HALO: High Autonomous Low-SWaP Operations

Authors

• Sloan Hatter, Florida Institute of Technology
• Blake Gisclair, Florida Institute of Technology

Document Type

Poster

Publication Title

Northrop Grumman Engineering & Science Student Design Showcase

Abstract

Orbital object detection is a vital aspect of space operations, particularly for identifying satellite components. Convolutional Neural Networks (CNNs) are typically used for such operations by running onboard models directly on satellite systems. However, a new neural network architecture, known as Vision Transformers (ViTs), have shown greater effectiveness due to their ability to capture global context. One main issue of deploying systems with such capabilities is resource allocation. One solution is to run models on a Low-SWaP system; however, this results in inefficient performance. To enable efficient ViT operations on Low-SWaP systems, the model must be scaled down through quantization, enabling the achievement of High Autonomous Low-SWaP Operations.

Advisor

Ryan White

Publication Date

4-24-2026

Recommended Citation

Hatter, Sloan and Gisclair, Blake, "HALO: High Autonomous Low-SWaP Operations" (2026). Mathematics and System Engineering Student Publications. 13.
https://repository.fit.edu/math_student/13