Articles tagged with Transportation Engineering
The new center aims to make mobility systems more sustainable and efficient by leveraging AI, autonomy, digital infrastructure, and data-driven decision-making. Stanford faculty members across five schools are affiliated with the center, which will be funded through corporate partnerships.
A new study by Florida Atlantic University researchers highlights the role of urban planning in increasing pedestrian and bicyclist fatalities in the US. The study reveals that everyday destinations like grocery stores and pharmacies along busy roads significantly increase risk of serious injury or death.
Researchers at NTNU have developed a model that calculates which high-speed passenger routes can be operated with zero-emission express ferries. The study shows that a combination of batteries and fuel cells is necessary to meet the goal, emphasizing the importance of smart energy management.
Researchers developed a novel approach to personalize travel behavior analysis without centralizing sensitive user data. The IPC-FM framework achieves high accuracy and adapts quickly to new users, offering a customizable solution for individual mobility needs.
KEPT, an AI system, combines video understanding with a memory of similar past scenes to help self-driving cars predict their own short-term path more safely. The system uses a fast and lightweight retrieval module to reduce prediction errors and potential collisions.
A new study developed a multi-scale dynamic driving environment to assess the impact of daily driving behavior on electric vehicle battery health. The framework uses deep reinforcement learning to optimize battery health and energy efficiency, and its results show that stable driving behavior can extend battery lifetime by approximatel...
A new artificial intelligence framework called SS-MA-PPO treats mandatory lane-change control as a coordinated multi-agent problem, enabling CAVs to effectively coordinate with surrounding vehicles. The framework consistently delivered the best performance in terms of delay, waiting time, fuel consumption, and stop-and-go frequency.
Researchers proposed a dynamically expandable learning framework for interactive trajectory prediction to enable models to adapt to evolving traffic environments. The approach effectively mitigates catastrophic forgetting and maintains stable predictions for critical interaction scenarios across multiple learning stages.
Researchers propose a novel latency-aware trajectory prediction framework, LatenAux, empowered by a consolidated auxiliary learning paradigm. The framework transforms latency from a hindrance into an opportunity for improved performance. Extensive experiments validate its effectiveness and superiority.
Researchers propose TrafficPerceiver, a unified multimodal framework that supports coarse-grained scene understanding tasks and fine-grained target-oriented segmentation tasks. The method achieves superior performance on the CTSU dataset, demonstrating its potential for building robust traffic perception systems.
Researchers developed a modular, edge-intelligent framework called mOS to address limitations of existing V2X-based systems. The study demonstrates the feasibility of MR-integrated infrastructure intelligence and offers a scalable pathway for deploying AV coordination systems.
A new deep learning framework has been developed to improve the accuracy of vehicle re-identification in large-scale drone-based traffic monitoring. By integrating visual and temporal information, the approach delivers significant improvements over traditional vision-only methods.
A new study finds that aggressive policy action and cost reductions can accelerate the global shift to electric vehicles, reducing energy use and carbon emissions. The study suggests a uniform 20% reduction in non-energy costs could dramatically increase EV adoption rates, with market share rising from 25-50% to 70-85% globally by 2035.
The AUMOVIO-NTU Corporate Lab will focus on areas like AI, sustainability, novel materials, and connectivity to develop solutions for safer, smarter, and more sustainable transportation. The joint lab aims to accelerate innovations that can support Singapore's future mobility ecosystem.
Researchers have created a carbon-fiber composite that swallows sound waves while retaining the strength of industrial load-bearing panels. The design achieves an average sound absorption coefficient of over 0.9 across a frequency range of 1,500 to 5,500 hertz.
A study by researchers at Pohang University of Science & Technology discovered that engineered disorder can amplify transverse electron transport in magnetic materials. The findings suggest that deliberately using disorder in materials design could lead to new opportunities in spintronics and thermoelectric energy-conversion technologies.
Researchers examined how autonomous vehicles affect morning commutes and parking in business districts, finding that AVs could increase vehicle hours and miles traveled. Urban planners can adapt policies to accommodate AVs by adjusting parking fees or infrastructure, reducing total system cost by up to 28.5 percent.
Researchers suggest changing flight paths to avoid contrails could slash aviation's global warming impact by nearly half. Implementing such a policy could recover around 9% of the temperature budget the world has left before breaching the Paris Agreement's 2°C limit.
