Future Transp., Volume 5, Issue 3 (September 2025) – 16 articles

Efficient detection of road surface defects is vital for timely maintenance and traffic safety. This study introduces a novel AI-powered web framework, TriRoad AI, that integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—for automated detection of potholes and cracks. A user-friendly browser interface was developed to enable real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. Experimental evaluation was conducted using two datasets: one from online sources and another from field-collected images in Ankara, Turkey. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%. The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization. These contributions address current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments. Full article

Climate change, the consequences of which have been more intense than ever in the last few decades, makes the need for sustainable transportation even more imperative. The promotion of public transportation and the discouragement of private car use are among the main priorities of sustainable transport planning in modern urban areas. However, the selection of the most appropriate transport project, apart from significant opportunities, is also accompanied by significant challenges, especially under the demand of compromising—often conflicting—social, environmental, and economic criteria, as well as different stakeholders’ interests. The aim of the present paper is to provide decision analysts and policy-makers with a decision-support tool for the prioritization and optimum selection of public transport projects for an urban area within the framework of sustainability. For this purpose, a comprehensive inventory of criteria for the evaluation of urban public transport systems (alternatives), along with a standardized table with the relevant performance of the most common alternatives (i.e., metro, tram, monorail, and BRT) are provided based on international literature review. A multi-criteria decision-aiding methodology based on TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), allowing for the direct exclusion of an alternative not meeting certain “binding” criteria from further evaluation, thus saving time, effort and cost, taking into account different stakeholders’ interests and preferences, as well as the particularities and special characteristics of the study area, is then proposed and tested through a theoretical case study. Full article

As electric vehicles (EVs) become increasingly integrated into urban mobility, the load on electrical grids increases, prompting innovative energy management strategies. This paper investigates the deployment of vehicle-to-grid (V2G) services at the University of Rome Tor Vergata, leveraging high-resolution floating car data (FCD) to forecast and schedule energy transfers from EVs to the grid. The methodology follows a four-step process: (1) vehicle trip detection, (2) the spatial identification of V2G in the campus, (3) a real-time scheduling algorithm for V2G services, which accommodates EV user mobility requirements and adheres to charging infrastructure constraints, and finally, (4) the predictive modelling of transferred energy using ARIMA and LSTM models. The results demonstrate that substantial energy can be fed back to the campus grid during peak hours, with predictive models, particularly LSTM, offering high accuracy in anticipating transfer volumes. The system aligns energy discharge with campus load profiles while preserving user mobility requirements. The proposed approach shows how campuses can function as microgrids, transforming idle EV capacity into dynamic, decentralised energy storage. This framework offers a scalable model for urban energy optimisation, supporting broader goals of grid resilience and sustainable development. Full article

This study aims to predict the purpose of the use of IC card data in LRT immediately after its opening by means of a questionnaire survey and to understand the changes in the number of commuters to better understand the growth in LRT commuter ridership, which has not been fully clarified in Japan. Furthermore, to assess long-term commuter retention for LRT systems, the analysis revealed the following three points. First, a discriminant analysis based on a national PT survey revealed that commuting and leisure or business activities can be classified with high accuracy. Second, it was found that commuter numbers increased immediately after opening, while the number of leisure or business users decreased in the first few months after opening and then leveled off. Third, the increase in the number of commuters was modeled using a logistic curve, and the annual rate of change in ridership was predicted to be less than 1% in the first three to four years after opening. Full article

This paper explores the potential of public webcams as a source of data for transport research. Eight different open-source object detection models were tested on three publicly accessible webcams located in the city of Brunswick, Germany. Fifteen images at different lighting conditions (bright light, dusk, and night) were selected from each webcam and manually labelled with regard to the following six categories: cars, persons, bicycles, trucks, trams, and buses. The manual counts in these six categories were then compared to the number of counts found by the object detection models. The results show that public webcams constitute a useful source of data for transport research. In bright light conditions, applying out-of-the-box object detection models can yield reliable counts of cars or persons in public squares, streets, and junctions. However, the detection of cars and persons was not reliably accurate at dusk or night. Thus, different object detection models might have to be used to generate accurate counts in different lighting conditions. Furthermore, the object detection models worked less well for identifying trams, buses, bicycles, and trucks. Hence fine-tuning and adapting the models to the specific webcams might be needed to achieve satisfactory results for these four types of traffic participants. Full article

