Urban Intersections Research Articles

Complexity Evaluation for Urban Intersection Scenarios in Autonomous Driving Tests: Method and Validation

As autonomous driving technology scales up, complex urban intersections pose significant safety challenges. Current testing methods struggle to simulate these complex scenarios at a manageable cost, making simulation testing essential. For effective evaluation, establishing comprehensive and objective complexity metrics is crucial. However, existing complexity evaluation methods often depend on the performance of the primary vehicle and are based on local interaction relationships, which lack a global perspective and objectivity and have yet to be validated by autonomous driving systems. To address this issue, this paper proposes a multidimensional complexity assessment framework that introduces system-level indicators such as vehicle count, interaction density, disorder, and risk. This framework quantifies the complex interactions at intersections from a global perspective, independent of primary vehicle performance. Experimental results demonstrate that the complexity evaluation results are highly consistent with the performance of a high-level autonomous driving system (Apollo). The framework has been successfully applied to test scenario generation on the Apollo platform, achieving twice the scenario generation efficiency of traditional methods, thus showcasing substantial engineering value.

VTSIM: Attention‐Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

ABSTRACTSimulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule‐based and deep learning‐based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset.

Investigating pedestrians’ red light running intentions at urban intersections in different traffic Environments: A scenario-based analysis guided by theoretical frameworks

Pedestrian risky behaviors are one of the contributing factors to crashes involving pedestrians. Therefore, it is crucial to comprehend the mechanisms by which pedestrians interact with many influential components in the traffic environment. This study aimed to evaluate pedestrians’ red light running intentions and related factors under different traffic flow scenarios, including straight traffic flow, right-turning traffic flow, and left-turning traffic flow. A theoretical approach based on the theory of planned behavior (TPB) and the prototype willingness model (PWM) was employed. Data were collected from an online survey of 2250 participants in Tehran, Iran. Structural equation modeling (SEM) was used to identify the significant factors that explain intentions. All models successfully explained the behavioral intention for red light running violation; however, the findings revealed that the integrated model was the best-performing model to represent violation and, thus, was selected for interpreting the results and drawing relevant conclusions. Different traffic flow scenarios had varied effects on violation intentions for individual characteristics and model constructs. Previous crash experiences and driving-related background variables emerged to impact pedestrian violation intention across three scenarios. The findings also suggested that the rational constructs (attitude, perceived behavioral control, and facilitating conditions) had a more robust impact on violation intention compared to reactive constructs (prototype similarity, prototype favorability), with facilitating conditions being the strongest predictor of the model, followed by attitudes toward violation as a significant predictor of intention for red light violation. According to the results, the mechanism of risk-taking varies depending on the direction of the traffic flow. Higher risk was associated with the violation at the intersections with straight traffic flow compared to the intersections with turning traffic flow. Based on the findings of this study, several implications, including interventions focusing on individuals’ transportation safety attitudes, countermeasures to increase the risk perception of pedestrians toward turning vehicles, and countermeasures regarding the use of mobile phones while walking for the context of this study were proposed.

Evaluation of Autonomous Driving Conservativeness by Urban Intersections with Real-World Data

Evaluation of Autonomous Driving Conservativeness by Urban Intersections with Real-World Data

Investigating Age-Specific Respiratory Deposition Doses of Traffic-Related Particles at Urban Intersections in Pune, India

Investigating Age-Specific Respiratory Deposition Doses of Traffic-Related Particles at Urban Intersections in Pune, India

Evaluating the environmental benefits of autonomous vehicles in urban intersections: a microscopic simulation approach

This research delves into the environmental and energy implications of incorporating autonomous vehicles (AVs) into urban traffic systems, mainly focusing on emissions and fuel efficiency. The study employed PTV VISSIM simulation software to model a four-leg signalized intersection in Balgat, Ankara, under varying levels of AV integration and driving behaviors. A total of 21 scenarios were simulated, assessing the impact of cautious, normal, aggressive, and platooning AV behaviors on emissions of CO, NOx, and VOCs, as well as fuel consumption, across different traffic signal cycle durations. The results indicate that shorter signal cycle times consistently significantly reduce emissions and fuel consumption, irrespective of AV driving behavior. The most notable improvements were observed in platooning scenarios, attributed to their optimized traffic flow. In contrast, longer cycle times increased emissions and fuel consumption, especially with human-driven and cautious AVs, due to more frequent idling and stop-and-go traffic patterns. This study highlights the importance of refining AV driving algorithms and optimizing signal control systems to reduce environmental impacts and improve fuel efficiency in urban settings, providing crucial insights for advancing sustainable urban mobility and traffic management strategies.

