Home Research | People | Publications | Slides  
  e.l.e.c.t.r.i.c   e.l.v.e.s

he operation of a human organization requires dozens of everyday tasks to ensure coherence in organizational activities, to monitor the status of such activities, to gather information relevant to the organization, to keep everyone in the organization informed, etc. Teams of software agents can aid humans in accomplishing these tasks, facilitating the organization's coherent functioning and rapid response to crises, while reducing the burden on humans. Based on this vision, Electric Elves has been in operation 24/7 at ISI since June 1, 2000.

Tied to individual user workstations, fax machines, voice, mobile devices such as cell phones and palm pilots, Electric Elves has assisted us in routine tasks, such as rescheduling meetings, selecting presenters for research meetings, tracking people's locations, organizing lunch meetings, etc. There are a number of underlying AI technologies that support the Electric Elves, including technologies devoted to agent-human interactions, agent coordination, accessing multiple heterogeneous information sources, dynamic assignment of organizational tasks, and deriving information about organization members.

This project was funded by the Defense Research Advanced Project Agency (DARPA), Control of Agent-based Systems (COABS) program. Prof. Jim Hendler is the program manager for this program.

This project unites all existing COABS agent projects at the Information Sciences Institute Intelligent systems Division. These constituent projects include:

Teamcore - Milind Tambe, David Pynadath

Rapid integration of such distributed, heterogeneous agents via a novel teamwork-based agent integration framework. In this framework, software developers first specify an agent organization through team-oriented programming. To recruit agents for this organization, an agent resources manager (an analogue of a "human resources manager") searches for agents of interest to this organization, and monitors their performance over time. Agents in this organization are wrapped with TEAMCORE wrappers, that make them team ready, and thus ensure robust, flexible teamwork among the members of the newly formed organization. This implemented framework promises to reduce the software development effort in agent integration while providing robustness due to its teamwork-based foundations. We have successfully demonstrated this framework in a NEO TIE as part of the DARPA Control of Agent-based Systems (COABS) program.

ARIADNE - Craig Knoblock, Kristina Lerman, Jean Oh

To address the problems of accessing and verifying information from heterogeneous soures, we developed a set of techniques for learning to recognize the content of the required information. The capability makes it possible to automatically access and maintain wrappers to extract data from online sources. It also provides semantic interoperability among software agents: to verify information from other agents, identify semantic mismatches in data, as well as automatically determine the type of information being communicated by an agent.

Ontology-Based Agent Matching and Communication - Yolanda Gil, Hans Chalupsky, Tom Russ

The main goal of this effort is to investigate how ontologies help in agent coordination and communication. We are developing ontology-based agent matchmakers (Phosphorus) and ontology-based translation (Rosetta). This work is a joint effort of the EXPECT and Loom projects at ISI.

This project was funded by the Defense Research Advanced Project Agency (DARPA), Control of Agent-based Systems (COABS) program. Prof. Jim Hendler is the program manager for this program.