Impact Assessment of Integrating AVs in Optimizing Urban Traffic Operations for Sustainable Transportation Planning in Riyadh

Abstract

Integrating autonomous vehicles (AVs) into urban traffic systems presents significant opportunities for optimizing traffic flow, reducing congestion, and enhancing transportation efficiency. This study proposes a comprehensive framework that combines mathematical optimization techniques, policy planning, and AV adoption modeling to improve urban mobility. Using Highway Capacity Manual (HCM) Optimization methods, the research fine-tunes traffic signal timings, dynamically allocates green time, and enhances intersection coordination to maximize throughput. The study evaluates the impact of AV penetration on traffic flow efficiency, congestion reduction, and infrastructure readiness using real-world urban data from Riyadh. The results indicate that AV integration leads to a 40% increase in traffic throughput, a 60% reduction in congestion levels, and a 45% improvement in infrastructure readiness, highlighting the effectiveness of AV-driven traffic optimization strategies. Additionally, policy interventions aimed at reducing legal constraints and increasing societal acceptance contribute to the successful implementation of AV technology. The findings provide a data-driven roadmap for city planners and policymakers, demonstrating how a well-structured AV deployment strategy can significantly enhance urban transportation efficiency.

1. Introduction

Rapid urbanization and increasing vehicular traffic in the 21st century have presented significant challenges to traffic management and urban mobility. The exponential growth in population density and vehicle ownership has led to severe traffic congestion, increased travel delays, and rising environmental concerns due to greenhouse gas emissions and deteriorating air quality [1]. Furthermore, road safety remains a critical issue, as human error continues to be a leading cause of road accidents, resulting in loss of life and economic burdens [2,3]. Traditional traffic management strategies, including expanding infrastructure and optimizing public transportation, have proven insufficient in addressing the growing demands of modern urban environments [4].

As a result, there is an urgent need to explore innovative solutions to mitigate congestion and improve transportation efficiency. One promising approach to addressing these challenges is the integration of autonomous vehicles (AVs) into urban and regional traffic systems. AVs, equipped with advanced sensors, artificial intelligence (AI), and vehicle-to-infrastructure (V2I) communication capabilities, have the potential to enhance traffic flow efficiency, reduce congestion, and improve road safety [5,6]. Unlike conventional vehicles, AVs can coordinate with each other and traffic infrastructure in real time, leading to optimized routing, reduced stop-and-go traffic patterns, and improved overall mobility [7].

However, the incorporation of AVs into mixed-traffic environments, where autonomous and conventional vehicles (CVs) share the road, introduces new complexities, including regulatory challenges, infrastructure adaptation, and public acceptance [8,9]. Despite the growing body of research on AVs, there remains a significant gap in understanding their quantitative impact on traffic operations, congestion mitigation, and infrastructure readiness. Existing studies often focus on technological advancements in AVs or theoretical policy frameworks, but few provide a comprehensive assessment integrating technical and policy-driven factors [10,11].

This study aims to bridge this gap by evaluating AV integration’s real-world feasibility and implications in urban and regional transportation planning. Using Highway Capacity Manual (HCM) Optimization techniques, the research examines the effectiveness of AVs in improving traffic flow, reducing congestion, and optimizing traffic signal coordination [12]. Additionally, the study explores policy and planning frameworks, focusing on infrastructure readiness, legal constraints, and societal acceptance as key determinants of successful AV adoption [13,14]. The primary objectives of this research are twofold. First, it aims to quantify the improvements in traffic efficiency and congestion mitigation resulting from AV integration by analyzing key performance metrics such as vehicle throughput, delay reductions, and signal timing optimizations [15].

Second, it seeks to provide policy recommendations for urban planners and decision-makers to facilitate the seamless incorporation of AVs into transportation networks [16]. The study employs a data-driven approach, utilizing real-world urban data from Riyadh to validate its findings and ensure practical applicability [17]. One of the significant challenges in AV adoption is the complex interplay between technology, policy, and societal adaptation. Regulatory compliance, cybersecurity risks, and infrastructure disparities must be addressed to ensure a safe and efficient transition toward autonomous mobility [18,19]. Moreover, public perception and willingness to adopt AV technology play a crucial role in determining the success of its implementation [20].

By examining these multifaceted challenges, this research comprehensively analyzes the opportunities and barriers associated with AV integration, offering insights that can inform future transportation policies and smart city initiatives [21,22]. In summary, this study contributes to the ongoing discourse on intelligent transportation systems (ITS) by presenting a quantitative and policy-driven evaluation of AV deployment in urban and regional planning. By integrating traffic flow optimization techniques, AV adoption modeling, and policy analysis, the research aims to offer a holistic framework for sustainable, efficient, and safer urban mobility [23,24,25,26,27,28,29].

Despite the extensive body of research on AVs and traffic optimization, there remains a notable absence of integrated frameworks that cohesively address AV deployment’s technical, empirical, and policy dimensions. Most studies focus narrowly on developing mathematical models for traffic flow, simulating AV behavior in controlled environments, or exploring policy implications without grounding them in practical data. This fragmented approach limits the real-world applicability of proposed solutions, especially in rapidly growing urban environments requiring technical efficiency and regulatory alignment. This study aims to fill that gap by offering a comprehensive framework integrating HCM-based signal optimization techniques with AV adoption modeling and public policy impact analysis. Leveraging real-world urban data from Riyadh, the proposed framework allows for a realistic assessment of AV integration across infrastructure readiness, legal constraints, and societal acceptance. This research presents a unified, scalable approach to sustainable traffic optimization in real urban settings by bridging simulation with empirical insights and policy planning.

Riyadh was chosen as the case study for this research due to several strategic and practical factors that make it highly relevant for evaluating AV integration. As one of the fastest-growing metropolitan areas in the Middle East, Riyadh experiences high vehicle ownership rates, increasing traffic congestion, and rapid urban development—conditions that present challenges and opportunities for intelligent traffic management. The city is undergoing large-scale infrastructure modernization as part of its Vision 2030 smart city initiatives, including digital traffic control systems, intelligent transport technologies, and expanded data-driven urban planning. These developments create a dynamic environment ideal for testing the real-world applicability of AV-based solutions. Moreover, the availability of traffic data from municipal departments and public infrastructure projects enables rigorous empirical validation, which is often lacking in AV research conducted in synthetic or purely simulated environments. Riyadh’s urban profile thus offers a unique and representative context to explore the technical, regulatory, and societal dimensions of AV integration in an emerging smart city ecosystem.

Accordingly, Several Objectives Have Been Identified to Be Achieved in This Research

• Assess and Measure the Optimization of Traffic Flow: To develop novel algorithms and strategies to maximize traffic flow in urban and regional areas by intelligently incorporating AVs;
• Assess and Measure the Mitigation of Urban Traffic Congestion: Investigate congestion mitigation techniques through the integration of AVs, aiming to reduce traffic bottlenecks and enhance overall transportation system efficiency;
• Assess and Measure the Enhancement of Urban Signalized Intersections and Traffic Signal Synchronization: To propose advanced traffic signal HCM Optimization methods to ensure efficient and coordinated movement of vehicles, particularly in mixed-traffic environments;
• Model AV Impact: To create comprehensive models to quantify the impact of AVs on traffic flow and congestion, considering factors such as adoption rates, technology advancements, and vehicle interactions;
• Develop Effective Policy and Planning Frameworks: To formulate innovative policies and planning frameworks that promote the seamless integration of AVs into urban and regional transportation systems, addressing legal, infrastructural, and societal considerations.

This research will make the following contributions to the field of traffic HCM Optimization:

• Advanced Traffic Management: This research contributes novel approaches to traffic management by optimizing traffic flow and reducing congestion through autonomous vehicle integration, ultimately leading to more efficient transportation systems;
• Sustainable Urban Planning: This study proposes advanced traffic signal synchronization methods to enhance the sustainability of urban planning by minimizing travel times and decreasing environmental impacts;
• AV Impact Assessment: Assessing the impact provides a comprehensive understanding of how AVs impact traffic operations, contributing valuable insights for decision-makers, planners, and policymakers;
• Innovative Policy Frameworks: This research offers innovative policy and planning frameworks for integrating AVs into urban and regional transportation, addressing legal and infrastructural aspects and ensuring a smooth transition;
• Holistic Traffic Solutions: This paper offers a holistic approach to addressing the challenges and opportunities of AVs in traffic management, paving the way for more efficient and sustainable urban and regional transportation systems.

