Vulnerable Group Of Road Users Research Articles

Revisiting the hybrid approach of anomaly detection and extreme value theory for estimating pedestrian crashes using traffic conflicts obtained from artificial intelligence-based video analytics

Pedestrians represent a group of vulnerable road users who are at a higher risk of sustaining severe injuries than other road users. As such, proactively assessing pedestrian crash risks is of paramount importance. Recently, extreme value theory models have been employed for proactively assessing crash risks from traffic conflicts, whereby the underpinning of these models are two sampling approaches, namely block maxima and peak over threshold. Earlier studies reported poor accuracy and large uncertainty of these models, which has been largely attributed to limited sample size. Another fundamental reason for such poor performance could be the improper selection of traffic conflict extremes due to the lack of an efficient sampling mechanism. To test this hypothesis and demonstrate the effect of sampling technique on extreme value theory models, this study aims to develop hybrid models whereby unconventional sampling techniques were used to select the extreme vehicle–pedestrian conflicts that were then modelled using extreme value distributions to estimate the crash risk. Unconventional sampling techniques refer to unsupervised machine learning-based anomaly detection techniques. In particular, Isolation forest and minimum covariance determinant techniques were used to identify extreme vehicle–pedestrian conflicts characterised by post encroachment time as the traffic conflict measure. Video data was collected for four weekdays (6 am–6 pm) from three four-legged intersections in Brisbane, Australia and processed using artificial intelligence-based video analytics. Results indicate that mean crash estimates of hybrid models were much closer to observed crashes with narrower confidence intervals as compared with traditional extreme value models. The findings of this study demonstrate the suitability of machine learning-based anomaly detection techniques to augment the performance of existing extreme value models for estimating pedestrian crashes from traffic conflicts. These findings are envisaged to further explore the possibility of utilising more advanced machine learning models for traffic conflict techniques.

A Bayesian extreme value theory modelling framework to assess corridor-wide pedestrian safety using autonomous vehicle sensor data

Pedestrians are a vulnerable road user group, and their crashes are generally spread across the network rather than in a concentrated location. As such, understanding and modelling pedestrian crash risk at a corridor level becomes paramount. Studies on pedestrian crash risks, particularly with the traffic conflict data, are limited to single or multiple but scattered intersections. A lack of proper modelling techniques and the difficulties in capturing pedestrian interaction at the network or corridor level are two main challenges in this regard. With autonomous vehicles trialled on public roads generating massive (and unprecedented) datasets, utilising such rich information for corridor-wide safety analysis is somewhat limited where it appears to be most relevant. This study proposes an extreme value theory modelling framework to estimate corridor-wide pedestrian crash risk using autonomous vehicle sensor/probe data. Two types of models were developed in the Bayesian framework, including the block maxima sampling-based model corresponding to Generalised Extreme Value distribution and the peak over threshold sampling-based model corresponding to Generalised Pareto distribution. The proposed framework was applied to autonomous vehicle data from Argoverse—a Ford Motors subsidiary. This autonomous vehicle fleet of Agro AI (owner of Argoverse dataset) is equipped with two 64 beams synchronised LiDAR sensors, a cluster of seven high-resolution cameras, and a pair of stereo-vison high-resolution cameras to capture surrounding road users’ information within a range of 200 meters. A subset of the Argoverse dataset, focussing on an arterial corridor in Miami, USA, was used to extract pedestrian and vehicle trajectories. From these trajectories, vehicle–pedestrian conflicts were identified and measured using post encroachment time. The non-stationarity of extremes was captured by vehicle volume, pedestrian volume, average vehicle speed, and average pedestrian speed in the extreme value model. Both block maxima and peak over threshold sampling-based models were found to provide a reasonable estimate of historical pedestrian crash frequencies. Notably, the block maxima sampling-based model was more accurate than the peak over threshold sampling-based model based on mean crash estimates and confidence intervals. This study demonstrates the potential of using autonomous vehicle sensor data for network-level safety, enabling an efficient identification of pedestrian crash risk zones in a transport network.

