Clustered vehicle routing problems (CluVRPs) represent a complex class of combinatorial optimization problems with significant real-world relevance. They extend classic VRPs by introducing pre-specified customer clusters and requiring effective routing both between clusters and within each cluster. While numerous deep learning approaches have been developed to address the standard VRP, research on CluVRPs remains relatively limited, presenting opportunities and challenges for advancing solutions to more practical VRPs with cluster-related constraints. This paper offers a deep reinforcement learning (DRL) approach to solving CluVRPs. We propose a cluster-aware attention module in the encoder, along with inter-cluster and intra-cluster decoders to specialize the constructive policies within and between clusters. Symmetrical data augmentation is adopted in the training to improve the performance. Empirical results in different CluVRP variants manifest that the DRL method outperforms existing approaches, consistently offering advantages for various instances.

Efficient matching in ride-hailing and ride-pooling services depends not only on how matches are constructed, but also on when the platform triggers a matching operation. Many systems use batched matching with a fixed time interval to accumulate requests before matching, which increases the candidate set but cannot adapt to real time supply-demand fluctuations and may induce unnecessary waiting. This paper proposes a reinforcement learning approach that learns when to trigger matching based on current system conditions. We formulate the timing problem as a finite-horizon Markov decision process and train the policy using the Proximal Policy Optimization algorithm. To address sparse and delayed feedback, we introduce a finite-horizon, potential-based reward shaping scheme that preserves the optimal policy while densifying the learning signal; the same framework applies to both ride-hailing and ride-pooling, where detour delay is incorporated into the reward for pooling. Using a data-driven simulator calibrated on NYC trip records, the learned policy adapts matching timing decisions to the current state of waiting requests and available drivers and outperforms fixed-interval, rule-based dynamic, and first-dispatch baselines. It reduces total waiting time by 3.1% in ride-hailing and 20.1% in ride-pooling, and detour delay by 36.1% in pooling, while maintaining short matching times.

Electric buses (EBs) play a crucial role in achieving global greenhouse gas emission targets. However, efficiently operating an electric bus fleet (EBF) requires a comprehensive approach that considers both mobility and energy systems, particularly when implementing opportunity charging strategies. Existing literature and many real-life implementations often focus on only one of these systems, oversimplifying the other, which can lead to inefficiencies, operational challenges, or even unfeasible implementations. To fill this gap, we propose a framework to assess the impact of bus opportunity charging strategies on the power grid by integrating a traffic simulation model (SUMO) and a power grid simulation model (Gaia). SUMO evaluates the energy consumption and charging needs of the EBs, while Gaia assesses the impact of the transformer load in the distribution grid. The integrated method is applied to Rotterdam’s bus line 36 to demonstrate the practicality of this approach. Results indicate that designing an electric bus route with opportunity charging is feasible only when both mobility and energy systems are carefully coordinated.

Existing activity-based and agent-based simulations alone often failed to capture the interaction between individual activity scheduling and detailed urban traffic dynamics. ActivitySim provides a representation of individual activity schedulings but often lacks detailed traffic dynamics, whereas MATSim can capture detailed interactions between travellers and mobility systems but often overlooks several decision-making factors, such as activity scheduling shift, household interactions and land-use influences. To address these limitations, this paper presents an Activity- and Agent-based Co-simulation framework that integrates ActivitySim and MATSim, both of which are open-source software popularly adopted in each research community. ActivitySim generates individual activity schedules and location choices, which serve as synthetic travel demand input for MATSim. MATSim then simulates detailed mobility interactions, with its outputs aggregated into zonal level-of-service matrices and fed back to ActivitySim for iterative scheduling adjustments. The feedback loop bridges the strengths of both models and is applied to the MRDH (Rotterdam-The Hague Metropolitan) region in the Netherlands. The initial MRDH model for the base-year reference scenario demonstrates that the proposed co-simulation framework effectively replicates existing mobility patterns, paving the way for fine-grained intervention evaluations like ride-hailing services in the future.

