A dual linear autoencoder approach for vessel trajectory prediction using historical AIS data. (1st August 2020)

• Record Type: Journal Article
• Authors: Murray, Brian; Perera, Lokukaluge Prasad
• Is Part Of: Ocean engineering. Volume 209(2020)
• Publication Date: 2020-08-01
• Subjects: Maritime situation awareness -- Trajectory prediction -- Collision avoidance -- Machine learning -- Autoencoder -- AIS; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2020.107478
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: Advances in artificial intelligence are driving the development of intelligent transportation systems, with the purpose of enhancing the safety and efficiency of such systems. One of the most important aspects of maritime safety is effective collision avoidance. In this study, a novel dual linear autoencoder approach is suggested to predict the future trajectory of a selected vessel. Such predictions can serve as a decision support tool to evaluate the future risk of ship collisions. Inspired by generative models, the method suggests to predict the future trajectory of a vessel based on historical AIS data. Using unsupervised learning to facilitate trajectory clustering and classification, the method utilizes a cluster of historical AIS trajectories to predict the trajectory of a selected vessel. Similar methods predict future states iteratively, where states are dependent upon the prior predictions. The method in this study, however, suggests predicting an entire trajectory, where all states are predicted jointly. Further, the method estimates a latent distribution of the possible future trajectories of the selected vessel. By sampling from this distribution, multiple trajectories are predicted. The uncertainties of the predicted vessel positions are also quantified in this study. Highlights: This study applies machine learning techniques to historical AIS data. A dual linear autoencoder approach is introduced, inspired by deep generative models. The approach predicts the future trajectory of a vessel, to aid in collision avoidance. A procedure to evaluate the uncertainty of the trajectory prediction is also presented. The approach is evaluated using test cases from the region of Tromsø, Norway.