This paper proposes a formal framework which offers an external representation of conversations between conversational agents. Using this formalism allows us: (1) to represent the dynamics of conversations between agents; (2) to analyze conversations; (3) to help autonomous agents to take part in consistent conversations. The proposed formalism, called “commitment and argument network”, uses a ...

We present a population of autonomous agents that exist within a sonic eco-system derived from real-time analysis of live audio. In this system, entitled Coming Together: Shoals, agents search for food consisting of CataRT unit analyses, which, when found, are consumed through granulation. Individual agents are initialised with random synthesis parameters, but communicate these parameters to ag...

Imagine a (web-based or mobile) route planning service that understands and behaves like another person. This conceptual paper addresses the first step towards this vision. It looks at the ways people would like to talk to their route planner in the initial phase of the route communication when specifying the travel route and time. The paper systematically collects service requirements, based o...

Having the right sensory channels is an important ingredient for building an autonomous agent, but we still have the problem of making sense of the sensory data for the agent. This is the basic problem of artificial intelligence. Here we propose an algebraic method for generating abstract coordinate system representations of the environment based on the agent’s actions. These internal represent...

The Vowel Agent Argumentation Architecture (V3A) is an abstract model by means of which an autonomous agent argues with itself to manage its motivations and arbitrate its possible internal conflicts. We propose an argumentation technique which specifies the internal dialectical process and a dialogue-game amongst internal components which can dynamically join/leave the game, thus having the pot...

This paper describes a novel architecture for a casebased reasoning (CBR) system. Unlike other agent CBR systems in this architecture every case is an autonomous agent with its own retrieval, adaptation and maintenance behaviour. The paper discusses the motivation for this research and what impact this architecture has on the main tasks of processes of a CBR system. The paper concludes by descr...

The ARTUE (Autonomous Response to Unexpected Events) system was built as a prototype to demonstrate the usefulness of Goal-Directed Autonomy. We provide an overview of some of the design decisions made in its construction, as well as a discussion of how we chose to evaluate it. We close with a brief discussion of interesting research questions raised by ARTUE’s design.

What do I need to say to convince you to do something? This is an important question for an autonomous agent deciding whom to approach for a resource or for an action to be done. Were similar requests granted from similar agents in similar circumstances? What arguments were most persuasive? What are the costs involved in putting certain arguments forward? In this paper we present an agent decis...

In this paper we describe a model for navigation of an autonomous agent in which localization, path planning, and locomotion is performed in a qualitative manner instead of relying on exact coordinates. Our approach is grounded in a decomposition of navigable space based on a novel model of visibility and occlusion relations between extended objects for agents with very limited sensor abilities...

the current study aimed to define some factors contributing to implicit attitude formation mainly in the social interaction context. an agent-based computer simulation of a society including autonomous agents and an attitude object was used to track the implicit attitude progress towards the object. the society could simulate the autonomic behaviors. we provided a complex adaptive system and ob...