ABSTRACT. Max-pressure (MP) control has proven effective at stabilizing network queues and improving traffic throughput in large-scale urban road networks. However, conventional MP controllers based on connected vehicle (CV) data face two critical limitations: network stability diminishes when connected vehicle (CV) penetration rates are low, and significant privacy concerns arise when utilizing individual vehicle data. To address these challenges, this paper proposes a novel Private-MP controller that fuses data from both fixed-location detectors and CVs in an architecture of mobile edge computing. To fully safeguard CV privacy, including macro-route information and micro-trajectory information, Private-MP employs a privacy-preserving mechanism that combines homomorphic encryption with an adaptive randomized response strategy. Simulation studies on a network with five intersections showed that despite some increases in average vehicle delay due to privacy protection, Private-MP still ensures a more robust performance on average vehicle delay than CV-based MP in low penetration rate scenarios and outperforms traditional detector-based MP control while improving fairness among connected and non-connected vehicles.

ABSTRACT. Urban traffic congestion remains a critical challenge in modern cities, with traffic signal control systems often struggling to manage congestion during peak travel times. Perimeter control of a Protected Network (PN) has emerged as a potential solution to reducing gridlock in urban networks. This paper proposes a novel auction-based mechanism for green time allocation at signalized intersections, for effective perimeter control application. Utilising a Sealed Bid, Second Price auction framework, our approach combines real-time traffic monitoring with market-inspired mechanisms to regulate vehicle inflows into PN areas. Unlike existing methods that focus primarily on gated links, our system allocates budgets to individual traffic movements, providing greater flexibility in managing multi-directional flows. We evaluate the proposed mechanism using a test case intersection with a single controlled inflow, comparing it against a volume-based fixed-time approach. The results demonstrate that our auction-based method controls flows into the PN with improved accuracy, outperforming the volume-based approach in terms of inflow regulation, queue management and delays. The framework can be applied in real time to any generic intersection, offering a scalable solution for urban traffic management. This work bridges the gap between perimeter control and market-based intersection auctions, providing a pathway for further research on adaptive traffic management systems.

ABSTRACT. The global ride-hailing (RH) industry plays an essential role in multi-modal transportation systems by improving user mobility, particularly as first- and last-mile solutions. While many RH rebalancing studies focus on nominal scenarios with regular demand patterns, it is crucial to consider disruptions that negatively impact operational efficiency. This study examines how RH rebalancing strategies can strengthen the resilience of multi-modal transportation systems against supply-side disruptions. We incorporate RH services into systems where users choose and switch transportation modes based on their preferences, accounting for uncertainties in demand predictions. To address the stochastic supply-demand dynamics, we propose a multi-agent reinforcement learning (MARL) strategy, specifically utilizing a multi-agent deep deterministic policy gradient (MADDPG) approach. The results demonstrate significant improvements in key performance indicators, including user waiting time, resilience metrics, total travel time, and travel distance.

ABSTRACT. Smart traffic systems, like those using well-established methods such as SCOOT, SCATS and TUC, aim to improve traffic flow by dynamically adjusting signal timings based on real-time traffic conditions. Traffic engineers need to understand the objective functions behind traffic signal control to analyze, improve, and optimize network performances. However, different jurisdictions, different operators and competing interests imply that the underlying objective functions governing traffic signal control might not be publicly known with sufficient detail (e.g. to preserve Intellectual Property Rights). A method for discovering these functions is therefore needed, particularly to enable better cooperation among stakeholders. In this work, we train computer models to mimic the decisions made by smart traffic light systems. Using data from a simulated traffic network (with virtual sensors tracking vehicles), we test a variety of supervised models, ranging from simple decision trees to more complex neural networks. Our results show these models can accurately mimic the underlying system's actions, achieving up to 99\% accuracy. This work demonstrates that supervised learning can serve as a powerful tool for uncovering hidden traffic control functions by training models to replicate the system’s decisions. By analyzing these models, we can then infer the key factors influencing signal control, thereby gaining insights into the underlying objective function.

ABSTRACT. Traffic management has traditionally focused on toll-based road pricing. However, road pricing often raises concerns about accessibility and public dissatisfaction, leading to its prohibition in some regions, such as Finland. This study optimises the dynamic allocation of incentives to drivers, encouraging them to reroute onto alternative (potentially longer) paths to achieve greater societal benefit, namely reduced total travel time and total emissions in the transportation network, contributing to climate change mitigation. We employ a multi-agent reinforcement learning approach to dynamically assign incentives to drivers to reduce both total travel time and emissions, with travel times estimated using traffic simulation software. We demonstrate that, with an unlimited budget and an objective of minimising travel time, the incentive scheme reduces total travel time (TTT) by 16\% compared to the dynamic UE. With a budget equivalent to about 11% of the UE total time, a 16% reduction in TTT is achieved. When the goal is to minimise emissions, a 9% reduction in CO2 emissions is observed under an unlimited budget. We demonstrate a critical trade-off: minimising TTT leads to an increase in emissions, while prioritising emission reductions raises TTT. However, with the right combination of weights in the multi-objective function, both TTT and total emissions are improved beyond the baseline.

