Browse Topic: Mobility

Items (1,729)
North American CAV Performance Data StandardWP-0015To be published on 07/22/2026
As the deployment of connected and automated vehicles (CAVs) expands, the need for a consistent, cross-industry approach to performancerelevant CAV data exchange is becoming more pressing. Vehicle developers, infrastructure owners and operators (IOOs), and technology providers generate and consume data that support safety, mobility, and operational efficiency, yet much of the data remains fragmented, inconsistently formatted, and difficult to reuse across systems. To address these gaps, the Society of Automotive Engineers (SAE) and the Canadian Standards Association (CSA) convened a multi-stakeholder workshop on November 3, 2025, with participants representing original equipment manufacturers (OEMs), automated driving system (ADS) developers, state and local agencies, standards bodies, and technology partners. The workshop focused on identifying challenges, clarifying needs, and outlining a path toward a North American CAV Performance Data Standard. Key themes from the workshop included: -A shared data language is needed to support safe and interoperable CAV operations. -The current ecosystem lacks consistent formatting, labeling, and visibility regarding who produces and consumes data. -A “start small, iterate, and scale” approach is needed, beginning with well-defined use cases such as school zones or baseline work zones. -Progress depends on technical harmonization and governance structures that build trust and support sustained coordination. This white paper summarizes the key findings and outlines a practical approach to developing a Version 0.1 base-layer data standard that can support measurable progress in 2026 and beyond.
Nesheli, Mahmood
Against the backdrop of accelerating urbanization and diversifying social demands, aerospace technology has extensively permeated numerous fields such as logistics and transportation, emergency and disaster relief, environmental monitoring, and urban transportation. Its application scope is expanding from traditional reconnaissance and surveillance to complex scenarios like material transportation, manned operations, and precision maintenance. Within this trend, high-payload, vertical take-off and landing (VTOL), and high-safety aircraft have become key equipment for enhancing operational efficiency across multiple sectors. Among these, high-payload ducted fan aircraft, with their high safety, excellent low-speed performance, and outstanding VTOL capability, demonstrate unique advantages in tall building fire suppression, power lines and towers maintenance, and personal flight experiences. This paper first outlines the diversified application prospects of aerospace technology, then focuses on high-payload ducted fan aircraft. It discusses the technical requirements specific to such aircraft in the aforementioned key scenarios and analyzes the critical technical bottlenecks hindering their broader application, along with potential viable solutions.
Lou, BinLi, ZhuoyuanZhang, YuansongZhou, HaoyuLi, ChengLuo, ZiniuTian, ConglingYang, Chengchuan
When quadrotor unmanned aerial vehicles (UAVs) operate in urban low-altitude airspace, especially within complex environments, their sensor perception signals are highly susceptible to blockages, deviations, and the inclusion of high-frequency noise. These factors, in turn, induce nonlinear variations in the UAVs’ flight mechanical properties, giving rise to abnormal flight stability issues such as attitude jitter, altitude fluctuations, and trajectory deviations. To address these challenges, this paper puts forward a method aimed at enhancing the positional accuracy of quadrotor UAVs, which is based on Extended Kalman Filter (EKF) multi-sensor fusion. In conjunction with the redundant configuration of sensors, a proportional-integral controller is specifically designed to allow optical flow sensors to compensate for the speed data generated by inertial sensors. Building on the EKF method, a comprehensive data fusion model is established, encompassing both position and speed states. Leveraging the MATLAB platform, trajectory flight simulations are conducted, utilizing multi-sensor data fused via EKF, with the sensor suite including GPS, IMU, Optical Flow sensors, and Barometers. The simulation results demonstrate that this proposed method can effectively mitigate the adverse impacts of environmental interference and sensor noise on the positional accuracy of quadrotors. By continuously correcting position information and accurately estimating position states, it significantly improves the UAVs’ flight position accuracy. This research outcome lays a robust and theoretically sound foundation for in-depth investigations on critical issues related to general aviation applications, such as the safe and efficient autonomous flight, adaptive and reliable intelligent navigation, and ultra-precise and mission-critical operations of quadrotor UAVs, thereby significantly contributing to the sustained and innovative advancement of the field.
Cui, NanLiu, WenzhiLiu, HanqiWang, JingruiWang, ZhizhongZhi, Haonan
This paper focuses on autonomous drone landing scenarios. Addressing the core requirements of accurate landing site assessment and intuitive visual presentation, it conducts in-depth research on the application of 3D LiDAR (TOF technology) point cloud data. LiDAR captures point cloud data containing 3D coordinates and reflection intensity values. While sparse, non-uniform, and disordered, its high measurement accuracy and strong anti-interference capabilities make it a key sensor for landing terrain perception. Based on a review of recent research results from related teams, this study designed and implemented a comprehensive technical solution: First, raw point cloud data is acquired via the UDP protocol combined with an SDK interface. Preprocessing is then performed using voxel grid filtering (downsampling) and radius filtering (denoising). The assessment area is then divided into a row-by-column grid. A sliding window method is used to calculate the elevation difference, empty grid ratio, flatness, and slope of each grid. Based on these attributes, the grids are classified into six categories: Risk, Warning, Blank, Unknown, No Landing, and Landing. Finally, a grid attribute coloring method and OpenGL 3D rendering are used to generate the visual scene. Through the development of verification programs and moving obstacle experiments, it has been proven that the solution can efficiently process point cloud data and accurately identify safe landing areas, providing key technical support for the engineering realization of the autonomous landing function of drones, and also laying the foundation for the intelligent development of drone landing decisions in complex environments.
Guo, HangyuShi, Zhe
Public transportation serves as a crucial component of urban mobility, contributing to the alleviation of urban congestion, reduction of travel expenses, and mitigation of air pollution. Nonetheless, the dynamic passenger demand and the complex traffic conditions render traditional bus timetables inadequate, leading to ineffective allocation of public transportation resources. Consequently, it is essential to create bus timetables that are responsive to actual traffic scenarios and fluctuating passenger demand. This study regards the bus timetable planning problem as a Markov decision-making process within a discrete time framework, proposing a deep reinforcement learning-based optimization model for bus timetables. In particular, the model is designed to account for both bus companies and passengers, incorporating a state space and reward calculation method that emphasizes passenger comfort. Then Deep Q-Network (DQN) methodology is employed to issue instructions on whether a bus departure at each time, and bus timetable is generated gradually over time. Experimental results indicate that the proposed approach significantly reduces bus travel costs and enhances the overall travel experience for passengers in comparison to traditional methods.
