Research into Ship Trajectory Prediction Based on An Improved LSTM Network

Abstract

The establishment of ship trajectory prediction is critical in analyzing trajectory data. It serves as a critical reference point for identifying abnormal behavior and potential collision risks for ships. Accurate and real-time ship trajectory prediction is essential during navigation. Since the timing of automatic identification system (AIS) data is irregular, traditional methods usually use time calibration to simulate the data of uniform sequencing before analysis. Inevitably, this increases the chances of error and time delays. To address this issue, we propose a time-aware LSTM (T-LSTM) single-ship trajectory model combined with the generative adversarial network (GAN) to predict multiple ship trajectories. These analysis methods are capable of directly analyzing AIS data and have demonstrated better performance in both single-ship and multi-ship trajectories. Our experimental results show that the proposed method achieves high accuracy and can meet the practical navigation requirements of ships.

L2-SSA-LSTM Prediction Model of Steering Drilling Wellbore Trajectory

“…Y. Wang presented a novel off-road multi-agent trajectory prediction framework called SA-LSTM for predicting autonomous off-road vehicle trajectories [14]. J. Zhang et al proposed a time-aware LSTM single-ship trajectory model in combination with a Generative Adversarial Network (GAN) to predict the trajectories of multiple ships [15]. To accurately predict high-precision cutter head torque (CHT), Yi Qin et al proposed a new embedded long short-term memory (ELSTM) network with a dual memory structure [16].…”