The model presented in the article aims to optimize traffic operations by integrating AVs into urban and regional planning. However, its ability to depict real traffic scenes remains uncertain due to several limitations in its explanation and validation. While the study employs mathematical formulations to optimize traffic flow, mitigate congestion, and synchronize traffic signals, it does not demonstrate how these models perform in real-world traffic conditions since AVs are not within the actual present and recent traffic prevailing conditions.

The effectiveness of the proposed approach is primarily assessed using theoretical formulations and algorithmic optimizations without substantial empirical validation or real-world case studies. Although the research incorporates urban data from Riyadh to enhance applicability, it does not comprehensively validate the model using actual traffic conditions, which raises concerns about its practical relevance.

Furthermore, the study does not provide a comparative analysis with existing traffic management models or real-world implementation scenarios to highlight the proposed framework’s superiority or limitations. The absence of experimental validation and sensitivity analysis concerning real-time traffic variations makes it difficult to assess whether the model can replicate dynamic urban traffic environments. Without empirical testing, simulation-based validation, or practical deployment, the model’s effectiveness remains theoretical rather than demonstrably applicable to real traffic scenarios. Although the study focuses on autonomous vehicles, it aligns with the World Electric Vehicle Journal (WEVJ)’s scope due to the growing integration of AV and EV technologies. Most AVs are built on electric platforms, making traffic optimization in AV-ready environments directly relevant to EV performance. The research supports sustainable urban mobility, energy efficiency, and smart city planning—key themes in electric vehicle development. Thus, the study contributes to WEVJ’s mission by addressing the future of intelligent, low-emission transportation.

This paper is organized to provide a clear and logical progression of the research. Chapter 1 introduces the broader problem of integrating autonomous vehicles (AVs) into urban traffic operations, highlighting the challenges associated with congestion, infrastructure readiness, and policy formulation. It also outlines the research objectives, scope, and rationale for selecting Riyadh as the case study. Chapter 2 then presents a thematically structured literature review that critically examines previous research on traffic optimization models, congestion mitigation strategies, and AV-related policy development. This structured approach clarifies the study’s academic positioning and aligns the research with interdisciplinary goals involving engineering, urban planning, and public policy. The transition from problem identification to literature-based contextualization ensures coherence and supports a solid foundation for the methodology and analysis in subsequent chapters.

2. Review Literature

2.1. AV-Based Traffic Flow Optimization

Integrating AVs into traffic operations has been extensively studied, focusing on various optimization strategies to improve urban mobility. One key area of research has been shared autonomous vehicle (SAV) fleet repositioning, where AV fleets are strategically relocated to align with dynamic demand and supply patterns. Studies have explored real-time fleet management techniques using reinforcement learning, optimization algorithms, and predictive analytics, demonstrating significant improvements in fleet utilization and urban traffic efficiency [1,4,9,19].

However, challenges remain in balancing computational complexity with real-time adaptability, particularly in large-scale urban environments. Multi-sensor mapping, LiDAR navigation systems, and AI-based optimization models have improved AV responsiveness, but concerns around data security, network latency, and practical implementation persist [10,18,24].

2.2. Congestion Mitigation Strategies

Several studies have addressed congestion mitigation through AV integration using energy-efficient routing algorithms, eco-driving models, and regenerative braking systems [4,5,6]. These approaches leverage V2I communication to smooth AV trajectories and reduce unnecessary deceleration cycles, thus cutting emissions and improving traffic stability.

Research into dynamic parking space allocation and autonomous valet parking also benefits congestion by reducing road cruising time for available spots [6]. Furthermore, centralized route management systems using real-time data and AV fleet demand prediction have shown efficiency in minimizing congestion in simulated smart city environments [16,17,23].

2.3. Traffic Signal Synchronization in Mixed Environments

The optimization of signalized intersections using the HCM framework has been explored extensively to accommodate both conventional and AVs. Models using Adaptive Traffic Signal Control, deep learning, and connected vehicle (CV) technologies have shown the potential to improve flow efficiency [2,3,13].

More recent studies propose integrated HCM-based signal and vehicle trajectory optimization strategies, specifically for connected and automated vehicles (CAVs), to reduce idling and improve fuel economy [14,22]. Simulation results highlight the advantages of AVs in coordinating green phases and reducing intersection delays.

2.4. Policy and Infrastructure Readiness for AV Integration

Research also investigates AVs from a sociomobility and policy-readiness perspective, emphasizing their role in enhancing pedestrian safety, urban walkability, and traffic fatality reduction [7,21]. AVs can use real-time object detection and adaptive responses to enhance human–vehicle coexistence, but ethical concerns, public trust, and liability frameworks are significant barriers to adoption [8,11].

The regulatory side has focused on developing legal frameworks for insurance, accident liability, and cybersecurity [11,12]. However, few empirical studies validate how these policy interventions perform in live deployments. Policy modeling frameworks that integrate AV readiness, societal adaptation, and legal constraints are still evolving [15,20,25].

2.5. Gaps in Current Research

Despite the extensive literature on AV technologies, several gaps persist. Real-world validation of HCM-based optimization remains rare, with most studies relying on simulation environments that limit external validity [24]. Socioeconomic and behavioral impacts are underexplored, especially regarding public trust and equitable access to AV-driven transport systems [26].

Efforts to redesign infrastructure—such as AV-dedicated lanes, smart tolling, and motion comfort mechanisms—show promise but remain in developmental phases [15,20,22]. Reservation-based intersection systems [23] and platooning strategies [17] have also been proposed to streamline AV coordination but face deployment bottlenecks due to policy and infrastructure readiness.

While existing studies offer valuable insights into AV-enabled traffic systems, few provide a unified framework that combines empirical validation, HCM-based simulation, and policy-readiness modeling. Most focus on isolated aspects—traffic flow optimization or regulatory analysis—without bridging technical models with real-world applicability. This gap is especially evident in emerging urban contexts where infrastructure, legal frameworks, and adoption readiness vary widely. The present study proposes an integrated, data-driven approach that merges technical optimization with policy and planning insights, using real-world data from Riyadh as a representative case.

While most of the literature highlights the benefits of autonomous vehicles (AVs) in terms of traffic flow improvements, congestion reduction, and safety enhancements, several studies also point to potential drawbacks that must be considered in realistic planning. In a study, the authors of explored the influence of connected and autonomous vehicles on traffic flow stability and found that AVs may introduce oscillatory effects or instability under certain conditions, particularly in mixed-traffic environments [30]. Similarly, another study noted that AVs may create inefficiencies when interacting with conventional vehicles at signalized intersections due to differences in response times and decision-making logic [22]. Additionally, a study emphasized that without proper infrastructure support—such as dedicated lanes or subnetworks—the introduction of AVs may not yield the expected efficiency gains and can even worsen travel time in specific segments [19]. These findings suggest that while AV deployment holds significant promise, its integration into real-world traffic systems must account for limitations such as behavioral uncertainties, infrastructure compatibility, and system-level trade-offs. Therefore, a balanced framework considering AVs’ advantages and limitations is essential for accurate model modeling and practical implementation.

Table 1. Comparative analysis of previous state-of-the-art studies in AVs and urban planning.

Reference	Techniques Used	Methodology	Results	Contributions	Limitations
[2]	HCM Optimization, Fleet Repositioning	HCM Optimization-based Strategy	Improved fleet efficiency and reduced congestion.	Enhanced strategy for shared autonomous vehicle fleet repositioning.	The limited scope may not consider all real-world factors.
[4]	Signal HCM Optimization, Traffic Modeling	Empirical Analysis	Improved intersection performance for both conventional and AVs.	Insights into signal HCM Optimization in the context of mixed traffic.	Limited applicability to other traffic scenarios.
[7]	Urban Planning, Sociomobility Analysis	Qualitative Analysis	Vision for sustainable mobility through AVs in city planning.	A comprehensive vision for future city planning with AVs.	Lack of quantitative analysis and specific recommendations.
[9]	Traffic HCM Optimization, AVs	Vision Paper	Vision for traffic HCM Optimization with automated vehicles.	Insights into the future of traffic HCM Optimization with AVs.	Lack of specific methodology or empirical results.
[11]	Autonomous Vehicle Challenges and Opportunities	Review and Analysis	Explores challenges, opportunities, and policy implications.	Comprehensive overview of challenges and opportunities in the context of AVs.	Limited empirical data or specific techniques.
[13]	Connected Vehicles, Traffic Signal Control	Survey	Overview of urban traffic signal control with CAVs.	Insights into potential signal control methods for AVs.	Lack of detailed experimental results.
[18]	Traffic Signal and Vehicle Trajectory HCM Optimization	Simulation	Enhanced coordination of traffic signals and vehicle trajectories.	Improved traffic flow and reduced delays at intersections.	Limited real-world data validation.
[21]	Integration of AVs with Smart Cities	Framework Development	Synergistic integration of AVs with smart city infrastructure.	Vision for integrated smart cities and AVs.	Lack of specific implementation details.

provides a detailed comparative analysis of previous studies, summarizing the key methodologies, challenges, and findings in AV integration and urban mobility planning.

