University of Southern California (USC) researchers are developing several parts of the Defense Advanced Research Projects Agency (DARPA) Deep Green program. Their efforts are intended to help commanders on the battlefield to anticipate enemy moves. 'The system interweaves anticipatory planning with adaptive execution to help the commander think ahead, identify when a plan is going awry and prepare options before they are needed.' Deep Green will be able to add computing resources on the spot if the problem faced by a commander is too difficult. Two teams at ISC are developing components for this program. But read more...
The figure above describes the basic system architecture of Deep Green, comprised of the Commander's Associate (with three sub-components, the Sketch to Plan, Automated Options Generation, and the Sketch to Decide), Blitzkrieg, and Crystal Ball. This illustration was picked from a 2007 DARPA's document about the Deep Green Approach. Some components might have slighly changed since 2007.
But what exactly is Deep Green? "Deep Green is a next-generation, commander-centered battle command and decision support technology that interleaves anticipatory planning with adaptive execution to help the commander think ahead, identify when a plan is going awry, and prepare options -- before they are needed." This program is managed by Colonel John R. "Buck" Surdu who holds a Ph.D. in computer science from Texas A&M University.
According to the USC news release mentioned above, the USC Viterbi School of Engineering’s Information Sciences Institute (ISI) will receive $7.6 million from DARPA for the two projects it's heading.
The first one is headed by Paul Cohen, a professor in computer science and director of the Center for Research on Unexpected Events (CRUE), with the help of research scientist Yu-Han Chang. Cohen noted that even if the program was named Deep Green by reference to the IBM's Deep Blue chess playing program, a battlefield and a chess board are very different.
Here are some quotes from Cohen picked from a previous news release from the USC Viterbi School of Engineering News, "Deep Green Models Rapid Change for Combat Commanders" (March 31, 2008). "'Chess is a special, artificial situation,' Cohen notes. 'The pieces occupy fixed positions for long intervals, then move instantaneously.' The battlefield is a very different place, Cohen says. There, units on both sides are in continuous motion. Moreover, chess players can see the whole board, whereas commanders have limited visibility of the battlefield. A program like Deep Blue visualizes where pieces might move in the future, based on the moves possible for knight, bishop, and so on. The problem for Deep Green is that time and location change continuously, so the very notion of a 'state of the board' needs a new formulation."
A second program is handled by Robert Lucas, director of ISI's computational science division, and Dan Davis, project director of the ISI's Joint Experimentation on Scalable Parallel Processors program. Their goal is to "take Cohen and Chang's work out of laboratory situations by finding ways to put the huge computational resources necessary into a system that Cohen could actually be used in chaotic wartime conditions."
Here are additional details. "Chang and Cohen's program, called Adversarial Continuous Time and Space Search, (ACCTS), represents collections of interacting combatants (units) by what are called 'fluents,' a concept close to the time-space operators called vectors familiar to first-year physics students." Davis and Lucas are working to create "a system that links to portable electronics; a very efficient, bandwidth-saving, distributed computing platform and an effective method for assessing local computation and communications limitations. If it can be done -- if they can create a very large trans-globally distributed computer network that still requires very little bandwidth, the Deep Green system can be made scalable -- 'it will run effectively on one processor to 20 processors on scene, or hundreds within the battlespace, or thousands across the globe,' Lucas explained."
The researchers acknowledge that many problems remain to be solved and that the Deep Green program will not be used on the battlefield before a few years.
Sources: Eric Mankin, University of Southern California (USC), April 24, 2008; and various websites
You'll find related stories by following the links below.