Risk assessment of pedestrian red-light violation behavior using surrogate safety measures: Influence of human, road, vehicle, and environmental factors

Pedestrian red-light violation is one of the crucial causes of pedestrian crashes at urban intersections, which cause considerable injuries and casualties to this vulnerable road group of road users. The objective of this study is to evaluate the risk of pedestrian-vehicle collisions by clustering the pedestrians' red-light violations using surrogate safety measures. The present study utilized surveillance camera footage to collect data on pedestrians' red-light violations at two urban intersections in Babol City. Based on critical thresholds of post-encroachment time (PET), Time to Collision (TTC), and Gap Time (GT), three different risk levels of red-light violations were identified through the use of a K-means algorithm. Moreover, structural equation models were developed for each of the risk levels considering variables that are associated with four major components: human, environment, road, and vehicle. Lastly, policy insights into amending pedestrian behavior and promoting traffic safety culture were proposed, with an overarching emphasis on the human factor, due to its identified greater influence on the propensity for red-light violations.

Cycling-related cranio-spinal injuries admitted to a Major Trauma Centre in the cycling capital of the UK

Background The increased popularity of cycling is leading to an anticipated increase in cycling-related traffic accidents and a need to better understand the demographics and epidemiology of craniospinal injuries in this vulnerable road user group. This study aims to systematically investigate and characterise cycling-related head and spine injuries seen in the Major Trauma Centre for the Eastern region, which has the highest cycling rates in the UK. Methods We performed a retrospective cohort study comparing the incidence, patterns, and severity of head and spine injuries in pedal cyclists presenting to the Major Trauma Centre in Cambridge between January 2012 and December 2020. Comparisons of injury patterns, characteristics, and associations were made according to mechanism of injury, helmet use, patient age and gender. Results A total of 851 patients were admitted after being involved in cycling-related collisions over the study period, with 454 (53%) sustaining head or spine injuries. The majority of victims (80%) were male and in mid-adulthood (median age 46 years). Head injuries were more common than spine injuries, with the most common head injuries being intracranial bleeds (29%), followed by skull fractures (12%), and cerebral contusions (10%). The most common spine injuries were cervical segment fractures, particularly C6 (9%), C7 (9%), and C2 (8%). Motorised collisions had a higher prevalence of spine fractures at each segment (p < 0.001) and were associated with a higher proportion of multi-vertebral fractures (p < 0.001). These collisions were also associated with impaired consciousness at the scene and more severe systemic injuries, including a lower Glasgow coma scale (R = −0.23, p < 0.001), higher injury severity score (R = 0.24, p < 0.001), and longer length of stay (R = 0.21, p < 0.001). Helmet use data showed that lack of head protection was associated with more severe injuries and poorer outcomes. Conclusion As cycling rates continue to increase, healthcare providers may expect to see an increase in bicycle-related injuries in their practice. The insights gained from this study can inform the treatment of these injuries while highlighting the need for future initiatives aimed at increasing road safety and accident prevention.

Prehospital Care in Road Traffic Accident Cases

Abstract Background: Rapid population growth, industrialization and an increase in road vehicles, have led to a drastic increase in the number of Road Traffic Accidents (RTA).Pedestrians, motorized two wheeled vehicle (MTV) users, and cyclists are the most vulnerable road user groups in terms of injuries and fatalities resulting from road traffic crashes in India. At least one-third of potentially preventable deaths occur prior to arrival at hospital and over half occur during the hospital reception and resuscitation phase of care. Prehospital emergency care in India is only beginning to develop. Thirty per cent of emergency patients in India die before they reach a hospital. Persons who shift the victims are usually untrained members of the public. Crash victims are often taken to the nearest hospital, regardless of the hospital’s capabilities for dealing with trauma. The vast majority of ambulances are used for inter-hospital transfer, not for primary response. This highlights the need of urgent steps for establishing good pre-hospital care and trauma services at site in India. Aims and Objectives: The study attempts to know the status of provision of pre hospital care to RTA victims and to suggest measures for improving hospital and pre-hospital care to the same. Methods: The study was conducted on patients of RTI admitted at Trauma Centre of King George’s Medical University UP (KGMU), Lucknow. A semi-structured questionnaire was used gather information about the socio demographic profile of RTA victims and the status of provision of pre hospital care to them. Results: It was seen in the present study that only eight percent cases had some sort of pre-hospital care given, or some interventions done before victim was taken to the hospital. Majority of these interventions were given by the bystanders and included measures like shifting the victim from the accident site (76.5%), water splinting/fanning/water given to drink (8.8%), or wound covered with cloth (5.9%) or medications (8.8%). In 9.7 percent cases, it was not known whether any pre hospital intervention was given. Out of the total cases who died, 66.7 percent had not received any intervention before hospitalization. The proportion of mortality was 2.5 percent in cases where no interventions were given, while there was no mortality in cases where some interventions were given before hospitalization. Conclusion: It was seen that very few cases got some intervention before hospitalization and a number of cases were referred from government health facilities due to unavailability of beds, equipment or medical staff. About thirty percent interviewees were not aware of ambulance emergency number. Lower proportion of mortality was seen in cases that got intervention at a health facility within an hour.

