發(fā)布時(shí)間：2018-06-17 04:16

  本文選題：交通燈控制 + 車輛誘導(dǎo)��； 參考：《沈陽(yáng)理工大學(xué)》2017年碩士論文

【摘要】：隨著我國(guó)城市現(xiàn)代化進(jìn)程的不斷推進(jìn),交通問(wèn)題成為影響社會(huì)發(fā)展的一個(gè)大問(wèn)題。其中,交通擁堵是最為常見(jiàn)并影響較大的交通問(wèn)題,國(guó)內(nèi)外許多學(xué)者致力于交通擁堵問(wèn)題的研究并提出了相應(yīng)的解決方案。其中,智能交通系統(tǒng)是一種有效解決交通問(wèn)題的智能系統(tǒng)。在智能交通系統(tǒng)的重要研究中,自適應(yīng)交通燈控制系統(tǒng)是目前公認(rèn)的緩解城市交通擁堵的有效途徑。由于城市交通系統(tǒng)的復(fù)雜性和不確定性,現(xiàn)有的交通燈定時(shí)信號(hào)控制系統(tǒng)不能很好解決交通擁堵問(wèn)題。為此,本文以基于最短路徑策略的車輛誘導(dǎo)系統(tǒng)為基礎(chǔ),利用善于與環(huán)境交互的強(qiáng)化學(xué)習(xí)算法來(lái)建立智能交通控制策略。首先,我們?cè)O(shè)計(jì)基于Q學(xué)習(xí)的交通燈控制策略對(duì)交通信號(hào)燈進(jìn)行動(dòng)態(tài)配時(shí),以減少車輛在交叉口的平均等待時(shí)間。其次,從協(xié)同優(yōu)化的角度出發(fā),提出基于模糊Q學(xué)習(xí)的交通燈控制策略,利用模糊邏輯控制根據(jù)車輛誘導(dǎo)信息獲取協(xié)同交叉口的信息對(duì)Q學(xué)習(xí)的動(dòng)作選擇進(jìn)行優(yōu)化,以提高Q學(xué)習(xí)算法的收斂速度。最后,為了提高智能交通系統(tǒng)的整體性能,提出基于Sarsa學(xué)習(xí)的車輛誘導(dǎo)和基于Q學(xué)習(xí)的交通燈控制協(xié)同策略,實(shí)現(xiàn)兩個(gè)系統(tǒng)在數(shù)據(jù)處理、策略實(shí)施和信息產(chǎn)生等方面協(xié)同,更好的提升交通系統(tǒng)的性能。本文以交通燈控制算法為基礎(chǔ),將自適應(yīng)交通燈控制系統(tǒng)、強(qiáng)化學(xué)習(xí)、模糊邏輯控制優(yōu)化動(dòng)作選擇策略、車輛誘導(dǎo)系統(tǒng)的性能提升融合在交通燈控制算法中,尤其是把強(qiáng)化學(xué)習(xí)的自學(xué)習(xí)特性應(yīng)用到動(dòng)態(tài)交通系統(tǒng)中。實(shí)驗(yàn)結(jié)果表明,基于Q學(xué)習(xí)的交通燈控制策略縮減了交通系統(tǒng)中車輛在交叉口的平均等待時(shí)間,減少了交通系統(tǒng)的擁堵現(xiàn)象,提升了交通系統(tǒng)的性能。并且,以該控制策略為基礎(chǔ),分別從強(qiáng)化學(xué)習(xí)算法的收斂速度和系統(tǒng)整體性能的角度進(jìn)行改進(jìn)。實(shí)驗(yàn)結(jié)果表明,改進(jìn)策略進(jìn)一步提升了交通系統(tǒng)的性能。
[Abstract]:With the development of urban modernization in China, traffic problem has become a major problem affecting social development. Among them, traffic congestion is the most common and influential traffic problems. Many scholars at home and abroad have devoted themselves to the research of traffic congestion and put forward corresponding solutions. Among them, Intelligent Transportation system (its) is an effective intelligent system to solve traffic problems. In the important research of intelligent transportation system, adaptive traffic light control system is recognized as an effective way to alleviate urban traffic congestion. Due to the complexity and uncertainty of urban traffic system, the existing traffic light timing signal control system can not solve the traffic congestion problem well. Therefore, based on the vehicle guidance system based on the shortest path strategy, the intelligent traffic control strategy is established by using the reinforcement learning algorithm which is good at interacting with the environment. First of all, we design the traffic light control strategy based on Q learning to dynamically match the traffic signal to reduce the average waiting time of the vehicle at the intersection. Secondly, a traffic light control strategy based on fuzzy Q learning is proposed from the view of collaborative optimization. The action selection of Q learning is optimized by using fuzzy logic control to obtain the information of collaborative intersection according to the vehicle guidance information. In order to improve the convergence speed of Q learning algorithm. Finally, in order to improve the overall performance of the intelligent transportation system, a traffic light control coordination strategy based on Sarsa learning and Q-learning is proposed. The two systems can cooperate in data processing, strategy implementation and information generation. Better improve the performance of the transportation system. Based on the traffic light control algorithm, this paper integrates the adaptive traffic light control system, reinforcement learning, fuzzy logic control optimization action selection strategy and vehicle guidance system performance enhancement into the traffic light control algorithm. Especially, the self-learning characteristic of reinforcement learning is applied to dynamic traffic system. The experimental results show that the traffic light control strategy based on Q learning reduces the average waiting time of the vehicle at the intersection in the traffic system, reduces the congestion of the traffic system, and improves the performance of the traffic system. On the basis of the control strategy, the convergence rate of reinforcement learning algorithm and the overall performance of the system are improved respectively. The experimental results show that the improved strategy can further improve the performance of the transportation system.
【學(xué)位授予單位】：沈陽(yáng)理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U491.54

