智能网联环境下多簇交通波消散的车辆群体协同控制方法

doi:10.16097/j.cnki.1009-6744.2026.05.007

交通运输系统工程与信息 ›› 2026, Vol. 26 ›› Issue (5): 79-88.DOI: 10.16097/j.cnki.1009-6744.2026.05.007

智能网联环境下多簇交通波消散的车辆群体协同控制方法

杨静文¹，齐旭东²，王萍^*3，夏新海¹

1. 广州航海学院，未来交通学院，广州510725；2.西安建筑科技大学，城市发展与现代交通学院，西安710055； 3. 中山大学，智能工程学院，广东深圳518107

收稿日期:2026-04-26 修回日期:2026-06-26 接受日期:2026-07-08 出版日期:2026-10-25 发布日期:2026-10-21
作者简介:杨静文（1996—），女，安徽阜阳人，讲师，博士。
基金资助:
国家自然科学基金 (52372321)。

Cooperative Vehicle Group Control for Mitigating Multi-cluster Traffic Waves in Connected and Automated Vehicles Environments

YANG Jingwen¹, QI Xudong², WANG Ping^*3, XIA Xinhai¹

1. Future Transportation College, Guangzhou Maritime University, Guangzhou 510725, China; 2. School of Urban Development and Modern Transportation, Xi'an University of Architecture and Technology, Xi'an 710055, China; 3. School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, Guangdong, China

Received:2026-04-26 Revised:2026-06-26 Accepted:2026-07-08 Online:2026-10-25 Published:2026-10-21
Supported by:
National Natural Science Foundation of China (52372321)。

摘要/Abstract

摘要： 针对多汇入区走廊中多簇交通波传播难以协同调控，且现有方法缺乏跨区域协同与精细化调控能力的问题，本文提出一种基于深度强化学习的分布式车辆群体协同控制方法。首先，根据汇入区结构与控制对象对走廊进行单元划分与分组，构建可扩展的模块化架构，实现对走廊交通系统的统一建模，从而将多簇交通波消散问题转化为多智能体协同决策问题。其次，考虑交通流交互特性对瓶颈通行能力的动态影响，协同设计状态空间与奖励函数，构建面向车辆群体的车道级速度控制模型。最后，基于多智能体近端策略优化算法训练分布式控制策略，通过多车道限速联合决策实现车道层协同调控，以提升多瓶颈交通系统的整体运行性能。仿真结果表明，控制周期为30s时，所提方法在停车次数、平均等待时间和潜在碰撞次数上分别降低49.88%、80.65%和26.84%。该方法将控制粒度由路段级细化至车道级，控制范围由单瓶颈拓展至多瓶颈，实现了交通系统跨层级的协同优化。

关键词: 智能交通, 协同控制, 多智能体近端策略优化算法, 多瓶颈走廊, 深度强化学习

Abstract: To address the difficulties of cooperatively regulating multi-cluster traffic waves in a freeway corridor, as well as the limitations of existing methods in cross-region coordination and fine-grained control, this paper proposes a distributed cooperative vehicle-group control method based on deep reinforcement learning. First, the corridor is divided into some units and groups according to the merge-area structure and control objects. A scalable modular architecture is then constructed to enable unified modeling of the corridor traffic system, which transforms the dissipation of multi-cluster traffic waves into a multi-agent cooperative decision-making problem. Second, considering the dynamic influence of traffic-flow interactions on bottleneck capacity, the state space and reward function is designed, and a lane-level speed control model for vehicle groups is developed. Finally, a distributed control policy is trained based on the multi-agent proximal policy optimization algorithm. Lane-level cooperative regulation is achieved through joint decision-making of multi-lane speed limits, which improves the overall operational performance of the multi-bottleneck traffic system. Simulation results show that the proposed method reduces the number of stops, average waiting time, and potential collisions by 49.88%, 80.65% and 26.84% respectively under a control interval of 30 seconds. By refining the control granularity from the road-segment level to the lane level and extending the control scope from a single bottleneck to multiple bottlenecks, the proposed method realizes the cross-level collaborative optimization of traffic system.

