Survey of pedestrian trajectory prediction methods based on deep learning

In order to plan a reasonable path to avoid pedestrians, the research on pedestrian trajectory prediction has a wide range of application value. Traditional methods based on manual features are difficult to predict pedestrian trajectory in complex scenes. Deep learning is based on artificial neural networks, which has strong learning ability and has achieved remarkable results in various fields. The pedestrian trajectory prediction method based on deep learning has gradually developed into a trend. In order to grasp the research status of pedestrian trajectory prediction based on deep learning, firstly, different methods are organized and classified, their advantages and disadvantages are compared, and the application and development of these methods in the field of pedestrian trajectory prediction are discussed. Then, according to the design differences of pedestrian trajectory prediction models, effects of different algorithms on the model performance are compared. Finally, in view of existing problems in pedestrian trajectory prediction, the future development of pedestrian trajectory prediction method based on deep learning is prospected. © 2021, Editorial Office of Control and Decision. All right reserved.