Engineering Commons^™

Controlling Complex Dynamic Transportation Systems: Development And Adaptation Of A Novel Distributed Cooperative Multi-Agent Learning Technique, Russell Thomas Graves

Doctoral Dissertations

Intelligent transportation systems continue to increase complexity, scale, and scope as more devices contain embedded compute. Cooperation among vehicles, intersections, and other members of the greater traffic ecosystem at a system-of-systems level is critical to improving the efficiency of the multi-billion-dollar asset that is the U.S. roadway infrastructure. This work introduces a negotiations strategy among multi-agent reinforcement learning agents and applies this to both traffic signal control and supervisory control of vehicle platooning. The traffic signal control implementation builds off of many prior research thrusts, and was shown to improve vehicle throughput by an average of 671veh/hr over actuated traffic …

A Self-Learning Intersection Control System For Connected And Automated Vehicles, Ardeshir Mirbakhsh

Dissertations

This study proposes a Decentralized Sparse Coordination Learning System (DSCLS) based on Deep Reinforcement Learning (DRL) to control intersections under the Connected and Automated Vehicles (CAVs) environment. In this approach, roadway sections are divided into small areas; vehicles try to reserve their desired area ahead of time, based on having a common desired area with other CAVs; the vehicles would be in an independent or coordinated state. Individual CAVs are set accountable for decision-making at each step in both coordinated and independent states. In the training process, CAVs learn to minimize the overall delay at the intersection. Due to the …

Utilizing Shockwave Theory And Deep Learning To Estimate Intersection Traffic Flow And Queue Length Based On Connected Vehicle Data., Abdulmaged Algomaiah

Electronic Theses and Dissertations

The development of Connected Vehicles (CV) facilitates the use of trajectory data to estimate queue length and traffic volume at signalized intersections. The previously proposed models involved additional information that may require conducting different types of data collection. Also, most models need higher market penetration rate or more than a vehicle per cycle to provide adequate estimation. This is mainly because a significant number of the estimation models utilized only queued vehicles. However, the state of motion in non-queued vehicles, particularly slowed-down vehicles, provides much information about the traffic characteristics. There is a lack of exploiting the information from slowed-down …

Deep Reinforcement Learning Approach For Lagrangian Control: Improving Freeway Bottleneck Throughput Via Variable Speed Limit, Reza Vatani Nezafat

Civil & Environmental Engineering Theses & Dissertations

Connected vehicles (CVs) will enable new applications to improve traffic flow. The focus of this dissertation is to investigate how reinforcement learning (RL) control for the variable speed limit (VSL) through CVs can be generalized to improve traffic flow at different freeway bottlenecks. Three different bottlenecks are investigated: A sag curve, where the gradient changes from negative to positive values causes a reduction in the roadway capacity and congestion; a lane reduction, where three lanes merge to two lanes and cause congestion, and finally, an on-ramp, where increase in demand on a multilane freeway causes capacity drop. An RL algorithm …

Development And Evaluation Of Cooperative Intersection Management Algorithm Under Connected Vehicles Environment, Slobodan Gutesa

Dissertations

Recent technological advancements in the automotive and transportation industry established a firm foundation for development and implementation of various automated and connected vehicle (C/AV) solutions around the globe. Wireless communication technologies such as the dedicated short-range communication (DSRC) protocol are enabling instantaneous information exchange between vehicles and infrastructure. Such information exchange produces tremendous benefits with the possibility to automate conventional traffic streams and enhance existing signal control strategies. While many promising studies in the area of signal control under connected vehicle (CV) environment have been introduced, they mainly offer solutions designed to operate a single isolated intersection or they require …

A Microscopic Simulation Study Of Applications Of Signal Phasing And Timing Information In A Connected Vehicle Environment, Gwamaka Lameck Njobelo

UNF Graduate Theses and Dissertations

The connected vehicle technology presents an innovative way of sharing information between vehicles and the transportation infrastructure through wireless communications. The technology can potentially solve safety, mobility, and environmental challenges that face the transportation sector. Signal phasing and timing information is one category of information that can be broadcasted through connected vehicle technology. This thesis presents an in-depth study of possible ways signal phasing and timing information can be beneficial as far as safety and mobility are concerned. In total, three studies describing this research are outlined.

The first study presented herein focuses on data collection and calibration efforts of …

Enhancing Intersection Safety For The Blind And Visually Impaired (Bvi) Pedestrian Using Device-To-Infrastructure Communication, Mohammad Sayyah Al-Akash

Masters Theses

Visually impaired pedestrians have limited mobility options, where they rely heavily on walking and transit for their transportation needs. One of the major issues facing these pedestrians is intersection crossing. Accessible Pedestrian Signals (APS), as a means of helping their intersection crossings, were introduced in the United States as early as 1920 but were not included in the Manual on Uniform Traffic Control Device (MUTCD) until 2000. The most recent type of APS is the beaconing APS which has shown improvements in road crossing abilities of blind pedestrians though it has many downsides to it. This study developed a cane …

A Smart Highway Work Zone Merge System Enabled By Connected Vehicles., Abdulmaged Algomaiah

Electronic Theses and Dissertations

Typical traffic control and operations at work zones usually are not very effective in mitigating the work zone bottleneck. A major reason is that the common early merge behaviors limits utilizing the available capacity in the closed lane, especially under moderate to high traffic demands. Recently, using late merge strategy is encouraged to prevent early merge behavior and fully utilize the closed lane and therefore increase capacity of work zone. The development of late merge strategy was not enough to substantially improve the situation due to the lack of compliance and communication among drivers. This thesis suggests and investigates a …

Modeling, Control, And Impact Analysis Of The Next Generation Transportation System, Feng Zhu

Open Access Dissertations

This dissertation aims to develop a systematic tool designated for connected and autonomous vehicles, integrating the simulation of traffic dynamics, traffic control strategies, and impact analysis at the network level.

The first part of the dissertation is devoted to the traffic flow modeling of connected vehicles. This task is the foundation step for transportation planning, optimized network design, efficient traffic control strategies, etc, of the next generation transportation system. Chapter 2 proposes a cell-based simulation approach to model the proactive driving behavior of connected vehicles. Firstly, a state variable of connected vehicle is introduced to track the trajectory of connected …

Safety Aspects Of Bicyclists In A Connected Vehicle Environment, Ajaykumar Patil

Civil Engineering Theses

The revival in the number of bicyclists, bike infrastructure investments and bike policies in the U.S. in the last two decades has escalated the importance of bicycling as a mode of transportation. With the proliferating role of the bicycle mode, bike fatalities continue to grow, too. In response to the increase in fatalities and crashes caused by human driven vehicles, the automobile industry and governments seek to develop autonomous vehicles that can address most of the human related crash causes. While increasing safety remains the primary goal of autonomous vehicles (AV) innovation, the difficulty of bicyclist and pedestrian detection using …