Accurate detection of vehicle, pedestrian, cyclist and wheelchair from roadside light detection and ranging sensors

Accurate detection plays a critical role in improving the safety situation of vulnerable road users. This study extends infrastructure-based LiDAR application to all three major vulnerable road user groups including pedestrians, cyclists, and wheelchair users. Two critical problems for accurate detection of small-sized road users are scanning angle variability and feature fluctuation. To address these issues, a feature-based classification method combined with prior LiDAR trajectory information is developed. Effective dimension-related features are proposed and five classifiers including artificial neural network (ANN), random forest (RF), adaptive boosting (AdaBoost), random under-sampling boosting (RUSBoost), and long short-term memory (LSTM) are tested with a novel feature engineering process. A total of seven features are selected from the point cloud of clusters for vehicle/pedestrian/cyclist/wheelchair classification. By updating these significant features based on prior information of the entire trajectory, the performance of road user classification (imbalanced datasets) has been significantly improved. Experimental study is conducted to examine the recall rate, F1-score, and AUC of vehicles, pedestrians, cyclists, and wheelchairs before and after integration with prior trajectory information. The result shows the trained AdaBoost, RUSBoost, and LSTM classifiers with prior trajectory information can achieve recall/F1-score/AUC: (1) Low traffic volumes – vehicles (100%/99.96%/99.96%), pedestrians (99.96%/99.96%/99.97%), cyclists (99.74%/99.45%/99.67%), and wheelchairs (99.22%/99.68%/99.01%) and (2) Moderate traffic volumes – vehicles (99.39%/99.44%/99.69%), pedestrians (98.33%/97.99%/98.64%), and cyclists (95.41%/94.29%/94.40%), using 32-laser LiDAR sensors (10 Hz).

A comprehensive study of child pedestrian crash outcomes in Ghana

Pedestrians are considered as one of the vulnerable road user groups. Among pedestrians of all ages, children are the most at risk. Previous studies have shown that children have inadequate knowledge of road safety and are unable to identify risks on road. Despite these limitations associated with children, society places the burden on them to protect themselves. However, to be able to adequately address child pedestrian safety issues there is the need to understand the factors that influence their crash involvement and severity of injury they sustain. To address this gap, this study performed a comprehensive analysis of historical crash data in Ghana to find holistic countermeasures for these crashes. The study used five years of child pedestrian (below 10 years) crash records obtained from the Building and Road Research Institute (BRRI) in Ghana. A temporal analysis of the data revealed that the highest number of the crashes coincide with when school-going children go to and close from school. A random parameter multinomial logit model was developed to identify crash variables that are significantly associated with child pedestrian crash outcomes. The estimation results revealed that children are likely to be killed in crashes when the driver is speeding and inattentive. Also, it was found that children walking along the road, crossing the road, and those in urban areas are more susceptible to incapacitating injury crashes. Male drivers accounted for 95.8% of child pedestrian crashes, and crashes involving male drivers are 7.8% more likely to be fatal.The findings from this study provide a deeper, data-driven understanding of child pedestrian crashes and how temporal characteristics, vehicle type, location of pedestrian, traffic operation, and environmental and human factors affect crash outcomes. These findings will help in developing countermeasures like providing conspicuous pedestrian crossings, footbridges on multi-lane high-speed roadways, and the use of school buses to convey students to help mitigate the number and severity of child pedestrian crashes in Ghana, and by extension other countries in the sub-region.