A Multi-Scene Roadside Lidar Benchmark towards Digital Twins of Road Intersections

Abstract. In recent years, the evolution of digital twin technology has paved the way for the construction of intelligent holographic intersections. This can be facilitated by utilizing precise point clouds from roadside lidar. With its capability of real-time monitoring, lidar plays a crucial role in enhancing intersection perception, enabling precise detection and tracking of road objects, as well as providing accurate speed estimates. Despite the introduction of few roadside lidar datasets aimed at enhancing supervised learning algorithms, their applicability to intelligent intersection monitoring remains limited. To address this, this paper presents an Intelligent Intersections (Int2sec) dataset, which exhibits several salient features: 1) it encompasses a broad array of urban intersection scenarios accompanied by a substantial quantity of object annotations; 2) the deployment of dual lidar stations facilitates a thorough scanning of scenes, thereby ensuring expansive scene coverage and mitigating the mutual occlusion phenomenon amongst objects; and 3) the dataset not only catalogues the coordinates, dimensions, and orientations of objects but also encompasses additional attributes such as tracking IDs and real-time motion statuses. Furthermore, the paper evaluates the efficacy of various prominent benchmarking networks, providing a critical analysis and prospective for future research.

Virtual Reality Study on Pedestrians’ Perceived Trust in Interactions with Automated Vehicles

This paper investigates the impact of different automated vehicle (AV) communication concepts on pedestrians' perceived trust when interacting with the AV in an urban intersection setting. For this, two virtual reality (VR) studies were conducted. The first examined the influence of vehicle automation on how pedestrians interpret driving behavior, while the second analyzed the effects of explicit communication concepts on pedestrians' perceived trust. The results show that AV driving behavior evokes similar associations as manually driven vehicles, with overall perceived trust scores not differing considerably (with driver: 4.7, without driver: 4.6). However, qualitative interviews revealed that pedestrians ultimately interpret AV behavior differently, yielding insights into the applicability of driving behavior of manually driven vehicles as a model for AV driving behavior. The second study showed an increase in pedestrians' perceived trust when vehicle-based explicit communication was present (mean: 4.9). In contrast, infrastructure-based communication showed no difference compared to implicit communication (mean: 4.6). The investigation of the influence of the traffic infrastructure (presence of traffic lights) has shown different results for implicit and explicit communication of AVs. For implicit communication, pedestrians' perceived trust increased with traffic lights (mean: 4.8) compared to scenarios without them (mean: 4.4). However, for explicit communication, the perceived trust decreased with traffic lights (vehicle-based: 4.7, infrastructure-based: 4.6) compared to scenarios without traffic lights (mean: 5.1). One reason for this is possible cognitive overload caused by the perception of multiple visual aids that are not always in the same field of view.

Vehicle trajectory extraction and integration from multi-direction video on urban intersection

With the gradual maturity of computer vision technology, using intersection surveillance videos for vehicle trajectory extraction has become a popular method to analyze vehicle conflicts and safety in urban intersection. However, many intersection surveillance videos have blind spots, failing to fully cover the entire intersection. Vehicles may also obstruct each other, resulting in incomplete vehicle trajectories. The angle of surveillance videos can also lead to inaccurate trajectory extraction. In response to these challenges, this study proposes an vehicle trajectory extraction and integration framework using surveillance videos collected from four entrance of urban intersection. The framework first employs the improved YOLOv5s model to detect the positions of vehicles. Then, we proposed an object tracking model MS-SORT to extract the trajectories in each surveillance video. Subsequently, the trajectories of each surveillance video are mapped into the same coordinate system. Then the integration of trajectories is achieved using space–time information and re-identification (ReID) methods. The framework extracts and integrates trajectories from four intersection surveillance videos, obtaining trajectories with significantly broader temporal and spatial coverage compared to those obtained from any single direction of surveillance video. Our detection model improved mAP by 1.3 percentage points compared to the basic YOLOv5s, and our object tracking model improved MOTA and IDF1 by 2.6 and 2.1 percentage points compared to DeepSORT. The trojectory integration method achieved 94.7 % of F1-Score and RMSE of 0.51 m. The average length and number of the extracted trajectories has increased by at least 47.6 % and 24.2 % respectively compared to trajectories extracted from a single video.

