Applications and Challenges of Reinforcement Learning in Autonomous Driving Technology

被引：0
|
作者：
He Y. [1 ,2 ]
Lin H. [3 ]
Liu Y. [3 ]
Yang L. [2 ]
Qu X. [3 ]
机构：
[1] School of Civil Engineering and Transportation, South China University of Technology, Guangzhou
[2] School of Information Engineering, Chang’an University, Xi’an
[3] School of Vehicle and Mobility, Tsinghua University, Beijing
来源：
Tongji Daxue Xuebao/Journal of Tongji University | 2024年 / 52卷 / 04期
关键词：
artificial intelligence; autonomous driving; reinforcement learning;
D O I：
10.11908/j.issn.0253-374x.23397
中图分类号：
学科分类号：
摘要：
This paper provides a comprehensive overview and summary of the application of reinforcement learning in the field of autonomous driving. First，an introduction to the principles and development of reinforcement learning is presented. Following that，the autonomous driving technology system and the fundamentals required for the application of reinforcement learning in this field are systematically introduced. Subsequently， application cases of reinforcement learning in autonomous driving are described according to different directions of use. Finally，the current challenges of applying reinforcement learning in the field of autonomous driving are deeply analyzed，and several prospects are proposed. © 2024 Science Press. All rights reserved.
引用
收藏
页码：520 / 531
页数：11
相关论文
共 83 条
  • [81] DAI Shanshan, LIU Quan, Action constrained deep reinforcement learning based safe automatic driving method［J］, Computer Science, 48, 9, (2021)
  • [82] SHASHUA A., Safe ， multi-agent， reinforcement learning for autonomous driving［J］, (2016)
  • [83] LIU Y，, Et al., Learning to drive from simulation without real world labels ［C］, 2019 International Conference on Robotics and Automation（ICRA）, pp. 4818-4824, (2019)
123456789