Rapid urbanization and growing mobility demand are reshaping transportation systems, calling for more advanced intelligence and management capabilities. Artificial intelligence (AI) has emerged as a key enabler for enhancing perception, prediction, and decision-making in transportation. This paper presents a systematic review of AI applications across four major transportation domains: road, rail, air, and maritime systems. Rather than exhaustively surveying all published studies, this review adopts a thematic synthesis approach, organizing representative, recent research by major transportation modes and core AI application scenarios, with an emphasis on influential studies published in leading journals and conferences. The review examines representative applications and key functionalities within each domain, highlighting how AI techniques—such as deep learning, graph-based models, reinforcement learning, and emerging foundation models—are adapted to diverse transportation contexts. Furthermore, this paper analyzes key challenges, including data quality and sparsity, interpretability, uncertainty, and cross-domain generalization, and discusses emerging research directions such as foundation models, physics-informed learning, and continual adaptation. By integrating insights from both methodologies and real-world applications, this review provides insights for advancing intelligent, scalable, and resilient transportation systems.

Driven by rapid advancements in electric vertical take-off and landing (eVTOL) technology, urban air mobility (UAM) has attracted unprecedented attention worldwide, with governments, industries, and researchers exploring its potential to revolutionize urban transportation. In this paper, we conduct a comprehensive review of key research problems in UAM to establish a foundational knowledge framework and provide insights for researchers, policymakers, and industry stakeholders. Specifically, we examine UAM-related studies and reports from the perspectives of planning, operations, and management, including topics such as infrastructure development, airspace management, and service optimization. Additionally, the potential societal impact and public acceptance of UAM are explored to provide a balanced view of opportunities and challenges in this emerging field. The application of UAM in several representative scenarios is also analyzed to examine the operational feasibility of integrating this new mobility solution into modern urban transportation networks. Based on our review findings, we identify a series of challenges and open questions that need to be adequately addressed for future UAM commercialization. Finally, the paper concludes with a discussion of potential research directions aimed at designing a more reliable and scalable UAM network.

Recent advances in electric vertical takeoff and landing (eVTOL) aircraft, automation and intelligent transportation technologies are accelerating the emergence of urban air mobility (UAM) as a new low-altitude transport mode. As UAM operations become denser, more heterogeneous and increasingly automated, conflict management becomes essential for maintaining operational safety. However, UAM has not yet established a unified conflict management framework for future operations. This paper develops a cross-modal review framework to examine how mature transport systems can inform UAM conflict management. The review first compares conflict definitions, safety boundaries, and indicators across road, railway, maritime, commercial aviation, and UAM systems. It then reviews representative conflict management problems in mature transport modes and evaluates the transferability of their underlying mechanisms to UAM. The comparison shows that road traffic provides principles for structured corridor organization and local interaction control. Railway systems inform the allocation of constrained network resources over time. Maritime transport contributes encounter classification and responsibility assignment, while commercial aviation supports balancing demand and capacity and coordinating vertiport resources. However, these transfers must be adapted to UAM characteristics, including structured three-dimensional corridor operations, temporal occupation of ground and airspace resources, limited operational buffers, and dense automated multi-aircraft operations. A matrix based on seven criteria further classifies the mechanisms as transferable, conditionally transferable, or not transferable to UAM. These findings provide a structured basis for developing integrated UAM conflict management systems that are both safe and operationally feasible.

