arXiv Machine Learning August 6, 2026 By Minhyeok Ko, Abdollah Shafieezadeh

Unscented KalmanNet: a hybrid deep learning filter with calibrated posterior covariance for nonlinear state estimation

Read the original on arXiv Machine Learning →

arXiv:2608. 04201v1 Announce Type: new Abstract: State estimation for nonlinear dynamical systems is commonly performed with the Unscented Kalman filter (UKF), which propagates the state moments through deterministic sigma points and reports a posterior covariance at every step.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

6d ago

Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise

arXiv:2608. 04201v2 Announce Type: replace Abstract: Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements.

By Minhyeok Ko, Abdollah Shafieezadeh

safety

arXiv Machine Learning

Jun 3

Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification

arXiv:2606. 02767v1 Announce Type: cross Abstract: Kalman filtering performance is highly sensitive to model mismatch and noise covariance tuning.

By Jiho Lee, Nisar R. Ahmed, Rebecca Russell

arXiv Machine Learning

Jul 28

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

arXiv:2607. 24608v1 Announce Type: new Abstract: This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction.

By Mariela De Lucas \'Alvarez, Melvin Laux, Arthur de Freitas Precht, Maurice Martin, Edoardo Caroselli, Frank Kirchner, Alexander Fabisch

safety

arXiv Machine Learning

Jun 26

Learning Probabilistic Filters with Strictly Proper Scoring Rules

arXiv:2606. 26497v1 Announce Type: new Abstract: Bayesian filtering of partially and noisily observed dynamical systems seeks to infer the evolving conditional distribution of the state of a dynamical system, given observations, in an online fashion.

By Eviatar Bach, Ricardo Baptista, Jochen Br\"ocker, Bohan Chen, Andrew Stuart

llms multimodal safety

arXiv Machine Learning

Jul 8

Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba

arXiv:2607. 05669v1 Announce Type: cross Abstract: Reliable localization in GNSS-denied environments remains a fundamental challenge for intelligent vehicles, as inertial navigation systems accumulate unbounded drift without external correction.

By Abinav Kalyanasundaram, Karthikeyan Chandra Sekaran, Wolfgang Utschick, Michael Botsch

arXiv AI

Jun 2

FW-NKF: Frequency-Weighted Neural Kalman Filters

arXiv:2606. 02251v1 Announce Type: cross Abstract: Robust state estimation is central to robotic autonomy, yet classical Kalman filters struggle with frequency-dependent disturbances and model mismatch such as sensor vibrations, electromagnetic interference, and periodic noise.

By Adnan Harun Dogan, Berken Utku Demirel, Christian Holz

computer-vision robotics benchmarks

Related stories

Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise

Hybrid Adaptive Kalman Filtering for Data-Efficient Joint Tracking and Classification

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

Learning Probabilistic Filters with Strictly Proper Scoring Rules

Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba

FW-NKF: Frequency-Weighted Neural Kalman Filters