End-to-End Race Driving with Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach for end-to-end race driving that learns directly from RGB images, achieving robust control and generalization in a realistic rally simulation.

Contribution

It proposes new reward and learning strategies within an A3C framework for end-to-end driving without mediated perception, demonstrating improved convergence and robustness.

Findings

Faster convergence with new reward strategies

Robust driving across diverse tracks and conditions

Some domain adaptation to real image sequences

Abstract

We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to faster convergence and more robust driving using only RGB image from a forward facing camera. An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road structures (turns, hills), graphics (seasons, location) and physics (road adherence). A thorough evaluation is conducted and generalization is proven on unseen tracks and using legal speed limits. Open loop tests on real sequences of images show some domain adaption capability of our method.