Showing papers in "Transportation Research Part C-emerging Technologies in 2002"

Comparison of parametric and nonparametric models for traffic flow forecasting

Abstract: Single point short-term traffic flow forecasting will play a key role in supporting demand forecasts needed by operational network models. Seasonal autoregressive integrated moving average (ARIMA), a classic parametric modeling approach to time series, and nonparametric regression models have been proposed as well suited for application to single point short-term traffic flow forecasting. Past research has shown seasonal ARIMA models to deliver results that are statistically superior to basic implementations of nonparametric regression. However, the advantages associated with a data-driven nonparametric forecasting approach motivate further investigation of refined nonparametric forecasting methods. Following this motivation, this research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether nonparametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.

Modelling lane changing and merging in microscopic traffic simulation

Abstract: This paper introduces Simulation of Intelligent TRAnsport Systems (SITRAS), a massive multi-agent simulation system in which driver-vehicle objects are modelled as autonomous agents. The simulation outputs can be used for the evaluation of Intelligent Transport Systems applications such as congestion and incident management, public transport priority and dynamic route guidance. The model concepts and specifications, and the first applications of the model in the area of incident modelling in urban arterial networks were described in previous publications. This paper presents the details of the lane changing and merging algorithms developed for the SITRAS model. These models incorporate procedures for ‘forced’ and ‘co-operative’ lane changing which are essential for lane changing under congested (and incident-affected) traffic conditions. The paper describes the algorithms and presents simulation examples to demonstrate the effects of the implemented models. The results indicate that only the forced and cooperative lane changing models can produce realistic flow-speed relationships during congested conditions.

Urban traffic flow prediction using a fuzzy-neural approach

Abstract: This paper develops a fuzzy-neural model (FNM) to predict the traffic flows in an urban street network, which has long been considered a major element in the responsive urban traffic control systems. The FNM consists of two modules: a gate network (GN) and an expert network (EN). The GN classifies the input data into a number of clusters using a fuzzy approach, and the EN specifies the input–output relationship as in a conventional neural network approach. While the GN groups traffic patterns of similar characteristics into clusters, the EN models the specific relationship within each cluster. An online rolling training procedure is proposed to train the FNM, which enhances its predictive power through adaptive adjustments of the model coefficients in response to the real-time traffic conditions. Both simulation and real observation data are used to demonstrative the effectiveness of the method.

An agent-based approach to modelling driver route choice behaviour under the influence of real-time information

Abstract: This paper presents an agent-based approach to modelling individual driver behaviour under the influence of real-time traffic information. The driver behaviour models developed in this study are based on a behavioural survey of drivers which was conducted on a congested commuting corridor in Brisbane, Australia. Commuters' responses to travel information were analysed and a number of discrete choice models were developed to determine the factors influencing drivers' behaviour and their propensity to change route and adjust travel patterns. Based on the results obtained from the behavioural survey, the agent behaviour parameters which define driver characteristics, knowledge and preferences were identified and their values determined. A case study implementing a simple agent-based route choice decision model within a microscopic traffic simulation tool is also presented. Driver-vehicle units (DVUs) were modelled as autonomous software components that can each be assigned a set of goals to achieve and a database of knowledge comprising certain beliefs, intentions and preferences concerning the driving task. Each DVU provided route choice decision-making capabilities, based on perception of its environment, that were similar to the described intentions of the driver it represented. The case study clearly demonstrated the feasibility of the approach and the potential to develop more complex driver behavioural dynamics based on the belief-desire-intention agent architecture. (C) 2002 Elsevier Science Ltd. All rights reserved.

Coordinated and integrated control of motorway networks via non-linear optimal control

Abstract: The problem of designing integrated traffic control strategies for motorway networks with the use of ramp metering, route guidance, and motorway-to-motorway control measures is considered in this paper. A generic problem formulation is presented in the format of a discrete-time optimal control problem whose numerical solution is achieved by use of a feasible-direction algorithm. As an illustrative example, a relatively simple motorway network is considered under different control scenarios. In each case the optimal control strategy is discussed along with its effect on the traffic flow process. The results demonstrate the efficiency of the proposed approach as well as the genuinely intelligent behaviour of the designed control strategy.