Traffic safety assessments rely on Surrogate Safety Measures (SSMs), yet their diversity hinders understanding and selection. This paper proposes a novel conceptual framework to systematically categorize SSMs through what we term Motion Scenario Mapping, an approach inspired by queuing theory notation and the concept of short-term behavioral storytelling. The framework explicitly defines interaction stories between a following and leading vehicle to reveal hidden assumptions within each SSM, achieved through a combined coding system. Examining ten common SSMs, the research demonstrates that the framework effectively exposes underlying assumptions, enabling critical evaluation of their contextual validity. By emphasizing short-term risk dynamics, this approach offers a structured understanding of interaction mechanisms and provides a systematic foundation for comparing existing SSMs, identifying research gaps, and guiding future development. This structured ontology has the potential to enhance the analysis and design of safety measures for future transportation systems. Full article

This study presents a comprehensive review of risk assessment and scheduling techniques in highway construction, addressing the complex interplay between uncertainty, project planning, and decision-making. The research critically reviews key risk assessment methods, including Probability–Impact (P-I), Monte Carlo Simulation (MCS), Fuzzy Set Theory (FST), and the Analytical Hierarchy Process (AHP), alongside traditional scheduling approaches such as the Critical Path Method (CPM) and the Program Evaluation and Review Technique (PERT). The findings reveal that, although traditional methods like CPM and PERT remain widely used, they exhibit limitations in addressing the dynamic and uncertain nature of construction projects. Advanced techniques such as MCS, FST, and AHP enhance decision-making capabilities but require careful adaptation. The review further highlights the growing relevance of hybrid and integrated approaches that combine risk assessment and scheduling. Bayesian Networks (BNs) are identified as highly promising due to their capacity to integrate both qualitative and quantitative data, offering potential for greater reliability in risk-informed scheduling while supporting improvements in cost efficiency, schedule reliability, and adaptability under uncertainty. The study outlines recommendations for the future development of intelligent, risk-based scheduling frameworks suitable for industry adoption. Full article

Bicycle use has been increasing in many countries for active, sustainable transportation and recreation. Bicycling can benefit an individual’s mental and physical health and contribute to a community’s well-being and desirability, and it is more environmentally sustainable than automobiles. Nonprofit organizations lead bicycle advocacy efforts in the USA, both for bicycling as recreation and as part of local transportation systems. Outride is one of the larger advocacy organizations, and it sponsors a unique grant system targeting grassroots bicycling organizations dedicated to increasing bicycling. Using the Bicycle Community Development Framework (BCDF) as a lens, this study aims to evaluate Outride’s efforts through an interpretative phenomenological approach (IPA) using semi-structured interviews to gather data regarding grant recipients’ experiences using Outride funds. Findings suggest fund recipients are increasing bicycling through programs and infrastructure development, but with more intentionality, could better support building bicycle communities. Regarding the BCDF, the recipients strongly promoted education, engineering, and equity & accessibility while fostering a sense of community, belonging, and empowerment in their participants. Full article

Railway infrastructures necessitate the inspection of various elements to ensure operational safety. This study concentrates on five key components: rail, sleepers and ballast, track geometry, and catenary. The operational principles of the primary defect measurement sensors are elaborated, emphasizing the use of ultrasound, eddy currents, active and passive optical elements, accelerometers, and ground penetrating radar. Each sensor type is evaluated in terms of its advantages and limitations. Examples of mobile inspection platforms are provided, ranging from laboratory trains to draisines and track trolleys. The authors foresee future trends in railway inspection, including the implementation of IoT sensors, autonomous robots, and geospatial intelligence technologies. It is anticipated that the integration of sensors within both infrastructure and rolling stock will enhance maintenance and safety, with an increased utilization of autonomous robotic systems for hazardous and hard-to-reach areas. Full article

