Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions

TL;DR

This paper provides a comprehensive overview of explainable AI techniques for autonomous vehicles, highlighting current approaches, proposing a conceptual framework, and outlining future research directions to improve transparency and societal acceptance.

Contribution

It offers a thorough review of XAI methods in autonomous driving, introduces a conceptual framework, and suggests future research directions for enhancing transparency and trust.

Findings

Overview of state-of-the-art XAI approaches for AVs

A proposed conceptual framework for explainable autonomous driving

Identification of promising future research directions

Abstract

Autonomous driving has achieved significant milestones in research and development over the last two decades. There is increasing interest in the field as the deployment of autonomous vehicles (AVs) promises safer and more ecologically friendly transportation systems. With the rapid progress in computationally powerful artificial intelligence (AI) techniques, AVs can sense their environment with high precision, make safe real-time decisions, and operate reliably without human intervention. However, intelligent decision-making in such vehicles is not generally understandable by humans in the current state of the art, and such deficiency hinders this technology from being socially acceptable. Hence, aside from making safe real-time decisions, AVs must also explain their AI-guided decision-making process in order to be regulatory compliant across many jurisdictions. Our study sheds comprehensive light on the development of explainable artificial intelligence (XAI) approaches for AVs. In particular, we make the following contributions. First, we provide a thorough overview of the state-of-the-art and emerging approaches for XAI-based autonomous driving. We then propose a conceptual framework that considers the essential elements for explainable end-to-end autonomous driving. Finally, we present XAI-based prospective directions and emerging paradigms for future directions that hold promise for enhancing transparency, trustworthiness, and societal acceptance of AVs.