University Kebangssan Malaysia Faculty of Engineering Department of Civil and Structural Engineering Intelligent Urban Traffic Control System

KKKA6424

Assignment 2

Supervision: Prof. Ir. Dr Riza Atiq Prepared by: Hassn Ahmed H Hassn P64139 Malek M A Algadi P64143

Introduction
An Urban Traffic Control system (UTC) based on agent technology that is Able to adapt and respond to traffic conditions in real-time and still maintain Its integrity and stability within the overall transportation system and in the Meantime get a system that makes better use of the capacity of intersections. The key aspects of improved control, for which contributions from artificial Intelligence (AI) and artificial intelligent agents (IA) can be expected Include (Ambrosino et al., 1994): - The capability of dealing with multiple problems and conflicting Objectives; - The capability of making decisions on the basis of temporal analysis and Developments. - The ability of managing, learning, and responding to non-recurrent and Unexpected events; - self adjustability is an integral part of IA based units; - The, more flexible, control unit can, pro-active, optimize while operating. The most useful agent in UTC would be a traffic signal control device. Saito et al. (1997) have found that the use of quick response demand prediction models in saturated situations (degree of saturation > 0.5) could improve delay's per vehicle on a single approach intersection by 5% to 15 %. In saturated situations such an improvement is huge and is achievable by intelligent signal control. Such an UTC system requires: monitoring system of traffic, a rule- or model base for evaluation and adjustment, a model of the surrounds and an efficient diagnostic routine for both traffic light operations as well as rule- and parameter adjustments. Figure 1: Actuated control strategy based on agents The essence of an, demand responsive, proactive, UTC system can be based on several, coupled, intersection control ITSA's (Intelligent Traffic Signaling Agent). The design of a multi-agent system requires flexible autonomy. Meaning that agents will be required to Work autonomously, but will often be influenced by others. For a specific ITSA, implemented to serve as an urban traffic control agent, the following aspects are taken into account (Rosemont, 1998): - The ITSA has some goals to accomplish: maximizing traffic flow, given its

Rule-base; - The ITSA has rules to obey and roles to perform; - The ITSA decide on what actions to take; helped by its controller, the view and knowledge it has of its environment, its abilities and its state; - The ITSA has skills and tasks that it can perform depending on situations. The agent solves a problem mostly acting on its own 'feeling' and its Knowledge.

SCATS It has long been a priority for Suffolk County to ensure the availability of Safe and reliable public transportation for all our residents particularly for Those people with disabilities who have special transportation needs. Operating since 1994, the Suffolk County Accessible Transportation (SCAT) program has provided shared ride, curb-to-curb reservation Transportation service to Suffolk residents who are unable to use the fixed Route public bus service for some or all of their trips. SCAT was designed to Increase mobility for people who cannot use our fleet of transit buses, which Is wheelchair-lift equipped to accommodate a wide range of disabilities. SCAT dispatchers will make every effort to make your trip as direct and Quick possible. However, SCAT is a form of public transit and your trip is Likely to be combined SCAT customers can also travel from Suffolk County To points West in Nassau by transferring to Nassaus Able Ride or Connecting from the LIRR for longer trips. Federal guidelines also allow you to travel on other paratransit systems as

in the United States up to 21 days per year, as long as you have your SCAT-ID card up to date.Upon request, SCAT drivers will assist passengers who use wheelchairs while boarding and leaving via lift, and with the use of the securement device. For curb to curb service drivers are not required to escort you between curbside and building entrances. Drivers are not required to carry packages for you. If you need assistance getting to and from your pickup locations, please arrange for someone to help you.

