A Hybrid Long Short-Term Memory and Kalman Filter Model for Train Trajectory Prediction

Trajectory prediction of the train ahead is vital for deciding the minimum safe distance for train separation. An important research challenge, in this regard, is how to effectively and accurately estimate the trajectory of the train ahead using spatiotemporal approaches with train operating data. In this paper, we present a novel hybrid model for predicting train trajectories by integrating Long Short-Term Memory (LSTM) and Kalman Filter (KF). In the proposed hybrid LSTM-KF model, the LSTM model is used to analyze time series data and discover the long-term dependencies of train trajectory data, which can be assumed as observation data for the KF model. The KF model can combine train dynamics mechanism to extract local features of train operation data, so as to smooth the train trajectory predicted by LSTM model. A novel on-the-fly algorithm is devised for efficient realization of the proposed LSTM-KF model. Experiments are carried out using the train data collected from Chengdu Metro Line 8. The results indicate that our hybrid LSTM-KF model has greatly improved the accuracy of long-term train trajectory prediction.

I. Introduction

With the development of urbanization, new challenges have been posed to the development of urban rail transit capacity. Continuing to build a large number of new rail lines to alleviate congestion is a costly and slow-return approach. Moreover, the existing Communication-Based Train Control (CBTC) systems have already reached their capacity enhancement limits. The railway industry is therefore investigating application of advance technologies for unconventional solutions in mass-transit railway operations.