Road Traffic Environments Research Articles

Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility.

For smart mobility, autonomous vehicles, and advanced driver-assistance systems (ADASs), perception of the environment is an important task in scene analysis and understanding. Better perception of the environment allows for enhanced decision making, which, in turn, enables very high-precision actions. To this end, we introduce in this work a new real-time deep learning approach for 3D multi-object detection for smart mobility not only on roads, but also on railways. To obtain the 3D bounding boxes of the objects, we modified a proven real-time 2D detector, YOLOv3, to predict 3D object localization, object dimensions, and object orientation. Our method has been evaluated on KITTI’s road dataset as well as on our own hybrid virtual road/rail dataset acquired from the video game Grand Theft Auto (GTA) V. The evaluation of our method on these two datasets shows good accuracy, but more importantly that it can be used in real-time conditions, in road and rail traffic environments. Through our experimental results, we also show the importance of the accuracy of prediction of the regions of interest (RoIs) used in the estimation of 3D bounding box parameters.

Robust steering control for trajectory following in road traffic environments

The process of modelling vehicle motion in a road traffic environment requires the integration of trajectory generation with vehicle control. The steps involved here are generating a feasible trajectory based on the existing traffic and tracking the trajectory to control it with a steering angle input. Since the parameters of a physical system vary with changes in operating conditions, it is important to consider robustness when designing controllers. This article aims at developing a trajectory-following model with robust steering control strategies to accurately follow a generated trajectory. In this study, performance-based proportional, robust proportional and sliding mode control strategies are designed for trajectory following. The robustness of the proportional controller is established using Kharitonov’s theorem, which is compared with a proportional controller tuned for performance. Sliding mode control is designed for robustness and chattering elimination using two kinds of reaching laws – a constant reaching law and a novel power rate exponential reaching law. The controllers are designed using a dynamic bicycle model considering the error with respect to the trajectory. The controllers are then evaluated in IPG CarMaker®. The resulting trajectories and control inputs are compared for the considered control methodologies using the ISO double lane change and the Slalom tests. Sliding mode control with power rate exponential reaching law is concluded to be more robust as compared to the other controllers, with lower response times, up to 84% lower heading angle deviations from the trajectory and an overshoot of only 3.2% in lane changing.

Crash model based on integrated design consistency with low traffic volumes (due to health disaster (COVID-19)/movement control order)

Malaysia is listed as one of Asia's developing countries with high-road accidents rate. The accident involves the most between the motorcyclist and other vehicles such as a passenger car which is 17 times safer than the motorcyclist. Current research reveals that the three major forms of incidents in Malaysia are single-motorcycle incidents, passenger car crashes and cars–motorcycles crash. In general, the lack of accuracy of road geometric design, traffic volumes and overlapping movements of vehicles was the main cause of road accidents in Malaysia, which caused drivers to make mistakes and errors due to road geometric characteristics and traffic environments. However, during our recent COVID-19 pandemic, the traffic volumes are relatively low in the whole country as the government announces the movement control order in March 2020. The country was almost completely lockdown (people and vehicles' movements were controlled). In contrast with the reduction of the traffic volumes, the number of crashes shows relatively high numbers. This phenomenon can be derived so that other factors cause vehicle crashes and fatalities should be considered. Several factors related to road geometric such as lane width, shoulder width, access point, curve length and tangent length are considered in developing profiles of operating speed for motorcycles and cars formed of tangents and curves. The analysis of the geometric factors and traffic environments took place at federal road F0050 from 21 to 25 km in Johor, Malaysia. This study was carried out using GPS (DG-200) where the data (vehicles tracked movements) on the continuous speed profiles used a current method of analysis to determine the profiles of road design consistency for motorcycles and cars. The profiles are used to measure the importance index of the integrated design consistency model of the road. The model depends on parameters such as the confine region of speed profiles, average speed, and velocity deviation standard of the profiles. Therefore, a special software of ACAD was used to build the profile of the consistency model. The design accuracy of the speed profile in traffic and safety assessments are affected by the integrated-consistency model. The highest number of accidents has been identified at 24 km at F0050 based on the area design consistency where poor design is the integrated quality consistency model for car and motorcycle. The study shows that crashes and fatalities are not fully affected by traffic volumes but road design performances and driving behaviors.

