城市高架桥下停车场规划设计探讨

随着城市的发展及机动车数量的快速增长,城市停车难矛盾日益突出。在对高架桥下设置停车场可行性分析的基础上,提出2种停车需求分析方法,并对高架桥下停车场设计准则及要点进行分析,给出了高架桥下建设停车场的几点建议,对城市高架桥下停车场的规划设计具有较强的指导意义。     

神经网络用于船舶操纵动态特性学习的研究

本文针对BP网络存在的一些问题，提出一种单层神经网络结构，通过大量的仿真试验，对两种网络在学习、预报和适应参数变化等方面的特性进行了对比。结果表明单层神经网络用于学习船舶操纵动态特性，具有收敛速度极快、预测误差较小、能快速跟踪参数变化等优点，可用于船舶操纵特性的实时学习。     

不均匀流中船舶操纵运动仿真模型及应用

本文给出不均匀流中船舶操纵运动数学模型，研究了在不均匀流中作用于船体上流体动力的估算及不均匀流场的生成，提出了不均匀流中船舶操纵运动的仿真方法。最后介绍了在港口引航实践中的两个仿真应用。     

联合机动编队兵力配置冲突消解

联合机动编队兵力配置是攻防作战的前提,众多兵力同时配置产生的冲突制约编队战斗力的发挥。着眼于联合机动编队整体作战效益,对联合机动编队兵力配置中的冲突消解问题展开研究。在分析联合机动编队兵力配置冲突产生原因的基础上,确定消解冲突的原则,针对联合机动编队兵力配置中的典型冲突问题提出消解方法,为解决联合机动编队兵力配置中的冲突问题提供思路。     

停车诱导信息集成结构模型设计及实现

面对动态、多变、实时的交通信息以及驾驶员对停车场信息的需求,停车管理需要走向智能化。停车诱导系统能为驾驶员提供实时的停车场信息以及周边道路情况,在基于多Agent系统的基础上进行分析,给出停车诱导信息集成结构模型,并利用面向对象的Agent进行设计,最后指出实现该系统还需进行的后续研究。     

A similarity-based neuro-fuzzy modeling for driving behavior recognition applying fusion of smartphone sensors

Drivers’ behavior evaluation is one of the most important problems in intelligent transportation systems and driver assistant systems. It has a great influence on driving safety and fuel consumption. One of the challenges in this regard is the modeling perspective to treat with uncertainty in judgments about driving behaviors. Really, assessing a single maneuver with a rigid threshold leads to a weak judgment for driving evaluation. To fill this gap, a novel neuro-fuzzy system is proposed to classify the driving behaviors based on their similarities to fuzzy patterns when all of the various maneuvers are stated with some fuzzy numbers. These patterns are also fuzzy numbers and they are extracted from statistical analysis on the smartphone sensors data. Our driving evaluation system consists of three processes. Firstly, it detects the type of all of the maneuvers through the driving period, by using a multi-layer perceptron neural network. Secondly, it extracts a new feature based on the acceleration and assigns three fuzzy numbers to driver’s lane change, turn and U-turn maneuvers. Thirdly, it determines the similarity between these three fuzzy numbers and the fuzzy patterns to evaluate the safe and the aggressive driving scores. To validate this model, Driver’s Angry Score (DAS) questionnaires are used. Results show that the fusion of Inertial Measurement Unit (IMU) sensors of smartphones is enough for the proposed driving evaluation system. Accuracy of this system is 87% without using GPS and GIS data and this system is independent of smartphones and vehicles types.     

智能网联汽车运动规划方法研究综述（双语出版）

分析了近年来智能网联汽车（Intelligent Connected Vehicle，ICV）运动规划方法的研究，根据规划时空尺度和任务目标，将ICV运动规划细分为路径规划、路线规划、动作规划和轨迹规划4级子任务，回顾了各级子任务中智能网联技术的研究和应用现状；探讨了ICV中驾驶人行为特性及其对运动规划结果的影响；从技术背景、研究场景、算法流程和应用理论4个方面，提出ICV运动规划方法研究的未来发展方向。结果表明：由于ICV主要依赖车辆网联信息规划运动路径，而路网中同时存在不同网联等级的ICV，这将增加路径规划问题的求解难度；现有ICV路线规划模型较少考虑周边多车运动状态以及路段车道设置情况，将现有算法与微观交通流模型相结合有助于解决此问题；ICV中人机协同及任务切换领域已出现诸多研究热点，如城市道路上换道与转弯动作规划、ICV引导非网联车辆行驶等问题；借鉴驾驶人行为模式规划ICV运动轨迹已成为研究共识，但是车-车、车-路网联信息在此领域的应用仍然有限；采用反馈-迭代的方法进行ICV运动路线和动作协同规划、运动规划和轨迹跟踪控制有助于获得全局最优的运动规划结果和车辆控制策略；根据具体规划任务特点选择构建ICV运动规划模型的基础理论，有助于发挥各类理论的优势，提升规划算法的灵活性和适用性。     