The study analyzed 430 test runs in Mannheim and Friedrichshafen, finding that autonomous shuttles can make everyday trips easier, replacing car trips. Users are open to technology as long as they feel safe, and responsibilities need to be clearly defined for reliable operation.
A Norwegian University of Science and Technology study highlights seafarers' concerns about autonomous ships' technical safety, trust in technology, and crew competence. The researchers aim to ensure safer use of advanced technology and increase seafarers' trust in autonomy by addressing the challenges highlighted by the seafarers.
Researchers at Tokyo Metropolitan University have created a rotating tabletop device to test dynamic wireless power transfer for electric vehicles. They successfully replicated conditions of a car moving at 40 kilometers per hour, promising accelerated research into next-gen charging.
Researchers demonstrated a breakthrough in microrobotics: swarms of magnetic microrobots can manipulate objects without physical contact by harnessing fluid-generated torque. The microrobots act as motors to move millimeter-sized passive objects, opening new pathways for precision manufacturing and biomedical applications.
Researchers at KIT have achieved a significant milestone in compressorless hydrogen gas turbine technology, extending runtime to over five minutes. The innovation saves energy and increases efficiency by utilizing pressure-gain combustion, making it an attractive option for fossil-free energy systems.
The article highlights the psychological demands of self-driving cars on human brains, citing Professor McLeod's research and personal experience. He emphasizes the need for clearer interfaces, simulation-based training, and updated driving tests to address these challenges and ensure safe automation uptake across society.
A new model maps foot traffic in New York City, providing insights into pedestrian activity and hazard locations. The study reveals high densities of foot traffic outside Manhattan, with many streets having similar foot-traffic levels to Manhattan's busiest areas.
NTU Singapore has unveiled its first locally designed and built full-sized eVTOL aircraft technology demonstrator, combining aerodynamic efficiency with hovering capability. The aircraft was developed over three years by researchers and engineers, powered by NTU-designed electric motors and featuring eight lift rotors.
LIST's patented infrared welding process enables rapid assembly of thick carbon-fibre-reinforced thermoplastic components, reducing weight, costs and environmental impact. The innovation is estimated to reduce CO2 emissions by 12.5 tonnes per wing rib.
Researchers at the University of Michigan developed a pair of sensors that can detect ice and freezing rain, alerting pilots to potential hazards and reducing crashes. The sensors use microwaves and lasers to detect ice on planes and roads, potentially saving lives by slowing down drivers and preventing accidents.
Researchers used machine learning to evaluate 1,773 bus stops across Massachusetts, identifying 13 crash-relevant characteristics and proposing countermeasures. The study found that bus stop types in mixed-use arterial corridors and dense urban cores have the highest prevalence of crashes.
The Journal of Intelligent and Connected Vehicles is transitioning to an open-access platform on SciOpen, providing barrier-free access to cutting-edge research. The journal aims to foster greater global collaboration and leverage modern publishing infrastructure.
The journal will be published on SciOpen, a platform dedicated to high-quality open research dissemination. Starting Jan 1, 2026, all new submissions must be directed through the journal's submission portal.
A new study by MIT researchers reveals that cities with strong airline connections are more likely to attract multinational firms, particularly in knowledge industries. The study analyzed 7.5 million firms in 800 cities and found that direct flights lead to a 20% increase in subsidiaries, compared to cities with only one-stop connections.
A new framework for ride-pooling addresses low matching efficiency and promotes flexible cooperation. The multi-level coalition formation game framework consistently improves vehicle utilization, reduces travel costs, and fosters cooperation in diverse regional contexts.
A team of researchers proposes a novel attention-based graph neural network to estimate network-wide traffic flow across multiple cities. The model leverages correlations between road traffic flow and urban characteristics, such as building structures, human activity, infrastructure connectivity, and dynamic traffic conditions.
Researchers developed PriorFusion, integrating semantic, geometric, and generative shape priors to improve road element perception in complex urban scenarios. The method outperforms state-of-the-art methods in difficult scenarios like intersections and occluded areas, achieving an overall mAP of 70.4%.
Researchers at National University of Singapore used machine learning models to predict traffic congestion in Alameda County before, during, and after the pandemic. The study found that Bi-LSTM models were more accurate than traditional forecasting tools and provided transparent insights into the drivers of congestion changes.
A new framework, MARL-OD-DA, offers a promising answer to making AI truly scalable and reliable for real-time traffic assignment. The approach redesigns learning agents at the origin–destination level, utilizing Dirichlet-based continuous actions to achieve stable and high-quality solutions under dynamic travel demand.
