The behavior of self-driving cars must be compatible with an enormous set of conflicting and ambiguous objectives, from law, from ethics, from the local culture, and so on. This paper describes a new way to conveniently define the desired behavior for autonomous agents, which we use on the self-driving cars developed at nuTonomy. We define a "rulebook" as a pre-ordered set of "rules", each akin to a violation metric on the possible outcomes ("realizations"). The rules are partially ordered by priority. The semantics of a rulebook imposes a pre-order on the set of realizations. We study the compositional properties of the rulebooks, and we derive which operations we can allow on the rulebooks to preserve previously-introduced constraints. While we demonstrate the application of these techniques in the self-driving domain, the methods are domain-independent.
@article{arxiv.1902.09355,
title = {Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks},
author = {Andrea Censi and Konstantin Slutsky and Tichakorn Wongpiromsarn and Dmitry Yershov and Scott Pendleton and James Fu and Emilio Frazzoli},
journal= {arXiv preprint arXiv:1902.09355},
year = {2019}
}