Embedded ATR Software for Autonomous Guided Munitions

Prism SKR delivers automated target detection, classification, tracking, and aim-point localization across air-to-ground, air-to-air, ground-to-air, and ground-to-ground scenarios.

It supports platforms including loitering munitions, air-launched effects (ALE), counter-unmanned aerial systems (C-UAS), low-cost missiles, and smart munitions. Its algorithmic architecture comprises modular components for target search, identification, target state estimation, and precise localization, enabling full autonomy in mission-critical environments.

Designed for edge deployment, Prism SKR runs on low-power embedded platforms such as NVIDIA® systems or the Teledyne FLIR AVP — a system-on-module (SOM) incorporating the Qualcomm Dragonwing™ QCS8550 processor. The software supports direct integration with Teledyne FLIR’s Boson® and Neutrino® infrared (IR) camera modules, as well as integrator-supplied visible-spectrum sensors, delivering real-time data via a Weapon Open System Architecture (WOSA)-compliant interface.

Prism SKR is embedded within a cohesive software ecosystem designed to accelerate development timelines and minimize integration risk. The system interfaces directly with Prism Supervisor, enabling autonomous mission control and platform guidance. Detection and tracking models are powered by Prism AI, trained on a dataset of six million annotated thermal and visible frames. The ecosystem supports rapid expansion through Prism AIMMGen, which generates synthetic datasets and models to meet mission-specific targeting requirements.

For full system customization, Prism SKR is delivered with a complete API and SDK, enabling detailed control of processing pipelines and performance tuning.