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.     

Integrating mesoscopic dynamic traffic assignment with agent-based travel behavior models for cumulative land development impact analysis

A number of approaches have been developed to evaluate the impact of land development on transportation infrastructure. While traditional approaches are either limited to static modeling of traffic performance or lack a strong travel behavior foundation, today’s advanced computational technology makes it feasible to model an individual traveler’s response to land development. This study integrates dynamic traffic assignment (DTA) with a positive agent-based microsimulation travel behavior model for cumulative land development impact studies. The integrated model not only enhances the behavioral implementation of DTA, but also captures traffic dynamics. It provides an advanced yet practical approach to understanding the impact of a single or series of land development projects on an individual driver’s behavior, as well as the aggregated impacts on the demand pattern and time-dependent traffic conditions. A simulation-based optimization (SBO) approach is proposed for the calibration of the modeling system. The SBO calibration approach enhances the transferability of this integrated model to other study areas. Using a case study that focuses on the cumulative land development impact along a congested corridor in Maryland, various regional and local travel behavior changes are discussed to show the capability of this tool for behavior side estimations and the corresponding traffic impacts.     

大洪山生态文化旅游区空间发展模式研究

文章针对近域旅游区主导旅游资源相似和相异并存的特点,提出旅游区＂整合-竞合＂发展模式（3C模式）,并以大洪山生态文化旅游区组织与规划为例,提出基于游客行为的旅游线路组织模式及相应的旅游公路网布局结构与交通设计理念。     

Gantry crane operations to transfer containers between trains: A simulation study of a Spanish terminal

Freight transfer operations are critical in combined transport networks. In this paper a simulation model and modelling approach to the transfer of cargo between trains at rail terminals is presented. The model is used to study the Port-Bou terminal, the main intermodal terminal at the Spanish-French frontier. Four different gantry crane operation modes to interchange containers between trains are evaluated. These operation rules are tested in several scenarios to examine the critical factors of the system and the best operation rule for each situation. Latest generation software is used to develop the model that incorporates modular programming and enhanced graphic systems for output representation. It allows a dynamic display of the simulated system and, likewise, the possibility of developing modules that can be reused in other studies. The research shows how simulation can be a useful planning tool in the rail transportation context.     

Toward regional transportation governance: a case study of Greater Vancouver

This paper discusses the evolving institutional structure and governance of transportation planning, policy development and transit delivery within one major North American city-region, the Greater Vancouver area. Various methods of transportation governance are explored from complete independence to full regional integration. The move away from a direct provincial role in transportation management to a greater regional transit authority is discussed and critiqued. This revised version was published online in June 2006 with corrections to the Cover Date.     

Developing a Spatially Enabled Inventory of Recreational Boats Using Vessel Registration Data

Effective waterway management requires information on the characteristics and locations of boats. A field-based boat census—a traditional method to obtain spatially accurate information—is relatively expensive, time-consuming, and restrictive in scope. Vessel registration data, maintained by all U.S. states, is potentially a more robust information source. This research evaluated the accuracy and reliability of vessel registration data to supply location and attribute information for boats. The study premise was to use vessel registration data, which includes the mailing address of registered boat owners, to develop a spatially enabled inventory of boats. The study area comprised 12,064 salt-water accessible property parcels in two Florida counties. An on-water census (OWC) provided location and characteristics for 5,023 vessels, which were compared to 8,681 vessel registration records linked to the study area. Discrepancies between the OWC and vessel registration data were explained by a stratified, random sample of 485 telephone survey respondents. Study results show that vessel registration data accurately located and characterized roughly 81% of the boat population; in contrast, the OWC accurately located less than 56%. A conclusion is that state vessel registration data is a better alternative than an OWC for locating and characterizing boats kept along waterways.     

试论大学英语课堂活动的有效策划

随着教学改革的不断深入,英语教师越来越重视活动在课堂中的运用。本文首先分析了大学英语课堂活动中存在的问题,再从五个方面提出了策划课堂活动时提高活动有效性的原则及改进方法,这五个方面分别是:明确活动的目标性、加强活动实用性、确保活动的可行性、把握活动的可控性、提高活动的参与性。     

Support for Oregon land‐use planning: A multi‐level analysis

Abstract

This article analyzes support for and opposition to state land‐use planning in Oregon, using voting records from the 1976 referendum to repeal Oregon's regulatory legislation and survey data. Support for controlled growth legislation is found to be a product of both individual‐level characteristics and characteristics of the larger community where one resides. The most influential contextual variables are the county's economy and the class composition of the city. The authors conclude that coastal zone managers must exercise caution when interpreting individual survey data which indicate support for various environmental concerns. Contextual differences must be taken into consideration because sources of support for coastal zone management may vary among individuals, depending on the nature of the communities in which they live.     

舰船物资转运方案计算机辅助决策算法研究

瞬息万变的现代战场对大中型水面战斗舰船甲板物资转运的效率提出越来越高的要求。引入计算机辅助决策技术,在考虑多种牵制因素的情况下,快速获得最优的物资转运方案。详细分析和阐述舰船物资转运线路规划、时间计算、作业排序以及资源配班等4个主要问题的计算机解决方法,为利用计算机辅助制定最优物资转运方案提供可行途径。     

一般收费道路通行费收入实用预测方法研究

重点探讨实际道路规划项目中一般收费道路的收费收入预测方法,目的在于尽可能使收费收入预测更为精确。在我国,高速公路通常采用依靠征收通行费以偿还投资借贷的方式进行建设,因此在规划的过程中需要对通行费收入进行预测,并进行财务分析,以保证决策者做出正确的投资决策。以笔者在日本从事的高速公路建设项目为例,分析研究了基于实用型交通量增量分配方法结合使用车种转换矩阵的高速公路路网中一般收费道路通行费收入的预测方法,并将其应用到实际道路项目财务评价中。结果表明通过控制收费道路出入口间交通量预测精度,以及采用需求相关性较大的车种转换调查数据可以提高通行费预测精度。研究表明这一方法具有很强的实用性,该方法对我国的高速公路需求预测有着借鉴作用。