Articles tagged with Traffic Flow
Assistant Professor Yingxue Zhang's project aims to develop urban AI models that can efficiently process vast amounts of human-generated data to optimize commute times, traffic safety, and more. The model will utilize offline reinforcement learning to tackle spatial-temporal dynamics in urban life.
A new study from Carnegie Mellon University and Oxford Saïd Business School found that the entry of ride-hailing platforms drove measurable increases in economic output and intermittent employment. Regional GDP per capita increased, and the number of seasonal, temporary, or intermittent jobs rose after Uber and Lyft entered the region.
Global road injury rates declined by 38.3% for new cases and 32.3% for deaths between 1990 and 2023, but progress was uneven across income groups. Low- and middle-income countries bear the greatest burden, with nearly six times higher mortality rates than high-income countries.
The MOVEO general assembly showcased advancements in smart transport connections, with a focus on EU-funded research and innovation. The project aims to unite expertise from nine European countries to improve inspection, monitoring, logistics, mobility, and inclusiveness.
A research project led by University of Tennessee at Knoxville associate professor Candace Brakewood aims to evaluate the impact of congestion pricing on public transit systems. The study will focus on New York City's recent implementation, analyzing how it increased transit ridership across subway, bus, and regional rail systems.
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 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 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.
A study by UMass Amherst researchers found that nearly a quarter of MA drivers run through the red light at pedestrian hybrid beacons. Drivers also often stop too soon or fail to slow down during flashing yellow phases, causing confusion and potential safety issues.
Researchers at FAU have developed a smarter AI framework that can manage complex systems with unequal levels of authority and adapt to imperfect information. The framework, based on reinforcement learning and game theory, reduces unnecessary computation while maintaining system stability and optimal strategy outcomes.
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 transportation system management and operations data exchange solution will be developed by SwRI for the North Central Texas Council of Governments. The platform aims to enhance mobility, safety, and infrastructure management in the region. It will serve as a regional clearinghouse for real-time transportation system data.
A Safe Systems Approach emphasizes that road users, designers, operators, policymakers, administrators, and healthcare professionals all have a role to play in reducing fatalities. By adopting this approach, countries can realize significant success in eliminating roadway deaths, but full commitment from stakeholders is necessary.
A new study by Virginia Tech Transportation Institute found that teen drivers who practiced more had 30% fewer crash or near-crash incidents. Researchers analyzed data from 82 teen drivers monitored for 22 months, revealing that supervised driving experiences and safety education are crucial for reducing novice driver risks.
A new INFORMS Management Science study reveals AI-powered traffic cameras improve overall road safety by promoting safer driving behavior and reducing accidents. The study estimates that citywide deployment of AI-enabled cameras could prevent approximately 1,190 accidents annually.
Researchers at UCF used a combination of emerging technologies to evaluate the safety of concrete bridges. By combining infrared thermography, high-definition imaging and neural network analysis, they can quickly identify defects and prioritize repairs.
University of Missouri researchers developed a method using lidar and AI to analyze pedestrian, cyclist, and vehicle interactions at traffic signals. The approach aims to enhance driver awareness, reduce accidents, and improve mobility.
Researchers discovered that pedestrians form neat lanes in crossing roads only until people start veering off at extreme angles, after which the flow becomes disordered. The team's theory predicts that critical angle of 13 degrees marks the point where crowds collapse from order to disorder.
A team of mathematicians studied crowd flow and developed a way to predict when pedestrian paths become disorganized. They found that an angular spread of around 13 degrees is the threshold for transition, beyond which the flow becomes less efficient and potentially more dangerous.
The researchers developed a novel camera-based system that adapts to traffic flow in real-time, ensuring efficient monitoring and resource use. The system's two approaches, the Random-Value-Camera-Level Algorithm and the ALL-Random-With-Weight Algorithm, optimize camera usage and save energy while maintaining reliable surveillance.
A team of researchers from UniTrento examined how ants manage traffic congestion using pheromone trails and observed individual ant movements. Their findings could provide a model for optimizing autonomous vehicle traffic flow, reducing congestion and emissions.
Listening to natural soundscapes reduces self-reported stress and anxiety levels, while traffic sounds negate these benefits. The study suggests reducing traffic speed in urban areas can positively impact human health.
