[1] Bie Yiming, Wang Dianhai, Ma Dongfang, Zhu Zibo, et al. A distributed algorithm for signal coordination of multiple agentswith embedded platoon dispersion model [J]. Journal of Southeast University (English Edition), 2011, 27 (3): 311-315. [doi:10.3969/j.issn.1003-7985.2011.03.017]

Copy

A distributed algorithm for signal coordination of multiple agentswith embedded platoon dispersion model()

基于车队离散模型的分布式多智能体信号协调控制算法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

27

Issue:

2011 3

Page:

311-315

Research Field:

Traffic and Transportation Engineering

Publishing date:

2011-09-30

Info

Title:

A distributed algorithm for signal coordination of multiple agentswith embedded platoon dispersion model

基于车队离散模型的分布式多智能体信号协调控制算法

Author(s):

Bie Yiming¹;  Wang Dianhai²;  Ma Dongfang¹;  Zhu Zibo¹

¹ College of Transportation, Jilin University, Changchun 130025, China
² College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China

别一鸣¹;  王殿海²;  马东方¹;  朱自博¹

¹ 吉林大学交通学院, 长春 130025; ² 浙江大学建筑工程学院, 杭州 310058

Keywords:

multiple agents;  signal coordination;  reinforce learning;  platoon dispersion model

多智能体;  信号协调;  增强学习;  车队离散模型

PACS:

U491

DOI:

10.3969/j.issn.1003-7985.2011.03.017

Abstract:

In order to reduce average arterial vehicle delay, a novel distributed and coordinated traffic control algorithm is developed using the multiple agent system and the reinforce learning(RL). The RL is used to minimize average delay of arterial vehicles by training the interaction ability between agents and exterior environments. The Robertson platoon dispersion model is embedded in the RL algorithm to precisely predict platoon movements on arteries and then the reward function is developed based on the dispersion model and delay equations cited by HCM2000. The performance of the algorithm is evaluated in a Matlab environment and comparisons between the algorithm and the conventional coordination algorithm are conducted in three different traffic load scenarios. Results show that the proposed algorithm outperforms the conventional algorithm in all the scenarios. Moreover, with the increase in saturation degree, the performance is improved more significantly. The results verify the feasibility and efficiency of the established algorithm.

为减少干线协调交叉口的车辆延误, 基于多智能体系统与增强学习算法(RL)建立了一种新的分布式交通信号协调算法.增强学习算法通过训练各个智能体与外界环境的交互能力达到减少车辆延误的目的.为更精确地描述干线上的车队运动规律, 引入了罗伯逊车队离散模型, 并基于该模型以及HCM2000中的干线交叉口车流延误计算公式建立了RL中的回报函数.在Matlab中仿真验证了所建算法的控制效果, 并在3种不同交通负荷下与传统信号协调算法进行对比.结果表明, 该算法较传统算法能有效降低干线车流延误;并且随着干线饱和度的增加降低幅度逐渐增大.该结果验证了所建算法的可行性与有效性.

References:

[1] National Transportation Operations Coalition. National traffic signal report card [R]. Washington, DC: National Research Council, 2005.
[2] Little J D C, Kelson M D, Gartner N. MAXBAND: a program for setting signals on arterials and triangular networks [J]. Journal of Transportation Research Record, 1981, 75: 40-46.
[3] Lin L T, Tung L W, Ku H C. Synchronized signal control model for maximizing progression along an arterial [J]. Journal of Transportation Engineering, 2010, 36(8): 727-735.
[4] Xu Jianmin. Traffic management and control [M].Beijing: China Communications Press, 2007:230-240.(in Chinese)
[5] Choy M C, Srinivasan D, Cheu R L. Hybrid agent architecture for real-time traffic signal control [J].IEEE Transactions on Systems, Man, and Cybernetics, 2003, 33(5): 597-607.
[6] Liu A C, Urbanik T, Kohls A G.. Reinforcement learning-based multi-agent system for network traffic signal control [J]. IET Intelligent Transportation Systems, 2010, 4(2):128-135.
[7] Yang Q F, Yang C. On-line selection method of the traffic control and route guidance collaboration mode based on Q learning algorithm [J]. Journal of Jilin University: Engineering and Technology Edition, 2010, 40(5):1215-1219.(in Chinese)
[8] Huang Yanguo, Tang Jun, Xu Lunhui. Urban road traffic signal control method based on agent [J]. Journal of Highway and Transportation Research and Development, 2009, 26(10): 126-129.(in Chinese)
[9] Ma Shoufeng, Li Ying, Liu Bao. Agent-based learning control method for urban traffic signal of single intersection [J]. Journal of System Engineering, 2003, 18(3):273-278.(in Chinese)
[10] Abdulhai B. Reinforcement learning for the true adaptive traffic signal control [J]. Journal of Transportation Engineering, 2003, 129(3):278-285.
[11] Oliveira L D B, Camponogara E. Multi-agent model predictive control of signaling split in urban traffic networks [J]. Transportation Research Part C, 2010, 18(1):120-139.
[12] Wiering M. Multi-agent reinforcement learning for traffic light control [C]// Proceedings of the 17th International Conference on Machine Learning. San Francisco, CA, USA, 2000: 1151-1158.
[13] Wang Dianhai. Traffic flow theory [M]. Beijing: China Communications Press, 2002:146-147.(in Chinese)
[14] Transportation Research Board. Highway capacity manual [R]. Washington, DC: National Research Council, 2000.

Memo

Memo:

Biographies: Bie Yiming(1986—), male, graduate; Wang Dianhai(corresponding author), male, professor, wangdianhai@sohu.com.
Foundation items: The National Key Technology R&D Program during the 11th Five-Year Plan Period of China(No.2009BAG17B02), the National High Technology Research and Development Program of China(863 Program)(No.2011AA110304), the National Natural Science Foundation of China(No.50908100).
Citation: Bie Yiming, Wang Dianhai, Ma Dongfang, et al. A distributed algorithm for signal coordination of multiple agents with embedded platoon dispersion model[J].Journal of Southeast University(English Edition), 2011, 27(3):311-315.[doi:10.3969/j.issn.1003-7985.2011.03.017]

Common functions