Cooperative Lane Changing via Deep Reinforcement Learning

Guan Wang; Jianming Hu; Zhiheng Li; Li Li

Cooperative Lane Changing via Deep Reinforcement Learning

Systems and Control 2019-06-21 v1 Artificial Intelligence Machine Learning Systems and Control

Authors: Guan Wang , Jianming Hu , Zhiheng Li , Li Li

Abstract

In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning. We show that the reward of the system should consider the overall traffic efficiency instead of the travel efficiency of an individual vehicle. In summary, cooperation leads to a more harmonic and efficient traffic system rather than competition

Keywords

autonomous vehicle control machine learning transportation systems

Cite

@article{arxiv.1906.08662,
  title  = {Cooperative Lane Changing via Deep Reinforcement Learning},
  author = {Guan Wang and Jianming Hu and Zhiheng Li and Li Li},
  journal= {arXiv preprint arXiv:1906.08662},
  year   = {2019}
}

Comments

7 pages, 6 figures

Related papers

View all related →