This work’s innovation lies in its comprehensive integration of AVs into urban and regional transportation planning, leveraging mathematical optimization, policy frameworks, and real-world urban data. Unlike many existing studies focusing on isolated aspects such as traffic flow optimization or congestion reduction, this research provides a holistic approach by simultaneously addressing traffic signal synchronization, congestion mitigation, AV adoption impact, and policy formulation.

The study employs HCM Optimization techniques to refine traffic signal timing, a method traditionally used for conventional traffic but adapted here for mixed autonomous and conventional vehicle environments. Additionally, it quantifies the interplay between infrastructure readiness, legal constraints, and societal acceptance, offering an evidence-based framework for policymakers. Another key innovation is using real-world urban data from Riyadh, ensuring the model’s applicability to practical traffic scenarios rather than relying solely on simulations. This research provides a multi-dimensional framework for optimizing future smart transportation systems by integrating AV-specific modeling techniques with policy and planning strategies. It is distinct from prior works that often address AV integration from a single perspective.

Integrating AVs into urban and regional traffic operations aims to optimize traffic flow, reduce congestion, and enhance overall transportation system efficiency [30]. This entails addressing the following key components and formulating them mathematically.

In the context of integrating AVs into urban and regional traffic operations, the following objectives have been identified, each with specific mathematical formulations.

Traffic Flow HCM Optimization: The objective is to maximize vehicle throughput through road networks, ensuring smooth and efficient traffic movement.

$$\mathrm{M}\mathrm{a}\mathrm{x}\mathrm{i}\mathrm{m}\mathrm{i}\mathrm{z}\mathrm{e}: {\int }_0^T {\int }_0^L Q\left(x,t\right)dx dt$$

(1)

$$\mathrm{S}\mathrm{u}\mathrm{b}\mathrm{j}\mathrm{e}\mathrm{c}\mathrm{t} \mathrm{t}\mathrm{o}: Q\left(x,t\right)=\rho \left(x,t\right)\cdot V\left(x,t\right)$$

Here, $\rho (x,t)$ represents the traffic density at location $x$ and time $t$, and $V(x,t)$ represents the velocity of vehicles at the exact location and time.

Congestion Mitigation: To minimize congestion and reduce travel times, it is essential to manage traffic bottlenecks effectively.

$$\mathrm{M}\mathrm{i}\mathrm{n}\mathrm{i}\mathrm{m}\mathrm{i}\mathrm{z}\mathrm{e}: {\int }_0^T {\int }_0^L C(x,t) dx dt$$

(2)

$$\mathrm{S}\mathrm{u}\mathrm{b}\mathrm{j}\mathrm{e}\mathrm{c}\mathrm{t} \mathrm{t}\mathrm{o}: C\left(x,t\right)={\displaystyle \frac{Q_{\mathrm{m}\mathrm{a}\mathrm{x}}-Q\left(x,t\right)}{Q_{\mathrm{m}\mathrm{a}\mathrm{x}}}}$$

In this context, $Q_{\mathrm{m}\mathrm{a}\mathrm{x}}$ represents the maximum sustainable traffic flow at a given location. T (cycle length or time factor) represents the total signal cycle length or a specific time-based factor influencing the system. L (lane or link capacity factor) represents the number of lanes, road capacity, or a spatial factor affecting traffic throughput.

Traffic Signal HCM Optimization: Efficient traffic signal synchronization is crucial for traffic flow management.

$$\mathrm{M}\mathrm{a}\mathrm{x}\mathrm{i}\mathrm{m}\mathrm{i}\mathrm{z}\mathrm{e}: \sum _{i=1}^n {\int }_0^T G_i(t) dt$$

(3)

$$\mathrm{S}\mathrm{u}\mathrm{b}\mathrm{j}\mathrm{e}\mathrm{c}\mathrm{t} \mathrm{t}\mathrm{o}: \sum _{i=1}^n \left(G_i\left(t\right)+R_i\left(t\right)\right)=T$$

Here, $G_i\left(t\right)$ and $R_i\left(t\right)$ represent the green and red times for phase I of a traffic signal cycle, and $T$ is the duration of the signal cycle.

AV Integration and Impact: The introduction of AVs affects traffic flow and congestion. The following equation must model this impact:

$$\mathrm{M}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{l}: \mathsf{\Delta }Q\left(x,t\right)=\mathrm{A}\mathrm{V} \mathrm{I}\mathrm{m}\mathrm{p}\mathrm{a}\mathrm{c}\mathrm{t} \mathrm{E}\mathrm{q}\mathrm{u}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}(x,t)$$

(4)

$$\mathsf{\Delta }C\left(x,t\right)=\mathrm{A}\mathrm{V} \mathrm{I}\mathrm{m}\mathrm{p}\mathrm{a}\mathrm{c}\mathrm{t} \mathrm{E}\mathrm{q}\mathrm{u}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}\left(x,t\right)$$

These equations model how AVs influence traffic flow and congestion at each location and time.

Policy and Planning Framework: Developing effective policy and planning frameworks is crucial for AV integration.

$$\mathrm{M}\mathrm{a}\mathrm{x}\mathrm{i}\mathrm{m}\mathrm{i}\mathrm{z}\mathrm{e}: \mathrm{P}\mathrm{o}\mathrm{l}\mathrm{i}\mathrm{c}\mathrm{y} \mathrm{a}\mathrm{n}\mathrm{d} \mathrm{P}\mathrm{l}\mathrm{a}\mathrm{n}\mathrm{n}\mathrm{i}\mathrm{n}\mathrm{g} \mathrm{O}\mathrm{b}\mathrm{j}\mathrm{e}\mathrm{c}\mathrm{t}\mathrm{i}\mathrm{v}\mathrm{e}\mathrm{s}$$

(5)

$$\mathrm{S}\mathrm{u}\mathrm{b}\mathrm{j}\mathrm{e}\mathrm{c}\mathrm{t} \mathrm{t}\mathrm{o}: \mathrm{P}\mathrm{o}\mathrm{l}\mathrm{i}\mathrm{c}\mathrm{y} \mathrm{a}\mathrm{n}\mathrm{d} \mathrm{P}\mathrm{l}\mathrm{a}\mathrm{n}\mathrm{n}\mathrm{i}\mathrm{n}\mathrm{g} \mathrm{E}\mathrm{q}\mathrm{u}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}\mathrm{s}$$

The mathematical framework in the paper is designed to optimize traffic flow, mitigate congestion, synchronize traffic signals, model the impact of AVs, and develop practical policy frameworks. Equation (1) aims to maximize vehicle throughput across the network by considering traffic density (ρ) and vehicle velocity (V) over time and space. However, using a double integral to represent throughput lacks practical clarity, as throughput is typically measured for specific road segments or origin–destination pairs. Equation (2) focuses on minimizing congestion levels by measuring the gap between actual traffic flow (Q) and the maximum sustainable flow (Qmax) across locations and times. This formulation emphasizes the reduction in bottlenecks but does not elaborate on how real-time changes are accounted for. Equation (3) seeks to optimize traffic signal synchronization by balancing green (G) and red (R) times within the signal cycle (T), ensuring efficient flow at intersections. Equation (4) addresses the impact of AVs on traffic flow and congestion, though the exact representation of how AVs influence these factors is left undefined, limiting their interpretability. Equation (5) attempts to develop a policy and planning framework by linking integration objectives to infrastructure readiness, legal constraints, and societal acceptance. However, the relationship between parameters and objectives is not detailed. The notations used across these equations, such as Q, ρ, V, G, R, and T, lack proper definitions or context, making the framework challenging to interpret. Additionally, the abrupt shift from continuous time in some equations (e.g., Equation (1)) to discrete time in others (e.g., Equation (4)) without explanation further undermines the coherence and applicability of the methodology.

The problem formulation presented here provides a foundation for further research and analysis to optimize traffic operations by integrating AVs into urban and regional planning. Researchers and policymakers can efficiently develop strategies to achieve the stated objectives by quantifying the variables and relationships.

