AUTHOR=Zhao Licheng , Zuo Yi , Zhang Wenjun , Li Tieshan , Chen C. L. Philip 

TITLE=End-to-end model-based trajectory prediction for ro-ro ship route using dual-attention mechanism

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2024.1358437

DOI=10.3389/fncom.2024.1358437

ISSN=1662-5188

ABSTRACT=With rapidly increasing of economic globalization, the significant expansion of shipping volume has resulted in shipping routes congestion, causing the necessity of trajectory prediction for effective service and efficient management. With AIS data as the basis, most of trajectory prediction can achieve high accuracy. However trajectory prediction can achieved relatively high level of accuracy, the performance and generalization of prediction models remain critical bottlenecks. Therefore, this paper proposes a dual-attention (DA) based end-to-end (E2E) neural network (DAE2ENet) for trajectory prediction. In E2E structure, long short-term memory (LSTM) units are included for the task of pursuing sequential trajectory data from encoder layer to decoder layer. In DA mechanisms, global attention is introduced between the encoder and decoder layers to facilitate interactions between input and output trajectory sequences, and multi-head self-attention is utilized to extract sequential features from the input trajectory. In experiments, we use ro-ro ship with fixed navigation route as cased study. To be compared with baseline models and benchmark neural networks, DAE2ENet can obtain higher performance on trajectory prediction, and better validation of environmental factors on ship navigation.