arXiv subjects

Shadi Sharif Azadeh

Publications and source records attributed to Shadi Sharif Azadeh.

9 recordsLinked to original sources

arXiv2026

Modular Autonomous Transit: From Vehicle Modularity to Deployment-Ready Transit Operations

Audience: Tech companies such as NExT leadership; public transport operators; autonomous transit developers; charging partners; public authorities, and industrial partners considering pilots. Content: The strongest aspect of Modular Autonomous Vehicles (MAVs) is not only that vehicles can physically couple. A MAV is composed of Modular Autonomous Units (MAUs), and modularity creates operating advantages across line-level operations, intermodal services, network-level operations, stochastic real-time control, and electrified vehicle operations and charging infrastructure. Research basis and disclaimer: The brief summarizes scientific findings of four studies conducted by Dr. Xia and Dr. Sharif Azadeh on modular transit operations, including a charging infrastructure study using technical data associated with NExT MAUs.

math.OC↗

arXiv2026

T-STAR: A Context-Aware Transformer Framework for Short-Term Probabilistic Demand Forecasting in Dock-Based Shared Micro-Mobility

Reliable short-term demand forecasting is essential for managing shared micro-mobility services and ensuring responsive, user-centered operations. This study introduces T-STAR (Two-stage Spatial and Temporal Adaptive contextual Representation), a novel transformer-based probabilistic framework designed to forecast station-level bike-sharing demand at a 15-minute resolution. T-STAR addresses key challenges in high-resolution forecasting by disentangling consistent demand patterns from short-term fluctuations through a hierarchical two-stage structure. The first stage captures coarse-grained hourly demand patterns, while the second stage improves prediction accuracy by incorporating high-frequency, localized inputs, including recent fluctuations and real-time demand variations in connected metro services, to account for temporal shifts in short-term demand. Time series transformer models are employed in both stages to generate probabilistic predictions. Extensive experiments using Washington D.C.'s Capital Bikeshare data demonstrate that T-STAR outperforms existing methods in both deterministic and probabilistic accuracy. The model exhibits strong spatial and temporal robustness across stations and time periods. A zero-shot forecasting experiment further highlights T-STAR's ability to transfer to previously unseen service areas without retraining. These results underscore the framework's potential to deliver granular, reliable, and uncertainty-aware short-term demand forecasts, which enable seamless integration to support multimodal trip planning for travelers and enhance real-time operations in shared micro-mobility services.

cs.LG↗

arXiv2026

Integrated timetabling and scheduling of modular autonomous vehicles under uncertainty

Addressing the Integrated Timetabling and Vehicle Scheduling (TTVS) problem is important for improving transit operations. Recently, the emerging modular autonomous vehicles composed of modular autonomous units have made it possible to dynamically adjust on-board capacity to better match space-time imbalanced passenger flows. This paper introduces an integrated framework for the TTVS problem in a dynamically capacitated and modularized bus network, considering time-varying and uncertain passenger demand. In this network, units can be decoupled and rerouted across different lines within the network at various times and locations, providing passengers with the opportunity to make in-vehicle transfers -- that is, to transfer between lines while remaining onboard. We formulate a stochastic programming model to jointly determine the optimal robust timetable, dynamic formations of vehicles, and cross-line circulations of units, aiming to minimize the weighted sum of operator and passenger costs. To solve realistic instances, we propose a tailored integer L-shaped method that dynamically solves the model through a rolling-horizon optimization algorithm. Furthermore, we extend our approach into a novel learning-based real-time decision-making framework that fine-tunes timetables and re-optimizes vehicle schedules in response to evolving and new demand realizations during operations. At its core is a scenario-retention method that selects a representative subset of scenarios using a machine learning model trained on scenario-level features. This subset is then incorporated into the optimization, ensuring both computational scalability and solution quality. To validate the effectiveness of our methods, we conduct experiments based on the Beijing bus network.

math.OC↗

arXiv2025

Integrated demand-side management and timetabling for an urban rail transit line: A Benders decomposition approach