ABSTRACT. The transition to sustainable mobility not only changes the appearance of the city but can also have an impact on the safety of citizens. If the transition is poorly planned, it can lead to a decline in the safety level of citizens, as the emergency services and the fire brigade may need more time to reach the patient/emergency site. The large number of simultaneous and mutually influencing changes requires a prior digital impact assessment. To digitally analyze the effects of mobility changes on emergency services at an early stage, it is necessary to model precisely the expected arrival times and routes of emergency vehicles. Based on recorded GPS data and publicly available map data, a route choice model is created that realistically models the road sections and routes taken during the trip to the emergency site. The results show that emergency drivers prefer to stay on main roads and try to avoid potential bottlenecks, e.g., single-lane scenarios, without the possibility for overtaking. In addition, the current results, e.g. observed average speeds, of the case study carried out on the basis of two fire stations of the Munich Fire Brigade are listed. The presented model and the given parameters enable decision-makers to make well-founded prior analyses, thus ensuring safety in urban areas.

ABSTRACT. This study explores factors influencing travelers’ willingness to participate in Crowd-sourced Parcel Delivery(CPD), an emerging concept blending passenger and parcel delivery service. To assess the feasibility and potential of crowdshipping, a stated adaptation choice experiment (SACE) was conducted, offering two unlabeled options adapted with the reported trips of respondents, plus the possibility of rejecting the request. A random parameter logit model is employed to capture the variation in preference across individuals, providing insights into the heterogeneity of different types of travelers. The results reveal that socio-demographics, trip characteristics (such as transport modes and the number of trip legs), and CPD attributes (such as detours and monetary incentives) significantly influence CPD acceptance. These findings offer valuable guidance for designers and planners in the initial development of CPD platforms and can help to foster the success and future growth of crowdshipping initiatives.

ABSTRACT. Autonomous shuttles represent one of the most promising innovations in public transport, yet their large-scale deployment still faces significant technological and social challenges, and the impact of this technology to the perceived quality of service is still unclear. This study investigates user perceptions of an autonomous shuttle service operating in Luxembourg, based on a dedicated mobility survey. Two main findings emerge from the analysis. First, results highlight an ongoing transition phase toward the acceptance of this innovative autonomous driving technology. Although curiosity and interest in experiencing the service are evident, concerns about safety and reliability persist. In this context, the presence of an on-board supervisor emerges as a key factor in fostering user trust and improving service acceptability. Second, the survey data collection campaign revealed that the service is predominantly used by elderly individuals and people with reduced mobility, suggesting that autonomous shuttles hold significant potential to improve accessibility for these user groups, and hence can contribute to promote inclusive urban mobility. These insights can guide the future development of autonomous public transport services, supporting the design of solutions more closely aligned with the needs of vulnerable user groups and more widely accepted by the public.

ABSTRACT. The increasing complexity of urban environments has transformed mobility needs, requiring the development of sustainable and technology-driven transportation solutions. Mobility as a Service (MaaS) has emerged as a promising model, integrating multiple mobility services into a single digital platform to enhance accessibility and efficiency. However, the widespread adoption of MaaS depends not only on technological advances but also on psychological factors influencing user acceptance of such a mobility service. Based on the Technology Acceptance Model (TAM), this study proposes and evaluates a theoretical framework to examine key psychological determinants of individuals' willingness to use smartphone applications for travel planning. The research explores how perceived ease of use and perceived usefulness can influence behavioral intention and actual adoption of MaaS solutions. Using Structural Equation Model (SEM), the study investigates the relationships among these psychological dimensions and provides insights into the mechanisms that drive technology acceptance in urban mobility. The findings contribute to a deeper understanding of the psychological barriers and facilitators of MaaS adoption and provide valuable implications for service providers to enhance sustainable mobility solutions.

ABSTRACT. Achieving sustainability objectives necessitates a transformation in passenger mobility behaviour. This paper introduces a Generative AI framework developed by the MUV platform to address the enduring attitude-behaviour gap in sustainable urban mobility. Anchored in Self-Determination Theory, the system utilises behavioural, contextual, and qualitative data to create personalised competitions that enhance intrinsic motivation. The framework features a three-layer architecture and a virtual mobility trainer to support game dynamics, while federated learning and bias audits provide ethical safeguards. The framework is set to be piloted at ISPRA, with a mixed-methods evaluation planned to assess its impact on behaviour and inclusivity. This study presents a replicable model for responsible AI-driven behavioural change in alignment with the European Green Deal.

ABSTRACT. TBD

ABSTRACT. The evolution of 5G New Radio (NR) Vehicle-to-Everything (V2X) communication is opening new horizons for both road and rail transport. Designed to support direct Sidelink (SL) communication between vehicles, infrastructure, and other road users, NR V2X enhances safety and enables time-critical applications such as collision avoidance and intersection coordination. While originally targeted at automotive use cases, NR V2X is now being considered as a key enabler for next-generation train communication systems, offering the potential to support wireless train backbones and consist networks in scenarios where infrastructure-based coverage is limited. This presentation will examine the current limitations of decentralized 5G NR V2X Sidelink scheduling mechanisms, particularly in Mode 2(a), where autonomous resource selection can suffer from issues such as the hidden-node problem. We will explore cooperative scheduling strategies, also referred to by 3GPP as Inter-UE coordination, which aim to improve the reliability of resource allocation in such decentralized scenarios. A candidate implementation of a cooperative scheduling mechanism will be presented, along with preliminary performance evaluation results that illustrate its potential and highlight remaining challenges.

ABSTRACT. This presentation introduces a distributed framework for joint scheduling and multi-hop relaying in 5G NR V2X Sidelink communications. Targeting challenging scenarios such as dense train formations, the proposed approach combines inter-UE coordinated resource allocation with B.A.T.M.A.N.-based routing and a hybrid metric that balances SINR and resource availability. The design emphasizes compatibility with decentralized architectures and builds upon practical extensions of existing sidelink control mechanisms. Simulation results demonstrate superior reliability, spatial reuse, and routing efficiency under realistic channel and topology conditions.

ABSTRACT. TBD