交通燈控制系統(tǒng)外文翻譯

1、本科生畢業(yè)設(shè)計(jì)（論文）外文文獻(xiàn)翻譯畢業(yè)設(shè)計(jì)題目： 交通燈智能控制系統(tǒng) 學(xué) 院： 信息科學(xué)與工程學(xué)院 專業(yè)班級(jí)： 測(cè)控技術(shù)與儀器0703班 學(xué)生姓名： 王欣 指導(dǎo)教師： 桑海峰 2011年 3月 19日外文原文intelligent traffic light controlmarco wiering, jelle van veenen, jilles vreeken, and arne koopman intelligent systems groupinstitute of information and computing sciences utrecht universitypadual

2、aan 14, 3508tb utrecht, the netherlandsemail: marcocs.uu.nljuly 9, 2004abstractvehicular travel is increasing throughout the world, particularly in large urban areas.therefore the need arises for simulating and optimizing traffic control algorithms to better accommodate this increasing demand. in th

3、is paper we study the simulation and optimization of traffic light controllers in a city and present an adaptive optimization algorithm based on reinforcement learning. we have implemented a traffic light simulator, green light district, that allows us to experiment with different infrastructures an

4、d to compare different traffic light controllers. experimental results indicate that our adaptive traffic light controllers outperform other fixed controllers on all studied infrastructures.keywords: intelligent traffic light control, reinforcement learning, multi-agent systems (mas), smart infrastr

5、uctures, transportation research1 introductiontransportation research has the goal to optimize transportation flow of people and goods.as the number of road users constantly increases, and resources provided by current infrastructures are limited, intelligent control of traffic will become a very im

6、portant issue in the future. however, some limitations to the usage of intelligent traffic control exist. avoiding traffic jams for example is thought to be beneficial to both environment and economy, but improved traffic-flow may also lead to an increase in demand levinson, 2003.there are several m

7、odels for traffic simulation. in our research we focus on microscopic models that model the behavior of individual vehicles, and thereby can simulate dynamics of groups of vehicles. research has shown that such models yield realistic behavior nagel and schreckenberg, 1992, wahle and schreckenberg, 2

8、001.cars in urban traffic can experience long travel times due to inefficient traffic light control. optimal control of traffic lights using sophisticated sensors and intelligent optimization algorithms might therefore be very beneficial. optimization of traffic light switching increases road capaci

9、ty and traffic flow, and can prevent traffic congestions. traffic light control is a complex optimization problem and several intelligent algorithms, such as fuzzy logic, evolutionary algorithms, and reinforcement learning (rl) have already been used in attempts to solve it. in this paper we describ

10、e a model-based, multi-agent reinforcement learning algorithm for controlling traffic lights.in our approach, reinforcement learning sutton and barto, 1998, kaelbling et al., 1996 with road-user-based value functions wiering, 2000 is used to determine optimal decisions for each traffic light. the de

11、cision is based on a cumulative vote of all road users standing for a traffic junction, where each car votes using its estimated advantage (or gain) of setting its light to green. the gain-value is the difference between the total time it expects to wait during the rest of its trip if the light for

12、which it is currently standing is red, and if it is green. the waiting time until cars arrive at their destination is estimated by monitoring cars flowing through the infrastructure and using reinforcement learning (rl) algorithms.we compare the performance of our model-based rl method to that of ot

13、her controllers using the green light district simulator (gld). gld is a traffic simulator that allows us to design arbitrary infrastructures and traffic patterns, monitor traffic flow statistics such as average waiting times, and test different traffic light controllers. the experimental results sh

14、ow that in crowded traffic, the rl controllers outperform all other tested non-adaptive controllers. we also test the use of the learned average waiting times for choosing routes of cars through the city (co-learning), and show that by using co-learning road users can avoid bottlenecks.this paper is

15、 organized as follows. section 2 describes how traffic can be modelled, predicted, and controlled. in section 3 reinforcement learning is explained and some of its applications are shown. section 4 surveys several previous approaches to traffic light control, and introduces our new algorithm. sectio

16、n 5 describes the simulator we used for our experiments, and in section 6 our experiments and their results are given. we conclude in section 7.2 modelling and controlling trafficin this section, we focus on the use of information technology in transportation. a lot of ground can be gained in this a