Evaluating the performance of implementing regionally coordinating bus priority signals under different control schemes

Bus Rapid Transit (BRT) proves its effectiveness in alleviating traffic congestion, especially in urban areas. The implementation of Transit Signal Priority (TSP) for BRT has shown a significant reduction in delays. However, in densely populated urban areas, this priority can inadvertently cause additional delays for other modes of transportation. In this paper, we propose a control strategy for Regionally Coordinating Bus Priority Signals Control (RCBPSC) at urban intersections. The aim is not only to reduce bus delays but also to consider minimizing delays for pedestrians and other vehicles. To achieve this, we modeled two consecutive intersections along the Amman BRT. Essentially, we evaluated three different control scenarios in addition to the current base scenario. These scenarios include adaptive traffic signal control, RCBPSC with no signal timing optimization, and RCBPSC with signal optimization. Simulation results indicate that the adaptive traffic signal timing has the worst operational performance in terms of average delay and Level of Service (LOS) compared to the base scenario. Additionally, the results show that BRT delays significantly decrease at both intersections when we implement RCBPSC scenarios. When implementing RCBPSC with optimization scenarios, the results show an average reduction of more than 60% in intersection delay, a decrease in emissions of more than 50%, and an improved LOS for system users compared to the base scenario. The findings of this work can help agencies improve the current operational condition of BRT when implementing RCBPSC.

A hybrid intersection control strategy for CAVs under fluctuating traffic demands: A value approximation approach

Confronted with growing and fluctuating traffic demands, urban transportation system has been encountering mounting challenges in traffic congestion, especially at intersections. With enhanced traffic control precision enabled by the emerging Connected and Automated Vehicle (CAV) technologies, this study proposes a hybrid control strategy for connected and automated traffic at urban intersections, which enables the integration of diverse control schemes to harness their strengths and mitigate their weaknesses. With rolling horizon strategy, a nonlinear optimization model is developed to determine the optimal traffic control plans considering both current status and forthcoming vehicle arrivals. Vehicle delays are elaborately characterized without relying on any empirical assumptions. The original model is converted to a Mixed Integer Programming with Quadratic Constraints (MIP-QC) by employing appropriate linearization techniques, which could be solved by commercial solvers. For the acquisition of instant and reliable solutions, a multilayer feedforward network-based approximate algorithm is developed, referred as Value Approximation Control (VAC) algorithm. Theoretical derivation is provided to validate the capability of VAC algorithm in the precise approximations of the value function in the traffic plan optimization problem, and ultimately enabling to acquire global optimal solutions via specific network design and training techniques. Numerical experiments on both artificial and researcher-collected datasets demonstrate that our proposed VAC algorithm achieves performance nearly equivalent to the mathematical model. Significantly, it outperforms current state-of-art traffic control methods in terms of both intersection throughput and average vehicle delay. Moreover, sensitivity analysis reveals the robustness of the VAC algorithm against inaccuracy in vehicle arrival information, and the stable performance even in the presence of significant disturbances.

Electric vehicle eco-driving strategy at signalized intersections based on optimal energy consumption

Electric vehicles (EVs), which are a great substitute for gasoline-powered vehicles, have the potential to achieve the goal of reducing energy consumption and emissions. However, the energy consumption of an EV is highly dependent on road contexts and driving behavior, especially at urban intersections. This paper proposes a novel ecological (eco) driving strategy (EDS) for EVs based on optimal energy consumption at an urban signalized intersection under moderate and dense traffic conditions. Firstly, we develop an energy consumption model for EVs considering several crucial factors such as road grade, curvature, rolling resistance, friction in bearing, aerodynamics resistance, motor ohmic loss, and regenerative braking. For better energy recovery at varying traffic speeds, we employ a sigmoid function to calculate the regenerative braking efficiency rather than a simple constant or linear function considered by many other studies. Secondly, we formulate an eco-driving optimal control problem subject to state constraints that minimize the energy consumption of EVs by finding a closed-form solution for acceleration/deceleration of vehicles over a time and distance horizon using Pontryagin’s minimum principle (PMP). Finally, we evaluate the efficacy of the proposed EDS using microscopic traffic simulations considering real traffic flow behavior at an urban signalized intersection and compare its performance to the (human-based) traditional driving strategy (TDS). The results demonstrate significant performance improvement in energy efficiency and waiting time for various traffic demands while ensuring driving safety and riding comfort. Our proposed strategy has a low computing cost and can be used as an advanced driver-assistance system (ADAS) in real-time.

