Logo

CIRG - Research  -  Multi-Agent Systems 



[Bullet] Home
About
News
[Bullet]

- NN
- DM
- SI
- EC
- MAS
- AIS
- IA
- Bioinf
- Games
- Opt
- FA
- Industry

Publications
People
Resources
Links
Contact Us

OVERVIEW

This focus area concentrates on approaches to control and manage a collection of embedded agents to perform a collective task. The main focus is on swarm robotics, where a collection of robot agents have to compete or cooperate to successfully achieve a task. This is achieved by developing control and communications mechanisms that have their foundations in the social and economic sciences.

ACTIVE MEMBERS

List the current members actively doing research in this focus area. [ Show ]

ALUMNI MEMBERS

List alumni of this research focus area. [ Show ]

GROUP PUBLICATIONS


Social Networks as a Task Allocation Tool for Multi-Robot Teams
Rodic, D. Engelbrecht, AP. 2004.
South African Computer Journal

Unavailable for download.

Abstract:

The last decade saw a renewed interest in the field of robotics research and a shift in research focus. In the eighties and early nineties, the focus of robotic research was on finding optimal robot architectures, often resulting in non-cognitive, insect-like entities.In recent years, the processing power available to embedded autonomous agents (robots) has improved and this development has allowed for more complex robot architectures. The focus has shifted from single robot to multi-robot teams. The key to the full utilisation of multi-robot teams lies in coordination. Although a robot is a special case of an agent, many existing multiagent coordination techniques could not be directly ported to multi-robot teams. In this paper, we overview mainstream multi-robot coordination techniques and propose a new approach to coordination, based on models of organisational sociology, namely social networks. The social network based approach relies on trust and kinship relationships,modified for use in heterogeneous multi-robot teams. The proposed task allocation mechanism is then tested using two approaches: the multi-robot team task allocation simulation and a more realistic coordination problem in simulated robot environments. For the purpose of these two tests, two robotic simulators were developed. The social networks based task allocation algorithm has performed according to expectations and the obtained results are very promising. Although it is applied to simulated multi-robot teams, the proposed coordination model is not robot specific, but can also be applied to any multi-agent system without major modifications.

Back to top Up Arrow



INDABA - Proposal for an Intelligent Distributed Agent Based Architecture
Rodic, D. Engelbrecht, AP. 2003.
Second International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore, 2003

Download this publication from the Multi-Agent Systems group.

Abstract:

This paper presents an overview of Intelligent Distributed Agent Based Architecture (INDABA), a framework for building socially aware Multi Agent Systems (MAS) that is currently under development as a part of the research effort at the University of Pretoria. The guiding idea behind this framework is not to necessarily improve on every single aspect of multi-agent systems (such as agent architecture, interaction language etc.), but to provide a test bed for experimenting with various interaction mechanisms. Effort has been made to keep our architecture as standard as possible, to allow for possible joint efforts between various entities (industry, academic institutions and research centres). Many mechanisms described as a part of INDABA are already in development and for the others the overall guiding ideas for their implementation are presented. The proposed architecture will be a test bed for a multidisciplinary research effort that will include elements of artificial intelligence, sociology, artificial life and biology. However, the main focus is in embedded multi-agent systems, robotic teams. The purpose of this article is, therefore to describe the laying of a foundation for a new, hybrid, architecture. In addition, in this paper we also overview a coordination mechanism loosely based on Contract Net Protocol that, through innovative application of social networks, incorporates some elements of artificial life, i.e. like competition and specialisation.

Back to top Up Arrow



Investigation into the Applicability of Social Networks as a Task Allocation Tool for Multi-Robot Teams
Rodic, D. Engelbrecht, AP. 2003.
Second International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore, 2003

Download this publication from the Multi-Agent Systems group.

Abstract:

Robotics research has become one of the most active research fields in the domain of artificial intelligence. Over the last decade, researchers have proposed numerous robot architecture models, quite often very complex in nature. Most of those architectures were implemented only in simulations. The real test of an architecture is its performance in real world embodied robots, and it would be beneficial if physical robots were used instead of simulations. One of the most popular, albeit fairly complex architecture models is the so called ``three-layer'' architecture. Unfortunately, on the one hande real robots complex enought to support such architecture, are often costly and difficult to construct. On the other hand, there is abundance of well-tested, commercially available robots that have limited processing power. In this paper, we propose an implementation of ``three-layer'' derivative architecture on a hybrid robotic platform that consits of a PC and an off-the-shelf LEGO robot.

Back to top Up Arrow



Investigation of Low Cost Hybrid Three-Layer Robot Architecture
Rodic, D. Engelbrecht, AP. 2003.
Second International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore, 2003

Download this publication from the Multi-Agent Systems group.

Abstract:

The robotics research has become one of the most active research fields in the domain of artificial intelligence. Over the last decade, researchers have proposed numerous robot architecture models, quite often very complex in nature. Most of those architectures were implemented only in simulations. The real test of an architecture is its performance in real world embodied robots, and it would be beneficial if physical robots were used instead of simulations. One of the most popular, albeit fairly complex, architecture models is the so called "three-layer" architecture. Unfortunately, on the one hand real robots complex enough to support such architecture, are often costly and difficult to construct . On the other hand, there is abundance of well-tested, commercially available robots that have limited processing power. In this paper, we propose an implementation of "three-layer" derivative architecture on a hybrid robotic platform that consists of a PC and an off-the-shelf LEGO robot.

Back to top Up Arrow



Social Networks as a Coordination Technique for Multi-Robot Systems
Rodic, D. Engelbrecht, AP. 2003.
International Conference on System Design and Applications, Oklahoma

Download this publication from the Multi-Agent Systems group.

Abstract:

The last decade saw a renewed interest in the robotics research field and a shift in research focus. In the eighties and early nineties, the focus of robotic research was on finding optimal robot architectures, often resulting in non-cognitive, insect-like entities. In recent years, processing power available to autonomous agents has improved and that has allowed for more complex robot architectures. The focus has shifted from single robot to multi-robot teams. The key to the full utilisation of multi-robot teams lies in cooperation. Although a robot is a special case of an agent, many existing multi-agent cooperation techniques could not be directly ported to multi-robot teams. In this paper, we overview mainstream multi-robot coordination techniques and propose a new approach to coordination, based on models of organisational sociology. The proposed coordination model is not robot specific, but it can be applied to any multi-agent system without any modifications.

Back to top Up Arrow






You are visitor #29206
Contact webmaster
Back to top

QualNet Network Simulator University Program Valid XHTML 1.0! Valid CSS!


Computational Intelligence Research Group
University of Pretoria
Copyright © 2017