Driver response to variable message sign information in London

Abstract: Variable message signs (VMS) have been installed in London to notify motorists of planned events and current network problems. To guide investment and operational decisions an understanding is required of the impacts of VMS information. This paper presents the results of a study of driver response to VMS information. The study employed questionnaires to investigate the effect of different messages on route choice. A statistical analysis of stated intention questionnaire data enabled logistic regression models to be developed relating the probability of route diversion to driver, journey and message characteristics. The resultant models indicate that the location of the incident and the message content are important factors influencing the probability of diversion. A survey of drivers' actual responses to a message activation showed that only one third of drivers saw the information presented to them and few of these drivers diverted, although many found the information useful. Only one-fifth of the number of drivers diverted compared to that expected from the results of the stated intention questionnaire. It is thought that the low response rate achieved for the stated intention survey will have exaggerated drivers' responsiveness to VMS messages. Interestingly, survey data for another UK city with a newly installed VMS system showed that the number of drivers diverting due to VMS information was very similar to that expected from the results of the stated intention questionnaire. It is suggested that the use of London's VMS signs to display warnings of disruptions expected on future dates may be reducing their effectiveness as a channel for more urgent warnings.

Genetic algorithms in bus network optimization

Abstract: This paper focuses on a new method to compute fitness function (ff) values in genetic algorithms for bus network optimization. In the proposed methodology, a genetic algorithm is used to generate iteratively new populations (sets of bus networks). Each member of the population is evaluated by computing a number of performance indicators obtained by the analysis of the assignment of the O/D demand associated to the considered networks. Thus, ff values are computed by means of a multicriteria analysis executed on the performance indicators so found. The goal is to design a heuristic that allows to achieve the best bus network satisfying both the demand and the offer of transport.

Fleet scheduling and dispatching for demand-responsive passenger services

Abstract: This paper describes a software system designed to manage the deployment of a fleet of demand-responsive passenger vehicles such as taxis or variably routed buses. Multiple modes of operation are supported both for the fleet and for individual vehicles. Booking requests can be immediate (i.e. with zero notice) or in advance of travel. An initial implementation is chosen for each incoming request, subject to time-window and other constraints, and with an objective of minimising additional travel time or maximising a surrogate for future fleet capacity. This incremental insertion scheme is supplemented by post-insert improvement procedures, a periodically executed steepest-descent improvement procedure applied to the fleet as a whole, and a “rank-homing” heuristic incorporating information about future patterns of demand. A simple objective for trip-insertion and other scheduling operations is based on localised minimisation of travel time, while an alternative incorporating occupancy ratios has a more strategic orientation. Apart from its scheduling functions, the system includes automated vehicle dispatching procedures designed to achieve a favourable combination of customer service and efficiency of vehicle deployment. Provision is made for a variety of contingencies, including travel slower or faster than expected, unexpected vehicle locations, vehicle breakdowns and trip cancellations. Simulation tests indicate that the improvement procedures yield substantial efficiencies over more naive scheduling methods and that the system will be effective in real-time applications.

A cooperative multi-agent transportation management and route guidance system

Abstract: Developing real-time approaches to manage roadway network congestion over time and space is a difficult problem. While many approaches to solving networking problems have been posed, the roadway routing problem is fundamentally different in that route choice behavior rests solely with the flow entities (drivers). The challenge is to find and implement solutions that achieve an efficient reallocation of network capacity over time and space without seriously violating any individual user’s preferences for mode, routing, departure, and/or arrival time. This paper proposes a solution approach based on cooperative multi-agent-based principled negotiation between agents that represent network managers, information service providers, and drivers equipped with route guidance systems. It is demonstrated that the cooperative, multi-agent approach is a natural extension of the National ITS Architecture. Furthermore, the approach is highly scalable and adaptable to a variety of networks and user populations.