Modelling the road network riskiness for motorcycle transport: The use of accident probability and accessibility to emergency medical service

Abstract Motorcycle users are generally perceived as one of the most vulnerable road user groups. It is therefore evident that, in addition to a range of prevention and awareness-raising activities, it is also necessary to identify specific locations where motorcycle users are at risk. We use a synthetic approach to identify the road network sections dangerous for motorcycle traffic. We perceive the risk level of individual sections as a complex combination of the causes (accident probability) and consequences (accessibility of medical services) of motorcycle accidents. The combination of both factors is then used to define the Road Network Hazard Index (RNHI) as a newly introduced indicator synthetically assessing the risk levels of individual road network sections for motorcycle traffic. The motorcycle accident probability on the Czech road network is extremely differentiated. The time accessibility of accident locations from EMS dispatch stations shows a clear correlation with the severity of motorcycle accidents. The model for the accident locations’ accessibility indicates that the sparsely populated peripheral regions of the Czech Republic in particular show not only a higher motorcycle accident probability but also higher time accessibility values for emergency vehicles. The new RNHI provides a comprehensive view of the risk levels for motorcycle traffic in different Czech road network sections.

Perceptions and Preferences of University Students for Use of Pedestrian Bridge: A Gender Based Study

This research highlights a very important aspect of road safety which is related to the use of pedestrian facilities by young adults, with special focus on the differences related to gender. Pedestrians are considered as the most vulnerable road user group. Moreover, involvement of young people in road crashes is among the most alarming aspects for most of the countries in the world. This research employs a survey questionnaire to determine the preferences related to use of pedestrian bridge, before and after its rehabilitation. The analysis of the questionnaire included statistical tests, logistic regression and CART model. It was found that the physical condition of the bridge has the most profound effect on the hazard perception of young pedestrians, in spite of the presence of other factors related to safety and security. Most of the pedestrians preferred using the pedestrian bridge during the afternoon, irrespective of the condition of the bridge. It was also found that the before data had a higher impact of gender, with more female respondents showing safety concerns and using the pedestrian bridge. The after data showed a more uniform distribution among genders. Although, the CART model showed significant impact of gender on the perception related to beggars, being the most important risk hazard. It is recommended for future studies to be performed on a larger dataset, include more variables and employ CART technique for modeling.

A Bayesian generalised extreme value model to estimate real-time pedestrian crash risks at signalised intersections using artificial intelligence-based video analytics

Pedestrians represent a vulnerable road user group at signalised intersections. As such, properly estimating pedestrian crash risk at discrete short intervals is important for real-time safety management. This study proposes a novel real-time vehicle-pedestrian crash risk modelling framework for signalised intersections. At the core of this framework, a Bayesian Generalised Extreme Value modelling approach is employed to estimate crash risk in real-time from traffic conflicts captured by post encroachment time. A Block Maxima sampling approach, corresponding to a Generalised Extreme Value distribution, is used to identify pedestrian conflicts at the traffic signal cycle level. Several signal-level covariates are used to capture the time-varying heterogeneity of traffic extremes, and the crash risk of different signal cycles is also addressed within the Bayesian framework. The proposed framework is operationalised using a total of 144 hours of traffic movement video data from three signalised intersections in Queensland, Australia. To obtain signal cycle-level covariates, an automated covariate extraction algorithm is used that fuses three data sources (trajectory database from the video feed, traffic conflict database, and signal timing database) to obtain various covariates to explain time-varying crash risk across different cycles. Results show that the model provides a reasonable estimate of historical crash records at the study sites. Utilising the fitted generalised extreme value distribution, the proposed model provides real-time crash estimates at a signal cycle level and can differentiate between safe and risky signal cycles. The real-time crash risk model also helps understand the differential crash risk of pedestrians at a signalised intersection across different periods of the day. The findings of this study demonstrate the potential for the proposed real-time framework in estimating the vehicle-pedestrian crash risk at the signal cycle level, allowing proactive safety management and the development of real-time risk mitigation strategies for pedestrians.

