A Method of Deep Reinforcement Learning for Simulation of Autonomous Vehicle Control

Anh Huynh, Anh Huynh, Ba-Tung Nguyen, Ba-Tung Nguyen, Hoai-Thu Nguyen, Hoai-Thu Nguyen, Sang Vu, Sang Vu, Hien Nguyen, Hien Nguyen

Abstract

Nowadays autonomous driving is expected to revolutionize the transportation sector. Carmakers, researchers, and administrators have been working on this field for years and significant progress has been made. However, the doubts and challenges to overcome are still huge, regarding not only complex technologies but also human awareness, culture, current traffic infrastructure. In terms of technical perspective, the accurate detection of obstacles, avoiding adjacent obstacles, and automatic navigation through the environment are some of the difficult problems. In this paper, an approach for solving those problems is proposed by using of Policy Gradient to control a simulated car via reinforcement learning. The proposed method is worked effectively to train an agent to control the simulated car in Unity ML-agents Highway, which is a simulating environment. This environment is chosen from some criteria of an environment simulating autonomous vehicle. The testing of the proposed method got positive results. Beside the average speed was well, the agent successfully learned the turning operation, progressively gaining the ability to navigate larger sections of the simulated raceway without crashing.

Download


Paper Citation


in Harvard Style

Huynh A., Nguyen B., Nguyen H., Vu S. and Nguyen H. (2021). A Method of Deep Reinforcement Learning for Simulation of Autonomous Vehicle Control. In Proceedings of the 16th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE, ISBN 978-989-758-508-1, pages 372-379. DOI: 10.5220/0010478903720379


in Bibtex Style

@conference{enase21,
author={Anh Huynh and Ba-Tung Nguyen and Hoai-Thu Nguyen and Sang Vu and Hien Nguyen},
title={A Method of Deep Reinforcement Learning for Simulation of Autonomous Vehicle Control},
booktitle={Proceedings of the 16th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,},
year={2021},
pages={372-379},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010478903720379},
isbn={978-989-758-508-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE,
TI - A Method of Deep Reinforcement Learning for Simulation of Autonomous Vehicle Control
SN - 978-989-758-508-1
AU - Huynh A.
AU - Nguyen B.
AU - Nguyen H.
AU - Vu S.
AU - Nguyen H.
PY - 2021
SP - 372
EP - 379
DO - 10.5220/0010478903720379