Home // International Journal On Advances in Intelligent Systems, volume 6, numbers 1 and 2, 2013 // View article

Multidimensional Adaptiveness in Multi-Agent Systems

Authors:
Nadia Abchiche-Mimouni
Antonio Andriatrimoson
Etienne Colle
Simon Galerne

Keywords: Adaptive control, adaptiveness, rule-based system, multi-agent system, ambient assistance

Abstract:
Adaptivity is widely studied as a capability that makes a system able to exhibit a cooperative and intelligent behavior. Moreover, software increasingly has to deal with ubiquity, so that it can apply a certain degree of intelligence. Ambient assistive robotics can be defined as an extension of ambient intelligence which integrates a robot and its embedded sensors. The interaction among the components in such systems is fundamental. In a previous cite{Andriatrimoson2012} work, we presented Coalaa (Coalitions for ambient assistance), which concerns the design and the implementation of an ambient assistive living framework that takes advantage of an ambient environment: a robot cooperating with a network of communicating objects present in the person's home. The aim was to provide a service to an elderly or a sick person. A multi-agent system (MAS) reifies the sensors and the mobile and autonomous robot, allowing the cooperation among the agents by means of adaptation features. The agents form coalitions by adapting the cardinality of the coalitions according to the availability of data sensors so that the whole system can answer to a user request (obtain a particular effect). In the present work, adaptiveness of Coalaa has been improved by integrating a rule-based system able to determine, in a dynamic way, a priority for the criteria to consider during the coalition formation process. On the other hand, new experimental results show the validity of the approach implemented in Coalaa. Multiple dimensions of the adaptiveness have been identified allowing Coalaa being extendable with a meta model of the adaptiveness. The next section details the context application and describes a particular usage scenario. Section III includes a brief overview of existing ambient assistive living systems and argues for a new one based on adaptive coalition-based MAS. The designed system Coalaa is described in details in Section IV. The Section V describes the rule-based module and the adaptation behaviors of the agents. Evaluations and analysis of Coalaa in the context of robotic localization are presented in Section VI. Finally, Section VII draws some conclusions and introduce future works.

Pages: 124 to 135

Copyright: Copyright (c) to authors, 2013. Used with permission.

Publication date: June 30, 2013

Published in: journal

ISSN: 1942-2679