基于深度强化学习的综合驾驶决策方法,适用于自动驾驶商用车辆

IF 1.5 4区 工程技术 Q3 ENGINEERING, MECHANICAL
Weiming Hu, Xu Li, Jinchao Hu, Yan Liu, Jinying Zhou
{"title":"基于深度强化学习的综合驾驶决策方法,适用于自动驾驶商用车辆","authors":"Weiming Hu, Xu Li, Jinchao Hu, Yan Liu, Jinying Zhou","doi":"10.1007/s12239-024-00135-2","DOIUrl":null,"url":null,"abstract":"<p>Effective driving decision-making significantly enhances the safety of automated commercial vehicles. Different from small passenger vehicles mainly focusing on anti-collision, the inducements of collision and rollover for commercial vehicles are coupled with each other. However, these factors are not considered together which results in a limitation in the safety performance. This paper proposes a novel comprehensive driving decision-making methodology based on deep reinforcement learning (CDDM-DRL) for automated commercial vehicles in expressway scenarios. The CDDM-DRL consists of two parts. First, a feature encoding network is designed to encode hierarchical features from traffic situations and driving conditions, which can provide more useful feature information. Then an actor–critic network incorporating ensemble methods is developed to learn and provide effective driving actions, such as whether to turn and when to turn. Finally, extensive simulations in common and challenging scenarios with different traffic densities were performed. Experimental results show that our proposed method is better than some classical DRL methods in terms of time headway, backward clearance, lateral acceleration, etc. Moreover, it can prevent collision and rollover simultaneously, and realize safe driving decision-making for automated commercial vehicles.</p>","PeriodicalId":50338,"journal":{"name":"International Journal of Automotive Technology","volume":"37 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Comprehensive Driving Decision-Making Methodology Based on Deep Reinforcement Learning for Automated Commercial Vehicles\",\"authors\":\"Weiming Hu, Xu Li, Jinchao Hu, Yan Liu, Jinying Zhou\",\"doi\":\"10.1007/s12239-024-00135-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Effective driving decision-making significantly enhances the safety of automated commercial vehicles. Different from small passenger vehicles mainly focusing on anti-collision, the inducements of collision and rollover for commercial vehicles are coupled with each other. However, these factors are not considered together which results in a limitation in the safety performance. This paper proposes a novel comprehensive driving decision-making methodology based on deep reinforcement learning (CDDM-DRL) for automated commercial vehicles in expressway scenarios. The CDDM-DRL consists of two parts. First, a feature encoding network is designed to encode hierarchical features from traffic situations and driving conditions, which can provide more useful feature information. Then an actor–critic network incorporating ensemble methods is developed to learn and provide effective driving actions, such as whether to turn and when to turn. Finally, extensive simulations in common and challenging scenarios with different traffic densities were performed. Experimental results show that our proposed method is better than some classical DRL methods in terms of time headway, backward clearance, lateral acceleration, etc. Moreover, it can prevent collision and rollover simultaneously, and realize safe driving decision-making for automated commercial vehicles.</p>\",\"PeriodicalId\":50338,\"journal\":{\"name\":\"International Journal of Automotive Technology\",\"volume\":\"37 1\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Automotive Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s12239-024-00135-2\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Automotive Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12239-024-00135-2","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0

摘要

有效的驾驶决策可大大提高自动驾驶商用车辆的安全性。与以防碰撞为主的小型乘用车不同,商用车辆的碰撞和侧翻诱因是相互关联的。然而,这些因素没有被一并考虑,导致安全性能受到限制。本文提出了一种基于深度强化学习的新型综合驾驶决策方法(CDDM-DRL),适用于高速公路场景下的自动驾驶商用车辆。CDDM-DRL 包括两个部分。首先,设计了一个特征编码网络,对交通状况和驾驶条件中的分层特征进行编码,从而提供更有用的特征信息。然后,开发了一个包含集合方法的行为批判网络,以学习和提供有效的驾驶操作,如是否转弯和何时转弯。最后,我们在不同交通密度的常见场景和具有挑战性的场景中进行了大量模拟。实验结果表明,我们提出的方法在时间车距、后退间隙、横向加速度等方面都优于一些经典的 DRL 方法。此外,它还能同时防止碰撞和侧翻,实现自动驾驶商用车辆的安全驾驶决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

A Comprehensive Driving Decision-Making Methodology Based on Deep Reinforcement Learning for Automated Commercial Vehicles

A Comprehensive Driving Decision-Making Methodology Based on Deep Reinforcement Learning for Automated Commercial Vehicles

Effective driving decision-making significantly enhances the safety of automated commercial vehicles. Different from small passenger vehicles mainly focusing on anti-collision, the inducements of collision and rollover for commercial vehicles are coupled with each other. However, these factors are not considered together which results in a limitation in the safety performance. This paper proposes a novel comprehensive driving decision-making methodology based on deep reinforcement learning (CDDM-DRL) for automated commercial vehicles in expressway scenarios. The CDDM-DRL consists of two parts. First, a feature encoding network is designed to encode hierarchical features from traffic situations and driving conditions, which can provide more useful feature information. Then an actor–critic network incorporating ensemble methods is developed to learn and provide effective driving actions, such as whether to turn and when to turn. Finally, extensive simulations in common and challenging scenarios with different traffic densities were performed. Experimental results show that our proposed method is better than some classical DRL methods in terms of time headway, backward clearance, lateral acceleration, etc. Moreover, it can prevent collision and rollover simultaneously, and realize safe driving decision-making for automated commercial vehicles.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
International Journal of Automotive Technology
International Journal of Automotive Technology 工程技术-工程:机械
CiteScore
3.10
自引率
12.50%
发文量
129
审稿时长
6 months
期刊介绍: The International Journal of Automotive Technology has as its objective the publication and dissemination of original research in all fields of AUTOMOTIVE TECHNOLOGY, SCIENCE and ENGINEERING. It fosters thus the exchange of ideas among researchers in different parts of the world and also among researchers who emphasize different aspects of the foundations and applications of the field. Standing as it does at the cross-roads of Physics, Chemistry, Mechanics, Engineering Design and Materials Sciences, AUTOMOTIVE TECHNOLOGY is experiencing considerable growth as a result of recent technological advances. The Journal, by providing an international medium of communication, is encouraging this growth and is encompassing all aspects of the field from thermal engineering, flow analysis, structural analysis, modal analysis, control, vehicular electronics, mechatronis, electro-mechanical engineering, optimum design methods, ITS, and recycling. Interest extends from the basic science to technology applications with analytical, experimental and numerical studies. The emphasis is placed on contributions that appear to be of permanent interest to research workers and engineers in the field. If furthering knowledge in the area of principal concern of the Journal, papers of primary interest to the innovative disciplines of AUTOMOTIVE TECHNOLOGY, SCIENCE and ENGINEERING may be published. Papers that are merely illustrations of established principles and procedures, even though possibly containing new numerical or experimental data, will generally not be published. When outstanding advances are made in existing areas or when new areas have been developed to a definitive stage, special review articles will be considered by the editors. No length limitations for contributions are set, but only concisely written papers are published. Brief articles are considered on the basis of technical merit.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信