SIA-Net: Scalable Interaction-Aware Network for Vehicle Trajectory Prediction Based on Self-Attention

Abstract

In order to navigate through different scenarios safely and efficiently, self-driving vehicles must predict future trajectories of other vehicles, which is a challenging task due to the implicit vehicle interactions in the driving scenario. Because there is no predefined number of surrounding vehicles, the model must be scalable to cope with scenarios of different vehicle numbers with high accuracy and low computation cost for jointly predicting future trajectories of all vehicles. However, previous methods mainly focus on predicting a single trajectory of the target vehicle, which makes them subject to accuracy and computation speed. In this paper, we propose SIA-Net that predicts future trajectories of all vehicles in the scenario independent of the vehicle number. SIA-Net learns the implicit interactions of all vehicles by self-attention social pooling and generates each trajectory through one forward propagation by attentional decoder. Experiments demonstrate the improvement of our model in prediction accuracy on the publicly available NGSIM and INTERACTION datasets while keeping the computation cost low. We also present qualitative analysis to study the mechanism of our model.