Improved context-sensitive transformer model for inland vessel trajectory prediction
Kathrin Donandt, Karim Böttger, Dirk Söffker
TL;DR
The paper tackles inland vessel trajectory prediction under restricted navigable spaces by replacing separate spatial processing with river- and navigation-specific dislocation representations (R-CSCT and N-CSCT) integrated directly into a context-sensitive transformer. It introduces non-equidistance mitigation via waterway kilometerization and typical-route statistics, and adds Monte Carlo dropout to quantify epistemic uncertainty. Across Rhine and Danube datasets, the river- and navigation-aware CSCT variants achieve improved medium- and long-term accuracy and provide calibrated uncertainty estimates, aiding safety-critical decision-making without increasing model complexity. This approach enhances spatial awareness in DL-based VTP and offers practical benefits for collision avoidance and route planning in inland waterways.
Abstract
Physics-related and model-based vessel trajectory prediction is highly accurate but requires specific knowledge of the vessel under consideration which is not always practical. Machine learning-based trajectory prediction models do not require expert knowledge, but rely on the implicit knowledge extracted from massive amounts of data. Several deep learning (DL) methods for vessel trajectory prediction have recently been suggested. The DL models developed typically only process information about the (dis)location of vessels defined with respect to a global reference system. In the context of inland navigation, this can be problematic, since without knowledge of the limited navigable space, irrealistic trajectories are likely to be determined. If spatial constraintes are introduced, e.g., by implementing an additional submodule to process map data, however, overall complexity increases. Instead of processing the vessel displacement information on the one hand and the spatial information on the other hand, the paper proposes the merging of both information. Here, fairway-related and navigation-related displacement information are used directly. In this way, the previously proposed context-sensitive Classification Transformer (CSCT) shows an improved spatial awareness. Additionally, the CSCT is adapted to assess the model uncertainty by enabling dropout during inference. This approach is trained on different inland waterways to analyze its generalizability. As the improved CSCT obtains lower prediction errors and enables to estimate the trustworthiness of each prediction, it is more suitable for safety-critical applications in inland navigation than previously developed models.