Xu, JieXia, DongYang, JianxiWang, Bing
SAE TOMORROW TODAY - What Baja SAE Teaches That College Can?t135746/26/2026
What does it really take to engineer under pressure? From mud-soaked vehicles and broken suspensions to team dynamics and split-second decisions, Baja SAE has become a proving ground for the next generation of engineering leaders. By challenging engineering students to design, build, and race single-seat off-road vehicles capable of surviving extreme terrain, Baja SAE requires every team to use the same 14 hp Kohler engine -- creating an even playing field and putting the focus on innovation, durability, and teamwork. Listen in as Honda's Adam Hussemann and TTX Company's Jason Rounds pull back the curtain on the intense, unpredictable world of Baja SAE competitions and how they prepare students for careers in manufacturing, mobility, and beyond. After hearing this conversation, you'll understand why more and more companies value Baja experience just as much as a perfect GPA. We'd love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don't forget to take a moment to follow SAE Tomorrow Today--a podcast where we discuss emerging technology and trends in mobility with the leaders, innovators and strategists making it all happen--and give us a review on your preferred podcasting platform. Follow SAE on LinkedIn, Instagram, Facebook, X, and YouTube. Follow host Grayson Brulte on LinkedIn, X, and Instagram.
Patterson, Lori
This paper presents a novel concept for battery electric vehicles (BEVs), referred to as the low-voltage reconfigurable electric vehicle (LVREV). The LVREV is designed to bridge the gap between L- and M-class vehicles by adopting a <60 V multi-phase powertrain combined with a swappable battery system, maintaining the overall vehicle mass below one ton. This configuration enables adaptable driving range, optimized energy consumption in urban environments, and enhanced safety. The LVREV features two distinct operating modes. Frugal mode is intended for urban use and employs a smaller battery pack to maximize efficiency and reduce vehicle mass, while Dual mode is tailored for longer extra-urban trips through the use of a dual-battery configuration. The key innovations of the LVREV concept include a reconfigurable vehicle architecture capable of meeting both urban and extra-urban mobility requirements, thus providing a highly versatile transportation solution. In addition, the low-voltage powertrain improves safety and lowers system costs, facilitating manual battery replacement and compatibility with domestic charging infrastructure. By integrating these technological solutions, the LVREV expands the potential of low-voltage electric vehicles and supports the development of more flexible, efficient, and user-oriented mobility concepts. Experimental and simulation results demonstrate the feasibility of the proposed solution and provide initial validation of the reconfigurable powertrain and battery architecture.
Tramacere, EugenioFavelli, StefanoGalluzzi, RenatoTonoli, Andrea
There's a well-known video from San Francisco in 1906 that comes up repeatedly in mobility discussions here in the 21st Century. If you haven't seen A Trip Down Market Street, it depicts the absolute bonkers variety of transportation methods used on Market Street back then: cable cars, horsecars, streetcars, pedestrians, automobiles and more. Past is prologue in a world that is adding scooters, delivery robots and other last-minute delivery vehicles to our streets. At the 2026 New York International Auto Show in April, Honda displayed its latest option in the form of the Fastport eQuad Prototype. The eQuad was originally unveiled at Eurobike 2025 and technically comes from Fastport, a micromobility venture from the Honda New Business Innovation Lab that was established to work on projects with global logistics companies. Jamie Davies, chief of operations for Fastport, called the group a kind of startup within Honda. “Three years ago,” Davies told SAE Media in New York, “a small group of Honda associates [came] together and [said], Okay, how can we create a new value for the company, a new business vertical? And so we've run the project in an agile way, working with customers all along the way to understand what their needs are, what the requirements are, and to bring to market something that fits.”
Blanco, Sebastian
The present paper reports preliminary requirement elicitation for Urban Air Mobility (UAM) from Indian perspective. A mission based approach has been adopted to identify the stakeholders and their respective requirements during different phases of the mission profile. Non adherence to the requirements emerge as possible risks for the mission and need mitigation planning. Three UAM operations for Bengaluru city viz. cargo delivery, organ delivery and passenger transport using UAM vehicle are elaborated. Stakeholders for these missions are identified and associated requirements are reported. For the cargo delivery mission, a detailed analysis is carried out to emphasis on how the India specific statutory restrictions of abiding by the red zone restrictions levied by DGCA impacts the de-tour factor and flight time. A qualitative assessment of the impact of these mission based requirements on the UAM vehicle design is presented.
DE, Manabendra M.Hebbar, ArchanaHenry, Devanandham
Automated aircraft parking systems enhance airport ground operations by enabling precise and autonomous docking of aircraft at gates. These systems reduce turnaround time, minimize human error, and optimize apron space through real-time object detection, obstacle avoidance, and dynamic path planning. Unlike fixed guided-path methods, the proposed system adapts to congestion and environmental conditions such as low visibility, ensuring safety and efficient maneuvering. Validation through simulation demonstrates the system’s potential to improve operational resilience and support scalable automation in future airport infrastructure.
Penugonda, Navya SunainaEdiga, Venkatadiwakar Goud
Unmanned Aircraft Systems (UAS) are increasingly deployed in diverse missions, and maintaining heading stability in the presence of unpredictable wind disturbance is a significant challenge. This paper proposes a novel model reference adaptive gain-scheduled PID (Proportional-Integral-Derivative) control framework tailored for the heading control of flapping-wing UAS (ornithopter) operating under dynamic wind conditions. The control architecture integrates an estimated wind disturbance value and adaptively tunes the PID gains by minimizing the error between the actual system response and a desired reference model. Gain scheduling mechanism uses airspeed, yaw rate, and estimated wind magnitude to ensure stability. The proposed method is validated on a 6-DOF UAS simulation model subjected to dynamic wind and temperature variation profiles. Comparative results show improved heading accuracy, responsiveness, and robustness over conventional fixed-gain and static gain-scheduled PID controllers, paving the way for safer and more efficient autonomous UAS missions. Also, the approach can be adapted to other platforms in future applications.
