FlexKalmanNet: A Modular AI-Enhanced Kalman Filter Framework Applied to Spacecraft Motion Estimation

TL;DR

FlexKalmanNet is a modular AI-enhanced Kalman filter framework that learns filter parameters directly from measurement data, improving spacecraft motion estimation accuracy without extensive manual tuning.

Contribution

It introduces a novel modular framework that integrates neural networks with Kalman filters, enabling automatic learning of filter parameters from data and supporting various Kalman filter variants.

Findings

Rapid training convergence demonstrated.

High accuracy in spacecraft pose estimation.

Outperforms manually tuned Extended Kalman filters.

Abstract

The estimation of relative motion between spacecraft increasingly relies on feature-matching computer vision, which feeds data into a recursive filtering algorithm. Kalman filters, although efficient in noise compensation, demand extensive tuning of system and noise models. This paper introduces FlexKalmanNet, a novel modular framework that bridges this gap by integrating a deep fully connected neural network with Kalman filter-based motion estimation algorithms. FlexKalmanNet's core innovation is its ability to learn any Kalman filter parameter directly from measurement data, coupled with the flexibility to utilize various Kalman filter variants. This is achieved through a notable design decision to outsource the sequential computation from the neural network to the Kalman filter variant, enabling a purely feedforward neural network architecture. This architecture, proficient at handling complex, nonlinear features without the dependency on recurrent network modules, captures global data patterns more effectively. Empirical evaluation using data from NASA's Astrobee simulation environment focuses on learning unknown parameters of an Extended Kalman filter for spacecraft pose and twist estimation. The results demonstrate FlexKalmanNet's rapid training convergence, high accuracy, and superior performance against manually tuned Extended Kalman filters.