Ethically Compliant Sequential Decision Making

Authors

  • Justin Svegliato University of Massachusetts Amherst
  • Samer B. Nashed University of Massachusetts Amherst
  • Shlomo Zilberstein University of Massachusetts Amherst

DOI:

https://doi.org/10.1609/aaai.v35i13.17386

Keywords:

Morality & Value-based AI, Sequential Decision Making, Planning with Markov Models (MDPs, POMDPs), Planning under Uncertainty

Abstract

Enabling autonomous systems to comply with an ethical theory is critical given their accelerating deployment in domains that impact society. While many ethical theories have been studied extensively in moral philosophy, they are still challenging to implement by developers who build autonomous systems. This paper proposes a novel approach for building ethically compliant autonomous systems that optimize completing a task while following an ethical framework. First, we introduce a definition of an ethically compliant autonomous system and its properties. Next, we offer a range of ethical frameworks for divine command theory, prima facie duties, and virtue ethics. Finally, we demonstrate the accuracy and usability of our approach in a set of autonomous driving simulations and a user study of planning and robotics experts.

Downloads

Published

2021-05-18

How to Cite

Svegliato, J., Nashed, S. B., & Zilberstein, S. (2021). Ethically Compliant Sequential Decision Making. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11657-11665. https://doi.org/10.1609/aaai.v35i13.17386

Issue

Section

AAAI Technical Track on Philosophy and Ethics of AI