The impact of real-time information in a two-route scenario using agent-based simulation

Abstract: Since advanced traveler information systems (ATIS) have been introduced, their potential benefits as well as their drawbacks have been discussed controversially. This will continue as long as the drivers’ reactions upon current or even predictive information about the traffic situation are not known. Thus, traffic models that also consider this feedback are necessary. In this paper, we address a basic two-route scenario with different types of information and study the impact of it using simulations. The road users are modeled as agents, a natural and promising approach to describe them. Different ways of generating current information are tested. It is pointed out that the nature of the information very much influences the potential benefits of the ATIS.

Multiagent architectures for intelligent traffic management systems

Abstract: This paper reports our experiences with agent-based architectures for intelligent traffic management systems. We describe and compare integrated TRYS and TRYS autonomous agents, two multiagent systems that perform decision support for real-time traffic management in the urban motorway network around Barcelona. Both systems draw upon traffic management agents that use similar knowledge-based reasoning techniques in order to deal with local traffic problems. Still, the former achieves agent coordination based on a traditional centralized mechanism, while in the latter coordination emerges upon the lateral interaction of autonomous traffic management agents. We evaluate the potentials and drawbacks of both multiagent architectures for the domain, and develop some conclusions respecting the general applicability of multiagent architectures for intelligent traffic management.

Reducing bias in probe-based arterial link travel time estimates

Abstract: Advanced traveler information systems and advanced traffic management systems require the ability to obtain accurate estimates of travel times within signalized networks. Probe vehicles have been suggested as a means of obtaining these travel times, but previous research has shown that bias in arrival time distributions of probe vehicles will lead to a systematic bias in the sample estimate of the mean. This paper proposes a methodology, based on stratified sampling techniques, for reducing the effect of this bias. The arrival time distribution of all vehicles, obtained from a traffic surveillance method such as an in-road loop detector, is used to weight each probe travel time report. Simulation results for a single intersection approach and for an arterial corridor illustrate the effectiveness of this method. The results for the single intersection approach indicate a correlation between the biased estimate and the population mean of 0.61, and an improved correlation between the proposed estimation method and the population mean of 0.81. Application of the proposed method to the arterial corridor resulted in a reduction in the mean travel time error of approximately 50%. The proposed method is easy to implement in field conditions and is shown to represent an improvement over traditional biased methods.

A real-time decision support system for roadway network incident response logistics

Abstract: Incident-related congestion is a serious problem of great concern for most metropolitan traffic management authorities. The high economic and social impact associated with the incident-related congestion has prompted Traffic Management Agencies world-wide to develop incident management systems (IMS). Incident response logistics (IRL) encompass all actions needed for the effective deployment of incident response resources and constitute an essential component of any IMS. The incident management decision making environment suggests that decision support systems (DSSs) can be used in order to improve the quality of the decisions and expedite the decision making process of the IRL. The objective of this paper is to develop a DSS for supporting real-time decisions related to IRL. The development of the proposed DSS is based on an extensive user-requirements survey in six European countries and integrates mathematical models, rules and algorithms in a user friendly environment in order to minimise incident response time. The proposed DSS provides the following functionalities: (i) districting, (ii) dispatching of response units (RUs), (iii) routing of the RUs, and (iv) on-scene management and it has been demonstrated successfully under real life conditions and accepted as a useful decision making tool by its users.

