Autonomous Car Driving Based on Deep Reinforcement Learning

DOI

10.2991/978-94-6463-052-7_95How to use a DOI?

Keywords

deep reinforcement learning; autonomous driving; twin delay depth certainty gradient strategy algorithm

Abstract

Autonomous driving car is an important direction for the future automobile development. In order to make its algorithm have better learning ability and decision-making ability, this paper proposes the M_TD3 algorithm by improving the TD3 algorithm. Improve the sampling method and redivide the experience pool into temporary, success and failure experience pools, with the data structure of the binary tree for each experience as a node. Through a large number of simulation experiments, the model of this algorithm is constructed and analyzed and verified with other algorithms. It is proved that the vehicle controlled by the M_TD3 algorithm has a higher running speed and has a guarantee of high safety and high comfort, besides the experiment verified the feasibility of this model.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zelin Zhang
PY  - 2022
DA  - 2022/12/27
TI  - Autonomous Car Driving Based on Deep Reinforcement Learning
BT  - Proceedings of the 2022 International Conference on Economics, Smart Finance and Contemporary Trade (ESFCT 2022)
PB  - Atlantis Press
SP  - 835
EP  - 842
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-052-7_95
DO  - 10.2991/978-94-6463-052-7_95
ID  - Zhang2022
ER  -