Search

Pedestrian intent prediction is an essential task for ensuring the safety of pedestrians and vehicles on the road. This task involves predicting whether a pedestrian intends to cross a road or not based on their behavior and surrounding environment. Previous studies have explored feature-based machine learning and vision-based deep learning models for this task but these methods have limitations in capturing the global spatio-temporal context and fusing different features of data effectively. To address these issues, we propose a novel hybrid framework HSTGCN for pedestrian intent prediction that combines spatio-temporal graph convolutional neural networks (STGCN) and long short-term memory (LSTM) networks. The proposed framework utilizes the strengths of both models by fusing multiple features, including skeleton pose, trajectory, height, orientation, and ego-vehicle speed, to predict their intentions accurately. The framework's performance have been evaluated on the JAAD benchmark dataset and the results show that it outperforms the state-of-the-art methods. The proposed framework has potential applications in developing intelligent transportation systems, autonomous vehicles, and pedestrian safety technologies. The utilization of multiple features can significantly improve the performance of the pedestrian intent prediction task. [ABSTRACT FROM AUTHOR]

In this study, pedestrians' violation rate at signalised crosswalks and the associated risk factors were investigated. The data for the study were obtained through roadside pedestrian observational surveys at 10 selected crosswalks within Accra Metropolis, Ghana. The associated risk factors for the red-light violations were determined using mixed-effect logistic regression model. The descriptive statistics revealed that the red-light violation rate in the Accra metropolis was approximately 62%. Most (63.5%) of the violations occurred during the evening and on weekends (73.6%). Over 98% of pedestrians demonstrated safety consciousness by way of crossing behaviour before and during crossing by observing oncoming traffic. From the mixed-effect logistics regression model, six independent variables being age, signal cycle length, number of pedestrians crossing at a time, day of the week and pedestrian light observation significantly influenced the risk of red-light violation by pedestrians. Effective law enforcement, education campaigns and engineering measures could be used to reduce the tendency of red-light violations by pedestrians and improve pedestrian safety at signalised crosswalks in the Accra metropolis. [ABSTRACT FROM AUTHOR]

Pedestrian safety becoming a serious issue, especially in developing nations, wherein higher crash rates have been reported by the World Health Organization. Despite evidence suggesting higher pedestrian crash counts at signalised intersections in urban areas, there is a lack of in-depth analysis in most developing countries. Motivated by this need, this study aims to: 1) identify significant roadway environment characteristics and traffic volume factors influencing pedestrian – vehicle accidents at signalised intersections in Amman, Jordan, 2) elucidate relationships between pedestrian – vehicle accidents and these factors, and 3) discuss the limitations of pedestrian crash data and propose solutions for future research. We have analysed 166 accidents at 47 signalised intersections in Amman during the period of 2007–2019. The multilevel Generalised Linear Mixed Gamma regression model is the best fit for the data, indicating significant positive correlations between pedestrian crash frequencies and Annual Average Daily Traffic, pedestrian crossing volume, number of lanes, average lane width, and number of parking sides. Conversely, commercial land use and the presence of public transit facilities showed significant negative correlations with pedestrian crashes. This work presents a novel approach that will help developing countries to determine and explain pedestrian crash causes while considering various challenges in these contexts. [ABSTRACT FROM AUTHOR]

Pedestrian Hybrid Beacons (PHBs) facilitate safe pedestrian crossings at marked crosswalks in unsignalized locations. However, few studies have recognized situations in which individuals may cross roads without PHB activation, potentially raising safety concerns. The influential factors contributing to pedestrian and bicycle crashes near PHBs remain insufficiently investigated. This study identifies characteristics of pedestrians and bicyclists prone to crossing without PHB activation. Additionally, this study uncovers differences between crash-prone and non-crash-prone PHB locations. Furthermore, this investigation examines the diverse factors that impact pedestrian and bicycle crashes in proximity to activated PHBs and accessible PHBs in Tucson, Arizona. Descriptive analysis and Bayesian multilevel Poisson-Lognormal regressions are conducted. Results indicate that young individuals (minimum age 13 and median age 29) and males were more likely to cross when PHBs were not activated. Moreover, the odds of pedestrian and bicycle crashes near PHBs increased when approach speeds decreased 5 to 10 minutes before crashes and at night (even with activated PHBs), while they decreased in regions with a greater proportion of non-White individuals and higher household incomes. These findings provide insights for transportation agencies, enabling them to implement targeted education and supplementary traffic control strategies to improve pedestrian and bicycle safety near PHBs. [ABSTRACT FROM AUTHOR]

In recent years, rapid advancements in the Autonomous Vehicles (AVs) industry have greatly motivated the research and development in pedestrian trajectory prediction and risk assessment. One of the critical requirements for AVs is to predict the future trajectories of pedestrians and provide collision warnings in an accurate and prompt manner. Nevertheless, accurate prediction of pedestrian trajectories remains a technical challenge, mainly caused by the heterogeneity of pedestrian crossing behavior and uncertainties in vehicle-pedestrian interactions. This paper proposes a deep learning-based method for pedestrian trajectory prediction and risk assessment, using trajectory data extracted from roadside LiDAR data and corresponding signal phasing information at MLK and Georgia Avenue in Chattanooga, TN. Meanwhile, a set of criteria referred to as the risk factor is established to quantitatively evaluate the risk of the pedestrian crossing behavior, which also serves as a learnable feature. A Long Short-Term Memory (LSTM) network is proposed, which takes the following data as the input: the pedestrian trajectory data, signal phasing data, and risk factors from the past 10 steps. Meanwhile, the network predicts the pedestrian trajectory and risk factor at the future time step. In the experimental study, the root-mean-square errors between the predicted and ground truth x and y coordinates are 0.225 meters and 0.377 meters, respectively, and the F1 score value for the risk factor is 99.6%, demonstrating the efficacy of the proposed LSTM-based methodology on pedestrian trajectory prediction and risk assessment. [ABSTRACT FROM AUTHOR]

Objectives: Currently, pedestrians' road-crossing decisions depend on the traffic at the crossing point, crossing opportunities, and circumstantial elements. Longer wait times on the curb and time pressure raise the number of traffic violations among pedestrians. The era of fully autonomous vehicles (FAVs) promises new interactions. External Human-Machine Interfaces (eHMIs) aim to increase the understanding of FAVs' intentions and will influence pedestrians' intent to cross. Yet, how pedestrian behaviors will change in the FAV era remains unclear. Further, there are no good metrics for evaluating the intricate interaction of crossing-related factors. Methods: In a laboratory study, sixty participants observed crossing scenarios of a typical one-lane road with 10–12 FAVs driving along, two possible eHMI messages ("Cross!"/"Stop!"), and varying crossing opportunities (safe, risky, and unsafe). Participants had to indicate when they intended to cross the road using a designated button. Half of the participants were induced to feel time pressure. We developed index scores to convey the complexity of such crossing situations from the perspective of a pedestrian and used them to analyze the experimental data. Results: In total, 48% of participants' indications were to cross in safe crossing opportunities, 34% risky, and 18% unsafe; 69% were made when the eHMI proposition was "Cross!" and 31% for "Stop!". High, significant, and negative correlations were found for compatible responses, e.g., with a safe crossing gap and an eHMI sign to "Cross!". The opposite was true for incompatibility, e.g., a safe crossing gap and an eHMI sign to "Stop!" or an unsafe crossing gap and an eHMI sign to "Cross!". The time pressure group's median times to cross were shorter, making riskier decisions. Conclusion: Our findings reflect a tendency to comply with the eHMI. In more complex scenarios where the crossing opportunity was uncertain or waiting times were longer, we observed that pedestrians were more inclined to follow the eHMI's guidance to cross. These findings suggest that pedestrians may be more likely to follow the eHMI's suggestion to cross than their self-skill, especially under time pressure. Our indices and metrics reflect the intricate interaction aspects of pedestrian behavior with eHMIs. [ABSTRACT FROM AUTHOR]