Split, Cycle and Offset Optimization Technique (SCOOT) Modern traffic signal control provides an important tool in the traffic managers toolbox for managing the highway network and SCOOT is the world leading adaptive signal control system. It coordinates the operation of all the traffic signals in an area to give good progression to vehicles through the network. Whilst coordinating all the signals, it responds intelligently and continuously as traffic flow changes and fluctuates throughout the day. It removes the dependence of less sophisticated systems on signal plans, which have to be expensively updated. Many benefits are obtained from the installation of an effective Urban Traffic Control system utilizing SCOOT, both reducing congestion and maximizing efficiency which in turn is beneficial to the local environment and economy. World leading adaptive control system Customized congestion management Reductions in delay of over 20% Maximize network efficiency Flexible communications architecture Public transport priority Traffic management Incident detection Vehicle emissions estimation

Comprehensive traffic information

Modern traffic management and control systems must account for all methods of transport in our urban areas and SCOOT provides effective priority for public transport without disadvantaging the normal traffic, allowing public transport vehicles to adhere to their schedule and hence provide a credible alternative mode of travel. SCOOT has been demonstrated in over 200 towns and cities in over 14 countries around the world given proven benefits in reduced congestion and delay. These have been demonstrated several times with detailed studies highlighting the effectives of SCOOT urban traffic control as a tool for management of traffic and congestion.

The development of SCOOT In urban areas where traffic signals are close together, the co-ordination of adjacent signals is important and gives great benefits to road users. Coordinating

signals over a network of conflicting routes are much more difficult than co coordinating along a route. Early work developed off-line software to calculate optimum signal settings for a signal network. TRANSYT, developed by TRL, is probably the best known example. TRANSYT can be used to compile a series of fixed time signal plans for different times of day or for special recurring traffic conditions. TRL developed a methodology to overcome these problems. An on line computer continuously monitored traffic flows over the whole network, fed the flows into an online model, similar to that used in TRANSYT, and used the output from the model as

input to its signal timing optimizers. These optimizers made a series of frequent small adjustments to signal timings to minimize the modeled vehicle delays throughout the network. This was the basis of SCOOT, which, has been continuously developed to meet the needs of today's traffic managers.

The working of SCOOT The Kernel software at the heart of a SCOOT system is standard to all installations. The additional software (the knitting or UTC software) which links the SCOOT Kernel to on-street equipment and which provides the user interface is specific to the supplier. The user interface includes the data input to store information on the detector locations, physical layout of the road network and how the traffic signals control the individual traffic streams in the SCOOT database. Any adaptive traffic control system relies upon good detection of the current conditions in real-time to allow a quick and effective response to any changes in the current traffic situation. Detectors are normally required on every link. Their location is important. To provide good information in advance of the vehicles arrival at the stop line SCOOT detectors are usually positioned at the upstream end of the approach link. Inductive loops are normally used, but other methods are also available.

Information from the detectors is input to the SCOOT model, which models the progression of the traffic from the detector through the stop line. It takes due account of the state of the signals and any consequent queues. The operation of the model is summarized in the diagram and described below. When vehicles pass the detector, SCOOT receives the information and converts the data into its internal units and uses them to construct "Cyclic flow profiles" for each link. The sample profile shown in the diagram is cooler coded green and red according to the state of the traffic signals when the vehicles will arrive at the stop line at normal cruise speed. Vehicles are modeled down the link at cruise speed and join the back of the queue (if present). During the green, vehicles discharge from the stop line at the validated saturation flow rate. The data from the model is then used by SCOOT in three optimizers which are continuously adapting three key traffic control parameters the amount of green for each approach at each junction (Split), the time between adjacent signals (Offset) and the time allowed for all approaches to a signaled intersection (Cycle time). These three optimizers are used to continuously adapt these parameters for all intersections in the SCOOT controlled area, minimizing wasted green time at intersections and reducing stops and delays by synchronizing adjacent sets of signals. The operation of the optimizers provides the necessary combination of responsiveness to traffic fluctuations and the stability to maintain coordination. The split optimizer optimizes every stage change, the offset is optimized each signal cycle for every node and the cycle time for each region is optimized once every five minutes or once every two and a half minutes when required to respond to rapid flow changes. SCOOT signal timings evolve as the traffic situation changes without any of the harmful disruption caused by changing fixed time plans on more traditional urban traffic control systems. By the combination of relatively small changes to traffic signal timings, SCOOT responds to short term local peaks in traffic demand, as well as following trends over time and maintaining constant co-ordination of the signal network. The traffic engineer can use the traffic management facilities of SCOOT to manage traffic in line with the local policy as described overleaf.

