Communications in Transportation Research最新文献

Solving optimal control problems serves as the basic demand of industrial control tasks. Existing methods like model predictive control often suffer from heavy online computational burdens. Reinforcement learning has shown promise in computer and board games but has yet to be widely adopted in industrial applications due to a lack of accessible, high-accuracy solvers. Current Reinforcement learning (RL) solvers are often developed for academic research and require a significant amount of theoretical knowledge and programming skills. Besides, many of them only support Python-based environments and limit to model-free algorithms. To address this gap, this paper develops General Optimal control Problems Solver (GOPS), an easy-to-use RL solver package that aims to build real-time and high-performance controllers in industrial fields. GOPS is built with a highly modular structure that retains a flexible framework for secondary development. Considering the diversity of industrial control tasks, GOPS also includes a conversion tool that allows for the use of Matlab/Simulink to support environment construction, controller design, and performance validation. To handle large-scale problems, GOPS can automatically create various serial and parallel trainers by flexibly combining embedded buffers and samplers. It offers a variety of common approximate functions for policy and value functions, including polynomial, multilayer perceptron, convolutional neural network, etc. Additionally, constrained and robust algorithms for special industrial control systems with state constraints and model uncertainties are also integrated into GOPS. Several examples, including linear quadratic control, inverted double pendulum, vehicle tracking, humanoid robot, obstacle avoidance, and active suspension control, are tested to verify the performances of GOPS.

Parameter calibration of the traffic assignment models is vital to travel demand analysis and management. As an extension of the conventional traffic assignment, boundedly rational activity-travel assignment (BR-ATA) combines activity-based modeling and traffic assignment endogenously and can capture the interdependencies between high dimensional choice facets along the activity-travel patterns. The inclusion of multiple episodes of activity participation and bounded rationality behavior enlarges the choice space and poses a challenge for calibrating the BR-ATA models. In virtue of the multi-state supernetwork, this exploratory study formulates the BR-ATA calibration as an optimization problem and analyzes the influence of the two additional components on the calibration problem. Considering the temporal dimension, we also propose a dynamic formulation of the BR-ATA calibration problem. The simultaneous perturbation stochastic approximation algorithm is adopted to solve the proposed calibration problems. Numerical examples are presented to calibrate the activity-based travel demand for illustrations. The results demonstrate the feasibility of the solution method and show that the parameter characterizing the bounded rationality behavior has a significant effect on the convergence of the calibration solutions.

The COVID pandemic has accelerated the growth of ecommerce and reshaped shopping patterns, which in turn impacts trip-making and vehicle miles traveled. The objectives of this study are to define shopping styles and quantify their prevalence in the population, investigate the impact of the pandemic on shopping style transition, understand the generational heterogeneity and other factors that influence shopping styles, and comment on the potential impact of the pandemic on long-term shopping behavior. Two months after the initial shutdown (May/June 2021), we collected ecommerce behavioral data from 313 Sacramento Region households using an online survey. A K-means clustering analysis of shopping behavior across eight commodity types identified five shopping styles, including ecommerce independent, ecommerce dependent, and three mixed modes in-between. We found that the share of ecommerce independent style shifted from 55% pre-pandemic to 27% during the pandemic. Overall, 30% kept the same style as pre-pandemic, 54% became more ecommerce dependent, and 16% became less ecommerce dependent, with the latter group more likely to view shopping an excuse to get out. Heterogeneity was found across generations. Pre-pandemic, Millennials and Gen Z were the most ecommerce dependent, but during the pandemic they made relatively small shifts toward increased ecommerce dependency. Baby Boomers and the Silent Generation were bimodal, either sticking to in-person shopping or shifting to ecommerce-dependency during the pandemic. Post-pandemic intentions varied across styles, with households who primarily adopt non-food ecommerce intending to reverse back to in-person shopping, while the highly ecommerce dependent intend to limit future in-store activities.

Online demand prediction plays an important role in transport network services from operations, controls to management, and information provision. However, the online prediction models are impacted by streaming data quality issues with noise measurements and missing data. To address these, we develop a robust prediction method for online network-level demand prediction in public transport. It consists of a PCA method to extract eigen demand images and an optimization-based pattern recognition model to predict the weights of eigen demand images by making use of the partially observed real-time data up to the prediction time in a day. The prediction model is robust to data quality issues given that the eigen demand images are stable and the predicted weights of them are optimized using the network level data (less impacted by local data quality issues). In the case study, we validate the accuracy and transferability of the model by comparing it with benchmark models and evaluate the robustness in tolerating data quality issues of the proposed model. The experimental results demonstrate that the proposed Pattern Recognition Prediction based on PCA (PRP-PCA) consistently outperforms other benchmark models in accuracy and transferability. Moreover, the model shows high robustness in accommodating data quality issues. For example, the PRP-PCA model is robust to missing data up to 50% regardless of the noise level. We also discuss the hidden patterns behind the network level demand. The visualization analysis shows that eigen demand images are significantly connected to the network structure and station activity variabilities. Though the demand changes dramatically before and after the pandemic, the eigen demand images are consistent over time in Stockholm.

