Human-like autonomous car-following model with deep reinforcement learning

This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates from the empirical data. Through these interactions, an optimal policy, or car-following model that maps in a human-like way from speed, relative speed between a lead and following vehicle, and inter-vehicle spacing to acceleration of a following vehicle is finally obtained. The model can be continuously updated when more data are fed in. Two thousand car-following periods extracted from the 2015 Shanghai Naturalistic Driving Study were used to train the model and compare its performance with that of traditional and recent data-driven car-following models. As shown by this study’s results, a deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1 s, denoted as DDPGvRT, can reproduce human-like car-following behavior with higher accuracy than traditional and recent data-driven car-following models. Specifically, the DDPGvRT model has a spacing validation error of 18% and speed validation error of 5%, which are less than those of other models, including the intelligent driver model, models based on locally weighted regression, and conventional neural network-based models. Moreover, the DDPGvRT demonstrates good capability of generalization to various driving situations and can adapt to different drivers by continuously learning. This study demonstrates that reinforcement learning methodology can offer insight into driver behavior and can contribute to the development of human-like autonomous driving algorithms and traffic-flow models.     

Climate change behaviors related to purchase and use of personal cars: Development and validation of eco-socially conscious consumer behavior scale

A constantly changing environment and global warming are issues that are recognized at all global forums. One of the major reasons for global warming is the emission of greenhouse gasses which is primarily caused by use of personal cars as means of transport. This study reports on the development of an eco-socially conscious consumer behavior (ESCCB) scale specific to purchase and use of personal cars, based on samples of actual automobile customers in Pakistan. Using mixed method approaches, the results of 3 studies yield a 9-item three-dimensional scale (eco-social conservation, eco-social use, and eco-social purchase) with satisfactory reliability, construct validity and nomological validity. Second-order factor analysis revealed that eco-social purchase was the most important dimension, followed by eco-conservation and eco-social use. A test of nomological behavior shows that the scale is positively associated with a related construct: environmental concern. This study advances the literature on pro-environmental behaviors by introducing a conceptual definition of ESCCB related to personal car purchase and use, developing a measure for the ESCCB concept and validating the scale in the context of an emerging economy, Pakistan. The scale provides important insights for marketers in the automobile industry for remodelling marketing plans, as well as for environmentalists focusing on strategies to bring change in consumer behavior.     

The impact of land-use mix on residents' travel energy consumption: New evidence from Beijing

Policies that encourage mixed land use are widely believed to make transport more energy efficient. However, few studies have directly examined the impacts of land-use heterogeneity on travel energy consumption at the individual level. Moreover, the definition and measures of land-use heterogeneity are debated. This paper aims to fill these gaps using the large city of Beijing, China, as a case study. Three types of land use are examined in terms of their effects on individual residents’ travel energy consumption. The results suggest that high land-use diversity and a good jobs-housing balance significantly reduces commuting travel. Interestingly, highly heterogeneous retail and housing areas may have high travel energy use, as residents are more likely to go shopping. There are obvious spatial variations in these effects. Residents of suburban ‘newtowns’, where the jobs-housing balance is particularly good, consume less travel energy. The results suggest that decreased use of conventional planning patterns, such as the socialist danwei system, and increasing urban sprawl, bring new challenges to achieving transport efficiency. Mixed land-use policies can be an effective solution to these challenges.     

Subjective-utility travel time budget modeling in the stochastic traffic network assignment

ABSTRACT

In this article, we propose a new model called subjective-utility travel time budget (SU-TTB) model to capture travelers' risk-averse route choices. In the travel time budget (TTB) and mean-excess travel time (METT) model, a predefined confidence level is needed to capture the risk-aversion in route choice. Due to the day-to-day route travel time variations, the exact confidence level is hard to be predicted. With the SU-TTB model, we assume travelers' confidence level belongs to an interval that they may comply with in the route choice. The two main components of SU-TTB are the utility function and the TTB model. We can show that the SU-TTB can be reduced to the TTB and METT model with proper utility function for the confidence levels. We can also prove its equivalence with our recently proposed nonlinear-expectation route travel time (NERTT) model in some cases and give some new interpretation on the NERTT with this equivalence. Finally, we formulate the SU-TTB model as a variational inequality (VI) problem to model the risk-averse user equilibrium (RAUE), termed as generalized RAUE (GRAUE). The GRAUE is solved via a heuristic gradient projection algorithm, and the model and solution algorithm are demonstrated with the Braess's traffic network and the Nguyen and Dupuis's traffic network.     