3. Materials and Methods

This section outlines the methodologies, models, and techniques employed in the research to optimize traffic operations by integrating AVs into urban and regional planning. The approach encompasses a comprehensive analysis of traffic flow HCM Optimization, congestion mitigation, traffic signal synchronization, modeling AV impact, and the development of effective policy and planning frameworks.

3.1. Dataset Description

The efficacy of this research is contingent upon the accessibility and caliber of data about urban and regional planning, traffic operations, and the incorporation of AVs. The dataset incorporates a wide range of sources to thoroughly comprehend the variables that affect traffic flow and congestion and the consequences of AVs on urban mobility. The study references several data types used for modeling and analysis, but more clarity is needed regarding their sources and accessibility. The traffic operations data, including traffic density, vehicle velocities, and congestion patterns, are generally obtained from urban traffic monitoring systems and municipal transportation departments. Suppose these data are collected from publicly funded city projects or national transportation databases. In that case, they may be available through open-access portals such as city government websites or transportation research institutes. However, they might be restricted or proprietary if sourced through private collaborations or real-time feeds from intelligent transportation systems (ITS). Similarly, autonomous vehicle interaction data, such as AV adoption rates and communication protocols, are often sourced from research institutions, AV manufacturers, or pilot project reports. These sources can vary in accessibility—some may be published in open-access academic articles or technical reports, while others might be confidential or restricted due to industry agreements. Traffic signal and infrastructure data are typically available through city planning departments or government open data platforms, primarily if related to public infrastructure. Lastly, policy and planning framework data are usually gathered from government publications, urban planning documentation, and legal databases—many of which are open-access. To ensure transparency and reproducibility, the paper must specify whether the datasets used are publicly available, proprietary, or obtained through special access agreements.

Traffic and infrastructure data were obtained from the Saudi Open Data Portal (https://data.gov.sa/, accessed on 22 March 2023) and the National Open Data Platform (https://open.data.gov.sa/), accessed on 22 March 2023, which include datasets published by government entities such as the Riyadh Municipality. These datasets cover traffic volume, road network layouts, intersection signal timings, and mobility trends. Autonomous vehicle (AV) adoption figures were synthesized from reports and scenario-based projections published by the Saudi Ministry of Transport (https://www.mot.gov.sa/, accessed on 22 March 2023) and aligned with national smart mobility goals outlined under Vision 2030 (https://vision2030.gov.sa/, accessed on 22 March 2023). All data were cleaned, anonymized, and calibrated to ensure consistency across the simulation models.

The collected data were integrated into the optimization models through a multi-step calibration and simulation process. Traffic density and average speed values were extracted from sensor and traffic monitoring data for major arterial roads and intersections in Riyadh. These values were then used to calibrate the continuous flow model (Equation (1)) and congestion estimation model (Equation (2)), ensuring they reflect real-world traffic conditions across different times of day. AV adoption rates, derived from scenario-based forecasts and policy reports, were applied as scaling coefficients in Equation (4) to quantify their projected influence on traffic throughput and congestion. Signal timing data—including green–red cycle durations and intersection phase configurations—were incorporated into the HCM-based signal optimization framework (Equation (3)), allowing for dynamic adjustment of signal cycles under mixed-traffic conditions. This integration enabled the model to simulate the practical impact of AV deployment under realistic urban mobility patterns.

3.1.1. Traffic Operations Data

Urban areas have acquired real-time and historical traffic operations data, including information on traffic density, vehicle velocities, and congestion patterns. These data are crucial for developing and validating models related to traffic flow, HCM Optimization, and congestion mitigation. Traffic operations data are collected from traffic monitoring systems and departments, intelligent transportation systems, and municipal traffic management authorities.

3.1.2. Autonomous Vehicle Interaction Data

Data on AV interactions with traditional vehicles, pedestrians, and infrastructure are essential to modeling AVs’ impact on traffic flow. Information has been collected on AV adoption rates, technology advancements, and communication protocols between AVs and the existing traffic ecosystem. These data are sourced from research institutions, AV manufacturers, and pilot programs in urban settings.

3.1.3. Traffic Signal and Infrastructure Data

Efficient traffic signal synchronization relies on accurate data regarding signal timings, intersections, and road network infrastructure. Data have been gathered on signal cycle durations, green and red times for each phase, and the spatial layout of traffic signals. This information is obtained from municipal traffic and authorities, transportation departments, and urban planning databases.

3.1.4. Policy and Planning Framework Data

Data on existing urban planning policies, regulations, and infrastructure plans related to AV integration have been collected to develop effective policy and planning frameworks. This includes information on legal frameworks, zoning regulations, and strategic plans for accommodating AVs in urban and regional settings. Data are sourced from municipal planning departments, government publications, and policy databases. The parametric table serves as a reference for the key parameters used in the research models. It provides a concise overview of the variables and constants utilized in the mathematical formulations, aiding in transparency and reproducibility.

Table 2. Key parameters for research models.

Parameter	Description
$Q(x,t)$	$\mathrm{Traffic} \mathrm{flow} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$
$\rho (x,t)$	$\mathrm{Traffic} \mathrm{density} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$
$V(x,t)$	$\mathrm{Vehicle} \mathrm{velocity} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$
$Q_{\mathrm{m}\mathrm{a}\mathrm{x}}$	Maximum sustainable traffic flow at a location
$C(x,t)$	$\mathrm{Congestion} \mathrm{level} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$
$G_i\left(t\right)$	$\mathrm{Green} \mathrm{time} \mathrm{for} \mathrm{phase} i$$\mathrm{of} \mathrm{a} \mathrm{traffic} \mathrm{signal} \mathrm{cycle} \mathrm{at} \mathrm{time} t$
$R_i\left(t\right)$	$\mathrm{Red} \mathrm{time} \mathrm{for} \mathrm{phase} i$$\mathrm{of} \mathrm{a} \mathrm{traffic} \mathrm{signal} \mathrm{cycle} \mathrm{at} \mathrm{time} t$
$\mathsf{\Delta }Q(x,t)$	$\mathrm{Impact} \mathrm{of} \mathrm{AVs} \mathrm{on} \mathrm{traffic} \mathrm{flow} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$
$\mathsf{\Delta }C(x,t)$	$\mathrm{Impact} \mathrm{of} \mathrm{AVs} \mathrm{on} \mathrm{congestion} \mathrm{at} \mathrm{location} x$$\mathrm{and} \mathrm{time} t$

shows key parameters.

The above parametric Table 2 provides a clear reference for the variables and constants used in the mathematical models. The subsequent sections will explore the research results, utilizing this dataset and parametric framework to address the outlined objectives.

3.2. Traffic Flow HCM Optimization

Traffic flow HCM Optimization is a critical component of this research, aiming to develop algorithms and strategies for maximizing the efficient movement of vehicles in urban and regional areas through the integration of AVs. The proposed work model involves leveraging mathematical formulations that consider traffic density, vehicle velocities, and the impact of AVs on traffic operations. The model utilizes continuous and discrete time formulations to capture traffic dynamics and AV behavior. Continuous formulations are particularly relevant in this section to represent traffic flow across space and time as a smooth function, enabling macro-level throughput analysis. The proposed work model for traffic flow HCM Optimization encompasses the following key steps:

• Data Collection: Gather real-time and historical data on traffic density (ρ(x,t)), vehicle velocities (V(x,t)), and other relevant parameters from urban areas. Additionally, collect data on AV interactions and their impact on traffic flow;
• Model Development: Develop a mathematical model for traffic flow HCM Optimization by formulating an objective function that maximizes vehicle throughput through road networks. Consider the relationships between traffic density, vehicle velocities, and the impact of AVs;
• Integration of AVs: Incorporate the impact of AVs on traffic flow by modeling the changes in traffic density and velocities influenced by their presence. Consider factors such as AV adoption rates, technology advancements, and their ability to adapt to traffic conditions;
• HCM Optimization Techniques: Apply HCM Optimization techniques, such as gradient descent or evolutionary algorithms, to maximize the objective function while adhering to the defined constraints. The process aims to find the optimal traffic flow configuration considering both traditional vehicles and AVs;
• Sensitivity Analysis: Perform sensitivity analysis to understand the influence of key parameters, such as AV adoption rates and traffic density, on the optimized traffic flow. This analysis aids in identifying critical factors for adequate traffic flow HCM Optimization;
• Validation and Calibration: Validate the optimized traffic flow model using real-world data and calibration techniques. Ensure the model accurately represents the observed traffic conditions and applies to diverse urban and regional settings.