Traffic flow stability induced by constant time headway policy for adaptive cruise control vehicles

Abstract: This paper is concerned with the traffic flow stability/instability induced by a particular adaptive cruise control (ACC) policy, known as the “constant time headway (CTH) policy”. The control policy is analyzed for a circular highway using three different traffic models, namely a microscopic model, a spatially discrete model, and a spatially continuous model. It is shown that these three different modeling paradigms can result in different traffic stability properties unless the control policy and traffic dynamics are consistently abstracted for the different paradigms. The traffic dynamics will, however, be qualitatively consistent across the three modeling paradigms if a consistent biasing strategy is used to adapt the CTH policy to the various modeling frameworks. The biasing strategy determines whether the feedback quantity for use in the control, is taken colocatedly, downstream or upstream to the vehicle/section/highway location. For ACC vehicles equipped with forward looking sensors, the downstream biasing strategy should be used. In this case, the CTH policy induces exponentially stable traffic flow on a circular highway in all three modeling frameworks. It is also shown that traffic flow stability will be preserved for an open stretch highway if the entry and exit conditions are made to observe the downstream biasing strategy.

Using BDI agents to improve driver modelling in a commuter scenario

Abstract: The use of multi-agent systems to model and to simulate real systems consisting of intelligent entities capable of autonomously co-operating with each other has emerged as an important field of research. This has been applied to a variety of areas, such as social sciences, engineering, and mathematical and physical theories. In this work, we address the complex task of modelling drivers’ behaviour through the use of agent-based techniques. Contemporary traffic systems have experienced considerable changes in the last few years, and the rapid growth of urban areas has challenged scientific and technical communities. Influencing drivers’ behaviour appears as an alternative to traditional approaches to cope with the potential problem of traffic congestion, such as the physical modification of road infrastructures and the improvement of control systems. It arises as one of the underlying ideas of intelligent transportation systems. In order to offer a good means to evaluate the impact that exogenous information may exert on drivers’ decision making, we propose an extension to an existing microscopic simulation model called Dynamic Route Assignment Combining User Learning and microsimulAtion (DRACULA). In this extension, the traffic domain is viewed as a multi-agent world and drivers are endowed with mental attitudes, which allow rational decisions about route choice and departure time. This work is divided into two main parts. The first part describes the original DRACULA framework and the extension proposed to support our agent-based traffic model. The second part is concerned with the reasoning mechanism of drivers modelled by means of a Beliefs, Desires, and Intentions (BDI) architecture. In this part, we use AgentSpeak(L) to specify commuter scenarios and special emphasis is given to departure time and route choices. This paper contributes in that respect by showing a practical way of representing and assessing drivers’ behaviour and the adequacy of using AgentSpeak(L) as a modelling language, as it provides clear and elegant specifications of BDI agents.

Trucking industry adoption of information technology: a multivariate discrete choice model

Abstract: The objective of this research is to understand the demand for information technology among trucking companies. A multivariate discrete choice model is estimated on data from a large-scale survey of the trucking industry in California. This model is designed to identify the influences of each of twenty operational characteristics on the propensity to adopt each of seven different information technologies, while simultaneously allowing the seven error terms to be freely correlated. Results showed that the distinction between for-hire and private fleets is paramount, as is size of the fleet and the provision of intermodal maritime and air services.

Development and adaptation of constructive probabilistic neural network in freeway incident detection

Abstract: This paper investigates the use of constructive probabilistic neural network (CPNN) in freeway incident detection, including model development and adaptation. The CPNN was structured based on mixture Gaussian model and trained by a dynamic decay adjustment algorithm. The model was first trained and evaluated on a simulated incident database in Singapore. The adaptation of CPNN on the I-880 freeway in California was then investigated in both on-line and off-line environments. This paper also compares the performance of the CPNN model with a basic probabilistic neural network (BPNN) model. The results show that CPNN has three main advantages over BPNN: (1) CPNN has clustering ability and therefore could achieve similarly good incident-detection performance with a much smaller network size; (2) each Gaussian component in CPNN has its own smoothing parameter that can be obtained by the dynamic decay adjustment algorithm with a few epochs of training; and (3) the CPNN adaptation methods have the ability to prune obsolete Gaussian components and therefore the size of the network is always within control. CPNN has shown to have better application potentials than BPNN in this research.

