Skip to main content Skip to main navigation

Publication

Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation

Mariela De Lucas Álvarez; Melvin Laux; Arthur de Freitas Precht; Maurice Martin; Edoardo Caroselli; Frank Kirchner; Alexander Fabisch
In: Jakub Nalepa; Przemyslaw Biecek; Krzysztof Kotowski; Lukasz Tulczyjew; Marek Kraft; Nicolas Longepe; Evridiki V. Ntagiou; Agata M. Wijata (Hrsg.). Explainable AI in Space - Second International Workshop, EASi 2026, Held in Conjunction with the 35th International Joint Conference on Artificial Intelligence, IJCAI-ECAI 2026 - Proceedings. Joint Workshop on Explainable AI in Space and Explainable Artificial Intelligence for the Medical Domain (EASi-EXPLIMED-2026), located at IJCAI 2026, August 17, Bremen, Germany, Pages 124-144, Communications in Computer and Information Science (CCIS), Vol. 3107, ISBN 978-3-032-36805-8 / 978-3-032-36806-5, Springer Nature, Cham, Switzerland, 2027.

Abstract

This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction. A 1-D Convolutional Neural Network is trained to predict residual angular rate corrections from multi-sensor inputs, including gyroscope and star tracker measurements. The bias corrections are sent to a flight-representative Gyro-Stellar Estimator. The network produces both mean corrections and input-dependent (heteroscedastic) aleatoric uncertainty, while epistemic uncertainty is estimated via an ensemble of independently trained models.