A Voting-Based System for Ethical Decision Making
Abstract
We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma at runtime, efficiently aggregate those preferences to identify a desirable choice. We provide a concrete algorithm that instantiates our approach; some of its crucial steps are informed by a new theory of swap-dominance efficient voting rules. Finally, we implement and evaluate a system for ethical decision making in the autonomous vehicle domain, using preference data collected from 1.3 million people through the Moral Machine website.
Cite
@article{arxiv.1709.06692,
title = {A Voting-Based System for Ethical Decision Making},
author = {Ritesh Noothigattu and Snehalkumar 'Neil' S. Gaikwad and Edmond Awad and Sohan Dsouza and Iyad Rahwan and Pradeep Ravikumar and Ariel D. Procaccia},
journal= {arXiv preprint arXiv:1709.06692},
year = {2018}
}
Comments
25 pages; paper has been reorganized, related work and discussion sections have been expanded