Using Deep Learning Algorithms To Give Bicyclists The “Green Wave” At Traffic Signals,
2021
University of Oregon
Using Deep Learning Algorithms To Give Bicyclists The “Green Wave” At Traffic Signals, Stephen Fickas
TREC Project Briefs
Led by Dr. Stephen Fickas of the University of Oregon (UO), transportation researchers are working to give bicyclists smoother rides by allowing them to communicate with traffic signals via a mobile app.
An Improved Learnable Evolution Model For Solving Multi-Objective Vehicle Routing Problem With Stochastic Demand,
2021
Singapore Management University
An Improved Learnable Evolution Model For Solving Multi-Objective Vehicle Routing Problem With Stochastic Demand, Yunyun Niu, Detian Kong, Rong Wen, Zhiguang Cao, Jianhua Xiao
Research Collection School Of Computing and Information Systems
The multi-objective vehicle routing problem with stochastic demand (MO-VRPSD) is much harder to tackle than other traditional vehicle routing problems (VRPs), due to the uncertainty in customer demands and potentially conflicted objectives. In this paper, we present an improved multi-objective learnable evolution model (IMOLEM) to solve MO-VRPSD with three objectives of travel distance, driver remuneration and number of vehicles. In our method, a machine learning algorithm, i.e., decision tree, is exploited to help find and guide the desirable direction of evolution process. To cope with the key issue of "route failure" caused due to stochastic customer demands, we propose a …
Gp3: Gaussian Process Path Planning For Reliable Shortest Path In Transportation Networks,
2021
Singapore Management University
Gp3: Gaussian Process Path Planning For Reliable Shortest Path In Transportation Networks, Hongliang Guo, Xuejie Hou, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
This paper investigates the reliable shortest path (RSP) problem in Gaussian process (GP) regulated transportation networks. Specifically, the RSP problem that we are targeting at is to minimize the (weighted) linear combination of mean and standard deviation of the path's travel time. With the reasonable assumption that the travel times of the underlying transportation network follow a multi-variate Gaussian distribution, we propose a Gaussian process path planning (GP3) algorithm to calculate the a priori optimal path as the RSP solution. With a series of equivalent RSP problem transformations, we are able to reach a polynomial time complexity algorithm with guaranteed …
Data Files: Green Waves, Machine Learning, And Predictive Analytics: Making Streets Better For People On Bikes,
2021
University of Oregon
Data Files: Green Waves, Machine Learning, And Predictive Analytics: Making Streets Better For People On Bikes, Stephen Fickas
TREC Datasets and Databases
The project builds on a prior app that was designed for Green Light Optimized Speed Advisory (GLOSA). This is more colloquially known as keeping a vehicle in the green wave: you are at a location and moving at a speed that will allow you to (theoretically) have a green light at each intersection you encounter along a corridor. Our long-term goal is to extend the FastTrack app described in the Background section to include actuated signals along a corridor. This project takes a first step by evaluating the effectiveness of machine-learning algorithms to predict the next phase of an actuated …
Dynamic Lane Traffic Signal Control With Group Attention And Multi-Timescale Reinforcement Learning,
2021
Fudan University
Dynamic Lane Traffic Signal Control With Group Attention And Multi-Timescale Reinforcement Learning, Qize Jiang, Jingze Li, Weiwei Sun, Baihua Zheng
Research Collection School Of Computing and Information Systems
Traffic signal control has achieved significant success with the development of reinforcement learning. However, existing works mainly focus on intersections with normal lanes with fixed outgoing directions. It is noticed that some intersections actually implement dynamic lanes, in addition to normal lanes, to adjust the outgoing directions dynamically. Existing methods fail to coordinate the control of traffic signal and that of dynamic lanes effectively. In addition, they lack proper structures and learning algorithms to make full use of traffic flow prediction, which is essential to set the proper directions for dynamic lanes. Motivated by the ineffectiveness of existing approaches when …
Gaps And Opportunities In Accessibility Policy For Autonomous Vehicles,
2021
University of San Francisco
Gaps And Opportunities In Accessibility Policy For Autonomous Vehicles, William Riggs, Anurag Pande
Mineta Transportation Institute