How drivers adapt their behaviour to changes in task complexity: The role of secondary task demands and road environment factors

The present study investigates the impact of different sources of task complexity such as driving demands and secondary task demands on driver behaviour. Although much research has been dedicated to understanding the impact of secondary task demands or specific road traffic environments on driving performance, there is little information on how drivers adapt their behaviour to their combined presence. This paper aims to describe driver behaviour while negotiating different sources of task complexity, including mobile phone use while driving (i.e., calling and texting) and different road environments (i.e., straight segments, curves, hills, tunnels, and curves on hills). A driving simulator experiment was conducted to explore the effects of different road scenarios and different types of distraction while driving. The collected data was used to estimate driving behaviour through a Generalized Linear Mixed Model (GLMM) with repeated measures. The analysis was divided into two phases. Phase one aimed to evaluate driver performance under the presence and absence of pedestrians and oncoming traffic, different lanes width and different types of distraction. The second phase analysed driver behaviour when driving through different road geometries and lane widths and under different types of distraction. The results of the experiment indicated that drivers are likely to overcorrect position in the vehicle lane in the presence of pedestrians and oncoming traffic. The effect of road geometry on driver behaviour was found to be greater than the effect of mobile phone distraction. Curved roads and hills were found to influence preferred speeds and lateral position the most. The results of this investigation also show that drivers under visual-manual distraction had a higher standard deviation of speed and lateral position compared to the cognitive distraction and the non-distraction condition.

Artificial intelligence based commuter behaviour profiling framework using Internet of things for real-time decision-making

Road traffic environments are highly dynamic and volatile with a multitude of roadside and external environmental factors contributing to its dynamicity. Apart from infrastructure-related means such as traffic lights, planned and unplanned road events and different road networks, a core component which contributes towards the traffic environment is the human factor which is heavily overlooked in the current studies. Due to diverse travel patterns of day-to-day activities, the commuter behaviour is directly depicted in traffic patterns providing an opportunity to further explore human behaviours using road traffic. Conducting such analysis would reveal different commuter behavioural patterns that can be used for optimization and timely management of operations. However, to conduct such real-time behaviour analysis, large volumes of high-frequency data are required with high granularity, as well as, a suitable technology to manage such data. Addressing these needs, we propose an environment-driven commuter behavioural model that can be used to elucidate diverse behaviours in road traffic environments. We conceptualized, designed and developed an artificial intelligence based commuter behaviour profiling framework to detect diverse commuter behavioural profiles, fluctuating and routine patterns among commuters using traffic flow profiling and travel trajectory analysis. We evaluated the framework using 190 million data points captured from the Bluetooth sensor network of the Melbourne arterial road network, in the state of Victoria in Australia. The results demonstrate that traffic flow profiling of the proposed framework can provide insights on recurrent commuter behaviours that are distinct to a selected area with a high granularity. Moreover, traffic trajectory analysis provides insights on non-recurrent behaviours such as accidents with regard to how such incidents impact the dynamics of the network and how the impact is propagated through the network. Besides road traffic management, the proposed framework will enable real-time decision-making when planning road infrastructure and support decision-making of government and business entities to optimize operations.

Examining Head-Down Time in Transportation: Case Study in Single-Pilot General Aviation Operations

The “head-down time” problem refers to the potential inability of an operator (e.g., pilot, car driver, or train driver) to divide his or her attention optimally between the primary visual field (e.g., out the window) and an auxiliary tool (e.g., visual display screen). This problem has become an important safety concern in road, rail, and air traffic environments. To improve transportation safety, researchers are applying technology to minimize head-down time. One of these emerging technologies is a pilot-oriented cognitive assistant called the Digital Copilot. The Digital Copilot is a working prototype that provides contextual information and aviation related reminders to the pilot in a timely manner. However, the effects of using this cognitive assistant on the pilot had not been evaluated. This research uses a cognitive task modeling software, called Cogulator, to model a pilot’s expected thoughts and actions and compare them across two different environments: one using the Digital Copilot and one using three different electronic flight bags (EFBs) without cognitive assistance. This study examines how effectively the cognitive assistant can manage mental effort, simplify tasks, and decrease head-down time during preparation for the approach phase of flight for the following five tasks: determine weather frequency, determine communication frequency, review and follow a checklist, determine if the tower is open, and determine the preferred landing runway. Results show that the Digital Copilot provides: time savings in all tasks except for determining weather frequency; savings in head-down time for all tasks; and working memory load savings, or no change, for all tasks.