M V, ArunaMelissa, Arul
This paper addresses the critical challenge of fault-tolerant control in autonomous multi-copters, particularly under conditions of one or two rotor failures a scenario that often leads to severe instability and a complete loss of directional control due to unbalanced torque and resultant autorotation. Existing advanced control strategies, including optimal approaches such as LQR, typically require precise system modeling and state estimation, which are difficult to achieve in real-world, dynamic failure scenarios. Alternative methods like fuzzy logic, sliding mode control, and gain-scheduling either lack robust generalization or are impractical for enumerating all possible failure cases. In this work, a hybrid control framework integrating Physics Informed Neural Networks (PINN) with a standard PID controller is proposed for fault-tolerant operation of autonomous multi-copters subject to multiple actuator failures. PINNs incorporate governing physical laws as regularization in their loss functions, allowing them to learn optimal counter-torque actions and thrust balancing necessary to arrest autorotation and stabilize flight, despite limited training data and uncertainty in failure conditions. The calculated moments and thrust commands are executed via a robust PID scheme, enabling reliable real-time implementation and minimizing residual oscillations. This hybrid control architecture demonstrates significant potential to enhance the resilience and operational safety of autonomous multi-copters during unexpected motor failures. By leveraging PINN’s physics-based generalization and PID’s consistent execution, the proposed method offers an adaptive, model-agnostic approach for maintaining stable flight and directional control under severe actuator faults, with implications for next-generation fault-tolerant UAV systems deployed in complex environments.
Charapalle, SamruddhiVenugopalan, NandagopalanNerkundram Muralidharan, ArunSundararaj, Laveen
As an emerging innovative mode of public transportation, electric modular buses (EMBs) offer a novel solution to the problems of existing public transportation systems, due to the coupling-decoupling processes. In this paper, we study the energy consumption characteristics of EMBs by joining vehicle-to-vehicle (V2V) charging and reduction in aerodynamic drag due to coupling. For the pursuit of energy economy, ride comfort, and operational efficiency, we constructed an optimization scheme based on the simulated annealing (SA) algorithm to facilitate the coupling-decoupling process. The simulation results show that EMBs can meet 82.5 % of service requests compared with 61.8 % for the benchmark group, and V2V presents a significant contribution to energy efficiency, especially at low battery state of charge (SOC). Additionally, sensitivity analysis is conducted to study the impact of initial SOC, operation interval, and route type. The results provide insights for optimizing EMBs’ operations and emphasize the potential role of EMBs in supporting low-carbon and sustainable urban mobility systems.
Liao, PengGuo, JiaheNing, DonghongLi, SijiaWang, Tao
The aging of the population has been a key issue worldwide, with mobility and fall of the elderly an important problem to be solved. In this paper, we propose an elderly mobility assist system based on the intelligent power-assisted device consisting of an assistive cane and an intelligent companion. It has the functions of standing support after falling, daily support and on-site rest. The assistive cane adopts a two-stage expansion mechanism of crank and slider structure, which forms a stable triangular support after unfolding, so that the patient can stand safely. The intelligent companion platform is driven by drive wheels, equipped with pushrod motors and vacuum suction devices, it can automatically approach the user and form an stable support column when the cane is in the out-of reach range; the control system is designed by combining microcontroller, camera object recognition, wristband remote control, to realize automatic steering and autonomous navigation at differential speed. The overall design satisfies the requirements of safety and strength through mechanical verification and stress analysis. The proposed system can help the elderly people to recover from falls better and enhance their independence and safety in their daily walks.
Yu, ChenxiWang, LongyiZhu, HuayunDong, YanMi, RuixueZhu, Lihong
Advanced air mobility (AAM) seeks to develop a large-scale transportation system to revolutionize how people live and work, with electric vertical take-off and landing (eVTOL) aircraft serving a central role due to reduced emissions and noise impact. An important aspect for eVTOL aircraft certification is safe urban operations, which require understanding of the response due to aerodynamic disturbances. Experimental data are required to support eVTOL aircraft development with respect to flight dynamics and controllability, as well as design specification development. While flight testing of the full-sized air vehicle will be necessary as part of the certification process, subscale testing offers many advantages with respect to cost and flexibility, in addition to examining operational conditions that one would be reluctant to test in flight at full scale such as emergency conditions. These advantages only may be seen if the underlying scaling principles of flight dynamics / control, aerodynamic interactions, and propulsion-airframe integration are understood. This paper describes initial work towards development of a general subscale testing methodology for eVTOL aircraft flight dynamics and disturbance response characteristics including limited degree of freedom (DOF) and free flight testing. An overview of the initial development work is provided, including discussion of scaling relationships, subscale air vehicle model development, and testing activities focusing on flying qualities and stability / control characteristics.
Keller, Jeffrey D.McKillip, Jr., Robert M.Horn, JosephLee, Soohyeon
This paper introduces a novel concept for an AI-powered system designed to manage vertiport takeoffs and landings by proactively addressing the safety-critical issues of downwash and outwash. The proposed system utilizes a stream of live feedback from on-site sensors, combined with a robust predictive modeling engine, to generate optimal, aircraft-specific approach and landing trajectories in real-time. By leveraging a comprehensive database of pre-computed downwash/outwash scenarios for a multitude of UAM aircraft configurations, the AI can accurately predict the unique outwash operational footprint for each individual landing operation, based on the approaching aircraft and under the prevailing conditions. This powerful predictive capability allows the system to calculate and assign an optimal approach vector that actively minimizes risk by directing hazardous airflows away from personnel, active walkways, and other sensitive ground assets. This represents a paradigm shift from static, reactive safety measures to a proactive, intelligent, and performance-based operational model; thereby paving the way for the safe, efficient, and large-scale implementation of UAM aircraft and air taxi operations.
Rogers, DamianBelluomini, Luca
Electric vertical takeoff and landing (eVTOL) aircraft have rapidly emerged as a potential promising solution for sustainable and scalable urban air mobility. These vehicles are at a crucial stage of development, with sub-scale and full-scale flight test campaigns already underway. In forward flight, critical structural components of these variable RPM rotary wing aircraft can experience strong time varying aerodynamic loads. These components are lightweight, stiff, and often have very little intrinsic damping. Thus, from a life-cycle perspective, vibratory strains are of significant concern. This work investigates the use of Impact Dampers (IDs) in attenuating the bending and torsional response of a characteristic eVTOL boom. A computational reduced order model of an ID is developed using the Hunt-Crossley nonlinear contact model and linear beam finite elements. Predicted damper performance is compared with prior experimental measurements. Parametric studies are performed by varying key damper design variables, and predicted trends are shown to be consistent with experimentally observed behavior. The IDs attenuated the system structural response at resonance by 60.7% in bending and 52.1% in torsion, for a 5% mass penalty. Building on works presented at the 80th and 81st Vertical Flight Society Annual Forums, this publication is a next step towards establishing IDs as a viable multi-modal passive vibration control device in variable RPM multirotor vehicles.
