Wars of the Virtual Worlds

 

 

Every few months, a continent crackles into life on linked supercomputers. It is a place of huge cities surrounded by countryside with an intricate network of roads where thousands of trucks, tanks, mopeds, other vehicles and pedestrians move.

 

The newly created world is an electronic arena in which top military officers of the U.S. Joint Forces Command (JFCOM) develop tactics for the future – an arena that has taken a significant leap in complexity in the past three years, courtesy of computer skills from the USC Viterbi School’s Information Sciences Institute (ISI).

 

The ISI-JFCOM team’s simulation software is “scaleable,” or not artificially limited to a small number of simulated participants.  ISI has collaborated with Caltech, Lockheed Martin, Alion Sciences, SAIC and Toyon and in March, the scientists received a bridge grant to continue their efforts.

 

“Urban Resolve,” one experiment in this series, set in the year 2015, involves a U.S.-led coalition force that must confront and overcome a skilled adversary equipped with modern capabilities and operating in an urban environment.

 

Two groups of officers – the blue team leaders of the coalition, and the red team leaders of the adversary – control their forces from separate command posts, rooms full of monitors where specially trained aides make the moves ordered by commanders. The aides are called “puckers” – a holdover from the days when military exercises were conducted on huge tables and soldiers pushed model ships or tanks (“pucks”) around with sticks. Two other computer control rooms complete the set-up. A green team controls the “clutter” – vehicles, pedestrians and other facets of the civilian population – not part of the forces of either side. Finally, a white room for the experiment’s umpires offers a combined view of operation — a so-called “angel’s eye view.”

 

Puckers for green, red and blue teams add vehicles to the world by selecting them from a menu of thousands of pre-written units of software code, each describing the behavior of a specific vehicle –taxi, tank or city bus.   Some of the vehicles have very complex behavior sets, but even the simple robots “know” how fast to go on which roads, turn corners, avoid collisions and stay on the road. They are also time-sensitive, crowding the roads during morning and afternoon rush hours.  A select few – most of them combat units – are far more complex, endowed with artificial intelligence that allows them to respond and react to changing circumstances in complex ways.

 

Simple or complex, the population of the arena world used to be much smaller.

 

“For a long time, there was an unacceptable ceiling for the number of the vehicles that could be simulated on individual workstations on a local network,” said ISI project director Dan Davis, a Marine Corps veteran who has turned his combat-zone experience to good use.  “They couldn’t get much above about 30,000.”

 

Robert Lucas, director of the computational sciences division at ISI, broke this barrier with a major event in 2002. That event was the record for SemiAutomated Forces so far: one million entities.

 

”While we are hesitant to say just exactly where the final limits may be,” Davis said, “we now see no immediate constraints on the delivered scalability.”

 

The experiments in 2004 used about 100,000 entities, employing cluster supercomputers located at two military supercomputing centers, one in Ohio and another in Maui. All experiments are directed from the Joint Experimentation Directorate in Suffolk, Va., with two other sites where controllers and analysts work: the U.S. Army Topographic Engineering Center at Fort Belvoir, Va., and at the Space and Naval Warfare Systems Command facilities in San Diego, Calif.

 

ISI computer scientists Ke-Thia Yao, Gene Wagenbreth, Brian Barrett and John Tran also participated in the effort. Tran, who joined the team two years ago, may soon have an opportunity to see in real life some of the issues he has been simulating: He has just been called up for six months of reserve duty.