Virtual instrument to obtain electrical models of piezoelectric elements used in energy harvesting

ABSTRACTA new virtual instrument (VI) has been designed to obtain the Fourier model of piezoelectric devices under test (PDUT) in road traffic environments, and the linear electrical model of the piezoelectric harvester circuit involved in energy harvesting applications. The VI provides a high grade of automatisation and high accuracy in the characterisation procedure of a piezoelectric harvesting system. The maximum power can be predicted and the number of piezoelectric elements can be calculated to achieve a given power value. The VI system controls the test bench (patent protected), which simulates the effect of the road traffic, and obtains the Fourier model of the PDUT. The VI controls the switched circuit’s matrix of the harvesting electronic hardware (HEH) to select the PDUTs and the rectifier topology. The VI also connects capacitors and load resistors of the HEH and computes the key parameters of the piezoelectric harvester model.

Virtual instrument to obtain an optimal linear model for piezoelectric elements involved in road traffic energy harvesting

A new Virtual Instrument (VI) system is presented in this paper. The VI is designed to obtain the linear electrical models of the piezoelectric elements involved in energy harvesting applications in road traffic environments. The system, the modelling and the verification methodology are described in this paper, comparing the obtained results. The piezoelectric devices under test (PDUT) are mechanically driven by a test bench, which simulates the effect of heavy or light vehicles passing over a lane in a real road. Parameters such as the traffic flow rate and vehicle speed are configurable. In addition, the VI system controls the specific hardware designed to store the energy with different harvesting topologies. The VI system described in this paper is able to parameterize the test and to control both the test bench and the harvesting hardware. It also conditions and measures electrical signals from the PDUT, and obtains the electrical model of the piezoelectric element. Using this model it is possible to scale both the number of elements and find the optimal topology needed to harvest the required energy by an electronic load.

Piezoelectric energy harvesting computer controlled test bench

In this paper a new computer controlled (C.C.) laboratory test bench is presented. The patented test bench is made up of a C.C. road traffic simulator, C.C. electronic hardware involved in automating measurements, and test bench control software interface programmed in LabVIEW™. Our research is focused on characterizing electronic energy harvesting piezoelectric-based elements in road traffic environments to extract (or "harvest") maximum power. In mechanical to electrical energy conversion, mechanical impacts or vibrational behavior are commonly used, and several major problems need to be solved to perform optimal harvesting systems including, but no limited to, primary energy source modeling, energy conversion, and energy storage. It is described a novel C.C. test bench that obtains, in an accurate and automatized process, a generalized linear equivalent electrical model of piezoelectric elements and piezoelectric based energy store harvesting circuits in order to scale energy generation with multiple devices integrated in different topologies.

Assessment of the masking effects of birdsong on the road traffic noise environment.

This study aims to explore how the soundscape quality of traffic noise environments can be improved by the masking effects of birdsong in terms of four soundscape characteristics, i.e., perceived loudness, naturalness, annoyance and pleasantness. Four factors that may influence the masking effects of birdsong (i.e., distance of the receiver from a sound source, loudness of masker, occurrence frequencies of masker, and visibility of sound sources) were examined by listening tests. The results show that the masking effects are more significant in the road traffic noise environments with lower sound levels (e.g., <52.5 dBA), or of distance from traffic (e.g., >19 m). Adding birdsong can indeed increase the naturalness and pleasantness of the traffic noise environment at different distances of the receiver from a road. Naturalness, annoyance, and pleasantness, but not perceived loudness, can be altered by increasing the birdsong loudness (i.e., from 37.5 to 52.5 dBA in this study). The pleasantness of traffic noise environments increases significantly from 2.7 to 6.7, when the occurrence of birdsong over a period of 30 s is increased from 2 to 6 times. The visibility of the sound source also influences the masking effects, but its effect is not as significant as the effects of the three other factors.

