the eŒects of their actions on sentient beings and act accordingly may ultimately be the most important task faced by the designers of arti® cially intelligent automata.