Modelling factors that impact the use of child safety seats for nursery school travel

Children, as one of the most vulnerable road user groups, are exposed to a high risk of traffic crash-related injuries and fatalities. Children’s incomplete physical and cognitive development leads to inaccurate detection of traffic hazards and inadequate road crossing decisions. When young children travel as car occupants, their body structures are immature, and restraint over larger and sometimes different body areas is necessary. Therefore, children’s vulnerability as car occupants is subject to their age and physical development. This research investigates factors influencing child car seat usage, particularly child restraint systems or booster seats, for commuting to nursery schools. An experimental study was conducted in three suburbs of Athens, Greece, with distinctive socioeconomic status (SES) and built environment characteristics. For this purpose, a self-administered parental questionnaire was completed for 734 children attending municipality nursery schools, exploring the traffic safety practices for preschool children, child-parent interactions, the parent’s risk perception, behaviour, and knowledge of traffic safety. Responses reveal that the surveyed children—irrespective of the residence area—travel to the nursery school mainly as car occupants (89.6% overall, ranging between 84.8% for the area with the lowest SES and 96.1% for the area with the highest SES). In addition, the results indicate that three-quarters of the children are often placed in a car seat, while almost one-quarter are never restrained. Regression and structural equation models are estimated and used to examine factors affecting the usage of child safety seats. Finally, conclusions are drawn, along with suggestions to overcome the limitations and complete this research with ongoing and future data collection and analyses.

Towards Vision Zero

Almost half of the casualties on European roads can be accounted to the group of the so-called Vulnerable Road Users (VRUs). The introduction of V2X Communication makes it possible to extend the awareness horizon of automated and autonomous vehicles, in order to avoid accidents with VRUs. In this paper we learn how V2X communication will protect VRUs, what requirements have to be met, what the key performance metrics are and how different communication and localization technologies perform. The Vision Zero goal is to reduce the road traffic casualties including VRUs to zero.

Pedestrians' Crossing Behaviors and Crossing Preferences: A Field Study

Pedestrians are one of the most vulnerable road user groups in traffic and face many risky situations in traffic, especially when pedestrians cross the street, where a pedestrians-vehicle interaction or conflict is most likely. Different from the previous studies on pedestrian behavior, the current study targeted exploring pedestrian behavior and safety at a specific street in Ankara-Tunali Hilmi Street Turkey employing two different data collection methods. Specifically, the current study aimed to understand the behaviors, perceptions, and crossing preferences of pedestrians in the study area. In addition to the above, it aimed to identify situations that create safety concerns for pedestrians in the area and offer area-specific countermeasures addressing these concerns. For this purpose, an online survey study and an observational study were conducted. The results of the survey based on investigations of the crossing preferences of 96 pedestrians revealed an understanding of the participants' motivation when crossing the street, their attitudes toward traffic rules, and their safety perceptions about the area. Additionally, it targeted to understand the situations that negatively affect road safety in the area for pedestrians. According to the survey respondents, the study area was unsafe for pedestrians and the biggest problem in terms of pedestrian safety is vehicle traffic and parking. The observation study presented significant differences in crosswalk use, compliance with the signal between pedestrians who cross alone or in a pair and those who cross in a group. People who cross the street as a group use crosswalk and comply with the traffic signal more than people crossing alone or in a pair. In addition, considering the illegal crossing rate, it can be said that jaywalkers - people who do not use crosswalk - are the majority in the study area. As a result, the current study helps to arrange crossing facilities according to pedestrian preference because the proper design of facilities contributes to pedestrian safety and encourages walking without sacrificing safety and comfort. Accordingly, reducing vehicle traffic, increasing and arranging parking areas, and increasing number of pedestrian facilities are suggested to increase pedestrian safety in the area.

Effect of pedestrian characteristics and their road crossing behaviors on driver yielding behavior at controlled intersections

Introduction: Globally, pedestrians are one of the most vulnerable road-user groups. Their vulnerability increases while crossing the road at controlled intersections during the “don’t walk” phase. Previous literature shows that driver yielding behavior has an association with pedestrian safety at intersections. Though several studies have explored driver yielding behavior towards pedestrians at conflict points, evidence on how pedestrian actions influence driver yielding behavior at intersections is yet to be investigated. Method: To pursue this end, a binary logistic regression model was developed using the collected data to explore the effect of non-compliant pedestrian characteristics and their road crossing behavior on driver yielding behavior towards pedestrians at six controlled intersections of Dhaka, Bangladesh. The data were collected through videography survey. Results: Results showed that drivers were more likely to yield to pedestrians who were female, crossing in a group, carrying baggage, not using a mobile, making some hand gesture to the driver, or crossing by rolling gap strategy. Practical Applications: These findings add new insights for transportation planners into the complex interaction between vehicles and pedestrians at busy controlled intersections, and thus would help to make a pedestrian friendly street.