Bapat, Siddhant SandeepSmith, EdwardVlajic, Nicholas
This paper presents an efficient numerical framework for prediction of broadband noise scattering through time-domain synthesis and propagation. For efficient scattering of broadband noise sources, a time-domain boundary element method is applied to propagate all frequencies together in a single computation. To obtain a time-resolved incident field without high-fidelity aerodynamic simulation, a stochastic broadband noise synthesis method is developed based on a semi-analytical airfoil broadband noise modeling approach. The framework is validated for airfoil trailing edge noise prediction, and the correspondence of the time-domain broadband noise synthesis method to existing semi-analytical broadband noise models is demonstrated. The framework is then applied to predict fuselage scattering of rotor tonal and broadband noise for a full-size urban air mobility concept vehicle. Significant differences are observed between the scattering effects in the tonal and broadband contributions.
Groom, MaksZhou, Beckett
A high-fidelity computational study investigates the aerodynamic behavior, flight response, and control effectiveness of a multirotor electric Vertical Take-Off and Landing (eVTOL) configuration. The investigation is organized into two parts. Part I employs an unsteady computational fluid dynamics (CFD) framework coupled with a six-degree-of-freedom (6-DoF) rigid-body dynamics module. Simulations for isolated coaxial rotors and a complete eVTOL isolate rotor aerodynamics and rotor–airframe interactions under constrained kinematics, quantifying lift capability, fuselage download, and a residual nose-up pitching moment arising from fore-aft rotor lift imbalance. Fully coupled 6-DoF free-flight simulations capture the transient vehicle response to a motor failure and recovery sequence during hover. Part II assesses flight control response through a cascade Proportional-Derivative (PD) controller implemented in MATLAB/Simulink across two maneuver cases: hover stabilization and climb rate tracking, which are parameterized using aerodynamic data extracted from the isolated rotor CFD simulation. This decoupled approach enables systematic gain tuning and controller assessment without the computational overhead of fully coupled closed-loop CFD simulations. The results confirm that the CFD–6-DOF framework effectively resolves tightly coupled aerodynamic-dynamic interactions inherent to distributed electric propulsion configurations, and that the cascade PD architecture provides initial control authority assessment across the primary flight axes. These findings establish a foundation for trim strategy development, advanced control law design, and future integration toward robust flight control for urban air mobility operations.
Sheng, ChunhuaBasnet, SunilZhao, Qiuying
This study evaluates the impact of range extension on gross takeoff weight (GTOW) and energy cost for the NASA Lift+Cruise eVTOL configuration under present and near-term battery technology limitations. A baseline 8,210 lb, 6-passenger vehicle, originally designed for a 75-mile mission at 400 Wh/kg battery energy density, is shown to achieve only 15 miles at a more realistic 200 Wh/kg, largely due to the 20-minute SFAR reserve, which accounts for 64% of total onboard energy. To quantify the penalties of range extension, three sizing strategies are examined: fixed GTOW with payload trade-offs, fixed-geometry overloading, and fully co-scaled vehicle resizing. The co-scaled configurations reveal a strong nonlinear GTOW growth driven by an "adding battery to carry battery" effect, in which increases in GTOW necessitate heavier structure and propulsion, leading to a practical feasibility ceiling near 45 miles. Energy cost per payload-mile is found to be non-monotonic, reaching a minimum near 20-25 miles before increasing due to compounding weight penalties, contrary to trends predicted by fixed-weight analyses. Significant off-design penalties are also observed; operating a 40-mile aircraft on a 10-mile mission incurs a 72% energy cost increase relative to a co-scaled vehicle for 10 miles. Increasing battery energy density by 22.5% (to 245 Wh/kg) reduces the 6-passenger 40-mile design GTOW by 33% (from 13,712 lb to 9,187 lb) and shifts the optimal energy cost point outward to 30 miles. Ultimately, battery energy density is identified as the dominant parameter dictating the vehicle size, weight, performance, and the fundamental operational feasibility of UAM eVTOLs.
Chandravanshi, AshutoshGandhi, FarhanHalder, Anubhav
Urban Air Mobility (UAM) vehicles will operate in complex atmospheric environments where unsteady inflow conditions can significantly influence rotor performance and acoustic emissions. This study investigates the impact of an axially oscillating time-harmonic gust (i.e., a single mode of an impinging turbulence spectrum) on the aerodynamics and acoustics of a subscale UAM rotor in edgewise flight. Both mid-fidelity and high-fidelity analysis methods are employed to capture the unsteady rotor response and provide cross-validation of predictions. The results highlight a frequency modulation mechanism, wherein the gust excitation introduces sideband content around the blade-passing frequency (BPF), located at BPF ± the gust frequency and higher harmonics. This modulation alters both the tonal structure and overall acoustic signature of the rotor, with corresponding implications for performance metrics. A novel analytical method, employing a spatio-temporal modal representation of the gust field, is used to predict the unsteady rotor response.
Golubev, VladimirLyrintzis, AnastasiosMankbadi, RedaMarques, MichaelMaleki, AlirezaVoropayev, VadimOssyra, Stanley
This historical paper explores the development of vertical lift. Beginning with Leonardo's aerial screw, a profound conceptual leap, which was a helical device intended to compress air beneath it and rise vertically. Though never constructed or flown, it represents the first recorded articulation of rotary lift. The idea of rising directly upward would echo through the dirigible era of the early twentieth century, the helicopter age of the mid-century, and the emerging era of Advanced Air Mobility (AAM). This study traces that intellectual lineage and explores the technological and social forces that shaped the destiny of vertical passenger flight.
Lorenzon, JasonAlrutz, Amy
This study highlights that rotor-rotor interactions can significantly modify both tonal and broadband noise characteristics. Continued investigation into these mechanisms is vital to developing reliable noise prediction methodologies and establishing design strategies that balance propulsion efficiency with acoustic acceptability for AAM vehicles. This work sought to answer what physical mechanisms contribute to the increased dominance of broadband noise in eVTOL-scale rotors. By characterizing the tip vortex of a single rotor, it was found that rotor-rotor interaction is highly dependent on two factors: Blade-vortex phasing and interaction duration. Characteristic vortex time scales can be correlated with increased noise. Interactions that generate increased noise have a non-linear relationship with rotor positioning. The interaction-generated noise is highly directive. This work aims to elucidate the dominant source noise mechanisms of rotor-rotor interaction noise by characterizing blade tip vortices using PIV.