Nearly 1 in 5 people in the US have a disability (more than 57 million) (U.S. Census Bureau), and people with disabilities use the automobile as a travel mode at significantly lower rates than people without disabilities (Bureau of Transportation Statistics). For example, people aged 18 to 64 with disabilities make 28% fewer trips per day (2.6 v. 3.6 trips) on average than people without disabilities. The disparity is even more significant for non-workers. These statistics highlight the notable technological, design, and policy failings in today’s transportation system - that disabled individuals have considerable suppressed demand for travel that is …
How Do Environmental Factors Affect Drivers’ Gaze And Head Movements?,
2021
University of Virginia
How Do Environmental Factors Affect Drivers’ Gaze And Head Movements?, Arash Tavakoli, Vahid Balali, Arsalan Heydarian
Mineta Transportation Institute
Studies have shown that environmental factors affect driving behaviors. For instance, weather conditions and the presence of a passenger have been shown to significantly affect the speed of the driver. As one of the important measures of driving behavior is the gaze and head movements of the driver, such metrics can be potentially used towards understanding the effects of environmental factors on the driver’s behavior in real-time. In this study, using a naturalistic study platform, videos have been collected from six participants for more than four weeks of a fully naturalistic driving scenario. The videos of both the participants’ faces …
Spatio-Temporal Analysis Of The Roadside Transportation Related Air Quality (Startraq) And Neighborhood Characterization,
2021
California State University, Fresno
Spatio-Temporal Analysis Of The Roadside Transportation Related Air Quality (Startraq) And Neighborhood Characterization, Jaymin Kwon, Yushin Ahn, Steve Chung
Mineta Transportation Institute
To promote active transportation modes (such as bike ride and walking), and to create safer communities for easier access to transit, it is essential to provide consolidated data-driven transportation information to the public. The relevant and timely information from data facilitates the improvement of decision-making processes for the establishment of public policy and urban planning for sustainable growth, and for promoting public health in the region. For the characterization of the spatial variation of transportation-emitted air pollution in the Fresno/Clovis neighborhood in California, various species of particulate matters emitted from traffic sources were measured using real-time monitors and GPS loggers …
A Deep Ensemble Method For Multi-Agent Reinforcement Learning: A Case Study On Air Traffic Control,
2021
Singapore Management University
A Deep Ensemble Method For Multi-Agent Reinforcement Learning: A Case Study On Air Traffic Control, Supriyo Ghosh, Sean Laguna, Laura Wynter, Laura Wynter, Hasan Poonawala
Research Collection School Of Computing and Information Systems
Reinforcement learning (RL), a promising framework for data-driven decision making in an uncertain environment, has successfully been applied in many real-world operation and control problems. However, the application of RL in a large-scale decentralized multi-agent environment remains a challenging problem due to the partial observability and limited communications between agents. In this paper, we develop a model-based kernel RL approach and a model-free deep RL approach for learning a decentralized, shared policy among homogeneous agents. By leveraging the strengths of both these methods, we further propose a novel deep ensemble multi-agent reinforcement learning (MARL) method that efficiently learns to arbitrate …
Integrating Empirical Analysis Into Analytical Framework: An Integrated Model Structure For On-Demand Transportation,
2021
Singapore Management University
Integrating Empirical Analysis Into Analytical Framework: An Integrated Model Structure For On-Demand Transportation, Yuliu Su, Ying Xu, Costas Courcoubetis, Shih-Fen Cheng
Research Collection School Of Computing and Information Systems
On-demand transportation services have been developing in an irresistible trend since their first launch in public. These services not only transform the urban mobility landscape, but also profoundly change individuals’ travel behavior. In this paper, we propose an integrated model structure which integrates empirical analysis into a discrete choice based analytical framework to investigate a heterogeneous population’s choices on ownership, usage and transportation mode with the presence of ride-hailing. Distinguished from traditional discrete choice models where individuals’ choices are only affected by exogenous variables and are independent of other individuals’ choices, our model extends to capture the endogeneity of supply …
Incorporating The 10th Edition Institute Of Traffic Engineers (Ite) Trip Generation Rates Into Virginia Department Of Transportation Guidelines,
