Electric vehicle charging faces challenges of high infrastructure costs and low utilization. Shared charging among fleet operators offers a sustainable alternative. This study formulates a collaborative scheduling problem in which two companies coordinate charging to minimize their individual costs while achieving efficient and equitable outcomes. A bi-objective optimization framework is developed, proposing the Balanced Bounding Box Method (B3M) to generate a representative subset of globally optimal solutions with substantially reduced computational effort. Cooperative bargaining is then applied to derive an actionable final decision from the efficient frontier. Numerical results show that this framework maintains frontier integrity while cutting computation time. Beyond improving decision efficiency, the study offers insights into how transparent and equitable solution selection can sustain long-term collaboration among operators. The framework provides practical guidance to improve charger utilization and reduce system costs, supporting more sustainable use of existing infrastructure.

The growth of e-commerce has led to a significant rise in daily parcel deliveries, placing increasing pressure on logistics services. Although various delivery options, including home and out-of-home delivery, are offered to enhance customer availability, uncertainty in customer preferences regarding delivery locations and time slots further complicates delivery operations. In this paper, we introduce a last-mile delivery problem with flexible delivery options under stochastic customer behavior, formulated as a two-stage stochastic programming model. The novelty of our model lies in the integration of comprehensive delivery options, including various locations and time slots, with pricing decisions. Furthermore, we incorporate heterogeneous customer preferences across mixed delivery options. To efficiently solve the problem, we develop a hybrid adaptive large neighborhood search (h-ALNS) heuristic based on scenario simulations. Extensive numerical experiments demonstrate the advantages of the mixed delivery strategy and confirm the effectiveness of the proposed algorithm. Our numerical analysis offers important managerial insights for optimizing last-mile delivery assortment and pricing, particularly in addressing customer uncertainty.

This paper proposes a modular vehicle system for passenger-freight integration along a bidirectional transit corridor. The system uses homogeneous units that can be coupled into vehicles and assigned to either passenger or freight service. Freight is carried by dedicated units, with loading and unloading coordinated with docking and undocking and separated from passenger boarding and alighting. To better respond to uncertain passenger demand and integrate freight transport, vehicles can be reconfigured at intermediate stations, where they can also depart and terminate. We jointly optimize departure-specific service routes, timetables, vehicle compositions, unit schedules, and passenger-freight demand assignments, with unit reuse constrained by explicit docking and undocking times. These decisions are modeled on a space-time-state network and formulated as a stochastic mixed-integer program that minimizes unit deployment costs, passenger waiting costs, and penalties for unmet freight demand. Passenger demand uncertainty is addressed using linearized chance constraints. To solve the problem, we develop an exact Benders decomposition algorithm with valid inequalities and a warm-start strategy, together with a tailored decomposition-based heuristic for larger instances. Computational experiments on instances generated from representative transit corridors in Gothenburg demonstrate the effectiveness of the Benders algorithm for small- and medium-sized instances and the scalability of the heuristic for larger problems. Sensitivity analyses highlight the value of accounting for passenger demand uncertainty and the effects of temporal overlap between passenger and freight demand. Comparisons with benchmark transit systems further demonstrate the operational advantages of the proposed modular integrated system.

Public electric vehicle (EV) charging infrastructure has expanded rapidly, yet utilization across charging stations remains uneven and often inefficient. Existing operator-determined pricing schemes offer limited flexibility to coordinate heterogeneous user demand within constrained capacity. This study proposes a user-driven pricing and scheduling framework for public EV charging. Users submit advance bids specifying acceptable time slots, bid prices, and quantity bounds. Based on these bids, the charging operator determines prices and charging slot assignments. After observing the outcomes, users decide whether to accept the resulting prices and allocations. The operator's decision problem incorporates profit objectives, user participation requirements, and capacity constraints across charging levels and time slots. The framework captures a three-stage interaction involving user bidding, operator decisions, and user acceptance. Numerical case studies reveal trade-offs among user acceptance, operator revenue, and charging capacity utilization under different charging levels. The findings provide practical guidance and insights into designing flexible pricing schemes that better accommodate heterogeneous user preferences while improving system efficiency.

Shared e-scooter systems provide a flexible and sustainable solution for short urban trips. However, low operational efficiency often results in long idle periods, during which e-scooters waste energy without providing service. This study investigates how excessive inter-operator competition is associated with such inefficiencies. Using high-resolution operational data from Parma, Italy, where two operators coexisted, we reconstruct full lifecycles and introduce a novel entropy-based competition index. We use an interpretable machine learning framework to assess how competition factors relate to idle energy consumption. The results show that competition-related patterns are associated with higher idle energy consumption, with relocation-based rivalry being most informative for the non-dominant operator. For the weaker operator, over half of battery discharge occurs while idle, with competition accounting for about 70% of the total SHAP importance. These findings call for demand-responsive fleet management and context-sensitive regulation to reduce unnecessary competition and support sustainable micromobility.