The transit bus environment is considered one of the primary sources of transmission of the COVID-19 (SARS-CoV-2) virus. Modeling disease transmission in public buses remains a challenge, especially with uncertainties in passenger boarding, alighting, and onboard movements. Although there are initial findings on the effectiveness of some of the mitigation policies (such as face-covering and ventilation), evidence is scarce on how these policies could affect the onboard transmission risk under a realistic bus setting considering different headways, boarding and alighting patterns, and seating capacity control. This study examines the specific policy regimes that transit agencies implemented during early phases of the COVID-19 pandemic in USA, in which it brings crucial insights on combating current and future epidemics. We use an agent-based simulation model (ABSM) based on standard design characteristics for urban buses in USA and two different service frequency settings (10-min and 20-min headways). We find that wearing face-coverings (surgical masks) significantly reduces onboard transmission rates, from no mitigation rates of 85% in higher-frequency buses and 75% in lower-frequency buses to 12.5%. The most effective prevention outcome is the combination of KN-95 masks, open window policies, and half-capacity seating control during higher-frequency bus services, with an outcome of nearly 0% onboard infection rate. Our results advance understanding of COVID-19 risks in the urban bus environment and contribute to effective mitigation policy design, which is crucial to ensuring passenger safety. The findings of this study provide important policy implications for operational adjustment and safety protocols as transit agencies seek to plan for future emergencies.

Global supply chain disruptions caused by the six-day blockage of the Suez Canal in March 2021 and the reduction in shipping through the Bosporus Strait since the onset of the Ukraine War in February 2022 are recent demonstrations of the critical importance of marine chokepoints to international trade and thus global economic security. To better understand and anticipate effects of a chokepoint closure on global trade, we combine GIS data of international shipping lanes with 2019 bilateral trade data to estimate how the closure of each of eleven chokepoints could change trade flows through other chokepoints and between countries. Estimates from the closure scenarios reveal alternate-shipping route linkages between seven chokepoints whereby if one were closed for an extended period, trade through one or more of the others would change significantly. The estimates also underscore the economic importance of the Danish Straits, the Bosporus Strait, the Strait of Hormuz, and the South China Sea and East China Sea to those countries that must rely on these chokepoints for access to maritime trade. Moreover, the estimates project delays and shifts in coastal seaport activity that could lead to knock-on effects that disrupt global supply chains long after a chokepoint blockage is cleared.

Sensors installed on a ship return high quality data that can be used for ship bunker fuel efficiency analysis. However, important information about weather and sea conditions the ship sails through, such as waves, sea currents, and sea water temperature, is often absent from sensor data. This study addresses this issue by fusing sensor data and publicly accessible meteorological data, constructing nine datasets accordingly, and experimenting with widely adopted machine learning (ML) models to quantify the relationship between a ship's fuel consumption rate (ton/day, or ton/h) and its voyage-based factors (sailing speed, draft, trim, weather conditions, and sea conditions). The best dataset found reveals the benefits of fusing sensor data and meteorological data for ship fuel consumption rate quantification. The best ML models found are consistent with our previous studies, including Extremely randomized trees (ET), Gradient Tree Boosting (GB) and XGBoost (XG). Given the best dataset from data fusion, their R² values over the training set are 0.999 or 1.000, and their R² values over the test set are all above 0.966. Their fit errors with RMSE values are below 0.75 ton/day, and with MAT below 0.52 ton/day. These promising results are well beyond the requirements of most industry applications for ship fuel efficiency analysis. The applicability of the selected datasets and ML models is also verified in a rolling horizon approach, resulting in a conjecture that a rolling horizon strategy of “5-month training + 1-month test/applicatoin” could work well in practice and sensor data of less than five months could be insufficient to train ML models.

Widespread adoption of electric vehicles (EVs) is a common and critical component of international strategies to mitigate environmental pollution, climate change and oil dependency. The ability of consumers to assess the total cost of ownership (TCO) of EVs relative to internal combustion engine vehicles (ICEVs) remains an important factor for EV uptake. The TCO of vehicles is not universal across different car segments and user profiles. We analyse and compare the TCO of ICEVs and EVs from 17 car segments across short- and long-term ownership periods, and further advance existing TCO approaches by integrating detailed activity-based driving profiles, taxation, grant structures and pricing. Results show that EV options in the most popular Irish car segments have existing battery EV options with a TCO averaging respectively 26% and 42% less than their equivalent petrol and diesel ICEV options over a 4-year ownership term when the current grant is included. This integrated method for granular TCO evaluation offers important insights for this market and affords scope to investigate how changes in travel patterns, car-segment pricing, taxation, grant policy, fuel costs, and carbon pricing and other transport policies can all affect TCO values over time across a broad range of market offerings.