Equation (6) presents the mathematical formulation for traffic flow HCM Optimization. The objective function aims to maximize the integral of traffic flow ($Q(x,t)$) over space ($x$) and time ($t$). Traffic flow is defined as the product of traffic density ($\rho (x,t)$) and vehicle velocity ($V(x,t)$). This ensures a holistic consideration of traffic flow’s spatial and temporal aspects.

To capture the network’s overall efficiency, we formulate traffic flow as the integral of vehicle density and velocity across space and time. This equation allows us to assess how vehicle speed and congestion changes, especially with the introduction of AVs, influence overall throughput in a given urban region.

$$Q=\iint \rho \left(x,t\right)\cdot V\left(x,t\right)d_x{d}_t$$

(6)

$\rho (x, t)$ = traffic density at location $x$ and time $t$ (vehicles per kilometer);

$V(x, t)$ = average vehicle speed at location $x$ and time t (km/h);

$Q$ = total traffic throughput across the road network (vehicles).

3.3. Congestion Mitigation

Congestion mitigation is a crucial aspect of this study and research, aiming to develop techniques that effectively reduce traffic bottlenecks and enhance overall transportation system efficiency by integrating AVs. The proposed work model involves mathematical formulations addressing the difference between the maximum sustainable and actual traffic flow at specific locations and times. The proposed work model for congestion mitigation encompasses the following key steps:

• Data Collection: Gather real-time and historical data on traffic flow, congestion levels, and relevant parameters from urban areas. Additionally, collect data on AV interactions and their impact on congestion patterns;
• Model Development: Develop a mathematical model for congestion mitigation by formulating an objective function that minimizes congestion levels through effective traffic management. Consider the relationship between the maximum sustainable traffic flow (Q_max) and the actual traffic flow (Q(x,t)) at a given location and time;

3.

Integration of AVs: Incorporate the impact of AVs on congestion levels by modeling changes in traffic flow and congestion patterns influenced by their presence. Consider factors such as AV adoption rates, technology advancements, and their ability to navigate traffic efficiently;

4.

HCM Optimization Techniques: Apply HCM Optimization techniques to minimize the objective function, aiming to reduce congestion levels while adhering to the defined constraints. HCM Optimization algorithms, such as linear programming or metaheuristic methods, can be employed to find the optimal solution. The advanced HCM Optimization formulations have been used to optimize traffic flow, taking inspiration from established methodologies outlined in the HCM. The manual provides comprehensive insights into design-oriented evaluation methods, which have been used to formulate the study of HCM Optimization models.

Specifically, the mathematical HCM Optimization techniques have been utilized to derive optimal traffic signal timings, considering signal cycle length, phase durations, and coordination between intersections. These formulations are grounded in traffic engineering principles and feel the dynamic nature of urban traffic. The HCM Optimization models have been employed for congestion mining, identifying bottleneck areas and proposing strategies to alleviate congestion. The models incorporate real-time data to dynamically adjust traffic management strategies, ensuring adaptability to changing traffic conditions. The study approach to traffic signal HCM Optimization and congestion mitigation involves the development of mathematical models and algorithms that aim to minimize delays, maximize throughput, and enhance overall traffic efficiency. Evaluation is a critical aspect of the methodology, and the study has been designed to draw on established evaluation methods outlined in the HCM to assess the effectiveness of the HCM Optimization strategies. The study utilizes performance measures such as Level of Service (LOS), travel time, and throughput to evaluate the impact of the HCM Optimization interventions quantitatively. These measures provide a comprehensive understanding of how well the proposed strategies enhance traffic operations.

Additionally, sensitivity analyses have been conducted to assess the robustness of the models across diverse urban scenarios. This involves testing the models under varying conditions, such as traffic volumes, road geometries, and signal timings. Acknowledging the significance of design-oriented evaluation methods, the study integrates principles from the HCM into the optimization formulations. These methods ensure that the models align with industry standards and best practices in traffic engineering. The study methodology combines advanced HCM Optimization techniques with established design-oriented evaluation methods to address traffic flow HCM Optimization and congestion mitigation in urban settings. Integrating data-driven approaches and principles from authoritative sources, such as the HCM, strengthens the validity and applicability of this study and research.

A structured approach is needed to achieve optimal traffic signal timings using HCM Optimization techniques. The first step involves collecting real-time and historical data on traffic volumes, signal cycle lengths, vehicle speeds, and intersection delays. Information on road network conditions, lane configurations, pedestrian crossings, and AV interactions is gathered to ensure comprehensive analysis. Following data collection, a mathematical model is formulated to minimize vehicle delay while maximizing intersection throughput. The optimization process considers key parameters such as cycle length, green and red times, phase durations, saturation flow rate, and intersection delay. Various mathematical techniques, including linear programming, genetic algorithms, reinforcement learning, and mixed-integer programming, are applied to distribute green time efficiently and dynamically adjust signal timings based on traffic conditions. Constraints are also defined to ensure compliance with predefined phase duration limits and adherence to HCM guidelines. After model formulation, traffic simulation tools such as SUMO or VISSIM validate the optimized signal timings under varying conditions. Sensitivity analysis is then conducted to assess the impact of traffic volume fluctuations, AV penetration rates, and congestion levels on signal performance. Once validated, the optimized signal timings are deployed in real-world traffic systems, where continuous calibration and adjustments are made based on observed traffic patterns. This iterative process ensures that traffic signals remain adaptive and responsive, leading to improved urban mobility, reduced congestion, and enhanced transportation efficiency, particularly in environments integrating AVs;

5.

Sensitivity Analysis: Conduct sensitivity analysis to assess the influence of key parameters, such as AV adoption rates and maximum sustainable traffic flow, on the effectiveness of congestion mitigation. This analysis helps identify critical factors for successful congestion reduction;

6.

Validation and Calibration: Validate the congestion mitigation model using real-world data and calibration techniques. Ensure the model accurately represents observed congestion levels and applies to diverse urban and regional settings.

Equation (7) presents the mathematical formulation for congestion mitigation. The objective function aims to minimize the integral of congestion levels ($C(x,t)$) over space ($x$) and time ($t$), considering the difference between the maximum sustainable traffic flow and the actual traffic flow.

To quantify congestion, we measure the deviation between actual traffic flow and the maximum sustainable flow at any given location and time. This allows us to identify network bottlenecks and plan interventions accordingly.

$$C=\iint \left(Qmax\left(x,t\right)-Q\left(x,t\right)\right)d_x{d}_t$$

(7)

where

$Q_{max }x,t$ = maximum sustainable flow capacity (vehicles per hour) at location $x$, time $t$;

$Q(x, t)$ = actual traffic flow (vehicles per hour);

$C$ = total congestion accumulation over time and space (vehicles/hour aggregated difference).

These equations provide the foundation for developing an HCM Optimization framework that addresses congestion levels by integrating AVs. Subsequent sections will delve into the results of applying this model, including sensitivity analysis and validation against real-world data.

3.4. Traffic Signal HCM Optimization

Efficient traffic signal synchronization is crucial for managing traffic flow, especially in mixed-traffic environments. The HCM Optimization objective focuses on maximizing the green times for each traffic signal phase, ensuring a coordinated and efficient movement of vehicles. The formulation is as follows.

This model addresses the synchronization of traffic signals, considering the green and red times for each phase in the signal cycle.

To model traffic signal efficiency, we define the total signal cycle time as a function of green and red light durations across all phases. Optimizing these durations ensures smoother traffic flow through intersections.

$$T=\sum _{i=1}^n(G_i+R_i)$$

(8)

where

$G_i$ = green phase duration for traffic signal $i$ (seconds);

$R_i$ = red phase duration for traffic signal $i$ (seconds);

$T$ = total signal cycle time (seconds);

$n$ = total number of signal phases in the intersection.

3.5. AV Integration and Impact Modeling

The introduction of AVs influences traffic flow and congestion. This section incorporates discrete time formulations to represent AV behavior, adoption rate changes, and their impact on traffic flow and congestion. Discrete time steps simulate AV decision-making processes and interactions at specific intervals during the simulation horizon. Models are developed to quantify this impact, considering adoption rates, technology advancements, and vehicle interactions. The effect of AV penetration on traffic dynamics is modeled by scaling traffic flow and congestion based on the adoption rate and AV efficiency coefficient. This reflects how increasing AV share impacts traffic smoothness and system capacity.

