Page 143 - 《软件学报》2021年第8期
P. 143
软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2021,32(8):2425−2438 [doi: 10.13328/j.cnki.jos.006191] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563
∗
面向优先车辆感知的交通灯优化控制方法
邵明莉, 曹 鹗, 胡 铭, 章 玥, 陈闻杰, 陈铭松
(上海市高可信计算重点实验室(华东师范大学),上海 200062)
通讯作者: 陈铭松, E-mail: mschen@sei.ecnu.edu.cn
摘 要: 智慧交通灯控制能够有效地改善道路交通的秩序和效率.在城市交通网络中,具有紧急任务的特殊车辆
对于通行效率的要求更高.目前已有的智慧交通灯控制算法通常对路网中的所有车辆一视同仁,没有考虑到特殊车
辆的优先性;而传统的控制特殊车辆优先通行的方法基本上都是采用信号抢占的方式,对普通车辆的通行干扰过大.
为此,提出一种面向优先车辆感知的交通灯优化控制方法,通过与道路环境的不断交互来学习交通灯控制策略,在设
置状态和奖励函数时增加特殊车辆的权重,并利用 Double DQN 和 Dueling DQN 来提升模型表现,最终在城市交通
模拟器 SUMO 中进行仿真实验.在训练趋于稳定之后,与固定时长控制方法的对比实验结果显示,该方法能够将特
殊车辆与普通车辆的平均等待时间分别缩短 68%与 22%左右;与不考虑优先级的方法相比,特殊车辆的平均等待时
间也有 35%左右的优化.验证了该方法能够在提高车辆通行效率的同时,体现出对特殊车辆的优先处理.同时,实验
也表明该方法能够扩展应用于多路口场景中.
关键词: 智慧交通;交通信号控制;强化学习;深度学习;车辆优先级
中图法分类号: TP311
中文引用格式: 邵明莉,曹鹗,胡铭,章玥,陈闻杰,陈铭松.面向优先车辆感知的交通灯优化控制方法.软件学报,2021,32(8):
2425−2438. http://www.jos.org.cn/1000-9825/6191.htm
英文引用格式: Shao ML, Cao E, Hu M, Zhang Y, Chen WJ, Chen MS. Traffic light optimization control method for priority
vehicle awareness. Ruan Jian Xue Bao/Journal of Software, 2021,32(8):2425−2438 (in Chinese). http://www.jos.org.cn/1000-
9825/6191.htm
Traffic Light Optimization Control Method for Priority Vehicle Awareness
SHAO Ming-Li, CAO E, HU Ming, ZHANG Yue, CHEN Wen-Jie, CHEN Ming-Song
(Shanghai Key Laboratory of Trustworthy Computing (East China Normal University), Shanghai 200062, China)
Abstract: Intelligent traffic light control can effectively improve the order and efficiency of road traffic. In urban traffic networks,
special vehicles with urgent tasks have higher requirements for traffic efficiency. However, current intelligent traffic light control
algorithms generally treat all vehicles equally, without considering the priority of special vehicles, while the traditional methods basically
adopt signal preemption to ensure the priority of special vehicles, which has a great influence on the passage of ordinary vehicles.
Therefore, this study proposes a traffic light optimization control method orient priority vehicle awareness. It learns traffic light control
strategies through continuous interaction with the road environment. the weight of special vehicles is increased in state definition and
reward function, and Double DQN and Dueling DQN are used to improve the performance of the model. Finally, the experiments are
carried out in the urban traffic simulator SUMO. After the training stabilizes, compared with the fixed time control method, the proposed
∗ 基金项目: 国家重点研发计划(2018YFB2101300); 国家自然科学基金(61872147); 华东师范大学优秀博士生学术创新能力提
升计划(YBNLTS2020-041)
Foundation item: National Key Research and Development Program of China (2018YFB2101300); National Natural Science
Foundation of China (61872147); Academic Innovation Promotion Program for Excellent Doctoral Students of East China Normal
University (YBNLTS2020-041)
本文由“泛在嵌入式智能系统”专题特约编辑郭兵教授、王泉教授、邓庆绪教授、陈铭松教授、张凯龙副教授推荐.
收稿时间: 2020-07-24; 修改时间: 2020-09-07; 采用时间: 2020-11-02; jos 在线出版时间: 2021-02-07
