Latent-KalmanNet: Learned Kalman filtering for tracking from high-dimensional signals

I Buchnik, G Revach, D Steger… - IEEE Transactions …, 2023‏ - ieeexplore.ieee.org
The Kalman filter (KF) is a widely used algorithm for tracking dynamic systems that are
captured by state space (SS) models. The need to fully describe an SS model limits its …

Neural extended Kalman filters for learning and predicting dynamics of structural systems

W Liu, Z Lai, K Bacsa, E Chatzi - Structural Health …, 2024‏ - journals.sagepub.com
Accurate structural response prediction forms a main driver for structural health monitoring
and control applications. This often requires the proposed model to adequately capture the …

Differentiable factor graph optimization for learning smoothers

B Yi, MA Lee, A Kloss, R Martín-Martín… - 2021 IEEE/RSJ …, 2021‏ - ieeexplore.ieee.org
A recent line of work has shown that end-to-end optimization of Bayesian filters can be used
to learn state estimators for systems whose underlying models are difficult to hand-design or …

AI-Aided Kalman Filters

N Shlezinger, G Revach, A Ghosh, S Chatterjee… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal
processing. These methods are used for state estimation of dynamic systems by relying on …

Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction via Self-Supervision

F Janjoš, M Keller, M Dolgov… - 2023 IEEE Intelligent …, 2023‏ - ieeexplore.ieee.org
Accurate vehicle trajectory prediction is an unsolved problem in autonomous driving with
various open research questions. State-of-the-art approaches regress trajectories either in a …

[HTML][HTML] Model-based Imitation Learning from Observation for input estimation in monitored systems

W Liu, Z Lai, CD Stoura, K Bacsa, E Chatzi - Mechanical Systems and …, 2025‏ - Elsevier
In the context of structural and industrial asset monitoring and twinning, the estimation of
unknown inputs–typically reflecting the loads acting onto a system–stands as a critical factor …

Nonlinear Kalman Estimators for Low-Cost Bioprocess Monitoring with Unstructured Mechanistic Models

C Freitas Iglesias Junior - 2024‏ - ruor.uottawa.ca
Bioprocess monitoring is a critical component in the biopharmaceutical industry, essential
for ensuring the consistent production of high-quality biopharmaceutical products. Despite …

Degradation Vector Fields with Uncertainty Considerations

M Star - 2023‏ - espace.curtin.edu.au
The focus of this work is on capturing uncertainty in remaining useful life (RUL) estimates for
machinery and constructing some latent dynamics that aid in interpreting those results. This …

Deep State Space Models for Remaining Useful Life Estimation

M Star, K Mckee - Available at SSRN 4864843‏ - papers.ssrn.com
Deep learning has been used to train neural networks to estimate the Remaining Useful Life
(RUL) of a machine given sensor signals from that machine. This has resulted in some …

[PDF][PDF] Model-based Unknown Input Estimation via Partially Observable Markov Decision Processes

W Liu, Z Lai, CD Stoura, K Bacsa, E Chatzi - 2022‏ - drive.google.com
In the context of condition monitoring for structures and industrial assets, the estimation of
unknown inputs, usually referring to acting loads, is of salient importance for guaranteeing …