This study is titled “Success Factors in Transport Interventions: A Mixed-Method Systematic Review (1990–2022)”. The purpose of the systematic review is to (1) identify effective interventions for transitioning individuals from private car reliance to sustainable transport, (2) summarise psychosocial theories shaping transportation choices and identify enablers and barriers influencing sustainable mode adoption, and (3) determine the success factors for interventions promoting sustainable transport choices. The last search was conducted on 18 November 2022. Five databases (Scopus, Web of Science, MEDLINE, APA PsycInfo, and ProQuest) were searched using customised Boolean search strings. The identified papers were included or excluded based on the following criteria: (a) reported a modal shift from car users or cars to less CO₂-emitting modes of transport, (b) covered the adoption of low-carbon transport alternatives, (c) comprised interventions to promote sustainable transport, (d) assessed or measured the effectiveness of interventions, or (e) proposed behavioural models related to mode choice and/or psychosocial barriers or drivers for car/no-car use. The identified papers eligible for inclusion were critically appraised using Sirriyeh’s Quality Assessment Tool for Studies with Diverse Designs. Inter-rater reliability was assessed using Cohen’s Kappa to evaluate the risk of bias throughout the review process, and low-quality studies identified by the quality assessment were excluded to prevent sample bias. Qualitative data were extracted in a contextually relevant manner, preserving context and meaning to avoid the author’s bias of misinterpretation. Data were extracted using a form derived from the Joanna Briggs Institute. Data transformation and synthesis followed the recommendations of the Joanna Briggs Institution for mixed-method systematic reviews using a convergent integrated approach. Of the 7999 studies, 4 qualitative, 2 mixed-method, and 30 quantitative studies successfully passed all three screening cycles and were included in the review. Many of these studies focused on modelling individuals’ mode choice decisions from a psychological perspective. In contrast, case studies explored various transport interventions to enhance sustainability in densely populated areas. Nevertheless, the current systematic reviews do not show how individuals’ inner dispositions, such as acceptance, intention, or attitude, have evolved from before to after the implementation of schemes. Of the 11 integrated findings, 9 concerned enablers and barriers to an individual’s sustainable mode choice behaviour. In addition, two integrated findings emerged based on the effectiveness of the interventions. Although numerous interventions target public acceptance of sustainable transport, this systematic review reveals a critical knowledge gap regarding their longitudinal impact on individuals and effectiveness in influencing behavioural change. However, the study may be affected by language bias as it only included peer-reviewed articles published in English. Due to methodological heterogeneity across the studies, a meta-analysis was not feasible. Further high-quality research is needed to strengthen the evidence. This systematic review is self-funded and has been registered on the International Platform of Registered Systematic Review and Meta-analysis Protocols (INPLASY; Registration Number INPLASY202420011). Full article

This study outlines a conceptual discussion within the transport planning field through an extensive systematic literature review that draws upon diverse case studies on alternative transportation. The article focuses on context-dependent multidimensional understandings of alternative transport services in the Global South and the Global North, which other systematic literature review studies lack. Thus, this research aims to pose conceptual differentiations between paratransit, informal transportation, emerging transportation, and micro-mobility to pinpoint specific characteristics and varied understandings of such phenomena for further academic research within transport planning. Tendencies of research approaches and case studies’ policy and regulation based on geographical zones are also addressed. The outcomes enrich the field of study at a theoretical and practical level toward its application in policy and regulation for green transitions of alternative transport services. Full article

Delays in road construction projects pose significant challenges in the Philippines, resulting in increased costs, project overruns, and unmet infrastructure goals. Common causes include poor financial management, inadequate subcontractor performance, deficient planning, and regulatory bottlenecks. This study aims to develop a comprehensive and data-driven framework to mitigate construction delays using the Analytical Hierarchy Process (AHP). The methodology integrates literature review, expert surveys, and pairwise comparisons to identify and prioritize critical delay factors. Experts from the Department of Public Works and Highways (DPWH), private contractors, and academia contributed to the AHP model. The results highlight seven major factor groups: client-related, contractor-related, consultant-related, materials, labor and equipment, contractual issues, and external influences. AHP analysis identified financial management, planning and scheduling, and regulatory coordination as the most impactful causes. Based on these findings, a strategic framework was developed and visualized using a Fishbone Diagram to present mitigation strategies tailored to each factor. While environmental engineering principles—such as material efficiency, energy use optimization, and impact assessments—are acknowledged, they serve as guiding themes rather than formal components of the framework. The study offers practical, stakeholder-validated recommendations for both pre- and post-construction phases, including real-time monitoring, risk anticipation, and improved multi-agency coordination. This framework provides a scalable tool for DPWH and related agencies to improve infrastructure delivery while supporting long-term sustainability goals. Full article

Walking and cycling, as active modes of transportation, play a vital role in advancing sustainable urban mobility by reducing emissions and improving public health. However, widespread adoption faces challenges such as inadequate infrastructure, safety concerns, socio-cultural barriers, and policy limitations. This study systematically reviewed 56 peer-reviewed articles from 2004 to 2024, across 30 countries across five continents, employing the Capability, Opportunity and Motivation-Behaviour (COM-B) framework to identify the main drivers of walking and cycling behaviours. Findings highlight that the lack of dedicated infrastructure, inadequate enforcement of road safety measures, personal and traffic safety concerns, and social stigmas collectively hinder active mobility. Strategic interventions such as developing integrated cycling networks, financial incentives, urban planning initiatives, and behavioural change programs have promoted increased engagement in walking and cycling. Enhancing urban mobility further requires investment in pedestrian and cycling infrastructure, improved integration with public transportation, the implementation of traffic-calming measures, and public education campaigns. Post-pandemic initiatives to establish new pedestrian and cycling spaces offer a unique opportunity to establish enduring changes that support active transportation. The study suggests expanding protected cycling lanes and integrating pedestrian pathways with public transit systems to strengthen safety and accessibility. Additionally, leveraging digital tools can enhance mobility planning and coordination. Future research is needed to explore the potential of artificial intelligence in enhancing mobility analysis, supporting the development of climate-resilient infrastructure, and informing transport policies that integrate gender perspectives to better understand long-term behavioural changes. Coordinated policy efforts and targeted investments can lead to more equitable transportation access, support sustainability goals, and alleviate urban traffic congestion. Full article