2021
Old Dominion University
Incorporating The 10th Edition Institute Of Traffic Engineers (Ite) Trip Generation Rates Into Virginia Department Of Transportation Guidelines, Kun Xie, Mecit Cetin, Hong Yang, Xiaomeng Dong
Civil & Environmental Engineering Faculty Publications
The Institute of Transportation Engineers (ITE) released the Trip Generation (TG) 10th edition in 2017, which significantly updated its database, and some of its trip generation rates were substantially lower than those of earlier editions. This study aims to investigate the applicability of the TG 10th edition in various Virginia contexts and to recommend how to incorporate the TG 10th edition into state guidelines. The research team surveyed 31 state transportation agencies to obtain a clear understanding of current practices in the adoption of trip rates and trip estimation approaches. We systematically compared trip rates of TG 9th and 10th …
Exploration Of Corridor-Based Tolling Strategies For Virginia’S Express Toll Lanes,
2021
George Mason University
Exploration Of Corridor-Based Tolling Strategies For Virginia’S Express Toll Lanes, Shanjiang Zhu, Mecit Cetin, Hong Yang, Olcay Sahin, Atabak Mardan
Civil & Environmental Engineering Faculty Publications
Virginia has invested significant resources in the development of express toll lanes (ETLs), which adjust toll rates dynamically based on the level of toll lane usage. A tool is needed to investigate the potential impact of the I-66 Outside-the-Beltway (OTB) ETLs on regional traffic patterns. This study developed a microscopic traffic simulation model in TransModeler to evaluate a set of corridor-based tolling strategies for the I-66 ETLs in NOVA. This model also considered the changes in vehicle occupancy, mode split, and departure time among travelers because of tolls based on locally collected data. An interactive map-based analyzer based on the …
Assessing The Impact Of Health Benefits And Carbon Footprint In Student Parking Decisions At A University Campus,
2021
University of Texas at El Paso
Assessing The Impact Of Health Benefits And Carbon Footprint In Student Parking Decisions At A University Campus, Emiliano Ruiz
Open Access Theses & Dissertations
In the student parking location problem, traditionally, the parking permit cost, the last-mile travel time, and the ease of finding an available parking stall are the only decision criteria driving permit purchases. However, a studentâ??s choice of parking location has associated walking health benefits and sustainability impacts. These impacts are related to the walking distance from the parked vehicle to the final destination on campus, in addition to the location effect on the carbon footprint of a vehicle-trip taken to campus. As such, this Thesis examined a multi-criteria decision approach to a university studentâ??s choice of parking location. This approach …
User Acceptance Of Autonomous Public Transport Systems (Apts): Extended Utaut2 Model,
2021
Istanbul University
User Acceptance Of Autonomous Public Transport Systems (Apts): Extended Utaut2 Model, Huseyin Korkmaz, Akif Fidanoglu, Salih Ozcelik, Abdullah Okumus
Journal of Public Transportation
The purpose of this study is to investigate the factors affecting the acceptance and use of the APTS by its potential users. To achieve this, an integrated and expanded user acceptance model is introduced to explain the factors affecting the Behavioral Intention to use the APTS. A total of 316 surveys were conducted, from 275 participants by online surveys and 41 participants by face to face interviews. With the data that are acquired from Public Transportation (PT) users in Istanbul, the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) Model is modified and Performance Expectancy, Effort Expectancy, Social …
Webinar: The Impact Of Ride Hail Services On The Accessibility Of Nonprofit Services,
2021
University of Oregon
Webinar: The Impact Of Ride Hail Services On The Accessibility Of Nonprofit Services, Dyana Mason
TREC Webinar Series
Nonprofit organizations are responsible for providing human services across the United States, often in partnership with government agencies. In this work, they address some of the most pressing social issues – including homelessness, poverty, health care and education. While many of these organizations consider location and accessibility crucial to supporting their clients – often locating services near bus or train stops, for example – little is known about the impact of new technologies, including ride hail services (also called Transportation Network Companies, or TNCs) like Lyft and Uber, on nonprofit accessibility. Do these services help fill gaps in client needs? …
Data-Driven Methods To Address Truck Parking Shortages For Long-Haul Commercial Truck Drivers,
2021
