CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleResearch on Intelligent Traffic Signal Control Based on Adaptive Dynamic Programming
Thesis Advisor赵冬斌 ; 易建强
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline控制理论与控制工程
Keyword交通信号控制 模糊逻辑控制 自适应动态规划 Traffic Signal Control Fuzzy Logic Control Adaptive Dynamic Programming
Abstract交通问题一直是人类文明的一个重要方面。但是伴随着经济的高速增长,城市的交通需求也快速增长,越来越多的车辆行驶在城市路网上,并带来了一系列的问题,如交通拥挤、交通延误、环境污染和交通事故等。如何充分有效地利用现有的道路资源,以最大限度地满足日益增长的交通需要,是解决城市交通问题的重要方向。随着人工智能技术研究的飞速进展,许多专家学者把人工智能的专家系统、模糊控制、人工神经网络、遗传算法等技术相继引入城市交通控制领域,以期克服传统交通控制系统的固有缺陷和局限性。 本论文试图通过对城市交通信号控制问题以及模糊逻辑控制和自适应动态规划方法的研究,寻求合适的城市交通信号控制算法,从一定程度上解决城市交通拥堵问题。主要内容如下: 1.为单路口设计了一种自适应动态规划优化各相位绿灯时间的方法,并进行了仿真研究,结果表明自适应动态规划在处理交通信号控制这种非线性离散系统时是切实有效的。 2.设计了单路口多相位交通信号模糊逻辑控制器。该控制器不仅考虑了所有相位的排队情况,并结合了感应控制的优点。为了尝试解决不同交通流环境下的信号控制问题,本文在不同流量的恒定交通流和有突变的交通流下进行了模糊逻辑控制器和感应控制器的仿真研究,结果表明该模糊逻辑控制器具有更好的效果,能适应不同状况下的交通流。 3.为了优化上述交通信号模糊逻辑控制器,本文设计了一种用自适应动态规划来优化其参数的方法。不同流量的恒定交通流和有突变的交通流下的仿真研究结果表明经过自适应动态规划优化的模糊逻辑控制器的效果要优于未经过优化的模糊逻辑控制器。 4.最后,本论文结合仿真结果分析了模糊逻辑控制和自适应动态规划用于交通信号控制的优缺点等问题。
Other AbstractTransportation has always been an important aspect of human civilization. With the rapid increase in economy, more and more vehicles are running in the urban traffic networks and bring some problems to the cities, such as traffic congestion, delay, pollution and accidents. In order to solve these problems, we need to maximize the utilization of existing roads. With the development of artificial intelligence technology, expert systems, fuzzy logics, neural networks and genetic algorithms are applied in traffic signal control field to overcome the deficiency of traditional traffic signal control systems. In order to find an urban traffic signal control algorithm with better performance to minimize traffic delays, fuzzy logic control and adaptive dynamic programming are studied. Main works and contributions of this paper are: 1. An adaptive dynamic programming method for optimizing green light times of a single traffic intersection is designed. Simulation results show that adaptive dynamic programming is suitable for solving such nonlinear discrete system control problems. 2. A fuzzy logic traffic signal controller is designed for a single intersection. This controller considers vehicle queues of four phases, and adopts the advantages of actuated control strategies. In order to solve signal control problems under various traffic conditions, the fuzzy logic controller and actuated controller are tested under constant traffic flows and flow with sudden changes. Simulation results show that this fuzzy logic controller performs better in reducing traffic delay than the actuated controller. 3. Adaptive dynamic programming is used to optimize the above fuzzy logic controller. A fuzzy logic controller with adaptive dynamic programming optimization (ADPFLC) is designed and studied under the same traffic conditions with the original fuzzy logic controller (FLC). Simulation results show that the ADPFLC performs better than the original FLC. 4. The advantages, disadvantages, and some other problems of fuzzy logic control and adaptive dynamic programming using in traffic signal control are summarized.
Other Identifier200528014628024
Document Type学位论文
Recommended Citation
GB/T 7714
田艺. 基于自适应动态规划的智能路口信号控制的研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2008.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20052801462802(871KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[田艺]'s Articles
Baidu academic
Similar articles in Baidu academic
[田艺]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[田艺]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.