Assessing Traffic Performance: Comparative Study of Human and Automated HGVs in Urban Intersections and Highway Segments

This study conducts a comparative analysis of traf�ic dynamics at urban signalized intersections and on highways, incorporating both human-operated and automated heavy goods vehicles (HGVs) using the PTV VISSIM simulation model. It examines the impacts of automated driving technologies on critical traf�ic performance metrics such as queue length, travel time, vehicle delay, emissions, and fuel consumption. Initial �indings indicate that automation in HGVs enhances traf�ic �low, particularly by reducing queue lengths and vehicle delays. However, varying levels of automation from cautious to aggressive reveal complex trade-offs between operational ef�iciency and environmental impacts. On highways, automated HGVs demonstrate superior performance by reducing travel times and delays while increasing throughput compared to human-driven HGVs. These results underscore the operational bene�its of automated HGVs under diverse traf�ic conditionsand highlight their signi�icant implications for transportation planning and policy-making. This research contributes valuable insights into the integration of automated technologies in transportation systems, facilitating informed decision-making for stakeholders considering the adoption of these advancements in the current infrastructure.

A correction method for the estimation of accident in different types of urban intersections

The main goal of this article is to present a method for estimating accidents in all types of level crossings in the city by using a type of statistical model. This study was conducted on 140 3-line and 4-line level intersections, both with and without traffic lights, in Tehran, whose accident information was collected in a period of three years (2019–2021) from police accident system reports and other required data. The data has been collected by field methods. To build the required model, the multiplicative form of the Riha equation, which is a comprehensive equation for predicting traffic accidents, has been used. In this equation, descriptive variables are selected in two continuous and binary forms, which are pre-determined by a functional form. They are obtained using the integral-differential method and are introduced to the mentioned equation. The results showed that in urban level intersections, the volume of traffic entering the intersection has the greatest effect on the amount of accidents, and for a certain volume of traffic, the effects of the geometric shape of the intersection (3-lane and 4-lane) and the type of traffic control (with or without lights) in the amount accidents are insignificant and negligible. According to the obtained results, the level of traffic safety can be significantly increased by controlling the volume of traffic entering intersections.

Predicting urban signal-controlled intersection congestion events using spatio-temporal neural point process

ABSTRACT The urban traffic signal-controlled intersections are of great significance for solving the problem of urban road congestion. Previous research on congestion prediction mainly aggregated data at the level of road segments or traffic flow at a coarse regulated time interval. Fine-grained prediction of congestion events at the lane-level and cycle-level enables detailed a understanding of spatio-temporal dependencies, leading to congestion reduction, improved efficiency. This paper presents a Spatio-Temporal Neural Point Process (STNPP) model that combines Graph Neural Networks and Neural Temporal Point Process to predict congestion events at urban intersections. The proposed model allows for complete prediction of congestion events, including their occurrence, development, dissipation. In the process of spatial correlation modeling, graph neural networks are used to model the spatial relationships between both region and intersections. The current intersection and its upstream/downstream areas are modeled separately. To model the temporal correlations at individual intersections, we focus on a specific lane and capture the evolution of congestion events using the Neural Point Process Gated Recurrent Unit (NPPGRU), which captures the temporal granularity changes of signal-controlled cycles in congestion events. Using actual traffic speed and signal-controlled data from Hangzhou city, we validate that the proposed method achieves stable predictive performance.

Analysis of driving left-turn errors of young and older drivers at urban intersections

Numerous traffic crashes occur at intersections in urban areas. Understanding the mechanism of driving errors at intersections and providing effective solutions will significantly reduce traffic injuries. The objective of this study is to examine the age and hazard level’s effects on driver left-turn errors at urban intersections. In order to achieve this goal, this study customized the cognitive reliability and error analysis method (CREAM) for left-turn driving task at intersections, and driver error profiles were investigated using a driving simulation experiment as a case study. The results showed that age did not significantly affect drivers’ left turn error probability, while the error probability of both groups of drivers increased with the hazard level. Drivers were most likely to have inadequate monitoring and misjudgment in left-turn maneuvers, more so in the older group. Young drivers were more likely to make planning, decision-making, and adjustment errors compared to older drivers. In addition, observation errors were the most likely cognitive (74.5%). This study achieves the common and characteristic performance of human errors under the three hazardous intersections for the two age groups, and provides a basis for the design of effective training modules and driver assistance systems.

Traffic simulation-emission modelling to evaluate impact of signal cycle on automobile emissions

Vehicular traffic comprises different types of vehicles with varying static and dynamic characteristics, under heterogeneous traffic conditions in India. The continuous growth of vehicles results in high congestion and becoming the main source of air pollution. The reduction in emissions is directly linked to the reduction in traffic congestion. At urban corridors, higher concentration of pollutants is observed near the traffic signals because of the influence of traffic signal operations on vehicular speed. The present research is carried out with the principal objective as the study of the effect of intersection control on emissions in the urban intersection of a metropolitan city. Microscopic traffic simulation models have been used to simulate real traffic conditions, and effectively represent the extensive performance of vehicles associated with speed and acceleration states. The simulation model is revised with optimum signal cycle time considering the signal phase system shows a substantial reduction in automobile emissions.

