UB-LSTM: A Trajectory Prediction Method Combined with Vehicle Behavior Recognition

• Main Authors: Haipeng Xiao, Chaoqun Wang, Zhixiong Li, Rendong Wang, Cao Bo, Miguel Angel Sotelo, Youchun Xu
• Format: Article
• Language: English
• Published: Hindawi-Wiley 2020-01-01
• Series: Journal of Advanced Transportation
• Online Access: http://dx.doi.org/10.1155/2020/8859689

In order to make an accurate prediction of vehicle trajectory in a dynamic environment, a Unidirectional and Bidirectional LSTM (UB-LSTM) vehicle trajectory prediction model combined with behavior recognition is proposed, and then an acceleration trajectory optimization algorithm is proposed. Firstly, the interactive information with the surrounding vehicles is obtained by calculation, then the vehicle behavior recognition model is established by using LSTM, and the vehicle information is input into the behavior recognition model to identify vehicle behavior. Then, the trajectory prediction model is established based on Unidirectional and Bidirectional LSTM, and the identified vehicle behavior and the input information of the behavior recognition model are input into the trajectory prediction model to predict the horizontal and vertical speed and coordinates of the vehicle in the next 3 seconds. Experiments are carried out with NGSIM data sets, and the experimental results show that the mean square error (MSE) between the predicted trajectory and the actual trajectory obtained by this method is 0.124, which is 97.2% lower than that of the method that does not consider vehicle behavior and directly predicts the trajectory. The test loss is 0.000497, which is 95.68% lower than that without considering vehicle behavior. The predicted trajectory is obviously optimized, closer to the actual trajectory, and the performance is more stable.