# Robust Unscented Kalman Filtering via Recurrent Meta-Adaptation of Sigma-Point Weights

arXiv: https://arxiv.org/abs/2603.04360 · HTML: https://mlsanity.com/paper/2603.04360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Forward and Reverse Gradient-Based Hyperparameter Optimization](https://mlsanity.com/paper/1703.01785/) (2017)
- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors](https://mlsanity.com/paper/1805.11122/) (2018)
- [Backprop KF: Learning Discriminative Deterministic State Estimators](https://mlsanity.com/paper/1605.07148/) (2016)
- [End-To-End Semi-supervised Learning for Differentiable Particle Filters](https://mlsanity.com/paper/2011.05748/) (2020)
- [Weak in the NEES?: Auto-tuning Kalman Filters with Bayesian Optimization](https://mlsanity.com/paper/1807.08855/) (2018)
- [Accurate Vision-based Manipulation through Contact Reasoning](https://mlsanity.com/paper/1911.03112/) (2019)
- [Sigma-point Kalman Filter with Nonlinear Unknown Input Estimation via Optimization and Data-driven Approach for Dynamic Systems](https://mlsanity.com/paper/2306.12361/) (2023)

## Abstract (arXiv)

The Unscented Kalman Filter (UKF) is a ubiquitous tool for nonlinear state estimation; however, its performance is limited by the static parameterization of the Unscented Transform (UT). Conventional weighting schemes, governed by fixed scaling parameters, assume implicit Gaussianity and fail to adapt to time-varying dynamics or heavy-tailed measurement noise. This work introduces the Meta-Adaptive UKF (MA-UKF), a framework that reformulates sigma-point weight synthesis as a hyperparameter optimization problem addressed via memory-augmented meta-learning. Unlike standard adaptive filters that rely on instantaneous heuristic corrections, our approach employs a Recurrent Context Encoder to compress the history of measurement innovations into a compact latent embedding. This embedding informs a policy network that dynamically synthesizes the mean and covariance weights of the sigma points at each time step, effectively governing the filter's trust in the prediction versus the measurement. By optimizing the system end-to-end through the filter's recursive logic, the MA-UKF learns to maximize tracking accuracy while maintaining estimation consistency. Numerical benchmarks on maneuvering targets demonstrate that the MA-UKF significantly outperforms standard baselines, exhibiting superior robustness to non-Gaussian glint noise and effective generalization to out-of-distribution (OOD) dynamic regimes unseen during training.