17、rea, and intelligent transportation systems (its) gained interest of several governments and commercial companies ten-t expert group on its, 2002, white paper, 2001, epa98, 1998.its research includes in-car safety systems, simulating effects of infrastructural changes, route planning, optimization o

18、f transport, and smart infrastructures. its main goals are: improving safety, minimizing travel time, and increasing the capacity of infrastructures. such improvements are beneficial to health, economy, and the environment, and this shows in the allocated budget for its.in this paper we are mainly i

19、nterested in the optimization of traffic flow, thus effectively minimizing average traveling (or waiting) times for cars. a common tool for analyzing traffic is the traffic simulator. in this section we will first describe two techniques commonly used to model traffic. we will then describe how mode

20、ls can be used to obtain real-time traffic information or predict traffic conditions. afterwards we describe how information can be communicated as a means of controlling traffic, and what the effect of this communication on traffic conditions will be. finally, we describe research in which all cars

21、 are controlled using computers.2.1 modelling traffic.traffic dynamics bare resemblance with, for example, the dynamics of fluids and those of sand in a pipe. different approaches to modelling traffic flow can be used to explain phenomena specific to traffic, like the spontaneous formation of traffi

22、c jams. there are two common approaches for modelling traffic; macroscopic and microscopic models.2.1.1 macroscopic models.macroscopic traffic models are based on gas-kinetic models and use equations relating traffic density to velocity lighthill and whitham, 1955, helbing et al., 2002. these equati

23、ons can be extended with terms for build-up and relaxation of pressure to account for phenomena like stop-and-go traffic and spontaneous congestions helbing et al., 2002, jin and zhang, 2003, broucke and varaiya, 1996. although macroscopic models can be tuned to simulate certain driver behaviors, th

24、ey do not offer a direct, flexible, way of modelling and optimizing them, making them less suited for our research.2.1.2 microscopic models.in contrast to macroscopic models, microscopic traffic models offer a way of simulating various driver behaviors. a microscopic model consists of an infrastruct

25、ure that is occupied by a set of vehicles. each vehicle interacts with its environment according to its own rules. depending on these rules, different kinds of behavior emerge when groups of vehicles interact.cellular automata. one specific way of designing and simulating (simple) driving rules of c

26、ars on an infrastructure, is by using cellular automata (ca). ca use discrete partially connected cells that can be in a specific state. for example, a road-cell can contain a car or is empty. local transition rules determine the dynamics of the system and even simple rules can lead to chaotic dynam

27、ics. nagel and schreckenberg (1992) describe a ca model for traffic simulation. at each discrete time-step, vehicles increase their speed by a certain amount until they reach their maximum velocity. in case of a slower moving vehicle ahead, the speed will be decreased to avoid collision. some random

28、ness is introduced by adding for each vehicle a small chance of slowing down. experiments showed realistic behavior of this ca model on a single road with emerging behaviors like the formation of start-stop waves when traffic density increases.cognitive multi-agent systems. a more advanced approach

29、to traffic simulation and optimization is the cognitive multi-agent system approach (cmas), in which agents interact and communicate with each other and the infrastructure. a cognitive agent is an entity that autonomously tries to reach some goal state using minimal effort. it receives information f

30、rom the environment using its sensors, believes certain things about its environment, and uses these beliefs and inputs to select an action. because each agent is a single entity, it can optimize (e.g., by using learning capabilities) its way of selecting actions. furthermore, using heterogeneous mu

31、lti-agent systems, different agents can have different sensors, goals, behaviors, and learning capabilities, thus allowing us to experiment with a very wide range of (microscopic) traffic models.dia (2002) used a cmas based on a study of real drivers to model the drivers response to travel informati

32、on. in a survey taken at a congested corridor, factors influencing the choice of route and departure time were studied. the results were used to model a driver population, where drivers respond to presented travel information differently. using this population, the effect of different information sy

33、stems on the area where the survey was taken could be simulated. the research seems promising, though no results were presented.a traffic prediction model that has been applied to a real-life situation, is described in wahle and schreckenberg, 2001. the model is a multi-agent system (mas) where driv

34、ing agents occupy a simulated infrastructure similar to a real one. each agent has two layers of control; one for the (simple) driving decision, and one for tactical decisions like route choice. the real world situation was modelled by using detection devices already installed. from these devices, i

