Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments

TL;DR

This paper introduces BNKF, a hybrid neural Kalman filter that combines Bayesian neural networks with traditional Kalman filtering to improve UAV state estimation under noisy and sparse sensor data.

Contribution

The paper presents BNKF, a novel hybrid framework integrating Bayesian neural networks with Kalman filtering, enhancing robustness and uncertainty quantification in UAV state estimation.

Findings

BNKF outperforms Extended and Unscented Kalman Filters in accuracy and precision.

BNKFe, an ensemble variant, further improves precision in high-noise scenarios.

BNKF maintains real-time performance with minimal inference overhead.

Abstract

Accurate state estimation of nonlinear dynamical systems is fundamental to modern aerospace operations across air, sea, and space domains. Online tracking of adversarial unmanned aerial vehicles (UAVs) is especially challenging due to agile nonlinear motion, noisy and sparse sensor measurements, and unknown control inputs; conditions that violate key assumptions of classical Kalman filter variants and degrade estimation performance. Neural networks (NNs) can learn complex nonlinear relationships from data, but lack principled uncertainty quantification, which is critical for state estimation tasks where confidence bounds drive downstream decisions. We address this with Bayesian Neural Networks (BNNs), which model uncertainty through distributions over network weights and produce predictive means and uncertainties via Monte Carlo sampling. Building on this, we propose the Bayesian Neural Kalman Filter (BNKF): a hybrid framework coupling a trained BNN with a Kalman correction step for robust online UAV state estimation. Unlike related neural Kalman approaches, BNKF produces full state predictions and incorporates Bayesian uncertainty directly into covariance propagation, improving robustness under high noise conditions. We evaluate BNKF under varying radar noise levels and sampling rates using synthetic nonlinear UAV flight data. Five fold cross validation demonstrates that BNKF outperforms Extended and Unscented Kalman Filters in accuracy, precision, and truth containment under degraded sensing. An ensemble variant (BNKFe) further improves precision in high-noise edge cases at a slight accuracy tradeoff. Runtime analysis confirms minimal inference overhead, supporting real-time deployment feasibility.