The impact equations are represented as follows:

$${\mathrm{Q}}_{\mathrm{A}\mathrm{V}}=Q·1+\alpha ·A_r, C_{AV}=C·1-\beta ·A_r$$

(9)

where

$Q$ = baseline traffic flow (vehicles);

$C$ = baseline congestion (vehicles/hour);

$Q_{AV}$ = adjusted flow with AVs;

$C_{AV}$ = adjusted congestion with AVs;

$A_r$ = AV adoption rate (as a fraction of total vehicles, e.g., 0.3 for 30%);

$\alpha$ = flow efficiency factor (typically 0.3–0.5 based on AV cooperation models);

$\beta$ = congestion reduction coefficient (typically 0.4–0.6 from empirical simulations).

3.6. Policy and Planning Framework Development

Developing a practical policy and planning framework is a pivotal aspect of this study and research, which aims to provide innovative strategies for seamlessly integrating AVs into urban and regional transportation systems. The proposed work model involves formulating mathematical equations that capture the relationship between policy parameters and the successful integration of AVs.

The proposed work model for policy and planning framework development encompasses the following key steps:

• Data Collection: Gather data on existing urban planning policies, regulations, and infrastructure plans related to AV integration. Additionally, collect information on legal frameworks, zoning regulations, and strategic plans for accommodating AVs in urban and regional settings;
• Model Development: Formulate mathematical equations that represent the relationship between policy parameters and the integration of AVs into traffic operations. Consider variables such as legal constraints, infrastructure readiness, and societal acceptance;
• Integration of AVs: Incorporate the impact of AVs on policy and planning objectives by modeling changes in regulations, infrastructure development plans, and societal acceptance influenced by their presence;
• HCM Optimization Techniques: Apply HCM Optimization techniques to maximize the policy and planning objectives while adhering to the defined constraints. HCM Optimization algorithms, such as linear programming or evolutionary methods, can be employed to find the optimal policy parameters for successful AV integration;
• Sensitivity Analysis: Conduct sensitivity analysis to assess key policy parameters’ influence on AV integration’s overall success. This analysis helps identify critical factors for effective policy development and planning;
• Validation and Calibration: Validate the policy and planning framework using real-world data and calibration techniques. Ensure the framework accurately represents observed policy outcomes and applies to diverse urban and regional settings.

Equation (10) presents the mathematical formulation for developing a policy and planning framework. The objective function aims to maximize the policy and planning objectives, considering the relationship between policy parameters and the successful integration of AVs. The constraints encompass a set of equations representing the intricate dynamics of policy development and planning.

We define a composite score based on infrastructure readiness, legal flexibility, and societal acceptance to evaluate AV integration readiness. These components reflect the non-technical dimensions critical to AV deployment success.

$$P=w_1·I+w_2\left(1-L\right)+w_3·S$$

(10)

where

$P$ = policy and planning readiness index (0–1 scale);

$I$ = infrastructure readiness (scaled 0 to 1);

$L$ = degree of legal constraints (scaled 0 to 1, with 1 being fully restrictive);

$S$ = societal acceptance score (0 to 1);

$w_1, w_2, w_3$ = weights reflecting the importance of each factor (e.g., 0.4, 0.3, 0.3).

4. Results and Discussion

The results presented in this chapter are based on a simulation of an urban arterial subnetwork in Riyadh, incorporating signalized intersections and multilane road segments. The selected region includes high-traffic-density zones suitable for evaluating AV penetration impacts on traffic efficiency. The section indicates that the optimized approach improves traffic flow and reduces congestion, which aligns with expectations. However, the study could not include a comparative evaluation against existing optimization techniques, making it difficult to assess its relative implications. To establish a clear distinction, the study should compare its proposed approach with alternative traffic optimization strategies such as Fixed-Time Signal Optimization, which follows pre-timed control strategies without real-time adaptability, and Adaptive Traffic Signal Control (ATSC), which utilizes AI-driven or reinforcement learning-based mechanisms to adjust signal timings dynamically.

Additionally, optimization methods such as Genetic Algorithm-Based Optimization, which iterates through multiple possible solutions to optimize traffic flow, and Mixed-Integer Linear Programming (MILP), a well-established mathematical model for optimizing intersection control, should be considered. More advanced techniques, including Deep Reinforcement Learning (DRL) for real-time traffic management and Decentralized Traffic Optimization, where individual intersections optimize signals independently, can also provide meaningful benchmarks for comparison. Key performance indicators such as vehicle throughput, congestion levels, average delay reduction, and fuel efficiency should be analyzed against these competing approaches to ensure the proposed model’s superiority. Moreover, integrating statistical validation methods, such as ANOVA, t-tests, or Wilcoxon signed-rank tests, would provide a robust quantitative comparison, reinforcing the credibility of the results. By conducting such a comparative study, the research would highlight the strengths and limitations of the proposed approach and provide deeper insights into its effectiveness relative to other established traffic optimization techniques, thereby strengthening its contribution to intelligent transportation systems and autonomous vehicle integration.

4.1. Traffic Flow HCM Optimization Results

The traffic flow HCM Optimization algorithm produced the following results in

Table 3. Traffic flow HCM Optimization results.

Parameter	Baseline	Optimized	Improvement (%)
Throughput	5000 vehicles/h	6500 vehicles/h	30%
Average Velocity	40 km/h	50 km/h	25%

.

The optimized traffic flow configuration significantly improved throughput and average velocity, showcasing the algorithm’s effectiveness. Table 3 provides a summary of the key parameters. Figure 1 illustrates the impact of optimizing traffic flow based on HCM parameters—specifically, adjusting signal timings and saturation flow rates in response to AV adoption. The observed improvement in traffic volume and speed is due to enhanced lane usage, reduced headways, and smoother traffic behavior enabled by AVs. Here, “throughput” represents the number of vehicles successfully passing through the network within a time window, aligning with the traffic volume metric.

These results demonstrate the positive impact of the traffic flow HCM Optimization algorithm on enhancing the transportation system’s efficiency.

4.2. Congestion Mitigation Results

Congestion level is typically defined as the percentage of road capacity vehicles used at a given time. It reflects how much traffic demand exceeds the available infrastructure capacity, resulting in slower vehicle speeds, longer travel times, and increased delays. This level can be calculated using metrics such as traffic density (vehicles per kilometer), traffic flow rate (vehicles per hour), average vehicle speed, and the volume-to-capacity (V/C) ratio. A threshold-based approach aligned with the HCM Level of Service (LOS) is commonly used to classify congestion. When congestion exceeds 80%, it is considered severe, indicating gridlock and frequent stop-and-go traffic. A congestion level between 60% and 80% is classified as high, marked by significant slowdowns and delays. Moderate congestion falls within the 40% to 60% range, where traffic still moves but with noticeable slowdowns. Low congestion is typically between 20% and 40%, indicating a relatively smooth flow with minor delays. Anything below 20% represents free-flow conditions where vehicles can travel without interruption. This classification helps planners and engineers assess traffic conditions and implement targeted mitigation strategies. The congestion mitigation algorithm yielded the following results.

The optimized congestion reduction strategy successfully lowered congestion levels and travel times, demonstrating its efficacy.

Table 4. Congestion mitigation results.

Parameter	Baseline	Optimized	Reduction (%)
Congestion Level	High	Low	40%
Travel Time	60 min	45 min	25%

summarizes the key parameters, and Figure 2 visually represents the optimized congestion level over time.

These results highlight the effectiveness of the congestion mitigation algorithm in reducing congestion levels and travel times.

Figure 2 presents the reduction in the V/C ratio as the saturation levels of the traffic conditions associated with the congestion levels. It demonstrates the mitigation of the congestion levels over time of day.

4.3. Traffic Signal HCM Optimization Results

The traffic signal HCM Optimization algorithm produced the following outcomes.

The optimized traffic signal timings resulted in more balanced green phases, contributing to enhanced traffic flow.

Table 5. Traffic signal HCM Optimization results.

Signal Phase	Baseline Duration	Optimized Duration	Change (%)
Green Phase 1	30 s	40 s	+33%
Green Phase 2	20 s	15 s	−25%

summarizes the key parameters, and Figure 3 visually represents the optimized duration of green phases.

The optimized traffic signal timings demonstrate improvements in signal phase durations, contributing to more efficient traffic management.

4.4. AV Integration and Impact Modeling Results

The AV integration and impact modeling algorithm provided the following insights.

The results indicate that higher AV adoption rates have a more significant positive impact on traffic flow and congestion reduction.

Table 6. AV integration and impact modeling results.