Objective: Automatic emergency braking systems with pedestrian detection (PAEB) are effective at preventing pedestrian crashes, but the safety benefits are not observed at night. This study used the Insurance Institute for Highway Safety (IIHS) PAEB test data to characterize PAEB responses in different lighting conditions and for different rated systems. Methods: Data from 6,919 IIHS PAEB tests were retrieved from IIHS databases. Invalid trials, trials without AEB, and trials with outliers were removed leaving 5,894 trials from 212 model year 2018 to 2023 vehicles for analysis. PAEB responses were characterized by computing the time-to-collision (TTC) of forward collision warning (FCW) and AEB; brake threat number (BTN); mean deceleration; maximum deceleration; and maximum jerk. A linear mixed-effects model was used to predict each dependent measure with scenario (crossing adult, stationary adult), speed, rating (superior, basic/advanced), lighting (day, night with high beams, night with low beams), and their interactions. Vehicle was included as a random effect. A Bonferroni correction was applied to maintain a family-wise type-1 error rate of 0.05 across 138 total hypothesis tests. Results: PAEB system warnings were later and automatic braking occurred later as speed increased at night with low beams but changed little at night with high beams and during the day (p < 0.0004). BTN increased more rapidly as speed increased at night with low beams compared with high beams and during the day (p < 0.0004). Based on the BTN model, on average, PAEB systems can brake to avoid the adult mannequin (BTN < 1) when closing speed is less than 67 km/h during the day and at night with high beams but only when closing speed is less than 49 km/h at night with low beams. Superior-rated PAEB systems warned and braked earlier compared with basic/advanced-rated systems (p < 0.0004). Conclusions: Increased lighting from high beams made nighttime performance resemble daytime performance in controlled testing. Increasing output from vehicle low beams, increasing the use of high beams, and enhancing overhead lighting around crosswalks and pedestrian areas are all methods for increasing lighting, improving pedestrian conspicuity, and enhancing PAEB performance to prevent pedestrian crashes. [ABSTRACT FROM AUTHOR]

Studies of macroscopic speed modeling of bidirectional pedestrian cross-flows have relied heavily on scenario experiments, but the data itself may be deficient because large-scale scenario experiments are not easy to organize and subjects may not be walking under normal conditions. In order to explore the possibility of using microscopic pedestrian flow simulations for macroscopic speed modeling of pedestrian flows, a series of two-way pedestrian cross-flow simulation experiments were designed. Bidirectional pedestrian flows are defined as Peds1 and Peds2. The crossing angle and pedestrian flow rate are used as variables, and a bidirectional pedestrian flows simulation is designed as an orthogonal experiment. The crossing angles range from 15 to 165 degrees, and bidirectional pedestrian flow rate range from 1 ped/s to 8 ped/s. A series of simulations are built and performed on the GIS agent-based modeling architecture (GAMA) platform. By analyzing the flow data of bidirectional flows in the crossing area, it is found that when the Peds1 density falls below a threshold, Peds1 speed is determined by pedestrians themselves and mainly remains in a free flow state; otherwise, the Peds1 speed decreases with density. The clear effects such as Peds2 density on the Peds1 speed cannot be determined. A piecewise function combined with a linear function and an exponential function is constructed as the Peds1 speed model considering the influence of the crossing angle. The calibration results show that the piecewise function should be better than the non-piecewise function. Compared to the results of established studies, the results in this paper have some differences. Therefore, the simulation method cannot completely replace the scene experiments. However, this approach can provide suggestions for subsequent refinement of the experimental program, as well as a feasible direction for the construction of a speed relationship for bidirectional pedestrian flows. [ABSTRACT FROM AUTHOR]

The pedestrians are the most exposed amongest all road traffic users to the possibility of being attacked or harmed, either physically or emotionally. In the present investigational study, an attempt is made to develop the model on pedestrian road crossing behaviour by considering the elements of pedestrian crossing behaviour, especially the size of the vehicular gap accepted by pedestrians and also pedestrians decision to cross or not cross the road. A field investigation was carried out at two zebra crossing facilities located at two major roundabouts in Shivamogga city. Data collection and extraction was done by utilising video-graphic data in real-time traffic conditions by the Department of Traffic Police, Shivamogga and also, by observing the behaviour of pedestrians while crossing the road. The study will also aid in determining correlations between pedestrian characteristics, crossing facilities, and vehicular traffic. This data will be analysed by regression methods in statistical analysis. As a result of this research, it is intended that a model of pedestrian gap acceptance and pedestrian crossing choice could be developed that also includes the factors that pedestrians look for when accepting the vehicle gaps between the vehicles to cross the crosswalks in roundabouts. [ABSTRACT FROM AUTHOR]

In response to the sudden violation of pedestrians crossing the road, intelligent vehicles take into account factors such as the road conditions in the accident zone, traffic rules, and surrounding vehicles' driving status to make emergency evasive decisions. Thus, the collision simulation models for pedestrians and three types of vehicles, i.e., sedans, Sport Utility Vehicles (SUVs), and Multi-Purpose Vehicle (MPVs), are built to investigate the impact of vehicle types, vehicle steering angles, collision speeds, collision positions, and pedestrian orientations on head injuries of pedestrians. The results indicate that the Head Injury Criterion (HIC) value of the head increases with the increase in collision speed. Regarding the steering angles, when a vehicle's steering direction aligns with a pedestrian's position, the pedestrian remains on top of the vehicle's hood for a longer period and moves together with the vehicle after the collision. This effectively reduces head injuries to pedestrians. However, when the vehicle's steering direction is opposite to the pedestrian's position, the pedestrian directly collides with the ground, resulting in higher head injuries. Among them, MPVs cause the most severe injuries, followed by SUVs, and sedans have the least impact. Overall, intelligent vehicles have great potential to reduce head injuries of pedestrians in the event of sudden pedestrian-vehicle collisions by combining with Automatic Emergency Steering (AES) measures. In the future, efforts need to be made to establish an optimized steering strategy and optimize the handling of situations where steering is ineffective or even harmful. [ABSTRACT FROM AUTHOR]

Problem, research strategy, and findings: As active transport planning gains momentum worldwide, our study underscores the importance of connecting people and places by focusing on the convenience dimension of walkability. Specifically, we used the pedestrian detour ratio (PDR) to measure the degree of circuity of a walking route. We considered residential buildings as origins and 10 different types of public facilities as destinations within the walkable range of 1 km. This led to a territory-wide analysis covering 3.85 million origin–destination pairs in Hong Kong. Overall, walking convenience was the best in the central business district (CBD), but variations existed by district and by facility. Through an assessment matrix, 35.8% of home–destination pairs required attention. When examined at the street block and village cluster levels, walking inconvenience was associated with vehicle-oriented street blocks (with higher vehicular traffic and more private parking spaces), high-income areas, and difficult terrain. Pedestrian crossings, major roads, and bus stops enhanced route directness. This research is a first step in helping quantify the PDR distribution across different cities and their various functional areas. Takeaway for practice: In areas where walking is inconvenient, treatments to calm vehicular traffic and facilitate pedestrian crossings should be stipulated. In the longer term, we recommend integrating the PDR in the design and planning of streets, especially around essential facilities. [ABSTRACT FROM AUTHOR]

