外文文獻(xiàn)翻譯 智能交通信號燈控制 中英文對照

1、英語原文Intelligent Traffic Light Control by Marco WieringThe topic I picked for our community project was traffic lights. In a community, people need stop signs and traffic lights to slow down drivers from going too fas

2、t. If there were no traffic lights or stop signs, people’s lives would be in danger from drivers going too fast. The urban traffic trends towards the saturation, the rate of increase of the road of big city far lags behi

3、nd rate of increase of the car.The urban passenger traffic has already become the main part of city traffic day by day and it has used about 80% of the area of road of center district. With the increase of population and

4、 industry activity, people's traffic is more and more frequent, which is unavoidable. What means of transportation people adopt produces pressure completely different to city traffic. According to calculating, if it

5、is 1 to adopt the area of road that the public transport needs, bike needs 5-7, car needs 15-25, even to walk is 3 times more than to take public transits. So only by building road can't solve the city traffic proble

6、m finally yet. Every large city of the world increases the traffic policy to the first place of the question.For example， according to calculating, when the automobile owning amount of Shanghai reaches 800,000 (outside c

7、ars count separately ), if it distributes still as now for example: center district accounts for great proportion, even when several loop-lines and arterial highways have been built up , the traffic cannot be improved mo

8、re than before and the situation might be even worse. So the traffic policy Shanghai must adopt , or called traffic strategy is that have priority to develop public passenger traffic of city, narrow the scope of using of

9、 the bicycle progressively , control the scale of growth of the car traffic in the center district, limit the development of the motorcycle strictly. There are more municipals project under construction in big city. the

10、influence on the traffic is greater.Municipal infrastructure construction is originally a good thing of alleviating the traffic, but in the course of constructing, it unavoidably influence the local traffic. Some road se

11、ctions are blocked, some change into an one-way lane, thus the vehicle can only take a devious route . The construction makes the road very narrow, forming the bottleneck, which seriously influence the car flow.When havi

12、ng stop signs and traffic lights, people have a tendency to drive slower and receive information about how to drive through a city in order to minimize their waiting times. This means that we are coping with a complex mu

13、lti-agent system, where communication and coordination play essential roles. Our research has led to a novel system in which traffic light controllers and the behaviour of car drivers are optimized using machine-learning

14、 methods.Our idea of setting a traffic light is as follows. Suppose there are a number of cars with their destination address standing before a crossing. All cars communicate to the traffic light their specific place in

15、the queue and their destination address. Now the traffic light has to decide which option (ie, which lanes are to be put on green) is optimal to minimize the long-term average waiting time until all cars have arrived at

16、their destination address. The learning traffic light controllers solve this problem by estimating how long it would take for a car to arrive at its destination address (for which the car may need to pass many different

17、traffic lights) when currently the light would be put on green, and how long it would take if the light would be put on red. The difference between the waiting time for red and the waiting time for green is the gain for

18、the car. Now the traffic light controllers set the lights in such a way to maximize the average gain of all cars standing before the crossing. To estimate the waiting times, we use 'reinforcement learning' which

19、keeps track of the waiting times of individual cars and uses a smart way to compute the long term average waiting times using dynamic programming algorithms. One nice feature is that the system is very fair; it never let

20、s one car wait for a very long time, since then its gain of setting its own light to green becomes very large, and the optimal decision of the traffic light will set his light to green. Furthermore, since we estimate wai

21、ting times before traffic lights until the destination of the road user has been reached, the road user can use this information to choose to which next traffic light to go, thereby improving its driving behaviour throug

22、h a city. Note that we solve the traffic light control problem by using a distributed multi-agent system, where cooperation and coordination are done by communication, learning, and voting mechanisms. To allow for green

23、waves during extremely busy situations, we combine our algorithm with a special bucket algorithm which propagates gains from one traffic light to the next one, inducing stronger voting on the next traffic controller opti

24、on.We have implemented the 'Green Light District', a traffic simulator in Java in which infrastructures can be edited easily by using the mouse, and different levels of road usage can be simulated. A large number

25、 of fixed and learning traffic light controllers have already been tested in the simulator and the resulting average waiting times of cars have been plotted and compared. The results indicate that the learning controller