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙華;呂增文;;我國(guó)城市交通擁擠現(xiàn)狀及其對(duì)策研究[J];中國(guó)管理信息化;2015年14期

2 譚吉祥;丁宇;張杰;華婷;王柳;;智能交通燈控制系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];計(jì)算機(jī)與網(wǎng)絡(luò);2015年08期

3 殷招偉;戴文博;錢(qián)俊彥;;Dijkstra算法在GIS車輛誘導(dǎo)系統(tǒng)的優(yōu)化實(shí)現(xiàn)[J];大眾科技;2015年02期

4 夏新海;;MDP下基于特征表示強(qiáng)化學(xué)習(xí)的自適應(yīng)交通信號(hào)控制[J];公路交通科技;2015年01期

5 張學(xué)成;錢(qián)力強(qiáng);王曉;錢(qián)志誠(chéng);劉和劍;;基于車流量檢測(cè)的多相位智能交通燈控制系統(tǒng)[J];科技視界;2015年01期

6 官錚;何敏;錢(qián)文華;;基于車輛驅(qū)動(dòng)的交通燈控制策略及仿真研究[J];系統(tǒng)仿真學(xué)報(bào);2014年11期

7 趙建玉;郭仲林;鄭顯臣;;基于模糊邏輯的單交叉口交通信號(hào)控制方法設(shè)計(jì)及實(shí)現(xiàn)[J];交通信息與安全;2013年05期

8 段宣翡;唐澤杭;;基于車流量的紅綠燈實(shí)時(shí)配時(shí)算法[J];硅谷;2013年13期

9 劉祥鵬;隋樹(shù)林;;單交叉口交通信號(hào)控制方法現(xiàn)狀及其展望[J];科技信息;2012年32期

10 盧守峰;邵維;韋欽平;劉喜敏;;基于綠燈時(shí)間等飽和度的離線Q學(xué)習(xí)配時(shí)優(yōu)化模型[J];系統(tǒng)工程;2012年07期

相關(guān)博士學(xué)位論文 前1條

1 龔;城市交通誘導(dǎo)與控制的融合研究[D];北京科技大學(xué);2015年

相關(guān)碩士學(xué)位論文 前2條

1 蔡錦德;城市道路交叉口的信號(hào)配時(shí)優(yōu)化研究[D];北京交通大學(xué);2012年

2 梁子君;城市道路智能交通信號(hào)控制系統(tǒng)[D];合肥工業(yè)大學(xué);2007年

，

本文編號(hào)：2029637