Key words: intelligent transportation, cooperative control, multi-agent proximal policy optimization (MAPPO), multi-bottleneck corridor, deep reinforcement learning

中图分类号:

U491.4

杨静文, 齐旭东, 王萍, 夏新海. 智能网联环境下多簇交通波消散的车辆群体协同控制方法[J]. 交通运输系统工程与信息, 2026, 26(5): 79-88.

YANG Jingwen, QI Xudong, WANG Ping, XIA Xinhai. Cooperative Vehicle Group Control for Mitigating Multi-cluster Traffic Waves in Connected and Automated Vehicles Environments[J]. Journal of Transportation Systems Engineering and Information Technology, 2026, 26(5): 79-88.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2026.05.007

http://www.tseit.org.cn/CN/Y2026/V26/I5/79

参考文献

[1]ZHANG R, XU S, YU R, et al. Enhancing multi-scenario applicability of freeway variable speed limit control strategies using continual learning[J]. Accident Analysis &Prevention, 2024, 204: 107645.

[2] YANG J, QI X, WANG P, et al. Multi-agent reinforcement learning-based ramp metering control for enhancing mainline efficiency in freeway corridors[C]// CICTP 2025, Guangzhou, China: American Society of Civil Engineers, 2025: 340-350.

[3] YUAN T, ALASIRI F, IOANNOU P A. Selection of the speed command distance for improved performance of a rule-based VSL and lane change control[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19348-19357.

[4]JIN H Y, JIN W L. Control of a lane-drop bottleneck through variable speed limits[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 568-584.

[5]HAN Y, WANG M, HE Z, et al. A linear lagrangian model predictive controller of macro-and micro-variable speed limits to eliminate freeway jam waves[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103121.

[6]TODOROVIĆ U, FREJO J R D, DE SCHUTTER B. Distributed MPC for large freeway networks using alternating optimization[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23: 1875-1884.

[7]DING H, ZHANG L, CHEN J, et al. MPC-based dynamic speed control of CAVs in multiple sections upstream of the bottleneck area within a mixed vehicular environment [J]. Physica A: Statistical Mechanics and Its Applications, 2023, 613: 128542.

[8]韩磊,张轮,郭为安.混合交通流环境下基于改进强化学习的可变限速控制策略[J].交通运输系统工程与信息, 2023, 23(3): 110-122. [HAN L, ZHANG L, GUO W A. Variable speed limit control based on improved dueling double deep Q network under mixed traffic environment[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 110-122.]

[9] LU W, YI Z, GU Y, et al. TD3LVSL: A lane-level variable speed limit approach based on twin delayed deep deterministic policy gradient in a connected automated vehicle environment[J]. Transportation Research Part C: Emerging Technologies, 2023, 153: 104221.

[10] LU X Y, SHLADOVER S E, JAWAD I, et al. Novel algorithm for variable speed limits and advisories for a freeway corridor with multiple bottlenecks[J]. Transportation Research Record, 2015, 2489(1): 86-96.

[11] 宿永辉, 欧阳涛,潘新福,等.面向高速公路连续瓶颈的协同可变限速控制[J].交通运输工程与信息学报, 2024, 22(3): 166-180. [SU Y H, OUYANG T, PAN X F, et al. A collaborative variable speed limit control for continuous bottlenecks on freeways[J]. Journal of Transportation Engineering and Information, 2024, 22 (3): 166-180.]

[12] WANG C, XU Y, ZHANG J, et al. Integrated traffic control for freeway recurrent bottleneck based on deep reinforcement learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9): 15522 15535.

[13] ZHANG Y, QUINONES-GRUEIRO M, ZHANG Z, et al. MARVEL: Bringing multi-agent reinforcement-learning based variable speed limit controllers closer to deployment[J]. IEEE Access, 2024, 12: 161995-162014.

[14] HAN L, ZHANG L, PAN H. Improved multi-agent deep reinforcement learning-based integrated control for mixed traffic flow in a freeway corridor with multiple bottlenecks[J]. Transportation Research Part C: Emerging Technologies, 2025, 174: 105077.