Urban air mobility (UAM), as an emerging transportation mode, represents an effective strategy to alleviate ground traffic congestion and is expected to be promoted globally in the coming years. This study focuses on the data-driven optimization of vertiport location. By integrating travel choice modeling with a three-phase multi-objective integer programming (TP-MOIP) model based on K-means clustering analysis, the study provides decision-making support for scientific vertiport network planning. The study combines revealed preference (RP) and stated preference (SP) surveys, employing binomial logistic regression to analyze the probability of individuals choosing UAM, while introducing time value coefficients to identify potential user groups. Utilizing ride-hailing order data, potential vertiport locations were identified through K-means clustering. The developed TP-MOIP model simultaneously optimizes the objectives of demand coverage maximization and cost minimization across three implementation phases. Using Shenzhen as a case study, the feasibility of the proposed approach was validated. The results show that the average selection probability for UAM is 16.7%, with time-sensitive users being a critical demographic. In addition, the TP-MOIP model achieved a demand coverage rate of 88.21%. Sensitivity analysis indicates that the land cost budget has the most pronounced impact on demand coverage. This research establishes both theoretical foundations and practical methodologies for vertiport location optimization, offering substantial implications for advancing UAM development.

The successful deployment of Urban Air Mobility (UAM) depends on the strategic placement of vertiports, which is complicated by inherent uncertainties, particularly weather induced disruptions to low-altitude flight routes. This paper tackles the UAM vertiport location optimization problem, with a focus on the uncertainty arising from adverse weather to aerial route connectivity. We propose a two-stage stochastic programming formulation to tackle this challenge. In this framework, the first-stage decisions involve the strategic selection of vertiport locations from a set of candidate vertiports, while the second-stage decisions manage the flow of vehicles under a multitude of weather scenarios. A significant computational bottleneck in such models arises from the need to enumerate all possible flight routes across all scenarios, leading to a massive number of decision variables and intractable solving time for large-scale instances. The key methodological contribution of this work is the introduction of a data-preprocessing strategy, which identifies and eliminates infeasible routes a priori based on weather-impacted aerial connectivity and operational constraints in each scenario. This preprocessing step results in a substantial reduction of the decision variable space, leading to a more compact and computationally efficient model. We conduct computational studies comparing the proposed preprocessing-augmented model against the traditional exhaustive variable approach. Experimental results demonstrate a superior improvement in solving time while maintaining identical solution quality. Through sensitivity analysis, we further derive critical insights into how varying levels of weather uncertainty and different parameters influence the optimal vertiport configuration and system costs. The study concludes with policy implications for urban planners and UAM operators, highlighting how advanced modeling techniques can improve operational resilience and efficiency.

With the rapid expansion of urban scale, traditional Ground-Based Response Units (GBRUs) face increasing challenges in maintaining efficient response times for traffic incidents, particularly under congestion and spatiotemporal uncertainty. This study develops an application-oriented strategic planning framework for an Unmanned Aerial Vehicle (UAV)-Assisted Traffic Incident Management System (UATIMS). The framework combines data-driven robust facility location with simulation-based operational validation. To represent the heterogeneous attributes of urban traffic incidents, we introduce an Urgency-Importance-Ambiguity (UIA) assessment framework that translates incident severity, network impact, and early-stage information uncertainty into planning-relevant risk categories. Based on this characterization, a weighted structural uncertainty set is constructed and embedded into a min-max robust location model to support capacity allocation under long-tail demand risks. The model incorporates a congestion-aware stability constraint and is reformulated into a tractable Mixed-Integer Linear Programming (MILP) model through strong duality. Using real-world traffic incident data from Hangzhou, China, we evaluate the proposed framework through computational experiments and Discrete Event Simulation (DES). The results show that the Full UIA model provides incremental value over homogeneous and urgency-weighted robust baselines, especially in reducing high-urgency service shortages and tail response risks under resource-constrained conditions. The simulation further indicates that the resulting UAV-assisted layout can achieve high net service coverage and maintain average response times within an operationally acceptable range. These findings suggest that heterogeneous risk representation can complement existing drone-service design models by supporting strategic hangar siting and fleet allocation for traffic incident management.