A UBC study analyzing pedestrian interactions with vehicles on busy streets found that distracted pedestrians face higher safety risks compared to undistracted road users. Distracted pedestrians remained unaware of their surroundings, making fewer adjustments to their path or speed.
Long-term exposure to air pollution is associated with a higher need for help with lost independence in later life. Traffic-related sources generate the largest and most consistent increases in risk, suggesting controlling air pollution may delay or divert care needs.
A study predicts UAM demand in Chengdu will increase as travel distance grows, particularly beyond 15 kilometers. The data suggests UAM share rates could rise by 0.73% for every additional kilometer, making it a viable option for medium to long-range transport.
A mathematical model developed by Alexandre Solon and Eric Bertin describes the movement of particles in situations similar to cars on a road or bacteria attracted to a nutrient source. The model identifies conditions that favor traffic jams, including high vehicle density and driver inertia.
The algorithm facilitates dynamic trajectory planning for connected automated vehicles, improving transportation efficiency. It also reduces average delays and fuel consumption as CAV penetration increases.
A new study reveals that retention ponds and wetlands can significantly reduce the amount of tyre particles entering aquatic environments, with an average reduction of 75%. The research found that tyre wear particles outweigh other forms of microplastics, but are also removed in greater quantities.
A comprehensive survey published in Intelligent Computing explores deep learning techniques for cellular traffic prediction, enhancing intelligent 5G network construction and resource management. The review highlights three main applications of cellular traffic prediction, including temporal and spatial-temporal prediction methods.
A new traffic signal concept, known as the 'white phase,' uses autonomous vehicles to expedite traffic flow at intersections. The concept has been shown to improve travel time for both pedestrians and vehicles, especially when autonomous vehicles make up a higher percentage of traffic.
A University of Michigan team recalibrated traffic signals using GPS data from connected vehicles, resulting in a 20-30% decrease in stops at intersections. The system reduces costs and cuts vehicle emissions by optimizing signal patterns for changing traffic flows.
Researchers found that neighborhoods within 3 kilometers of an Amazon last-mile delivery station experience twice the amount of delivery van and truck traffic as farther-away areas. These neighborhoods are disproportionately home to low-income households and people of color, who order 14% fewer packages than average. The study highligh...
A new deep learning-based detection system has been developed by INU researchers to improve the detection capabilities of autonomous vehicles. The system, aided by IoT technology, generates bounding boxes and confidence scores for visible obstacles using point cloud data and RGB images as input.
Yu Yang's NSF-funded research aims to reduce vehicle emissions and promote the use of electric bikes and scooters by developing socially informed traffic signal control systems. The project involves a three-pronged method that uses low-cost mobile air-quality sensing, spatial-temporal graph diffusion learning, and reinforcement learnin...
Researchers at North Carolina State University found that connected vehicles improve travel time through intersections, but automated vehicles without connectivity actually increase wait times. The study suggests that incorporating vehicle-to-vehicle and vehicle-to-infrastructure communication is crucial for optimizing traffic flow.
A study uses statistical physics to analyze hourly plane landing volumes, estimating airport operations' efficiency. The model demonstrates that airport operations become more random after the COVID-19 pandemic, indicating changes in aircraft interactions.
Scientists developed a modeling technique to study urban traffic flows and verified it with real-world data from Shanghai. They discovered that Zhonghuan Road is a potential bottleneck that could lead to cascading failure of the entire urban traffic system.
A sensor embedded in concrete allows for more precise data on pavement strength, reducing the need for repairs and improving road sustainability. This technology has been implemented in several states, including Indiana and Texas, to reduce traffic delays and save taxpayer dollars.
A new machine learning model can predict city traffic activity in different zones of cities, enabling targeted responses from policymakers. Understanding people's mobility patterns is crucial for improving urban traffic flow, and the model provides insights into urban interactions.
A new approach, called the white phase concept, uses autonomous vehicles to control traffic flow at intersections, reducing fuel consumption and travel time. The system informs human drivers through a clearly identifiable signal, improving safety and efficiency.
A new study found that stop-and-go traffic may be linked to reduced birthweight, with a nine-gram decrease in weight among infants born to parents who reside in areas with heavy traffic. This association was seen even after controlling for background air pollution levels and other environmental co-exposures.
The study developed an extended deep Q-network (EDQN)-incorporated context-based meta-RL model that can autonomously detect traffic states, classify regimes, and assign signal phases. The model outperformed existing algorithms in simulation experiments and showed adaptability to new tasks without adjusting parameters.
