Intelligent Transportation System Technologies and Applications: Closing Editorial

1. Introduction

The rapid evolution of urban environments and the increasing complexity of mobility demands necessitate a shift in the paradigm of transportation systems. Intelligent transportation systems (ITSs) have emerged as a pivotal field of research and development, aiming to address critical challenges related to traffic congestion, environmental sustainability, and road safety [1,2]. By leveraging advancements in artificial intelligence, Internet of Things (IoT) connectivity, and big data analytics, ITSs promise to transform traditional infrastructure into adaptive, efficient, and user-centric ecosystems [3].

A core objective within modern ITSs is the seamless integration of connected and automated vehicles (CAVs) into the existing traffic fabric, which includes not only other vehicles but also vulnerable road users [4,5]. Research in this domain is increasingly focused on developing cooperative frameworks that ensure safety and smooth interactions. For instance, significant work has explored coordination models between CAVs and pedestrians to enhance both safety and traffic flow, particularly in complex environments like industrial sites [6]. However, a persistent gap remains in the development of holistic and robust solutions that can dynamically respond to the unpredictable nature of real-world traffic, especially in mixed traffic scenarios where legacy vehicles, CAVs, and pedestrians must coexist [7].

This Special Issue, “Intelligent Transportation System Technologies and Applications,” was conceived to help fill these knowledge gaps. It presents the following 12 articles:

• Systemic Design Strategies for Shaping the Future of Automated Shuttle Buses.
• Review of Traffic Assignment and Future Challenges.
• Controlling Traffic Congestion in a Residential Area via GLOSA Development.
• Stability of Traffic Equilibria in a Day-to-Day Dynamic Model of Route Choice and Adaptive Signal Control.
• Energy-Efficient Internet of Drones Path-Planning Study Using Meta-Heuristic Algorithms.
• Improving Driving Style in Connected Vehicles via Predicting Road Surface, Traffic, and Driving Style.
• Decision System Based on Markov Chains for Sizing the Rebalancing Fleet of Bike Sharing Stations.
• Vehicle Ego-Trajectory Segmentation Using Guidance Cues.
• Traffic Signal Control with State-Optimizing Deep Reinforcement Learning and Fuzzy Logic.
• Prediction of Traffic Volume Based on Deep Learning Model for AADT Correction.
• Applying Topological Information for Routing Commercial Vehicles Around Traffic Congestion.
• Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields.

This Special Issue brings together a collection of innovative studies that present novel methodologies, from advanced algorithmic approaches to systemic design strategies, all aimed at pushing the boundaries of what is possible in modern transportation. The following section provides an overview of the key contributions from the articles featured in this issue.

2. An Overview of Published Articles

Recent advancements in the field of ITSs focus on enhancing the efficiency, safety, and sustainability of urban mobility through approaches that combine artificial intelligence, mathematical modeling, advanced optimization techniques, and systemic design. The articles included in this Special Issue advance intelligent transportation research across multiple domains, reflecting the field’s interdisciplinary nature. The contributions span from algorithmic innovations to systemic integration approaches, collectively addressing key challenges in urban mobility. Several articles analyze both theoretical models and practical implementations of emerging technologies. The articles collectively address these challenges through complementary approaches, which can be broadly categorized into three thematic areas.

2.1. Adaptive Traffic Control and Congestion

A significant research thrust involves developing intelligent systems for traffic management. Several studies analyze theoretical models and practical implementations, including an innovative approach that combines deep reinforcement learning (DRL) and fuzzy logic for adaptive traffic signal control. This method, detailed in “Traffic Signal Control with State-Optimizing Deep Reinforcement Learning and Fuzzy Logic,” dynamically adjusts signal cycles according to real-time traffic conditions to reduce congestion and improve flow stability. Another article also discusses the prediction of traffic volume based on a deep learning model. Complementary research explores topological analysis methods for routing commercial vehicles, enabling congestion avoidance by leveraging road network structures to improve delivery times and reduce bottlenecks. Further advancing this domain, “Stability of Traffic Equilibria in a Day-to-Day Dynamic Model of Route Choice and Adaptive Signal Control” provides theoretical insights into system convergence under combined route choice and signal control strategies.

2.2. Multi-Modal System Optimization and Prediction

This Special Issue also addresses optimization across transportation modes. Energy-efficient path planning for drones in the Internet of Drones (IoD) [8] is examined through comparisons of metaheuristic algorithms (e.g., PSO, ABC, and CIPSO) in “Energy-Efficient Internet of Drones Path-Planning Study Using Meta-Heuristic Algorithms,” showing promise for optimizing consumption while maintaining connectivity. Additionally, a decision system based on Markov chains optimizes bike-sharing fleet rebalancing using historical data from real-world networks. Complementary research also discusses how to predict the traffic volume based on a deep learning model for annual average daily traffic (AADT) correction.

2.3. Risk Assessment and Autonomous Vehicle Technologies

Safety enhancement represents another critical focus, particularly for CAVs. A physics-inspired model based on molecular potential fields has been proposed to quantify driving risks, as presented in “Quantification Method of Driving Risks for Networked Autonomous Vehicles Based on Molecular Potential Fields.” This approach enables intuitive visualization and accurate risk assessment in various traffic scenarios. Further contributing to this domain, a self-supervised learning technique segments vehicle trajectories using visual cues, facilitating the interpretation of automated driving behaviors and anomaly detection.

Beyond technical optimization, the study by Yan et al. [9] adopts a systemic approach to integrating autonomous shuttles into public transport, highlighting through participatory co-design workshops the importance of addressing social, environmental, and organizational dimensions alongside technological considerations. These works align with broader efforts to review foundational methods like traffic assignment, which highlights key challenges for future research [10].

Collectively, the contributions highlight the increasing significance of artificial intelligence, advanced planning methods, and systemic thinking in addressing contemporary urban mobility challenges, providing pathways toward smarter, safer, and more sustainable transportation systems.

3. Conclusions and Future Research Directions

The diverse articles compiled in this Special Issue provide a compelling snapshot of the current state of research in ITSs. They demonstrate a clear trend towards the integration of sophisticated computational intelligence techniques, such as DRL, fuzzy logic, and metaheuristic optimization, with fundamental transportation models to solve complex, real-world problems. The collective findings underscore a multidisciplinary effort to enhance traffic flow efficiency, ensure the safety of automated vehicle operations, optimize multi-modal mobility services, and reduce the environmental footprint of transportation networks.

Looking forward, several promising research avenues emerge from the work presented here. First, the successful integration of ITS technologies must extend beyond technical performance to encompass broader human factors and societal acceptance. Future work should further investigate user trust in automated systems, the ethical implications of algorithmic decision-making, and the development of inclusive design principles that cater to all segments of the population. Second, as the volume and variety of data continue to grow, research into robust, privacy-preserving, and explainable AI models will be crucial for building transparent and trustworthy ITS solutions [11]. Finally, the resilience of transportation networks against disruptions, whether from cyber-attacks, extreme weather events, or other unforeseen circumstances, represents a critical area for future investigation. Developing adaptive and fault-tolerant control systems will be essential for ensuring the continuous and safe operation of next-generation mobility services, particularly as they evolve to manage the complexities of mixed traffic environments [12].

In conclusion, this Special Issue has made a significant contribution to the advancement of ITSs by presenting a range of innovative solutions to current challenges. We are confident that the insights gleaned from these studies will inspire further research and accelerate the transition towards knowledgeable, sustainable, and equitable transportation systems. We extend our sincere gratitude to all the authors, reviewers, and the editorial team of Applied Sciences for their invaluable contributions to this successful endeavor.