Since autonomous vehicles (AV) are in the testing process, it is an open question of how pedestrians will communicate with self-driving cars. Nowadays, explicit communication pattern is the main way of pedestrian-driver interaction, however, AV may use implicit communication when making crossing decisions. This study aims to analyze pedestrians' gaze behavior when crossing the road using an eye camera and find the most applicable location for the LED interface on AVs. 10 pedestrian crossings in Gyor, Hungary were analyzed using the synchronized eye-tracking (ET) technology and regular video cameras for combined data processing. The data were analyzed using digital image processing techniques and statistical methods to identify where pedestrians looked and whether a pedestrian-driver interaction was captured during the crossing maneuver. [ABSTRACT FROM AUTHOR]

AbstractRich training datasets are essential for machine learning models to work well. Safety-critical applications, such as autonomous driving, that heavily rely on supervised learning algorithms, require accurate prediction of human behavioral intentions. Training such prediction algorithms requires not only micro-level action labels but also the estimation of human cognitive states and corresponding reasoning explanations at the same granularity level. However, traditional data labeling tools have limited support for these annotation tasks and deficient data structure. This article proposes a novel annotation tool, MindReaD, that facilitates labeling micro-level interactions with free-form reasoning text and grounding text with their visual representations. Focusing on pedestrian–vehicle interactions as a case study, we defined a data structure to label interaction events, collected data from 83 participants using multiple UI designs, and used the data to train ML models for predicting pedestrian crossing intent. The results show that the unique UI design features of Point-and-Explain and multiple prompts can significantly increase the quality of reasoning data annotations. The model trained with data using the proposed data annotation design outperforms the baseline data, with approximately 7% improvement in overall accuracy. User experience study also confirms positive user attitudes towards the developed data annotation system. The data annotation tool will be released to the public. [ABSTRACT FROM AUTHOR]

Unnecessary vehicular delay occurs at actuated signalized intersections during 'ghost' pedestrian intervals when a pedestrian activates the pushbutton then jaywalks. Safety issues arise when pedestrians remain in the crosswalk at the end of the Flashing Don't Walk phase, and vehicles receive a circular green. A Pedestrian Call Extension and Cancelation System was evaluated at a signalized midblock crossing in Hillsboro, OR. Thermal sensors and controller logic were implemented to detect pedestrians and passively cancel or extend calls. A Case 1-after study was conducted to evaluate how vehicular delay and pedestrian behavior was impacted by the system. 1,649 observations Case 1 and 3,002 observations after system installation were recorded. Pedestrian delay did not change, but average vehicular stop time delay significantly decreased by 12 sec. 76 extensions occurred with 99.2% accuracy. Findings suggest that transportation agencies could improve driver waiting time and pedestrian safety by using dynamic passive pedestrian detection. [ABSTRACT FROM AUTHOR]

Objective Pedestrian injury is a leading contributor to childhood deaths. This study compared the crossing behaviors of children with adults when crossing in virtual single-lane vs. two-lane traffic conditions. Method Using a fully immersive virtual reality system, children 7–10 years and adults crossed streets with traffic in one lane (near lane) or in two lanes (near and far lane) with 0 offset so cars from opposing directions arrived at the child's crossing line at the same time. On each trial, pedestrians made a decision on when to cross and then completed the crossing, with measures of attention and crossing behaviors automatically recorded by the system as they did so. Results In comparison to crossing a single lane of traffic, crossing two-lane roads increased injury risk for all pedestrians, though children experienced significantly greater risk than adults. Children predominantly crossed by stopping before entering the far lane, whereas adults showed greater synchronization of self-movement to traffic flow and more often crossed both lanes without stopping. Conclusions Children experience more high-risk outcomes than adults when crossing single-lane roads. Crossing two-lane roads elevates risk for pedestrians of both ages, though this risk is significantly greater for child than adult pedestrians. The predominant strategy used to cross two lanes of traffic shows significant developmental changes. Implications for injury prevention are discussed. [ABSTRACT FROM AUTHOR]

Objective: In Bangladesh, drivers' failure to yield to pedestrians at designated crossings poses a significant safety risk and discourages their use of such crossings. The use of behavior change theories could be more appropriate in such complex situations where the interdependent behaviors of drivers and pedestrians interact. While many studies have identified factors that affect drivers' yielding behavior in the literature, fewer efforts have been made to apply behavior change theories in exploring and validating these factors, and to reach a consensus among competing road users. This study is among the first to utilize behavior change theories in Bangladesh to identify pedestrians' safety factors that could promote drivers' yielding behavior, upon which a consensus between drivers and pedestrians could be established. Methods: A self-reported attitudinal survey was administered to 202 drivers on two highways in Bangladesh with a questionnaire using the capability, opportunity, motivation, and behavior (COM-B) model for the comprehensive coverage of behavior change theories. The focus group interviews were also conducted with 40 pedestrians and 19 drivers who have experience with four crossing sites on the selected highways. The collected data were analyzed using a regression model to identify significant factors influencing the drivers' yielding behavior. These factors were then justified using a deductive thematic coding framework based on behavior change theories. Results: The regression model explained the variance in drivers' yielding by 45.1% with eight factors. The model found seven positive significant contributory factors in the drivers' yielding that could promote pedestrian safety. Of them, the motivation factors were avoiding random crossing by pedestrians, vulnerable groups, assertiveness, and facial fear expressions; and the opportunity factors were traffic signs or advanced yield lines, crossing in groups at specific times, and enforcement. Conclusions: The study's findings have practical implications for policymakers, highway designers, and other stakeholders involved in promoting pedestrian safety by acknowledging their stake in making any decision that might impact them. Highway designers can use the thematic coding framework to recommend any contributory factors involved, where competing drivers' unwillingness to yield is the primary threat to pedestrians' safety. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Modern Science is the property of Alcide De Gasperi University of Euroregional Economy and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automobile Technology is the property of Automobile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

While pedestrian crashes on suburban roads have received more attention over recent years, the role of pedestrian crossing risk in areas adjacent to pedestrian crossing facilities, such as pedestrian overpasses, has been neglected. Most pedestrians in suburban areas tend to avoid pedestrian overpasses, exhibiting crossing behaviors that increase the likelihood of pedestrian-involving crashes. As a result of the presence of overpasses, drivers may think that there are no pedestrians in the surroundings, so they choose a speed based only on the prevailing traffic and road environment without accounting for potential interactions with pedestrians. Consequently, crashes will occur, with pedestrians typically being the most seriously affected casualties. In this study, using video recordings from a suburban road in Amol-Babol, Iran, the risk of pedestrian crossing behavior in areas near pedestrian overpasses is investigated. The speed selection behavior of drivers in these areas has also been examined using speedometer cameras. To quantify the level of risk for pedestrians when interacting with approaching vehicles during the crossing movements, the post encroachment time (PET) was used as a surrogate safety measure. Based on critical thresholds of PET, three different risk levels were identified using a K-means algorithm: high, medium, and low risk. To identify the elements affecting the risk of pedestrian crossing behavior, structural equation models were estimated for all three risk levels. The results showed that human factors, relating to both drivers and pedestrians, have a dominant impact on pedestrian safety, especially in high and medium risk contexts. Road and vehicle factors were also found to have statistically observable effects on pedestrian safety, but to a milder extent compared to human factors. The findings of this study highlight the need for intervening in several aspects of vehicle-pedestrian interactions with critical importance for pedestrian safety, including road users' performance and compliance, state of alertness, and interaction with road infrastructure. [ABSTRACT FROM AUTHOR]

