Survey on Autonomous Vehicle Control Using Reinforcement Learning

Abstract

In this paper we study the demonstration of the application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, the model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. The paper provides a general and easy to obtain reward: the distance travelled by the vehicle without going of the lane. Model use a continuous, model free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle.This demonstrates a new framework for autonomous driving which moves away from reliance on pre determined logical rules, mapping, and direct supervision. The paper discusses the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.