You are here

Probabilistic and Relational Inferences in Dynamic Environments (PRIDE)

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: W31P4Q-11-C-0083
Agency Tracking Number: 08ST1-0075
Amount: $1,499,383.00
Phase: Phase II
Program: STTR
Solicitation Topic Code: ST081-004
Solicitation Number: 2008.A
Timeline
Solicitation Year: 2008
Award Year: 2011
Award Start Date (Proposal Award Date): 2011-01-18
Award End Date (Contract End Date): N/A
Small Business Information
625 Mount Auburn Street, Cambridge, MA, -
DUNS: 115243701
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Avi Pfeffer
 Senior Scientist
 (617) 491-3474
 apfeffer@cra.com
Business Contact
 Ninos Hanna
Title: Contract Specialist
Phone: (617) 491-3474
Email: nhanna@cra.com
Research Institution
 University of California Berkeley
 Patricia Gates
 Sponsored Projects Office
2150 Shattuck Ave., Suite 313
Berkeley, CA, 94704-
 (510) 642-8109
 Nonprofit college or university
Abstract
Uncertainty on the modern battlefield makes mission planning and decision making extremely complex for field commanders. Mission planners can be aided by initial and ongoing situation assessment, future state estimation, assessment of the current plan"s probability of success, what-if analysis, and suggestions for decisions. At present, few automated tools exist to provide mission planners with the required information. An automated tool to assist mission planners must deal with both the inherent uncertainty and the complexity of the situation. Charles River Analytics proposes a system for Probabilistic and Relational Inferences in Dynamic Environments (PRIDE), an approach based on probabilistic relational models (PRMs). PRMs use probabilities to handle uncertainty while capturing the logical and relational structure of a situation to handle complexity. We base our implementation of PRMs on probabilistic programming (PP), which provides a powerful and flexible way to represent probabilistic models using the power of programming languages. We propose to design and develop a full-fledged prototype of our PRM and PP engine, to design and develop temporal reasoning capabilities, and to design and develop decision-theoretic reasoning capabilities.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government