Skip to main content

Über dieses Buch

Defense and security related applications are increasingly being tackled by researchers and practioners using technologies developed in the field of Intelligent Agent research. This book is a collection of recent refereed papers drawn from workshops and other colloquia held in various venues around the world in the last two years.

The contributions in this book describe work in the development of command and control systems, military communications systems, information systems, surveillance systems, autonomous vehicles, simulators and Human Computer Interactions. The broad nature of the application domain is matched by the diversity of techniques used in the papers that are included in the collection which provides, for the first time, an overview of the most significant work being performed by the leading workers in this area. It provides a single reference point for the state of the art in the field at the moment and will be of interest to Computer Science professionals working in the defense sector, and academics and students investigating the technology of Intelligent Agents that are curious to see how the technology is applied in practice.



Nexus: Self-organising Agent-based Peer-to-Peer Middleware for Battlespace Support

The problem facing the security and defence communities is the volume, complexity and timeliness of information. In particular the ability to locate and access the right ICT service at the right time is crucial to achieving real-time responsiveness and situational awareness. The Nexus system is a Peer-to-Peer (P2P) agent-based middleware that creates a fully distributed and highly resilient Service Oriented Architecture (SOA). The combination of a structured P2P overlay network and autonomous service discovery, delivers a powerful capability to support real-time operations in either security or defence applications. This paper outlines the overall architecture of the Nexus system and its application in a defence scenario with a detailed review of the service selection algorithm utilised, termed Mercury. Mercury provides an autonomous, efficient and distributed service selection framework and collaborative algorithms for SOA construction and real-time adaptation.
Alex Healing, Robert Ghanea-Hercock, Hakan Duman, Michal Jakob

Information-Based Control of Decentralised Sensor Networks

This chapter describes how formal information measures can be used as the basis for enabling decentralised, intelligent and autonomous control of large-scale sensor network resources, with widespread application throughout the military and security domain. These information measures are the result of filtering and fusing local sensor observations, assimilating the products over a communication network, and interpreting them in the wider context to infer underlying states of interest to the military or security operation. Information provides a currency against which a constrained set of sensing and communication actions can be valued, resulting in a single action or sequence of actions being executed. This is known as Information-Based Control (IBC). The main focus of this chapter is the problem of decentralised IBC in a large-scale sensor network, and its solution in terms of multi-agent system methodologies. Examples and applications, relevant to the military world, are used to highlight a number of important practical considerations.
David Nicholson, Sarvapali D. Ramchurn, Alex Rogers

Managing Intelligence Resources Using Semantic Matchmaking and Argumentation

Effective deployment and utilisation of limited and constrained intelligence, surveillance and reconnaissance (ISR) resources is seen as a key issue in modern network-centric joint-forces operations. In this chapter, we examine the application of semantic matchmaking and argumentation technologies to the management of ISR resources in the context of coalition operations. We show how ontologies and reasoning can be used to assign sensors and sources to meet the needs of missions, and we show how argumentation can support the process of gathering and reasoning about uncertain evidence obtained from various sources.
Alun Preece, Tomothy J. Norman, Mario Gomez, Nir Oren

Agent Applications in Defense Logistics

During World War II, US Military logistics was the envy of the world. By Desert Storm / Desert Shield, overwhelming mass had become the supply strategy of the day. In the years following Desert Storm, the military set out to reinvent its logistics strategy through Focused Logistics and the Defense Advanced Research Projects Agency (DARPA) was charged with developing the next generation information technology to make it a reality. This chapter reviews the vision, concepts and technologies of DARPAs Advanced Logistics Project (ALP) and UltraLog Project as well as the development, experimentation, demonstration, transition and eventual commercialization of the Cognitive Agent Architecture (Cougaar).
Todd Carrico, Mark Greaves

