Conference Paper

Integrating individual and social intelligence into module-based agents without central coordinator

DOI: 10.3233/978-1-58603-893-9-82 Conference: STAIRS 2008 - Proceedings of the Fourth Starting AI Researchers' Symposium, Patras, Greece, 21-25 July, 2008
Source: DBLP


Robots are complex entities that can be modeled as multi-agent systems. The multi-agent paradigm,provides an integrated intelligence framework,such as a path planning agent that uses search techniques interacts with a fuzzy-based agent that moves the robot to a given location. Agent coordination is required to achieve the appropriate global behavior. When there is no central agent that coordinates the overall architecture, the intelligence required for social interaction should therefore be deployed at the agent level. In such a situation, individual intelligence (how to reach a goal) and social intelligence (how to collaborate or compete for resource with other agents) should be integrated at the agent level. In this paper we propose the use of module-based agents to achieve this integration. The whole multi-agent robot architecture, ARMADiCo, has been implemented with several module-based agents and tested on a Pioneer 2DX of ActivMedia. Some preliminary results are shown and discussed. Keywords. Robotics, Agents

Download full-text


Available from: Joaquim Salvi, Jan 28, 2016
  • Source
    • "identifying knowledge expert, understanding knowledge found as knowledge sought). For the purpose of proposing an integrated intelligence in module-based agents without a central coordinator, Innocenti, Lopez and Salvi [6] emphasised the importance of having social intelligence to collaborate or compete for resources with other agents. Looking at one aspect of social intelligence, having its ability to collaborate (instead of compete) for resources in a social network could result in knowledge management outside of personal and organisational boundaries. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Personal intelligence has been coined by a number of authors and one of them relates the concept with agent-mediated personal knowledge management (PKM). The concept of agent-mediated PKM has recently been expanded to a bottom-up approach towards collective goals in organisational knowledge management (OKM). Exploiting this concept further from the perspective of crossing organisational boundaries and into the world wide web of social network, the concept of social intelligence is proposed. In this paper, a nodal approach to agent-mediated PKM is extended to model the concept of social intelligence in social network, in which knowledge workers work cooperatively with software agents in a virtual workspace called a node. This paper analyses the knowledge management processes by characterising these nodes as intelligent social entities.
    Full-text · Conference Paper · Jan 2011