35、nformation about the number of cars entering and leaving a stretch of road are obtained. using this information, the number of vehicles that take a certain turn at each junction can be inferred. by instantiating this information in a faster than real-time simulator, predictions on actual traffic can

36、 be made. a system installed in duisburg uses information from the existing traffic control center and produces real-time information on the internet. another system was installed on the freeway system of north rhine-westphalia, using data from about 2.500 inductive loops to predict traffic on 6000

37、km of roads.中文譯文智能交通燈控制馬克 威寧，簡(jiǎn)麗 范 威，吉爾 威瑞肯，安瑞 庫(kù)普曼智能系統(tǒng)小組烏得勒支大學(xué)信息與計(jì)算科學(xué)研究所荷蘭烏得勒支padualaan14號(hào)郵箱：marcocs.uu.nl2004年7月9日摘要世界各地的車輛運(yùn)行逐漸增多，尤其是在一個(gè)大的本地區(qū)域。因此就需要有關(guān)交通控制的模擬與優(yōu)化算法，來(lái)更好的地適應(yīng)日益增長(zhǎng)的需求。在文中，我們學(xué)習(xí)了在城市中的模擬與優(yōu)化的交通燈控制器，以及目前基于強(qiáng)化學(xué)習(xí)的自適應(yīng)優(yōu)化算法。我們已經(jīng)實(shí)行了一個(gè)交通等模擬器，綠燈區(qū)，這允許我們用不同的基礎(chǔ)設(shè)施和不同的交通控制器去實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明，在所有基礎(chǔ)設(shè)施的研究領(lǐng)域內(nèi)，我們的自適應(yīng)交通燈

38、控制器優(yōu)于其他固定的控制器。關(guān)鍵字：智能交通燈控制，強(qiáng)化學(xué)習(xí)，多代理系統(tǒng)（mas），智能基礎(chǔ)設(shè)施，運(yùn)輸研究1 介紹運(yùn)輸研究的目的是優(yōu)化人流和物流。隨著道路使用者的數(shù)量不斷上漲，當(dāng)前基礎(chǔ)設(shè)施所提供的資源受到限制，在未來(lái)，交通智能控制將會(huì)成為一個(gè)非常重要的問(wèn)題。然而，一些交通智能控制使用受限問(wèn)題的存在。避免交通堵塞，例如，被認(rèn)為是對(duì)環(huán)境和經(jīng)濟(jì)有益的，但是增加的交通流也可能導(dǎo)致資源需求的增加。萊文森，2003。這有幾個(gè)交通仿真模型。在我們的研究中，我們專注于那些具有個(gè)體車輛行為的微觀模型，從而更好的模擬群體車輛的動(dòng)力學(xué)。研究表明，這種模型的出現(xiàn)具有現(xiàn)實(shí)意義nagel and schreckenber

39、g，1992，wahle and schreckenberg，2001。汽車在城市交通中經(jīng)歷了漫長(zhǎng)的運(yùn)行時(shí)間，要?dú)w因于低效的交通燈控制。因此，使用成熟傳感器和智能優(yōu)化算法的交通燈優(yōu)化控制可能是有益的。優(yōu)化的交通燈切換增加了道路的容量和人流，能阻止交通堵塞。交通燈控制是一個(gè)復(fù)雜的優(yōu)化問(wèn)題和幾個(gè)智能算法，例如模糊邏輯、遺傳算法和強(qiáng)化學(xué)習(xí)（rl）已被應(yīng)用去試圖解決問(wèn)題。在本文中，我們描述了一種對(duì)交通燈控制，基于模型的、多代理的強(qiáng)化學(xué)習(xí)算法。我們的方法，強(qiáng)化學(xué)習(xí)sutton and barto，1998，kaelbling，1996和基于道路使用者的價(jià)值功能威寧，2000被用來(lái)決定每個(gè)交通燈的優(yōu)化選擇

