Multi-agent Reinforcement Learning for Traffic Signal Control

Optimal control of traffic lights at junctions or traffic signal control (TSC) is essential for reducing the average delay experienced by the road users amidst the rapid increase in the usage of vehicles. In this paper, we formulate the TSC problem as a discounted cost Markov decision process (MDP) and apply multi-agent reinforcement learning (MARL) algorithms to obtain dynamic TSC policies. We model each traffic signal junction as an independent agent. An agent decides the signal duration of its phases in a round-robin (RR) manner using multi-agent Q-learning with either is an element of-greedy or UCB 3] based exploration strategies. It updates its Q-factors based on the cost feedback signal received from its neighbouring agents. This feedback signal can be easily constructed and is shown to be effective in minimizing the average delay of the vehicles in the network. We show through simulations over VISSIM that our algorithms perform significantly better than both the standard fixed signal timing (FST) algorithm and the saturation balancing (SAT) algorithm 15] over two real road networks.

Effects of longer heavy vehicles on traffic congestion

Two-lane, "microscopic" (vehicle-by-vehicle) simulations of motorway traffic are developed using existing models and validated using measured data from the M25 motorway. An energy consumption model is also built in, which takes the logged trajectories of simulated vehicles as drive-cycles. The simulations are used to investigate the effects on motorway congestion and fuel consumption if "longer and/or heavier vehicles" (LHVs) were to be permitted in the UK. Baseline scenarios are simulated with traffic composed of cars, light goods vehicles and standard heavy goods vehicles (HGVs). A proportion of conventional articulated HGVs is then replaced by a smaller number of LHVs carrying the same total payload mass and volume. Four LHV configurations are investigated: an 18.75 m, 46 t longer semi-trailer (LST); 25.25 m, 50 t and 60 t B-doubles and a 34 m, 82 t A-double. Metrics for congestion, freight fleet energy consumption and car energy consumption are defined for comparing the scenarios. Finally, variation of take-up level and LHV engine power for the LST and A-double are investigated. It is concluded that: (a) LHVs should reduce congestion particularly in dense traffic, however, a low mean proportion of freight traffic on UK roads and low take-up levels will limit this effect to be almost negligible; (b) LHVs can significantly improve the energy efficiency of freight fleets, giving up to a 23% reduction in fleet energy consumption at high take-up levels; (c) the small reduction in congestion caused by LHVs could improve the fuel consumption of other road users by up to 3% in dense traffic, however in free-flowing traffic an opposite effect occurs due to higher vehicle speeds and aerodynamic losses; and (d) underpowered LHVs have potential to generate severe congestion, however current manufacturers' recommendations appear suitable. © 2013 IMechE.

Risk of fatal injury in older adult drivers, passengers, and pedestrians

Objectives To compare risk of fatal injury in elderly road users (drivers, passengers, pedestrians) with that of younger age groups and to assess the contribution of elderly road users to the number of reported fatalities in the population. Design Fatality age was categorized as 21 to 29, 30 to 39, 40 to 49, 50 to 59, 60 to 69, or 70 and older, and road user was categorized as driver, passenger, or pedestrian. Estimated number of trips made by each age group was used to adjust for exposure and to measure individual risk. Setting Fatalities recorded in Britain between 1989 and 2009. Participants Population-wide fatal injury counts in Britain. Measurements Age of fatally injured drivers, passengers, and pedestrians. Estimated number of trips made per year by drivers, passengers, and pedestrians. Results Risk of fatal injury, but not fatality numbers in the population, were higher for older adult (=70) drivers than for younger age groups. Risk of fatal injury was also high for older adult passengers and pedestrians, who represented the majority of older adult fatalities. Conclusion Previous emphasis on driver impairment in older age has unduly focussed attention on elderly drivers, who represent a minority of all driver fatalities. Older adults represent a much larger proportion of passenger and pedestrian fatalities. Additional policy schemes and initiatives should be targeted at safeguarding older adult passengers and making the road environment safer for elderly pedestrians. © 2012, Copyright the Authors Journal compilation © 2012, The American Geriatrics Society.

