This paper introduces a deep transformer network for estimating the relative six-dimensional (6D) pose of an unmanned aerial vehicle (UAV) with respect to a ship using monocular images. A synthetic data set of ship images is created and annotated with two-dimensional keypoints of multiple ship parts. A transformer neural network model is trained to detect these keypoints and estimate the 6D pose of each part. The estimates are integrated using Bayesian fusion. The model is tested on synthetic data and in situ flight experiments, demonstrating robustness and accuracy in various lighting conditions. The position estimation error is approximately 0.8 and 1.0% of the distance to the ship for the synthetic data and the flight experiments, respectively. The method has potential applications for ship-based autonomous UAV landing and navigation.
Deep Transformer Network for Monocular Pose Estimation of Shipborne Unmanned Aerial Vehicle
Journal of Guidance, Control, and Dynamics ; 48 , 8 ; 1915-1930
01.08.2025
Aufsatz (Konferenz) , Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Unmanned aerial vehicle shipborne portable ground station system
Europäisches Patentamt | 2024
|Telescopic rotating shipborne unmanned aerial vehicle pelvic fin
Europäisches Patentamt | 2023
|Shipborne unmanned aerial vehicle undercarriage and adjusting method thereof
Europäisches Patentamt | 2022
|Unmanned sampling, throwing and clamping equipment based on shipborne unmanned aerial vehicle
Europäisches Patentamt | 2024
|