Geon Technologies is pleased to announce the award of a contract towards the Navy Technology Acceleration Topic: Unmanned Aircraft Systems Autonomy and Automation.

Geon will be developing the Multi-Input Data Fused Image Processing System (MIDFIPS) for the Navy with the goal to improve autonomous tasks with Unmanned Aircraft Systems (UAS). This will be a multimodal image processing Machine Learning (ML) framework comprised of a Deep Neural Network (DNN) paradigm that provides an alternative prediction system with confidence and credibility metrics. The Deep k-Nearest Neighbor (DkNN) technique will be used to assess the outputs of intermediate layers in a DNN to perform classification and evaluate the credibility of its decisions, producing a confidence metric that can be used to provide robustness to adversarial attacks. The DkNN approach is supplemented with data fusion techniques to improve robustness and to further mitigate the disadvantages of single-mode approaches.

This win demonstrates Geon’s ability to stay in front of technology trends to deliver innovative ISR capabilities to the Military. We are excited to start working on the development and evaluation of MIDFIPS.