Logical Connectivity Prediction Models for VANET based on Nonlinear Regression and ELM: An Example of the AODV Protocol

Differing from the physical connectivity of the topology structure, the logical connectivity of VANET considers both the interior network configuration and the external communication environment. Hence, the traditional mathematical analysis and modeling methods which are usually used in physical connectivity research are no longer suitable for the logical connectivity prediction. Taking the AODV protocol as an example, this paper simulates the effects of different road traffic parameters on logical connectivity probability and selects three main effect factors, roadway length, vehicle number and vehicle speed. Furthermore, the inner relation between the logical connectivity and the three road traffic parameters is studied based on data mining technique and then two logical connectivity prediction models are presented, the nonlinear regression-based model and the extreme learning machinebased model. Simulation results show that the two models are both with high accuracy in predicting the network logical connectivity under different road traffic environments.

Modeling the Effects of Rainfall Intensity on Traffic Speed, Flow, and Density Relationships for Urban Roads

The relationships between traffic speed, flow, and density under various rainfall conditions on urban roads in Hong Kong are investigated in this study. The effects of rainfall intensities are examined empirically, particularly their effects on the reduction of key traffic stream parameters such as free-flow speed, speed at capacity, and capacity (or maximum flow) on urban roads. Rainfall intensity has been found to have significant impacts on urban road key traffic stream parameters, but not on traffic jam density. Generalized speed-flow and speed-density functions are also proposed and calibrated, taking into account the effects of varied rainfall intensity. The calibrated generalized functions are validated with an independent data set from the same location. The generalized speed-flow and speed-density functions are useful for assessing the performance of urban roads, particularly in cites with relatively high annual rainfall intensity. It is believed that the findings could provide better insights into the effects of rainfall intensity on urban road traffic environments for modeling their impacts on road users’ route choice behaviors.

New considerations for PM, Black Carbon and particle number concentration for air quality monitoring across different European cities

Abstract. In many large cities of Europe standard air quality limit values of particulate matter (PM) are exceeded. Emissions from road traffic and biomass burning are frequently reported to be the major causes. As a consequence of these exceedances a large number of air quality plans, most of them focusing on traffic emissions reductions, have been implemented in the last decade. In spite of this implementation, a number of cities did not record a decrease of PM levels. Thus, is the efficiency of air quality plans overestimated? Do the road traffic emissions contribute less than expected to ambient air PM levels in urban areas? Or do we need a more specific metric to evaluate the impact of the above emissions on the levels of urban aerosols? This study shows the results of the interpretation of the 2009 variability of levels of PM, Black Carbon (BC), aerosol number concentration (N) and a number of gaseous pollutants in seven selected urban areas covering road traffic, urban background, urban-industrial, and urban-shipping environments from southern, central and northern Europe. The results showed that variations of PM and N levels do not always reflect the variation of the impact of road traffic emissions on urban aerosols. However, BC levels vary proportionally with those of traffic related gaseous pollutants, such as CO, NO2 and NO. Due to this high correlation, one may suppose that monitoring the levels of these gaseous pollutants would be enough to extrapolate exposure to traffic-derived BC levels. However, the BC/CO, BC/NO2 and BC/NO ratios vary widely among the cities studied, as a function of distance to traffic emissions, vehicle fleet composition and the influence of other emission sources such as biomass burning. Thus, levels of BC should be measured at air quality monitoring sites. During morning traffic rush hours, a narrow variation in the N/BC ratio was evidenced, but a wide variation of this ratio was determined for the noon period. Although in central and northern Europe N and BC levels tend to vary simultaneously, not only during the traffic rush hours but also during the whole day, in urban background stations in southern Europe maximum N levels coinciding with minimum BC levels are recorded at midday in all seasons. These N maxima recorded in southern European urban background environments are attributed to midday nucleation episodes occurring when gaseous pollutants are diluted and maximum insolation and O3 levels occur. The occurrence of SO2 peaks may also contribute to the occurrence of midday nucleation bursts in specific industrial or shipping-influenced areas, although at several central European sites similar levels of SO2 are recorded without yielding nucleation episodes. Accordingly, it is clearly evidenced that N variability in different European urban environments is not equally influenced by the same emission sources and atmospheric processes. We conclude that N variability does not always reflect the impact of road traffic on air quality, whereas BC is a more consistent tracer of such an influence. However, N should be measured since ultrafine particles (&lt;100 nm) may have large impacts on human health. The combination of PM10 and BC monitoring in urban areas potentially constitutes a useful approach for air quality monitoring. BC is mostly governed by vehicle exhaust emissions, while PM10 concentrations at these sites are also governed by non-exhaust particulate emissions resuspended by traffic, by midday atmospheric dilution and by other non-traffic emissions.

