Automated Threat Response using Intelligent Agents (ATRIA)

Today's dynamic battlefield environment requires rapid reconfiguration and reorganization of warfighter assets, communication links, and computing resources in response to enemy attacks. The extent to which supporting operations can take place autonomously, and thus more rapidly, could be critical to neutralize future enemy threats. This paper describes a software system called Automated Threat Response using Intelligent Agents (ATRIA). The ATRIA software agent architecture is based on a commercial off-the-shelf (COTS) agent development environment. ATRIA agents detect signals indicating an enemy attack and then automatically gather strategic data, generate internal plans, and task surveillance and strike resources to counter an enemy threat. The agents discover and access data and resource information distributed across a dynamic, wide area network. The agent-based design allows rapid access to and communication with heterogeneous military data sources that have been traditionally difficult to coordinate. The initial demonstration scenario deals with the detection, tracking, and destruction of enemy theater ballistic missiles. A simulation infrastructure has been implemented to allow testing of the ATRIA system against various scenarios. The agents are implemented in a combination of the COTS tool's rule-based language, Java, and Prolog. Surveillance and strike resources are simulated using Prolog.