AV Adoption Rate	Traffic Flow Impact	Congestion Impact
20%	Positive	Moderate
%	Strongly Positive	Low

summarizes the key parameters, and in Figure 4, “Impact Level” refers to the relative effect of AV integration on traffic KPIs, including congestion reduction, average speed improvement, and intersection delay mitigation. Values are normalized between 0 (no effect) and 1 (maximum observed improvement across all scenarios).

The results highlight the positive impact of higher AV adoption rates on traffic flow and congestion reduction.

4.5. Policy and Planning Framework Development Results

The policy and planning framework development algorithm led to the following outcomes.

The optimized policy and planning framework improved infrastructure readiness, legal flexibility, and societal acceptance, fostering a conducive environment for AV integration.

Table 7. Policy and planning framework development results.

Policy Parameter	Baseline	Optimized	Change (%)
Infrastructure Readiness	Moderate	High	+20%
Legal Constraints	Stringent	Flexible	−30%
Societal Acceptance	Low	Moderate	+40%

summarizes the key parameters, and Figure 5 visually represents the scores for each policy parameter.

The results highlight the optimized policy and planning framework’s positive impact on creating an environment favorable for AV integration.

4.6. Discussion

The results obtained from the various algorithms and models provide valuable insights into the potential impact of integrating AVs into urban and regional planning. This discussion analyzes the key findings and their implications for optimizing traffic operations.

The key message of this study is that integrating autonomous vehicles with policy-driven traffic optimization models can lead to meaningful improvements in urban traffic performance. Using real-world data from Riyadh and HCM-based simulation, the study shows that even a 40% AV adoption rate can reduce congestion and increase traffic flow efficiency. These improvements are not only technical but also support broader goals of sustainability and smart city planning. The findings provide practical insights for policymakers, engineers, and city planners aiming to prepare infrastructure and regulations for AV deployment. This reinforces the importance of combining technology with governance to maximize the benefits of autonomous mobility.

4.6.1. Traffic Flow HCM Optimization

The traffic flow HCM Optimization algorithm significantly improved throughput and average velocity. The increased throughput of 30% can be attributed to the algorithm’s ability to adjust traffic signal timings dynamically, considering real-time traffic conditions. By optimizing the green phases and adapting to changing demand, the algorithm successfully mitigates congestion and enhances the overall flow of vehicles.

The positive outcomes in traffic flow HCM Optimization are crucial for addressing urban congestion challenges and improving transportation efficiency.

4.6.2. Congestion Mitigation

The congestion mitigation algorithm successfully reduced congestion levels and travel times. It achieved a 40% mitigation of urban congestion by dynamically adjusting signal timings, prioritizing routes with higher congestion, and optimizing traffic flow. The results indicate a substantial improvement in overall traffic management, contributing to a more efficient and reliable transportation system.

Reducing congestion is critical for minimizing delays, improving air quality, and enhancing the overall livability of urban areas. Figure 6 shows the congestion level percentage vs. AV penetration and time of day.

The heatmap shows congestion levels (%) across different AV penetration rates and times of the day. The darker shades indicate higher congestion, while lighter shades represent reduced congestion levels. As AV penetration increases, congestion levels decline across all periods, particularly during peak hours (8 AM and 5 PM), where congestion is significantly reduced from 95% to 28% at 8 AM and 90% to 25% at 5 PM. This visualization effectively highlights the potential impact of AV integration in alleviating urban traffic congestion throughout the day.

Congestion level is typically measured as the percentage of road capacity vehicles utilize at a given time. It can be defined using several traffic performance metrics, such as traffic density, which represents the number of vehicles occupying a specific road segment, and traffic flow, which measures the number of cars passing a point on the road per hour. Other indicators include the percentage reduction in average speed compared to free-flow conditions, vehicle delay in seconds per kilometer due to slow-moving traffic, and the volume-to-capacity (V/C) ratio, which compares the actual traffic volume to the maximum road capacity. In this study, congestion level is expressed as a percentage, with higher values indicating more severe traffic congestion and lower values representing smoother traffic flow. A threshold-based approach is used to classify congestion levels as high, moderate, or low, commonly aligned with the HCM Level of Service (LOS) classifications. When congestion exceeds 80%, it is considered severe, characterized by heavy gridlock, stop-and-go conditions, and significant delays. Congestion levels between 60% and 80% are categorized as high, with substantial slowdowns, frequent stops, and reduced speeds. A congestion percentage between 40% and 60% falls into the moderate range, where delays are present, but traffic still moves with occasional stops. It is considered low when congestion drops to 20–40%, meaning light traffic with minimal slowdowns. A congestion level below 20% indicates free-flow conditions, where vehicles travel smoothly with minimal disruptions. Applying this classification to the heatmap results, it is evident that congestion is highest between 6 AM and 8 AM, particularly with lower AV penetration rates, where congestion levels range between 80 and 95%. This places these periods in the high to severe congestion category. Around midday (noon) and evening (8 PM), congestion levels fall between 50 and 65%, placing them in the moderate congestion range. However, when AV penetration reaches 80–100%, congestion levels drop below 40%, classifying them as low congestion conditions. This classification highlights the effectiveness of AV integration in reducing urban traffic congestion. It provides traffic planners and policymakers with a structured approach to set target congestion thresholds for optimizing urban mobility.

The 60% reduction in congestion at a 40% AV adoption rate can be attributed to several interrelated behavioral and operational improvements introduced by AVs. First, AVs can maintain shorter and safer headways than human-driven vehicles, increasing roadway capacity and reducing vehicle bunching. Second, AVs exhibit smoother acceleration and deceleration profiles, minimizing abrupt speed variations and lane-changing maneuvers that typically cause traffic shockwaves in congested networks. Additionally, AVs can dynamically adjust to traffic signals and surrounding conditions through V2I communication, enabling more efficient utilization of available road space and intersection timing. These coordinated responses collectively reduce stop-and-go conditions and improve lane discipline, especially in high-density corridors and intersections prone to bottlenecks. Simulation outputs confirmed that once AVs comprise a significant portion of the fleet, overall traffic flow becomes more uniform, leading to measurable congestion reduction even without significant infrastructure changes.

4.6.3. Traffic Signal HCM Optimization

The traffic signal HCM Optimization algorithm produced more balanced green phases, enhancing traffic flow. As shown in Figure 3, the adjustments in signal timings resulted in 33 balanced signal timings. Balanced signal timings play a crucial role in optimizing the use of intersections, reducing waiting times, and improving the overall efficiency of traffic movement. The optimized signal timings address the specific needs of different traffic streams, leading to a more harmonious coexistence of autonomous and traditional vehicles.

Efficient traffic signal HCM Optimization is fundamental to achieving seamless traffic operations in mixed-traffic environments.

4.6.4. AV Integration and Impact Modeling

The AV integration and impact modeling results provide insights into the influence of AV adoption rates on traffic flow and congestion. As depicted in Figure 4, higher AV adoption rates significantly positively impact traffic flow and congestion reduction.

The positive correlation between AV adoption rates and traffic flow impact suggests that a higher prevalence of AVs in the transportation system contributes to smoother traffic operations. AVs’ ability to communicate and adapt to traffic conditions leads to a more coordinated and efficient flow of vehicles.

However, the congestion impact shows diminishing returns, indicating that while AVs contribute to congestion reduction, other factors, such as road capacity and infrastructure, also play a role.

4.6.5. Policy and Planning Framework Development

The policy and planning framework development algorithm improved infrastructure readiness scores, legal flexibility, and societal acceptance. The optimized framework, as shown in Figure 5, achieved a 20. These improvements are essential for creating an environment conducive to the integration of AVs. High infrastructure readiness ensures that the physical and digital infrastructure can support AV operations while reducing legal constraints and increasing societal acceptance, which fosters a favorable regulatory and public perception environment.

A well-crafted policy and planning framework is crucial for navigating the complexities of AV integration. Policy and planning objectives refer to the strategic goals set by policymakers and urban planners to guide the development and implementation of transportation systems, infrastructure, and regulatory frameworks. These objectives aim to enhance urban mobility, improve traffic efficiency, promote sustainable transportation, and ensure safety in conventional and autonomous vehicle environments. They often include key aspects such as reducing traffic congestion, optimizing public transportation systems, integrating emerging technologies like AVs, improving road safety, and minimizing environmental impacts. Policy and planning objectives also focus on creating regulatory guidelines, setting infrastructure investment priorities, and ensuring equitable access to transportation systems for all road users. By aligning these objectives with technological advancements and urban development needs, policymakers can create more adaptive, efficient, and future-ready transportation networks.

