CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving; Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving
Dong Li1,2; Dongbin Zhao1,2; Qichao Zhang1,2; Yaran Chen1,2
Source PublicationIEEE Computational Intelligence Magazine ; IEEE Computational Intelligence Magazine
ISSN1556-603X ; 1556-603X
2019-04 ; 2019-04
Volume14Issue:2Pages:83-98
Abstract

This paper investigates the vision-based autonomous driving with deep learning and reinforcement learning methods. Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a perception module and a control module. The perception module which is based on a multi-task learning neural network first takes a driver-view image as its input and predicts the track features. The control module which is based on reinforcement learning then makes a control decision based on these features. In order to improve the data efficiency, we propose visual TORCS (VTORCS), a deep reinforcement learning environment which is based on the open racing car simulator (TORCS). By means of the provided functions, one can train an agent with the input of an image or various physical sensor measurement, or evaluate the perception algorithm on this simulator. The trained reinforcement learning controller outperforms the linear quadratic regulator (LQR) controller and model predictive control (MPC) controller on different tracks. The experiments demonstrate that the perception module shows promising performance and the controller is capable of controlling the vehicle drive well along the track center with visual input.

;

This paper investigates the vision-based autonomous driving with deep learning and reinforcement learning methods. Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a perception module and a control module. The perception module which is based on a multi-task learning neural network first takes a driver-view image as its input and predicts the track features. The control module which is based on reinforcement learning then makes a control decision based on these features. In order to improve the data efficiency, we propose visual TORCS (VTORCS), a deep reinforcement learning environment which is based on the open racing car simulator (TORCS). By means of the provided functions, one can train an agent with the input of an image or various physical sensor measurement, or evaluate the perception algorithm on this simulator. The trained reinforcement learning controller outperforms the linear quadratic regulator (LQR) controller and model predictive control (MPC) controller on different tracks. The experiments demonstrate that the perception module shows promising performance and the controller is capable of controlling the vehicle drive well along the track center with visual input.

KeywordDeep Learning Autonomous Driving Visual Control Reinforcement Learning Deep Learning Autonomous Driving Visual Control Reinforcement Learning
Indexed BySCI ; SCI
Language英语 ; 英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23517
Collection复杂系统管理与控制国家重点实验室_深度强化学习
Corresponding AuthorDongbin Zhao
Affiliation1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Dong Li,Dongbin Zhao,Qichao Zhang,et al. Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving, Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving[J]. IEEE Computational Intelligence Magazine, IEEE Computational Intelligence Magazine,2019, 2019,14, 14(2):83-98, 83-98.
APA Dong Li,Dongbin Zhao,Qichao Zhang,&Yaran Chen.(2019).Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving.IEEE Computational Intelligence Magazine,14(2),83-98.
MLA Dong Li,et al."Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving".IEEE Computational Intelligence Magazine 14.2(2019):83-98.
Files in This Item:
File Name/Size DocType Version Access License
2019.CIM_LiZhaoZhang(2205KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Dong Li]'s Articles
[Dongbin Zhao]'s Articles
[Qichao Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Dong Li]'s Articles
[Dongbin Zhao]'s Articles
[Qichao Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Dong Li]'s Articles
[Dongbin Zhao]'s Articles
[Qichao Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2019.CIM_LiZhaoZhangChen.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.