Do parking standards matter? Evaluating the London parking reform with a matched-pair approach

Minimum parking standards, which require developers to build a certain amount of off-street parking spaces, are increasingly criticized for leading to excess parking supply and automobile travel in recent years. However, due to the difficulty in identifying the policy effect, few empirical studies have directly and accurately estimated the effects of parking standards on parking supply. The present study examines a parking reform in London, UK, where minimum parking standards for residential developments were replaced with maximum standards in the early 2000s. Using planning application records, we match neighboring pre-reform and post-reform developments to estimate the effect of the parking standard switch and further identify the “binding” and “capping” effects of minimum and maximum parking standards. It is found that the parking reform in London has led to a reduction of approximately 0.76 parking spaces per unit in residential development applications, or 49% of the pre-reform level. Minimum parking standards seem to have a larger impact than maximum ones on parking supply that fell more upon inner city developments, while maximum parking standards have more influenced suburban neighborhoods. Market forces have played a major role in the decline of parking supply. The findings provide strong evidence for the market distortion effect of minimum parking standards.     

Development of location-based services for recommending departure stations to park and ride users

More and more commuters are beginning to favour public transportation. Fast and convenient park and ride (PnR) services provided by public transportation authorities are the result of changes of household demographics and household, increasing fuel prices and a focus on environmental sustainability. However, lack of parking spaces in PnR facilities creates a major bottleneck to this service. The aim of this research is to develop a location-based service (LBS) application to help PnR users choose the best train station to use to reach their destination using a multicriteria decision making model. A fuzzy logic method is used to estimate parking availability when a user is estimated to arrive at a PnR facility. Two surveys are conducted to collect traffic flow, travel behaviour and service quality data at four selected Perth Western Australia train stations. With the proposed approach and survey data, a prototype of LBS application, Station Finder, was developed using the Android SDK 4.0 and Google API 16. This application is a useful and practical tool to save travel cost and time of PnR users’.     

Electric vehicle parking in European and American context: Economic,energy and environmental analysis

The transportation sector faces increasing challenges related to energy consumption and local and global emissions profiles. Thus, alternative vehicle technologies and energy pathways are being considered in order to overturn this trend and electric mobility is considered one adequate possibility towards a more sustainable transportation sector.In this sense, this research work consisted on the development of a methodology to assess the economic feasibility of deploying EV charging stations (Park-EV) by quantifying the tradeoff between economic and energy/environmental impacts for EV parking spaces deployment. This methodology was applied to 4 different cities (Lisbon, Madrid, Minneapolis and Manhattan), by evaluating the influence of parking premium, infrastructure cost and occupancy rates on the investment Net Present Value (NPV). The main findings are that the maximization of the premium and the minimization of the equipment cost lead to higher NPV results. The NPV break-even for the cities considered is more “easily” reached for higher parking prices, namely in the case of Manhattan with the higher parking price profile. In terms of evaluating occupancy rates of the EV parking spaces, shifting from a low usage (LU) to a high usage (HU) scenario represented a reduction in the premium to obtain a NPV = 0 of approximately 14% for a 2500 € equipment cost, and, in the case of a zero equipment cost (e.g. financed by the city), a NPV = 0 was obtained with approximately a 2% reduction in the parking premium. Moreover, due to the use of electric mobility instead of the average conventional technologies, Well-to-Wheel (WTW) gains for Lisbon, Madrid, Minneapolis and Manhattan were estimated in 58%, 53%, 52% and 75% for energy consumption and 66%, 75%, 62% and 86% for CO₂ emissions, respectively.This research confirms that the success of deploying an EV charging stations infrastructure will be highly dependent on the price the user will have to pay, on the cost of the infrastructure deployed and on the adhesion of the EV users to this kind of infrastructure. These variables are not independent and, consequently, the coordination of public policies and private interest must be promoted in order to reach an optimal solution that does not result in prohibitive costs for the users.