Learning-based methods for routing have gained significant attention in recent years, both in single-objective and multi-objective contexts. Yet, existing methods are unsuitable for routing on multigraphs, which feature multiple edges with distinct attributes between node pairs, despite their strong relevance in real-world scenarios. In this paper, we propose two graph neural network-based methods to address multi-objective routing on multigraphs. Our first approach operates directly on the multigraph by autoregressively selecting edges until a tour is completed. The second model, which is more scalable, first simplifies the multigraph via a learned pruning strategy and then performs autoregressive routing on the resulting simple graph. We evaluate both models empirically, across a wide range of problems and graph distributions, and demonstrate their competitive performance compared to strong heuristics and neural baselines.

The paper addresses safety concerns associated with electric micromobility vehicles, particularly e-scooters, which accounted for 1% of trips but nearly 4% of traffic accidents in Sweden, 2019. To mitigate potential risks from increased micromobility usage, we developed robust AI algorithms to detect drunk driving. Based upon our own developed Virtual Reality simulations, involving 30 participants, we utilized hand-tracking technology to enhance realism and reduce nausea. Results indicated that LSTM (Long Short-Term Memory network) model successfully identified 86% of drunk riders. A Transformer method was tested with further aggregated data where we have achieved 100% precise identification of drunk drivers. LSTM methods that we tested in the project have shown significant improvement for detecting drunk drivers, compared with machine learning methods e.g. Random Forest and Recurrent Neural Networks (RNNs). This research contributes to Vision Zero, zero fatalities and severe injuries from road traffic in the Nordics by 2050, by providing robust sensing algorithm for identifying e-scooter misuse, with future work focusing on refining models, expanding data collection, and integrating advanced neural networks. Our findings offer valuable insights for stakeholders like shared e-scooter operators and urban transport administrations to enhance urban mobility safety.

Predicting future trajectories is crucial for autonomous vehicles, as accurate predictions enhance safety and inform subsequent decision-making and planning modules. This is however a challenging task due to the complex interactions between surrounding vehicles. Existing methods struggled to extract deep representations and often overlook spatial dependence. To address this problem, this paper introduces GIVA, an interaction-aware trajectory prediction method based on the Gated Recurrent Unit (GRU)-Improved Visual Geometry Group (VGG)-Attention Mechanism model. GIVA first encodes the historical trajectories of the target vehicle and its surrounding vehicles using a GRU Encoder. Next, an Interaction Module, which combines the Improved VGG Pooling Module and the Attention Mechanism Pooling Module, effectively captures spatial interaction features between vehicles. The Improved VGG Pooling Module extracts more detailed and effective interaction information, while the Attention Mechanism Pooling Module emphasizes the importance of surrounding vehicles for the target vehicle's future trajectory. Lastly, the dynamic encoding feature of the target vehicle and the fused interaction feature are concatenated and input into a GRU Decoder to generate the future trajectory. Experiments on the public Next Generation Simulation (NGSIM) dataset showcase the effectiveness of GIVA compared to existing prediction approaches, demonstrating its potential for improving autonomous vehicle performance.

There is a rise in the need for efficient battery charging methods due to the high penetration of electromobility solutions. Battery swapping, a technique in which fully or partially depleted batteries are exchanged and then transported to a central facility for charging, introduces a unique scheduling problem. For scenarios involving a large number of batteries, commercial solvers and existing methods do not yield optimal or near-optimal solutions in a reasonable time due to high computational complexity. Our study presents a novel approach that combines variable layering with Lagrangian decomposition. We develop a new, tighter time-block reformulation for one of the Lagrangian sub-problems, enhancing convergence rates when used with our partial-variable fixing Lagrangian heuristic. We also propose an ergodic-iterate-based local search method to further improve the solution quality. Lower bounds are improved by learning the relation between Lagrangian multipliers and electricity cost. Our extensive benchmarks show superior computational performance against commercial solvers. We achieved, on average, a 43 state-of-the-art methods. In 71 solutions (optimality gap less than 6 10 feasibility using incumbent methods. The developed exact method aims to support future research on charging scheduling, especially important for micromobility industry, vehicle-to-grid (V2G) applications, and second-life utilization of batteries. Furthermore, the developed polyhedral insights can be useful in other scheduling problems with a common underlying mathematical structure.