AbstractProblem, research strategy, and findingsTakeaway for practiceCrossing distance is considered a factor in both pedestrian safety and behavior. However, it has seldom been quantified within or across entire cities or related to walking outcomes. Combining data encoded in OpenStreetMap and drawn from high-resolution satellite imagery, we measured formal pedestrian crossings throughout a dense European city (Paris [France]), a dense American city (San Francisco [CA]), and a less-dense, more car-centric American city (Irvine [CA]). This granular approach—covering roughly 49,000 total crossings—identified inter- and intraurban spatial patterns in the distribution of pedestrian crossing distance, including clusters of long crossings that likely deter walking and increase its risk. By overlaying recent pedestrian–vehicle collisions on these novel data sets we found that longer crossing distance correlated with increased likelihood of collisions, raising the salience of traffic-calming interventions.Quantifying pedestrian crossing distance at the scale of entire municipalities empowers transportation planners to identify pedestrian-hostile crossings (individuals and clusters), add context to collision trends, and geographically target locations for traffic calming. These cases collectively demonstrate how the increasing prioritization of the automobile in city planning quantitatively changes (and degrades) the pedestrian environment, as well as how low-tech investments, such as sidewalk extensions and refuge islands, can mitigate these trends. [ABSTRACT FROM AUTHOR]

Pedestrian two-stage crossings are common at large, busy signalized intersections with long crosswalks and high traffic volumes. This design aims to address pedestrian operation and safety by allowing navigation in two stages, negotiating each traffic direction separately. Understanding crosswalk behavior, especially during bidirectional interactions, is essential. This paper presents a two-stage pedestrian crossing model based on Physics-Informed Neural Networks (PINNs), incorporating fluid dynamics equations to determine characteristics such as speed, density, acceleration, and Reynolds number during crossings. The study shows that PINNs outperform traditional deep learning methods in calculating and predicting pedestrian fluid properties, achieving a mean squared error as low as 10–8. The model effectively captures dynamic pedestrian flow characteristics and provides insights into pedestrian behavior impacts. The results are significant for designing pedestrian facilities to ensure comfort and optimizing signal timing to enhance mobility and safety. Additionally, these findings can aid autonomous vehicles in better understanding pedestrian intentions in intelligent transportation systems. [ABSTRACT FROM AUTHOR]

There has been a concerning rise in pedestrian fatalities resulting from traffic accidents. This study conducts an in-depth analysis of the factors that contribute to the injury severity of pedestrians considering human, vehicle, roadway, and environmental characteristics of the crashes. A novel approach is proposed by combing a data mining technique and mixed logit models. First, the Apriori algorithm is employed to uncover patterns between fatal and incapacitating injury outcomes and their influencing factors. Then, mixed logit models are developed to investigate heterogeneity across all observations under two different lighting conditions. It is found that eight variables show heterogeneity affecting the injury severity of crash outcomes. Results also indicate that drivers older than 65 years old will increase the probability of pedestrian injury severity at dark-unlighted roads. Additionally, the present of signal and double yellow line has could increase the injury severity. Creating optimal lighting conditions at pedestrian crossings during nighttime hours and enhancing safety education initiatives for pedestrians are critical factors to improve pedestrian safety. The finding of this study will benefit policymakers and road safety professionals develop more effective strategies for preventing pedestrian injuries in vehicle crashes. [ABSTRACT FROM AUTHOR]

The major advances in intelligent transportation systems are pushing societal services toward autonomy where road management is to be more agile in order to cope with changes and continue to yield optimal performance. However, the pedestrian experience is not sufficiently considered. Particularly, signalized intersections are expected to be popular if not dominant in urban settings where pedestrian density is high. This paper presents the design of a novel environment for simulating human motion on signalized crosswalks at a fine-grained level. Such a simulation not only captures typical behavior, but also handles cases where large pedestrian groups cross from both directions. The proposed simulator is instrumental for optimized road configuration management where the pedestrians' quality of experience, for example, waiting time, is factored in. The validation results using field data show that an accuracy of 98.37% can be obtained for the estimated crossing time. Other results using synthetic data show that our simulator enables optimized traffic light scheduling that diminishes pedestrians' waiting time without sacrificing vehicular throughput. [ABSTRACT FROM AUTHOR]

This study examines the impact of urban form and street infrastructure on pedestrian safety in Atlanta, Georgia, and Boston, Massachusetts. With a significant rise in pedestrian fatalities over the past decade, understanding how cities' built environments influence safety is critical. We conducted geospatial analyses and statistical tests, revealing unique patterns in each city. Atlanta's sprawling, motorist-oriented layout is associated with increased pedestrian accidents, particularly at crosswalks, due to limited land use diversity, arterial roads, and streets with high speed limits and multiple lanes. In contrast, Boston's compact, pedestrian-oriented design leads to improved safety, featuring safer pedestrian crossings, greater land use diversity, reduced arterial roads and lower speed limits on single-lane streets. This study also highlights the importance of diverse urban forms and pedestrian infrastructure in shaping pedestrian safety. While population density and land use diversity impact accident rates, the presence of crosswalks and street configurations play crucial roles. Our findings underscore the urgency for urban planners to prioritize pedestrian safety through targeted interventions, such as enhancing crosswalks, reducing speed limits and promoting mixed land use. Future research should explore additional variables, alternative modelling techniques and non-linear approaches to gain a more comprehensive understanding of these complex relationships. [ABSTRACT FROM AUTHOR]

The study primarily seeks to investigate the behavioral attribution of distraction in pedestrian road crossing. A distraction-themed questionnaire survey was conducted across Kolkata city, India, to understand the contribution of distraction to near-misses and injuries. The survey response showed that among all reported respondents, 13.7% (61) encountered at least one near-miss and 4.5% (20) experienced at least one accident in the past. The video-based observational field study of 2,360 pedestrians revealed that 28.7% of the pedestrians were distracted while crossing the road. Pedestrians who text walked relatively slowly and 7.9% more likely to violate signal. Additionally, mobile phone talkers were observed to be 4.5% more likely to nearly hit/bump into another oncoming pedestrian. The present study constitutes vital information for planners and policymakers and plays a pivotal role in identifying critical intersections and developing countermeasures to minimize the impact or occurrence of pedestrian distraction and unsafe behavior. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The use of pedestrian bridges is often ineffective as pedestrians tend to prefer crossing directly on the roadway, even though heavy traffic conditions increase the risk of accidents. This lowers the safety level of crossers and causes traffic problems. This study aims to evaluate the efficient use of pedestrian bridges and determine public perceptions of road crossing facilities. The research was conducted using geometric assessment and road performance evaluation methods that refer to the 2023 Indonesian Road Capacity Guidelines. In addition, crossing times were analyzed based on the traffic TCT distribution histogram, as well as pedestrian perceptions of crossing facilities. The evaluation results show that the effectiveness of road services falls into category A. Based on pedestrian perceptions, 60% of respondents prefer to cross directly on the roadway, with an average TCT of 1.2 m/sec. From the results of the CSI analysis, the level of respondents' satisfaction with the condition of the pedestrian bridge is 71.373%. Based on the results of the study, the use of pedestrian bridges will be effective in the next 15 years. Recommendations proposed to increase the effectiveness of the use of pedestrian bridges and the level of pedestrian safety is the use of guardrails. [ABSTRACT FROM AUTHOR]

