Tactical Maritime Intelligence: Adaptive AI and Autonomy at the Tactical Edge

The National Geospatial-Intelligence Agency, through its Rapid Capabilities Office, in coordination with the Office of Naval Intelligence and Army Contracting Command - Redstone Arsenal Innovation, seeks to prototype artificial intelligence-enabled computer vision capabilities that sustain tactical maritime intelligence at the edge. Warfighters operating in contested maritime environments depend on continuous custody of vessels of interest. Current approaches face challenges in low-connectivity environments and require improved automation. Tactical sensors increasingly hand off custody of vessels of interest to computer-vision-based tracking, but current models degrade in novel environments and require reach-back to enterprise cloud infrastructure for retraining, which challenging conditions preclude. Analysts and operators need a capability that can be deployed and adapted at the point of need, with minimal labeled data and minimal coding expertise, to maintain continuous custody of vessels critical to tactical maritime intelligence and national security decision-making. This prototype effort will develop an automated maritime vessel detection, tracking, and re-identification capability deployable at the tactical edge, built on low-shot computer vision models and integrated with standard GEOINT data formats and tactical data dissemination systems. The prototype will undergo evaluation to inform future development and transition decisions, addressing critical capability gaps in maintaining vessel custody under austere communications conditions without cloud dependency.
## Problem Statement
Tactical sensors increasingly hand off custody of vessels of interest to computer-vision-based tracking, but current models degrade in novel environments and require reach-back to enterprise cloud infrastructure for retraining, which challenging conditions preclude. Analysts and operators need a capability that can be deployed and adapted at the point of need, with minimal labeled data and minimal coding expertise, to maintain continuous custody of vessels critical to tactical maritime intelligence and national security decision-making.
## Overall Objective
Prototype, test, and validate an edge-deployable automated maritime vessel detection, tracking, and re-identification capability that enables warfighters to maintain continuous custody of vessels of interest in contested maritime environments. The prototype will demonstrate low-shot computer vision models operating on size, weight, and power-constrained edge hardware without cloud reach-back, integrated with standard GEOINT data formats and tactical data dissemination systems including the TAK ecosystem and REST API architectures. The effort will validate model performance against defined F1, precision, and recall thresholds while maintaining custody across multiple simultaneous detections and re-identifying vessels following loss of custody. Success will deliver a capability that analysts and operators can deploy and adapt at the point of need with minimal labeled data and minimal coding expertise, with documented performance outcomes to inform transition and follow-on development decisions supporting tactical maritime intelligence and national security decision-making.