Sorensen, PeterSeth, DhureeCuppoletti, Daniel
Urban Air Mobility (UAM) represents a paradigm shift in metropolitan transportation, introducing electric vertical takeoff and landing (eVTOL) aircraft into dense urban ecosystems. This transformation is driven by advances in electrification, digital infrastructure, and integrated airspace management. According to the U.S. Department of Transportation's Advanced Air Mobility National Strategy 2025, UAM is expected to become a cornerstone of multimodal urban transport, with commercial operations projected in multiple U.S. cities before 2030 [1].
Namuduri, KameshSampath, Arunkumar
A plethora of electric vertical takeoff and landing (eVTOL) aircraft development projects aim at developing passenger-carrying aerial vehicles for the purpose of providing point-to-point mobility services within and between metropolitan areas. The nascent passenger-carrying advanced air mobility (AAM) industry promises more affordable fares and seamless experience through innovation in aircraft design with the roll-out of these novel eVTOL within five years, new concepts of operations involving more automation, and higher utilization than with today's helicopter charter operations. AAM operators plan to leverage existing heliport facilities as well as trigger the development of new vertiports-some of them could be located on existing city real estate (e.g., high-rise buildings and parking garage rooftops). Moving vertical flight toward higher-intensity passenger operations and enabling a broad adoption as outlined during the dawn of AAM raise the question of accessibility. This includes access to the VTOL door sill for passengers with reduced mobility (PRMs), the VTOL boarding and deplaning process, and the feasibility of carrying their equipment onboard (including wheelchairs). This context includes the intermodal aspects of the first and last miles to the vertiport, the availability of equipment for facilitating PRM boarding, and the broad variety of aviation facilities that are served by VTOL aircraft-including small helipads and vertipads that are not all PRM-accessible. The study identifies key design and operational criteria for reducing barriers to an unhindered boarding and deboarding of VTOL aircraft-including helicopters and eVTOLs. It suggests mitigation in aircraft design and vertiport design. The analysis emphasizes the importance of incorporating accessibility considerations in the development of the different components of AAM in order to enhance operational safety, efficiency, and customer experience and to prevent adverse impacts on dignity, fairness, and mobility for all.
Le Bris, GaëlNguyen, Loup-Giang
This paper presents an adaptive model predictive control (MPC) framework for nonlinear urban air mobility (UAM) vehicles operating across the full flight envelope. The proposed approach leverages a linear parameter-varying (LPV) representation to update the predictive model online, enabling accurate capture of strongly nonlinear and time-varying dynamics associated with distributed electric propulsion (DEP) eVTOL aircraft. To systematically address the highdimensional and coupled nature of MPC tuning, a multi-objective evolutionary optimization strategy based on NSGAII is employed, incorporating proper normalization of states and control inputs to ensure balanced weighting and meaningful exploration of the design space. The resulting controller explicitly accounts for actuator constraints and enables reconfigurable control allocation for fault-tolerant operation. The framework is evaluated in nonlinear simulations using NASA's Generic Urban Air Mobility (GUAM) model and benchmarked against a robust servomechanism linear quadratic regulator (RSLQR). Results demonstrate that the proposed adaptive MPC achieves improved trajectory tracking and enhanced robustness under both nominal conditions and actuator degradation scenarios, including partial motor failure, while maintaining constraint satisfaction throughout all flight regimes.
Ngo, Tri
Electric Vertical Take-Off and Landing (eVTOL) aircraft are poised to transform urban and regional mobility by offering zero-emission, congestion-free transportation. As regulatory frameworks evolve and advanced air mobility (AAM) gains traction, manufacturers are exploring propulsion strategies that improve range, power delivery, and overall system efficiency. A key challenge in eVTOL development is balancing range with payload capacity. While larger battery packs can extend range, they also increase system weight, reduce payload, and prolong charging times, limiting operational flexibility and turnaround time. Hydrogen fuel cells, supported by liquid hydrogen (LH₂) present a promising alternative for eVTOL propulsion. This study proposes a methodology for optimizing fuel cell propulsion systems tailored to eVTOL applications. A multi-physics modeling framework for eVTOL flight dynamics and propulsion system was developed, representing the target eVTOL configuration. For a defined flight path including vertical takeoff, hover, cruise, and landing, a Genetic Algorithm (GA) based optimization was conducted on propulsion system. The algorithm down-selected battery size, fuel cell stack specifications, and hydrogen tank capacity to meet mission requirements while minimizing propulsion system weight. The modeling framework was also used to evaluate trade-offs between payload and performance as functions of component sizing, battery chemistry and energy distribution strategy.
Garcia, BrunoPaul, SumitZeigler, SophiaFranke, MichaelJoshi, SatyumAraujo, Joao
This paper develops an engineering concept and research framework showing how Cherokee MC2 (Mobile Command Center) and MVP (Mobile Vertipad Platform) can individually, and then as a combined system, resolve key operational and infrastructure challenges facing rotorcraft, eVTOL, VTOL, and UAS missions across civil, commercial, and military contexts. The investigation synthesizes current vertiport / vertipad design guidance, UAM and UTM operational architectures, and recent research on rotor downwash and degraded visual environment hazards to derive a deployable "vertiport node" architecture for austere and time-critical operations. MC2 is treated as the digital and procedural core enabling command, control, communications, data fusion, and manned–unmanned teaming, while MVP is treated as the physical landing interface enabling rapid, load-bearing, illuminated vertical-lift operations without fixed infrastructure. The primary contribution is a traceable topic-to-capability mapping supported by standards and research, plus a modeling, simulation, and optimization workflow to validate safety zones, capacity, scheduling, and resilience. Conclusions identify practical deployment pathways and research gaps for certification-aligned operations.
Vandy, Justin
The proliferation of Autonomous Aerial Vehicles (AAVs) necessitates robust solutions for dynamic obstacle avoidance, particularly against non-cooperative intruders whose trajectories are unpredictable. While traditional path-planning algorithms excel in static environments, they struggle with dynamic obstacles due to the inherent difficulty in accurately estimating and registering their real-time depth and velocity into a world model. This paper presents a novel two-stage vision-based framework that leverages deep learning for reactive avoidance of non-cooperative dynamic intruders. Our approach decouples the perception and decision-making processes: an object detection deep neural network first processes monocular camera images to detect and track the 2D pixel coordinates of intruders. This perceptual output is then fed into a deep reinforcement learning agent, which learns a mapping from the intruder's image-space location to a high-level avoidance maneuver. This leads to more efficient learning, as the RL agent focuses solely on the policy without the burden of learning visual features. The advantage of using RL lies in its ability to handle partially observable situations—because reliable depth or full 3-D position information is not always readily available from monocular imagery, the RL agent learns to act based on the observable visual cues. Simulation results confirm that our proposed framework provides an effective solution for vision-based, non-cooperative intruder avoidance.
