Toward Fully Autonomous Driving: AI, Challenges, Opportunities, and Needs

TL;DR

This paper reviews the current state and future challenges of fully autonomous driving, emphasizing AI's role in overcoming complexities, while addressing safety, transferability, and technological needs for advancement.

Contribution

It provides a comprehensive analysis of AI's impact on autonomous driving, identifying key challenges, limitations, and research needs for achieving full autonomy.

Findings

AI outperforms classical methods in handling complex driving scenarios

Safety and transferability remain critical challenges for autonomous vehicles

Technological advancements are needed to address open-world uncertainties

Abstract

Automated driving (AD) is promising, but the transition to fully autonomous driving is, among other things, subject to the real, ever-changing open world and the resulting challenges. However, research in the field of AD demonstrates the ability of artificial intelligence (AI) to outperform classical approaches, handle higher complexities, and reach a new level of autonomy. At the same time, the use of AI raises further questions of safety and transferability. To identify the challenges and opportunities arising from AI concerning autonomous driving functionalities, we have analyzed the current state of AD, outlined limitations, and identified foreseeable technological possibilities. Thereby, various further challenges are examined in the context of prospective developments. In this way, this article reconsiders fully autonomous driving with respect to advancements in the field of AI and carves out the respective needs and resulting research questions.