TEENAGERS AND ILLICIT DRUG-USE - EXPANDING THE USER VS NONUSER DICHOTOMY

The present study examines proximal and distal factors associated with the use and non-use of illegal substances within a sample of 860 teenagers in North Wales. Arguing that there is predictive utility in expanding the traditional 'users vs non-users' design dichotomy, four groups are identified-resistant and vulnerable non-users and experimental and repeated users. 'Person' variables (life satisfaction, deviance, hopelessness and drug-related attributions) appeared to primarily differentiate the vulnerable group from their resistant counterparts and identify this, as yet non-using group, with user samples. It is suggested that these variables might represent 'risk' factors for illicit substance use and that the group design employed suggests they precede, rather than follow as a consequence of, illicit drug use. Like their resistant counterparts however, the vulnerable group are differentiated from user samples on some lifestyle and context indices. It is argued that these represent 'protective' influences in an otherwise at-risk group of non-users. Variables associated with an escalation of illicit drug use are discussed in considering the differences between the experimental and repeated user groups. Apart from the more proximal factor of drug-related attributions, 'person' variables appeared less involved here. Repeated users did however, tend to use a greater number of drugs, have a greater proportion of friends who also used illegal substances and significantly fewer had a Welsh cultural identity.

Overestimated crash risks of young and elderly drivers

Young and elderly drivers are reported to have markedly greater crash rates than drivers of other ages, but they travel less frequently and represent a minority of road users. Consequently, many crashes involving young or elderly drivers also involve drivers of middle age ranges who travel more frequently.

Using geotechnical and LIDAR spatial monitoring to determine key environmental slope instability thresholds of a Jurassic coastal landslide: Straidkilly Point, Northern Ireland, UK.

The Antrim Coast Road stretching from the seaport of Larne in the East of Northern Ireland to the famous Giant’s Causeway in the North has a well-deserved reputation for being one of the most spectacular roads in Europe (Day, 2006). At various locations along the route, fluid interactions between the problematic geology, Jurassic Lias Clay and Triassic Mudstone overlain by Cretaceous Limestone and Tertiary Basalt, and environmental variables result in frequent instances of slope instability within the vadose zone. During such instances of instability, debris flows and composite mudflows encroach on the carriageway posing a hazard to road users. This paper examines the site investigative, geotechnical and spatial analysis techniques currently being implemented to monitor slope stability for one site at Straidkilly Point, Glenarm, Northern Ireland. An in-depth understanding of the geology was obtained via boreholes, resistivity surveys and laboratory testing. Environmental variables recorded by an on-site weather station were correlated with measured pore water pressure and soil moisture infiltration dynamic data.
Terrestrial LiDAR (TLS) was applied to the slope for the monitoring of failures, with surveys carried out on a bi-monthly basis. TLS monitoring allowed for the generation of Digital Elevation Models (DEMs) of difference, highlighting areas of recent movement, erosion and deposition. Morphology parameters were generated from the DEMs and include slope, curvature and multiple measures of roughness. Changes in the structure of the slope coupled with morphological parameters are characterised and linked to progressive failures from the temporal monitoring. In addition to TLS monitoring, Aerial LiDARi datasets were used for the spatio-morphological characterisation of the slope on a macro scale. Results from the geotechnical and environmental monitoring were compared with spatial data obtained through Terrestrial and Airborne LiDAR, providing a multi-faceted approach to slope stability characterization, which facilitates more informed management of geotechnical risk by the Northern Ireland Roads Service.

L'habitude en matière de conduite automobile : une analyse de ses composantes et du rôle qu'elle joue dans le maintien et la régulation des comportements de conduite

