GHNet:Learning GNSS Heading from Velocity Measurements

TL;DR

GHNet is a deep-learning framework designed to accurately estimate the heading angle of land vehicles at low speeds using GNSS velocity data, outperforming traditional model-based methods in simulations and real-world tests.

Contribution

The paper introduces GHNet, a novel deep-learning approach that improves low-speed GNSS heading estimation beyond existing model-based techniques.

Findings

GHNet achieves higher accuracy than traditional methods.

The approach performs well in both simulation and real-world experiments.

GHNet effectively reduces heading angle drift at low speeds.

Abstract

By utilizing global navigation satellite system (GNSS) position and velocity measurements, the fusion between the GNSS and the inertial navigation system provides accurate and robust navigation information. When considering land vehicles,like autonomous ground vehicles,off-road vehicles or mobile robots,a GNSS-based heading angle measurement can be obtained and used in parallel to the position measurement to bound the heading angle drift. Yet, at low vehicle speeds (less than 2m/s) such a model-based heading measurement fails to provide satisfactory performance. This paper proposes GHNet, a deep-learning framework capable of accurately regressing the heading angle for vehicles operating at low speeds. We demonstrate that GHNet outperforms the current model-based approach for simulation and experimental datasets.