A Hybrid UKF–ST-Graph Transformer Framework for Cooperative Localization in Ship Ad-Hoc Networks

In sea environment the localization of ships is very important for traffic management. AutomaticIdentification System (AIS) dataset is widely used to get information of ship. This paper proposed ahybrid localization framework for Ship Ad hoc Networks (SANETs) using AIS dataset. This studyintegrates an Unscented Kalman Filter (UKF) with Spatio-Temporal Graph Transformer (ST-GT)built on SANETs to provide cooperative localization. First, UKF is utilized raw AIS data to getinitial position estimates for ship. Then, a SANETs based on spatial proximity is constructed to fromfeatures such as node degree and local connectivity. These features are used by the ST-GT model toobtain temporal motion patterns and inter-vessel interactions to enhance that initial position. Thesuggested framework outperforms the standalone UKF in experimental results on real AIS datasets.The localization errors under sparse and noisy environments is decreased by using this framework.The result shows the effectiveness of combining physical motion models with deep learning throughSANETs for enhance maritime localization.