Autonomous Asset Tracking System (AATS) using Machine Learning

Stratom proposes to develop a camera system and Machine Learning (ML) model that can automatically identify USAF assets on the flightline (aircraft, Material Handling Equipment (MHE), etc.) to streamline distributed operations and equipment and to address the imminent logistics challenges we believe will be created by Agile Combat Employment (ACE). We call this system the Autonomous Asset Tracking System (AATS) and it directly aligns with the DAFÆs resilient basing operational imperative, advanced computing and software technology focus area, and global reach/effectiveness strategic capability need. To initially prove the concept in a SBIR Phase I, Stratom will leverage our direct expertise to develop a ML model that can identify aircraft and tail numbers from still digital images at an airfield. Long term, this technology has wide-reaching benefits and use cases for the DoD and commercial industries. For the Air Force, it will greatly enhance efficiency, accuracy, and operational readiness by supporting command and control, maintenance groups, and logistics readiness squadrons. In the commercial sector AATS can help airports, rail operators, and construction companies track equipment status, perform quality checks, track fleet uptime, quantify resource utilization, and assure site security.