Asynchronous n-step Q-learning adaptive traffic signal control

Ensuring transportation systems are efficient is a priority for modern society. Intersection traffic signal control can be modeled as a sequential decision-making problem. To learn how to make the best decisions, we apply reinforcement learning techniques with function approximation to train an adaptive traffic signal controller. We use the asynchronous n-step Q-learning algorithm with a two hidden layer artificial neural network as our reinforcement learning agent. A dynamic, stochastic rush hour simulation is developed to test the agent’s performance. Compared against traditional loop detector actuated and linear Q-learning traffic signal control methods, our reinforcement learning model develops a superior control policy, reducing mean total delay by up 40% without compromising throughput. However, we find our proposed model slightly increases delay for left turning vehicles compared to the actuated controller, as a consequence of the reward function, highlighting the need for an appropriate reward function which truly develops the desired policy.     

隧道内设置车站时信号系统方案探讨

结合新建金华至台州铁路工程磐安至里林站区间隧道内车站设置方案研究,对车站联锁、运输调度指挥、集中监测等信号系统方案进行了研究和探讨。     

调车信号机白灯灯丝检查的探讨

在信号机点灯电路中,灯丝继电器只检查点灯灯丝的情况,不检查另外一个灯的情况。在不影响现有设备稳定性和安全性的前提下,对实时检查调车信号机白灯灯丝的情况进行探讨。     

A technical note on evaluating the effectiveness of bus rapid transit with transit signal priority

Transit Signal Priority (TSP) and Bus Rapid Transit (BRT) are innovative Intelligent Transportation System (ITS) tools that can reduce travel times for buses. Combining TSP and BRT can significantly improve bus travel, but can negatively impact network traffic operations. Although TSP has been implemented worldwide, few previous studies holistically examined the effects of using various conditional and unconditional TSP strategies with or without a BRT system. This research simulates multiple TSP and BRT combination scenarios to understand their impact on traffic operations, including crossing street traffic. A test bed along International Drive (I-Drive) in Orlando, Florida, was chosen as the simulation area. Field data collected for this test bed, which included traffic volumes, bus travel times, and traffic signal control data, were used to develop, calibrate, and validate the simulation model. Results showed that BRT with Conditional TSP 3 minutes behind significantly improved travel times, average speed, and average total delay per vehicle for the main through movements compared with no BRT or TSP, with only minor effects on crossing street delays. BRT with Unconditional TSP resulted in significant crossing street delays, especially at major intersections with high traffic demand, indicating that this scenario is impractical for implementation. The simulation suggests that BRT and TSP will be most effective when used in areas where crossing street volumes are low. However, it is unknown how these ITS tools affect pedestrian traffic. Using optimization methods can determine the best strategy to balance transit and pedestrian traffic.     

高分辨率罗兰C天波延迟估计新技术

提出了一种基于特征分解的多信号分类算法估计罗兰C接收机天波延迟的信号处理新技术。它为接收机基准点的实时设置提供了一种新方法。常规接收机为了防止天波干扰，将基准点设置在一个固定位置上，导致基准点处信噪比受包络限制而较低，从而大大增加了对准基准点的时间。利用这项技术，我们在低信噪比条件下分离出了地波和天波的到达时刻。这就使得接收机能根据天波延迟变化实时选择基准点最佳位置，并能利用地波到达时刻进行周期选择。由于此法有助于增加基准点处的信噪比，减少对准基准点的时间，因而能极大地提高现有罗兰C接收机的性能。还显示了新方法较IFFF方法有更高的分辨率。     

基于超高速AD9954的多模式信号的实现

通过对AD9954采用先进DDS技术性能特点的具体分析，利用其可编程幅度、频率、相位给出AD9954在高速调制信号系统中的应用方案，从而较方便容易地实现基于软件无线电技术的各种调制信号。     

关于容许信号点灯电路的探讨

通过对现有自动闭塞区间通过信号机容许信号点灯电路存在问题的分析，根据相关规范，提出解决办法。     

铁路信号综合防雷中接地的具体作法

针对现场实际,对铁路信号综合防雷中地网设置的具体作法进行了探索,阐述了设置地网时应当注意的技术问题。     

基于GPRS的机车信号远程实时监控系统

针对目前铁路机车信号系统监测存在实时性差的缺点，提出了一种基于GPRS无线网络的监测方法。以Atmel公司AT91R40008ARM处理器为核心，配以GR47GPRS模块，设计了GPRS数据发送盒，以实现机车信号信息的实时检测和无线传输。     

机车信号出入库巡更检测系统

介绍了一种采用精细电子巡更的机车信号出入库检测系统。从安全性、经济性、可靠性及可维护性等方面，对该系统在机车信号检测上的应用前景进行了分析。