Urban air mobility (UAM) is emerging as a promising solution to urban traffic congestion, yet its effective deployment hinges on seamless integration with ground transportation systems. With the increasing adoption of battery-powered electric vertical take-off and landing (eVTOL) vehicles in UAM systems, travel choices are no longer governed solely by conventional objective factors such as travel time, but are increasingly shaped by perception-driven range-related constraints. However, these constraints are rarely considered in existing UAM network equilibrium studies. To address these challenges, this paper develops an integrated land-air mobility network equilibrium model that incorporates travelers’ range anxiety and battery anxiety (ILAM-NE-RBA). These behavioral factors capture travelers’ subjective perceptions of path-level energy consumption and flight-stage risks, respectively, and are characterized by continuously distributed perceived weight limits of path weight and flight-stage weight. We further prove that the proposed ILAM-NE-RBA formulation constitutes a convex programming problem and that its Karush-Kuhn-Tucker (KKT) conditions characterize an anxiety-constrained generalized user equilibrium. To solve the model effectively, we develop a sub-demand decomposition-based improved gradient projection algorithm with three-dimensional Pareto (SD-IGP-TDP) guidance, which transforms conventional shortest-path search into a three-dimensional Pareto-optimal path search considering travel time, path weight, and flight-stage weight, thereby ensuring sufficient coverage of paths under dual-anxiety constraints. Meanwhile, sub-demand decomposition is introduced to address the inconsistency of feasible path sets across different anxiety intervals, enabling interval-based flow updates under heterogeneous perception constraints. Numerical results demonstrate that incorporating dual-anxiety mechanisms yields equilibrium flow patterns that differ significantly from those of conventional models; perception-driven constraints discourage travelers from selecting energy-intensive or high-risk paths, thereby inducing flow redistribution across the network. This study provides a unified behavioral perspective on the coupling between traveler route choice and network performance, and offers theoretical insights for the planning and operation of future integrated land-air mobility systems.

Urban air mobility (UAM) demands reliable sensing and communication to ensure safe and efficient electric vertical take-off and landing (eVTOL) operations in complex urban environments. This paper proposes a multitier tower base station (TBS) and tethered unmanned aerial vehicle (TUAV)-assisted integrated sensing and communication (ISAC) framework for the eVTOL approach and landing, where the rigid shapes of eVTOLs are represented by the millimeter wave (mmWave) radar point clouds rather than simplifying them as a single point, which is closer to the real world. Then, an integrated radar–communication fair optimization problem is formulated to jointly maximize radar and channel capacities while satisfying tether, safety, and terminal constraints. To address the randomness of radar point clouds, a point-cloud-aware deep reinforcement learning (PCDRL) method is developed to solve the above optimization problem. The proposed framework extracts radar point clouds features and learns adaptive TUAV 3D trajectory control and dynamic power ratio allocation across multiple eVTOLs. Simulation results demonstrate that PCDRL improves both radar and communication performance, achieving challenging performance among all the benchmarks.

In the development of the low-altitude economic field, unmanned aerial vehicle (UAV) three-dimensional (3D) path planning often suffers from slow convergence and local optima problems. To address these problems, this study established a comprehensive technical framework for path planning that spanned application scenario design to algorithm performance enhancement. A parametric stochastic 3D environment model was first established to simulate real-world uncertainties. Then, a multi-dimensional performance evaluation model integrating weather conditions and terrain types was developed. This model incorporated multiple core flight indicators, including the path length, safety, flight altitude, no-fly zone constraints, and path smoothness. Moreover, the weights of these indicators were dynamically adjusted to make the path planning results more aligned with actual operational needs. Based on this, an adaptive multi-strategy cooperative elk herd optimization (AMCEHO) algorithm with better chaotic ergodicity and optimization balance was proposed. Through the synergy of hybrid chaotic initialization, a dynamic elite pool, and multi-strategy collaborative updating, it not only overcame the population diversity limitation of a single chaotic map and calibrated search directions, but also balanced exploration and exploitation. The hierarchical correlation among the three components significantly enhanced the algorithm’s rapid convergence and global optimization capabilities, solving the key difficulties of traditional algorithms. Experiments were conducted for six benchmark functions and two scenarios (medium and complex obstacles scenarios), comparing the AMCEHO algorithm with several state-of-the-art algorithms. The results demonstrated that among the six benchmark functions, the AMCEHO algorithm achieved optimal values in the 10⁻² to 10⁻⁵ range with minimal standard deviation, significantly enhancing the global optimization capabilities. Compared with other algorithms, the AMCEHO algorithm achieved up to 71.9% fewer iterations and 56.4% lower total path cost, while achieving a maximum 36.7% reduction in overall fitness. This study provides a promising solution for high-quality UAV 3D path planning in low-altitude economic field.

