SBIR-STTR Award

Distributed Frameworks for Dynamic Human/Agent Collaborative Problem Solving
Award last edited on: 4/2/2008

Sponsored Program
SBIR
Awarding Agency
DOD : DARPA
Total Award Amount
$848,798
Award Phase
2
Solicitation Topic Code
SB062-008
Principal Investigator
Todd M Carrico

Company Information

Cougaar Software Inc

8260 Willow Oaks Corporate Drive Suite 700
Fairfax, VA 22031
   (703) 506-1700
   info@cougaarsoftware.com
   www.cougaarsoftware.com
Location: Single
Congr. District: 08
County: Fairfax

Phase I

Contract Number: ----------
Start Date: ----    Completed: ----
Phase I year
2007
Phase I Amount
$98,799
The objectives of this effort are to build upon the body of previous work by Cougaar Software Inc. (CSI) and University of Texas, Austin (UT) to develop a complete distributed framework for dynamic human / agent collaborative problem solving. This effort would specifically augment our current framework capabilities with key capabilities necessary to deliver a high-quality usable tool capable of achieving highly capable human / agent collaborative problem solving in complex environments and demonstrate that tool in a representative domain with real planners and reasoners. The key research objectives of this effort are to design, develop and integrate (1) a comprehensive framework for implementing distributed problem solving networks specifically geared toward maximizing the effectiveness of human / agent collaboration; (2) a suite of services and support infrastructure to enable the collaboration, cooperation and communication between human and agents actors in a dynamic system; and (3) demonstrate the feasibility of the framework and services in a limited domain problem and evaluate the issues associated with a full implementation.

Keywords:
Intelligent Agents, Human / Agent Collaboration, Distributed System, Information Fusion, Situational Understanding, Semantic Service Discovery, Dynami

Phase II

Contract Number: ----------
Start Date: ----    Completed: ----
Phase II year
2008
Phase II Amount
$749,999
In the Phase I effort, we studied the problem of how to achieve a high-quality distributed system for dynamic human / agent collaborative problem solving in a specialized domain. From that effort we determined that context was a key missing element that made that collaboration difficult to establish and maintain. Based on our work in Deep Situational Reasoning, we derived a framework from which an agent can maintain context with the human as an integral part of the user interface. Specifically, it combined the classical Model-View-Controller interface paradigm with our newer Object-Network-Semantic paradigm. The combination provided an interesting fusion of meaning, relationship, situated state, environment and intentions. It is our goal in this phase to build a working prototype of this framework and demonstrate it in a limited problem domain

Keywords:
Intellugent Agents, Human / Agent Collaboration, Distributed System, Information Fusion, Situational Understanding, Semantic Service Discovery, Dynami