The intelligent upgrading of metropolitan rail transit systems has made it feasible to implement demand-side management policies that integrate multiple operational strategies in practical operations. However, the tight interdependence between supply and demand necessitates a coordinated approach combining demand-side management policies and supply-side resource allocations to enhance the urban rail transit ecosystem. In this study, we propose a mathematical and computational framework that optimizes train timetables, passenger flow control strategies, and trip-shifting plans through the pricing policy. Our framework incorporates an emerging trip-booking approach that transforms waiting at the stations into waiting at home, thereby mitigating station overcrowding. Additionally, it ensures service fairness by maintaining an equitable likelihood of delays across different stations. We formulate the problem as an integer linear programming model, aiming to minimize passengers' waiting time and government subsidies required to offset revenue losses from fare discounts used to encourage trip shifting. To improve the computational efficiency, we develop a Benders decomposition-based algorithm within the branch-and-cut method, which decomposes the model into train timetabling with partial passenger assignment and passenger flow control subproblems. We propose valid inequalities based on our model's properties to strengthen the linear relaxation bounds at each node of the branch-and-bound tree. Computational results from proof-of-concept and real-world case studies on the Beijing metro show that our solution method outperforms commercial solvers in terms of computational efficiency.

math.OC↗

arXiv2025

Robust charging station location and routing-scheduling for electric modular autonomous units

Problem definition: Motivated by global electrification targets and the advent of electric modular autonomous units (E-MAUs), this paper addresses a robust charging station location and routing-scheduling problem (E-RCRSP) in an inter-modal transit system, presenting a novel solution to traditional electric bus scheduling. The system integrates regular bus services, offering full-line or sectional coverage, and short-turning services. Considering the fast-charging technology with quick top-ups, we jointly optimize charging station locations and capacities, fleet sizing, as well as routing-scheduling for E-MAUs under demand uncertainty. E-MAUs can couple flexibly at different locations, and their routing-scheduling decisions include sequences of services, as well as charging times and locations. Methodology: The E-RCRSP is formulated as a path-based robust optimization model, incorporating the polyhedral uncertainty set. We develop a double-decomposition algorithm that combines column-and-constraint generation and column generation armed with a tailored label-correcting approach. To improve computational efficiency and scalability, we propose a novel method that introduces super travel arcs and network downsizing methodologies. Results: Computational results from real-life instances, based on operational data of advanced NExT E-MAUs with cutting-edge batteries provided by our industry partner, indicate that charging at both depots and en-route fast-charging stations is necessary during operations. Moreover, our algorithm effectively scales to large-scale operational cases involving entire-day operations, significantly outperforming state-of-the-art methods. Comparisons with fixed-composition buses under the same fleet investment suggest that our methods are able to achieve substantial reductions in passengers' costs by flexibly scheduling units.

math.OC↗

arXiv2025

Dynamic Preference-based Multi-modal Trip Planning of Public Transport and Shared Mobility

The shift from private vehicles to public and shared transport is crucial to reducing emissions and meeting climate targets. Consequently, there is an urgent need to develop a multimodal transport trip planning approach that integrates public transport and shared mobility solutions, offering viable alternatives to private vehicle use. To this end, we propose a preference-based optimization framework for multi-modal trip planning with public transport, ride-pooling services, and shared micro-mobility fleets. We introduce a mixed-integer programming model that incorporates preferences into the objective function of the mathematical model. We present a meta-heuristic framework that incorporates a customized Adaptive Large Neighborhood Search algorithm and other tailored algorithms, to effectively manage dynamic requests through a rolling horizon approach. Numerical experiments are conducted using real transport network data in a suburban area of Rotterdam, the Netherlands. Model application results demonstrate that the proposed algorithm can efficiently obtain near-optimal solutions. Managerial insights are gained from comprehensive experiments that consider various passenger segments, costs of micro-mobility vehicles, and availability fluctuation of shared mobility.