Dadkhah Tehrani, NavidWeintraub, JustinAmonkar, RikhilCarlson, SeanCherepinsky, Igor
Urban air mobility with electric Vertical Take-Off and Landing (eVTOL) aircraft faces critical micro-weather and infrastructure readiness challenges. This paper proposes a novel socio-technical solution: a tokenized gamification platform that crowdsources hyper-local wind and weather data to enhance operational resilience. We outline the safety gap left by traditional aviation weather systems (METAR, AWOS, ASOS) in urban environments, and leverage community engagement to fill it. The proposed system integrates with Unmanned Traffic Management (UTM) and Safety Management Systems (SMS) to validate user-contributed micro-weather observations, incentivize accurate reporting through tokens and skill-level progression, and feed data into AI-driven forecasts. Early proof-of-concept results indicate improved wind hazard detection and robust user participation. By aligning with emerging regulations (FAA, EASA, DGCA) and test frameworks, this crowdsourced micro-weather ecosystem shows potential to uplift eVTOL safety, build public trust, and support city-scale planning for advanced air mobility.
Udipi, RangaRaul, SwarabEsturi, Ankith
Electric Vertical Take-Off and Landing (eVTOL) vehicles are emerging as solutions for urban air mobility, but their operation can encounter hazardous aerodynamic conditions such as the Vortex Ring State (VRS), which causes thrust loss and intense vibrations. This study investigates VRS for the Archer Maker tilter propeller by combining numerical simulations using the mid-fidelity solver DUST and the high-fidelity solver OVERFLOW with prior experimental observations. Propeller performance is evaluated through thrust and torque evolution under various descent conditions, while flow fields in the propeller wake at different descent ratios around VRS conditions are evaluated and compared via 2D visualizations. A comparison of results reveals that both numerical approaches are capable of evaluating the performance degradation in correlation with vortex ring formation within specific descent regimes, showing slight discrepancies particularly regarding the descent ratio regime where VRS occurs. A flow field comparison with experimental data validates the multi-fidelity numerical approach, showing the capabilities of both numerical approaches to capture the flow physics mechanisms that lead to the generation of the vortex ring around the propeller disk.
Droandi, GiovanniIsola, DarioPalmer, DavidNorena, DiegoSavino, AlbertoZanotti, Alex
For Urban Air Mobility taxis, passengers will experience different levels of heave motion during flight. Researchers at NASA Armstrong Flight Research Center conducted two studies in which passengers were exposed to varying levels of heave motion in the Armstrong Virtual Reality Passenger Ride Quality Laboratory. In the first study, twenty-three volunteers from the Armstrong workforce evaluated the motions on a five-point rating scale and a binary comfort scale; in the second study, fifty volunteers evaluated a flight experience with varying levels of stimuli using a five-point comfort scale and a five-point passenger acceptance scale. This paper combines the results of these two studies to observe the relationship between heave motion and passenger rider quality and acceptance. Both passenger comfort and acceptance were found to decrease with increasing heave acceleration The statistically significant relationship between the magnitude of heave acceleration and passenger comfort for individual studies and combined results are discussed.
Ramia, SaravanakumaarTzarnotzky, UriHendrickson, CoryRoss, JeremyGuy, ColetteHanson, Curtis
The aerospace industry is undergoing a profound transformation driven by emerging aviation technologies, including Advanced Air Mobility (AAM), electric vertical takeoff and landing (eVTOL) aircraft, and highly automated flight control systems. These complex systems often feature tightly coupled flight controls and power plants where traditional methods of compliance — relying heavily on physical ground and flight testing — are becoming increasingly impractical due to the vast number of potential interaction cases. To address this challenge, the SAE G-35 Modeling, Simulation, and Training for Emerging Aviation Technologies and Concepts Committee was formed to develop industry consensus standards. This presentation discusses the landmark release of SAE ARP7094, "Recommended Practice for Using Modeling and Simulation for Certification of Aircraft, Products, and Systems" and its role in establishing a standardized, simulation-based path to certification. The SAE G35C group is responsible for developing standards and procedures for using modeling and simulation as a method of compliance for the certification of AAM aircraft similar to the RCbS project conducted in collaboration between EASA, academia and industry in Europe.
Goericke, JanYates, CraigvanHoudt, John
Autonomous Inspection via small Unmanned Aircraft Systems (sUAS) is increasingly utilized across industrial use cases such as inspection of bridges, buildings, construction sites, roadways, transmission lines, pipes, wind turbines and power systems (1). In principle, the system workflow of inspection; identification and characterization of defects; and mapping in space is very similar across industries. Boeing and Proxim (A Near Earth Autonomy Company) have partnered to pursue this technology in the Aerospace and Defense industry for General Visual Inspection (GVI) of airframes predominantly in a maintenance setting. This activity began by deploying Proxim’s Autonomous Aircraft Inspection (AAI) technology and Boeing's Automated Damage Detection Software (ADDS) on Boeing C-17 Globemaster III at Joint Base Pearl Harbor-Hickam. It has expanded to offer U.S. Department of War (DoW) and Commercial customers aircraft-agnostic enhanced exterior GVI capability at point of need by leveraging unique ADDS AI algorithm in support of both home station and deployed operations. This paper gives an overview to industry developments in Autonomous Inspection, and the development AAI/ADDS technologies.
Ransick, HayleyGatto, VinceRhodes, PeterCoccia, CharlesNevinsky, Michael
Rainwater accumulation and management are critical to the safety and reliability of drones and emerging eVTOL aircraft. Current industry practice relies on physical rain testing, such as RTCA DO-160, which defines rainfall conditions for environmental qualification but is costly and difficult to apply during early design stages. This work presents a virtual rainwater assessment framework using Smoothed Particle Hydrodynamics (SPH) simulation in PreonLab. Using an early-stage APELEON cargo drone as a reference case, the method predicts rain impingement, surface runoff, pooling, and ingress under representative rainfall conditions. The meshless SPH approach enables direct simulation of complex geometries and transient interactions without mesh generation, while also supporting rotating components and arbitrary orientations. Results identify key mechanisms governing water transport, including geometry-driven runoff, hinge-related ingress, and droplet deflection from nearby structures. While the total water accumulated on the aircraft can reach on the order of several hundred grams, the amount entering the cargo space remain small. Localized moisture exposure highlights potential durability risks. The framework enables early design evaluation, parametric studies, and rapid assessment of mitigation strategies, supporting simulation-driven development and certification preparation for advanced air mobility systems.