Composite soil‐steel corrugated structures are well recognized and widely used for construction of culverts and pedestrian or animal crossings. Moreover, for the past decade corrugated soil‐steel structures because of their large span are also recognized and chosen for bridges and tunnels engineering. Record holder composite corrugated structure of 32.40 m span encourages new research in the development of innovations. This paper investigates innovative the deepest corrugation cross‐section strengthened with circular hollow section steel pipes influence on plate utilization of large span soil‐steel composite bridge. The numerical 2D model of 17.5 m span structure was developed for investigation. Parametric analysis indicated that introduction of circular pipes will reduce corrugated profile steel thickness because of reduction of buckling length of straight region of corrugation. Moreover, 3D numerical analysis of buckling shapes allowed to conclude that local buckling of the deepest corrugation of 500 × 237 mm could be controlled strengthening the plates with circular steel pipes. [ABSTRACT FROM AUTHOR]

This paper outlines the planning of a bridge in central Germany. Scheduled for construction in mid‐2024, this new bridge is a replacement for a century‐old pedestrian bridge crossing the Lahn river. The proposed bridge will be an airtight‐welded arch bridge, employing steel cross‐sections in both the arch and tension member. Designed as a single‐span, the arches extend 48.0m over the Lahn. The two arches have a flat rise of 4.65m, supporting the roadway through 9 inclined flat steel hangers. This paper delves into the structural engineering aspects, exploring challenges inherent in the design process. An examination of the parametric design process, facilitated through 3‐D modeling in Rhino® and Grasshopper®, will be presented, along with insights into their interface with the finite element modeling software, RFEM®. This process enables an engineering approach to form‐finding and structure optimisation through iterative design checks for various elements and stages of the structural analysis. [ABSTRACT FROM AUTHOR]

Observational studies, whether conducted on-site or through simulation, are practical options for investigating and comprehending pedestrian behaviour and validating the findings of similar studies that have already taken place on the same subject. Although they present difficulties in demographic characterisation and personal context, observation represents the adoption of actual behaviour, highlighting the different scenarios, contexts and characteristics of the environment and infrastructure in urban areas. However, with the growth in simulators, surveys, and data protection issues in Europe, field observation is less considered, and several studies have been left aside. Based on observation, this study answers behavioural and demographic questions, namely age and gender, using the data of six pedestrian crossings in Coimbra, Portugal. This experience occurred on different days of the week (the week before lockdown), registering blind (and non-blind) pedestrians' behaviour facing the electric vehicle in 6 crosswalks, 30 min in each crosswalk, morning or afternoon, with favourable weather conditions outside peak hours In total 180 (30*6) minutes were filmed and evaluated. The relationships between responsibility (when one pedestrian is guided by another) and group action in decision-making and crossing behaviour were also investigated. Another relevant aspect studied was the relationship between pedestrians and electric vehicles in different contexts. During the research, an electric vehicle was inserted in the observational experience, circulating in the streets to observe the pedestrians' reaction to the absence of noise. In this context, blind pedestrians were invited to perform crossings in these areas and identify the presence of the electric vehicle, to identify some differences in the behaviour of blind pedestrians and non-blind pedestrians. The results indicate that blind pedestrians tend to be more cautious than non-blind pedestrians, that younger and elderly pedestrians tend to have more dangerous and less calculated behaviours than other road users and that the differences are more perceptible in age than gender. It should be noted that when in a group, especially adolescents, they commit more traffic errors. Furthermore, regarding the absence of noise associated with the electric vehicle, in moments of pedestrian distraction, if the driver is not attentive, there is an increase in the risk of accidents. [ABSTRACT FROM AUTHOR]

AbstractIn the field of autonomous driving research, the use of immersive virtual reality (VR) techniques is widespread to enable a variety of studies under safe and controlled conditions. However, this methodology is only valid and consistent if the conduct of participants in the simulated setting mirrors their actions in an actual environment. In this paper, we present a first and innovative approach to evaluating what we term the behavioural gap, a concept that captures the disparity in a participant’s conduct when engaging in a VR experiment compared to an equivalent real-world situation. To this end, we developed a digital twin of a pre-existed crosswalk and carried out a field experiment (N = 18) to investigate pedestrian-autonomous vehicle interaction in both real and simulated driving conditions. In the experiment, the pedestrian attempts to cross the road in the presence of different driving styles and an external Human-Machine Interface (eHMI). By combining survey-based and behavioural analysis methodologies, we develop a quantitative approach to empirically assess the behavioural gap, as a mechanism to validate data obtained from real subjects interacting in a simulated VR-based environment. Results show that participants are more cautious and curious in VR, affecting their speed and decisions, and that VR interfaces significantly influence their actions. [ABSTRACT FROM AUTHOR]

While automobile transportation is increasing worldwide, it also negatively affects the safety of road users. Along with the neglect of traffic rules, pedestrians account for 22% of all highway traffic deaths. Millions of pedestrians suffer non-fatal injuries from these accidents. Most of these injuries and deaths occur at crosswalks, where the highway and pedestrians intersect. In this study, deep learning-based a new hybrid mobile CNN approaches are proposed to reduce injuries and deaths by automatically recognizing of crosswalks in autonomous vehicles. The first of these proposed approaches is the HMCNet approach, which is a hybrid model in which the MobileNetv3 and MNasNet CNN models are used together. This model achieves approximately 2% more accuracy than the peak performance of the lean used MobileNetv3 and MNasNet models. Another proposed approach is the FHMCNet approach, which increases the success of the HMCNet approach. In the FHMCNet approach, LSVC feature selection method and SVM classification method are used in addition to HMCNet. This approach increased the classification success of HMCNet by more than approximately 2%. Finally, the proposed FHMCNet offered approximately 3% more classification accuracy than state-of-the-art methods in the literature. [ABSTRACT FROM AUTHOR]

External human–machine interfaces (eHMIs) serve as communication bridges between autonomous vehicles (AVs) and road users, ensuring that vehicles convey information clearly to those around them. While their potential has been explored in one-to-one contexts, the effectiveness of eHMIs in complex, real-world scenarios with multiple pedestrians remains relatively unexplored. Addressing this gap, our study provides an in-depth evaluation of how various eHMI displays affect pedestrian behavior. The research aimed to identify eHMI configurations that most effectively convey an AV's information, thereby enhancing pedestrian safety. Incorporating a mixed-methods approach, our study combined controlled outdoor experiments, involving 31 participants initially and 14 in a follow-up session, supplemented by an intercept survey involving 171 additional individuals. The participants were exposed to various eHMI displays in crossing scenarios to measure their impact on pedestrian perception and crossing behavior. Our findings reveal that the integration of a flashing green LED, robotic sign, and countdown timer constitutes the most effective eHMI display. This configuration notably increased pedestrians' willingness to cross and decreased their response times, indicating a strong preference and enhanced concept understanding. These findings lay the groundwork for future developments in AV technology and traffic safety, potentially guiding policymakers and manufacturers in creating safer urban environments. [ABSTRACT FROM AUTHOR]

Road accidents involving pedestrians are frequent at urban signalised intersections predominantly due to unsafe pedestrian crossings. A good proportion of these accidents are occurring at T-intersection. This study aims at analysing pedestrian crossing behaviour at signalised T-intersections. Data is collected from five signalised T-intersections in Delhi, India, by using video recordings and a perception based questionnaire survey. Data is analysed using Chi-square, student t-test and Kendall's W hypothesis testing techniques. Significant variables are used to develop binary and ordinal logistic regression models. Results show that only a small percentage of pedestrians are abiding by the law to cross the road. Further a host of significant variables such as pedestrian demographics, trip purpose and state of the journey are significantly affecting crossing behaviour. The findings would be useful to improve pedestrians' safety and enrich the knowledge of pedestrian crossing behaviour at signalised T-intersections. [ABSTRACT FROM AUTHOR]