Traffic Management

In addition to the efficient control of traffic, SCOOT provides a wide range of traffic management facilities. Further details of the bus priority and gating techniques are provided in separate leaflets in this series. Throughout its life SCOOT has been enhanced, particularly to offer an ever wider range of traffic management tools. The traffic manager has many tools available within SCOOT to manage traffic and meet local policy objectives such as: favoring particular routes or movements, minimizing network delay, delaying rat runs and gating traffic in certain areas of the city. Because of its efficient control and modeling of current conditions, SCOOT has much more scope to manage traffic than less efficient systems. For instance, buses can be given extra priority without unacceptable disruption to other traffic. SCOOT detectors are positioned where they will detect queues that are in danger of blocking upstream junctions and causing congestion to spread through the network. Within SCOOT, the traffic manager is able to priorities where such problems should be minimized and SCOOT then automatically adjusts timings to manage the congestion. Where local action is insufficient, the engineer can specify holding areas where queues should be relocated to in critical conditions, gating traffic entering the urban area to ensure efficient operation of critical, bottleneck links. SCOOT will continuously monitor the sensitive area and smoothly impose restraint to hold traffic in the specified areas when necessary. SCOOT naturally reduces vehicle emissions by reducing delays and congestion within the network. In addition it can be set to adjust the optimization of the signal timings to minimize emissions and also provide estimations of harmful emissions within the controlled area. SCOOT MC3 includes a congestion supervisor to help apply the congestion management facilities most effectively to meet local conditions.

System basics Good traffic data is a prerequisite for successful operation and the detectors are an essential part of the SCOOT system. Inductive loops are most common, though other types of detector can be used. For best results, detectors are required on each link. Installing inductive loops, and maintaining them subsequently, is a significant element in the cost of SCOOT, although less than would be required if all the junctions were operated by isolated VA. Overhead detectors have been used successfully in some situations. A SCOOT network is divided into "regions", each containing a number of "nodes" (signalled junctions and pedestrian crossings) that all run at the same cycle time to allow co-ordination. Nodes may be "double cycled" (i.e. operate at half of the regional cycle time) at pedestrian crossings or under saturated junctions. Region boundaries are located across links where coordination is least critical, e.g. long links. Data on the regions, nodes, stages, links and detectors will need to be stored in the SCOOT database. When all the equipment has been installed and the network data input into the database, the system will need to be validated. Validation of SCOOT is the process of calibrating the SCOOT traffic model so that it reflects as accurately as possible the actual events on the street network. This is critical, to ensure effective performance of the system. Those parts of the system that have been validated can be operated under SCOOT control whilst further nodes are being validated. Once the system has been validated, the traffic management parameters can be set to manage traffic in line with the authoritys strategy. Highway authorities wishing to install a SCOOT system or to upgrade an existing one may wish to go straight to one or both of the two traffic system companies licensed to supply SCOOT. However, prospective users with limited experience of UTC systems may find it useful to seek advice from a consultant with experience in the field.

Intelligent Traffic Adaptive Control Area (ITACA)

ITACA is the ITS answer that brings to the urban network the greatest advances in the use of technology for traffic management. Telvent's R&D efforts and over 30 years of experience in systems and traffic control equipment have resulted in the ITACA (Intelligent Traffic Adaptive Control Agent) system: a solution for traffic management problems of urban mobility. ITACA continually adapts to the current traffic conditions by analysing the parameters for quantification of the current traffic demand and then defining a control plan that best serves that demand. ITACA changes the plan variables: cycle, split and offset, by reference to the parameters of flow and detector occupation - both collected in fine precision over short periods. Adaptive system in real time. That is, the traffic parameters integrated from these fine measurements are used to generate the control variables. The measurement and calculation is done at the best possible moment so that the control adjustments can be immediately implemented. They are restricted in size so as not to disrupt the traffic flow and used ahea of traffic as it approaches the stop light.

