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

TL;DR

This paper introduces the Meta-Adaptive UKF, a novel approach that uses meta-learning and recurrent encoding to dynamically optimize sigma-point weights, improving robustness and accuracy in nonlinear state estimation under challenging noise conditions.

Contribution

It presents a new meta-learning framework for adaptive sigma-point weight synthesis in UKF, enabling dynamic adjustment based on historical measurement data.

Findings

Outperforms standard UKF in maneuvering target tracking

Demonstrates robustness to non-Gaussian noise

Generalizes well to unseen dynamic regimes

Abstract

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.