Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control

Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinf...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenqi Fang, Shitian Zhang, Hui Huang, Shaobo Dang, Zhejun Huang, Wenfei Li, Zheng Wang, Tianfu Sun, Huiyun Li
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/2020/8495264
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109515601543168
author Wenqi Fang
Shitian Zhang
Hui Huang
Shaobo Dang
Zhejun Huang
Wenfei Li
Zheng Wang
Tianfu Sun
Huiyun Li
author_facet Wenqi Fang
Shitian Zhang
Hui Huang
Shaobo Dang
Zhejun Huang
Wenfei Li
Zheng Wang
Tianfu Sun
Huiyun Li
author_sort Wenqi Fang
collection DOAJ
description Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinforcement learning which automatically learns the decision. However, it usually requires large volume of samples. In this paper, to reduce the sample size, we exploit the deep Gaussian process, where a regression model is trained on small sample datasets and captures the most significant features correctly. Besides, to realize the real-time and close-loop control, we combine the feedback control into the process. Experimental results on the Torcs simulation engine illustrate smooth driving on virtual road which can be achieved. Compared with the amount of training data in deep reinforcement learning, our method uses only 0.34% of its size and obtains similar simulation results. It may be useful for real road tests in the future.
format Article
id doaj-art-4ab5c802bf4748e1b772fc7189250dfe
institution OA Journals
issn 0197-6729
2042-3195
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-4ab5c802bf4748e1b772fc7189250dfe2025-08-20T02:38:03ZengWileyJournal of Advanced Transportation0197-67292042-31952020-01-01202010.1155/2020/84952648495264Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback ControlWenqi Fang0Shitian Zhang1Hui Huang2Shaobo Dang3Zhejun Huang4Wenfei Li5Zheng Wang6Tianfu Sun7Huiyun Li8Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, SIAT Branch, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen 518172, ChinaAutonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinforcement learning which automatically learns the decision. However, it usually requires large volume of samples. In this paper, to reduce the sample size, we exploit the deep Gaussian process, where a regression model is trained on small sample datasets and captures the most significant features correctly. Besides, to realize the real-time and close-loop control, we combine the feedback control into the process. Experimental results on the Torcs simulation engine illustrate smooth driving on virtual road which can be achieved. Compared with the amount of training data in deep reinforcement learning, our method uses only 0.34% of its size and obtains similar simulation results. It may be useful for real road tests in the future.http://dx.doi.org/10.1155/2020/8495264
spellingShingle Wenqi Fang
Shitian Zhang
Hui Huang
Shaobo Dang
Zhejun Huang
Wenfei Li
Zheng Wang
Tianfu Sun
Huiyun Li
Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
Journal of Advanced Transportation
title Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
title_full Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
title_fullStr Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
title_full_unstemmed Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
title_short Learn to Make Decision with Small Data for Autonomous Driving: Deep Gaussian Process and Feedback Control
title_sort learn to make decision with small data for autonomous driving deep gaussian process and feedback control
url http://dx.doi.org/10.1155/2020/8495264
work_keys_str_mv AT wenqifang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT shitianzhang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT huihuang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT shaobodang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT zhejunhuang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT wenfeili learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT zhengwang learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT tianfusun learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol
AT huiyunli learntomakedecisionwithsmalldataforautonomousdrivingdeepgaussianprocessandfeedbackcontrol