Li, JunFuerlinger, AndreasSchneider, Juergen
Urban Air Mobility (UAM) vertical takeoff and landing (VTOL) air taxis might exhibit flight motions that are unfamiliar to many passengers. Researchers at the NASA Armstrong Flight Research Center performed a study to identify relationships between rotational flight motion and passenger comfort and acceptance. Fifty test subjects each completed a 20-min passenger experience in a virtual air taxi simulation. Subjects evaluated flight maneuvers with varying levels of rotational motion and indicated their comfort level and willingness to take a real flight with the motion they experienced. Study factors included yaw rate, pitch rate, and roll rate. Participants evaluated four levels of each study factor. The study found linear relationships for each study factor showing a decrease in passenger comfort and acceptance with increased motion. Statistical significance of the results, the possible influence of participants’ backgrounds and experiences, and other potential sources of bias in the study population are discussed.
Hanson, CurtisHendrickson, CoryTzarnotzky, UriRoss, JeremyGuy, ColetteRamia, Saravanakumaar
Electric vertical takeoff and landing aircraft impose significantly higher electrochemical and thermal demands on Li-ion batteries than conventional electric vehicles, yet publicly available aging datasets for this application remain limited in applicability, cell technology, and statistical robustness. This study experimentally characterizes the degradation behavior of state-of-the-art Molicel P45B 21700 cells under realistic Urban Air Mobility operating conditions involving high power demand, rapid turnaround, and repeated cycling. Eight cells are subjected to over 3,000 cycles using a fast constant-current charging protocol and a multi-segment constant-power discharge profile. The discharge profile is derived from a representative 7000-lb winged eVTOL with a 20-mile range, requiring normalized power rates of 6.4E during takeoff and landing and 1.6E during cruise. Periodic Reference Performance Tests are conducted to track capacity fade, internal resistance evolution, and energy efficiency. The cells retained over 90% of their initial capacity after 3,270 cycles, while total energy efficiency remained stable at 91%, comprising impedance and hysteresis-driven components of approximately 94% and 97%, respectively. Direct current internal resistance exhibited an initial decrease before stabilizing, yet total discharged capacity increased from 1.81 Ah to 1.84 Ah, indicating aging-driven polarization effects not captured by DCIR. A zero-order equivalent circuit model underpredicts discharged capacity by approximately 4% for fresh cells, increasing to nearly 6% at cycle 3,270 due to unmodeled time-dependent polarization effects. These results demonstrate that while modern Li-ion cells exhibit strong durability under repetitive high-power usage, the accuracy of battery performance prediction is strongly dependent on dynamic impedance effects beyond conventional DCIR-based models.
Halder, AnubhavGandhi, Farhan
Meta-wheels—non-pneumatic wheels whose performance is governed by structural geometry rather than internal pressure—offer new opportunities for directional stiffness control. Yet achieving independent tuning of longitudinal, lateral, and vertical stiffness within a single wheel architecture has remained challenging due to the inherent coupling in conventional radial and planar curved spokes. In this study, we introduce a three-dimensional (3D) discrete curved-spoke design that provides explicit geometric control through two independent parameters: the in-plane curvature angle (α) and the out-of-plane inclination angle (β). Using spoke-level and full-wheel finite-element (FE) simulations, supported by a simplified cantilever-beam analytical model, we show that these two geometric parameters govern stiffness in fundamentally different ways. The curvature angle α serves primarily as a geometric softener, reducing stiffness in all directions while maintaining a high top-loading ratio (TLR) (>92%). In contrast, the inclination angle β enables true directional stiffness decoupling: increasing β substantially raises longitudinal stiffness and decreases lateral stiffness, while leaving vertical stiffness nearly unchanged (≈1.4% variation). Compared with conventional two-dimensional (2D) spoke designs, the proposed 3D architecture achieves stiffness characteristics approaching those of pneumatic tires, particularly higher longitudinal stiffness and lower lateral stiffness, without sacrificing vertical load-bearing capacity. Moreover, the combined simulation–analysis framework provides an efficient early-stage screening tool by mapping desired stiffness ratios directly to geometric parameters, narrowing the feasible design space before full-wheel FE verification. Overall, this work demonstrates that 3D discrete curved spokes present a practical and interpretable route toward stiffness-decoupled, directionally programmable meta-wheels for next-generation mobility platforms.
Han, HeeseungLiu, ZhipengJu, Jaehyung
SAE TOMORROW TODAY - SAE Standards: Building Consensus for Moving Mobility Forward135634/16/2026
Standards aren't flashy ... but they make modern mobility possible by enabling emerging technologies to scale safely. Listen in as we sit down with SAE International experts Christian Thiele, Senior Director of Global Vehicle Ground Standards, and David Franks, Standards Specialist Engineer for Aerospace, for a wide‑ranging conversation on how SAE standards quietly enable trust, interoperability, and scale across automotive and aerospace. This discussion spans EV charging, wireless roads, automated driving, advanced air mobility, hydrogen propulsion, and the growing role of artificial intelligence. Go behind the scenes to learn how these standards are developed, the importance of industry consensus, and why they often exceed regulatory safety requirements. Are you interested in shaping the standards behind next-gen mobility technology? Get involved at sae.org/standards/development. We'd love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don't forget to take a moment to follow SAE Tomorrow Today--a podcast where we discuss emerging technology and trends in mobility with the leaders, innovators and strategists making it all happen--and give us a review on your preferred podcasting platform. Follow SAE on LinkedIn, Instagram, Facebook, X, and YouTube. Follow host Grayson Brulte on LinkedIn, X, and Instagram.