面向控制的SCR催化转化器温度模型

为了建立面向控制的SCR催化器温度模型,根据能量守恒和质量守恒方程并考虑热平衡中所涉及的换热过程不同,建立了4种SCR催化器温度的数学模型,并利用Matlab/Simulink构建图形化的计算模型。采用柴油机欧洲稳态循环(ESC)和欧洲瞬态循环(ETC)条件下的台架实测数据对模型进行检验,基于最大离散程度、拟合度和计算时间3个指标对模型进行评价和比较。结果表明,考虑催化器与废气和周围环境对流换热的温度模型具有良好的预测精度和实时性,更适合用于SCR控制策略。     

北京市小汽车交通发展研究

首先对北京市小汽车发展的历程进行了回顾,接着分析了现状和特点,并对北京市小汽车发展引发的诸多经济社会问题进行了反思。认为当前小汽车发展是超前消费,超过了经济发展速度,与城市化发展不协调,小汽车在交通出行结构中所占比例过高,加重了交通拥堵,给资源、环境造成了沉重的负担和影响。从可持续发展的理念出发,北京市小汽车发展的总体策略应该是：适量拥有、合理使用。政府管理部门要树立“公交优先”的思想,采取各种管理手段缓解交通拥堵,减少交通事故。     

低温独立液舱曲面外板加工减薄量评估

基于耐低温合金材料的非线性特性,以某液化气船的低温独立液舱曲面外板加工成形过程为研究对象,研究其塑形变形过程及机理。利用ABAQUS作为计算分析工具,建立了板材原料及上、下加工模具的分析模型,给定冲压成形的时间和初始速度,并设定时间步长,考察每个时间步长的计算结果,分析了其加工过程中的弹塑性变形过程,评估了低温合金材料在加工过程中的板厚变化情况,并与实际加工测量值进行对比,验证了模型和计算分析过程的准确性。为各类低温独立液舱的设计和材料尺寸选用提供了技术支持和指导。     

也论柴油轿车在国内市场的发展前景

研究了世界范围内柴油机在乘用车领域内的应用现状,阐述了柴油机作为车用动力的优势。根据国内的政策环境与市场环境,分析了排放法规、柴油品质对市场的影响。根据对柴油轿车的性能要求,包括振动和噪声、排放等,分析了更适合我国轿车柴油机发展的技术路线,并重点对若干关键技术和难点进行了剖析。柴油机技术进步和市场化应用表明,柴油轿车在我国具有广阔的应用前景,政府和企业应做好政策和技术上的准备。     

不锈钢地铁车辆侧墙焊缝缺陷率分析

由于非熔透型激光叠焊工艺的局限性,侧墙焊缝处会产生内外钢板局部未焊透的现象即焊缝缺陷.为研究这种焊缝在不同缺陷率下的拉剪强度及其对车体静强度的影响,结合某不锈钢地铁车辆激光焊车体,通过建立不同焊缝缺陷率的车体有限元模型,分析各个工况下不同焊缝缺陷率的车体侧墙焊缝剪应力的变化,以此确定在静载工况下不锈钢激光焊车体侧墙焊缝缺陷率的限值.     

《深圳市综合交通体系规划((2013—2030)》编制探索——以更具竞争力、可持续的综合交通体系促进城市转型发展

通过回顾评价深圳市历次综合交通体系规划的得失,分析城市转型对于综合交通体系的挑战以及新形势下综合交通体系规划的定位。以《深圳市综合交通体系规划(2013—2030)》为例,对规划编制的内容和方法开展研究,具体包括:转型导向的交通发展目标与指标体系、一体化的综合交通体系组织、立足区域协作的整体交通战略、与组团结构相匹配的交通分区组织、与城市功能布局的协调互动、注重协同的交通管控政策,以及应对大数据的智能交通策略等。最后介绍规划编制组织特点并提出城市转型期综合交通体系规划的进一步思考。