@inproceedings{8c89396bbd444bde9b5e0a2394bab178,
title = "Self-Supervised Neural Networks for Model-Free State Estimation",
abstract = "This paper introduces SsnNet-KF, a novel selfsupervised neural network-based Kalman filter designed for highprecision state estimation of aircraft operating in complex, nonlinear environments with significant time-varying noise. Unlike conventional filtering approaches that rely on explicit system models or ground-truth state labels, SsnNet-KF leverages Long Short-Term Memory (LSTM) units to directly learn the optimal Kalman gain. This eliminates the dependency on detailed system dynamics and allows for adaptive noise covariance estimation. Extensive simulations on aerospace vehicle state estimation demonstrate that SsnNet-KF significantly outperforms traditional Kalman filter variants and existing data-driven methods in terms of accuracy, robustness, and adaptability to strong disturbances and unknown time-varying noise profiles. Our approach provides a robust, model-free solution for real-time state estimation in challenging dynamic systems.",
keywords = "Adaptive filtering, Kalman filters, Nonlinear systems, Self-supervised learningLong shortterm memory networks, State estimation",
author = "Yangxin Liu and Yiheng Li and Qunli Xia and Puyang Qi",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 5th International Conference on Mechatronics Technology and Aerospace Engineering, ICMTAE 2025 ; Conference date: 26-09-2025 Through 28-09-2025",
year = "2025",
doi = "10.1109/ICMTAE66890.2025.11428060",
language = "English",
series = "2025 5th International Conference on Mechatronics Technology and Aerospace Engineering, ICMTAE 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "91--98",
booktitle = "2025 5th International Conference on Mechatronics Technology and Aerospace Engineering, ICMTAE 2025",
address = "United States",
}