The matching radius, defined as the maximum pick-up distance within which waiting riders and idle drivers can be matched, is a critical variable in ride-hailing systems. Optimizing the matching radius can significantly enhance system performance, but determining its optimal value is challenging due to the dynamic nature of ride-hailing environments. The matching radius should adapt to spatial and temporal variations, as well as to real-time fluctuations in supply and demand. To address this challenge, this paper proposes a dual-reply-buffer deep reinforcement learning method for dynamic matching radius optimization. By modeling the matching radius optimization problem as a Markov decision process, the method trains a policy network to adaptively adjust the matching radius in response to changing conditions in the ride-hailing system, thereby improving efficiency and service quality. We validate our method using real-world ride-hailing data from Austin, Texas. Experimental results show that the proposed method outperforms baseline approaches, achieving higher matching rates, shorter average pick-up distances, and better driver utilization across different scenarios.

Demand prediction is essential for effective management of Mobility-on-Demand (MoD) systems, as accurate forecasts enable better resource allocation, reduced wait times, and improved user satisfaction. Beyond that, probabilistic prediction methods that explicitly account for uncertainty are particularly valuable, as it allows decision-makers to assess risk and make robust plans under uncertain operational environments. However, most existing approaches focus on point predictions, which fail to capture the full spectrum of possible future outcomes. For probabilistic prediction, many methods typically rely on strong parametric distributional assumptions that may not accurately reflect the complex real-world environments. Nonparametric methods proposed in the literature, although promising, often suffer from high computational costs and model complexity, limiting their practical applicability. To overcome these challenges, we propose the Spatial-Temporal Graph Convolutional Network Variational Autoencoder (STGCN-VAE), a novel deep learning framework designed for uncertainty-aware probabilistic travel demand prediction in MoD services. The STGCN-VAE effectively captures complex spatial-temporal dependencies and inherent uncertainties in MoD demand data, generating diverse and realistic future demand scenarios and constructing comprehensive demand distributions. Specifically, the proposed framework integrates three key components: a Spatial-Temporal Graph Convolutional Network (STGCN) to learn complex spatial-temporal dependencies, a Variational Autoencoder (VAE) to compress these patterns into a latent space, and a Kernel Density Estimation (KDE) module to accurately construct probabilistic demand distributions and quantify uncertainties. Experiments on four different real-world MoD datasets including both rideshare and bikeshare services across different cities demonstrate that STGCN-VAE consistently outperforms state-of-the-art baselines in both point and probabilistic prediction, highlighting its robustness and broad transferability across service modes and urban contexts.

Ride-pooling has the potential to offer a sustainable solution for urban mobility by reducing vehicle use and emissions through shared trips. However, its adoption remains limited due to poor matching performance. Many requests fail to form feasible pools, and even successful matches often involve long detours or minimal cost savings. These inefficiencies largely arise from fragmented market structures: most operators act independently, restricting matching to their own request pools and limiting the formation of beneficial coalitions. Aggregation platforms improve efficiency by integrating regional operators through unified dispatch systems, but raise concerns over long-term stability. Differences in operator cost structures and market shares may incentivize deviation, at the same time, passengers may reject assigned payments if more attractive alternatives exist. To address these challenges, we propose a multi-level coalition formation game that jointly models operator and passenger collaboration. At the upper level, operators play a non-cooperative game to decide coalition partners. At the lower level, passengers are grouped into shared trips through a cooperative game that ensures individually rational payments. The two layers are coupled via constraint propagation, forming a unified decision-making process. We evaluate our framework using real-world data from three Chinese regions—Chengdu, Haikou, and the Ningxia Hui Autonomous Region—chosen to reflect diverse urban and regional contexts. Compared to independent operations, our approach increases vehicle occupancy by 14%–28%, reduces total costs by 10%–15%, and shortens average travel distances by 4%–5%. The system maintains stable coalition structures with operator deviation rates below 6.81% and near-zero passenger deviation rates.

Artificial Intelligence (AI) agents capable of autonomous learning and independent decision-making hold great promise for addressing complex challenges across various critical infrastructure domains, including transportation, energy systems, and manufacturing. However, the surge in the design and deployment of AI systems, driven by various stakeholders with distinct and unaligned objectives, introduces a crucial challenge: How can uncoordinated AI systems coexist and evolve harmoniously in shared environments without creating chaos or compromising safety? To address this, we advocate for a fundamental rethinking of existing multi-agent frameworks, such as multi-agent systems and game theory, which are largely limited to predefined rules and static objective structures. We posit that AI agents should be empowered to adjust their objectives dynamically, make compromises, form coalitions, and safely compete or cooperate through evolving relationships and social feedback. Through two case studies in critical infrastructure applications, we call for a shift toward the emergent, self-organizing, and context-aware nature of these multi-agentic AI systems.