Patterson, Lori
By the early 2020s, more than 4.5 billion people have been living in urban areas worldwide, compared to just 1 billion in 1960. Rising growth in urban populations present challenges to infrastructure and transportation systems. Higher traffic levels and reliance on conventional vehicles have contributed to heightened greenhouse gas (GHG) emissions, rising global temperatures, and irreversible environmental degradation. In response, emerging transportation solutions—including intelligent ridesharing, autonomous vehicles, zero-tailpipe-emission transport, and urban air mobility—offer opportunities for safer and more sustainable transportation ecosystems. However, their widespread adoption depends not only on technological performance and efficiency, but also on integration with current infrastructure, safety, resilience to unexpected disruptions, and economic viability. A dynamic agent-based System-of-Systems (SoS) transportation model is developed to simulate vehicle traffic and human movement for assessing mobility solutions against different demand scenarios and possible disruptions within a well-defined metropolitan area. The analysis adopts the concept of an airport city—a cluster of residential, commercial, and industrial spaces surrounding major airports—as a representative urban context. Using the Atlanta Aerotropolis as a case study, this work introduces an interactive, parametric decision-support methodology for evaluating the impact and benefits of future mobility options, as part of transportation master planning. Given the multi-objective and multi-stakeholder nature of transportation planning (e.g. local government, urban planners, engineers, and technology providers), the proposed approach leverages simulation-enabled digital twins of mobility solution alternatives to analyze traffic performance across multiple criteria, including energy consumption, emissions, affordability, accessibility, and connectivity within the broader urban infrastructure. The study reveals cost-benefit trade-offs among mobility solutions in the context of disruptive scenarios, such as the 2026 FIFA World Cup hosted by Atlanta, GA. The results highlight the importance of deploying a mix of mobility options over the city’s transportation network to maximize sustainability while maintaining resilient operations.
Rana, VishvaBalchanos, MichaelMavris, DimitriValenzuela Del Rio, Jose
Ensuring safe operation and reliable control of mobility systems remains a significant challenge, particularly for nonlinear and high-dimensional applications subject to external disturbances with hard constraints and limited computational resources in real-time implementations. A reference governor (RG) can enforce constraints using an add-on scheme that preserves the pre-stabilizing controller while balancing the need to satisfy other requirements, including reference tracking and disturbance rejection. Thus, in this paper, we exploit RG-based strategies focusing on nonlinear mobility systems. While the method is generalizable to other applications, such as waypoint following for autonomous driving, the flight dynamics of a quadrotor system with twelve states are used as an example. We implement a disturbance rejection RG to satisfy safety constraints and track set points. To handle nonlinearity, we propose an optimal strategy to quantify the maximum deviation between the nonlinear plant and the linearized prediction model, which are then incorporated into the RG’s disturbance bounds for safety margins. Simulation results demonstrate that the RG guarantees the satisfaction of constraints while maintaining desirable tracking performance and being computationally feasible. Furthermore, the framework effectively mitigates the impact of disturbances, thereby enhancing system robustness. The findings confirm that the RG can be successfully applied to complex nonlinear aerial vehicles, providing a promising solution for the extensions to other safety-critical mobility applications.
Dong, YilongLi, Huayi
The transition to sustainable mobility and energy systems represents a complex socio-technical challenge, with the success of new technologies and policies critically dependent on their interaction with human behavior. Traditional models frequently struggle to capture the nuanced, heterogeneous, and adaptive characteristics of individual decision-making in mobility choices and energy usage, thereby introducing significant uncertainties into system design and policy evaluation. This paper presents a novel paradigm to bridge this gap: the Hierarchical Generative Agent-based Simulation Framework (HGA-Sim). The framework's core innovations are twofold: 1) It utilizes Large Language Models to generate agents endowed with intrinsic personality traits autonomously, enabling a realistic simulation of diverse, human-like responses to environmental stimuli and personal experiences. 2) It employs a hierarchical "Archetype -Individual" architecture, rendering large-scale community simulations computationally feasible. Validated through a case study of a 495-agent community, the HGA-Sim framework accurately reproduces aggregate mobility and energy consumption patterns, including critical peak loads and temporal dynamics. It demonstrates remarkable fidelity to real-world data with a Root Mean Square Error of 0.1983. By establishing a human-in-the-loop virtual testing environment, this research provides a foundational tool for evaluating the real-world viability of sustainable mobility designs, assessing the potential socioeconomic impacts of new transportation and energy policies, and mitigating risks associated with investments in future sustainable infrastructure.
Chen, YongjianYang, ZhifengOu, Shiqi(Shawn)
Wet-gap crossings, which involve moving military forces across rivers and other water obstacles, remain among the most difficult operations to plan and execute. These maneuvers are complicated by choke points, fast-flowing water, and the exposure of forces and equipment to enemy fire. Despite these challenges, wet-gap crossings are critical to maintaining operational momentum during large-scale combat operations. This study examines doctrinal approaches to wet-gap crossings and explores the relationship between these operations and observed vehicle losses in the Russia-Ukraine War. Using a mixed-method approach, the analysis integrates daily operational reports from the Institute for the Study of War with visually confirmed equipment loss data from Oryxspioenkop. A custom Wet-Gap Relevance Score (WGRS) was developed using Natural Language Processing techniques to quantify the degree to which each ISW report focused on crossing operations. Statistical analysis shows that pontoon losses cluster within two days of major crossing events, confirming long-standing engineering doctrine regarding the vulnerability of bridging assets. However, the overall correlation between WGRS scores and total daily vehicle losses is weak, suggesting that broader attrition patterns obscure the distinct impact of crossing operations. These findings provide new empirical insight into how doctrinal principles manifest in modern conflict and underscore the design implications for future military vehicles. Effective wet-gap crossings require a diverse fleet: amphibious vehicles to establish bridgeheads, light vehicles that can be rafted to sustain momentum, and heavier vehicles that depend on bridging to continue the assault.
Lynch, BenjaminDosan, LoganMittal, Vikram
Shared Autonomous Electric Vehicles (SAEVs) can enhance urban mobility and efficiency. However, their operational performance is often hindered by the spatio-temporal imbalance between vehicle supply and passenger demand, leading to long wait times. This paper develops a novel repositioning framework where a lightweight CNN, informed by computationally intensive multi-agent simulations, enables real-time strategy deployment. The results show that: (1) An optimized repositioning policy, calibrated via multi-agent simulation, effectively cuts the mean passenger waiting time from 12.0 to 3.0 minutes (a 75% reduction). (2) A lightweight CNN surrogate model enables real-time deployment, reducing the policy computation time from ~4 hours to ~5 minutes (>98% faster). (3) The deep learning surrogate achieves this speed with a negligible performance trade-off, increasing the waiting time by only 0.156 minutes (4.9%) compared to the full optimization.
Shang, KaiWang, Ning
Items per page:
1 – 50 of 1729