If artificial intelligence (AI) is to be applied in safety-critical domains, its performance needs to be evaluated reliably. The present study investigated how humans evaluate AI systems for person detection in automatic train operation. In three experiments, participants viewed image sequences of people moving in the vicinity of railway tracks. A simulated AI system highlighted all detected people—sometimes correctly and sometimes not. Participants had to provide a numerical rating of the AI’s performance and then verbally explain their rating. The experiments manipulated several factors that might influence human ratings: the types and plausibility of AI mistakes, the number of affected images, the number of people present in an image, the position of people relevant to the tracks, and the methods used to elicit human evaluations. While all these factors influenced human ratings, some effects were unexpected or deviated from normative standards. For instance, the factor with the strongest impact was people’s position relative to the tracks, although participants had explicitly been instructed that the AI could not process such information. Taken together, the results suggest that humans may sometimes evaluate more than the AI’s performance on the assigned task. Such mismatches between AI capabilities and human expectations should be taken into consideration when conducting safety audits of AI systems. Full article

Since 1 January 2024, newly produced heavy-duty trailers are subject to the assessment of their performance regarding CO₂ and fuel consumption according to Implementing Regulation (EU) 2022/1362. The method is based on the already established approach for the CO₂ and energy consumption evaluation of trucks and buses, i.e., applying a combination of component testing and vehicle simulation using the software VECTO (Vehicle Energy Consumption calculation TOol). For the evaluation of trailers, generic conventional towing vehicles in combination with the specific CO₂ and fuel consumption-relevant properties of the trailer, such as mass, aerodynamics, rolling resistance etc., are simulated in the “VECTO Trailer” software. The corresponding results are used in the European HDV CO₂ standards with which manufacturers must comply to avoid penalty payments (2030: −10% for semitrailers and −7.5% for trailers compared with the baseline year 2025). Methodology and legislation are currently being extended to also cover the effects of electrified trailers (trailers with an electrified axle and/or electrically supplied auxiliaries) on CO₂, electrical energy consumption, and electric range extension (special use case in combination with a battery-electric towing vehicle). This publication gives an overview of the developed regulatory framework and methods to be implemented in a future extension of VECTO Trailer as well as a comparison of different e-trailer configurations and usage scenarios regarding their impact on CO₂, energy consumption, and electric range by applying the developed methods in a preliminary potential analysis. Results from this analysis indicate that e-trailers that use small batteries (5–50 kWh) to power electric refrigeration units achieve a CO₂ reduction of 5–10%, depending primarily on battery capacity. In contrast, e-trailers designed for propulsion support with larger batteries (50–500 kWh) and e-axle(s) (50–500 kW) demonstrate a reduction potential of up to 40%, largely determined by battery capacity and e-axle rating. Despite their reduction potential, market acceptance of e-trailers remains uncertain as the higher number of trailers compared with towing vehicles could lead to slow adoption, especially of the more expensive configurations. Full article

Traffic congestion constitutes a substantial global issue, adversely impacting economic productivity and quality of life, with associated costs estimated at approximately 2% of GDP in various nations. This systematic review investigates the application of machine learning (ML) in traffic congestion forecasting from 2010 to 2024, adhering to the PRISMA 2020 guidelines. A comprehensive search of three major databases (IEEE Xplore, SpringerLink, and ScienceDirect) yielded 9695 initial records, with 115 studies meeting the inclusion criteria following rigorous screening. Data extraction encompassed methodological approaches, ML techniques, traffic characteristics, and forecasting periods, with quality assessment achieving near-perfect inter-rater reliability (Cohen’s $\kappa$ = 0.89). Deep Neural Networks were the predominant technical approach (47%), with supervised learning being the most prevalent (57%). Classification tasks were the most common (42%), primarily addressing recurrent congestion scenarios (76%) and passenger vehicles (90%). The quality of publications was notably high, with 85% appearing in Q1-ranked journals, demonstrating exponential growth from minimal activity in 2010 to 18 studies in 2022. Significant research gaps persist: reinforcement learning is underutilized (8%), rural road networks are underrepresented (2%), and industry–academia collaboration is limited (3%). Future research should prioritize multimodal transportation systems, real-time adaptation mechanisms, and enhanced practical implementation to advance intelligent transportation systems (ITSs). This review was not registered because it focused on mapping the research landscape rather than intervention effects. Full article