Session
Weekend Poster Session 2
Location
Utah State University, Logan, UT
Abstract
The Spacecraft Compartmentalized Autonomous Learning and Edge-computing System (SCALES) represents a groundbreaking advancement in on-orbit machine learning (ML) and edge computing. This integrated hardware and software system leverages Commercial Off-The-Shelf (COTS) edge computing technology and NASA JPL's F' (F Prime) software framework to create a robust and reusable environment for ML algorithm execution and training directly on spacecraft.
SCALES addresses two primary challenges in the deployment of ML-based autonomy in Earth Orbit: the limited compute performance of flight-ready hardware and the absence of reliable, reusable software architectures for managing on-orbit computing. By combining a flight-qualified processor for core spacecraft functions with a dedicated edge computing processor for ML tasks, SCALES enhances computational capabilities without compromising system reliability.
Over the course of two years, the SCALES project aims to elevate the system from Technology Readiness Level (TRL) 4 to TRL 6, incorporating rigorous design, integration, and space environment testing. This advancement promices to revolutionize autonomous operations for small satellites, enabling rapid data processing, adaptive model retraining, and mission-critical decision-making without the need for continuous ground intervention.
SCALES: A Preliminary Architecture for a Modular and Scalable Edge Computing System for Small Spacecraft
Utah State University, Logan, UT
The Spacecraft Compartmentalized Autonomous Learning and Edge-computing System (SCALES) represents a groundbreaking advancement in on-orbit machine learning (ML) and edge computing. This integrated hardware and software system leverages Commercial Off-The-Shelf (COTS) edge computing technology and NASA JPL's F' (F Prime) software framework to create a robust and reusable environment for ML algorithm execution and training directly on spacecraft.
SCALES addresses two primary challenges in the deployment of ML-based autonomy in Earth Orbit: the limited compute performance of flight-ready hardware and the absence of reliable, reusable software architectures for managing on-orbit computing. By combining a flight-qualified processor for core spacecraft functions with a dedicated edge computing processor for ML tasks, SCALES enhances computational capabilities without compromising system reliability.
Over the course of two years, the SCALES project aims to elevate the system from Technology Readiness Level (TRL) 4 to TRL 6, incorporating rigorous design, integration, and space environment testing. This advancement promices to revolutionize autonomous operations for small satellites, enabling rapid data processing, adaptive model retraining, and mission-critical decision-making without the need for continuous ground intervention.