• Adolescents with ADHD are poorer than adolescents with no-ADHD in driving skills. • The ADHD group drive at speed and stop less at red lights and crosswalks. • Computerized cognitive training improves executive functioning in adolescents with ADHD. • Driving skills of both ADHD and non-ADHD adolescents were enhanced after training. • Computerized cognitive training may improve driving skills in the pre-driving stage. Youth with Attention Deficit Hyperactivity Disorder (ADHD) face challenges with road safety. While executive functions are developing in all young drivers, those diagnosed with ADHD have deficits in executive functions that are known to be important in driving. The aims of this study were to compare the executive functions and driving skills of adolescents identified with and without ADHD, and to evaluate whether a computerized cognitive training program is associated with improvement in executive functions (i.e., attention, working memory, inhibition) and driving skills. The hypotheses were: a) compared to a group of adolescents without ADHD, executive functions and driving skills of adolescents with ADHD will be poorer at pre-training; and b) while both groups will improve their executive function and driving skills after receiving the computerized cognitive training, the improvement will be greater in the ADHD group. This study used a quasi-experimental pre- and post-training control group design. Thirty adolescents aged 16 to 18 years with no prior driving experience participated in the study. Half (50 %) were diagnosed with ADHD and groups were matched by age. The Integrated Visual and Auditory (IVA-2) functional test was administered to insure proper inclusion in both groups. Twelve 45-minute sessions aimed at improving executive functioning were provided to both groups with the Captain's Log cognitive training software. Executive functioning was measured with cognitive tasks: attention with the Continuous Performance Task (CPT), working memory with the N-Back task, and inhibition with a Go/No Go task. Driving skills were appraised with a virtual reality driving task measuring speed management (mean, variability, percentage over the speed limit) and stopping (deceleration, and frequency of stopping at red traffic lights and pedestrian crosswalks). Executive functioning and driving skills were measured at pre- and post-training. Two repeated measures MANOVA were used to test the research hypotheses. Results from the IVA-2 confirmed group membership. At pre-training, the analyses showed that the ADHD group performed more poorly than the non-ADHD group on the CPT, N-Back, Go/No Go, and driving task (higher average driving speed, higher speed standard deviation and stopping less at red lights and crosswalks). At post-training, there was a significant improvement in executive functions and driving skills in both groups. Compared to the non-ADHD group, the cognitive training program was associated with stronger improvement in executive functions for the ADHD group. However, improvement in driving skills did not differ between groups. Results confirmed previous findings that computerized cognitive training is associated with greater improvement in executive functioning in adolescents diagnosed with ADHD than in non-ADHD individuals. Results also suggest that the training may have some potential to improve driving skills of both adolescents with and without ADHD in the pre-driving stage. Future research is recommended to examine computerized cognitive training aiming more directly to improve on-road driving performance of young ADHD individuals. [ABSTRACT FROM AUTHOR]

Crosswalks play a fundamental role in road safety. However, over time, many suffer wear and tear that makes them difficult to see. This project presents a solution based on the use of computer vision techniques for identifying and classifying the level of wear on crosswalks. The proposed system uses a convolutional neural network (CNN) to analyze images of crosswalks, determining their wear status. The design includes a prototype system mounted on a vehicle, equipped with cameras and processing units to collect and analyze data in real time as the vehicle traverses traffic routes. The collected data are then transmitted to a web application for further analysis and reporting. The prototype was validated through extensive tests in a real urban environment, comparing its assessments with manual inspections conducted by experts. Results from these tests showed that the system could accurately classify crosswalk wear with a high degree of accuracy, demonstrating its potential for aiding maintenance authorities in efficiently prioritizing interventions. [ABSTRACT FROM AUTHOR]

Featured Application: Featured Application: Fire Dynamics Simulator Pyrosim. In the existing research on tunnel fires, researchers primarily focus on straight tunnels, neglecting the impact of curved sidewalls in curved tunnels. Based on the theory of smoke diffusion, a series of CFD numerical simulations was conducted using the Fire Dynamics Simulator to investigate the characteristics of smoke distribution in a curved highway tunnel. The results indicated that distinct smoke distribution characteristics were observed when a fire occurred in a curved tunnel compared with those observed in straight tunnels, with significant differences particularly evident for the radius of curvature of the tunnel below 1000 m. By comparing the smoke distribution characteristics from various fire source locations, the most unfavorable fire source locations within a curved tunnel were determined. High-temperature fire smoke bounds between the inner and outer walls of the tunnel, leading to the formation of multiple high-temperature zones in proximity to the fire source, rather than diffusing directly towards the exit in a linear tunnel. Additionally, based on an analysis of temperature, visibility, and CO concentration at characteristic heights, suitable locations for pedestrian crossings within the tunnel were deduced and an evacuation strategy for persons within the core fire area was proposed. The results can provide a reference for personal evacuation strategies in curved highway tunnel fire scenarios and the design of an adit for people passing in such tunnels. [ABSTRACT FROM AUTHOR]

Pedestrian crossings are one of the most essential elements of linear infrastructure in road transportation. A crosswalk is a place where a pedestrian should feel safe crossing to the other side of the roadway. Regardless of what means of transportation each road user utilizes, sooner or later, he or she acts as a pedestrian. Thus, he or she becomes a potential victim of accidents that occur on Polish roads. A large proportion of accidents involving pedestrians occur at crosswalks, and proper signage, lighting, and traffic lights cannot always ensure pedestrian safety at a crossing. Many risks affect traffic safety. These include poor judgment on the part of the driver, failure to obey traffic laws, alcohol consumption, and poor weather conditions. Both the pedestrian and the driver of a vehicle can be victims or perpetrators of accidents. In order to prevent traffic hazards at pedestrian crossings, it is necessary to improve the following: the technical conditions of crossings, their markings, lighting, and the use of islands or footbridges. It is also necessary to conduct repeated educational activities among children, adolescents, and adults on the knowledge of traffic regulations. The purpose of the article is to present issues of road transport infrastructure based on the literature and to assess safety at selected pedestrian crossings in the city of Bielsko-Biala. [ABSTRACT FROM AUTHOR]

Taxila intersection is facing severe traffic issues includingcongestion, delays, increased travel times and inadequate infrastructure. The aim of the study is to highlight the real problems at Taxila intersection related to road users, vehicles and road infrastructure. Traffic data was collected during peak hours through traffic observing video cameras at the unsignalized intersection. Subsequently, traffic violation measurements and their comparisons between morning and evening peak hours, as well as between weekend and week days were developed. The study also identifies the involvement in traffic violations by different drivers, age groups and vehicle types. Comparing morning and evening peak hours reveals variations in traffic patterns and congestion levels throughout the day, helping to create customized plans. Similarly, investigating disparities between weekends and weekdays uncovers unique factors influencing traffic conditions on different days. Results showed that highest percentage of violations at the intersection resulted from 'illegal crossing of road by pedestrian' followed by 'illegal parking' at the intersection. While the lowest percentage of violation observed was 'wrong way driving' at the intersection. In conclusion, this research provides a comprehensive understanding of the traffic issues at the Taxila intersection and offers evidence-based strategies to improve traffic flow, mitigate congestion, and enhance road safety in the area. [ABSTRACT FROM AUTHOR]

