混合交通中联网和自动驾驶车辆合作变道的多代理强化学习

Wei Zhou, Dong Chen, Jun Yan, Zhaojian Li, Huilin Yin, Wanchen Ge
{"title":"混合交通中联网和自动驾驶车辆合作变道的多代理强化学习","authors":"Wei Zhou,&nbsp;Dong Chen,&nbsp;Jun Yan,&nbsp;Zhaojian Li,&nbsp;Huilin Yin,&nbsp;Wanchen Ge","doi":"10.1007/s43684-022-00023-5","DOIUrl":null,"url":null,"abstract":"<div><p>Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL) has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision-making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic (MA2C) method is proposed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is designed to incorporate fuel efficiency, driving comfort, and the safety of autonomous driving. A comprehensive experimental study is made that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety, and driver comfort.</p></div>","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s43684-022-00023-5.pdf","citationCount":"0","resultStr":"{\"title\":\"Multi-agent reinforcement learning for cooperative lane changing of connected and autonomous vehicles in mixed traffic\",\"authors\":\"Wei Zhou,&nbsp;Dong Chen,&nbsp;Jun Yan,&nbsp;Zhaojian Li,&nbsp;Huilin Yin,&nbsp;Wanchen Ge\",\"doi\":\"10.1007/s43684-022-00023-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL) has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision-making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic (MA2C) method is proposed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is designed to incorporate fuel efficiency, driving comfort, and the safety of autonomous driving. A comprehensive experimental study is made that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety, and driver comfort.</p></div>\",\"PeriodicalId\":71187,\"journal\":{\"name\":\"自主智能系统(英文)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-03-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1007/s43684-022-00023-5.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"自主智能系统(英文)\",\"FirstCategoryId\":\"1093\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s43684-022-00023-5\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"自主智能系统(英文)","FirstCategoryId":"1093","ListUrlMain":"https://link.springer.com/article/10.1007/s43684-022-00023-5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在过去二十年里,自动驾驶吸引了大量研究人员的关注,因为它能带来许多潜在的好处,包括让驾驶员从疲惫的驾驶中解脱出来,缓解交通拥堵等。尽管取得了可喜的进展,但变道仍然是自动驾驶汽车(AV)面临的巨大挑战,尤其是在混合和动态交通场景中。最近,强化学习(RL)被广泛用于自动驾驶汽车的变道决策,并取得了令人鼓舞的成果。然而,这些研究大多集中在单车环境下,而在多辆自动驾驶汽车与人类驾驶汽车(HDV)共存的情况下进行变道决策却很少受到关注。在本文中,我们将混合交通高速公路环境中的多辆自动驾驶汽车变道决策问题表述为多代理强化学习(MARL)问题,其中每辆自动驾驶汽车根据相邻自动驾驶汽车和 HDV 的运动做出变道决策。具体而言,本文提出了一种多代理优势代理批评(MA2C)方法,该方法具有新颖的局部奖励设计和参数共享方案。特别是,设计了一个多目标奖励函数,将燃油效率、驾驶舒适性和自动驾驶的安全性结合在一起。通过全面的实验研究,我们提出的 MARL 框架在效率、安全性和驾驶舒适性方面始终优于多个最先进的基准。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multi-agent reinforcement learning for cooperative lane changing of connected and autonomous vehicles in mixed traffic

Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL) has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision-making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic (MA2C) method is proposed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is designed to incorporate fuel efficiency, driving comfort, and the safety of autonomous driving. A comprehensive experimental study is made that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety, and driver comfort.

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
CiteScore
3.90
自引率
0.00%
发文量
0
×
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