Spacecraft processors and memory are subjected to high radiation doses and therefore employ radiation-hardened components. However, these components are orders of magnitude more expensive than typical desktop components, and they lag years behind in terms of speed and size. We have integrated algorithm-based fault tolerance (ABFT) methods into onboard data analysis algorithms to detect radiation-induced errors, which ultimately may permit the use of spacecraft memory that need not be fully hardened, reducing cost and increasing capability at the same time. We have also developed a lightweight software radiation simulator, BITFLIPS, that permits evaluation of error detection strategies in a controlled fashion, including the specification of the radiation rate and selective exposure of individual data structures. Using BITFLIPS, we evaluated our error detection methods when using a support vector machine to analyze data collected by the Mars Odyssey spacecraft. We observed good performance from both an existing ABFT method for matrix multiplication and a novel ABFT method for exponentiation. These techniques bring us a step closer to "rad-hard" machine learning algorithms.
Simulating and Detecting Radiation-Induced Errors for Onboard Machine Learning
2009-07-01
327242 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Detecting and Simulating Pilot Errors for Safety Enhancement
SAE Technical Papers | 2003
|Detecting and Simulating Pilot Errors for Safety Enhancement
British Library Conference Proceedings | 2003
|Towards Simulating Semantic Onboard UAV Navigation
IEEE | 2020
|How much Memory Radiation Protection do Onboard Machine Learning Algorithms Require?
British Library Conference Proceedings | 2009
|Applications of onboard analytics and machine learning
NTRS | 2017
|