Battlefield Management C4I (TBMC4I) centers must address complex, "off nominal" and time-critical theater ballistic missile (TBM) scenarios. Under the Missile Defense Agency's (MDA) Project Hercules, battlefield learning algorithms will evolve into an Adaptive Battlefield Learning Engine (ABLE) to provide decision support and unify situational awareness for missile defense assets. Researchers will leverage our data fusion and reasoning techniques from land attack and maritime domains to expedite BMC4I functions for Joint TBM assets, including the Navy's Cooperative Engagement Capability, the US-Israeli Arrow project, and the Medium Extended Air Defense System (MEADS). ABLE will ultimately leverage knowledge-based reasoning, genetic algorithms, and machine learning to: 1) decrease TBM "safe havens," 2) unify situational awareness and automate decision support templating, 3) support interoperability/sensor management, and 4) deliver timely cueing for interceptors like the airborne laser (ABL) and other sea-based midcourse systems. Rapid battlefield learning enablers will enhance layered defense capabilities via "learn as you go" experimentation and technology insertion. Follow-on efforts in this appropriate-risk, high-payoff endeavor include joint interoperability tests with the Cooperative Engagement Capability (CEC), MEADS, and the Airborne Laser (ABL) systems. The value of information derived from the OSEC-ORINCON Adaptive Battlefield Learning Engine (ABLE) can be demonstrated in TBMC4I tests at either the Experimental Laboratory or another government site