This paper studies a same-day crowd-sourced delivery setting where in-store customers deliver online orders on their way home. This environment is dynamic and uncertain, characterized by fluctuating numbers of in-store customers and online orders throughout the day, and unpredictable customer decisions to accept or reject delivery tasks. To address these challenges, we develop a two-stage event-driven dynamic matching framework. The first stage leverages short-term predictions about future arrivals of in-store customers and online orders, allowing us to postpone matching decisions for certain drivers and orders, thus optimizing immediate outcomes to maximize order satisfaction over a future time interval. In response to these initial outcomes, the second stage computes the probability of in-store customers accepting matched orders and introduces two compensation models. These models are designed to tailor compensation for each customer, aiming to minimize expected delivery costs at the current decision-making point. Experimental results demonstrate that our framework reduces delivery costs by approximately 15% compared to baseline methods, highlighting its potential to improve the efficiency of crowd-sourced delivery systems in a constantly changing market.

Crowd-Sourced Delivery Systems (CDS) depend on occasional drivers to deliver parcels directly to online customers. These freelance drivers have the flexibility to accept or reject orders from the platform, leading to a stochastic and often unstable matching process for delivery assignments. This instability results in frequent rematching, delayed deliveries, decreased customer satisfaction, and increased operational costs, all highlighting the critical need for improved matching stability within CDS. While traditional stable matching theory provides a foundation, it primarily addresses static and deterministic scenarios, making it less effective in the dynamic and unpredictable environments typical of CDS. Addressing this gap, this study extends the classic Gale–Shapley (GS) stable matching algorithm by incorporating tailored compensations for drivers, incentivizing them to accept assigned orders and thus improving the stability of matchings, even with the inherent uncertainties of driver acceptance. We prove that the proposed mechanism can generate reinforced stable matching results based on tailored compensation values. Also, our numerical study shows that this reinforced stable matching approach significantly outperforms traditional methods in terms of both matching stability and cost-effectiveness. It reduces the order rejection rate to as low as 1% and cuts operational costs by up to 18%.

MUDE stands for Modelling, Uncertainty and Data for Engineers, a required module in the MSc programs from the faculty of Civil Engineering and Geosciences at Delft University of Technology in the Netherlands.

The current version of the MUDE Textbook can be found at mude.citg.tudelft.nl/book and the most recent "complete" version is mude.citg.tudelft.nl/book/2024. Additional information about the book and its contents can be found on the Credits Page from 2024; technical information about the book and its source code can be found in the README of the GitHub repository TUDelft-MUDE/book. General information about MUDE can be found at mude.citg.tudelft.nl.

This Zenodo record archives the HTML files and provides a DOI for the MUDE Textbook. In general, the GitHub repository github.com/TUDelft-MUDE/book and book URL mude.citg.tudelft.nl/book should be used as primary links for the book, whereas Zenodo is used as an archive and DOI publisher, providing a "permanent" URL. The book is registrered in TU Delft's Research Portal PURE too.

The recommended citation for the MUDE Textbook is provided on the Credits page of the book (link above); the Zenodo recommendation on the side of this page should not be used (neither should the citation in the source code record).

Vehicle proactive guidance strategies are used by ride-hailing platforms to mitigate supply–demand imbalance across regions by directing idle vehicles to high-demand regions before the demands are realized. This article presents a data-driven stochastic optimization framework for computing idle vehicle guidance strategies. The objective is to minimize drivers’ idle travel distance, riders’ wait time, and the oversupply costs (OSCs) and undersupply costs (USCs) of the platform. Specifically, we design a novel neural network that integrates gated recurrent units (GRUs) with mixture density networks (MDNs) to capture the spatial-temporal features of the rider demand distribution.