Evaluation of ramp control algorithms using microscopic traffic simulation

Abstract: Ramp metering has emerged as an effective freeway control measure to ensure efficient freeway operations. A number of algorithms have been developed in recent years to ensure an effective use of ramp metering. As the performance of ramp metering depends on various factors (e.g. traffic volume, downstream traffic conditions, queue override policy etc), these algorithms should be evaluated under a wide range of traffic conditions to check their applicability and performance and to ensure their successful implementation. In view of the expenses of and confounding effects in field testing, simulation plays an important role in the evaluation of such algorithms. This paper presents an evaluation study of two ramp metering algorithms: ALINEA and FLOW. ALINEA is a local control algorithm and FLOW is an area wide coordinated algorithm. The purpose of the study is to use microscopic simulation to evaluate systematically how the level of traffic demand, queue spillback handling policy and downstream bottleneck conditions affect the performance of the algorithms. It is believed that these variables have complex interactions with ramp metering. MITSIM microscopic traffic simulator is used to perform the empirical study. The study consists of two stages. In the first stage, key input parameters for the algorithms were identified and calibrated. The calibrated parameters were then used for the second stage, where the performance of the algorithms were compared with respect to three traffic variables mentioned above using an orthogonal fraction of experiments. Regression analysis was used to identify the impacts of some of the interactions among experimental factors on the algorithms' performance, which is not otherwise possible with a tabular analysis. These results provide insights which may be helpful for design and calibration of more efficient ramp control algorithms.

Urban road transport navigation: performance of the global positioning system after selective availability

Abstract: Satellite navigation systems have a potential to support multi-modal transport navigation requirements. In road transport, the global positioning system (GPS) is currently supporting a wide variety of in-car navigation and transport telematics systems. The performance of GPS has in the past been limited by the artificial degradation of the signal through the process of selective availability (SA). With SA operational, the instantaneous horizontal positional accuracy was 100 m 95% of the time. Additional infrastructure was used with the differential concept (where range errors are determined at a known location and transmitted to users) to improve this to the level of a few metres. The US Government on 1 May 2000 removed SA. This paper presents the results of a study to assess and characterise the post-SA performance of GPS for positioning vehicles in urban areas. This is an important functionality of advanced transport telematics systems that aim to address everyday problems associated with road transport, particularly in urban areas. The performance assessment addresses, in varying levels of detail, the issues of service coverage, positioning accuracy, integrity and availability of service. Comparison is made with the results of a previous study conducted when SA was turned on. The results show an improvement in stand-alone navigation accuracy without SA compared to the period when SA was operational. Furthermore, no significant difference is seen between the level of accuracy achievable with differential positioning and post-SA stand-alone navigation. The parameters that characterise the performance of GPS determined at the analysis stage have been used to specify an architecture for a local navigation system for urban areas.

A multi-agent architecture for cooperative inter-jurisdictional traffic congestion management

Abstract: This paper describes Cartesius , an innovative multi-agent architecture for the provision of real-time decision support to Traffic Operations Center personnel for coordinated, inter-jurisdictional traffic congestion management on freeway and surface street (arterial) networks. Cartesius is composed of two interacting knowledge-based systems that perform cooperative reasoning and resolve conflicts, for the analysis of non-recurring congestion and the on-line formulation of integrated control plans. The two agents support incident management operations for a freeway and an adjacent arterial subnetwork and interact with human operators, determining control recommendations in response to the occurrence of incidents. The multi-decision maker approach adopted by Cartesius reflects the spatial and administrative organization of traffic management agencies in US cities, providing a cooperative solution that exploits the agencies’ willingness to cooperate and unify their problem-solving capabilities, yet preserves the different levels of authority and the inherent distribution of data and expertise. The interaction between the agents is based on the functionally accurate, cooperative paradigm, a distributed problem solving approach aimed at producing consistent solutions without requiring the agents to have shared access to all globally available information. The cornerstone of this approach is the assumption that effective solutions can be efficiently obtained even when complete and up-to-date information is not directly available to the agents, thus reducing the need for complex data communication networks and synchronization time delays. The simulation-based evaluation of the system performance validates this assumption. The paper focuses on the distributed architecture of the agents and on their communication and decision making characteristics.

Coordination of traffic management instruments using agent technology

Abstract: The objective of this paper is to prove by example the opportunities for cooperation between dynamic traffic management instruments. Agent technology is presented as a useful way to support the deployment of these ideas. In the Netherlands, more and more instruments are installed to promote the flow of traffic. As more and more instruments are deployed, chances are that conflicts will arise when control tools are applied in the same area. The increase in the number of the deployed instruments implies a bigger responsibility for the Dutch Traffic operators, who will have to ascertain which control scenarios are relevant to the situation at hand and implement them. By modeling the separate instruments as intelligent agents, it might be possible to tune the actions of the individual instruments through the agent concept of collaboration. Letting the individual instruments handle the most basic forms of coordination automatically might also relieve the traffic operator. This paper will demonstrate the aforementioned ideas using two simple examples: one in which consecutive ramp metering installations coordinate their actions to promote the flow at a downstream bottleneck and one in which traffic management instruments coordinate their actions to attain a common goal on the network-level.

Intelligent agents in traffic and transportation

Abstract: Transportation Research, Part C is a forum designed to serve as a focus for new efforts and achievements in traffic research. While its past issues have been a fertile ground for new scientific concepts and paradigms it is the appropriate international scientific platform to recognize the importance of agent technologies for the traffic research community. Thus I am very glad to follow Leighton Chipperfield’s (Social Science Department of Elsevier Science, Oxford, UK) invitation to be the guest editor for this special issue of Transportation Research, Part C.

Optimization of mainline traffic via an adaptive co-ordinated ramp-metering control model with dynamic OD estimation

Abstract: Frequently implemented at freeway accesses to streamline traffic, ramp-metering control strategy is often implemented during rush hours in heavily congested areas. This paper presents a novel ramp-metering control model capable of optimizing mainline traffic by providing metering rates for accesses within the control segments. Based on Payne's continuum traffic stream model, a linear dynamic model with a quadratic objective function is constructed for integrated-responsive ramp-metering control. Incorporating on-line origin–destination (OD) estimation of co-ordinated interchanges into the proposed model increases efficiency of the control. In addition, an iterative algorithm is proposed to obtain the optimal solution. Simulation results demonstrate the robustness of the proposed model and its ability to streamline freeway traffic while avoiding traffic congestion.

A new methodology for evaluating incident detection algorithms

Abstract: We present a novel, off-line approach for evaluating incident detection algorithms. Previous evaluations have focused on determining the detection rate versus false alarm rate curve––a process which we argue is inherently fraught with difficulties. Instead, we propose a cost-benefit analysis where cost mimics the real costs of implementing the algorithm and benefit is in terms of reduction in congestion. We argue that these quantities are of more practical interest than the traditional rates. Moreover, these costs, estimated on training data, can be used both as a mechanism to fine tune a single algorithm as well as a meaningful quantity for direct comparisons between different types of incident detection algorithms. We demonstrate our approach with a detailed example.

Instrumented city database analysts using multi-agents

Abstract: The Instrumented City (iC) database is a multi-purpose, transport-related database facility for use by the entire academic transport research community. Data from the UK Leicester City Council and Nottinghamshire County Council Traffic Management Computers is logged and archived on a continuous basis, by the Leeds University’s Institute for Transport Studies. Since its inception in 1992, the iC database has been used for various real-time applications such as air quality and noise monitoring, modelling and forecasting. This paper describes the framework that demonstrates the feasibility of using multi-agents as information analysts to process and manage the iC database. The agents are adaptive, interactive and personal. They can be trained via the interactions with the users to be personalised for individual preferences. These agents are designed to be responsible for (1) data clean-up to remove outliers; (2) missing data substitutions; (3) statistical data analysis; (4) data mining to enhance the understanding of the relationships between traffic and air quality, noise and health; and (5) knowledge discovery by identifying unknown but potentially important patterns.