CREATE: Context Reasoning for Autonomous Teaming

CREATE aims to explore the utility of artificial intelligence (AI) on the autonomous formation of scalable machine-to-machine teams capable of reacting to and learning from unexpected missions in the absence of centralized communication and control. CREATE seeks to develop the theoretical foundations of autonomous AI teaming to enable a system of heterogeneous, contextually-aware agents to act in a decentralized manner and satisfy multiple, simultaneous and unplanned missions goals. Agents within the team will have mechanism for regulation to ensure (favorable) emergent behavior of the team to: (1) better ensure the desired mission outcome; and (2) bound the cost of unintended adverse action or regret.

CREATE aims to explore the function and utility of encoding common knowledge (e.g. general places and things), procedural knowledge (e.g. user’s manuals and playbooks), and learned knowledge (evolving experiential, or semantically inferred information). Additionally, the program will explore the accuracy and value of decentralized machines decisions made form local observations and any available global context with an emphasis on decisions related to unplanned missions. To mitigate potential undesirable action while maintaining an interesting level of autonomy, the program will investigate the correct balance of hard coded and contextual safeguards.