Crowd-Sourced Delivery Services (CDS) use in-store customers, as crowd-shippers, to deliver online orders directly to other customers. As independent contractors, the crowd-shippers are free to decide whether to accept or reject the online orders assigned by the retailer. High order rejection rates can significantly influence the retailer’s delivery costs due to frequent reassignments and shifting the orders to more expensive professional fleet. To incentivize crowd-shippers to accept the matched orders, in this work, we propose a two-stage optimization framework that integrates bipartite matching with an individual compensation scheme. The first stage of the optimization framework computes the optimal matching between crowd-shippers and online orders to minimize the delivery detours and unassigned orders. Given the matching solutions as inputs, the second stage computes personal compensation for each crowd-shipper based on the characteristic of the matched order and his or her acceptance behavior uncertainty, with the goal of minimizing the expected total delivery cost of the retailer. Numerical experiments are conducted using the survey data to illustrate the performance of the proposed framework and compare it with existing matching and pricing strategies in the literature. Our results show that the proposed framework reduces the delivery cost by up to more than 15% and reduces the crowd-shippers’ rejection rate by an average of 55%.

The unprecedented growth of demand for charging electric vehicles (EVs) calls for novel expansion solutions to today’s charging networks. Riding on the wave of the proliferation of sharing economy, Airbnb-like charger sharing markets open the opportunity to expand the existing charging networks without requiring costly and time-consuming infrastructure investments, yet the successful design of such markets relies on innovations at the interface between game theory, mechanism design, and large scale optimization. In this paper, we propose a price-based iterative double auction for charger sharing markets where charger owners rent out their under-utilized chargers to the charge-needing EV drivers. Charger owners and EV drivers form a two-sided market which is cleared by a price-based double auction. Chargers’ locations, availabilities, and unit time service costs as well as drivers’ time and location preferences are considered in the allocation and scheduling process. The goal is to compute social welfare maximizing schedules which benefit both charger owners and EV drivers and, in turn, ensure the continuous growth of the market. We prove that the proposed double auction is budget balanced and individually rational. In addition, results from our computational study show that the proposed auction achieves on average 94% efficiency compared with that of the optimal solutions and is suitable for a larger day-ahead charger sharing market setting in terms of running time.

In ride-sharing services, travel time uncertainty significantly impacts the quality of matching solutions for both the drivers and the riders. This paper studies a one-to-many ride-sharing matching problem where travel time between locations is uncertain. The goal is to generate robust ride-sharing matching solutions that minimize the total driver detour cost and the number of unmatched riders. To this end, we formulate the ride-sharing matching problem as a robust vehicle routing problem with time window (RVRPTW). To effectively capture the travel time uncertainty, we propose a deep learning-based data-driven approach that can dynamically estimate the uncertainty sets of travel times. Given the NP-hard nature of the optimization problem, we design a hybrid meta-heuristic algorithm that can handle large-scale instances in a time-efficient manner. To evaluate the performance of the proposed method, we conduct a set of numeric experiments based on real traffic data. The results confirm that the proposed approach outperforms the non-data-driven one in several important performance metrics, including a proper balance between robustness and inclusiveness of the matching solution. Specifically, by applying the proposed data-driven approach, the matching solution violation rate can be reduced up to 85.8%, and the valid serving rate can be increased up to 42.3% compared to the non-data-driven benchmark.

To reduce the vehicle relocation rate considering relieving disequilibrium of the supply-demand ratios across regions for car-sharing systems, in this paper, we propose a data-driven optimization framework by integrating the non-parametric learning algorithm and two-stage stochastic programming modeling technique to address the one-way station-based car-sharing relocation problem. In contrast with the most existing work that deals with demand uncertainty using predefined probability distributions, the learning-based framework is capable of handling demand uncertainty by learning the intrinsic pattern from large-scale historical data and computing high quality solutions. To validate the performance of our proposed approach, we conduct a group of numerical experiments based on New York taxicab trip record data set. The experimental results show that our proposed data-driven approach outperforms the parametric approaches and deterministic model in terms of business profit, relocation rate, and value of stochastic solution (VSS). Most significantly, compared with the deterministic approach, the vehicle relocation rates are reduced by approximate 80%, 70% and 40% under small fleet size, medium fleet size and large fleet size, respectively. In addition, the VSS of our approach is more than 3 times higher than the one of Poisson distribution by average.

