Transportation Research Part C: Emerging Technologies
Multiagent architectures for intelligent traffic management systems
Introduction
The notion of software agents has become increasingly popular over the last couple of years. Public entities as well as private companies spend a considerable amount of time, effort and money in research development and promotion of the idea of software agents. To some respect this is surprising, as software agents essentially do what one expects a reasonable advanced computer program: it is embedded in an environment in which it is capable of achieving certain tasks with some degree of autonomy, i.e. without constant human guidance or intervention.
Still, the real potential of this technology becomes unleashed when several software agents are put to use in the same environment. In this case, the group of agents is usually conceived as a multiagent system, as the successful completion of their tasks is subject to the decisions and actions of other agents. So, in multiagent systems, agents are forced to coordinate their activities so as to avoid negative interactions with their acquaintances and to exploit synergic potentials. Initially, most distributed problem-solving systems were based on a distinguished agent, which achieved the coordination of the activities of its acquaintances in a centralized fashion (Steeb et al., 1988; Von Martial, 1992). More recently, the focus has shifted to more autonomous agents that coordinate in a decentralized fashion (Ephrati et al., 1995; Decker and Lesser, 1998).
An important reason for the growing success of multiagent technology is its potential to cope with high complexity problems that show an a priori distribution (Ossowski, 1999). From the technical point of view, the inherent distribution allows for a natural decomposition of the system into agents that interact so as to achieve a desired global functionality. By this, reusability is promoted, not just by the agents’ modularity, but also based on their autonomy. In addition, the scalability of systems operating in highly complex domains can be improved by choosing among specific coordination models that harmonize agent activities with respect to the multiagent system’s task. Through an adequate design of coordination mechanisms for a particular problem, it is believed that, from an economic point of view, multiagent systems may tackle complex problem with an acceptable degree of performance, but at a lower cost than traditional solutions.
Multiagent systems have been applied successfully to a variety of industrial problems (Chaib-Draa, 1998), from electronic commerce (Guttman et al., 1998; Foss, 1998) through energy management (Jennings, 1994; Correra et al., 1994), to road transportation related applications such as parking guidance tools or transportation scheduling systems (Fischer et al., 1996). So, it is natural to ask whether this promising new technology is capable of coping efficiently with advanced road traffic management scenarios. In the end, traffic management problems are intrinsically distributed, and suffer from a high degree of complexity that is constantly increasing in line with the incessant improvements of traffic control infrastructures.
This article reports our research and experiences in this respect: it analyzes how multiagent architectures can be applied to the problem of strategic road traffic management. Section 2 discusses the role of knowledge-based artificial intelligence techniques for traffic management. It argues in favor of the concept of intelligent traffic management systems (ITMS) as a means of integrating the increasingly complex and heterogeneous traffic control infrastructure and providing a means of strategic support for traffic management. Section 3 shows how knowledge-based ITMS for real-world traffic management problems can be instrumented in a computationally and economically efficient way by means of multiagent architectures. Two ITMS aimed at the management of the Barcelona freeway system, and based on different multiagent architectures, are described and compared. Finally, in Section 4, the potentials and drawbacks of both systems are analyzed in order to come up with a set of conclusions respecting the applicability of multiagent technology to the ITMS domain.
Section snippets
ITMS: coupling traffic management and knowledge modeling
In recent years, the evolution of the telematics infrastructure and technology has significantly increased the management possibilities of the traditional traffic control centers (TCCs). Whereas in urban control the focus still lies on traffic light control, the control options in urban and interurban motorways are manifold. Besides the different possibilities for direct control on motorways, indicated by Fig. 1, a variety of indirect control measures can be applied:
- •
Recommendations for the
The TRYS intelligent traffic management systems family
This section describes the applications of multiagent architectures to knowledge-based ITMS. In the first place, the TRYS traffic management generic architecture is outlined. Subsequently, the knowledge-based reasoning model of TRYS traffic management agents is outlined. Finally, in Section 3.3, the different multiagent coordination architectures of two real-world ITMS applications are discussed and illustrated by an example.