University of Arkansas, Fayetteville
Data-Driven Methods To Address Truck Parking Shortages For Long-Haul Commercial Truck Drivers, Sharif Mahmud
Graduate Theses and Dissertations
Truck parking is a critical concern for both the trucking industry and the truck drivers. Long-haul commercial truck drivers rely on safe and adequate parking to support interstate commerce, which has become a challenge due to parking shortages. The recent electronic logging device (ELD) mandate, forcing a strict compliance to hours of service (HOS) regulations, are leading to higher demand for parking. A number of federal, regional, and local studies reveal that truck activity will increase and truck parking demand will outpace parking supply in the coming years. Such parking shortages likely disrupt freight flows and pose risks to truck …
Researching Relationships Between Truck Travel Time Performance Measures And On-Network And Off-Network Characteristics,
2021
University of North Carolina at Charlotte
Researching Relationships Between Truck Travel Time Performance Measures And On-Network And Off-Network Characteristics, Sarvani Duvvuri, Srinivas S. Pulugurtha
Mineta Transportation Institute
Trucks serve significant amount of freight tonnage and are more susceptible to complex interactions with other vehicles in a traffic stream. While traffic congestion continues to be a significant ‘highway’ problem, delays in truck travel result in loss of revenue to the trucking companies. There is a significant research on the traffic congestion mitigation, but a very few studies focused on data exclusive to trucks. This research is aimed at a regional-level analysis of truck travel time data to identify roads for improving mobility and reducing congestion for truck traffic. The objectives of the research are to compute and evaluate …
A Model For Integrating Rail Services With Other Transportation Modalities: Identifying The Best Practices And The Gaps For California’S Next State Rail Plan,
2021
Mineta Transportation Institute
A Model For Integrating Rail Services With Other Transportation Modalities: Identifying The Best Practices And The Gaps For California’S Next State Rail Plan, Eric Peterson, Wenbin Wei, Lydon George
Mineta Transportation Institute
The California State Rail Plan (CSRP) is among the best rail plan documents published by any jurisdiction in the United States to date. As such, the CSRP is used in this paper as the basis of comparison to other state rail service plans. These plans will have been submitted to the Federal Railroad Administration (FRA) on record as of June 2020—as required under Section 303 of the Passenger Rail Investment and Improvement Act (PRIIA) of 2008. The purpose of this paper is to identify the best practices and gaps that may inform California and other states in their future rail …
Step-Wise Deep Learning Models For Solving Routing Problems,
2021
Singapore Management University
Step-Wise Deep Learning Models For Solving Routing Problems, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
Routing problems are very important in intelligent transportation systems. Recently, a number of deep learning-based methods are proposed to automatically learn construction heuristics for solving routing problems. However, these methods do not completely follow Bellman's Principle of Optimality since the visited nodes during construction are still included in the following subtasks, resulting in suboptimal policies. In this article, we propose a novel step-wise scheme which explicitly removes the visited nodes in each node selection step. We apply this scheme to two representative deep models for routing problems, pointer network and transformer attention model (TAM), and significantly improve the performance of …
Unintended Consequences Of Public Policy And Government Regulation On Supply Chain Structure, Conduct, And Performance,
2021
University of Arkansas, Fayetteville
Unintended Consequences Of Public Policy And Government Regulation On Supply Chain Structure, Conduct, And Performance, Jonathan Phares
Graduate Theses and Dissertations
Supply chains, and the firms within them, change their behaviors in response to industry conditions so they can provide efficiency, effectiveness, strategic enablement, and customer utility. Social and economic policies enacted to promote social welfare by correcting market failures can alter these conditions. While these policies may serve their intended purposes, they may also create unintended consequences that may make managing logistics, operations, and supply chains more challenging. This dissertation contributes to the nascent body of knowledge concerning the intended and unintended consequences of policy on supply chain management by examining three unique contextual settings using different methodologies and levels …
