Search By Subject

Teams of people need to coordinate in real-time in many dynamic and uncertain domains. Examples include disaster rescue, hospital triage, and military operations. It is possible to develop plan a priori, but many parts of these plans must be left ...

As computational learning agents continue to improve their ability to learn sequential decision-making tasks, a central but largely unfulfilled goal is to deploy these agents in real-world domains in which they interact with humans and make decisions ...

The Restaurant Game demonstrates an end-to-end system that captures and generates social behavior for virtual agents. Over 15,000 people have played The Restaurant Game, and we have developed a system to automatically learn patterns of interaction and ...

A major characteristic of combat is the need to quickly adapt to new situations. Providing support and protection for a convoy is challenging since it requires coordination between the different participants to efficiently allocate the protecting ...

My Ph.D. thesis focuses on the design of economic mechanisms inspired by sponsored search auctions to support new generation search engines. These engines (called integrators) are based on multi-domain queries and on the federation of multiple domain-...

Large-scale collaborative planning is critical in many domains such as sensor networks and disaster rescue. In large, heterogeneous multiagent teams, agents must work together to create plans that maximize the effectiveness of the team as a whole; ...

The goal of this thesis is to allow easier design of probability-based agents and multiagent systems, resulting in rational decision making. A multiagent framework is presented and compared with other proposed frameworks where advantages and ...

Empirical evidence suggests that self-interested agents often fail to reach optimal agreements in multi-issue negotiations. Most existing negotiation approaches either do not address fairness issues; or do not consider computational concerns. To address ...

The Intelligent Decentralised Energy-Aware Systems (iDEaS) project at the University of Southampton (see www.ideasproject.info) is developing and demonstrating the application of intelligent agents within the smart grid; a future vision of an ...

We present an agent-based system for modeling, analyzing and reasoning in the maritime domain with the emphasis on detecting, anticipating and preventing illegal activities, such as contemporary maritime piracy. At the core of the system is a data-...

This paper describes the THOMAS framework, a useful framework for the development of virtual organizations, on the basis of a service-based approach.

In this paper we present a system that automatically generates a 3D virtual world from a virtual institution (VI) specification, namely of activities that will take place in the virtual world. A virtual institution is an interaction environment where ...

A multi-agent coordination and control system is deployed for controlling multiple interacting agricultural vehicles involved in the crop harvesting process. Crops are gathered by combine harvesters. The harvested product is transferred to one or more ...

There is a chronic lack of shared application domains to test the research models and agent architectures on areas like negotiation, argumentation, trust and reputation. In this demostration we introduce such a friendly testbed called DipGame that can ...

Dora the Explorer is a mobile robot with a sense of curiosity and a drive to explore its world. Given an incomplete tour of an indoor environment, Dora is driven by internal motivations to probe the gaps in her spatial knowledge. She actively explores ...

We present a framework for non-mediated bilateral multi-issue negotiation under non-monotonic preference spaces. The framework is based on a region-based recursive bargaining mechanism. Preliminary experimental evaluation shows that our approach may ...

We present an initial comparative evaluation between monotonic mixing and the traditional linear weighted combination of tactics in a multi-issue negotiation scenario. As the traditional mixing method may produce a non-monotonic sequence of utilities of ...

The problem of finding agents' rational strategies in bargaining with incomplete information is well known to be challenging. The literature provides a collection of results for very narrow uncertainty settings, but no generally applicable algorithm. In ...

Users' preferences play a key role in automated negotiation since they dictate how an agent will act on behalf of its user. However, elicitation of these preferences from the user is difficul when there are dependencies between preferences. In many ...

We introduce the flexible approach for determining agents' orientation on ontology mappings (FDO), which provides a flexible mechanism for agents to decide whether or not they support an argument about a mapping. Whilst this results in agents relaxing ...