40、。這個(gè)決定是基于道路使用者站了一個(gè)交叉路口的累積投票，在那里每輛汽車使用其估計(jì)選票的優(yōu)勢(shì)(或增益)設(shè)置它的光的綠色。在其余路程，它的所有等待時(shí)間里，如果信號(hào)燈現(xiàn)在是紅色的或者綠色的，那么增益的值是不同的。汽車直到到達(dá)目的地后的等待時(shí)間，是通過(guò)監(jiān)測(cè)汽車流過(guò)基礎(chǔ)設(shè)施和應(yīng)用強(qiáng)化學(xué)習(xí)(rl)算法而估算出來(lái)的。本文寫(xiě)作安排如下。第二部分描述了交通是如何被建立、預(yù)測(cè)和控制的。在第三部分解釋了什么是強(qiáng)化學(xué)習(xí)和一些它的應(yīng)用。第四部分調(diào)查了幾個(gè)以前交通控制的方法，介紹了我們的新算法。第五部分描述了我們實(shí)驗(yàn)中所使用的仿真器，以及第六部分給出我們的實(shí)驗(yàn)和實(shí)驗(yàn)結(jié)果。在第七部分我們得出結(jié)論。2 建立和控制交通在這一部分

41、，我們專注于在交通運(yùn)輸方面所使用的信息技術(shù)。在這個(gè)區(qū)域增加了大量的土地，并且一些政府和商業(yè)公司在交通智能系統(tǒng)（its）方面獲得了利潤(rùn)。ten-t expert group on its，2002，白皮書(shū)，2001，epa98，1998。交通智能系統(tǒng)（its）研究包括車內(nèi)安全系統(tǒng)，基礎(chǔ)設(shè)施改變所引起的仿真效果，路途規(guī)劃，優(yōu)化運(yùn)輸和智能的基礎(chǔ)設(shè)施。其主要目標(biāo)是：提高安全性、減少運(yùn)行時(shí)間、增加基礎(chǔ)設(shè)施的能力。這種改進(jìn)有益健康、經(jīng)濟(jì)、環(huán)境，這表現(xiàn)在交通智能系統(tǒng)的分配預(yù)算方面。在本文中,我們主要對(duì)車流的優(yōu)化感興趣,從而有效減少平均運(yùn)行(或者等待)的車輛次數(shù)。一種常見(jiàn)的分析交通的工具就是交通仿真器。在這部

42、分中,我們將首先描述兩種常用于交通模型的技術(shù)。然后我們將描述模型是如何用來(lái)獲取實(shí)時(shí)交通信息或者預(yù)測(cè)交通情況的。后來(lái),我們描述信息是如何作為一種控制交通的手段來(lái)進(jìn)行溝通的,在這樣的交通條件下，溝通產(chǎn)生了什么樣的影響。最后,我們描述了所有的汽車都使用計(jì)算機(jī)進(jìn)行控制的研究。2.1 建立交通與交通動(dòng)力學(xué)僅有的相似之處是，例如，流體力學(xué)和管內(nèi)的沙子。建立車流模型的不同方法是用來(lái)解釋交通的特殊現(xiàn)象的，就像自發(fā)形成的交通堵塞狀況。有兩種普遍的方法去建立交通：宏觀和微觀模型。2.1.1 宏觀模型宏觀交通模型是基于gas-kinetic模型的，利用了關(guān)于交通密度和速度的方程式lighthill and whit

43、ham，1955，helbing et al.，2002。這些方程式可以延長(zhǎng)積累和放松壓力，歸因于類似的停停走走的交通和自發(fā)的擁堵的現(xiàn)象。helbing et al.，2002，jin and zhang, 2003，broucke and varaiya，1996。盡管宏觀模型可以來(lái)模擬一些特定的可調(diào)驅(qū)動(dòng)行為，但是他們不能提供一個(gè)直接的、靈活的建立和優(yōu)化交通的方法，這使他們不太適合我們的研究。2.1.2 微觀模型與宏觀模型相對(duì)比的，微觀交通模型提供了一種仿真各種各樣司機(jī)行為的方法。一個(gè)微觀模型由一組車輛占據(jù)的基礎(chǔ)設(shè)施組成。每輛車都根據(jù)自己的規(guī)則，和周圍的環(huán)境產(chǎn)生作用。根據(jù)這些規(guī)則，當(dāng)很多車輛互相作用時(shí)，不同種類的行為就會(huì)出現(xiàn)。元胞自動(dòng)機(jī)。一個(gè)在基礎(chǔ)設(shè)施上的具體設(shè)計(jì)和仿真（簡(jiǎn)單的