Investigation of factors influencing motorcyclist injury severity using random parameters logit model with heterogeneity in means and variances

Motorcyclists are an integral component of the traffic stream especially, in low-income developing countries like Pakistan. However, motorcyclists lay in the group of vulnerable road users i.e., road users with the least protection, along with pedestrians and cyclists. Therefore, the current study employed the random parameters logit model to identify key risk factors associated with motorcyclist injury severity using three years crash data (2017-2019) for city of Rawalpindi, Pakistan. To calibrate the model, motorcyclist injury severity thresholds are classified as no injury, minor injury, severe injury, and fatal injury. For motorcyclist injury severity analysis, the effects of vehicle crash characteristics, weather conditions, rider attributes and other socio-demographic considerations were primarily considered. The study results showed that severe and fatal injury risk is increased for crashes occurred during weekdays, involving riders aged above 50 years, involving the collision of motorcycles with passenger car and heavy vehicles, involving a female as a pillion rider, and those that occurred due to over speeding. Based on the results obtained from the model, the study suggests several policy implication as strict implementation of traffic regulations such as heavy fines or cancellation of driving license on over speeding, wrong turns, inappropriate passing, running a red light, not wearing helmet etc., instructing the females not to wear loose clothes or trailing scarves while riding the bike as pillion riders. The outcomes are expected to stimulate more interest and discussion regarding motorcycle safety in the country and can be used by city traffic police and highway authorities to boost the road safety.

Correlations of multiple rider behaviors with self-reported attitudes, perspectives on traffic rule strictness and social desirability

Powered Two-Wheeler (PTW) riders constitute a very vulnerable group of road users, while riding a PTW is considerably more dangerous than using any other motor vehicle. Behavioral issues have been identified major moderating factors to PTW crashes, as riders display great variability in their attitudes towards road safety. Τhe aim of this paper is to present a thorough, overarching structure of relationships correlating various unsafe stated PTW rider behaviors (riding after alcohol consumption, speeding, helmet use and texting) with several self-reported attitude parameters and factors regarding rider perspectives on traffic rule strictness and social desirability. A structural equation model (SEM) was developed using data from the ESRA2 survey, which provided a broad sample encompassing 5,958 respondent riders from 32 countries. Numerous statistical relationships were discovered and quantified correlating the four examined unsafe rider behaviors with eight latent unobserved variables. All covariances between unsafe behaviors were found to be positive and statistically significant, indicating that a rider who will engage more frequently in every single one of the four examined unsafe riding behaviors is more likely to also engage in all the others as well.

Interaction of automated driving systems with pedestrians: challenges, current solutions, and recommendations for eHMIs

ABSTRACT The conventional form of traffic interaction undergoes a notable change with the integration of automated driving systems as a new road user, into the public roads. This may be more challenging during the transition phase, while manual-driven vehicles are still on the road, and the road infrastructure is not fully ready for merging such vehicles into the traffic patterns. Therefore, developing a robust interaction method is crucial to ensure the safety of those users interacting with automated driving systems and to ensure the efficiency of these systems on the road. For this purpose, the interaction of automated driving systems with pedestrians, as one of the most vulnerable road user groups, is investigated in this paper. Previous studies have shown the necessity for a comprehensive understanding of pedestrian behaviours and intentions, their responses to different stimuli on the road, the factors influencing their decisions during the interaction, and various external communication techniques among road users. As a result, a wide range of factors related to the communication environment, pedestrian characteristics, and existing communication methods have been found to be significant in the decision-making process of pedestrians.