Electric mobility faces several challenges, most notably the high cost of infrastructure development and the underutilization of charging stations. The concept of shared charging offers a promising solution. The paper explores sustainable urban logistics through horizontal collaboration between two fleet operators and addresses a scheduling problem for the shared use of charging stations. To tackle this, the study formulates a collaborative scheduling problem as a bi-objective nonlinear integer programming model, in which each company aims to minimize its own costs, creating inherent conflicts that require trade-offs. The Balanced Bounding Box Methods (B3Ms) are introduced in order to efficiently derive the efficient frontier, identifying a reduced set of representative solutions. These methods enhance computational efficiency by selectively disregarding closely positioned and competing solutions, preserving the diversity and representativeness of the solutions over the efficient frontier. To determine the final solution and ensure balanced collaboration, cooperative bargaining methods are applied. Numerical case studies demonstrate the viability and scalability of the developed methods, showing that the B3Ms can significantly reduce computational time while maintaining the integrity of the frontier. These methods, along with cooperative bargaining, provide an effective framework for solving various bi-objective optimization problems, extending beyond the collaborative scheduling problem presented here.

OBJECTIVES:Dockless electric scooters (e-scooters) have emerged as a popular mode of short-distance transportation in urban environments, offering convenience and flexibility in rental and usage. However, users often engage in unsafe behaviors while riding, posing risks to themselves and others. In this study, we aim to identify unsafe riding behaviors through analysis of riding trajectories, to reduce safety incidents and promote safer e-scooter usage. METHODS:This study explores the classification of single and tandem e-scooter riding behaviors using a data-driven approach. Leveraging trajectory data from Gothenburg, Sweden, collected over 11 days in November 2023; we utilize Long Short-Term Memory (LSTM) neural networks to analyze dynamic temporal features. RESULTS:The LSTM model demonstrated significant performance advantages over both RNN and Random Forest models, achieving an accuracy of 92.65%, precision of 91.69%, recall of 93.85%, F1 score of 95.56%, and an AUC of 0.9169. CONCLUSIONS:Additionally, optimizing the input sequence length to 240 s of continuous trajectory features balanced computational efficiency with prediction accuracy and stability. Dynamic trajectory features such as acceleration, turning angle, speed, and start SOC play pivotal roles in differentiating riding patterns. The proposed method can assist city authorities and e-scooter operators in real-time risk detection, operational monitoring, and targeted safety interventions, contributing to safer shared micromobility systems.

This paper reviews the current progress in applying machine learning (ML) tools to solve NP-hard combinatorial optimization problems, with a focus on routing problems such as the traveling salesman problem (TSP) and the vehicle routing problem (VRP). Due to the inherent complexity of these problems, exact algorithms often require excessive computational time to find optimal solutions, while heuristics can only provide approximate solutions without guaranteeing optimality. With the recent success of machine learning models, there is a growing trend in proposing and implementing diverse ML techniques to enhance the resolution of these challenging routing problems. We propose a taxonomy categorizing ML-based routing methods into construction-based and improvement-based approaches, highlighting their applicability to various problem characteristics. This review aims to integrate traditional OR methods with state-of-the-art ML techniques, providing a structured framework to guide future research and address emerging VRP variants.

Most of the recent studies tackling routing problems like the Traveling Salesman Problem (TSP) with machine learning use a transformer or Graph Neural Network (GNN) based encoder architecture. However, many of them apply these encoders naively by allowing them to aggregate information over the whole TSP instances. We, on the other hand, propose a data preprocessing method that allows the encoders to focus on the most relevant parts of the TSP instances only. In particular, we propose graph sparsification for TSP graph representations passed to GNNs and attention masking for TSP instances passed to transformers where the masks correspond to the adjacency matrices of the sparse TSP graph representations. Furthermore, we propose ensembles of different sparsification levels allowing models to focus on the most promising parts while also allowing information flow between all nodes of a TSP instance. In the experimental studies, we show that for GNNs appropriate sparsification and ensembles of different sparsification levels lead to substantial performance increases of the overall architecture. We also design a new, state-of-the-art transformer encoder with ensembles of attention masking. These transformers increase model performance from a gap of $0.16\%$ to $0.10\%$ for TSP instances of size 100 and from $0.02\%$ to $0.00\%$ for TSP instances of size 50.

The deepening process of urbanization poses formidable challenges to the current transportation carrying capacity. The utilization of near-ground space (NGS) and urban air mobility (UAM) greatly enhance spatial dimensions and traffic flexibility of the transportation system. However, the current limited sensing capability falls short in meeting the real-time collaborative environmental sensing and intelligent control requirements of aerial transportation. Integrated sensing and communication (ISAC) combines the sensing system of UAM with 6G communication technologies, enabling them to collaborate and achieve data sensing, transmission, processing, and decision control. The use of artificial intelligence-generated content (AIGC) facilitates real-time data fusion and decision-making, adapting to dynamic and unpredictable environments. In this paper, we first model and analyze the traffic flow in three-dimensional space, achieving knowledge embedding based on artificial potential energy field theory. Next, we design a multimodal data fusion neural network structure, which utilizes the Variational Autoencoder (VAE) to generatively achieve feature fusion and compression. Finally, we construct a UAM digital simulation platform using AirSim, which generates considerable aerial data. The simulation results demonstrate that our proposed approach achieves a feature recognition accuracy of 90.38%. The total latency is below 0.6ms, which exhibits high real-time performance.