Assessment of genotoxicity of air pollution in urban areas using an integrated model of passive biomonitoring

Atmospheric pollution is a major public health issue and has become increasingly critical for human health. Urban atmospheric pollution is typically assessed through physicochemical indicators aligned with environmental legislation parameters, providing data on air quality levels. While the effects of pollution on sensitive organisms serve as a warning for public health decision-makers, there remains a need to explore the interpretation of environmental data on pollutants. The use of species adapted to urban environments as sentinels enables continuous and integrated monitoring of environmental pollution implications on biological systems. In this study, we investigated the use of the plant species Tradescantia pallida as a biomonitor to evaluate the genotoxic effects of atmospheric pollution under diverse vehicular traffic conditions. T. pallida was strategically planted at the leading urban intersections in Uberlândia, Brazil. During COVID-19 pandemic lockdowns, we compared indicators such as physical, biological, and traffic data at different intersections in residential and commercial zones. The reduction in vehicular traffic highlighted the sensitivity of plant species to changes in air and soil pollutants. T. pallida showed bioaccumulation of heavy metals Cd and Cr in monitored areas with higher traffic levels. Additionally, we established a multiple linear regression model to estimate genotoxicity using the micronucleus test, with chromium concentration in the soil (X1) and particulate matter (PM) in the atmosphere (X2) identified as the primary independent variables. Our findings provide a comprehensive portrait of the impact of vehicular traffic changes on PM and offer valuable insights for refining parameters and models of Environmental Health Surveillance.

Examining Factors Contributing to Motorcycle Collisions with Left-Turning Vehicles at Urban Intersection Locations

Motorcycle crashes account for a significant proportion of traffic-related fatalities on U.S. roadways. Compared with motor vehicles, motorcycles traveling straight ahead are more susceptible to collisions with left-turning vehicles at intersections (note – in a system where traffic travels on the right-hand side of the road). The limited knowledge of the causes and influences of this specific type of crash deters efforts to improve motorcycle safety and is partly influenced by two issues. First, significant variables are unknown; second, motorcycles comprise a small proportion of vehicles in the traffic stream. This study sought to understand the factors that may contribute to the disproportionate crash risk left-turning vehicles pose for motorcyclists while accounting for the imbalance of vehicle proportions. Data containing motorcycle-motor vehicle and motor vehicle-motor vehicle crashes involving left-turning motor vehicles at intersections in South Florida were collected from 2015 to 2017. The study applied logistic regression on a balanced dataset generated using the random oversampling technique. The proposed model improved the predictive accuracy and enabled the identification of factors contributing to motorcycle crashes with left-turning vehicles. A Bayesian network analysis was also applied to the balanced data to analyze the interrelationship of factors associated with motorcycle crashes with left-turning vehicles. Results indicated that the type of intersection and traffic control, time of day, age of drivers, sex of the motorcyclist, roadway type, and weather were significantly associated with motorcyclists’ susceptibility to collisions with left-turning vehicles. Recognizing these attributes could help devise engineering measures and policies for promoting motorcycle safety.

Real-world black carbon emissions of gasoline vehicles at urban intersections

To gain insight into the real-world black carbon (BC) emission patterns at urban intersections, we employed a portable emission measurement system (PEMS) to assess the BC emissions from three light-duty gasoline vehicles along a designated urban route. The BC emission factors were evaluated, and the contributions of vehicle operating conditions at the intersections to the total BC emissions were quantified. The results show that the BC emission factors in an intersection area range from 0.045 to 0.291 mg/km, higher than those at an intersection's connecting sections. The average BC emission factor at signalized intersections is 17.07% higher than at roundabouts. Emission contribution analysis of driving conditions showed that in a state of non-free traffic flow, acceleration and deceleration conditions are responsible for 39% ∼ 56% and 24% ∼ 33% of BC emissions at intersections, respectively. We also found that vehicle specific power (VSP) and delay time are almost equally crucial for BC emissions from vehicles at intersections in the multiple linear regression. Our research reveals the significant impact of vehicle delay time and acceleration conditions on black carbon emissions at urban intersections, further emphasizing the importance of smooth (congestion-free) intersection operation and steady driving in reducing urban black carbon emissions.