Browsing by Author "Zangeneh, Pouya"

Now showing 1 - 5 of 5
  • Thumbnail Image
    ItemOpen Access
    Connected and Autonomous Vehicles Trajectory Optimization for an On-Ramp Freeway Merging Segment in a Mixed Vehicular Traffic Environment
    (2024-02-15) Hesabi Hesari, Abbas; Kattan, Lina; Behjat, Laleh; Zangeneh, Pouya
    Efficient and smooth merging processes on highways are critical for ensuring traffic safety, flow, and network efficiency. While traditional techniques, such as ramp metering and variable speed limits, offer benefits, their ability to optimize highway throughput remains limited. The emergence of connected and automated vehicles (CAVs) in road networks holds promise for enhancing transportation network efficiency and safety. This research develops a novel control algorithm focused on optimizing autonomous vehicle trajectories in a mixed traffic environment on a multilane highway. The objective is to eliminate stop-and-go conditions during merging and enhance a smooth and safe merging maneuver. The merging process is outlined in a hierarchical hybrid control framework that consists of three control layers: the top control layer, the intermediate tactical control layer, and the lower operational layer. At the top level, the controller gathers data from the real-time traffic environment and identifies a group of vehicles most impacted by the merging maneuvers. This information is relayed to the mid-layer, which then establishes a multiphase kinematic model of the system. Utilizing this model, the tactical controller designs a multi-input-multi-output (MIMO) model predictive control (MPC) scheme that optimizes autonomous vehicle trajectories while adhering to various constraints. At the operational level, CAVs employ optimized trajectories as reference signals for executing essential longitudinal and lateral maneuvers during merging operations. A PI (Proportional-Integral) control scheme regulates longitudinal maneuvers, while a PID (Proportional-Integral-Derivative) control scheme manages lateral maneuvers, and both schemes consider the distinctive vehicle dynamics of each CAV. Through comprehensive simulations that encompass diverse driving scenarios, the hybrid technique demonstrates reliability, robustness, and precision across variable initial conditions. This study also introduces a novel centralized control technique that integrates the control layers of the hybrid control system into a single layer and manages the entire merging process in a continuous motion. Comparing the hybrid and centralized control techniques demonstrates that the hybrid approach has remarkable computational efficiency and showcases higher robustness against model uncertainties and communication disturbances. In contrast, the centralized controller exhibits better stability and control performance with higher fuel efficiency and passenger comfort.
  • Thumbnail Image
    ItemOpen Access
    Developing an Equity Analysis Framework for On-demand Mobility Services with Emphasis on Accessibility Outcomes
    (2024-01-04) Ding, Yuesong; Demissie, Merkebe; Kattan, Lina; Zangeneh, Pouya; Kutlu, Sule Nur
    The transportation market is transforming significantly due to emerging mobility trends and technologies. This new paradigm contains a wide range of flexible, on-demand mobility services, from micro-mobility options like shared bikes and scooters to ride-hailing services like Uber. These shared on-demand mobility services promise to deliver economic, environmental, and social benefits to society. However, questions arise about the equitable distribution of the benefits and negative impacts of emerging on-demand mobility services among different population groups. Research on the equity performance of shared on-demand mobility services is still evolving. Several challenges persist, including the limitations of existing methodologies that rely on the fixed spatial nature of traditional transit infrastructure to assess the equity of free-floating on-demand mobility services, a lack of high-resolution data, and the oversight of the unique characteristics of on-demand mobility services, such as rebalancing and matching dynamics. Given these complexities, there is a clear need to develop a comprehensive equity analysis framework capable of adapting to the complex service provision processes associated with shared on-demand mobility services. Consequently, this thesis aims to create a general framework for evaluating the equity performance of emerging shared on-demand mobility services, specifically focusing on assessing access to jobs and land uses as key indicators.
