Survey on Autonomous Vehicle Control Using Reinforcement Learning
Keywords:
Reinforcement Learning, Deep Learning, Self-Driving Cars, Imitation Learning, Autonomous cars and Lane Detection.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.
References
- Alex Kendall, Jeffrey Hawke, David Janz, Przemyslaw Mazur, Daniele Reda, John-Mark Allen, Vinh-Dieu Lam, “Alex Bewley, Amar Shah “Learning to Drive in a Day”, September 2018
- Mayank Bansal, Alex Krizhevsky, Abhijit Ogale, “ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst”, December 2018.
- Nihal Altunas, Erkan Imal, Nahit Emanet, Ceyda Nur Ozturk, “Reinforcement learning-based mobile robot navigation”, March 2016.
- Manon Legrand, Prof. Ann Nowe, “Deep Reinforcement Learning for Autonomous Vehicle Control among Human Drivers”, Sweden 2017
- Simon Kardell, Mattias Kuosku, “Autonomous vehicle control via deep reinforcement learning”, 2017
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.