Contrails formed from plane exhaust meet icy air, growing into threads that trap heat and contribute to warming the planet. Combining images from geostationary and low-Earth-orbiting satellites may provide a more complete picture of contrail life and radiative properties.
A new method analyzes nearby vehicle motion to estimate road's trajectory and vanishing point, capturing distant road areas and enhancing safety. The system outperformed conventional and deep learning-based techniques in tests under day and night conditions, reducing intersection-related accidents.
Professor Patricia Thornley, a renowned expert in sustainable energy and clean technologies, has been appointed as the new chief scientific adviser to the Department for Transport. She will leverage her three decades of experience to inform evidence-based policy and drive innovation across the transport system.
A team of researchers designed a custom approach sound library for electric vehicles using low-frequency noise, which was found to be more effective at alerting pedestrians. The sounds were tested with volunteers and ranked highly on criteria such as urgency and noticeability.
Researchers develop a novel integrated data model that merges construction and geospatial information standards to manage bridges' 3D geometry data and maintenance records. This framework enables accurate damage location assessment, repair prioritization, and predictive maintenance, leading to improved infrastructure safety and longevity.
A new study introduces a pioneering power management strategy that prevents ship blackouts by distributing intelligence among devices, allowing them to operate independently. The system is significantly safer, simpler, and more flexible than traditional centralized automation.
Research by University of Birmingham scientists reveals that lower-income individuals are more likely to own cheaper, higher-emitting vehicles contributing disproportionately to local urban air pollution. Spending an additional £10,000 on a diesel vehicle is associated with a 40% reduction in nitrogen oxide emissions per litre.
Researchers explore using municipal solid waste as a low-emission, cost-effective feedstock for sustainable aviation fuel, reducing greenhouse gas emissions by 80-90%. The study suggests that adopting municipal solid waste-based jet fuels could save airlines money under carbon pricing systems.
A new physics-based approach predicts how lightning strikes aircraft, identifying vulnerable regions for protection. The tool can be applied to any shape of aircraft, including unconventional designs.
The ATP-DEC calculator provides accurate and transparent information on carbon disclosure, helping align aviation with climate targets. It captures real-world variations and life cycle emissions, making it a crucial tool for policymakers, airlines, and passengers.
Researchers developed a novel framework to capture dynamic nature of social networks, finding that scattered seeds of connections only grow when nourished, while policy restrictions can cut network growth by almost one-third.
Lowering residential speed limits to 30kph significantly boosts bicycle riding safety without affecting car trip times, according to a study. The reduction in traffic stress leads to more people choosing bikes as a safe mode of transport.
A study of 744 bridges worldwide reveals that North American and African bridges are most at risk, with spaceborne monitoring able to detect problems before they become disasters. The proposed solution integrates satellite data into risk frameworks to significantly lower the number of high-risk bridges.
Researchers developed a new diagnostic metric called State of Mission (SOM) to predict EV battery performance based on both battery data and environmental factors. SOM significantly reduced prediction errors compared to traditional methods.
A new study found that historic droughts could become common for Gatún Lake, the main source of water for the Panama Canal locks. The study projects that water levels will decrease and increase evaporation under high-emissions scenarios.
The startup has assessed over 3,400 miles of Indiana roads using advanced computer vision algorithms to quickly and objectively assess pavement conditions. This platform provides actionable insights without requiring in-house data analysis expertise or costly hardware.
A new study by Portland State University's Transportation Research and Education Center (TREC) reveals that transit-oriented developments (TODs) in the Portland metro area generate significantly fewer car trips than previously estimated. At affordable housing sites, car trips were reduced to only a quarter to two-fifths of expected rates.
Researchers developed a data-driven macroscopic mobility model that relies on simple observations from city planners' routine data collection. The D3M model can accurately represent diverse traffic conditions and simulate complex system-level dynamics.
A recent study published in the Journal of Safety Research found that rented e-bikes have an eight times higher crash risk than rented e-scooters, calculated based on trip distance. The researchers used GPS data to compare micromobility in seven European cities and found a surprising result.
Researchers from Edith Cowan University have developed a method to incorporate waste plastics into pavement material, offering a dual benefit of improving road strength and reducing plastic pollution. The study highlights the potential for repurposing household plastics to create more sustainable and resilient roads.