AGENTFLY: Towards Multi-Agent Technology in Free Flight Air Traffic Control

Ever rising deployment of Unmanned Aerial Assets (UAAs) in complex military and rescue operations require novel and innovative methods for intelligent planning and collision avoidance among a high number of heterogeneous, semi-trusted flying assets in well specified and constrained areas [1]. We have studied the free flight concept as an alternative to the classical, centralized traffic control. In free flight the unmanned aerial assets are provided with flight trajectory that has been elaborated without consideration of other flying objects that may occupy the same air space. The collision threads are detected by each of the aircraft individually and the collisions are avoided by an asset-to-asset negotiation. Multi-agent technology is very well suited as a technological platform for supporting the free-flight concept among the heterogeneous UAAs. In this chapter we present AGENTFLY, multi-agent system for free-flight simulation and flexible collision avoidance.
David Šišlák, Michal Pěchouček, Přemysl Volf, Dušan Pavlíček, Jiří Samek, Vladimír Mařík, Paul Losiewicz

Controlling Teams of Uninhabited Air Vehicles

We describe a Multi-Agent System (MAS) for controlling teams of uninhabited air vehicles (UAVs) in the context of a larger system that has been used to evaluate potential concepts of use and technologies. The approach is one of a decision-making partnership between a human operator and an intelligent uninhabited capability. The MAS controls the UAVs and self-organises to achieve the tasks set by the operator with interaction via a variable autonomy interface. We describe how the agents are integrated with the rest of the system and present a number of system integration issues that have arisen. The overall system has been evaluated in a number of human-inthe-loop trials within a detailed synthetic environment.
Jeremy W. Baxter, Graham S. Horn

Simulating Fighter Pilots

Since 1990 a focused intelligent agent research and development programme within the Defence Science and Technology Organisation (DSTO) has underpinned a strong history of deployed operational simulations. Originally aimed at improving simulations of fighter pilots the research has expanded to include: fundamentals of agent languages and architectures; the cognition of teams; intention recognition and cognitive modelling; simulating civilian behaviour in conflict; intelligent environments; software engineering; and autonomy and uninhabited aerial vehicles. Capitalising on this research are a series of deployed simulations that have provided strong examples of the benefits of the technology. This paper presents a brief account of four successful agent-based simulation systems and a broad but shallow overview of some of the more interesting aspects of our relevant agent research and development activities.
Clint Heinze, Michael Papasimeon, Simon Goss, Martin Cross, Russell Connell

MAS Combat Simulation

Multi-agent systems offer a new stage in the evolution of combat simulation. Originally, warfighters simulated combat manually to explore alternatives and plan their campaigns. The first applications of computers to combat simulation used algorithms that aggregated the warriors on each side, such as differential equations or game theory, effectively modeling the entire battlespace with a single process. Entity-based models such as OOS and Combat XXI assign a single agent to each entity, following the standard MAS agenda. A new modeling construct, the polyagent, takes this trend one step further, and uses several agents to model each construct. This approach addresses several challenges that face the traditional MAS approach, including fitting, closure, dynamism, and singularity. This chapter surveys the history of combat modeling, gives two examples of polyagent systems (one for planning, the other for adversarial prediction), and discusses how this construct addresses the challenges.
H. Van Dyke Parunak

Using Multi-Agent Teams to Improve the Training of Incident Commanders

The DEFACTO system is a multi-agent based tool for training incident commanders for large scale disasters. While this system is currently used for the command of a disaster response scenario, the lessons learned and the methods used to approach this challenging domain apply directly to military applications such as the command and control of troops. In this paper, we highlight some of the lessons that we have learned from our interaction with the Los Angeles Fire Department (LAFD) and how they have affected the way that we continued the design of our training system. These lessons were gleaned from LAFD feedback and initial training exercises and they include: system design, visualization, improving trainee situational awareness, adjusting training level of difficulty and situation scale. We have taken these lessons and used them to improve the DEFACTO system’s training capabilities. We have conducted initial training exercises to illustrate the utility of the system in terms of providing useful feedback to the trainee.
Nathan Schurr, Milind Tambe
Weitere Informationen