Computational Grounding of Responsibility Attribution and Anticipation in LTLf

TL;DR

This paper explores responsibility attribution and anticipation in autonomous systems using LTLf, establishing connections with reactive synthesis to develop algorithms with complexity analysis for ethical decision-making.

Contribution

It introduces a novel approach to computationally ground responsibility in LTLf, linking it with reactive synthesis concepts and providing algorithms with complexity insights.

Findings

Established complexity characterizations for responsibility attribution in LTLf

Developed sound, complete, and optimal algorithms for responsibility reasoning

Connected responsibility notions with reactive synthesis strategies

Abstract

Responsibility is one of the key notions in machine ethics and in the area of autonomous systems. It is a multi-faceted notion involving counterfactual reasoning about actions and strategies. In this paper, we study different variants of responsibility in a strategic setting based on LTLf. We show a connection with notions in reactive synthesis, including synthesis of winning, dominant, and best-effort strategies. This connection provides the building blocks for a computational grounding of responsibility including complexity characterizations and sound, complete, and optimal algorithms for attributing and anticipating responsibility.