math.OC↗

arXiv2025

A Short-Term Predict-Then-Cluster Framework for Meal Delivery Services

Micro-delivery services offer promising solutions for on-demand city logistics, but their success relies on efficient real-time delivery operations and fleet management. On-demand meal delivery platforms seek to optimize real-time operations based on anticipatory insights into citywide demand distributions. To address these needs, this study proposes a short-term predict-then-cluster framework for on-demand meal delivery services. The framework utilizes ensemble-learning methods for point and distributional forecasting with multivariate features, including lagged-dependent inputs to capture demand dynamics. We introduce Constrained K-Means Clustering (CKMC) and Contiguity Constrained Hierarchical Clustering with Iterative Constraint Enforcement (CCHC-ICE) to generate dynamic clusters based on predicted demand and geographical proximity, tailored to user-defined operational constraints. Evaluations of European and Taiwanese case studies demonstrate that the proposed methods outperform traditional time series approaches in both accuracy and computational efficiency. Clustering results demonstrate that the incorporation of distributional predictions effectively addresses demand uncertainties, improving the quality of operational insights. Additionally, a simulation study demonstrates the practical value of short-term demand predictions for proactive strategies, such as idle fleet rebalancing, significantly enhancing delivery efficiency. By addressing demand uncertainties and operational constraints, our predict-then-cluster framework provides actionable insights for optimizing real-time operations. The approach is adaptable to other on-demand platform-based city logistics and passenger mobility services, promoting sustainable and efficient urban operations.

cs.CY↗

arXiv2025

Real-Time Integrated Dispatching and Idle Fleet Steering with Deep Reinforcement Learning for A Meal Delivery Platform

To achieve high service quality and profitability, meal delivery platforms like Uber Eats and Grubhub must strategically operate their fleets to ensure timely deliveries for current orders while mitigating the consequential impacts of suboptimal decisions that leads to courier understaffing in the future. This study set out to solve the real-time order dispatching and idle courier steering problems for a meal delivery platform by proposing a reinforcement learning (RL)-based strategic dual-control framework. To address the inherent sequential nature of these problems, we model both order dispatching and courier steering as Markov Decision Processes. Trained via a deep reinforcement learning (DRL) framework, we obtain strategic policies by leveraging the explicitly predicted demands as part of the inputs. In our dual-control framework, the dispatching and steering policies are iteratively trained in an integrated manner. These forward-looking policies can be executed in real-time and provide decisions while jointly considering the impacts on local and network levels. To enhance dispatching fairness, we propose convolutional deep Q networks to construct fair courier embeddings. To simultaneously rebalance the supply and demand within the service network, we propose to utilize mean-field approximated supply-demand knowledge to reallocate idle couriers at the local level. Utilizing the policies generated by the RL-based strategic dual-control framework, we find the delivery efficiency and fairness of workload distribution among couriers have been improved, and under-supplied conditions have been alleviated within the service network. Our study sheds light on designing an RL-based framework to enable forward-looking real-time operations for meal delivery platforms and other on-demand services.

eess.SY↗

arXiv2025

Designing a Robust and Cost-Efficient Electrified Bus Network with Sparse Energy Consumption Data

This paper addresses the challenges of charging infrastructure design (CID) for electrified public transport networks using Battery Electric Buses (BEBs) under conditions of sparse energy consumption data. Accurate energy consumption estimation is critical for cost-effective and reliable electrification but often requires costly field experiments, resulting in limited data. To address this issue, we propose two mathematical models designed to handle uncertainty and data sparsity in energy consumption. The first is a robust optimization model with box uncertainty, addressing variability in energy consumption. The second is a data-driven distributionally robust optimization model that leverages observed data to provide more flexible and informed solutions. To evaluate these models, we apply them to the Rotterdam bus network. Our analysis reveals three key insights: (1) Ignoring variations in energy consumption can result in operational unreliability, with up to 55\% of scenarios leading to infeasible trips. (2) Designing infrastructure based on worst-case energy consumption increases costs by 67\% compared to using average estimates. (3) The data-driven distributionally robust optimization model reduces costs by 28\% compared to the box uncertainty model while maintaining reliability, especially in scenarios where extreme energy consumption values are rare and data exhibit skewness. In addition to cost savings, this approach provides robust protection against uncertainty, ensuring reliable operation under diverse conditions.

math.OC↗