DM-BDD: Real-time Vessel Trajectory Prediction Based on Diffusion Probability Model Balancing Diversity and Determinacy

Accurate ship trajectory prediction is crucial to ensure the safety and interaction efficiency of maritime traffic, especially in areas with dense ships and areas with intersecting waterways. Different from the certainty of short-term trajectory prediction, for long-term trajectory prediction, the uncertainty of direction and speed changes in operation is amplified, and the prediction of ship trajectory is more difficult. To solve this problem, we propose A framework based on a diffusion probability model balancing diversity and determinacy (DM-BDD). Inspired by the denoising process in the diffusion model, we gradually reduce the range of trajectories that the ships are navigable, and finally achieve a desired and deterministic trajectory. This process is learned using a parameterized Markov chain based on the currently observed trajectory. The length of the chain is adjusted to control the degree of uncertainty of the running trajectory and the final position, and to balance the diversity and certainty of the prediction results. We design an architecture consisting of a temporal-social encoding network and an LSTM-based decoder network to achieve the purpose of capturing the spatial dependence and social dependence of trajectories. We test and compare on the AIS dataset of the real Weihai Port and the Nantong waterway of the Yangtze River estuary. The experimental results show that the short, medium and long-term prediction results of the proposed model on the two data sets achieve the best performance in the field of ship trajectory prediction.