The two pillars of ITACA: 1. Frequent small adjustments enabling ITACA to optimize the current plan without disrupting the traffic flow. Taking into account not only volume of flow on each approach to every intersection but also the second in the control cycle when it will arrive at the stop light is fundamental to coordinating intersections. 2.Using a traffic model updated frequently with fresh data enables a constantly available accurate prediction of the next control cycle. The model produces probabilities every five seconds at each stop light of each junction for each of the following details: the demand flow, rate of approach and timing the length of the queue the vehicle delay the number of vehicle stops ITACA does not need pre-calculated plans to work, as all plan variables are calculated (not selected) and implemented in real time according to the measured parameters of the current traffic conditions.

The problem of congestion The key to this predicament is a software tool with a wider view that can analyse the network situation and communicate its recommendations to the Adaptive Subsystem. Using the model of the controlled network, it can recognise pre-congestion and congested situations and implement strategies as resolution for them. The most flexible tool for this is the Expert Subsystem. With this, the local traffic engineer can investigate and record the strategies most helpful for coping with his own local network and its problems. UTMC UTMC - Urban Traffic Management and Control has been developed through a large programmed funded by the Department for Transport. The primary goal of UTMC is to deliver better tools which support the pro-active management of the urban traffic mix, essential if wide ranging local transport objectives are to be met. Such policy aims now include public transport priority, improved conditions for vulnerable road users, reducing traffic impact on air quality, improving safety, restraining traffic in sensitive areas and managing congestion. SCOOT has been at the heart of the

demonstration stage of UTMC and has been enhanced to maintain that position. The use of time-stamped data in SCOOT MC3 enables suppliers to produce systems that can exploit both modern packet switched communications systems and the UTMC data transmission protocols. Substantially compared with vehicle actuated (i.e. non co-ordinated) signal operation. Typical delay reductions were 23% in Worcester and 30% in Southampton. Comparisons of the benefits of SCOOT, with good fixed time plans, showed reductions in delays to vehicles of 12% in Glasgow and 27% at Folsehill Road in Coventry. Surveys were taken throughout the day in various locations, including a very dense urban network in the centre of Glasgow and a radial network in Coventry with longer link lengths. In practice, fixed time plans go out of date as traffic patterns change, on average by about 3% a year, so the benefits of SCOOT over an older fixed time plan would be even greater. On average, it is estimated that SCOOT would reduce delays by approximately 12% against up-to-date and 20% over a typical fixed-time system. In 1993 a SCOOT demonstration6 project in Toronto, Canada showed an average reduction in vehicle delays of 14% over the existing fixed time plans. during weekday evenings and Saturdays, vehicle delays were reduced by 21% and 34%. In unusual conditions following a baseball game, delays were reduced by 61%, demonstrating SCOOT's ability to react to unusual events. It was also estimated that updating the Toronto's fixed time plans would require 30 person years of effort.

BLISS These proceedings contain the papers presented at the 2008 ECSIS Symposium on Bioinspired, Learning, and Intelligent Systems for Security (BLISS-2008), held in Edinburgh, UK, on August 4-6, 2008. This symposium was addressed to developers and users of reliable, versatile and intelligent systems needed by a broad range of security applications. Intelligent systems are defined here as artificial computational systems which operate in part or fully autonomously, and which display behavior that if it were to be observed in animals would normally become associated with intelligence of one sort or another.

