Intelligent Course of Action Learning System (iCOALS)

ABSTRACT: SSCI proposes creation of an Intelligent Course of Action Learning System (iCOALS), building on extensive past experience in learning advanced fighter combat maneuvers from simulation. By learning from repeated simulations, robust strategies can be constructed that allocate a complete action repertoire (including the mission-specific, limited range of weapons, countermeasures, associated maneuvers, etc.) to multiple autonomous and semi-autonomous vehicles in mission scenarios. By utilizing SSCIs unique genetics-based rule learning (GBRL) techniques, these strategies take the form of rule sets, which can then be used for real-time reaction to evolving threats during mission execution. By evolving against a range of simulated mission conditions, the resulting rule sets will be robust against a corresponding range of IADS behaviors. This robustness can be further advanced by two-sided learning in the simulation, where the IADS also evolves strategy rule sets. iCOALS will encode strategies as rule sets that are highly human-readable. This will enhance the ability for human intervention in a semi-autonomous execution mode. The proposed Phase II will refine the vehicles models used in iCOALS, conduct additional experimentation and testing on new mission scenarios, and deliver a framework ready for integration with sponsor-provided simulation resources and other mission and simulation systems. BENEFIT: iCOALS is being designed as a modular system, which can find application in deriving reactive behaviors for a range of multi-vehicle mission systems. Such behaviors are essential if autonomous and semi-autonomous systems are to be deployed in any military or commercial domain that is potentially lethal, dangerous, or inconvenient for onboard human operators. As such, this is a critical element of SSCIs autonomous systems focus, which is being deployed in marine, air, and ground-based autonomous systems.