Integrated models of land use and transportation for the autonomous vehicle revolution

ABSTRACT

The advent of the autonomous vehicle (AV) will affect not only the transportation system, but also future patterns of land development. Integrated land use and transportation models will be critical tools in assessing the path forward with this technology. Key questions with respect to land use impacts of AVs arise from potential changes in sensitivity to travel and reduced demand for parking. It is an open question whether AVs will induce urban sprawl, or whether spatial economies of agglomeration will mitigate any reductions in travel time sensitivity. The deployment of shared fleets of AVs would likely reduce parking demand, producing yet to be explored impacts on property development within existing urban footprints. We perform a critical assessment of currently operational models and their ability to represent the adoption of AVs. We identify the representation of time in such models as a vital component requiring additional development to model this new technology. Existing model applications have focused on the discrete addition of new infrastructure or policy at a fixed point in time, whereas AV adoption will occur incrementally through time. Stated adaptation surveys are recommended as tools to quantify preferences and develop relevant model inputs. It is argued that existing models that assume comparatively static equilibrium have been convenient in the past, but are insufficient to model technology adoption. In contrast, dynamic model frameworks lack sufficient structure to maintain reasonability under large perturbations from base conditions. The ongoing advancement of computing has allowed models to move away from being mechanistic aggregate tools, towards behaviourally rich depictions of individual persons and firms. However, much work remains to move from projections of existing conditions into the future, to the evolution of the spatial economy as it evolves through time in response to new technologies and exogenous stresses. Principles from complex and evolutionary systems theory will be important in the development of models with the capacity to consider such dynamics.     

应用对象语义进行图像检索的新方法

为了降低图像高层语义与低层视觉特征之间的语义差异,本文以对象描述模型为基础,提出利用机器转换模型获取图像高层语义的方法。本方法首先利用图像分割技术对图像进行分割,然后利用机器学习的方法,得到训练样本集中高层语义与分割后低层视觉特征之间的先验概率关系;在查询的过程中,利用得到的先验概率模型计算与高层语义所对应的最大概率视觉低层特征,最后利用该低层特征进行检索,达到缩短高层语义与低层特征之间的语义差异的目的。在一个拥有5000幅图像的图像库上所做的测试结果表明了该方法的有效性和可行性,同时该方法也为解决图像高层语义与视觉低层特征之间语义的矛盾开扩了思路。     

“教学做合一”教学模式在汽车维修专业课教学中的实践

随着我国中等职业教育的发展与普及,学校对于学生的成绩要求降低,这也就在一定程度上导致所招收的学生综合素质能力水平不足。而在学习过程中,由于学生的学习基础较差、学习兴趣不足,影响专业技术的教学,不利于中职院校课堂教学的发展与进步。要想当前对教育教学形式,满足老师老师的教学需求,就要对中职院校的教学模式进行改变与创新。而"教学做合一"的教学模式能够通过实践活动、以学生为教学中心,引导学生主动参与到课堂教学当中,有效的提高课堂教学质量与效率。本文通过对"教学做合一"的教学模式的内涵和特征进行分析,进一步进行"教学做合一"教学模式在汽车维修专业课教学中的探索与实践。     

基于TD3算法的人机混驾交通环境自动驾驶汽车换道研究

提高人类驾驶人的接受度是自动驾驶汽车未来的重要方向,而深度强化学习是其发展的一项关键技术。为了解决人机混驾混合交通流下的换道决策问题,利用深度强化学习算法TD3（Twin Delayed Deep Deterministic Policy Gradient）实现自动驾驶汽车的自主换道行为。首先介绍基于马尔科夫决策过程的强化学习的理论框架,其次基于来自真实工况的NGSIM数据集中的驾驶数据,通过自动驾驶模拟器NGSIM-ENV搭建单向6车道、交通拥挤程度适中的仿真场景,非自动驾驶车辆按照数据集中驾驶人行车数据行驶。针对连续动作空间下的自动驾驶换道决策,采用改进的深度强化学习算法TD3构建换道模型控制自动驾驶汽车的换道驾驶行为。在所提出的TD3换道模型中,构建决策所需周围环境及自车信息的状态空间、包含受控汽车加速度和航向角的动作空间,同时综合考虑安全性、行车效率和舒适性等因素设计强化学习的奖励函数。最终在NGSIM-ENV仿真平台上,将基于TD3算法控制的自动驾驶汽车换道行为与人类驾驶人行车数据进行比较。研究结果表明：基于TD3算法控制的车辆其平均行驶速度比人类驾驶人的平均行车速度高4.8%,在安全性以及舒适性上也有一定的提升;试验结果验证了训练完成后TD3换道模型的有效性,其能够在复杂交通环境下自主实现安全、舒适、流畅的换道行为。     

