# Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks

## TL;DR

This paper introduces a rulebook framework for defining autonomous vehicle behavior that integrates legal, ethical, and cultural objectives, ensuring flexible and domain-independent behavior specification.

## Contribution

It proposes a novel rulebook structure with prioritized rules and analyzes its compositional properties for behavior specification in autonomous agents.

## Key findings

- Rulebooks effectively encode conflicting objectives.
- Operations on rulebooks preserve behavior constraints.
- Applicable across various autonomous agent domains.

## Abstract

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.