Drone delivery has been widely used in various areas of e-commerce, such as delivering packages, takeaways, etc. For the problem of logistic package delivery in remote rural areas, a drone only delivery system which considers integrating mixed sequences of pick-up and delivery is designed. In this system, the drone range limit, energy consumption constraint, weight constraint, pick-up and delivery mode are comprehensively considered. A three stage planning model is proposed to solve this problem, which is solved by SCIP and Advanced Clark and Wright Saving-Improved and Repaired Crow Search Algorithm (ACWS-IRCSA). In numerical experiments and analyses, the case of Hongergole town, Xilingole prefecture, Abaga county, Inner Mongolia Autonomous Region, China is designed for analysis. The parameters and algorithms are compared and analyzed. The experiments show that adding charging facilities triples the drone’s service radius, significantly improving coverage. Additionally, for reverse logistics with 100% higher pickup demand, energy consumption only rises by ~50%. Extensive studies are conducted based on the characteristics of the problem, such as changes in drone delivery coverage before and after the addition of charging facilities; the impact of reverse logistics services on energy consumption; the influence of cargo weight on the number of paths, charging times and the remaining power before charging.

Decision-makers in contemporary operational settings must navigate uncertainty arising from rapidly shifting contextual factors such as volatile market dynamics and intricate supply-chain interactions. Although distributionally robust optimization offers a principled means of guarding against distributional ambiguity, conventional formulations typically ignore the contextual information that shapes uncertainty in real applications. This paper outlines the emerging framework of Contextual Distributionally Robust Optimization (CDRO), which embeds covariate information into robust decision-making. We cast CDRO as a conditional worst-case optimization problem and organize existing research into two overarching streams: (1) predict-then-robustify, where ambiguity sets are constructed around estimated conditional distributions or moments; and (2) joint contextual robustification, where robustness is imposed on the joint distribution of covariates and uncertain parameters. Illustrative studies in transportation, healthcare, and inventory systems reveal that incorporating contextual information can substantially enhance adaptability and reliability in decision policies. The paper concludes with a discussion of open challenges, including data fidelity, causal confounding, computational scalability, privacy concerns, and model interpretability, that highlight promising directions for future research.

Artificial intelligence (AI) is reshaping driving-behavior research, but its value depends on whether data-driven models can be grounded in experimentally validated behavioral mechanisms. This Comment narrows the discussion to a specific mechanism-to-AI question: how can empirical regularities obtained from controlled traffic experiments be translated into constraints, priors, calibration targets, and validation criteria for AI-enhanced behavioral modeling? We synthesize key experimental mechanisms of longitudinal driving behavior, including concave oscillation growth, critical-velocity regimes, spacing-insensitive adaptation, intrinsic heterogeneity, and mean-reverting stochasticity. We then discuss how these mechanisms can guide foundation-model reasoning, digital-twin calibration, federated behavioral aggregation, and safety- or causality-oriented validation. To make this connection explicit, we propose a Hybrid AI–Experimental Behavioral Stack (HBS), not as a generic software architecture, but as a mechanism-to-implementation roadmap linking representation, scenario, policy, transmission, and validation layers. The discussion also clarifies the limitations of foundation models and large language models, including hallucination, weak physical grounding, real-time reliability, and safety verification. The central argument is that AI-enhanced driving-behavior models should be evaluated not only by predictive accuracy, but also by their consistency with experimentally observed behavioral mechanisms and their ability to support interpretable, verifiable, and transferable mixed-traffic modeling.