Josefa Z. Hernández

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.

Knowledge-based models for emergency management systems

Abstract This paper proposes the use of advanced knowledge models to support environmental emergency management as an adequate response to the current needs and technology. A generic architecture embodying the knowledge pieces required to manage emergencies in different kinds of problem scenarios is described. Simulation models of the physical system, integrated as part of the knowledge architecture, are also claimed to be adequate, both from the point of view of the knowledge model calibration and the training of the emergency personnel as well. The feasibility of the approach has been demonstrated with the application of the generic model to a particular real world problem: the management of flood emergencies in the Jucar river basin area (Spain). This work was developed in the framework of ARTEMIS, a European Commission research project.

KNOWLEDGE-BASED MODELS FOR ADAPTIVE TRAFFIC MANAGEMENT SYSTEMS

Abstract This paper describes a general approach for real time traffic management support using knowledge based models. Recognizing that human intervention is usually required to apply the current automatic traffic control systems, it is argued that there is a need for an additional intelligent layer to help operators to understand traffic problems and to make the best choice of strategic control actions that modify the assumption framework of the existing systems. The need for an open architecture is stated, in order to allow users to modify decision criteria according to their experience, given that no skills are available yet to deal with real time strategy decision making. An architecture of knowledge is described that is oriented towards traffic management strategic advice applied in the TRYS system developed by the authors. This system has been installed for urban motorway control in several Spanish cities. Finally, an example of knowledge-based modeling, using TRYS, is presented in a case study where both the TRYS model and its operation are described. It is concluded that such an approach is feasible, and is compatible with existing state of the art traffic control systems.

MULTI-AGENT SYSTEMS FOR DECISION SUPPORT: A CASE STUDY IN THE TRANSPORTATION MANAGEMENT DOMAIN

This article describes how agent and knowledge technology can be used to build advanced software systems that support operational decision making in complex domains. In particular, we present an abstract architecture and design guidelines for agent-based decision support systems. We illustrate our approach with a case study in the transportation management domain.

Using AI techniques to support advanced interaction capabilities in a virtual assistant for e-commerce

Abstract This paper presents our work in the ADVICE (IST-1999-11305, Information Societies Technology Programme, V Framework Programme of the European Commission) project, an on-going European Commission research project of the IST Programme. The overall objective of this project is to design and implement an advice-giving system for E-commerce, supporting a move from the current catalogue-based customer services to a customer adapted intelligent assistance, emulating in some way the performance of a human seller. With this aim, the main elements of the ADVICE approach include an agent-based architecture with an Interface Agent to manage the multimedia presentation, the Interaction Agent to support an advanced user–system interaction and the Intelligent Agent incorporating a knowledge-based model of the e-business for the pilot domain, that supports the reasoning for advise-giving according with the user needs and the dialogue evolution.

On multiagent co-ordination architectures: a traffic management case study

Reports our experiences with agent-based architectures for intelligent traffic management. We describe and compare TRYS and TRYSA/sub 2/, two multi-agent systems that perform decision support for real-time traffic management in the urban motorway network around Barcelona. Both systems draw upon similar traffic management knowledge, but the former is based on a centralised architecture, while in the latter, co-ordination emerges upon the lateral interaction of autonomous traffic management agents. We conclude that the centralised approach applied by TRYS promotes efficiency for real-time operation, whereas the decentralised approach used in TRYSA/sub 2/ promotes scalability.

REFLECTIVE KNOWLEDGE MODELS TO SUPPORT AN ADVANCED HCI FOR DECISION MANAGEMENT

Abstract In the previous years, the evolution of the telematics technology has introduced a new scenario of human–computer operation where the achievement of an adequate level of user–system interaction has become a key aspect. This issue is specially relevant in real-time management scenarios where the system is intended to provide an intelligent support to human operators in the decision-making task. This paper proposes the use of advanced knowledge-based models to support human–computer interaction in the context of real-time decision for management problems. The approach is mainly based on endowing intelligent systems with an introspection capability that makes possible an adaptive performance to the characteristics of the interaction. This capability is supported by a reflective architecture where a metalevel layer dynamically configures reasoning strategies to generate the required answers by looking into a structured collection of problem-solving components. The approach was developed and applied within the FLUIDS project, an European Commission Telematics Applications research project. The proposal is illustrated with an example in the domain of real-time private traffic management in the city of Turin.

Towards Smart Open Dynamic Fleets

Nowadays, vehicles of modern fleets are endowed with advanced devices that allow the operators of a control center to have global knowledge about fleet status, including existing incidents. Fleet management systems support real-time decision making at the control center so as to maximize fleet performance. In this paper, setting out from our experience in dynamic coordination of fleet management systems, we focus on fleets that are open, dynamic and highly autonomous. Furthermore, we propose how to cope with the scalability problem as the number of vehicles grows. We present our proposed architecture for open fleet management systems and use the case of taxi services as example of our proposal.

An Intelligent Model for Road Traffic Management in the Motorway Network Around Barcelona

This paper presents an advanced knowledge-based environment to develop real time traffic management applications called TRYS. The building process supported by the architecture is guided by the progressive definition of knowledge features from the knowledge level to the symbolic level. Firstly, the problem is presented showing the shortcomings perceived in the state of the art of traffic management systems. Secondly, a description of the KSM tool, aimed at supporting the organization of structured models at the knowledge level is commented. Thirdly, the generic model, intended to deal with traffic management, is described using the KSM format. Finally, the domain model of the application developed for Barcelona is described.

Designing Multiagent Decision Support Systems for Traffic Management

Modern Decision Support Systems (DSS) not only store large amounts of decision-relevant data, but also aim at assisting decision-makers in exploring the meaning of that data, so as to take decisions based on understanding. To this end, a distributed approach to the construction of DSS has become popular: decision-support agents are responsible for parts of the decision-making process in a (semi-)autonomous (individually) rational fashion. However, despite the advances in the field of agent-oriented software engineering, a principled approach to the design of multiagent systems for decision support is still to come.