In this paper, we develop a profit-sharing-based optimal routing mechanism to incentivize horizontal collaboration among urban goods distributors. The core of this mechanism is based on exchanging goods at meet points, which is optimally planned en route. We propose a Collaborative Electric Vehicle Routing Problem with Meet Points (CoEVRPMP) considering constraints such as time windows, opportunity charging, and meet-point synchronization. The proposed CoEVRPMP is formulated as a mixed-integer nonlinear programming model. We present an exact method via branching and a matheuristic that combines adaptive large neighborhood search with linear programming. The viability and scalability of the collaborative method are demonstrated through numerical case studies, including a real-world case and a large-scale experiment with up to 500 customers. The findings underscore the significance of horizontal collaboration among delivery companies in attaining both higher individual profits and lower total costs. Moreover, collaboration helps to reduce the environmental footprint by decreasing travel distance.

Truck platooning has gained increasing attention due to the benefits in energy and operation efficiency in freight transportation. One significant challenge for deploying truck platoons is the safe and efficient interaction with surrounding traffic, especially at freeway discontinuities where mandatory lane changes usually lead to the decoupling of truck platoons. This study proposes a cooperative truck platoon lane-changing model (CTPLC) to prevent the decoupling of truck platoons in a mixed traffic environment. Specifically, a two-step control strategy is presented, where vehicles in the target lane firstly cooperatively adjust speeds to create an appropriate gap for a truck platoon, and then trucks within the truck platoon conduct lane change sequentially. The cooperative speed profiles are generated by solving an optimization problem considering the lane-changing influence and energy consumption. Based on that, a two-dimensional nonlinear model predictive control (MPC) algorithm is employed to generate vehicular acceleration and steering angle for each truck. A series of numerical simulation experiments were conducted to validate the proposed strategy. As shown by the results, our proposed method truck platoon could conduct a lane change in a traffic-efficient and safe manner, and meanwhile, our method was more energy-efficient than a benchmark strategy.

Connected and Automated Vehicles (CAVs) are characterized by diverse communication attributes, embodying the trajectory of future automotive progress. Meanwhile, the transportation system will be in a mixed stage of CAVs and Human-Driven Vehicles (HDVs) for a long time. The study of communication capacity and strategies for mixed traffic systems is of great significance for the popularization of CAVs and the deployment of communication infrastructures. However, current research mainly focuses on the communication capacity analysis in the scenario with full penetration of CAVs, while the influence caused by HDVs on Vehicle-to-Vehicle (V2V) communications and the capacity analysis of connected vehicles in mixed traffic systems need further understanding. To address this issue, this paper considers the shadow fading caused by HDVs on wireless communication links and analyzes the communication capacity in mixed traffic systems. Specifically, we first synthesize the V2V and Vehicle-to-Infrastructure (V2I) communication modes to propose an analytical framework for vehicular network communication capacity in mixed traffic. Then, a predictive communication strategy is also provided that caches the required content at infrastructure in advance according to predicted vehicle trajectories to improve the capacity of vehicular networks in mixed traffic. Furthermore, the derived capacity analysis theorems reveal the communication capacity of mixed traffic is closely related to the CAV penetration rate, the vehicle arrival rate, and the infrastructure deployment interval. Simulation results prove the effectiveness of the proposed framework, and the proposed predictive communication strategy can increase the mixed traffic communication capacity compared to existing communication strategies. The theoretical results herein can guide the implementation of vehicular network applications and the design of communication strategies in mixed traffic systems.

Machine learning based approaches to solve the Travelling Salesman Problem (TSP) have achieved astonishing performance in the last years. A large number of works proposing such approaches use a type of encoder in their underlying frameworks to learn vector representations of the given problem. Since TSP can easily be interpreted as a graph theoretic problem, Graph Neural Networks (GNNs) have been a popular encoder architecture for this task. However, most papers ignore that GNNs are not designed to operate on complete graph instances like the TSP. We therefore propose two data preprocessing methods for GNNs to make the TSP instances sparse: a nearest neighbor based heuristic and a method based on minimum spanning tree called 1-Tree. We show that making the underlying TSP instances sparse by deleting unpromising edges in the preprocessing step improves the performance of the overall learning framework while, at the same time, the runtime decreases. In particular, the proposed method achieves an up to $\times 2 $ performance improvement w.r.t. the optimality gap and a decrease in runtime by 10\% during training and validation, when applied to GCNs. For GATs, the improvements in regards of runtime and optimality gap are even bigger when sparsifying the data first: We report up to $\times 22$ improvements for the optimality gap while reducing the runtime by 50\%.