« La grande majorité des accidents demeure liée aux comportements dangereux des usagers de la route ». Cet énoncé, lapidaire, fait aujourd’hui figure d’évidence au sein de la communauté des intervenants en sécurité routière. Il repose pourtant sur des prémisses discutables. Le problème le plus fondamental réside dans le fait que la recherche des dernières décennies s’est presque toute entière vouée à l’analyse des seuls aspects défaillants de la conduite (l’accident, les infractions, les erreurs et les fautes de conduite, les conducteurs à risque ou dysfonctionnels, les attitudes et traits de caractère incitant à la conduite dangereuse, etc.). Ce faisant, on a fini par oublier qu’il nous restait encore beaucoup de choses à apprendre sur le fonctionnement usuel de la conduite automobile. Comment, en effet, peut-on escompter élucider tous les rouages de la dynamique accidentelle sans avoir au préalable cerné, et bien compris, les mécanismes de la conduite « ordinaire » ? Comment peut-on parvenir à approfondir notre compréhension des comportements de conduite si l’on fait totalement abstraction de toutes les activités courantes, « normales », auxquelles se livrent les conducteurs lorsqu’ils sont au volant de leur véhicule ? C’est dans la perspective de mieux comprendre les comportements de conduite, dans leur complexité et dans leur diversité, que la présente thèse a été réalisée. Y a plus spécifiquement été examinée la question des habitudes en raison de leur prédominance dans l’activité de la conduite, mais également en raison de leur résistance, des obstacles bien concrets qu’elles sont susceptibles d’opposer à tous ceux qui tentent de modifier les comportements individuels de conduite. Des entrevues en profondeur, menées auprès de trente conducteurs et conductrices âgé(e)s de 17 à 54 ans, devaient permettre de répondre, entre autres, aux questions suivantes : De quoi sont constituées les différentes habitudes en matière de conduite automobile ? Quelle place occupent-elles dans la conduite des individus ? En quoi constituent-elles un frein au changement, à la modification des pratiques adoptées ? Quelles sont les dimensions qui participent à leur installation ? Les résultats de l’analyse ont permis de jeter les bases d’un modèle des comportements de conduite où les sensations corporelles se voient conférer un rôle des plus centraux, et où l’habitude – bien davantage caractérisée par la notion de confort que par celles d’automatisme ou de répétition – concourt non seulement à la pérennité, mais également à la régulation des conduites adoptées sur la route.

Veränderungen des Raum-Zeit-Verhaltens im Zuge von Lebensumbrüchen und ihre Anforderungen an die Stadt- und Verkehrsplanung am Beispiel des Eintritts in den Ruhestand

Veränderungen des Raum-Zeit-Verhaltens im Zuge von Lebensumbrüchen und ihre Anforderungen an die Stadt- und Verkehrsplanung am Beispiel des Eintritts in den Ruhestand. In der vorliegenden Dissertation wurde untersucht, ob und in welchem Maße sich das Raum-Zeit-Verhalten im Alltag mit dem Eintritt in den Ruhestand verändert. Bei der Untersuchung handelt es sich um eine mehrjährige Panel-Studie, die in den Regionen Hamburg und Kassel durchgeführt wurde. Mit insgesamt 50 Studienteilnehmern wurden vor und nach ihrem Ausscheiden aus dem Erwerbsleben umfassende Interviews geführt. Hierbei kam die an der Oxford University entwickelte „HATS“-Methode („Household Activity Travel Simulator“) zum Einsatz, die einen tiefen Einblick in die Alltagsstrukturen und das aus ihnen resultierende raum-zeitliche Verhalten ermöglicht. Ein Untersuchungsschwerpunkt lag auf der Verkehrsmittelwahl. Auf Grundlage der Untersuchungsergebnisse wurden Handlungsempfehlungen für die Stadt- und Verkehrsplanung abgeleitet. Es zeigte sich, dass die Studienteilnehmer mit ihrem Eintritt in den Ruhestand grundsätzlich deutlich später im Tagesverlauf als Verkehrsteilnehmer in Erscheinung treten. Darüber hinaus zeichnete sich ein Bedeutungszuwachs des Stadtquartiers bzw. der nahräumlichen Mobilität ab; der Fuß- und Fahrradverkehr gewinnt für die Alltagsmobilität an Bedeutung. Versorgungs- und Dienstleistungsangebote im eigenen Wohnquartier – und somit nutzungsgemischte Stadtquartiere – erweisen sich demnach insbesondere für die Gruppe der Ruheständler als besonders relevant. Trotz der steigenden Bedeutung des Fuß-und Fahrradverkehrs zeigt die Studie, dass dem Pkw in der Alltagsmobilität eine (nach wie vor) dominante Rolle zukommt – eine Entwicklung, die sich aufgrund des Kohorteneffekts eher noch verstärken wird. Im Rahmen der Diskussion geeigneter Handlungsansätze für die Stadt- und Verkehrsplanung zur Stärkung des Umweltverbundes werden – neben Interventionen zur Attraktivitätsminderung des Pkw – insbesondere verschiedene Maßnahmen zu Angebotsverbesserungen im ÖPNV behandelt. Dabei wird u. a. auch die Verhaltensrelevanz von Kostenwahrnehmungen betrachtet. Zusätzlich wird deutlich, dass bei der Etablierung verkehrsplanerischer Maßnahmen auch die zu-nehmende Bedeutung von Wegen, die in Begleitung anderer Haushaltsmitglieder zurückgelegt werden (Stichwort: Haushaltsmobilität), berücksichtigt werden muss. Der Eintritt in den Ruhestand erweist sich grundsätzlich als eine Umbruchsituation im Lebensverlauf, die ein Aufbrechen von (Verkehrs-)Gewohnheiten im Alltag begünstigt und die Betroffenen besonders empfänglich für Informationen zu verschiedenen Verkehrsangeboten bzw. Verhaltens-alternativen werden lässt. Hinsichtlich möglicher Handlungsansätze wird in dieser Studie u. a. thematisiert, wie im Rahmen einer zielgruppenspezifischen Kommunikation im ÖPNV dieses Zeit-fenster genutzt werden kann, um Menschen an der Schwelle zum Eintritt in den Ruhestand als regelmäßige Nutzer von Bus und Bahn (neu) zu gewinnen bzw. zu halten.

