Multi-Agent and Multi-Agent System Interoperability





To enable requester agents to find provider agents in environments with heterogeneous and dynamic information services, we have developed middle agents, which serve to increase agent interoperability.

To enable requester agents to find and communicate with agents operating in different multi-agent systems (MASs), we have developed multi-agent system interoperability. Multi-agent system interoperability allows heterogeneous agents to communicate across multiple systems and achieve designated goals, on a dynamic basis.

In particular, in the TIE3 Demo, we have demonstrated the interoperability of the RETSINA agent architecture and the Open Agent Architecture (OAA), by means of the the multi-agent system Interoperator. The Interoperator serves as a two-way translation and messaging agent, allowing for the agents of both systems to communicate.

In TIE3, the Messenger, receiving requests from within RETSINA, passes requests to available RETSINA information agents (e.g., Flight Agent, Weather Agent), and simultaneously, to the Interoperator. The Interoperator translates the messages for OAA communication, and passes the translated messages to the Facilitator, the middle agent within OAA. The OAA Facilitator then sends the requests to the appropriate agents within the OAA, receives replies, and returns replies back to the Interoperator. The Interoperator returns translated replies to the Matchmaker for redistribution within RETSINA.

Thus, TIE3 demonstrates, among other things, the interoperability of MAS's, or the ability of agent technology to solve the problems of architectural specificity in distributed computing.

Below is a Demo display of the TIE3 configuration with a sample message path:

For more information on MAS interoperability, see J. Giampapa, M. Paolucci, and K. Sycara, "Agent Interoperation Across Multiagent System Boundaries", in Proceedings of Agents 2000, Barcelona, Spain, June 3-7, 2000.


Copyright 2006 - 2012 © Advanced Agent-Robotics Technology Lab - The Robotics Institute - Carnegie Mellon University

Internal Site (Restricted Access).