A Hybrid Neural-Assisted Unscented Kalman Filter for Unmanned Ground Vehicle Navigation

TL;DR

This paper introduces a hybrid neural-assisted unscented Kalman filter that improves UGV navigation by predicting noise uncertainties with deep learning, trained solely on simulated data, and tested across diverse real-world scenarios.

Contribution

It presents a novel hybrid framework combining classical Kalman filtering with deep neural networks to adapt noise covariance estimates based on raw sensor data.

Findings

Achieved 12.7% position accuracy improvement over traditional adaptive methods.

Demonstrated robustness and generalization across different vehicle types and environmental conditions.

Validated the approach with a 160-minute real-world dataset from three different vehicle platforms.

Abstract

Modern autonomous navigation for unmanned ground vehicles relies on different estimators to fuse inertial sensors and GNSS measurements. However, the constant noise covariance matrices often struggle to account for dynamic real-world conditions. In this work we propose a hybrid estimation framework that bridges classical state estimation foundations with modern deep learning approaches. Instead of altering the fundamental unscented Kalman filter equations, a dedicated deep neural network is developed to predict the process and measurement noise uncertainty directly from raw inertial and GNSS measurements. We present a sim2real approach, with training performed only on simulative data. In this manner, we offer perfect ground truth data and relieves the burden of extensive data recordings. To evaluate our proposed approach and examine its generalization capabilities, we employed a 160-minutes test set from three datasets each with different types of vehicles (off-road vehicle, passenger car, and mobile robot), inertial sensors, road surface, and environmental conditions. We demonstrate across the three datasets a position improvement of $12.7\%$ compared to the adaptive model-based approach. Thus, offering a scalable and a more robust solution for unmanned ground vehicles navigation tasks.