The application of affine projection to the development of a siren noise cancellation system

Emergency vehicles use high-amplitude sirens to warn pedestrians and other road users of their presence. Unfortunately, the siren noise enters the vehicle and corrupts the intelligibility of two-way radio voice com-munications from the emergency vehicle to a control room. Often the siren has to be turned off to enable the control room to hear what is being said which subsequently endangers people's lives. A digital signal processing (DSP) based system for the cancellation of siren noise embedded within speech is presented. The system has been tested with the least mean square (LMS), normalised least mean square (NLMS) and affine projection algorithm (APA) using recordings from three common types of sirens (two-tone, wail and yelp) from actual test vehicles. It was found that the APA with a projection order of 2 gives comparably improved cancellation over the LMS and NLMS with only a moderate increase in algorithm complexity and code size. Therefore, this siren noise cancellation system using the APA offers an improvement in cancellation achieved by previous systems. The removal of the siren noise improves the response time for the emergency vehicle and thus the system can contribute to saving lives. The system also allows voice communication to take place even when the siren is on and as such the vehicle offers less risk of danger when moving at high speeds in heavy traffic.

Review of the effectiveness of vehicle activated signs

This paper reviews the effectiveness of vehicle activated signs. Vehicle activated signs are being reportedly used in recent years to display dynamic information to road users on an individual basis in order to give a warning or inform about a specific event. Vehicle activated signs are triggered individually by vehicles when a certain criteria is met. An example of such criteria is to trigger a speed limit sign when the driver exceeds a pre-set threshold speed. The preset threshold is usually set to a constant value which is often equal, or relative, to the speed limit on a particular road segment. This review examines in detail the basis for the configuration of the existing sign types in previous studies and explores the relation between the configuration of the sign and their impact on driver behavior and sign efficiency. Most of previous studies showed that these signs have significant impact on driver behavior, traffic safety and traffic efficiency. In most cases the signs deployed have yielded reductions in mean speeds, in speed variation and in longer headways. However most experiments reported within the area were performed with the signs set to a certain static configuration within applicable conditions. Since some of the aforementioned factors are dynamic in nature, it is felt that the configurations of these signs were thus not carefully considered by previous researchers and there is no clear statement in the previous studies describing the relationship between the trigger value and its consequences under different conditions. Bearing in mind that different designs of vehicle activated signs can give a different impact under certain conditions of road, traffic and weather conditions the current work suggests that variable speed thresholds should be considered instead.

Mapeamento geológico-geotécnico pelo método de detalhamento progressivo: aplicação no planejamento e gestão de obras rodoviárias

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Real-World Performance of Longitudinal Barriers Struck by Large Trucks

Outside of relatively limited crash testing with large trucks, very little is known regarding the performance of traffic barriers subjected to real-world large truck impacts. The purpose of this study was to investigate real-world large truck impacts into traffic barriers to determine barrier crash involvement rates, the impact performance of barriers not specifically designed to redirect large trucks, and the real-world performance of large-truck-specific barriers. Data sources included the Fatality Analysis Reporting System (2000-2009), the General Estimates System (2000-2009) and 155 in-depth large truck-to-barrier crashes from the Large Truck Crash Causation Study. Large truck impacts with a longitudinal barrier were found to comprise 3 percent of all police-reported longitudinal barrier impacts and roughly the same proportion of barrier fatalities. Based on a logistic regression model predicting barrier penetration, large truck barrier penetration risk was found to increase by a factor of 6 for impacts with barriers designed primarily for passenger vehicles. Although large-truck-specific barriers were found to perform better than non-heavy vehicle specific barriers, the penetration rate of these barriers were found to be 17 percent. This penetration rate is especially a concern because the higher test level barriers are designed to protect other road users, not the occupants of the large truck. Surprisingly, barriers not specifically designed for large truck impacts were found to prevent large truck penetration approximately half of the time. This suggests that adding costlier higher test level barriers may not always be warranted, especially on roadways with lower truck volumes.