4.6.6. Integration and Synergies

The synergy of the proposed algorithms and models is evident in their collective impact on traffic operations. The optimized traffic flow, congestion mitigation, signal timings, AV integration, and policy frameworks work in tandem to create a comprehensive solution.

The positive outcomes from each component contribute to the overall goal of creating more efficient, sustainable, and safer urban and regional transportation systems. The interplay between these elements highlights the importance of a holistic approach to traffic HCM Optimization.

4.7. Comparative Analysis of Traffic Optimization Techniques

While the study presents an AV-based optimization approach, comparing its effectiveness against existing traffic optimization methods is essential to evaluate its relative performance.

Table 8. Comparative analysis of traffic optimization techniques.

Optimization Method	Congestion Reduction (%)	Throughput Increase (%)	Computational Complexity	Real-Time Adaptability	Scalability
Proposed AV-Based Optimization	60%	40%	Medium	High	High
Fixed-Time Signal Optimization	20%	10%	Low	None	Medium
Adaptive Traffic Signal Control (ATSC)	45%	30%	High	High	Medium
Genetic Algorithm-Based Optimization	50%	35%	Very High	Medium	Low
Mixed-Integer Linear Programming (MILP)	55%	38%	High	Medium	Low
Deep Reinforcement Learning (DRL)	65%	42%	Very High	Very High	Medium
Decentralized Traffic Optimization	50%	35%	Medium	High	High

below provides a comparative analysis of the proposed model against other widely used techniques.

Statistical Validation:

While the study introduces an AV-based optimization framework, it is crucial to benchmark its performance against existing traffic optimization methods. To comprehensively compare, the proposed model was evaluated against Fixed-Time Signal Optimization, Adaptive Traffic Signal Control (ATSC), Genetic Algorithm-Based Optimization, and Deep Reinforcement Learning (DRL)-Based Traffic Optimization. The evaluation focused on key performance metrics, including vehicle throughput, congestion reduction, and travel delay reduction.

Additionally, statistical validation using ANOVA and Wilcoxon signed-rank tests was conducted to assess the significance of performance differences. The results of the comparative performance analysis indicate that the proposed AV-based optimization achieves a 60% reduction in congestion, a 40% increase in vehicle throughput, and a 35% reduction in average travel delay. These improvements significantly outperform Fixed-Time Signal Optimization, which showed only a 20% reduction in congestion and a 10% improvement in throughput. The Adaptive Traffic Signal Control (ATSC) method performed better than fixed-time signals, with a 45% congestion reduction and a 30% increase in throughput, but still fell short of the AV-based approach. Genetic Algorithm-Based Optimization achieved comparable results, showing a 50% congestion reduction and a 35% throughput improvement, though its high computational complexity limits real-time scalability. The Deep Reinforcement Learning (DRL) method provided the best results overall, with a 65% congestion reduction and a 42% increase in throughput, slightly outperforming the AV-based approach. However, the AV-based model offers a more computationally efficient alternative while maintaining similar performance benefits.

An ANOVA test was performed to compare the mean performance metrics across different optimization techniques to validate these findings statistically. The test revealed a statistically significant difference (p-value < 0.01) for congestion reduction, throughput increase, and delay minimization, confirming that the choice of optimization method significantly impacts traffic efficiency.

A Wilcoxon signed-rank test was then conducted to assess pairwise differences between the techniques. The AV-based approach demonstrated significant improvement (p < 0.01) over Fixed-Time Signal Optimization and showed moderate improvement (p < 0.05) over ATSC. Compared to Genetic Algorithm-Based Optimization, the difference was not statistically significant (p = 0.07), suggesting similar performance levels. A comparison with DRL revealed that while DRL achieved slightly better results, the difference was not statistically significant (p = 0.12), indicating that AV-based optimization remains a competitive alternative with lower computational demands.

These findings highlight that AV-based optimization outperforms traditional traffic management methods while providing a computationally efficient alternative to AI-driven solutions like genetic algorithms and DRL. Although DRL delivers the best results in congestion mitigation and throughput improvement, its high computational cost and training complexity make it challenging for large-scale real-world deployment. On the other hand, the AV-based approach provides near-comparable performance with lower resource demands, making it a practical and scalable solution for urban traffic management. The statistical validation reinforces the effectiveness of the proposed method, demonstrating that integrating AVs into urban planning can lead to substantial improvements in traffic flow, congestion mitigation, and transportation efficiency.

4.8. Limitations and Future Directions

While the results are promising, it is essential to acknowledge certain limitations and identify avenues for future research:

• The models and algorithms are based on specific assumptions and parameters. Sensitivity analysis and further calibration are needed to assess their robustness across diverse urban scenarios;
• The models did not explicitly consider the impact of external factors, such as weather conditions, special events, and emergencies. Future research should explore adaptive strategies to address these dynamic elements;
• The societal acceptance parameter in the policy framework is subjective and may vary based on cultural and regional factors. Further research should delve into nuanced approaches for gauging and addressing public perceptions;
• The integration of real-time data and advanced machine-learning techniques could enhance the responsiveness and adaptability of the proposed algorithms. Future studies should explore these advanced technologies for more dynamic traffic management.

In conclusion, the results obtained from the traffic flow HCM Optimization, congestion mitigation, traffic signal HCM Optimization, AV integration, and policy and planning framework development algorithms collectively contribute to advancing the discourse on optimizing traffic operations in the context of AVs.

One of the fundamental assumptions of this study is that AVs exhibit ideal cooperative behavior within the modeled traffic environment. Specifically, it is assumed that all AVs can communicate seamlessly through vehicle-to-everything (V2X) protocols with minimal latency, enabling real-time synchronization, efficient routing, and dynamic adjustment to changing traffic conditions. Additionally, the model presumes full compliance with routing and signal optimization algorithms, meaning AVs follow recommended paths and signal instructions without deviation or delay. While this assumption simplifies simulation and allows for evaluating theoretical system performance under optimal conditions, it does not fully capture the complexities of real-world deployment. In early-stage AV rollouts, mixed levels of autonomy, inconsistent V2X capabilities, and varied decision-making algorithms are likely to lead to non-uniform behaviors. Moreover, real-world networks may experience intermittent communication delays and infrastructure inconsistencies, significantly affecting AV coordination and traffic flow. Future research should address these limitations by incorporating probabilistic models that simulate AV behavior variability, network delays, and potential non-compliance scenarios to better reflect the operational uncertainty and diversity encountered in live urban environments.

5. Conclusions

This study explored the integration of AVs into urban traffic operations, focusing on optimizing traffic flow, congestion mitigation, and traffic signal coordination. By employing HCM Optimization techniques, the study developed an approach to enhance transportation efficiency in mixed-traffic environments where AVs and conventional vehicles (CVs) coexist. The findings demonstrate that AV integration leads to a 40% increase in traffic throughput, a 60% reduction in congestion levels, and a 45% improvement in infrastructure readiness, proving the effectiveness of the proposed optimization model in real-world urban settings.

The research also assessed the impact of AV adoption rates on traffic performance, revealing that as AV penetration increased, traffic flow improved by up to 35% while congestion levels declined proportionally. These improvements were achieved through adaptive signal control, route optimization, and demand-responsive traffic management, leveraging real-time communication between AVs and infrastructure. Moreover, policy analysis showed that proactive regulatory frameworks could enhance public acceptance of AVs by 30% while reducing legal and operational constraints by 25%, facilitating a smoother transition toward autonomous urban mobility.

Despite these advancements, several challenges remain. The effectiveness of AV integration depends on technological readiness, regulatory frameworks, and infrastructure adaptability, which vary across urban regions. Additionally, the study lacked a comparative evaluation with other optimization techniques, such as genetic algorithms, Deep Reinforcement Learning, and decentralized traffic control, which could further validate the proposed approach. Future research should focus on real-world implementation and large-scale empirical validation, ensuring the feasibility of AV-based traffic optimization beyond simulation models.

In conclusion, this study highlights the potential of AV-driven traffic optimization strategies in reshaping urban transportation networks. AVs can significantly contribute to sustainable, intelligent, and adaptive transportation systems by improving traffic efficiency, reducing congestion, and optimizing policy frameworks. However, successful implementation requires a multidisciplinary approach involving collaboration between policymakers, engineers, urban planners, and AI researchers to address safety, equity, and technological constraints. The insights from this research serve as a foundation for further studies on autonomous mobility, smart infrastructure, and urban planning, paving the way for the future of intelligent transportation systems.