Conclusions
In our view, from the work reported here, as well as in the several EU and US research initiatives previously mentioned, the use of artificial intelligence techniques to develop traffic management systems provides a clear added value to conventional systems. From the users point of view, the ITMS may be seen as an intelligent assistant capable to provide useful information for the decision making activity. This utility mostly relies on the fact that ITMS share a common language with the users,
Acknowledgements
The work reported in this article is largely based upon the close work of the authors with Professor José Cuena (1999), from the Technical University of Madrid, who was a main inspirator and provided the conceptual and scientific foundations of these systems and models. None of the results and achievements presented would have been possible without his continuous contributions, precious suggestions, strong and friendly support and enthusiasm. This work is dedicated to his memory.
References (50)
- et al.
Knowledge-based models for adaptive traffic management systems
Transportation Research, Part C
(1995) - et al.(1994)
- Barceló, J., Casas, J., Ferrer, J.L., Garcı́a, D., 1998. Modelling advanced transport telematic applications with...
- Behrendt, Riegelhuth, Stern, 1997. The ENTERPRICE Project––A step towards information and mobility management. In:...
- Boero, M., Kirschfink, H., Barceló, J., 1997. Real-time traffic management supporting intermobility and strategic...
- Bolelli, Leighton, Morello, 1994. A top–down approach to open European IRTE architecture: requirements, development...
- Bretherton, Bowen, 1990. Recent enhancements to SCOOT––SCOOT version 2.4. In: Proc. 3rd Int. Conf. on Road Traffic...
- Chaib-Draa, B., 1998. Industrial applications of distributed AI. In: Huhns and Singh,...
KSM: an environment for design of structured models
Knowledge oriented design of an application for real time traffic management: The TRYS system
An intelligent model of road traffic management in the motorway network around Barcelona
Advanced user interfaces for decision support in real time transport management
Deriving multi-agent co-ordination through filtering strategies
Cooperative transportation scheduling: an application domain for DAI
Special Issue on Intelligent Agents
Journal of Applied Artificial Intelligence
Cited by (126)
Adaptive traffic signal control for developing countries using fused parameters derived from crowd-source data
2023, Transportation LettersAI enabled applications towards intelligent transportation
2021, Transportation EngineeringCitation Excerpt :In this study, an agent-based control system monitors traffic, road incidents and other transportation activities. The article [22] compares two integrated autonomous agents deployed for intelligent traffic management systems that perform decision support for real-time traffic management around Barcelona. The study [51] investigates the applicability of autonomous intelligent agents in urban traffic control (UTC).
Optimization of the cost of urban traffic through an online bidding platform for commuters
2021, Economics of TransportationA survey on clustering methods for distributed and networked control systems
2021, Annual Reviews in ControlCitation Excerpt :The sheer size and possible geographical dispersion of large-scale systems (Kordestani, Safavi, & Saif, 2021; Scattolini, 2009), such as smart grids (Qi, Liu, & Christofides, 2011), water networks (Negenborn, van Overloop, Keviczky, & De Schutter, 2009), traffic systems (Hernández, Ossowski, & Garcıa-Serrano, 2002), and intelligent buildings (Scherer, Pasamontes, Guzmán, Álvarez, Camponogara, & Normey-Rico, 2014), causes the implementation of centralized strategies to demand strong computational and communication resources. In contrast to the centralized approach, where a single controller has full decision-making power and complete knowledge of the system, distributed strategies rely on a decentralization of the overall problem where, typically, a set of local controllers, also referred to as agents, manage the different systems partitions or subsystems (Hernández et al., 2002; Negenborn et al., 2009; Qi et al., 2011; Scherer et al., 2014), thus providing the overall control architecture higher scalability and redundancy at the expense of a more sophisticated design. In this setting, global performance is highly influenced by the extent to which communication and coordination among agents is considered (Rawlings & Stewart, 2008; Zheng, Li, Li, & Ren, 2017).
Prediction based traffic management in a metropolitan area
2020, Journal of Traffic and Transportation Engineering (English Edition)Multi-agent immune networks to control interrupted flow at signalized intersections
2017, Transportation Research Part C: Emerging Technologies