Exploring applications of deep reinforcement learning for real-world autonomous driving systems

TL;DR

This paper reviews the current state of deep reinforcement learning (DRL) in autonomous driving, highlighting its successes, challenges, and the gap between synthetic environments and real-world applications.

Contribution

It provides an overview of DRL applications in autonomous driving and discusses key challenges for deploying DRL in real-world systems.

Findings

DRL has achieved notable successes like AlphaGo and commercial vehicle deployment.

Most DRL research in autonomous driving is limited to synthetic simulation environments.

Addressing real-world deployment challenges is crucial for advancing DRL in autonomous vehicles.

Abstract

Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo. It has been successfully deployed in commercial vehicles like Mobileye's path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide an overview of the tasks in autonomous driving systems, reinforcement learning algorithms and applications of DRL to AD systems. We then discuss the challenges which must be addressed to enable further progress towards real-world deployment.