Freelance drivers in ride-hailing systems may strategically accept or reject ride requests based on their projection of the profitability of the assigned rides. This driver acceptance uncertainty is mainly caused by the flat rate payment and the blind ride acceptance rule adopted by most ride-hailing platforms. As a result, a high driver rejection rate has been observed, causing a negative impact on the service quality and matching efficiency for the ride-hailing systems. In this paper, we propose a pricing mechanism to improve drivers’ average ride acceptance rate by offering personalized payments computed based on the characteristics of individual riders and the estimated acceptance rates of the drivers. Specifically, we model and predict the drivers’ ride acceptance rates through a binary choice model and incorporate it into the stochastic optimization problem for the ride-hailing system. This provides personalized payment for each driver in connection with the characteristics of the assigned ride and the preferences of the drivers. We then evaluate the performance of the proposed pricing mechanism through extensive numerical experiments based on RideAustin trip data from June 2016 to April 2017. The results suggest that our proposed pricing mechanism improves the drivers’ average acceptance rate by an average of 60% compared to some commonly used pricing schemes. It also significantly increases the platform’s expected profit and matching rate. This implies a strong potential for the proposed pricing mechanism to improve service reliability and quality in ride-hailing systems.

Providing high-quality matching between drivers and riders is imperative for sustaining the growth of ride-sharing platforms. A user-focused matching mechanism design plays a key role in terms of ensuring user satisfaction. In this paper, we consider the matching problem in the community ride-sharing setting, where drivers and riders have strong personal preferences over the matched counterparties. Obtaining high-quality solutions that accommodate drivers’ and riders’ preferences in such a setting is particularly challenging as drivers and riders maybe reluctant to share with the platform their personal preferences over their ride-sharing counterparties due to privacy and ethical concerns. To this end, we propose a VOting-based MAtching (VOMA) mechanism to compute near-optimal matching solutions for drivers and riders, while preserving their privacy. The mechanism is a distributed implementation of the simulated annealing meta-heuristic, which computes matching solutions by guiding drivers and riders in the distributed search process using an iterative voting protocol. We evaluate the performance of VOMA using test cases generated based on New York taxi data sets. The experiment results show that the proposed matching mechanism achieves on average 90.9% efficiency compared with optimal solutions. We also show that VOMA improves the vehicle miles traveled (VMT) savings by up to 35% compared to an alternative voting-based greedy matching mechanism. System scalability and other practical issues regarding the implementation of such a matching mechanism in community ride-sharing platforms are also discussed.

This paper proposes an integrated dispatching framework for matching drivers with riders in ride-hailing systems. The goal is to compute matching solutions that maximize social welfare and benefit both sides of the market, such that the sustainable growth of the ride-hailing system is ensured. The proposed framework integrates data-driven proactive guidance strategies with batched matching optimization to increase social welfare, improve matching rate and reduce rider wait time. Proactive guidance strategies are computed by leveraging short-term demand forecasts based on historical data. Taken the resulting guidance strategies as inputs, the batched matching algorithm computes optimal bipartite matching between drivers and riders in a batch. Using New York City taxi data from 2016 March 1st to March 31st as input, we conduct a numerical study to evaluate the performance of the proposed framework and compare it with existing approaches in the literature. Our results show that the proposed framework improves social welfare for up to 50%. It also increases the matching rate by an average of 20% and reduces the average rider wait time by over 15%. This implies a strong potential for the proposed dispatching framework to improve service quality in ride-hailing systems.

In this paper, we study a one-to-one matching ride-sharing problem to save the travellers' total travel time considering travel time uncertainty. Unlike the existing work where the uncertainty set is assumed to be known or roughly estimated, in this work, we propose a learning-based robust optimization framework to handle the issue properly. Specifically, we assume the travel time varies in an uncertainty set which is predicted by a machine learning approach- ARIMA using travel time historical data, the predicted uncertainty set then serves as the input parameter for the robust optimization model. To evaluate the proposed approach, we conduct a group of numerical experiments based on New York taxi trip record data sets. The results show that our proposed data-driven robust optimization approach outperforms the robust optimization model with a given uncertainty set in terms of total travel time savings. Further, the proposed approach can improve the travel time savings up to 112.8%, and 34% by average. Most importantly, our proposed approach is capable of handling the uncertainty in a more effective way when the uncertainty degrees become high.