Non-illness-related factors contributing to traffic safety in older drivers: a litterature review

Background/Study Context: Older drivers are at increased risk of becoming involved in car crashes. Contrary to well-studied illness-related factors contributing to crash risk, the non-illness-related factors that can influence safety of older drivers are underresearched. METHODS: Here, the authors review the literature on non-illness-related factors influencing driving in people over age 60. We identified six safety-relevant factors: road infrastructure, vehicle characteristics, traffic-related knowledge, accuracy of self-awareness, personality traits, and self-restricted driving. RESULTS: The literature suggests that vehicle preference, the quality of traffic-related knowledge, the location and time of traffic exposure, and personality traits should all be taken into account when assessing fitness-to-drive in older drivers. Studies indicate that self-rating of driving skills does not reliably predict fitness-to-drive. CONCLUSIONS: Most factors discussed are adaptable or accessible to training and collectively may have the potential to increase traffic safety for older drivers and other road users.

Assessing the impact of adaptive accessibility on the optimal transport policy implementation by using an integrated land-use/transport model for Madrid

Accessibility is an essential concept widely used to evaluate the impact of land-use and transport strategies in transport and urban planning. Accessibility is typically evaluated by using a transport model or a land-use model independently or successively without a feedback loop, thus neglecting the interaction effects between the two systems and the induced competition effects among opportunities due to accessibility improvements. More than a mere methodological curiosity, failure to account for land- use/transport interactions and the competition effect may result in large underestimation of the policy effects. With the recent development of land-use and transport interaction (LUTI) models, there is a growing interest in using these models to adequately measure accessibility and evaluate its impact. The current study joins this research stream by embedding an accessibility measure in a LUTI model with two main aims. The first aim is to account for adaptive accessibility, namely the adjustment of the potential accessibility due to the effect of competition among opportunities (e.g., workplaces) as a result of improved accessibility. LUTI models are particularly suitable for assessing adaptive accessibility because the competition factor is a function of the number of jobs, which is related to land-use attractiveness and the number of workers which is related, among other factors, to the transport demand. The second aim is to identify the optimal implementation scenario of policy measures on the basis of the potential and adaptive accessibility and analyse the results in terms of social welfare and accessibility. The metropolitan area of Madrid is used as a case-study and two transport policy instruments, namely a cordon toll and bus frequency increase, have been chosen for the simulation study in order to present the usefulness of the approach to urban planners and policy makers. The MARS model (Metropolitan Activity Relocation Simulator) calibrated for Madrid was employed as the analysis tool. The impact of accessibility is embedded in the model through a social welfare function that includes not only costs and benefits to both road users and transport operators, but also costs and benefits for the government and society in general (external costs). An optimisation procedure is performed by the MARS model for maximizing the value of objective function in order to find the best (optimal) policy imp lementations intensity (i.e., price, frequency). Last, the two policy strategies are evaluated in terms of their accessibility. Results show that the accessibility with competition factor influences the optimal policy implementation level and also generates different results in terms of social welfare. In addition, mapping the difference between the potential and the adaptive accessibility indicators shows that the main changes occur in areas where there is a strong competition among land-use opportunities.

Real-time incidents detection in the highways of the future

Due to ever increasing transportation of people and goods, automatic traffic surveillance is becoming a key issue for both providing safety to road users and improving traffic control in an efficient way. In this paper, we propose a new system that, exploiting the capabilities that both computer vision and machine learning offer, is able to detect and track different types of real incidents on a highway. Specifically, it is able to accurately detect not only stopped vehicles, but also drivers and passengers leaving the stopped vehicle, and other pedestrians present in the roadway. Additionally, a theoretical approach for detecting vehicles which may leave the road in an unexpected way is also presented. The system works in real-time and it has been optimized for working outdoor, being thus appropriate for its deployment in a real-world environment like a highway. First experimental results on a dataset created with videos provided by two Spanish highway operators demonstrate the effectiveness of the proposed system and its robustness against noise and low-quality videos.