Reduction of Pedestrian Accidents – Automated Road Vehicles

The number of traffic accidents is decreasing thanks to measures taken by the government and also by car manufacturers. However, despite the measures, thousands of people die on the roads every year. The most vulnerable group of road users are pedestrians. In this article we will deal with the measures and ways of reducing the occurrence of traffic accidents by pedestrian-vehicle, or at least reducing the consequences of a traffic accident. It is important to point out the development of traffic accidents not only in Slovakia but also in the EU and to point out the possibilities of elimination or improvement in this area. One of the innovative ways to reduce the number of accidents, in general, is automated road vehicles. Technologies and procedures used in automated road vehicles can significantly reduce accidents. For this reason, the basic technological systems are being developed, which contribute to the reduction of the accidents. The hardware and software equipment of automated road vehicles will be described in this article. It is also necessary to focus on the detection of pedestrians by an automated road vehicle, where machine learning and algorithms are used to calculate an estimate the direction of pedestrians and their movement in the traffic.

ANALIZA WYPADKÓW Z UDZIAŁEM PIESZYCH W POLSCE

Pedestrian crossings today are an indispensable element of the road infrastructure. There are more and more of them. The reason for this state of affairs is the constantly constant level of pedestrian intensity and the need to change the path of the footpath. Pedestrian accidents occur as a result of many factors related to weather conditions or the technical condition of the vehicle. However, in Poland, most often the event happens due to human error, then the driver of a car or a pedestrian. In addition, the high accident rate depends on poor road infrastructure. Unfortunately, a pedestrian is the victim of every third accident in our country. Pedestrians are among the group of vulnerable road users in which participation in an accident has very serious consequences. The importance of this problem can be demonstrated by the fact that 270,000 pedestrians are killed on the world's roads every year. Globally, almost 22% of all fatalities are from pedestrian accidents, and this is an average value, as there are countries where this percentage exceeds 66%. Pedestrian safety is a serious problem on Polish roads. In Poland, most pedestrian accidents occur at pedestrian crossings. This is where pedestrians and vehicles cross, creating a risk of collisions between these road users. These accidents are caused by insufficient visibility of the driver and pedestrians. The analysis of police statistics made it possible to assess the effectiveness of factors aimed at improving road safety at pedestrian crossings. The main one is traffic light. Thanks to him, pedestrian crossings are safer. A big problem, which is still significant, is the concentration of pedestrian’s attention on phone screens. To prevent collisions with pedestrians, they do not monitor their safety when crossing the road, there are special programs for phones, the use of advertising campaigns, the installation of LED strips or the use of 3D strips. KEYWORDS: PEDESTRIAN, PEDESTRIAN CROSSING, ROAD SAFETY, ROAD ACCIDENTS, CAUSES OF ACCIDENTS WITH PEDESTRIANS.

The nature of the risk faced by pedestrians with neurodevelopmental disorders: A systematic review

Pedestrians represent one of the most vulnerable road user groups worldwide. Children and adult pedestrians with neurodevelopmental disorders may be at greater risk due to deficits in a range of domains, such as attention, social communication, motor control and executive function. According to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (American Psychological Association, 2013), neurodevelopmental disorders include individuals with a diagnosis of Autism Spectrum Disorders, Attention Deficit Hyperactivity Disorder, Specific Learning Disorder, Motor Difficulties, Communication Disorders and Intellectual Disabilities. The purpose of this systematic review and meta-analysis was to explore existing literature relating to determine the nature of the risk faced by pedestrians with neurodevelopmental disorders. Relevant databases including Web of Science, PhysInfo and CINAHL were searched up to July 2019. All peer reviewed journals that presented data focusing on neurodevelopmental disorders and some aspect of road crossing or roadside behaviour that included a control or comparison group were included. A total of 149 abstracts were assessed and 17 met the inclusion criteria. The identified papers could be grouped into four areas: (1) rate of injury; (2) assessment of risk; (3) eye gaze and understanding of road layout and (4) gap choice. No papers exploring the risk factors at the roadside for individuals with Specific Learning Disorders or Communication Disorders were identified. Overall, the review provide evidence for an elevated risk of injury for individuals with ADHD at the roadside, potentially as a consequence of poor temporal gap choice, although there was evidence that this risk could be mediated by executive dysfunction rather than ADHD symptomology. Furthermore, poor temporal gap choice was found in children with DCD but it remains unclear as to whether this risk translates to the roadside. Finally, both children and adults with ASD and children with ID were found to demonstrate differences in behaviour / understanding at the roadside. In general, co-occurrence between neurodevelopmental disorders has been largely ignored in the current literature relating to pedestrian risk and future research could consider this along with executive functioning.