Abstract: Crisis Management Systems are evolving from human organizations making use of information systems towards three-layered networks of human actors, artificial agents and traditional information systems. In order to understand the qualities of such complex “COMBINED” systems a joint effort of the sciences of human and artificial systems is required. To ensure practical results, research efforts should anticipate engineering efforts by providing architectural mechanisms and patterns associated with the qualities and capabilities of Combined Systems as a whole. © Proceedings ISCRAM 2004.

Abstract: This paper presents an intelligent system facilitating better-informed decision making under severe uncertainty as found in emergency management. The construction of decision-relevant scenarios, being coherent and plausible descriptions of a situation and its future development, is used as a rationale for collecting, organizing, filtering and processing information for decision making. The development of scenarios is geared to assessing decision alternatives, thus avoiding time-consuming analysis and processing of irrelevant information. The scenarios are constructed in a distributed setting allowing for a flexible adaptation of reasoning (principles and processes) to the problem at hand and the information available. This approach ensures that each decision can be founded on a coherent set of scenarios, which was constructed using the best expertise available within a limited timeframe. Our theoretical framework is demonstrated in a distributed decision support system by orchestrating both automated systems and human experts into workflows tailored to each specific problem.

Abstract: The first hours after a disaster are essential to minimizing the loss of life. The chance for survival in the debris of a collapsed building for example decreases considerably after 72 hours. However the available information in the first hours after a disaster is limited, uncertain and dynamically changing. A goal in the development of the Disaster Management Tool (DMT) was to support the management of this situation. Its module DMT-EOC specifically deals with problems of the members in an emergency operation centre (EOC) by providing a training environment for computer based table top exercises and assistance during earthquake disasters. The system is based on a flexible and extendible architecture that integrates different concepts and programming interfaces. It contains a simulation for training exercises and the evaluation of decisions during disaster response. A decision support implemented as a multi-agent system (MAS) combines operation research approaches and rule-base evaluation for advice giving and criticising user decisions. The user interface is based on a workflow model which mixes naturalistic with analytic decision-making. The paper gives an overview of the models behind the system components, describes their implementation, and the testing of the resulting system.

Abstract: Natural and human-made disasters create unparalleled challenges to Disaster Situation Management (DSM). One of the major weaknesses of the current DSM solutions is the lack of comprehensive understanding of the overall disaster operational situation, and very often making decisions based on a single event. Such weakness is clearly exhibited by the solutions based on the widely used Belief-Desire-Intention (BDI) models for building the Muiti-Agent Systems (MAS). In this work we present the adaptation of the AESOP situation management architecture to address the requirements of disaster relief operations. In particular, we extend the existing BDI model with the capability of situation awareness. We describe how the key functions of event collection, situation identification, and situation assessment are implemented in MAS architecture suitable to the characteristics of large-scale disaster recovery. We present the details of a BDI agent in this architecture including a skeleton ontology, and the distributed service architecture of the AESOP platform.

Abstract: Situation assessment in crisis management applications can be supported by automated information fusion systems, such as Distributed Perception Networks. DPNs are self-organizing fusion systems that can infer hidden events through interpretation of huge amounts of heterogeneous and noisy observations. DPNs are a logical layer on top of existing communication, sensing, processing and data storage infrastructure. They can reliably and efficiently process information of various quality obtained from humans and sensors through the existing communication systems, such as mobile phone networks or internet. In addition, modularity of DPNs supports efficient design and maintenance of very complex fusion systems. In this paper, a fully functional prototype of a DPN system is presented that fuses information from gas sensors and human observations. The task of the system is to compute probability values for the hypothesis that a particular gas is present in the environment. It is discussed how such a system could be used for crisis management.

Abstract: The need to gather and use decentralized information and resources in responding to disasters demands an integrated interface that can support large-scale collaboration. This paper describes the development of a collaboration tool interface. The tool will surpass existing groupware and social networking applications, providing easy entry, categorization, and visualization of masses of critical data; the ability to form ad-hoc teams with collaboration protocols for negotiated action; and agent-augmented mixed-initiative tracking and coordination of these activities. The paper reports user testing results concerning the data entry interface, emergent leadership, and the directed negotiation process. The paper also discusses planned enhancements, including formalized collaboration engineering and the use of a disaster simulation test bed.

Abstract: This article presents a social approach for disaster management, based on a social portal, so-called Disasters2.0, which provides facilities for integrating and sharing user generated information about disasters. The architecture of Disasters2.0 is designed following REST principles and integrates external mashups, such as Google Maps. This architecture has been consumed with different clients, including a mobile client, a multiagent system for assisting in the decentralized management of disasters, and an expert system for automatic assignment of resources to disasters. As a result, the platform allows seamless collaboration of humans and intelligent agents, and provides a novel web2.0 approach for multiagent and disaster management research.

Abstract: Modern safety-critical organizations are characterized by complex, nonlinear dynamics involving many interrelated actors and processes. Safety issues that emerge from these complex dynamics increasingly remain hidden, until an incident or even a serious accident occurs. Traditional safety analysis methods developed long ago for much simpler organizations cannot help identifying, explaining and predicting many safety-related properties of modern organizations. To address this issue, in the paper a formal approach is proposed to establish relations between local dynamics of actors of a complex safety-critical organization and global safetyrelated properties that emerge from these dynamics. In contrast to the traditional approaches, the organizational dynamics are specified by taking the agent perspective with an organizational layer. The application of the approach is illustrated by a simulation case study, in which spread of safety-critical information in an air navigation service provider is investigated. © 2012 ISCRAM.

Abstract: Combined Systems is aimed at exploring distributed decision support systems in open, complex chaotic environments. On a general scale, Combined is all about decision-making: observing the environment, making decisions and effectuating these to manage the current situation. Crisis management is a typical domain in which Combined-type systems can prove their value. For this reason the Combined project uses crisis management as primary case-domain. In this paper we highlight the key technologies that are subject of the Combined research, and we describe them in the light of crisis management. © Proceedings ISCRAM 2004.

Abstract: Results from disaster research suggest that methods for coordination between individual emergency responders and organizations should recognize the independence and autonomy of these actors. These actor features are key factors in effective adaptation and improvisation of response to emergency situations which are inherently uncertain. Autonomy and adaptability are also well-known aspects of a multi-agent system (MAS). In this paper we present two MAS strategies that can effectively handle aircraft deicing incidents. These MAS strategies help improve to prevent and reduce e.g. airplane delays at deicing stations due to changing weather conditions or incidents at the station, where aircraft agents adopting pre-made plans that would act on behalf of aircraft pilots or companies, would only create havoc. Herein each agent using its own decision mechanism deliberates about the uncertainty in the problem domain and the preferences (or priorities) of the agents. Furthermore, taking both these issues into account each proposed MAS strategy outperforms a naive first-come, first-served coordination strategy. The simulation results help pilots and companies taking decisions with respect to the scheduling of the aircraft for deicing when unexpected incidents occur: they provide insights in the impacts and means for robust selection of incident-specific strategies on e.g. deicing station delays of (individual) aircraft.