Human Trajectory Prediction Using Stacked Temporal Convolutional Network

Abstract

Human trajectory prediction is essential for avoiding collisions in crowded environments in the navigation of autonomous driving system. In the past few years, human trajectory prediction based on deep learning methods has been extensively studied and significant progress has been made. However, both the social interactions among pedestrians and the intention of the pedestrians are unpredictable. They cause great difficulty in forecasting the future paths. Previous methods use recurrent architectures which will produce lots of inefficient parameters in training process and lead to the low accuracy. In this paper, we propose a novel method to predict human trajectory by using stacked temporal convolutional network. First, we use a kernel function to embed the social interactions among pedestrians with the adjacency matrix. Next, we represent a spatial temporal representation of all pedestrian in the scene. Then, we conduct a spatial temporal embedding for observed trajectories. Finally, the stacked temporal convolutional network receives the features extracted by spatial temporal network and predicts the future human trajectories. The proposed approach is a data-driven approach which combines the advantages of spatial temporal graph convolutional network and stacked temporal convolutional network. Experimental results on two public datasets demonstrate that our stacked temporal method has high data efficiency and outperforms the existing methods.