[15] 孙剑, 胡家琦,孙杰.城市快速路交织区通行能力估计模型[J]. 中国公路学报,2016, 29(4): 114-122. [SUN J, HU J Q, SUN J. Capacity estimation model on weaving segments of urban expressway[J]. China Journal of Highway and Transport, 2016, 29(4): 114-122.]

智能网联环境下多簇交通波消散的车辆群体协同控制方法

Cooperative Vehicle Group Control for Mitigating Multi-cluster Traffic Waves in Connected and Automated Vehicles Environments

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	奇格奇, 董镇滔, 栾正凯, 关伟. 驾驶人脑电研究综述：状态感知、认知解码与人机交互协同[J]. 交通运输系统工程与信息, 2026, 26(5): 1-21.
[2]	陈坚, 胡功明, 简洪波, 傅志妍. 基于社交媒体数据的交通突发事件提取方法[J]. 交通运输系统工程与信息, 2026, 26(5): 122-131.
[3]	翁金贤 , 郭豪飞, 丁海峰. 基于驾驭工程的临时集卡专用道作业区粒流协同控制方法[J]. 交通运输系统工程与信息, 2026, 26(5): 173-183.
[4]	杜凯, 刘会洋, 何启航, 于艳波, 陈丹, 宋京妮. 融合车辆轨迹预测的高速匝道自动驾驶车辆汇入控制方法[J]. 交通运输系统工程与信息, 2026, 26(5): 184-196.
[5]	邹复民, 江林文, 蔡祈钦, 廖律超, 赖树坤. 考虑轨迹语义与时空关联的高速公路行程时间预测方法[J]. 交通运输系统工程与信息, 2026, 26(5): 227-237.
[6]	张建华, 陈云帅. 面向时空约束的网联车匝道合流分层协同控制[J]. 交通运输系统工程与信息, 2026, 26(5): 238-247.
[7]	程国柱, 罗天健, 王文志, 梁嘉祺, 冯天军. 城市快速路施工区上游智能网联汽车协同换道方法研究[J]. 交通运输系统工程与信息, 2026, 26(5): 386-402.
[8]	薛晴婉, 张先喆, 杨林溢, 闫睿轩, 王力. 辅助驾驶环境下融合驾驶行为熵的交叉口碰撞风险预测[J]. 交通运输系统工程与信息, 2026, 26(4): 112-123.
[9]	岳睿, 葛荣熙, 刘世杰, 杨广川, 林冬梅, 田宗忠. 网联车辆环境下干线信号与可变限速协同控制方法[J]. 交通运输系统工程与信息, 2026, 26(4): 124-136.
[10]	贾彦峰, 李富贵, 曲大义, 胡星辰, 李妍妍. 人工势场增强的网联异构车队分布式非线性纵横向耦合控制[J]. 交通运输系统工程与信息, 2026, 26(4): 148-161.
[11]	何永明, 那浩轩, 金玉凤, 张龙龙. 考虑交通流态势的自动驾驶车辆换道轨迹模型[J]. 交通运输系统工程与信息, 2026, 26(4): 162-172.
[12]	王昊, 陈旭梅. 考虑异质驾驶行为的智能网联车辆超车应对策略研究[J]. 交通运输系统工程与信息, 2026, 26(4): 173-187.
[13]	何子昂, 韩雨, 俞灏, 赵佳慧, 朱顺应. 基于宏观基本图的快速路多瓶颈与衔接路网优化控制方法[J]. 交通运输系统工程与信息, 2026, 26(4): 188-201.
[14]	马千里, 焦乙恩, 周屹恒, 贾鹏. 机场混编摆渡车队高峰小时服务调度优化[J]. 交通运输系统工程与信息, 2026, 26(4): 321-331.
[15]	程华, 张扬, 向飞, 马吉震, 唐明杰. 基于深度强化学习的机场地面保障调度方法[J]. 交通运输系统工程与信息, 2026, 26(4): 380-390.