基于人-车交互的行人轨迹预测

针对行人轨迹预测具有复杂、拥挤的场景和社会交互问题,基于长短时记忆网络（Long Short-term Memory Network, LSTM）对行人与车辆、行人与其他行人的交互进行建模,提出一种基于人-车交互的行人轨迹预测模型（VP-LSTM）。该模型同时考虑了行人与行人的交互、行人与车辆的交互,更适用于复杂的交通场景。所构建的VP-LSTM包括3个输入,以行人的方向和速度作为历史轨迹序列输入,行人与行人的相对位置作为人-人交互信息输入,行人与车辆的相对位置作为人-车交互信息输入。该方法首先设计扇形人-人交互邻域和圆形人-车交互邻域来准确捕捉对被预测行人有相互作用的行人和车辆;其次建立3种不同的LSTM编码层来编码历史行人轨迹序列、人-人、人-车社交信息;然后定义人-人、人-车交互的防碰撞函数和方向注意力函数作为人-车、人-人社交信息的权重,进一步提高社会信息的精度;再将人-人、人-车交互信息输入到注意力模块中筛选出对行人影响大的社会信息;最后将筛选后的社会信息与行人历史轨迹序列一起输入到LSTM神经网络中进行行人轨迹预测,并在构建的DUT人-车交互数据集上验证提出的网络。研究结果表明：提出的方法能够准确地预测出交通场景中,人-车交互行人未来一段时间内的运动轨迹,有效提高了预测精度,提高了智能驾驶决策的准确性。     

Autonomous cars: The tension between occupant experience and intersection capacity

Systems that enable high levels of vehicle-automation are now beginning to enter the commercial marketplace. Road vehicles capable of operating independently of real-time human control under an increasing set of circumstances will likely become more widely available in the near future. Such vehicles are expected to bring a variety of benefits. Two such anticipated advantages (relative to human-driver vehicle control) are said to be increased road network capacity and the freeing up of the driver-occupant’s time to engage in their choice of leisurely or economically-productive (non-driving) tasks.In this study we investigate the implications for intersection capacity and level-of-service of providing occupants of automated (without real-time human control), autonomously-operating (without vehicle-to-X communication) cars with ride quality that is equivalent (in terms of maximum rates of longitudinal and lateral acceleration) to two types of rail systems: [urban] light rail transit and [inter-urban] high-speed rail. The literature suggests that car passengers start experiencing discomfort at lower rates of acceleration than car drivers; it is therefore plausible that occupants of an autonomously-operating vehicle may wish to instruct their vehicle to maneuver in a way that provides them greater ride comfort than if the vehicle-control algorithm simply mimicked human-driving-operation.On the basis of traffic microsimulation analysis, we found that restricting the dynamics of autonomous cars to the acceleration/deceleration characteristics of both rail systems leads to reductions in a signalized intersection’s vehicle-processing capacity and increases in delay. The impacts were found to be larger when constraining the autonomous cars’ dynamics to the more-restrictive acceleration/deceleration profile of high-speed rail. The scenarios we analyzed must be viewed as boundary conditions, because autonomous cars’ dynamics were by definition never allowed to exceed the acceleration/deceleration constraints of the rail systems. Appropriate evidence regarding motorists’ preferences does not exist at present; establishing these preferences is an important item for the future research agenda.This paper concludes with a brief discussion of research needs to advance this line of inquiry.     

基于自主学习模式的精品课程共享资源后续建设研究

从当前我国高等学校精品课程的建设及应用现状出发，分析了不同自主学习模式对教育机构提供的精品课程或资源共享课程的需求，提出了基于自主学习模式的精品课程网络共享资源后续建设项目与标准建议。     

Vehicle platoon formation using interpolating control: A laboratory experimental analysis

This work addresses the formation phase of automatic platooning. The objective is to optimally control the throttle of vehicles, with a given arbitrary initial condition, such that desired ground speed and inter-vehicular spacings are reached. The steering of the vehicles is also controlled, because the vehicles should track a desired path while forming the platoon. In order to address the platoon formation problem, a cooperative strategy is formed by constructing a discrete state space model which represents the dynamics of a set of n vehicles. Once this model is set, a control method known as Interpolating Control, which aims at regulating to the origin an uncertain and/or time-varying linear discrete-time system with state and control constraints, is utilized. The performance of this control method is evaluated and compared with other approaches such as Model Predictive Control (MPC).Simulations are conducted which suggest that the Interpolating Control approach can be seen as an alternative to optimization-based control schemes such as Model Predictive Control, especially for problems for which finding the optimal solution requires calculations, where the Interpolating Control approach can provide a straightforward sub-optimal solution.In the experimental part of this work, the control algorithms for the platoon formation and path tracking problems are combined, and tested in a laboratory environment, using three mobile robots equipped with wireless routers. Validation of the proposed models and control algorithms is achieved by successful experiments.     

Identifying tourists and analyzing spatial patterns of their destinations from location-based social media data

Reliable travel behavior data is a prerequisite for transportation planning process. In large tourism dependent cities, tourists are the most dynamic population group whose size and travel choices remain unknown to planners. Traditional travel surveys generally observe resident travel behavior and rarely target tourists. Ubiquitous uses of social media platforms in smartphones have created a tremendous opportunity to gather digital traces of tourists at a large scale. In this paper, we present a framework on how to use location-based data from social media to gather and analyze travel behavior of tourists. We have collected data of about 67,000 users from Twitter using its search interface for Florida. We first propose several filtering steps to create a reliable sample from the collected Twitter data. An ensemble classification technique is proposed to classify tourists and residents from user coordinates. The accuracy of the proposed classifier has been compared against the state-of-the-art classification methods. Finally, different clustering methods have been used to find the spatial patterns of destination choices of tourists. Promising results have been found from the output clusters as they reveal most popular tourist spots as well as some of the emerging tourist attractions in Florida. Performance of the proposed clustering techniques has been assessed using internal clustering validation indices. We have analyzed temporal patterns of tourist and resident activities to validate the classification of the users in two separate groups of tourists and residents. Proposed filtering, identification, and clustering techniques will be significantly useful for building individual-level tourist travel demand models from social media data.