CORC  > 自动化研究所  > 中国科学院自动化研究所  > 毕业生  > 博士学位论文
题名基于移动多Agent的城市交通信号控制系统的研究
作者李镇江
学位类别工学博士
答辩日期2007-12-25
授予单位中国科学院研究生院
授予地点中国科学院自动化研究所
导师王飞跃 ; 汤淑明
关键词基于Agent的控制 多Agent系统 移动Agent 协调控制 基于特定应用的操作系统 Agent-based control Multi-agent system Mobile agent Coordination control ASOS
其他题名A Study of Urban Traffic Signal Control Systems Based on Mobile Multi-Agent Technology
学位专业控制理论与控制工程
中文摘要交通是关乎国计民生的重要领域。城市规模扩大、汽车数量增加,带来了交通拥堵、环境污染、能源消耗和交通事故等一系列问题。城市交通信号控制系统是智能交通系统的重要子系统,在改善交通状况、提高交通安全等方面发挥着重要的作用。目前,网络化已成为交通信号控制系统的发展趋势,将连通环境下联网系统的基于Agent的控制方法应用于交通信号控制系统,以移动Agent和多Agent技术为基础,将交通控制算法设计为交通控制Agent,实现交通控制Agent之间的协调合作,确立交通控制Agent的运行机制和工作流程,从而建立智能高效的城市交通信号控制系统是本文的主要研究内容。 论文首先回顾了城市交通信号控制系统的发展概况,介绍了其中一些有代表性的系统,分析了基于Agent的交通控制研究现状,总结了当前交通信号控制系统中存在的问题,提出了本文的研究方向和主要研究内容,随后各章从理论基础和应用研究两个方面对基于移动多Agent的城市交通信号控制系统进行了系统的研究。 在理论基础方面,从交通控制算法到交通控制Agent的转变出发,分析了实现这种转变的原因、意义和方法,并利用移动Agent技术,结合现有的交通控制算法,设计实现了定时、感应、模糊等5种交通控制Agent,对它们的控制效果进行了仿真验证。其次,研究了交通控制Agent的区域协调方法,控制Agent通过与相邻路口的控制Agent进行通信和协商,并按设定的规则进行模糊推理,调整其控制参数和控制行为,实现交通信号控制系统的区域协调控制和优化。最后,研究了交通控制Agent的运行机制和切换规则,采用分层递阶智能控制系统的划分方法,将交通信号控制系统分为中心组织层、区域协调层和现场执行层,分析了每一层的功能和相互之间的关系,给出了交通控制Agent从中心组织层到现场执行层的主导运行机制和工作流程,并给出了交通控制Agent在现场执行设备上的切换规则。 在应用研究方面,对系统的三层分别进行了实验研究。首先,基于JADE Agent开发平台进行了中心组织层和区域协调层软件平台的设计和开发,从控制Agent的行为实现、控制Agent移动、控制Agent通信、交通控制系统本体定义等方面给出了软件平台的设计和实现方法,并利用TSIS交通仿真软件对系统中心组织层和区域协调层的控制进行了仿真研究,验证了其控制的有效性。其次,进行了现场执行层的核心设备交通信号控制器的设计,利用嵌入式技术和ASOS概念,给出了基于Linux构建交通信号控制器专用操作系统(TC-ASOS)的方法,同时用LEAP技术建立了交通信号控制器的Agent运行环境,为基于移动多Agent的城市交通信号控制系统提供底层支持。
英文摘要In this dissertation, the current development of urban traffic signal control system is reviewed firstly. After introducing some typical traffic signal control systems and analyzing the research status of traffic signal control methods based on agent, the existing problems of current systems are summarized, then the research direction and main content of the dissertation are put forward. On the aspect of theoretical foundation, firstly, the conversion from traffic control algorithm to traffic control agent is proposed and the conversion reason and significance are also analyzed. Pre-timed, actuated, fuzzy and other five different traffic control agents are designed based on the utilizing of the mobile agent technology and some existing traffic signal control algorithms. The control effects of these agents are validated through simulation. Secondly, the coordination method of control agent is studied. Control agent communicates and negotiates with the adjacent intersections' control agents. Afterwards, it adjusts its control behaviors and parameters through fuzzy reasoning based on predefined rules and the control optimization of the whole area is realized. Lastly, the running mechanism and switched rules of traffic control agent are studied. The system's structure is divided into three levels: center organization level, area coordination level and field execution level using the hierarchical architecture developed for intelligent control systems. The function of every level and the correlation among them are analyzed. The hosting mechanism and working flow of traffic control agent from center organization level to field execution level are given. The switch rules of traffic control agent on traffic control devices are also given. On the aspect of applied research, the experimental research is separately carried on three levels. Firstly, the design and development of the software platform of the center organization level and area coordination level is carried through JADE agent development platform. The detailed design and development methods are presented on the following aspects: the behaviors' realization of control agent, the migration of control agent, the communication between control agents, and the definition of ontology of traffic control system. The control of center organization level and area coordination level is tested and validated on TSIS traffic simulation software. Secondly, an intelligent traffic signal controller is developed, which is the key device of the field execution level. Adopting the technology of embedded system and the concept of Application Specific Operating System (ASOS), a traffic controller application specific operation system (TC-ASOS) is constructed based on Linux. Utilizing the LEAP technology, an agent running environment on signal controller is created, which provides a bottom supporting to the urban traffic signal control systems based on mobile multi-agent technology.
语种中文
其他标识符200418014628065
内容类型学位论文
源URL[http://ir.ia.ac.cn/handle/173211/6039]  
专题毕业生_博士学位论文
推荐引用方式
GB/T 7714
李镇江. 基于移动多Agent的城市交通信号控制系统的研究[D]. 中国科学院自动化研究所. 中国科学院研究生院. 2007.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace