Multiagent architectures for intelligent traffic management systems

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.     

Multi-agent model predictive control of signaling split in urban traffic networks

The operation of large dynamic systems such as urban traffic networks remains a challenge in control engineering to a great extent due to their sheer size, intrinsic complexity, and nonlinear behavior. Recently, control engineers have looked for unconventional means for modeling and control of complex dynamic systems, in particular the technology of multi-agent systems whose appeal stems from their composite nature, flexibility, and scalability. This paper contributes to this evolving technology by proposing a framework for multi-agent control of linear dynamic systems, which decomposes a centralized model predictive control problem into a network of coupled, but small sub-problems that are solved by the distributed agents. Theoretical results ensure convergence of the distributed iterations to a globally optimal solution. The framework is applied to the signaling split control of traffic networks. Experiments conducted with simulation software indicate that the multi-agent framework attains performance comparable to conventional control. The main advantages of the multi-agent framework are its graceful extension and localized reconfiguration, which require adjustments only in the control strategies of the agents in the vicinity.     

Multi-agent fuzzy signal control based on real-time simulation

In this paper a traffic signal control system based on real-time simulation, multi-agent control scheme, and fuzzy inference is presented. This system called HUTSIG is closely related to the microscopic traffic simulator HUTSIM, both have been developed by the Helsinki University of Technology. The HUTSIM simulation model is used both for off-line evaluation of the signal control scheme and for on-line modeling of traffic situations during actual control. Indicators are derived from the simulation model as input to the control scheme. In the presented control technique, each signal operates individually as an agent, negotiating with other signals about the control strategy. Here the decision making of the agents is based on fuzzy inference that allows a combination of various aspects like fluency, economy, environment and safety. The fuzzy implementation of the HUTSIG signal control system is developed under the FUSICO-project at Helsinki University of Technology.     

Using BDI agents to improve driver modelling in a commuter scenario

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.     

Using intelligent agents for Transportation Regulation Support System design

This paper presents an agent-based approach used to design a Transportation Regulation Support System (TRSS), that reports the network activity in real-time and thus assists the bus network regulators. The objective is to combine the functionalities of the existing information system with the functionalities of a decision support system in order to propose a generic model of a traffic regulation support system. Unlike the other approaches that only deal with a specific task, the original feature of our generic model is that it proposes a global approach to the regulation function under normal conditions (network monitoring, dynamic timetable management) and under disrupted conditions (disturbance assessment and action planning of feasible solutions). Following the introduction, the second section presents the notions of the domain and highlights the main regulation problems. The third section details and motivates our choice of the components of the generic model. Based on our generic model, in the fourth section, we present a TRSS prototype called SATIR (Système Automatique de Traitement des Incidents en Réseau – Automatic System for Network Incident Processing) that we have developed. SATIR has been tested on the Brussels transportation network (STIB). The results are presented in the fifth section. Lastly, we show how using the multi-agent paradigm opens perspectives regarding the development of new functionalities to improve the management of a bus network.     

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

This paper describes , 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. 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 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.     

Can agents measure up? A comparative study of an agent-based and on-line optimization approach for a drayage problem with uncertainty

Experiments studying the behavior of agent-based methods over varying levels of uncertainty in comparison to traditional optimization methods are generally absent from the literature. In this paper we apply two structurally distinct solution approaches, an on-line optimization and an agent-based approach, to a drayage problem with time windows under two types of uncertainty. Both solution approaches are able to respond to dynamic events. The on-line optimization approach utilizes a mixed integer program to obtain a feasible route at 30-s intervals. The second solution approach deploys agents that engage in auctions to satisfy their own objectives based on the information they perceive and maintain locally. Our results reveal that the agent-based system can outperform the on-line optimization when service time duration is highly uncertain. The on-line optimization approach, on the other hand, performs competitively with the agent-based system under conditions of job-arrival uncertainty. When both moderate service time and job-arrival uncertainties are combined, the agent system outperforms the on-line optimization; however, in the case of extremely high combined uncertainty, the on-line optimization outperforms the agent-based approach.     

A dynamic cordon pricing scheme combining the Macroscopic Fundamental Diagram and an agent-based traffic model

Pricing is considered an effective management policy to reduce traffic congestion in transportation networks. In this paper we combine a macroscopic model of traffic congestion in urban networks with an agent-based simulator to study congestion pricing schemes. The macroscopic model, which has been tested with real data in previous studies, represents an accurate and robust approach to model the dynamics of congestion. The agent-based simulator can reproduce the complexity of travel behavior in terms of travelers’ choices and heterogeneity. This integrated approach is superior to traditional pricing schemes. On one hand, traffic simulators (including car-following, lane-changing and route choice models) consider travel behavior, i.e. departure time choice, inelastic to the level of congestion. On the other hand, most congestion pricing models utilize supply models insensitive to demand fluctuations and non-stationary conditions. This is not consistent with the physics of traffic and the dynamics of congestion. Furthermore, works that integrate the above features in pricing models are assuming deterministic and homogeneous population characteristics. In this paper, we first demonstrate by case studies in Zurich urban road network, that the output of a agent-based simulator is consistent with the physics of traffic flow dynamics, as defined by a Macroscopic Fundamental Diagram (MFD). We then develop and apply a dynamic cordon-based congestion pricing scheme, in which tolls are controlled by an MFD. And we investigate the effectiveness of the proposed pricing scheme. Results show that by applying such a congestion pricing, (i) the savings of travel time at both aggregated and disaggregated level outweigh the costs of tolling, (ii) the congestion inside the cordon area is eased while no extra congestion is generated in the neighbor area outside the cordon, (iii) tolling has stronger impact on leisure-related activities than on work-related activities, as fewer agents who perform work-related activities changed their time plans. Future work can apply the same methodology to other network-based pricing schemes, such as area-based or distance-traveled-based pricing. Equity issues can be investigated more carefully, if provided with data such as income of agents. Value-of-time-dependent pricing schemes then can also be determined.     

Multi-agent simulation of individual mobility behavior in carpooling

Carpooling is an emerging alternative transportation mode that is eco-friendly and sustainable as it enables commuters to save time, travel resource, reduce emission and traffic congestion. The procedure of carpooling consists of a number of steps namely; (i) create a motive to carpool, (ii) communicate this motive with other agents, (iii) negotiate a plan with the interested agents, (iv) execute the agreed plans, and (v) provide a feedback to all concerned agents. In this paper, we present a conceptual design of an agent-based model (ABM) for the carpooling a that serves as a proof of concept. Our model for the carpooling application is a computational model that is used for simulating the interactions of autonomous agents and to analyze the effects of change in factors related to the infrastructure, behavior and cost. In our carpooling application, we use agent profiles and social networks to initiate our agent communication model and then employ a route matching algorithm, and a utility function to trigger the negotiation process between agents. We developed a prototype of our agent-based carpooling application based on the work presented in this paper and carried out a validation study of our results with real data collected in Flanders, Belgium.     

Coordination of traffic management instruments using agent technology

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.     

A systems approach to area traffic control

Since the first pilot scheme for area‐traffic control was introduced in the city of Montreal (1959–60), computer control of traffic in urban areas through the adaptation of existing traffic‐signal systems has been provided to an increasing extent. This area of work may pose problems for the professional traffic engineer whose background in computer technology and general digital electronics may be limited.

In considering the engineering implications of such schemes a systems approach is important and is adopted here. Three existing and representative schemes are briefly mentioned in order to outline basic features. A more detailed examination of the various system elements follows with mention of data collection and transmission, and the role of the control computer.

The paper continues with a reconsideration of the three representative schemes in the light of the detailed treatment of system components. It concludes with a tentative assessment of the present position of area traffic control schemes and some suggestions as to the future development.     

Modeling the effect of electric vehicle adoption on pedestrian traffic safety: An agent-based approach

When operated at low speeds, electric and hybrid vehicles have created pedestrian safety concerns in congested areas of various city centers, because these vehicles have relatively silent engines compared to those of internal combustion engine vehicles, resulting in safety issues for pedestrians and cyclists due to the lack of engine noise to warn them of an oncoming electric or hybrid vehicle. However, the driver behavior characteristics have also been considered in many studies, and the high end-prices of electric vehicles indicate that electric vehicle drivers tend to have a higher prosperity index and are more likely to receive a better education, making them more alert while driving and more likely to obey traffic rules. In this paper, the positive and negative factors associated with electric vehicle adoption and the subsequent effects on pedestrian traffic safety are investigated using an agent-based modeling approach, in which a traffic micro-simulation of a real intersection is simulated in 3D using AnyLogic software. First, the interacting agents and dynamic parameters are defined in the agent-based model. Next, a 3D intersection environment is created to integrate the agent-based model into a visual simulation, where the simulation records the number of near-crashes occurring in certain pedestrian crossings throughout the virtual time duration of a year. A sensitivity analysis is also carried out with 9000 subsequent simulations performed in a supercomputer to account for the variation in dynamic parameters (ambient sound level, vehicle sound level, and ambient illumination). According to the analysis, electric vehicles have a 30% higher pedestrian traffic safety risk than internal combustion engine vehicles under high ambient sound levels. At low ambient sound levels, however, electric vehicles have only a 10% higher safety risk for pedestrians. Low levels of ambient illumination also increase the number of pedestrians involved in near-crashes for both electric vehicles and combustion engine vehicles.     

Multi-step prediction of experienced travel times using agent-based modeling

This paper develops an agent-based modeling approach to predict multi-step ahead experienced travel times using real-time and historical spatiotemporal traffic data. At the microscopic level, each agent represents an expert in a decision-making system. Each expert predicts the travel time for each time interval according to experiences from a historical dataset. A set of agent interactions is developed to preserve agents that correspond to traffic patterns similar to the real-time measurements and replace invalid agents or agents associated with negligible weights with new agents. Consequently, the aggregation of each agent’s recommendation (predicted travel time with associated weight) provides a macroscopic level of output, namely the predicted travel time distribution. Probe vehicle data from a 95-mile freeway stretch along I-64 and I-264 are used to test different predictors. The results show that the agent-based modeling approach produces the least prediction error compared to other state-of-the-practice and state-of-the-art methods (instantaneous travel time, historical average and k-nearest neighbor), and maintains less than a 9% prediction error for trip departures up to 60 min into the future for a two-hour trip. Moreover, the confidence boundaries of the predicted travel times demonstrate that the proposed approach also provides high accuracy in predicting travel time confidence intervals. Finally, the proposed approach does not require offline training thus making it easily transferable to other locations and the fast algorithm computation allows the proposed approach to be implemented in real-time applications in Traffic Management Centers.     

Network effects of intelligent speed adaptation systems

Intelligent Speed Adaptation (ISA) systems use in-vehicle electronic devices to enable the speed of vehicles to be regulated automatically. They are increasingly appreciated as a flexible method for speed management and control particularly in urban areas. On-road trials using a small numbers of ISA equipped vehicles have been carried out in Sweden, the Netherlands, Spain and the UK. This paper describes the developments made to enhance a traffic microsimulation model in order to represent ISA implemented across a network and the impact of this on the networks. The simulation modelling of the control system is carried out on a real-world urban network, and the impacts on traffic congestion, speed distribution and the environment assessed. The results show that ISA systems are more effective in less congested traffic conditions. Momentary high speeds in traffic are effectively suppressed, resulting in a reduction in speed variation which is likely to have a beneficial impact on safety. Whilst ISA reduces excessive traffic speeds in the network, it does not affect average journey times. In particular, the total vehicle-hours travelling at speeds below 10 km/hr have not changed, indicating that the speed control had not induced more slow-moving queues to the network. A statistically significant, eight percent, reduction in fuel consumption was found with full ISA penetration. These results are in accordance with those from field trials and they provide the basis for cost-benefit analyses on introducing ISA into the vehicle fleet. However, contrary to earlier findings from the Swedish ISA road trials, this study suggested that ISA is likely to have no significant effect on emission of gaseous pollutants CO, NO_x and HC.     

Time-dependent area-based pricing for multimodal systems with heterogeneous users in an agent-based environment

In this paper, we investigate an area-based pricing scheme for congested multimodal urban networks with the consideration of user heterogeneity. We propose a time-dependent pricing scheme where the tolls are iteratively adjusted through a Proportional–Integral type feedback controller, based on the level of vehicular traffic congestion and traveler’s behavioral adaptation to the cost of pricing. The level of congestion is described at the network level by a Macroscopic Fundamental Diagram, which has been recently applied to develop network-level traffic management strategies. Within this dynamic congestion pricing scheme, we differentiate two groups of users with respect to their value-of-time (which related to income levels). We then integrate incentives, such as improving public transport services or return part of the toll to some users, to motivate mode shift and increase the efficiency of pricing and to attain equitable savings for all users. A case study of a medium size network is carried out using an agent-based simulator. The developed pricing scheme demonstrates high efficiency in congestion reduction. Comparing to pricing schemes that utilize similar control mechanisms in literature which do not treat the adaptivity of users, the proposed pricing scheme shows higher flexibility in toll adjustment and a smooth behavioral stabilization in long-term operation. Significant differences in behavioral responses are found between the two user groups, highlighting the importance of equity treatment in the design of congestion pricing schemes. By integrating incentive programs for public transport using the collected toll revenue, more efficient pricing strategies can be developed where savings in travel time outweigh the cost of pricing, achieving substantial welfare gain.     

Personalized real-time traffic information provision: Agent-based optimization model and solution framework

The advancement of information and communication technology allows the use of more sophisticated information provision strategies for real-time congested traffic management in a congested network. This paper proposes an agent-based optimization modeling framework to provide personalized traffic information for heterogeneous travelers. Based on a space–time network, a time-dependent link flow based integer programming model is first formulated to optimize various information strategies, including elements of where and when to provide the information, to whom the information is given, and what alternative route information should be suggested. The analytical model can be solved efficiently using off-the-shelf commercial solvers for small-scale network. A Lagrangian Relaxation-based heuristic solution approach is developed for medium to large networks via the use of a mesoscopic dynamic traffic simulator.     

Air traffic management: Optimization models and algorithms

Current air traffic control systems are mainly conceived to ensure the safety of flights by means of tactical interventions, because of the difficulty of accurately foreseeing the traffic evolution. In fact, in real traffic conditions, planes are often penalized since sometimes safety standards are redundant. Today, this management philosophy is no longer valid because of congestion phenomena which often occur in the most important terminal areas. Therefore, as to future control systems it is necessary to introduce not only more automated procedures to keep adequate safety levels, but also planning functions in order to increase the system capacity and to improve system efficiency. In recent years several studies have been carried out, new control concepts have been introduced and some optimization models and algorithms developed to improve air traffic management. In this paper a survey of our early works in this field is reported and a multilevel model of air traffic management is proposed and discussed. The functions corresponding to the on-line control, that is flow control, strategic control of flights and aircraft sequencing in a terminal area, are examined and the optimization models and solution algorithms are illustrated. Finally, relevant problems coped by recent research are mentioned and new trends are indicated.     

Behavioral monitoring of public transport users through a mobile communication system

There are various activities now taking place in ITS research and development in Japan. Advanced information and communication technologies have been applied to improve public transport systems, as well as automated highway systems. In the first part of this paper, we show three examples of public transport systems recently developed in ITS environment. These transport systems are operated in local cities and towns in Japan: the travel information system for tram users in Hiroshima, the demand responsive bus system in Nakamura and the co‐operative use of electric vehicle in Ebina. In the second part of the paper, we explain how we have monitored individual passenger on public transport using cellular phones for location positioning. Location positioning technology for mobile object is essential for the operation and management of ITS supported public transport systems. Furthermore, such accurate and detailed positioning data can be utilized for travel behaviour analysis in demand modeling. The mobile instrument and monitoring systems shown in this paper can be combined with any of the case studies of ITS application to public transport systems.     

Integrating mesoscopic dynamic traffic assignment with agent-based travel behavior models for cumulative land development impact analysis

A number of approaches have been developed to evaluate the impact of land development on transportation infrastructure. While traditional approaches are either limited to static modeling of traffic performance or lack a strong travel behavior foundation, today’s advanced computational technology makes it feasible to model an individual traveler’s response to land development. This study integrates dynamic traffic assignment (DTA) with a positive agent-based microsimulation travel behavior model for cumulative land development impact studies. The integrated model not only enhances the behavioral implementation of DTA, but also captures traffic dynamics. It provides an advanced yet practical approach to understanding the impact of a single or series of land development projects on an individual driver’s behavior, as well as the aggregated impacts on the demand pattern and time-dependent traffic conditions. A simulation-based optimization (SBO) approach is proposed for the calibration of the modeling system. The SBO calibration approach enhances the transferability of this integrated model to other study areas. Using a case study that focuses on the cumulative land development impact along a congested corridor in Maryland, various regional and local travel behavior changes are discussed to show the capability of this tool for behavior side estimations and the corresponding traffic impacts.