Quite a large number of Iraqi – Iran war victims as well as casualties of Kurdish revolution since 1961 now making a noticeable ratio of the disablers population in Kurdistan of Iraq. In fact, recent uprising also did contribute in raising the number of the injured and handicaps within Kurdish community. Actually, all these people almost got no easy way for participating in entertainment within this park, or any similar parks in Erbil (Hawler). All these are because of lack of suitable road and even special gates within such parks. In fact, even babies and nurseries are in need to such gate and ways that is absent so far. A review of the actual design and pointing out the stages of establishing points in this respect will be the goal of the present study for such and other parks in the region in order to reduce the existing gaps in designing, planning and in constitution of any parks. Present study is concentrating on the effect on disablers, the psychological and physical effects on crippled individuals, and the effects on disability institutions. Sami Abdulrahman Park is one of Erbil's largest parks, present study's primary goal is to build a system that addresses issues with disabled people's access to these parks. According to studies, the existence of inaccessibility is routed, and cities are referred to eliminate it; design measures with interior locations are then used to suggest presenting options. Using sketches, photos, and interviews, researchers record the park's landscape design sites—entrances, streets, pedestrian crossings, parking lots, ramps, urban furniture, etc. [ABSTRACT FROM AUTHOR]

Timing traffic signals using coordination zones of one to three signalized intersections was tested as an approach for reducing speeding opportunities on urban arterials. Short coordination zones can reduce speeding opportunities because they allow cycle length to be shorter at most intersections, with less excess arterial green time during which vehicles can pass through unconstrained; they also avoid the outcome, common to long coordination zones, of having large clusters of intersections with simultaneous green, which create an incentive to speed. In a case study of Boston’s Huntington Avenue performed using microsimulation, existing coordinated control over a stretch of nine intersections was compared with control short coordination zones with one to three intersections per zone, with each zone’s cycle length tailored to the needs of its intersections. Speeding opportunities per hour—defined as the number of vehicles entering an intersection on a stale green and with no vehicle ahead of them for at least 5 s–fell by 46%–51% midday and by 24%–33% in the AM peak, depending on the base of comparison, while vehicle delay was unchanged in the AM peak and increased by only 9% midday, and average pedestrian delay crossing the arterial fell substantially. [ABSTRACT FROM AUTHOR]

• Perceptions of pedestrian safety interacting with self- vs. human-driven vehicles. • Deception experiment to measure implicit attitudes (Autonomy Bias). • Autonomy Bias exists, is negative on average, and varies widely across individuals. • Autonomy Bias is more related to technological orientation than socio-demographics. • Implicit and explicit attitudes are strongly related but distinct. Ensuring comfort and safety for pedestrians is essential to the responsible introduction of automated or self-driving vehicles (SDV). Few studies have attempted to isolate the effect of vehicle automation on perceptions of pedestrian interactions with SDV, separate from the potentially confounding effects of vehicle operation or appearance, and we still have limited understanding of the explicit and implicit attitudes mediating those perceptions. The objectives of this study are to determine 1) if there is an "Autonomy Bias" in the population of British Columbia, Canada (i.e., whether people perceive pedestrian-SDV interactions as inherently more or less comfortable and safe than otherwise equivalent interactions with human-driven vehicles or HDV), and if so, 2) which personal attributes influence Autonomy Bias. We isolate the effect of vehicle autonomy on perceptions using a novel deception-based experiment in which 1,133 participants rate 8 video clips of pedestrian interactions in a crosswalk; all clips show HDV, but a random half of the videos for each participant are described as SDV. Results show that Autonomy Bias varies widely across the population, with a small but significantly (p < 0.05) negative mean value (i.e., SDV interactions are perceived as less comfortable and safe). To ensure that an average person is as comfortable crossing with SDV as they currently are with HDV (i.e., to offset their Autonomy Bias), SDV must allow at least 0.4 s additional passing time at crosswalks; at least 3.7 s additional time is needed to ensure equivalent comfort for 85 % of the population. The implicit attitude of Autonomy Bias is strongly related to but distinct from explicit, self-reported attitudes toward technology and SDV, and may improve with SDV familiarity. [ABSTRACT FROM AUTHOR]

• Drivers' willingness to stop is influenced by distractions. • Distractors on the part of drivers strongly decrease the willingness to yield. • Distractions on both sides results in the lowest willingness to yield priority. • Drivers' behavior is influenced by the characteristics of pedestrians. • The factors were examined using a discrete choice model. The safety of vulnerable road users is one of the most important aspects of road safety. One of the most critical points for pedestrian traffic is the pedestrian crossing, where pedestrians and vehicles interact. Due to the speed and weight of vehicles, sufficient attention by drivers and pedestrians is essential for accident-free crossing. Our research aimed to identify the parameters that influence drivers' willingness to yield the right of way. The focus of our research was on the distractors of pedestrians and drivers. Our study involved on-site investigations. The measurements were taken at designated pedestrian crossings, with a road sign and road markings. During the measurements, we recorded all situations where there was a pedestrian-vehicle interaction. We recorded several parameters about drivers and pedestrians. The data were analyzed using both descriptive statistics and a discrete decision model. We have shown that the drivers' willingness to stop depends on distractions. We showed that distractors on the part of pedestrians slightly increase the drivers' willingness to stop, while distractors on the part of drivers strongly decrease the willingness to yield. In addition, we have shown that distractions from both sides result in the lowest willingness to yield the right of way. We have also shown that driver behavior depends on the gender, age, and behavior of pedestrians. Our results are valuable and useful in many ways in the field of road safety and the analysis of traffic behavior. [ABSTRACT FROM AUTHOR]

• Pedestrians' road-crossing decisions and head movement patterns in response to different vehicle kinematics in mixed traffic were investigated. • A distributed platform incorporating a CAVE-based pedestrian simulator and a desktop driving simulator was developed to enable pedestrian-vehicle interaction in VR. • Pedestrians displayed different head movement patterns prior to crossing and non-crossing decisions, suggesting this to be a promising indicator of pedestrians' road-crossing intention. • The 'last moment check' behaviour in pedestrians' head movements before crossing initiation, can be used by future AVs for early recognition of pedestrians' road-crossing intention. • The similar road-crossing percentage and head-turning patterns of pedestrians demonstrated that the kinematic difference between human-driven and predefined vehicles did not impact pedestrians' behaviour prior to road crossings. The impending deployment of automated vehicles (AVs) will lead to mixed traffic conditions, where pedestrians will be required to interact with both AVs and human-driven vehicles. For traffic flow to be safe and efficient, AVs' understanding of pedestrians' behaviour and intention is as important as pedestrians' perception of AVs' status and intent. To investigate pedestrians' road-crossing decisions and interactive behaviour in mixed traffic, a distributed simulation study was developed by linking a CAVE-based pedestrian simulator and a desktop driving simulator. Twenty-five pairs of pedestrians and drivers were recruited, and each pair experienced 32 trials, where pedestrians decided to cross (or not) before an approaching vehicle at an un-signalised, single-lane, road. The driving pattern of the approaching vehicle (controlled by either a predefined program or human driver) and braking mode (braking/non-braking) were manipulated. For the predefined vehicles, the braking pattern was subdivided into hard braking and soft braking to provide more kinematic variability. Human drivers were also instructed to yield, or not, in different trials. Pedestrians' road-crossing decisions and head movements were recorded and analysed. Results revealed a significant difference in head-turning patterns between crossing and non-crossing manoeuvres, demonstrating pedestrians' head movements as a valid indicator of their road-crossing intentions. Moreover, results identified a 'last moment check' behaviour before pedestrians' crossing initiation, with a significant increase in head-turning during the last 2 s. Finally, pedestrians made a similar percentage of road crossings and displayed a similar pattern of head movements, in response to human-driven and predefined vehicles, suggesting that the difference of implicit cues in the current mixed traffic setup does not impact their behaviour prior to road crossings. The findings from this study extend our knowledge of how pedestrians behave when crossing the road in mixed traffic, particularly in terms of their head-turning behaviour. We hope this information can be used by future AVs to better predict pedestrians' road-crossing intentions in urban settings. [ABSTRACT FROM AUTHOR]

