Culture-Based Explainable Human-Agent Deconfliction

TL;DR

This paper introduces an argumentation-based architecture for human-agent deconfliction that generates explanations aligned with human regulations, improving trust and performance especially in complex scenarios.

Contribution

It proposes a novel argumentation-based framework for explainable human-agent decision-making grounded in cultural rules and validates it through a user study.

Findings

Explanations significantly improve human performance in complex systems.

Complex rules increase the perceived challenge, which explanations help mitigate.

Explanations reduce perceived difficulty when rules are more complex.

Abstract

Law codes and regulations help organise societies for centuries, and as AI systems gain more autonomy, we question how human-agent systems can operate as peers under the same norms, especially when resources are contended. We posit that agents must be accountable and explainable by referring to which rules justify their decisions. The need for explanations is associated with user acceptance and trust. This paper's contribution is twofold: i) we propose an argumentation-based human-agent architecture to map human regulations into a culture for artificial agents with explainable behaviour. Our architecture leans on the notion of argumentative dialogues and generates explanations from the history of such dialogues; and ii) we validate our architecture with a user study in the context of human-agent path deconfliction. Our results show that explanations provide a significantly higher improvement in human performance when systems are more complex. Consequently, we argue that the criteria defining the need of explanations should also consider the complexity of a system. Qualitative findings show that when rules are more complex, explanations significantly reduce the perception of challenge for humans.