  • Thumbnail Image
    ItemOpen Access
  • Thumbnail Image
    ItemOpen Access
    Mapping the Practice of Site Layout Planning in the Construction Industry
    (2023-07) Marcano Pina, Agnei Victoria; Sadeghpour, Farnaz; Zangeneh, Pouya; Caird, Jeffrey
    Site Layout Planning (SLP) is a key activity for construction management and the overall success of construction projects. Past studies in this field have approached multiple techniques to solve SLP as a decision-making optimization problem. However, construction practitioners in the industry typically use intangible or subjective methods to plan the site layout, with the support of multiple tools that are not directly designed for planning construction sites. The mismatch between the available developments from research and actual methods approached in practice directed to the exploration of the practice of SLP conducted by practitioners to define the requirements needed in an SLP tool. Semi-structured interviews were conducted among forty-seven highly experienced construction practitioners who self-identified as fully responsible of SLP activities. Constructivist grounded theory and content analysis were used as the methodological basis to collect and analyze the data. From the analysis of 18635 transcript lines, 5028 codes were obtained, resulting in 190 labels, 60 categories, and 5 themes. The emergent themes describe the components of SLP as site characteristics, purpose, decision-making variables, tools and technology, and planning perspectives. The first part of the results details the practice of SLP, and the considerations and approaches taken by SLP practitioners when conducting a SLP, where the focus is to produce a functional site layout in the early stages of the project. The final part of the results presents the tools and functionalities that practitioners currently use to plan a site layout and highlights the need to integrate these functions and requirements into a single tool that can be practical for the construction industry. The requirements include resource properties and pairwise spatial relationships, planning documents and regulations, layout assessment metrics, and tool modules that facilitate addressing every stage of the planning as identified in the first part of the results. Finally, the aim of this study was to present a guideline for future developments in SLP to ensure their implementation in practical settings. This guideline was designed through the exploration of processes, needs, and requirements of the final users.
  • Thumbnail Image
    ItemOpen Access
    Optimal Route Planning for Parking Enforcement Patrol using Reinforcement Learning
    (2023-11-22) Alemi, Ali Reza; Saidi, Saeid; Sabouri, Alireza; Kattan, Lina; Zangeneh, Pouya; Black, Kerry
    With the considerable population growth in cities, the need for sustainable and feasible parking enforcement solutions becomes increasingly important. A Parking enforcement solution involves finding optimal patrol policy for enforcement agents. A Patrol policy refers to a strategy or a plan for how patrols should be conducted in areas with potential violations to prevent violations and improve parking agency compliance. Given a comprehensive database about violation's distribution in different parking locations, we can incorporate an optimization model to find optimal patrol policies for different agents. However, in an environment in which we do not have such a complete database and also drivers change their attitude towards parking fee payments frequently, the effectiveness of a parking enforcement solution is measured by how it can effectively address the uncertainty existing in the number of violations for different locations. The effectiveness and efficiency of patrol enforcement algorithms have been argued in the literature. Still, the solution proposed in this study aims to tackle the problem using learning algorithms that were rarely used in previous works. We consider the problem of finding an optimal routing plan for the parking enforcement patrol vehicles when only partial data about the distribution of violations over the city is available. The decision maker faces the well-known exploration-exploitation trade-off, i.e., choosing the best route given the current information or trying new routes to gather data on potentially better routes. In the absence of a learning-based algorithm, an optimal patrol policy can only be considered as optimal regarding the current state of the environment's features but if the environment's features change, the previous solution is no longer optimal. A learning-based algorithm aims to learn the dynamic features of an environment and construct the optimal patrol policy according to the learned features. In this thesis, we first describe the problem and different approaches for the proposed problem; then, we propose a multi-arm bandit formulation and use reinforcement learning to sequentially generate routes to maximize the system's expected reward. Next, we will analyze the performance of our framework against the current patrol policies being conducted in the city. During this study, an interactive dashboard is developed and used throughout the study for spatially analyzing the distribution of violations across the city. This tool is adaptable for any agency looking into the spatial analysis of violation patterns. Our analytical findings indicate a potential increase in the observed number of violations with the implementation of this framework which leads to the agency's compliance improvement. In the final section, we will discuss the contribution and expected outcomes of the study in detail.