A Surrogate Model Framework for Explainable Autonomous Behaviour

TL;DR

This paper introduces a surrogate model framework that enhances transparency and explainability of autonomous systems by breaking down their behavior into understandable components suitable for natural language explanations, addressing safety and stakeholder communication needs.

Contribution

The work presents a novel surrogate model approach that is agnostic to the autonomous system, allowing for easy updates and tailored explanations for diverse stakeholders.

Findings

Surrogate models effectively explain autonomous agent behaviors.

The approach enables natural language explanations of complex policies.

The framework improves transparency and stakeholder understanding.

Abstract

Adoption and deployment of robotic and autonomous systems in industry are currently hindered by the lack of transparency, required for safety and accountability. Methods for providing explanations are needed that are agnostic to the underlying autonomous system and easily updated. Furthermore, different stakeholders with varying levels of expertise, will require different levels of information. In this work, we use surrogate models to provide transparency as to the underlying policies for behaviour activation. We show that these surrogate models can effectively break down autonomous agents' behaviour into explainable components for use in natural language explanations.