This paper presents an empirical investigation into approach saturation headways at All-Way Stop-Controlled (AWSC) intersections. The mean approach saturation headway is a surrogate measure for approach capacity, which is largely a function of traffic demand on other intersection approaches. Video data was collected over four days at an AWSC intersection site in Bozeman, Montana. The site is characterized by single-lane approaches and a high level of vehicular and pedestrian traffic. Using strict protocols, video records were processed at the individual vehicle level and several information metrics were extracted for each vehicle in the data set on all approaches. Study results indicate that the mean approach saturation headways varied in a wide range due to variations in pedestrian activity, level of conflict, and the intended movement of the subject vehicle. The results suggest that, when no pedestrians were present, the maximum approach capacity in the absence of vehicular conflicts was in the order of 570 vph versus only 360 vph when conflicts were present on all other approaches. Statistical tests confirmed that the three study variables: pedestrian crossing activity, level of conflict, and subject vehicle movement all had significant effects on approach saturation headways. The pedestrian crossing activity was found to have the most significant impact on saturation headways, followed by the level of conflict and the subject vehicle movement, respectively. The results presented in this paper offer valuable information on approach saturation headways and capacity, a major input to operational analyses for this important type of intersection. [ABSTRACT FROM AUTHOR]

Traffic management is a critical activity, the population is increasing day by day and so the traffic on the road is also increasing. Traffic jams and long waiting queues of vehicles at the road crossing are now part of everyone's life. The traffic lights used at the crossing to regulate the traffic play a vital role in the smooth functioning of traffic movement. At a crossing of four roads, it has been observed that giving an equal amount of green light to all roads is meaningless since the arrival of traffic on different paths is different. Importantly, the arrival rate is responsible for all traffic jams, long queues, and increased waiting time. Therefore, this paper suggests a green light allocation scheme for all paths i depending on the arrival rate of the vehicles. Thus, the allocation of green light will be dynamic. Further, weight is also computed, where more arrival rate means more weight, thereby assigning more time to the green signal. This will help in reducing the long queue length, residual traffic, and long waiting times. On simulating the traffic with the traffic data, the proposed optimized green light allocation scheme to path i reduces the residue traffic to negligible, allowing smooth traffic flow even during peak hours. The work also provides a proficient optimization of the waiting time of vehicles accumulated during the red light. According to the simulation, the maximum time assigned for the green signal during the peak hour of 9:30 AM to 10:00 AM for paths i , where 1 ≤ i ≤ 4 is 39.96, 33.36, 26.64, and 20.04 seconds respectively. Similarly, during the second rush hour of 5:00 PM to 6:00 PM, the simulation assigns a green signal time of 41.4, 37.2, 24.84, and 16.56 seconds for corresponding paths 1–4. Thus, the proposed work suggests an effective traffic management scheme at the four-road crossing. [ABSTRACT FROM AUTHOR]

Accurate real-time prediction of pedestrian crossing intent during the autonomous driving process is crucial for ensuring the safety of both pedestrians and passengers, as well as improving riding comfort. However, existing methods for pedestrian crossing intent detection mostly rely on extracting complete pose information of pedestrians, leading to reduced accuracy when pedestrians are occluded. To address this issue, this paper proposes FHPE-Net: a lightweight, multi-branch prediction model that utilizes only the head pose features of pedestrians. In pedestrian crossing scenarios, pedestrian behavior is highly influenced by surrounding vehicles and the environment. FHPE-Net encodes pedestrian head poses and global context semantic image sequences to comprehensively capture spatiotemporal interaction features between pedestrians, vehicles, and the environment, thereby enhancing the accuracy of pedestrian crossing intent prediction. To improve the robustness of the FHPE-Net method, this study further processes bounding box positions and vehicle velocity features, making it more stable and reliable in complex traffic scenarios. Finally, a novel U-BiGRUs module is introduced for feature fusion, and an optimal fusion strategy is employed to achieve the best predictive performance in terms of F1 score and accuracy (ACC). Extensive ablation experiments are conducted on the PIE dataset, and performance analysis demonstrates that FHPE-Net achieves an accuracy of 90%, outperforming baseline methods such as PCPA and Multi-RNN, while using only pedestrian head pose features. This research holds significant guidance in enhancing traffic safety and optimizing urban traffic management. Furthermore, it provides essential technological support for advancing the commercialization of autonomous driving. [ABSTRACT FROM AUTHOR]

Road safety continues to be a critical issue, especially for vulnerable road users such as pedestrians walking across the road at a place designated for the purpose. The most effective method of safety improvement at pedestrian crossings is to install traffic lights to control traffic. Such a solution cannot be used anywhere, however, due to the risk of the lack of flow capacity, especially in the area of nearby junctions. Therefore, persons responsible for traffic safety look for alternatives to improve the situation at pedestrian crossings. To meet the expectations of those persons, this article proposes mechatronic systems which are worth installing at selected pedestrian crossings to improve safety and reduce the number of traffic incidents involving vulnerable people. Three pedestrian crossings, considered dangerous by the authors, and located in the town of Nowy Sącz, were taken for analysis. Among the safety features, the use of an active sign informing of a pedestrian crossing, reflective elements and LED lights embedded in asphalt, as well as active pedestrian crossing illumination, are suggested. The proposed solutions are distinguished by low operating costs, as energy needed to power those solutions is obtained from photovoltaic panels. [ABSTRACT FROM AUTHOR]

Artificial intelligence has brought many innovations to our lives. At the same time, it is worth designing robust safety machine learning (ML) algorithms to obtain more benefits from technology. Reinforcement learning (RL) being an important ML method is largely applied in safety-centric scenarios. In such a situation, learning safety constraints are necessary to avoid undesired outcomes. Within the traditional RL paradigm, agents typically focus on identifying states associated with high rewards to maximize its long-term returns. This prioritization can lead to a neglect of potentially hazardous situations. Particularly, the exploration phase can pose significant risks, as it necessitates actions that may have unpredictable consequences. For instance, in autonomous driving applications, an RL agent might discover routes that yield high efficiency but fail to account for sudden hazardous conditions such as sharp turns or pedestrian crossings, potentially leading to catastrophic failures. Ensuring the safety of agents operating in unpredictable environments with potentially catastrophic failure states remains a critical challenge. This paper introduces a novel metric-driven approach aimed at containing risk in RL applications. Central to this approach are two developed indicators: the Hazard Indicator and the Risk Indicator. These metrics are designed to evaluate the safety of an environment by quantifying the likelihood of transitioning from safe states to failure states and assessing the associated risks. The fact that these indicators are characterized by a straightforward implementation, a highly generalizable probabilistic mathematical foundation, and a domain-independent nature makes them particularly interesting. To demonstrate their efficacy, we conducted experiments across various use cases, showcasing the feasibility of our proposed metrics. By enabling RL agents to effectively manage hazardous states, this approach paves the way for a more reliable and readily implementable RL in practical applications. [ABSTRACT FROM AUTHOR]