Examples of such applications are: the detection and prevention of cybercrimes and identity theft, internet security, security of financial systems, security of public transportation systems, emergency response systems (e.g. combining space-based systems with geographical information systems), etc. Systems with different degrees of autonomy of operation benefit greatly from incorporating aspects and mechanisms that are found in a broad range of biological systems: from survivability and adaptation of the simple living structures to learning, creativity, cognition and various forms of intelligence that are normally associated with humans. The symposium aimed to bring together: (a) investigators of bio-inspired and intelligent techniques (more exactly, techniques that increase the machine intelligence quotient (MIQ), such as, for example, techniques of Artificial Intelligence) and their implementations on high performance systems with (b) real-world application developers, project managers, system integrators and end users of security applications. We would like to acknowledge the support and hard work of the many individuals who made BLISS-2008 a reality. First, we thank the authors and the invited speakers for their high quality contribution. We express our gratitude to the Program Committee for the gracious assistance in the referring process. We thank the University of Edinburgh for their support in local organization and hosting the event. We acknowledge and are grateful for the support from members of the ECSIS Network, Institute for System Level Integration, UK, and Spiral Gateway, Ltd, UK. Last, but not least, we thank Thomas Baldwin and Silvia Ceballos at the IEEE Computer Society Conference Publishing Service for their support in making this publication possible. BLIND SPOT ASSIST IS NOW AVAILABLE AS AN OPTION IN THE S CLASS AND CL CLASS MERCEDES: Mercedes-Benz employs six short-range radar sensors for the new assistance system, which can be found in the front and rear bumpers. The sensors monitor the zone to the side and rear of the car on both the left and the right. In so doing, they cover the area known as the "blind spot" which drivers are unable to see in the exterior mirrors. If the system detects another vehicle in the danger zone, a red warning symbol appears in the exterior mirror glass. This symbol informs the driver that it may be dangerous to

change lanes. Should the driver ignore this warning and switch on the indicators, the red symbol in the mirror will start to flash and an audible warning will also sound. Blind Spot Assist - This system uses radar sensors in the rear bumper to monitor your blind spot on both sides of the car. When you start the vehicle a little orange triangle in the side-view mirrors illuminates to let you know the system is active. While you are driving the mirror is clear unless there is a car in your blind spot. Then you will see a red triangle. If you attempt to change lanes with a red triangle illuminated, the red triangle begins to flash and the car beeps twice to alert you. This has been incredibly useful for me these last few days as the car I have been driving has all of the MSRP stickers blocking my view. I can see this feature being incredible helpful to everyone, but especially for those of shorter stature or with limited movement in their necks. Blind Spot Warning ITERIS AutoVue Blind Spot Warning system, manufactured by Delphi, helps drivers avoid or reduce the severity of side-related accidents resulting from objects in the side blind spot. When a vehicle is detected in the side blind spot, the Autocue Side Alert feature provides a visual alert to help drivers avoid an accident. When the turn signal is activated, an audible alert is also provided. The Autocue Blind Spot Warning system integrates radar-based technology with intuitive algorithms to work in a variety of situations.

Conclusions The particular techniques proposed are experimental and not yet mainstream, especially when proposed for such a large, on-line, application. The pro-active and re-active nature of agents can be a helpful paradigm in intelligent traffic management and control. Further (real-life) tests on a control strategy, based on intelligent and autonomous agents, are necessary to provide appropriate evidence for operational use as relatively little is known about the global behavior of these intelligent agent systems when they are scaled up to deal with more realistic problems. As this research is still ongoing we hope, in the end, to demonstrate that an integrated dynamic urban traffic control system based on agent technology can adapt and respond to real world traffic conditions in real-time. A working prototype of such a system should give appropriate evidence on the usability of AI agent based control systems. Signal control systems that have the capability of optimizing and adjusting the traffic light settings are able to improve the vehicular throughput and minimize delay through appropriate response to changes in demand patterns. With the introduction of two un-coupled loops, whether agent technology is used or not, a different theory of traffic control can be met. Artificial agents are a metaphor to be used for theoretical and implementation purposes. Primarily results indicate that

given an automated control strat implemented in the traffic signaling devices we can get a system that makes better use of the capacity of the intersection. It has been shown that control systems based on agent technology can adapt and respond to changing conditions in real-time and in the meantime making better use of the infrastructure. .