Gregory A. Godfrey

Senior Manager

Dr. Godfrey joined Metron in 1998, and has served as a Principal Investigator or Technical Lead on over a dozen projects for the Defense Advanced Research Projects Agency (DARPA), Office of Naval Research (ONR), Air Force Research Laboratory (AFRL), Missile Defense Agency (MDA), Naval Air Systems Center (NAVAIR), U. S. Transportation Command (USTRANSCOM) and the Intelligence Community.  His technical emphasis has been in developing detection, tracking, exploitation, and dynamic resource allocation algorithms in multiple domains.


For ONR’s Large Tactical Sensor Networks and Wide Area Surveillance programs, Dr. Godfrey led the development of activity and anomaly detection algorithms using vehicle tracks derived from wide area surveillance video. The approach extends classical likelihood ratio detection theory, which has had tremendous success detecting physical objects for military applications, to detect activities and events. These capabilities were demonstrated successfully at Empire Challenges 2009 and 2010 as part of the Threat Detection Suite (TDS). More recently, Metron transitioned TDS to the National Geospatial Intelligence Agency (NGA) InnoVision ISR Integration Division for use in exploiting archival repositories of wide-area derived track data.


Also under ONR LTSN, Dr. Godfrey led a two-month study on the use of statistical background modeling to detect both stationary and moving foreground targets (dismounts and vehicles) given low contrast imagery. The results showed a significant improvement in track completeness and a low false positive rate in spite of the increased coverage statistics. In addition, he led the development of Person of Interest scoring algorithms based on Resource Description Framework (RDF) statements from multiple application services and intelligence sources. Using Metron’s Paladin link analysis tool, we demonstrated this capability using operational data from Afghanistan and exercise data at Empire Challenge 2010.
For AFRL’s SNARE program, Dr. Godfrey led the development of algorithms and software designed to fuse information derived from geospatial surveillance data, especially GMTI tracks, with information derived from transactional data about entities and their networks. The goal is to discover hidden enemy networks and to estimate their organizational structure and behaviors.


For the Intelligence Community, Dr. Godfrey led the development of Metron’s TerrAlert software for tracking the progress of and optimizing courses of action to delay or disrupt suspected terrorist operations. The approach uses Monte Carlo sampling and Bayesian, nonlinear filtering to estimate the state (schedule) of a terrorist operation defined by a project management model (such as a PERT or Gantt chart) with uncertain task durations. The Office of Naval Intelligence has used TerrAlert to support classified experiments, and the Defense Threat Reduction Agency (DTRA) funded Metron to develop TerrAlert training scenarios and materials to train analysts in DTRA’s Threat Intelligence Division, Operations-Combating WMD Intelligence.


Under DARPA funding, Dr. Godfrey designed the algorithms for and managed the software development of multi-agent technology in two separate domains: coordinated unmanned aerial vehicle (UAV) search and surveillance and collaborative airlift planning. In the UAV domain, he developed negotiation mechanisms that enable distributed coordination of a fleet of autonomous UAVs performing search (detection) and surveillance (monitoring) on mobile ground targets.

 

Education

  • Bachelor of Science, Mathematics, Yale University, 1991 
  • Bachelor of Science, Applied Physics, Yale University, 1991 
  • Master of Arts, Operations Research, Princeton University, 1994 
  • Doctor of Philosophy, Operations Research, Princeton University, 2000