Grace车队密度散布模型的更正及应用

首先剖析Grace的交叉口车队密度散布模型，发现其错误所在。进而研究车队散布中的密度变化规律，提出正确的密度散布模型。并且将该模型用来推导下游信号灯交叉口绿灯开始被截的车辆数的数学表达式，这个结果可用于相邻交叉口信号灯协调控制。     

零截尾负二项模型在交叉口事故预测中的应用

事故预测模型是广泛采用的交通安全定量分析方法,但往往要求具有完备的道路、交通和事故数据。然而,基础数据相对不健全是包括中国在内的发展中国家交通安全管理面临的主要问题之一,例如仅有发生事故路段或者交叉口的相关属性特征（即零截尾数据）。为此,为确保基础数据不全的情况下交叉口事故预测的准确性,提出了基于零截尾的广义负二项回归模型;采集了246个非信号控制交叉口的交通与事故数据,采用传统负二项模型和新提出的零截尾负二项模型对全数据和零截尾数据分别进行对比分析。结果表明：在针对截尾数据的分析中,零截尾负二项模型明显优于传统负二项模型,并且零截尾负二项模型的参数估计值与基于全数据的负二项基准模型的估计值非常接近;在所有模型中,交叉口的主路交通量和支路交通量与交叉口的安全性之间存在较大的正关联。此外,同等条件下,十字形交叉口的事故数量高于T形交叉口的事故数量;利用传统负二项分布模型分析截尾数据得到的事故预测模型与使用全数据的基准模型有显著差异,其结果不可靠;采用零截尾负二项分布模型的参数结果与基准模型基本一致,截尾模型的置信区间包含基准模型相应的参数估计值。当受条件所限无法获取全部数据时,可以考虑使用零截尾负二项模型进行安全分析。     

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.     

Optimizing multi-agent based urban traffic signal control system

Agent-based approach is a popular tool for modelling and developing large-scale distributed systems such as urban traffic control system with dynamic traffic flows. This study proposes a multi-agent-based approach to optimize urban traffic network signal control, which utilizes a mathematical programming method to optimize the signal timing plans at intersections. To improve the overall network efficiency, we develop an online agent-based signal coordination scheme, underpinned by the communication among different intersection control agents. In addition, the initial coordination scheme that pre-adjusts the offsets between the intersections is developed based on the historical demand information. Comparison and sensitivity analysis are conducted to evaluate the performance of the proposed method on a customized traffic simulation platform using MATLAB and VISSIM. Simulation results indicate that the proposed method can effectively avoid network oversaturation and thus reduces average travel delay and improves average vehicle speed, as compared to rule-based multi-agent signal control methods.     

行人交通控制信号设置方法研究

系统地分析了设置行人交通控制信号的必要性，并对其设置方法作了详细研究，针对混合交通流建立了确定行人信号相位及其通行时间的定量模型，其成果对于提高中国城市信号控制交叉口的交通控制效果、进一步研究行人交通问题有着重要的理论意义和实用价值。     

线控系统中相位差优化模型的研究

以使沿干线双向行驶的车辆延误最小为目标，以最优化理论为基础，通过对上、下行车辆在交叉口的延误规律进行分析研究，建立起线控系统相位差调节的优化模型，为干线交通流畅通提供了一种优化控制方法。     

Artificial intelligence for traffic signal control based solely on video images

Learning-based traffic control algorithms have recently been explored as an alternative to existing traffic control logics. The reinforcement learning (RL) algorithm is being spotlighted in the field of adaptive traffic signal control. However, no report has described the implementation of an RL-based algorithm in an actual intersection. Most previous RL studies adopted conventional traffic parameters, such as delays and queue lengths to represent a traffic state, which cannot be exactly measured on-site in real time. Furthermore, the traffic parameters cannot fully account for the complexity of an actual traffic state. The present study suggests a novel artificial intelligence that uses only video images of an intersection to represent its traffic state rather than using handcrafted features. In simulation experiments using a real intersection, consecutive aerial video frames fully addressed the traffic state of an independent four-legged intersection, and an image-based RL model outperformed both the actual operation of fixed signals and a fully actuated operation.     

Decoupled robust control of vehicular platoon with identical controller and rigid information flow

Platoon driving has potential to significantly benefit road traffic. This study presents a decoupled robust control strategy for a vehicular platoon with identical feedback controller and rigid information topology. The node dynamics of vehicle with a lower-level controller is assumed to be covered by a multiplicative uncertainty model. The vehicular platoon control system is skillfully decomposed into an uncertain part and a diagonal system by applying linear transformation and eigenvalue decomposition on information flow graph. Then the requirements of robust stability and distance tracking error are equivalent to the H-infinity norm of decoupled sub-systems. Comparative simulations with a non-robust controller and different communication topologies are conducted to demonstrate the robust stability and distance tracking performances of the proposed method.     

交通信号机的信号灯故障检测技术研究

信号灯故障检测技术是道路交通信号控制机的关键技术之一,该技术直接关系到“绿灯7中突”和“红灯不亮”等严重影响道路交通安全故障的检测、判断,故障检测必须稳定可靠、快速简便。提出了几种高稳定的信号灯故障检测技术,详细分析了各电路的技术特性和应用特点,解决了多年来信号灯故障检测不够可靠、虚警率较高的问题。目前其中之一已经在国家“863”课题“新一代智能化交通控制系统技术”中得到应用和验证。     

Pressure model based coordinated control of VGT and dual-loop EGR in a diesel engine air-path system

This paper describes a pressure-model-based coordinated control method of a variable geometry turbine (VGT) and dual-loop exhaust gas recirculation (EGR) in a diesel engine air-path system. Conventionally, air fraction or burnt gas fraction states are controlled for the control of dual-loop EGR systems, but fraction control is not practical since sensors for fractions are not available on production engines. In fact, there is still great controversy over how best to select control outputs for dual-loop EGR systems. In this paper, pressure and mass flow states are chosen as control outputs without fraction states considering the availability and reliability of sensors. A coordinated controller based on the simple control-oriented model is designed with practical aspects, which is applicable for simultaneous operations of high pressure (HP) EGR, low pressure (LP) EGR, and VGT. In addition, the controller adopts the method of input-output linearization using back-stepping to solve the chronic problems of conventional pressure-based controllers such as coupling effects between operations of HP EGR, and VGT. The control performance is verified by simulation based on the proven GT-POWER model of a heavy-duty 6000cc diesel engine air-path.     

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

This research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. The comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better at higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO₂, NO_x, VOC, PM₁₀) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.