Researchers at NC State University have developed a cooperative distributed algorithm that allows autonomous vehicle software to make calculations more quickly, enabling real-time navigation of complex merging scenarios. The approach improves both traffic flow and safety, with zero incidents in simulations.
Researchers analyzed over 240,000 Google Street View images to find that streets with more visible sky, roadway, and signs have 48% more crashes than residential areas. The study highlights the dangers of 'open road' segments in urban areas, which drivers often perceive as highways, despite being near pedestrians and human activity.
A new method reduces computational complexity of traffic models, making them operate more efficiently. The modified algorithm breaks down complex forecasting questions into smaller problems that can be solved in parallel, significantly reducing run time. This approach also allows for a good enough solution within an error bar, rather t...
A study by Texas A&M researchers found that navigation systems frequently guide drivers to take paths with a greater risk of crashes, despite reducing travel time. The study analyzed road and traffic characteristics in five metropolitan areas and proposed a new system architecture for finding the safest route using navigation systems.
A West Virginia University researcher is studying the American implementation of turbo roundabouts, designed to limit weaving and lane changing movements. The study aims to reduce conflict points and severity of crashes, with a focus on gauging motorists' responses via computerized driving simulations.
Researchers at NYU Abu Dhabi have published a comprehensive review of 50 fundamental traffic models using an extensive data set of 2.3 billion vehicle observations from 25 cities worldwide. The study found that a non-parametric model outperformed other traffic flow models, regardless of road type and congestion level.
Researchers developed a robust, deep neural network model to analyze automobile traffic impacts of construction zones. The model estimates hourly traffic volumes without adjustment factors, helping transportation agencies plan for efficient work zone operations.
A new study uses machine-learning algorithms to predict the next phase of a traffic signal, giving bicyclists a smoother ride. The researchers achieved high accuracy with 85% prediction success rate, using LSTM and 1D CNN models.
Researchers at Portland State University developed data-driven speed management strategies to improve safety and efficiency in multimodal transportation. They found that disabling speed feedback signs on conventional roadways resulted in reduced driver speeds and a lower likelihood of severe crashes.
A new method developed by Gayah and Aalto University researcher Murat Bayrak suggests eliminating left turns at busy intersections to reduce congestion. The hybrid approach uses heuristic algorithms to identify the most efficient configurations, banning left turns in city centers while allowing them on periphery roads.
Researchers will develop an adaptive traffic control system leveraging connected vehicles and infrastructures to optimize and manage traffic flow. The goal is to reduce corridor-level fuel consumption by 20 percent, while maintaining a highly operable and safe transportation environment.
Researchers used routing apps to model real-time road traffic emissions, providing valuable insights into traffic flows and emissions hotspots. The study found that crowd-sourced data from routing apps could be used to calculate speed-related emissions and provide more accurate emissions models.
A new smart parking software developed at Cornell University reduces congestion and emissions by matching drivers with parking spots based on travel time. The system has been shown to decrease the amount of time spent looking for parking by an estimated 64% compared to other strategies.
The project aims to demonstrate that intelligent control of a small number of connected and automated vehicles can improve the energy efficiency of all vehicles in the flow by reducing congestion effects.
Researchers at the University of Cambridge programmed a fleet of miniature robotic cars to demonstrate how autonomous vehicles can communicate with each other and improve safety. In experiments, cooperative driving improved traffic flow by 35%, while aggressive driving increased this improvement to 45%.
Researchers found that adaptive cruise control systems can create phantom jams by slowing down too much, even when the vehicle ahead speeds up. The study suggests that designing ACC systems with traffic flow in mind is crucial for alleviating jams and improving traffic efficiency.
Researchers at Georgia Tech and Multiscale Systems Inc. used percolation theory to model how a large-scale hack on Internet-connected cars would affect traffic in Manhattan. A small-scale hack affecting only 10% of vehicles could cause citywide gridlock, while using multiple networks for connected vehicles decreases the risk.
A study by Georgia Institute of Technology researchers found that 30% of ants do 70% of the work in fire ant colonies, optimizing digging without clogs. Robots programmed to mimic ant behavior outperformed their human-made counterparts, demonstrating the efficiency of unequal work distributions and reversal behaviors.