Australian Occupational Therapy Driver Assessors’ Opinions on Improving On-Road Driver Assessment Procedures

We collected practitioner opinions to improve the validity and reliability of the on-road driver assessment procedures used in Australia. We used focus groups to document the views of experienced occupational therapy driver assessors using a purposive sampling method. Eight focus groups were conducted with 55 clinicians practicing in urban and rural regions. There was strong support for greater standardization of procedures for all tests. For drivers seeking unrestricted (open) licenses, use of standard routes with predetermined assessment points was important where practicable. Where use of a nonstandard route for this purpose was unavoidable, it was important to specify a minimum set of requirements related to route characteristics and assessment items. Australian occupational therapy driver assessors support greater standardization of test routes and procedures to improve reliability and validity. However, the extent to which standardization can be achieved is limited by variable road traffic environments where assessments are conducted.

Field evaluation of UHF radio propagation for an ITS safety system in an urban environment

Roadside-to-vehicle and vehicle-to-vehicle communication systems have been proposed as part of ITS development to help achieve vehicle safety and realize more secure road traffic environments. In this article we first introduce several typical applications and their radio range requirements for vehicle safety communication systems to clarify the technical point of view. Then we show some field experiment results in an urban area in Tokyo to investigate and verify the radio propagation characteristics and the quality of communications by using a wireless radio prototype system. Finally, we conclude that the current prototype system has potential to fulfill the radio range requirements of vehicle safety communications, but there are still lots of issues that need to be addressed.

New Metal Emission Patterns in Road Traffic Environments

The increased awareness of traffic as a major diffuse metal emission source emphasizes the need for more detailed information on the various traffic-related sources and how and where the metals are dispersed. In this study, metal emission patterns in the road traffic environment were examined from the perspective of different surrounding factors, e.g. the importance of intersections, deceleration, vehicle speed and traffic density. A total of 148 topsoil samples from 18 south Swedish roads were analysed (using GFAAS) for traffic-emitted metals, i.e. Cd, Cr, Cu, Ni, Pb, Sb and Zn. The roadside topsoil metal concentrations were used to examine correlations between metals and surrounding factors. The studied metals were divided into three groups corresponding to different emission sources: metals from decelerating activities (Cu, Sb and Zn), metals as historical residues from the combustion of petrol (Pb and Cd), and non-source-specific metals (Cr and Ni). It was found that Cu and Sb, despite their rather short history as traffic-emitted metals, have increased more than eightfold in roadside soils compared to background levels. The major source of road traffic related Cu and Sb is brake linings. The significant increase of Cu and Sb in roadside topsoil stresses the need for metal transport studies as well as effect studies of these metals. Metals emitted due to decelerating activities were not correlated to elevated concentrations near road junctions. Emission patterns of traffic-related metals alongside roads are crucial in order to be able to evaluate the optimal localization of storm water treatment ponds.

A Research on Interrelation between Illuminance at Intersections and Reduction in Traffic Accidents.

One recently apparent trend in increasing traffic accidents in Japan is the increase in nighttime accidents. To address this problem, various traffic safety measures have been introduced aiming at safer road traffic environments. Among these measures, road lighting, in particular ‘local lighting’ has been introduced in an increasing number as a countermeasure against nighttime accidents. However, in terms of number of fatal accidents by road profile, the ‘at intersection’ accounts for the largest portion of the fatalities. Therefore, a more effective intersection lighting measure must be studied. This paper discusses the illuminance levels expected for intersection lighting from the viewpoint of traffic accident reduction effect and reports the review result. The means used in reviewing were accident data before and after introduction of accident countermeasure and statistical analysis. It was learned from the result of these review works that an average road surface illuminance at intersections maintained at 20 lx or higher, as a level expected for intersection lighting, can provide the effect of accident countermeasure, and that an average road surface illuminance of 30 lx can further positively develop a statistically significant result as to reduction in traffic accidents.